From 55aebeb926b6f93a540328e7ac770ef536b09b77 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 10 Nov 2014 14:45:30 +0200 Subject: iio: core: Introduce IIO_ACTIVITY channel This channel will be used for exposing information about activity composite sensors. Activities supported so far: * running * jogging * walking * still THRESHOLD event is used to signal a change in the activity state. We associate a confidence interval for each activity expressed as a percentage from 0 to 100. * 0, means the sensor IS NOT reporting that activity. * 100, means the sensor IS reporting that activity. Users of this interface have two possible means to gather information about the ongoing activities. 1. Event based, via event file descriptor * sensor may report an event when ENTERING an activity or LEAVING an activity based on a threshold value. * drivers will wake up applications waiting data on the event fd 2. Polling, by reading the sysfs associated attribute files: * /sys/bus/iio/devices/iio:device0/in_activity_running_input expressed as percentage confidence value from 0 to 100. This will offer an interface for Android significant motion composite sensor defined here: http://source.android.com/devices/sensors/composite_sensors.html Activities listed above are supported by Freescale's MMA9553 sensor: http://freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf Signed-off-by: Irina Tirdea Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 4a2af8adf874..b3a241d53b54 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -30,6 +30,7 @@ enum iio_chan_type { IIO_CCT, IIO_PRESSURE, IIO_HUMIDITYRELATIVE, + IIO_ACTIVITY, }; enum iio_modifier { @@ -59,7 +60,11 @@ enum iio_modifier { IIO_MOD_NORTH_MAGN, IIO_MOD_NORTH_TRUE, IIO_MOD_NORTH_MAGN_TILT_COMP, - IIO_MOD_NORTH_TRUE_TILT_COMP + IIO_MOD_NORTH_TRUE_TILT_COMP, + IIO_MOD_RUNNING, + IIO_MOD_JOGGING, + IIO_MOD_WALKING, + IIO_MOD_STILL, }; enum iio_event_type { -- cgit v1.2.3 From 1843c2f3def16740eb6d129a9790c32dd21aa5ea Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Mon, 10 Nov 2014 14:45:31 +0200 Subject: iio: core: Introduce IIO_EV_DIR_NONE For some events (e.g.: step detector) a direction does not make sense. Add IIO_EV_DIR_NONE to be used with such events and generate sysfs event attributes that do not contain direction. Signed-off-by: Irina Tirdea Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index b3a241d53b54..52cb5329407b 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -86,6 +86,7 @@ enum iio_event_direction { IIO_EV_DIR_EITHER, IIO_EV_DIR_RISING, IIO_EV_DIR_FALLING, + IIO_EV_DIR_NONE, }; #define IIO_VAL_INT 1 -- cgit v1.2.3 From a88bfe78583026eb9f21d4014ba481b22b66cee3 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Mon, 10 Nov 2014 14:45:32 +0200 Subject: iio: core: Introduce STEPS channel, ENABLE mask and INSTANCE event These changes are needed to support the functionality of a pedometer. A pedometer has two basic functionalities: step counter and step detector. The step counter needs to be enabled and then it will count the steps in its hardware register. Whenever the application needs to check the step count, it will read the step counter register. To support the step counter a new channel type STEPS is added. Since the pedometer needs to be enabled first so that the hardware can count and store the steps, we need a specific ENABLE channel info mask. The step detector will generate an interrupt each time a step is detected. To support this functionality we add a new event type INSTANCE. For more information on the Android requirements for step counter and step detector see: http://source.android.com/devices/sensors/composite_sensors.html#counter and http://source.android.com/devices/sensors/composite_sensors.html#detector. A device that has the pedometer functionality this interface needs to support is Freescale's MMA9553L: http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf Signed-off-by: Irina Tirdea Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 1 + include/linux/iio/types.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 3642ce7ef512..f45a400a5e3e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -38,6 +38,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_HARDWAREGAIN, IIO_CHAN_INFO_HYSTERESIS, IIO_CHAN_INFO_INT_TIME, + IIO_CHAN_INFO_ENABLE, }; enum iio_shared_by { diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 52cb5329407b..904dcbbf0e6f 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -31,6 +31,7 @@ enum iio_chan_type { IIO_PRESSURE, IIO_HUMIDITYRELATIVE, IIO_ACTIVITY, + IIO_STEPS, }; enum iio_modifier { @@ -73,6 +74,7 @@ enum iio_event_type { IIO_EV_TYPE_ROC, IIO_EV_TYPE_THRESH_ADAPTIVE, IIO_EV_TYPE_MAG_ADAPTIVE, + IIO_EV_TYPE_INSTANCE, }; enum iio_event_info { -- cgit v1.2.3 From bcdf28fb1b8badf3cdba18d349f6251057e36a45 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Mon, 10 Nov 2014 14:45:33 +0200 Subject: iio: core: Introduce IIO_CHAN_INFO_CALIBHEIGHT Some devices need the height of the user to compute various parameters. One of this devices is Freescale's MMA9553L (http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf) that needs the height of the user to compute the stride length which is used further to determine distance, speed and activity type. Signed-off-by: Irina Tirdea Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index f45a400a5e3e..878d861b0610 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -39,6 +39,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_HYSTERESIS, IIO_CHAN_INFO_INT_TIME, IIO_CHAN_INFO_ENABLE, + IIO_CHAN_INFO_CALIBHEIGHT, }; enum iio_shared_by { -- cgit v1.2.3 From 0461a4149836c792d186027c8c859637a4cfb11a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 9 Dec 2014 21:38:05 +0000 Subject: spi: Pump transfers inside calling context for spi_sync() If we are using the standard SPI message pump (which all drivers should be transitioning over to) then special case the message enqueue and instead of starting the worker thread to push messages to the hardware do so in the context of the caller if the controller is idle. This avoids a context switch in the common case where the controller has a single user in a single thread, for short PIO transfers there may be no need to context switch away from the calling context to complete the transfer. The code is a bit more complex than is desirable in part due to the need to handle drivers not using the standard queue and in part due to handling the various combinations of bus locking and asynchronous submission in interrupt context. It is still suboptimal since it will still wake the message pump for each transfer in order to schedule idling of the hardware and if multiple contexts are using the controller simultaneously a caller may end up pumping a message for some random other thread rather than for itself, and if the thread ends up deferring due to another context idling the hardware then it will just busy wait. It can, however, have the benefit of aggregating power up and down of the hardware when a caller performs a series of transfers back to back without any need for the use of spi_async(). Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a6ef2a8e6de4..4e6db75e9469 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -260,6 +260,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @pump_messages: work struct for scheduling work to the message pump * @queue_lock: spinlock to syncronise access to message queue * @queue: message queue + * @idling: the device is entering idle state * @cur_msg: the currently in-flight message * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message @@ -425,6 +426,7 @@ struct spi_master { spinlock_t queue_lock; struct list_head queue; struct spi_message *cur_msg; + bool idling; bool busy; bool running; bool rt; -- cgit v1.2.3 From f9380e7123863a4cb0627d940533be954a0a15df Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Thu, 27 Nov 2014 01:42:45 +0300 Subject: iio: inkern: add iio_write_channel_raw Introduce API for easy in-kernel setting of DAC values. Signed-off-by: Dmitry Eremin-Solenikov Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 651f9a0e2765..6f64624f329b 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -150,6 +150,16 @@ int iio_read_channel_average_raw(struct iio_channel *chan, int *val); */ int iio_read_channel_processed(struct iio_channel *chan, int *val); +/** + * iio_write_channel_raw() - write to a given channel + * @chan: The channel being queried. + * @val: Value being written. + * + * Note raw writes to iio channels are in dac counts and hence + * scale will need to be applied if standard units required. + */ +int iio_write_channel_raw(struct iio_channel *chan, int val); + /** * iio_get_channel_type() - get the type of a channel * @channel: The channel being queried. -- cgit v1.2.3 From 217a5cf0a1100264ced523e437e2e22c442dca7c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 26 Nov 2014 18:55:09 +0100 Subject: iio: Unexport iio_scan_mask_set() Individual drivers should not be messing with the scan mask that contains the list of enabled channels. This is something that is supposed to be managed by the core. Now that the last few drivers that used it to configure a default scan mask have been updated to not do this anymore we can unexport the function. Note, this patch also requires moving a few functions around so they are all declared before the first internal user. Signed-off-by: Lars-Peter Clausen Reviewed-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 519392763393..8c8ce611949c 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -116,15 +116,6 @@ void iio_buffer_init(struct iio_buffer *buffer); int iio_scan_mask_query(struct iio_dev *indio_dev, struct iio_buffer *buffer, int bit); -/** - * iio_scan_mask_set() - set particular bit in the scan mask - * @indio_dev IIO device structure - * @buffer: the buffer whose scan mask we are interested in - * @bit: the bit to be set. - **/ -int iio_scan_mask_set(struct iio_dev *indio_dev, - struct iio_buffer *buffer, int bit); - /** * iio_push_to_buffers() - push to a registered buffer. * @indio_dev: iio_dev structure for device. -- cgit v1.2.3 From 3e1b6c95b990c93f4aa3b17e9f66221e2fa44bee Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 26 Nov 2014 18:55:12 +0100 Subject: iio: Move buffer registration to the core Originally device and buffer registration were kept as separate operations in IIO to allow to register two distinct sets of channels for buffered and non-buffered operations. This has since already been further restricted and the channel set registered for the buffer needs to be a subset of the channel set registered for the device. Additionally the possibility to not have a raw (or processed) attribute for a channel which was registered for the device was added a while ago. This means it is possible to not register any device level attributes for a channel even if it is registered for the device. Also if a channel's scan_index is set to -1 and the channel is registered for the buffer it is ignored. So in summary it means it is possible to register the same channel array for both the device and the buffer yet still end up with distinctive sets of channels for both of them. This makes the argument for having to have to manually register the channels for both the device and the buffer invalid. Considering that the vast majority of all drivers want to register the same set of channels for both the buffer and the device it makes sense to move the buffer registration into the core to avoid some boiler-plate code in the device driver setup path. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 8c8ce611949c..b0e006c3db43 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -150,22 +150,6 @@ static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, int iio_update_demux(struct iio_dev *indio_dev); -/** - * iio_buffer_register() - register the buffer with IIO core - * @indio_dev: device with the buffer to be registered - * @channels: the channel descriptions used to construct buffer - * @num_channels: the number of channels - **/ -int iio_buffer_register(struct iio_dev *indio_dev, - const struct iio_chan_spec *channels, - int num_channels); - -/** - * iio_buffer_unregister() - unregister the buffer from IIO core - * @indio_dev: the device with the buffer to be unregistered - **/ -void iio_buffer_unregister(struct iio_dev *indio_dev); - /** * iio_buffer_read_length() - attr func to get number of datums in the buffer **/ @@ -223,16 +207,6 @@ static inline void iio_device_attach_buffer(struct iio_dev *indio_dev, #else /* CONFIG_IIO_BUFFER */ -static inline int iio_buffer_register(struct iio_dev *indio_dev, - const struct iio_chan_spec *channels, - int num_channels) -{ - return 0; -} - -static inline void iio_buffer_unregister(struct iio_dev *indio_dev) -{} - static inline void iio_buffer_get(struct iio_buffer *buffer) {} static inline void iio_buffer_put(struct iio_buffer *buffer) {} -- cgit v1.2.3 From 616dde2a1ea3df9398b1fcc7d6d6516c5fab6183 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 26 Nov 2014 18:55:13 +0100 Subject: iio: Remove get_bytes_per_datum() from iio_buffer_access_funcs There haven't been any users of the get_bytes_per_datum() callback for a while. The core assumes that the number of bytes per datum can be calculated based on the enabled channels and the storage size of the channel and iio_compute_scan_bytes() is used to compute this number. So remove the callback. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index b0e006c3db43..79cdb3d1b1bc 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -25,7 +25,6 @@ struct iio_buffer; * available. * @request_update: if a parameter change has been marked, update underlying * storage. - * @get_bytes_per_datum:get current bytes per datum * @set_bytes_per_datum:set number of bytes per datum * @get_length: get number of datums in buffer * @set_length: set number of datums in buffer @@ -49,7 +48,6 @@ struct iio_buffer_access_funcs { int (*request_update)(struct iio_buffer *buffer); - int (*get_bytes_per_datum)(struct iio_buffer *buffer); int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); int (*get_length)(struct iio_buffer *buffer); int (*set_length)(struct iio_buffer *buffer, int length); -- cgit v1.2.3 From 08e7e0adaa17205f86894157d86c4bee3c714330 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 26 Nov 2014 18:55:15 +0100 Subject: iio: buffer: Allocate standard attributes in the core All buffers want at least the length and the enable attribute. Move the creation of those attributes to the core instead of having to do this in each individual buffer implementation. This allows us to get rid of some boiler-plate code. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer.h | 37 ++----------------------------------- 1 file changed, 2 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 79cdb3d1b1bc..16b7663036f2 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -83,10 +83,11 @@ struct iio_buffer { bool scan_timestamp; const struct iio_buffer_access_funcs *access; struct list_head scan_el_dev_attr_list; + struct attribute_group buffer_group; struct attribute_group scan_el_group; wait_queue_head_t pollq; bool stufftoread; - const struct attribute_group *attrs; + const struct attribute **attrs; struct list_head demux_list; void *demux_bounce; struct list_head buffer_list; @@ -148,40 +149,6 @@ static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, int iio_update_demux(struct iio_dev *indio_dev); -/** - * iio_buffer_read_length() - attr func to get number of datums in the buffer - **/ -ssize_t iio_buffer_read_length(struct device *dev, - struct device_attribute *attr, - char *buf); -/** - * iio_buffer_write_length() - attr func to set number of datums in the buffer - **/ -ssize_t iio_buffer_write_length(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len); -/** - * iio_buffer_store_enable() - attr to turn the buffer on - **/ -ssize_t iio_buffer_store_enable(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len); -/** - * iio_buffer_show_enable() - attr to see if the buffer is on - **/ -ssize_t iio_buffer_show_enable(struct device *dev, - struct device_attribute *attr, - char *buf); -#define IIO_BUFFER_LENGTH_ATTR DEVICE_ATTR(length, S_IRUGO | S_IWUSR, \ - iio_buffer_read_length, \ - iio_buffer_write_length) - -#define IIO_BUFFER_ENABLE_ATTR DEVICE_ATTR(enable, S_IRUGO | S_IWUSR, \ - iio_buffer_show_enable, \ - iio_buffer_store_enable) - bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev, const unsigned long *mask); -- cgit v1.2.3 From 374956600ecbedf5ca29c76bde114160eb805091 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Wed, 26 Nov 2014 18:55:17 +0100 Subject: iio: buffer: Drop get_length callback We already do have the length field in the struct iio_buffer which is expected to be in sync with the current size of the buffer. And currently all implementations of the get_length callback either return this field or a constant number. This patch removes the get_length callback and replaces all occurrences in the IIO core with directly accessing the length field of the buffer. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 16b7663036f2..b65850a41127 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -26,7 +26,6 @@ struct iio_buffer; * @request_update: if a parameter change has been marked, update underlying * storage. * @set_bytes_per_datum:set number of bytes per datum - * @get_length: get number of datums in buffer * @set_length: set number of datums in buffer * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. @@ -49,7 +48,6 @@ struct iio_buffer_access_funcs { int (*request_update)(struct iio_buffer *buffer); int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); - int (*get_length)(struct iio_buffer *buffer); int (*set_length)(struct iio_buffer *buffer, int length); void (*release)(struct iio_buffer *buffer); -- cgit v1.2.3 From 09546a30632fd35996373146657d5a0296fd37ca Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Tue, 23 Sep 2014 15:51:42 +0300 Subject: iio: consumer.h: Fix scale factor in function comment 1 milivolt is equal to 1000000 nanovolts. Signed-off-by: Ivan T. Ivanov Signed-off-by: Jonathan Cameron --- include/linux/iio/consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index 6f64624f329b..26fb8f6342bb 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -201,7 +201,7 @@ int iio_read_channel_scale(struct iio_channel *chan, int *val, * The scale factor allows to increase the precession of the returned value. For * a scale factor of 1 the function will return the result in the normal IIO * unit for the channel type. E.g. millivolt for voltage channels, if you want - * nanovolts instead pass 1000 as the scale factor. + * nanovolts instead pass 1000000 as the scale factor. */ int iio_convert_raw_to_processed(struct iio_channel *chan, int raw, int *processed, unsigned int scale); -- cgit v1.2.3 From e39f2d5956999c05c85814787a113ffadbcd4b26 Mon Sep 17 00:00:00 2001 From: Andrew Duggan Date: Fri, 12 Dec 2014 10:17:26 -0800 Subject: HID: rmi: Scan the report descriptor to determine if the device is suitable for the hid-rmi driver On composite HID devices there may be multiple HID devices on separate interfaces, but hid-rmi should only bind to the touchpad. The previous version simply checked that the interface protocol was set to mouse. Unfortuately, it is not always the case that the touchpad has the mouse interface protocol set. This patch takes a different approach and scans the report descriptor looking for the Generic Desktop Pointer usage and the Vendor Specific Top Level Collection needed by the hid-rmi driver to interface with the device. Signed-off-by: Andrew Duggan Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 06c4607744f6..efc7787a41a8 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -574,7 +574,9 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 -#define HID_SCAN_FLAG_MT_WIN_8 0x00000001 +#define HID_SCAN_FLAG_MT_WIN_8 BIT(0) +#define HID_SCAN_FLAG_VENDOR_SPECIFIC BIT(1) +#define HID_SCAN_FLAG_GD_POINTER BIT(2) struct hid_parser { struct hid_global global; -- cgit v1.2.3 From d64cb71bede87dbca60d586a7bb4cef87fbe2731 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Wed, 17 Dec 2014 10:31:08 -0800 Subject: Input: add regulator haptic driver This change adds support for haptic driver controlled by voltage of a regulator. Userspace can control the device via Force Feedback interface from input framework. Signed-off-by: Jaewon Kim Signed-off-by: Hyunhee Kim Acked-by: Kyungmin Park Tested-by: Chanwoo Choi Reviewed-by: Chanwoo Choi Reviewed-by: Pankaj Dubey Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/regulator-haptic.h | 29 ++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/linux/platform_data/regulator-haptic.h (limited to 'include/linux') diff --git a/include/linux/platform_data/regulator-haptic.h b/include/linux/platform_data/regulator-haptic.h new file mode 100644 index 000000000000..5658e58e0738 --- /dev/null +++ b/include/linux/platform_data/regulator-haptic.h @@ -0,0 +1,29 @@ +/* + * Regulator Haptic Platform Data + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Jaewon Kim + * Author: Hyunhee Kim + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _REGULATOR_HAPTIC_H +#define _REGULATOR_HAPTIC_H + +/* + * struct regulator_haptic_data - Platform device data + * + * @max_volt: maximum voltage value supplied to the haptic motor. + * + * @min_volt: minimum voltage value supplied to the haptic motor. + * + */ +struct regulator_haptic_data { + unsigned int max_volt; + unsigned int min_volt; +}; + +#endif /* _REGULATOR_HAPTIC_H */ -- cgit v1.2.3 From ceacbdbf65c4cf48a130db6152c6e03432c85ed1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:41:57 +0100 Subject: dmaengine: Make the destination abbreviation coherent The dmaengine header abbreviates destination as at least two different strings. Make a coherent use of a single one. Signed-off-by: Maxime Ripard Acked-by: Mark Brown Acked-by: Laurent Pinchart Acked-by: Stephen Warren Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 40cd75e21ea2..03a1febe8740 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -387,7 +387,7 @@ enum dma_residue_granularity { /* struct dma_slave_caps - expose capabilities of a slave channel only * * @src_addr_widths: bit mask of src addr widths the channel supports - * @dstn_addr_widths: bit mask of dstn addr widths the channel supports + * @dst_addr_widths: bit mask of dstn addr widths the channel supports * @directions: bit mask of slave direction the channel supported * since the enum dma_transfer_direction is not defined as bits for each * type of direction, the dma controller should fill (1 << ) and same @@ -398,7 +398,7 @@ enum dma_residue_granularity { */ struct dma_slave_caps { u32 src_addr_widths; - u32 dstn_addr_widths; + u32 dst_addr_widths; u32 directions; bool cmd_pause; bool cmd_terminate; @@ -639,10 +639,10 @@ struct dma_device { void (*device_free_chan_resources)(struct dma_chan *chan); struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)( - struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, size_t len, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor)( - struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, + struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, -- cgit v1.2.3 From 94a73e30dfe6722e9f4ef19f7892901d7d00eab1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:42:00 +0100 Subject: dmaengine: Introduce a device_config callback The fact that the channel configuration is done in device_control is rather misleading, since it's not really advertised as such, plus, the fact that the framework exposes a function of its own makes it not really intuitive, while we're losing the type checking whenever we pass that unsigned long argument. Add a device_config callback to dma_device, with a fallback on the old behaviour for now for existing drivers to opt in. Signed-off-by: Maxime Ripard Acked-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 03a1febe8740..cf7c85d408ad 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -608,6 +608,8 @@ struct dma_tx_state { * The function takes a buffer of size buf_len. The callback function will * be called after period_len bytes have been transferred. * @device_prep_interleaved_dma: Transfer expression in a generic way. + * @device_config: Pushes a new configuration to a channel, return 0 or an error + * code * @device_control: manipulate all pending operations on a channel, returns * zero or error code * @device_tx_status: poll for transaction completion, the optional @@ -674,6 +676,9 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)( struct dma_chan *chan, struct dma_interleaved_template *xt, unsigned long flags); + + int (*device_config)(struct dma_chan *chan, + struct dma_slave_config *config); int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned long arg); @@ -697,6 +702,9 @@ static inline int dmaengine_device_control(struct dma_chan *chan, static inline int dmaengine_slave_config(struct dma_chan *chan, struct dma_slave_config *config) { + if (chan->device->device_config) + return chan->device->device_config(chan, config); + return dmaengine_device_control(chan, DMA_SLAVE_CONFIG, (unsigned long)config); } -- cgit v1.2.3 From 23a3ea2f5bead4d3b16e119e9127a66234f41d53 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:42:01 +0100 Subject: dmaengine: split out pause/resume operations from device_control Split out the pause and resume operations to callbacks of their own. In order to preserve some backwark compatibility, the dmaengine_pause/dmaengine_resume are still falling back on dmaengine_device_control. Eventually, that will allow to get the device capabilities in a generic way, removing the need to implement device_slave_caps. Signed-off-by: Maxime Ripard Acked-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index cf7c85d408ad..01f27e8a69b7 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -612,6 +612,10 @@ struct dma_tx_state { * code * @device_control: manipulate all pending operations on a channel, returns * zero or error code + * @device_pause: Pauses any transfer happening on a channel. Returns + * 0 or an error code + * @device_resume: Resumes any transfer on a channel previously + * paused. Returns 0 or an error code * @device_tx_status: poll for transaction completion, the optional * txstate parameter can be supplied with a pointer to get a * struct with auxiliary transfer status information, otherwise the call @@ -681,6 +685,8 @@ struct dma_device { struct dma_slave_config *config); int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned long arg); + int (*device_pause)(struct dma_chan *chan); + int (*device_resume)(struct dma_chan *chan); enum dma_status (*device_tx_status)(struct dma_chan *chan, dma_cookie_t cookie, @@ -795,11 +801,17 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan) static inline int dmaengine_pause(struct dma_chan *chan) { + if (chan->device->device_pause) + return chan->device->device_pause(chan); + return dmaengine_device_control(chan, DMA_PAUSE, 0); } static inline int dmaengine_resume(struct dma_chan *chan) { + if (chan->device->device_resume) + return chan->device->device_resume(chan); + return dmaengine_device_control(chan, DMA_RESUME, 0); } -- cgit v1.2.3 From 7fa0cf462daa6f6121b332b87833d7f5bdb515c0 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:42:02 +0100 Subject: dmaengine: Add device_terminate_all callback Split out the terminate_all command from device_control to a dma_device callback. In order to preserve backward capability, still rely on device_control if no such callback has been implemented. Eventually, this will allow to create a generic dma_slave_caps callback. Signed-off-by: Maxime Ripard Acked-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 01f27e8a69b7..ded5161653aa 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -616,6 +616,8 @@ struct dma_tx_state { * 0 or an error code * @device_resume: Resumes any transfer on a channel previously * paused. Returns 0 or an error code + * @device_terminate_all: Aborts all transfers on a channel. Returns 0 + * or an error code * @device_tx_status: poll for transaction completion, the optional * txstate parameter can be supplied with a pointer to get a * struct with auxiliary transfer status information, otherwise the call @@ -687,6 +689,7 @@ struct dma_device { unsigned long arg); int (*device_pause)(struct dma_chan *chan); int (*device_resume)(struct dma_chan *chan); + int (*device_terminate_all)(struct dma_chan *chan); enum dma_status (*device_tx_status)(struct dma_chan *chan, dma_cookie_t cookie, @@ -796,6 +799,9 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_cap static inline int dmaengine_terminate_all(struct dma_chan *chan) { + if (chan->device->device_terminate_all) + return chan->device->device_terminate_all(chan); + return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0); } -- cgit v1.2.3 From cb8cea513c80db1dfe2dce468d2d0772005bb9a1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:42:04 +0100 Subject: dmaengine: Create a generic dma_slave_caps callback dma_slave_caps is very important to the generic layers that might interact with dmaengine, such as ASoC. Unfortunately, it has been added as yet another dma_device callback, and most of the existing drivers haven't implemented it, reducing its reliability. Introduce a generic behaviour to implement this, that rely on both the split of device_control to derive which functions are supported and on new variables to be set in the dma_device structure. These variables holds what used to be the capabilities, that were set per-channel. However, this proved to be a bit overkill, since every driver filling these so far were hardcoding it, disregarding which channel was actually given. Signed-off-by: Maxime Ripard Acked-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 41 +++++++++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index ded5161653aa..adf22089cc93 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -594,6 +594,14 @@ struct dma_tx_state { * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api + * @src_addr_widths: bit mask of src addr widths the device supports + * @dst_addr_widths: bit mask of dst addr widths the device supports + * @directions: bit mask of slave direction the device supports since + * the enum dma_transfer_direction is not defined as bits for + * each type of direction, the dma controller should fill (1 << + * ) and same should be checked by controller as well + * @residue_granularity: granularity of the transfer residue reported + * by tx_status * @device_alloc_chan_resources: allocate resources and return the * number of allocated descriptors * @device_free_chan_resources: release DMA channel's resources @@ -643,6 +651,11 @@ struct dma_device { int dev_id; struct device *dev; + u32 src_addr_widths; + u32 dst_addr_widths; + u32 directions; + enum dma_residue_granularity residue_granularity; + int (*device_alloc_chan_resources)(struct dma_chan *chan); void (*device_free_chan_resources)(struct dma_chan *chan); @@ -784,17 +797,37 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps) { + struct dma_device *device; + if (!chan || !caps) return -EINVAL; + device = chan->device; + /* check if the channel supports slave transactions */ - if (!test_bit(DMA_SLAVE, chan->device->cap_mask.bits)) + if (!test_bit(DMA_SLAVE, device->cap_mask.bits)) + return -ENXIO; + + if (device->device_slave_caps) + return device->device_slave_caps(chan, caps); + + /* + * Check whether it reports it uses the generic slave + * capabilities, if not, that means it doesn't support any + * kind of slave capabilities reporting. + */ + if (!device->directions) return -ENXIO; - if (chan->device->device_slave_caps) - return chan->device->device_slave_caps(chan, caps); + caps->src_addr_widths = device->src_addr_widths; + caps->dst_addr_widths = device->dst_addr_widths; + caps->directions = device->directions; + caps->residue_granularity = device->residue_granularity; + + caps->cmd_pause = !!device->device_pause; + caps->cmd_terminate = !!device->device_terminate_all; - return -ENXIO; + return 0; } static inline int dmaengine_terminate_all(struct dma_chan *chan) -- cgit v1.2.3 From 2c44ad914c56f4e53ef43285b5e4fe3459109769 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 17 Nov 2014 14:42:54 +0100 Subject: dmaengine: Remove device_control and device_slave_caps Now that device_control has been split into several functions, and device_slave_caps rendered useless, we can safely remove them. Signed-off-by: Maxime Ripard Acked-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 52 ++++++----------------------------------------- 1 file changed, 6 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index adf22089cc93..6d34ce91036c 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -188,25 +188,6 @@ enum dma_ctrl_flags { DMA_PREP_FENCE = (1 << 5), }; -/** - * enum dma_ctrl_cmd - DMA operations that can optionally be exercised - * on a running channel. - * @DMA_TERMINATE_ALL: terminate all ongoing transfers - * @DMA_PAUSE: pause ongoing transfers - * @DMA_RESUME: resume paused transfer - * @DMA_SLAVE_CONFIG: this command is only implemented by DMA controllers - * that need to runtime reconfigure the slave channels (as opposed to passing - * configuration data in statically from the platform). An additional - * argument of struct dma_slave_config must be passed in with this - * command. - */ -enum dma_ctrl_cmd { - DMA_TERMINATE_ALL, - DMA_PAUSE, - DMA_RESUME, - DMA_SLAVE_CONFIG, -}; - /** * enum sum_check_bits - bit position of pq_check_flags */ @@ -336,9 +317,8 @@ enum dma_slave_buswidth { * This struct is passed in as configuration data to a DMA engine * in order to set up a certain channel for DMA transport at runtime. * The DMA device/engine has to provide support for an additional - * command in the channel config interface, DMA_SLAVE_CONFIG - * and this struct will then be passed in as an argument to the - * DMA engine device_control() function. + * callback in the dma_device structure, device_config and this struct + * will then be passed in as an argument to the function. * * The rationale for adding configuration information to this struct is as * follows: if it is likely that more than one DMA slave controllers in @@ -618,8 +598,6 @@ struct dma_tx_state { * @device_prep_interleaved_dma: Transfer expression in a generic way. * @device_config: Pushes a new configuration to a channel, return 0 or an error * code - * @device_control: manipulate all pending operations on a channel, returns - * zero or error code * @device_pause: Pauses any transfer happening on a channel. Returns * 0 or an error code * @device_resume: Resumes any transfer on a channel previously @@ -631,7 +609,6 @@ struct dma_tx_state { * struct with auxiliary transfer status information, otherwise the call * will just return a simple status code * @device_issue_pending: push pending transactions to hardware - * @device_slave_caps: return the slave channel capabilities */ struct dma_device { @@ -698,8 +675,6 @@ struct dma_device { int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config); - int (*device_control)(struct dma_chan *chan, enum dma_ctrl_cmd cmd, - unsigned long arg); int (*device_pause)(struct dma_chan *chan); int (*device_resume)(struct dma_chan *chan); int (*device_terminate_all)(struct dma_chan *chan); @@ -708,27 +683,15 @@ struct dma_device { dma_cookie_t cookie, struct dma_tx_state *txstate); void (*device_issue_pending)(struct dma_chan *chan); - int (*device_slave_caps)(struct dma_chan *chan, struct dma_slave_caps *caps); }; -static inline int dmaengine_device_control(struct dma_chan *chan, - enum dma_ctrl_cmd cmd, - unsigned long arg) -{ - if (chan->device->device_control) - return chan->device->device_control(chan, cmd, arg); - - return -ENOSYS; -} - static inline int dmaengine_slave_config(struct dma_chan *chan, struct dma_slave_config *config) { if (chan->device->device_config) return chan->device->device_config(chan, config); - return dmaengine_device_control(chan, DMA_SLAVE_CONFIG, - (unsigned long)config); + return -ENOSYS; } static inline bool is_slave_direction(enum dma_transfer_direction direction) @@ -808,9 +771,6 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_cap if (!test_bit(DMA_SLAVE, device->cap_mask.bits)) return -ENXIO; - if (device->device_slave_caps) - return device->device_slave_caps(chan, caps); - /* * Check whether it reports it uses the generic slave * capabilities, if not, that means it doesn't support any @@ -835,7 +795,7 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan) if (chan->device->device_terminate_all) return chan->device->device_terminate_all(chan); - return dmaengine_device_control(chan, DMA_TERMINATE_ALL, 0); + return -ENOSYS; } static inline int dmaengine_pause(struct dma_chan *chan) @@ -843,7 +803,7 @@ static inline int dmaengine_pause(struct dma_chan *chan) if (chan->device->device_pause) return chan->device->device_pause(chan); - return dmaengine_device_control(chan, DMA_PAUSE, 0); + return -ENOSYS; } static inline int dmaengine_resume(struct dma_chan *chan) @@ -851,7 +811,7 @@ static inline int dmaengine_resume(struct dma_chan *chan) if (chan->device->device_resume) return chan->device->device_resume(chan); - return dmaengine_device_control(chan, DMA_RESUME, 0); + return -ENOSYS; } static inline enum dma_status dmaengine_tx_status(struct dma_chan *chan, -- cgit v1.2.3 From 3a2c0ba5ad00c018c0bef39a2224aca950aa33f2 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 8 Dec 2014 16:50:37 +0800 Subject: hwrng: use reference counts on each struct hwrng. current_rng holds one reference, and we bump it every time we want to do a read from it. This means we only hold the rng_mutex to grab or drop a reference, so accessing /sys/devices/virtual/misc/hw_random/rng_current doesn't block on read of /dev/hwrng. Using a kref is overkill (we're always under the rng_mutex), but a standard pattern. This also solves the problem that the hwrng_fillfn thread was accessing current_rng without a lock, which could change (eg. to NULL) underneath it. Signed-off-by: Rusty Russell Signed-off-by: Amos Kong Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 914bb08cd738..c212e71ea886 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -14,6 +14,7 @@ #include #include +#include /** * struct hwrng - Hardware Random Number Generator driver @@ -44,6 +45,7 @@ struct hwrng { /* internal. */ struct list_head list; + struct kref ref; }; /** Register a new Hardware Random Number Generator driver. */ -- cgit v1.2.3 From a027f30d72f2c4d27d6dd9bd053205d3102de7d1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 8 Dec 2014 16:50:38 +0800 Subject: hwrng: fix unregister race. The previous patch added one potential problem: we can still be reading from a hwrng when it's unregistered. Add a wait for zero in the hwrng_unregister path. Signed-off-by: Rusty Russell Signed-off-by: Amos Kong Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index c212e71ea886..7832e5008959 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -46,6 +46,7 @@ struct hwrng { /* internal. */ struct list_head list; struct kref ref; + bool cleanup_done; }; /** Register a new Hardware Random Number Generator driver. */ -- cgit v1.2.3 From c5f4546593e9911800f0926c1090959b58bc5c93 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 16 Dec 2014 11:58:18 -0600 Subject: livepatch: kernel: add TAINT_LIVEPATCH This adds a new taint flag to indicate when the kernel or a kernel module has been live patched. This will provide a clean indication in bug reports that live patching was used. Additionally, if the crash occurs in a live patched function, the live patch module will appear beside the patched function in the backtrace. Signed-off-by: Seth Jennings Acked-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Reviewed-by: Petr Mladek Reviewed-by: Masami Hiramatsu Signed-off-by: Jiri Kosina --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5449d2f4a1ef..d03e3deee091 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -471,6 +471,7 @@ extern enum system_states { #define TAINT_OOT_MODULE 12 #define TAINT_UNSIGNED_MODULE 13 #define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] -- cgit v1.2.3 From b700e7f03df5d92f85fa5247fe1f557528d3363d Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Tue, 16 Dec 2014 11:58:19 -0600 Subject: livepatch: kernel: add support for live patching This commit introduces code for the live patching core. It implements an ftrace-based mechanism and kernel interface for doing live patching of kernel and kernel module functions. It represents the greatest common functionality set between kpatch and kgraft and can accept patches built using either method. This first version does not implement any consistency mechanism that ensures that old and new code do not run together. In practice, ~90% of CVEs are safe to apply in this way, since they simply add a conditional check. However, any function change that can not execute safely with the old version of the function can _not_ be safely applied in this version. [ jkosina@suse.cz: due to the number of contributions that got folded into this original patch from Seth Jennings, add SUSE's copyright as well, as discussed via e-mail ] Signed-off-by: Seth Jennings Signed-off-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Reviewed-by: Petr Mladek Reviewed-by: Masami Hiramatsu Signed-off-by: Miroslav Benes Signed-off-by: Petr Mladek Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 133 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 133 insertions(+) create mode 100644 include/linux/livepatch.h (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h new file mode 100644 index 000000000000..950bc615842f --- /dev/null +++ b/include/linux/livepatch.h @@ -0,0 +1,133 @@ +/* + * livepatch.h - Kernel Live Patching Core + * + * Copyright (C) 2014 Seth Jennings + * Copyright (C) 2014 SUSE + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + */ + +#ifndef _LINUX_LIVEPATCH_H_ +#define _LINUX_LIVEPATCH_H_ + +#include +#include + +#if IS_ENABLED(CONFIG_LIVE_PATCHING) + +#include + +enum klp_state { + KLP_DISABLED, + KLP_ENABLED +}; + +/** + * struct klp_func - function structure for live patching + * @old_name: name of the function to be patched + * @new_func: pointer to the patched function code + * @old_addr: a hint conveying at what address the old function + * can be found (optional, vmlinux patches only) + * @kobj: kobject for sysfs resources + * @fops: ftrace operations structure + * @state: tracks function-level patch application state + */ +struct klp_func { + /* external */ + const char *old_name; + void *new_func; + /* + * The old_addr field is optional and can be used to resolve + * duplicate symbol names in the vmlinux object. If this + * information is not present, the symbol is located by name + * with kallsyms. If the name is not unique and old_addr is + * not provided, the patch application fails as there is no + * way to resolve the ambiguity. + */ + unsigned long old_addr; + + /* internal */ + struct kobject kobj; + struct ftrace_ops *fops; + enum klp_state state; +}; + +/** + * struct klp_reloc - relocation structure for live patching + * @loc: address where the relocation will be written + * @val: address of the referenced symbol (optional, + * vmlinux patches only) + * @type: ELF relocation type + * @name: name of the referenced symbol (for lookup/verification) + * @addend: offset from the referenced symbol + * @external: symbol is either exported or within the live patch module itself + */ +struct klp_reloc { + unsigned long loc; + unsigned long val; + unsigned long type; + const char *name; + int addend; + int external; +}; + +/** + * struct klp_object - kernel object structure for live patching + * @name: module name (or NULL for vmlinux) + * @relocs: relocation entries to be applied at load time + * @funcs: function entries for functions to be patched in the object + * @kobj: kobject for sysfs resources + * @mod: kernel module associated with the patched object + * (NULL for vmlinux) + * @state: tracks object-level patch application state + */ +struct klp_object { + /* external */ + const char *name; + struct klp_reloc *relocs; + struct klp_func *funcs; + + /* internal */ + struct kobject *kobj; + struct module *mod; + enum klp_state state; +}; + +/** + * struct klp_patch - patch structure for live patching + * @mod: reference to the live patch module + * @objs: object entries for kernel objects to be patched + * @list: list node for global list of registered patches + * @kobj: kobject for sysfs resources + * @state: tracks patch-level application state + */ +struct klp_patch { + /* external */ + struct module *mod; + struct klp_object *objs; + + /* internal */ + struct list_head list; + struct kobject kobj; + enum klp_state state; +}; + +extern int klp_register_patch(struct klp_patch *); +extern int klp_unregister_patch(struct klp_patch *); +extern int klp_enable_patch(struct klp_patch *); +extern int klp_disable_patch(struct klp_patch *); + +#endif /* CONFIG_LIVE_PATCHING */ + +#endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 2c658e212ce7e40ace56d9441c8c5634d4d420e3 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 18 Dec 2014 16:12:08 +0200 Subject: spi: Remove FSF mailing addresses Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown --- include/linux/spi/at86rf230.h | 4 ---- include/linux/spi/l4f00242t03.h | 4 ---- include/linux/spi/lms283gf05.h | 4 ---- include/linux/spi/mxs-spi.h | 4 ---- include/linux/spi/pxa2xx_spi.h | 4 ---- include/linux/spi/rspi.h | 5 ----- include/linux/spi/sh_hspi.h | 4 ---- include/linux/spi/spi.h | 4 ---- include/linux/spi/tle62x0.h | 4 ---- include/linux/spi/tsc2005.h | 5 ----- 10 files changed, 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h index b2b1afbb3202..cd519a11c2c6 100644 --- a/include/linux/spi/at86rf230.h +++ b/include/linux/spi/at86rf230.h @@ -12,10 +12,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - * * Written by: * Dmitry Eremin-Solenikov */ diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h index bc8677c8eba9..e69e9b51b21a 100644 --- a/include/linux/spi/l4f00242t03.h +++ b/include/linux/spi/l4f00242t03.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_ diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h index 555d254e6606..fdd1d1d51da5 100644 --- a/include/linux/spi/lms283gf05.h +++ b/include/linux/spi/lms283gf05.h @@ -11,10 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_ diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h index 4835486f58e5..381d368b91b4 100644 --- a/include/linux/spi/mxs-spi.h +++ b/include/linux/spi/mxs-spi.h @@ -15,10 +15,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ #ifndef __LINUX_SPI_MXS_SPI_H__ diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index d5a316550177..5eb56e35cf0d 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __linux_pxa2xx_spi_h #define __linux_pxa2xx_spi_h diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h index e546b2ceb623..a693188cc08b 100644 --- a/include/linux/spi/rspi.h +++ b/include/linux/spi/rspi.h @@ -11,11 +11,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * */ #ifndef __LINUX_SPI_RENESAS_SPI_H__ diff --git a/include/linux/spi/sh_hspi.h b/include/linux/spi/sh_hspi.h index a1121f872ac1..aa0d440ab4f0 100644 --- a/include/linux/spi/sh_hspi.h +++ b/include/linux/spi/sh_hspi.h @@ -9,10 +9,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef SH_HSPI_H #define SH_HSPI_H diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a6ef2a8e6de4..6e2664a17114 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -10,10 +10,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef __LINUX_SPI_H diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h index 60b59187e590..414c6fddfcf0 100644 --- a/include/linux/spi/tle62x0.h +++ b/include/linux/spi/tle62x0.h @@ -12,10 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ struct tle62x0_pdata { diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h index 8f721e465e05..563b3b1799a8 100644 --- a/include/linux/spi/tsc2005.h +++ b/include/linux/spi/tsc2005.h @@ -12,11 +12,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _LINUX_SPI_TSC2005_H -- cgit v1.2.3 From 556d2f055bf6d79ce81587dfe774d4dd10da473f Mon Sep 17 00:00:00 2001 From: Yalin Wang Date: Mon, 3 Nov 2014 03:01:03 +0100 Subject: ARM: 8187/1: add CONFIG_HAVE_ARCH_BITREVERSE to support rbit instruction this change add CONFIG_HAVE_ARCH_BITREVERSE config option, so that we can use some architecture's bitrev hardware instruction to do bitrev operation. Introduce __constant_bitrev* macro for constant bitrev operation. Change __bitrev16() __bitrev32() to be inline function, don't need export symbol for these tiny functions. Signed-off-by: Yalin Wang Acked-by: Will Deacon Signed-off-by: Russell King --- include/linux/bitrev.h | 77 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 73 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 7ffe03f4693d..fb790b8449c1 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -3,14 +3,83 @@ #include -extern u8 const byte_rev_table[256]; +#ifdef CONFIG_HAVE_ARCH_BITREVERSE +#include + +#define __bitrev32 __arch_bitrev32 +#define __bitrev16 __arch_bitrev16 +#define __bitrev8 __arch_bitrev8 -static inline u8 bitrev8(u8 byte) +#else +extern u8 const byte_rev_table[256]; +static inline u8 __bitrev8(u8 byte) { return byte_rev_table[byte]; } -extern u16 bitrev16(u16 in); -extern u32 bitrev32(u32 in); +static inline u16 __bitrev16(u16 x) +{ + return (__bitrev8(x & 0xff) << 8) | __bitrev8(x >> 8); +} + +static inline u32 __bitrev32(u32 x) +{ + return (__bitrev16(x & 0xffff) << 16) | __bitrev16(x >> 16); +} + +#endif /* CONFIG_HAVE_ARCH_BITREVERSE */ + +#define __constant_bitrev32(x) \ +({ \ + u32 __x = x; \ + __x = (__x >> 16) | (__x << 16); \ + __x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8); \ + __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ + __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ + __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ + __x; \ +}) + +#define __constant_bitrev16(x) \ +({ \ + u16 __x = x; \ + __x = (__x >> 8) | (__x << 8); \ + __x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4); \ + __x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2); \ + __x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1); \ + __x; \ +}) + +#define __constant_bitrev8(x) \ +({ \ + u8 __x = x; \ + __x = (__x >> 4) | (__x << 4); \ + __x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2); \ + __x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1); \ + __x; \ +}) + +#define bitrev32(x) \ +({ \ + u32 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev32(__x) : \ + __bitrev32(__x); \ +}) + +#define bitrev16(x) \ +({ \ + u16 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev16(__x) : \ + __bitrev16(__x); \ + }) +#define bitrev8(x) \ +({ \ + u8 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev8(__x) : \ + __bitrev8(__x) ; \ + }) #endif /* _LINUX_BITREV_H */ -- cgit v1.2.3 From 523c5b89640e147abc7c70466f55327df8559d0a Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 30 Nov 2014 17:52:32 +0100 Subject: i2c: Remove support for legacy PM There haven't been any I2C driver that use the legacy suspend/resume callbacks for a while now and new drivers are supposed to use PM ops. So remove support for legacy suspend/resume for I2C drivers. Since there aren't any special bus specific things to do during suspend/resume and since the PM core will automatically fallback directly to using the device's PM ops if no bus PM ops are specified there is no need to have any I2C bus PM ops. Signed-off-by: Lars-Peter Clausen Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e3a1721c8354..3090ee6e171d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -130,8 +130,6 @@ extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, * @probe: Callback for device binding * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown - * @suspend: Callback for device suspend - * @resume: Callback for device resume * @alert: Alert callback, for example for the SMBus alert protocol * @command: Callback for bus-wide signaling (optional) * @driver: Device driver model driver @@ -174,8 +172,6 @@ struct i2c_driver { /* driver model interfaces that don't relate to enumeration */ void (*shutdown)(struct i2c_client *); - int (*suspend)(struct i2c_client *, pm_message_t mesg); - int (*resume)(struct i2c_client *); /* Alert callback, for example for the SMBus alert protocol. * The format and meaning of the data value depends on the protocol. -- cgit v1.2.3 From c4827bb859cbe8afad9287c9dd4e7162119d3d59 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 18 Dec 2014 15:04:21 +0200 Subject: spi: pxa2xx: Add definition for Intel Quark DDS_RATE register Intel Quark DDS_RATE register is defined only in register access macro. Add a definition for it to common SSP register definitions for preparing to cleanup those macros. Signed-off-by: Jarkko Nikula Signed-off-by: Mark Brown --- include/linux/pxa2xx_ssp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 77aed9ea1d26..dab545bb66b3 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -37,6 +37,7 @@ #define SSDR (0x10) /* SSP Data Write/Data Read Register */ #define SSTO (0x28) /* SSP Time Out Register */ +#define DDS_RATE (0x28) /* SSP DDS Clock Rate Register (Intel Quark) */ #define SSPSP (0x2C) /* SSP Programmable Serial Protocol */ #define SSTSA (0x30) /* SSP Tx Timeslot Active */ #define SSRSA (0x34) /* SSP Rx Timeslot Active */ -- cgit v1.2.3 From 534a729866f9edc9264340c5b96cb94878ffda00 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 6 Aug 2014 10:52:41 +0200 Subject: dmaengine: Add 16 bytes, 32 bytes and 64 bytes bus widths The widths are missing, add them. Signed-off-by: Laurent Pinchart Tested-by: Kuninori Morimoto Tested-by: Wolfram Sang --- include/linux/dmaengine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6d34ce91036c..b7724a5d4661 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -279,6 +279,9 @@ enum dma_slave_buswidth { DMA_SLAVE_BUSWIDTH_3_BYTES = 3, DMA_SLAVE_BUSWIDTH_4_BYTES = 4, DMA_SLAVE_BUSWIDTH_8_BYTES = 8, + DMA_SLAVE_BUSWIDTH_16_BYTES = 16, + DMA_SLAVE_BUSWIDTH_32_BYTES = 32, + DMA_SLAVE_BUSWIDTH_64_BYTES = 64, }; /** -- cgit v1.2.3 From 32d17597d3e299ffe8b07e3afc12f8074e7ae483 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 9 Apr 2014 08:13:18 -0300 Subject: [media] v4l: vsp1: Remove support for platform data Now that all platforms instantiate the VSP1 through DT, platform data support isn't needed anymore. Signed-off-by: Laurent Pinchart Acked-by: Simon Horman Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/vsp1.h | 27 --------------------------- 1 file changed, 27 deletions(-) delete mode 100644 include/linux/platform_data/vsp1.h (limited to 'include/linux') diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h deleted file mode 100644 index 63170e2614b3..000000000000 --- a/include/linux/platform_data/vsp1.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * vsp1.h -- R-Car VSP1 Platform Data - * - * Copyright (C) 2013 Renesas Corporation - * - * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ -#ifndef __PLATFORM_VSP1_H__ -#define __PLATFORM_VSP1_H__ - -#define VSP1_HAS_LIF (1 << 0) -#define VSP1_HAS_LUT (1 << 1) -#define VSP1_HAS_SRU (1 << 2) - -struct vsp1_platform_data { - unsigned int features; - unsigned int rpf_count; - unsigned int uds_count; - unsigned int wpf_count; -}; - -#endif /* __PLATFORM_VSP1_H__ */ -- cgit v1.2.3 From 3110628d89f80fbafa085fd62e75afcb39fb764c Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Fri, 19 Dec 2014 17:15:53 +0900 Subject: spi: sh-msiof: Configure MSIOF sync signal timing in device tree The MSIOF controller has DTDL and SYNCDL in SITMDR1 register. So, this patch adds new properties like the following commit: d0fb47a5237d8b9576113568bacfd27892308b62 (spi: fsl-espi: Configure FSL eSPI CSBEF and CSAFT) Signed-off-by: Yoshihiro Shimoda Signed-off-by: Mark Brown --- include/linux/spi/sh_msiof.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h index 88a14d81c49e..b087a85f5f72 100644 --- a/include/linux/spi/sh_msiof.h +++ b/include/linux/spi/sh_msiof.h @@ -7,6 +7,8 @@ struct sh_msiof_spi_info { u16 num_chipselect; unsigned int dma_tx_id; unsigned int dma_rx_id; + u32 dtdl; + u32 syncdl; }; #endif /* __SPI_SH_MSIOF_H__ */ -- cgit v1.2.3 From 0425e2420c0ab1b5da24f6d9fce39241ad85fc46 Mon Sep 17 00:00:00 2001 From: Flora Fu Date: Fri, 5 Dec 2014 12:07:54 +0800 Subject: regulator: mt6397: Add support for MT6397 regulator Add MT6397 regulator driver. Signed-off-by: Flora Fu Signed-off-by: Mark Brown --- include/linux/regulator/mt6397-regulator.h | 49 ++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 include/linux/regulator/mt6397-regulator.h (limited to 'include/linux') diff --git a/include/linux/regulator/mt6397-regulator.h b/include/linux/regulator/mt6397-regulator.h new file mode 100644 index 000000000000..30cc5963e265 --- /dev/null +++ b/include/linux/regulator/mt6397-regulator.h @@ -0,0 +1,49 @@ +/* + * Copyright (c) 2014 MediaTek Inc. + * Author: Flora Fu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_MT6397_H +#define __LINUX_REGULATOR_MT6397_H + +enum { + MT6397_ID_VPCA15 = 0, + MT6397_ID_VPCA7, + MT6397_ID_VSRAMCA15, + MT6397_ID_VSRAMCA7, + MT6397_ID_VCORE, + MT6397_ID_VGPU, + MT6397_ID_VDRM, + MT6397_ID_VIO18 = 7, + MT6397_ID_VTCXO, + MT6397_ID_VA28, + MT6397_ID_VCAMA, + MT6397_ID_VIO28, + MT6397_ID_VUSB, + MT6397_ID_VMC, + MT6397_ID_VMCH, + MT6397_ID_VEMC3V3, + MT6397_ID_VGP1, + MT6397_ID_VGP2, + MT6397_ID_VGP3, + MT6397_ID_VGP4, + MT6397_ID_VGP5, + MT6397_ID_VGP6, + MT6397_ID_VIBR, + MT6397_ID_RG_MAX, +}; + +#define MT6397_MAX_REGULATOR MT6397_ID_RG_MAX +#define MT6397_REGULATOR_ID97 0x97 +#define MT6397_REGULATOR_ID91 0x91 + +#endif /* __LINUX_REGULATOR_MT6397_H */ -- cgit v1.2.3 From 0628ee7c81a8ced9b10f9ee300707f7f79fdecf1 Mon Sep 17 00:00:00 2001 From: Nicholas Krause Date: Sun, 21 Dec 2014 22:36:37 -0500 Subject: libata: s/ata_id_removeable()/ata_id_removable()/ Changes the spelling typos of removeable to removable where ata_id_removeable is defined in ata.h and called in libata-scsi.c respectively. Signed-off-by: Nicholas Krause Signed-off-by: Tejun Heo --- include/linux/ata.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index f2f4d8da97c0..1648026e06b4 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -503,7 +503,7 @@ struct ata_bmdma_prd { #define ata_id_has_dma(id) ((id)[ATA_ID_CAPABILITY] & (1 << 8)) #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) -#define ata_id_removeable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) +#define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ -- cgit v1.2.3 From 77584ee57434813b50fc85cde995a6271a5081b7 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 23 Dec 2014 16:40:17 +1100 Subject: hwrng: core - Use struct completion for cleanup_done There is no point in doing a manual completion for cleanup_done when struct completion fits in perfectly. Signed-off-by: Herbert Xu --- include/linux/hw_random.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 7832e5008959..eb7b414d232b 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -12,6 +12,7 @@ #ifndef LINUX_HWRANDOM_H_ #define LINUX_HWRANDOM_H_ +#include #include #include #include @@ -46,7 +47,7 @@ struct hwrng { /* internal. */ struct list_head list; struct kref ref; - bool cleanup_done; + struct completion cleanup_done; }; /** Register a new Hardware Random Number Generator driver. */ -- cgit v1.2.3 From 7ab374a053a43050117eb452306b6cd9dcb58cfd Mon Sep 17 00:00:00 2001 From: Karol Wrona Date: Fri, 19 Dec 2014 18:39:24 +0100 Subject: iio: kfifo: Remove unused argument in iio_kfifo_allocate indio_dev was unused in function body plus some small style fix - add new lines after "if(sth) return sth" and before the last return statement. The argument was removed also in its client. Signed-off-by: Karol Wrona Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index 25eeac762e84..1a8d57a41738 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -5,7 +5,7 @@ #include #include -struct iio_buffer *iio_kfifo_allocate(struct iio_dev *indio_dev); +struct iio_buffer *iio_kfifo_allocate(void); void iio_kfifo_free(struct iio_buffer *r); #endif -- cgit v1.2.3 From 780103fef5c88a97fb9c8d0079bf326ed6147f1f Mon Sep 17 00:00:00 2001 From: Karol Wrona Date: Fri, 19 Dec 2014 18:39:25 +0100 Subject: iio: kfifo: Add resource management devm_iio_kfifo_allocate/free iio kfifo allocate/free gained their devm_ wrappers. Signed-off-by: Karol Wrona Suggested-by: Jonathan Cameron Signed-off-by: Jonathan Cameron --- include/linux/iio/kfifo_buf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/kfifo_buf.h b/include/linux/iio/kfifo_buf.h index 1a8d57a41738..1683bc710d14 100644 --- a/include/linux/iio/kfifo_buf.h +++ b/include/linux/iio/kfifo_buf.h @@ -8,4 +8,7 @@ struct iio_buffer *iio_kfifo_allocate(void); void iio_kfifo_free(struct iio_buffer *r); +struct iio_buffer *devm_iio_kfifo_allocate(struct device *dev); +void devm_iio_kfifo_free(struct device *dev, struct iio_buffer *r); + #endif -- cgit v1.2.3 From 74d23cc704d19732e70ef1579a669f7d5f09dd9a Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 21 Dec 2014 19:46:56 +0100 Subject: time: move the timecounter/cyclecounter code into its own file. The timecounter code has almost nothing to do with the clocksource code. Let it live in its own file. This will help isolate the timecounter users from the clocksource users in the source tree. Signed-off-by: Richard Cochran Acked-by: Jeff Kirsher Signed-off-by: David S. Miller --- include/linux/clocksource.h | 102 ------------------------------------ include/linux/mlx4/device.h | 2 +- include/linux/timecounter.h | 122 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/types.h | 3 ++ 4 files changed, 126 insertions(+), 103 deletions(-) create mode 100644 include/linux/timecounter.h (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index abcafaa20b86..9c78d15d33e4 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -18,8 +18,6 @@ #include #include -/* clocksource cycle base type */ -typedef u64 cycle_t; struct clocksource; struct module; @@ -27,106 +25,6 @@ struct module; #include #endif -/** - * struct cyclecounter - hardware abstraction for a free running counter - * Provides completely state-free accessors to the underlying hardware. - * Depending on which hardware it reads, the cycle counter may wrap - * around quickly. Locking rules (if necessary) have to be defined - * by the implementor and user of specific instances of this API. - * - * @read: returns the current cycle value - * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, - * see CLOCKSOURCE_MASK() helper macro - * @mult: cycle to nanosecond multiplier - * @shift: cycle to nanosecond divisor (power of two) - */ -struct cyclecounter { - cycle_t (*read)(const struct cyclecounter *cc); - cycle_t mask; - u32 mult; - u32 shift; -}; - -/** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds - * Contains the state needed by timecounter_read() to detect - * cycle counter wrap around. Initialize with - * timecounter_init(). Also used to convert cycle counts into the - * corresponding nanosecond counts with timecounter_cyc2time(). Users - * of this code are responsible for initializing the underlying - * cycle counter hardware, locking issues and reading the time - * more often than the cycle counter wraps around. The nanosecond - * counter will only wrap around after ~585 years. - * - * @cc: the cycle counter used by this instance - * @cycle_last: most recent cycle counter value seen by - * timecounter_read() - * @nsec: continuously increasing count - */ -struct timecounter { - const struct cyclecounter *cc; - cycle_t cycle_last; - u64 nsec; -}; - -/** - * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds - * @cc: Pointer to cycle counter. - * @cycles: Cycles - * - * XXX - This could use some mult_lxl_ll() asm optimization. Same code - * as in cyc2ns, but with unsigned result. - */ -static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, - cycle_t cycles) -{ - u64 ret = (u64)cycles; - ret = (ret * cc->mult) >> cc->shift; - return ret; -} - -/** - * timecounter_init - initialize a time counter - * @tc: Pointer to time counter which is to be initialized/reset - * @cc: A cycle counter, ready to be used. - * @start_tstamp: Arbitrary initial time stamp. - * - * After this call the current cycle register (roughly) corresponds to - * the initial time stamp. Every call to timecounter_read() increments - * the time stamp counter by the number of elapsed nanoseconds. - */ -extern void timecounter_init(struct timecounter *tc, - const struct cyclecounter *cc, - u64 start_tstamp); - -/** - * timecounter_read - return nanoseconds elapsed since timecounter_init() - * plus the initial time stamp - * @tc: Pointer to time counter. - * - * In other words, keeps track of time since the same epoch as - * the function which generated the initial time stamp. - */ -extern u64 timecounter_read(struct timecounter *tc); - -/** - * timecounter_cyc2time - convert a cycle counter to same - * time base as values returned by - * timecounter_read() - * @tc: Pointer to time counter. - * @cycle_tstamp: a value returned by tc->cc->read() - * - * Cycle counts that are converted correctly as long as they - * fall into the interval [-1/2 max cycle count, +1/2 max cycle count], - * with "max cycle count" == cs->mask+1. - * - * This allows conversion of cycle counter values which were generated - * in the past. - */ -extern u64 timecounter_cyc2time(struct timecounter *tc, - cycle_t cycle_tstamp); - /** * struct clocksource - hardware abstraction for a free running counter * Provides mostly state-free accessors to the underlying hardware. diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 25c791e295fd..f1e41b33462f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -42,7 +42,7 @@ #include -#include +#include #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h new file mode 100644 index 000000000000..146f07a6651b --- /dev/null +++ b/include/linux/timecounter.h @@ -0,0 +1,122 @@ +/* + * linux/include/linux/timecounter.h + * + * based on code that migrated away from + * linux/include/linux/clocksource.h + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef _LINUX_TIMECOUNTER_H +#define _LINUX_TIMECOUNTER_H + +#include + +/** + * struct cyclecounter - hardware abstraction for a free running counter + * Provides completely state-free accessors to the underlying hardware. + * Depending on which hardware it reads, the cycle counter may wrap + * around quickly. Locking rules (if necessary) have to be defined + * by the implementor and user of specific instances of this API. + * + * @read: returns the current cycle value + * @mask: bitmask for two's complement + * subtraction of non 64 bit counters, + * see CLOCKSOURCE_MASK() helper macro + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) + */ +struct cyclecounter { + cycle_t (*read)(const struct cyclecounter *cc); + cycle_t mask; + u32 mult; + u32 shift; +}; + +/** + * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * Contains the state needed by timecounter_read() to detect + * cycle counter wrap around. Initialize with + * timecounter_init(). Also used to convert cycle counts into the + * corresponding nanosecond counts with timecounter_cyc2time(). Users + * of this code are responsible for initializing the underlying + * cycle counter hardware, locking issues and reading the time + * more often than the cycle counter wraps around. The nanosecond + * counter will only wrap around after ~585 years. + * + * @cc: the cycle counter used by this instance + * @cycle_last: most recent cycle counter value seen by + * timecounter_read() + * @nsec: continuously increasing count + */ +struct timecounter { + const struct cyclecounter *cc; + cycle_t cycle_last; + u64 nsec; +}; + +/** + * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds + * @cc: Pointer to cycle counter. + * @cycles: Cycles + * + * XXX - This could use some mult_lxl_ll() asm optimization. Same code + * as in cyc2ns, but with unsigned result. + */ +static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, + cycle_t cycles) +{ + u64 ret = (u64)cycles; + ret = (ret * cc->mult) >> cc->shift; + return ret; +} + +/** + * timecounter_init - initialize a time counter + * @tc: Pointer to time counter which is to be initialized/reset + * @cc: A cycle counter, ready to be used. + * @start_tstamp: Arbitrary initial time stamp. + * + * After this call the current cycle register (roughly) corresponds to + * the initial time stamp. Every call to timecounter_read() increments + * the time stamp counter by the number of elapsed nanoseconds. + */ +extern void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp); + +/** + * timecounter_read - return nanoseconds elapsed since timecounter_init() + * plus the initial time stamp + * @tc: Pointer to time counter. + * + * In other words, keeps track of time since the same epoch as + * the function which generated the initial time stamp. + */ +extern u64 timecounter_read(struct timecounter *tc); + +/** + * timecounter_cyc2time - convert a cycle counter to same + * time base as values returned by + * timecounter_read() + * @tc: Pointer to time counter. + * @cycle_tstamp: a value returned by tc->cc->read() + * + * Cycle counts that are converted correctly as long as they + * fall into the interval [-1/2 max cycle count, +1/2 max cycle count], + * with "max cycle count" == cs->mask+1. + * + * This allows conversion of cycle counter values which were generated + * in the past. + */ +extern u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp); + +#endif diff --git a/include/linux/types.h b/include/linux/types.h index a0bb7048687f..62323825cff9 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -213,5 +213,8 @@ struct callback_head { }; #define rcu_head callback_head +/* clocksource cycle base type */ +typedef u64 cycle_t; + #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ -- cgit v1.2.3 From 796c1efd6fa0ed696d550b68f4410ab1a1749d01 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 21 Dec 2014 19:46:57 +0100 Subject: timecounter: provide a helper function to shift the time. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some PTP Hardware Clock drivers use a struct timecounter to represent their clock. To adjust the time by a given offset, these drivers all perform a two step read/write of their timecounter. However, it is better and simpler just to adjust the offset in one step. This patch introduces a little routine to help drivers implement the adjtime method. Suggested-by: Janusz Użycki Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/timecounter.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index 146f07a6651b..af3dfa4e90f0 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -78,6 +78,15 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, return ret; } +/** + * timecounter_adjtime - Shifts the time of the clock. + * @delta: Desired change in nanoseconds. + */ +static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) +{ + tc->nsec += delta; +} + /** * timecounter_init - initialize a time counter * @tc: Pointer to time counter which is to be initialized/reset -- cgit v1.2.3 From 2eebdde6528a722fbf8e2cffcf7aa52cbb4c2de0 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Sun, 21 Dec 2014 19:47:06 +0100 Subject: timecounter: keep track of accumulated fractional nanoseconds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current timecounter implementation will drop a variable amount of resolution, depending on the magnitude of the time delta. In other words, reading the clock too often or too close to a time stamp conversion will introduce errors into the time values. This patch fixes the issue by introducing a fractional nanosecond field that accumulates the low order bits. Reported-by: Janusz Użycki Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/timecounter.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index af3dfa4e90f0..74f45496e6d1 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -55,27 +55,32 @@ struct cyclecounter { * @cycle_last: most recent cycle counter value seen by * timecounter_read() * @nsec: continuously increasing count + * @mask: bit mask for maintaining the 'frac' field + * @frac: accumulated fractional nanoseconds */ struct timecounter { const struct cyclecounter *cc; cycle_t cycle_last; u64 nsec; + u64 mask; + u64 frac; }; /** * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds * @cc: Pointer to cycle counter. * @cycles: Cycles - * - * XXX - This could use some mult_lxl_ll() asm optimization. Same code - * as in cyc2ns, but with unsigned result. + * @mask: bit mask for maintaining the 'frac' field + * @frac: pointer to storage for the fractional nanoseconds. */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, - cycle_t cycles) + cycle_t cycles, u64 mask, u64 *frac) { - u64 ret = (u64)cycles; - ret = (ret * cc->mult) >> cc->shift; - return ret; + u64 ns = (u64) cycles; + + ns = (ns * cc->mult) + *frac; + *frac = ns & mask; + return ns >> cc->shift; } /** -- cgit v1.2.3 From dd450777990baae668c1143064f2f234dbab1b9b Mon Sep 17 00:00:00 2001 From: Dmitry Eremin-Solenikov Date: Wed, 24 Dec 2014 01:14:14 +0300 Subject: arm: sa1100: move irda header to linux/platform_data In the end asm/mach/irda.h header is not used by anybody except sa1100. Move the header to the platform data includes dir and rename it to irda-sa11x0.h. Signed-off-by: Dmitry Eremin-Solenikov Signed-off-by: David S. Miller --- include/linux/platform_data/irda-sa11x0.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/platform_data/irda-sa11x0.h (limited to 'include/linux') diff --git a/include/linux/platform_data/irda-sa11x0.h b/include/linux/platform_data/irda-sa11x0.h new file mode 100644 index 000000000000..38f77b5e56cf --- /dev/null +++ b/include/linux/platform_data/irda-sa11x0.h @@ -0,0 +1,20 @@ +/* + * arch/arm/include/asm/mach/irda.h + * + * Copyright (C) 2004 Russell King. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#ifndef __ASM_ARM_MACH_IRDA_H +#define __ASM_ARM_MACH_IRDA_H + +struct irda_platform_data { + int (*startup)(struct device *); + void (*shutdown)(struct device *); + int (*set_power)(struct device *, unsigned int state); + void (*set_speed)(struct device *, unsigned int speed); +}; + +#endif -- cgit v1.2.3 From de40ed31b3c577cefd7b54972365a272ecbe9dd6 Mon Sep 17 00:00:00 2001 From: Nimrod Andy Date: Wed, 24 Dec 2014 17:30:39 +0800 Subject: net: fec: add Wake-on-LAN support Support for Wake-on-LAN using Magic Packet. ENET IP supports sleep mode in low power status, when system enter suspend status, Magic packet can wake up system even if all SOC clocks are gate. The patch doing below things: - flagging the device as a wakeup source for the system, as well as its Wake-on-LAN interrupt - prepare the hardware for entering WoL mode - add standard ethtool WOL interface - enable the ENET interrupt to wake us Tested on i.MX6q/dl sabresd, sabreauto boards, i.MX6SX arm2 boards. Signed-off-by: Fugang Duan Signed-off-by: David S. Miller --- include/linux/fec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fec.h b/include/linux/fec.h index bcff455d1d53..1454a503622d 100644 --- a/include/linux/fec.h +++ b/include/linux/fec.h @@ -19,6 +19,7 @@ struct fec_platform_data { phy_interface_t phy; unsigned char mac[ETH_ALEN]; + void (*sleep_mode_enable)(int enabled); }; #endif -- cgit v1.2.3 From 9b174d88c257150562b0101fcc6cb6c3cb74275c Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Tue, 30 Dec 2014 19:10:15 -0800 Subject: net: Add Transparent Ethernet Bridging GRO support. Currently the only tunnel protocol that supports GRO with encapsulated Ethernet is VXLAN. This pulls out the Ethernet code into a proper layer so that it can be used by other tunnel protocols such as GRE and Geneve. Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 41c891d05f04..1d869d185a0d 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -52,6 +52,10 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) +struct sk_buff **eth_gro_receive(struct sk_buff **head, + struct sk_buff *skb); +int eth_gro_complete(struct sk_buff *skb, int nhoff); + /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; -- cgit v1.2.3 From 1891172aa5c32f08ad9931b794edd71e91a4a527 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Fri, 2 Jan 2015 20:22:03 +0100 Subject: timecounter: provide a macro to initialize the cyclecounter mask field. There is no need for users of the timecounter/cyclecounter code to include clocksource.h just for a single macro. Signed-off-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/timecounter.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index 74f45496e6d1..4382035a75bb 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -19,6 +19,9 @@ #include +/* simplify initialization of mask field */ +#define CYCLECOUNTER_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) + /** * struct cyclecounter - hardware abstraction for a free running counter * Provides completely state-free accessors to the underlying hardware. @@ -29,7 +32,7 @@ * @read: returns the current cycle value * @mask: bitmask for two's complement * subtraction of non 64 bit counters, - * see CLOCKSOURCE_MASK() helper macro + * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) */ -- cgit v1.2.3 From c761d96b079e99d106fa4064e730ef7d0f312f9d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 2 Jan 2015 15:05:12 -0700 Subject: blk-mq: export blk_mq_freeze_queue() Commit b4c6a028774b exported the start and unfreeze, but we need the regular blk_mq_freeze_queue() for the loop conversion. Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 3b43f509432c..5b6500c77ed2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -212,6 +212,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn, void *priv); +void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); -- cgit v1.2.3 From 8d24c0b43125ec26cc80e04588477a9a2afc025c Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:14 +0100 Subject: rhashtable: Do hashing inside of rhashtable_lookup_compare() Hash the key inside of rhashtable_lookup_compare() like rhashtable_lookup() does. This allows to simplify the hashing functions and keep them private. Signed-off-by: Thomas Graf Cc: netfilter-devel@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index b93fd89b2e5e..1b51221c6bbd 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -96,9 +96,6 @@ static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht) int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); -u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len); -u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr); - void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj, @@ -111,7 +108,7 @@ int rhashtable_expand(struct rhashtable *ht); int rhashtable_shrink(struct rhashtable *ht); void *rhashtable_lookup(const struct rhashtable *ht, const void *key); -void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash, +void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key, bool (*compare)(void *, void *), void *arg); void rhashtable_destroy(const struct rhashtable *ht); -- cgit v1.2.3 From 88d6ed15acff1cb44b1d1f3c0a393b7f7744957a Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:16 +0100 Subject: rhashtable: Convert bucket iterators to take table and index This patch is in preparation to introduce per bucket spinlocks. It extends all iterator macros to take the bucket table and bucket index. It also introduces a new rht_dereference_bucket() to handle protected accesses to buckets. It introduces a barrier() to the RCU iterators to the prevent the compiler from caching the first element. The lockdep verifier is introduced as stub which always succeeds and properly implement in the next patch when the locks are introduced. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 173 ++++++++++++++++++++++++++++++--------------- 1 file changed, 116 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 1b51221c6bbd..b54e24a08806 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -87,11 +87,18 @@ struct rhashtable { #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(const struct rhashtable *ht); +int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); #else static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht) { return 1; } + +static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, + u32 hash) +{ + return 1; +} #endif /* CONFIG_PROVE_LOCKING */ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); @@ -119,92 +126,144 @@ void rhashtable_destroy(const struct rhashtable *ht); #define rht_dereference_rcu(p, ht) \ rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht)) -#define rht_entry(ptr, type, member) container_of(ptr, type, member) -#define rht_entry_safe(ptr, type, member) \ -({ \ - typeof(ptr) __ptr = (ptr); \ - __ptr ? rht_entry(__ptr, type, member) : NULL; \ -}) +#define rht_dereference_bucket(p, tbl, hash) \ + rcu_dereference_protected(p, lockdep_rht_bucket_is_held(tbl, hash)) -#define rht_next_entry_safe(pos, ht, member) \ -({ \ - pos ? rht_entry_safe(rht_dereference((pos)->member.next, ht), \ - typeof(*(pos)), member) : NULL; \ -}) +#define rht_dereference_bucket_rcu(p, tbl, hash) \ + rcu_dereference_check(p, lockdep_rht_bucket_is_held(tbl, hash)) + +#define rht_entry(tpos, pos, member) \ + ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) /** - * rht_for_each - iterate over hash chain - * @pos: &struct rhash_head to use as a loop cursor. - * @head: head of the hash chain (struct rhash_head *) - * @ht: pointer to your struct rhashtable + * rht_for_each_continue - continue iterating over hash chain + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the previous &struct rhash_head to continue from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index */ -#define rht_for_each(pos, head, ht) \ - for (pos = rht_dereference(head, ht); \ +#define rht_for_each_continue(pos, head, tbl, hash) \ + for (pos = rht_dereference_bucket(head, tbl, hash); \ pos; \ - pos = rht_dereference((pos)->next, ht)) + pos = rht_dereference_bucket((pos)->next, tbl, hash)) + +/** + * rht_for_each - iterate over hash chain + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + */ +#define rht_for_each(pos, tbl, hash) \ + rht_for_each_continue(pos, (tbl)->buckets[hash], tbl, hash) + +/** + * rht_for_each_entry_continue - continue iterating over hash chain + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the previous &struct rhash_head to continue from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + */ +#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member) \ + for (pos = rht_dereference_bucket(head, tbl, hash); \ + pos && rht_entry(tpos, pos, member); \ + pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** * rht_for_each_entry - iterate over hash chain of given type - * @pos: type * to use as a loop cursor. - * @head: head of the hash chain (struct rhash_head *) - * @ht: pointer to your struct rhashtable - * @member: name of the rhash_head within the hashable struct. + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. */ -#define rht_for_each_entry(pos, head, ht, member) \ - for (pos = rht_entry_safe(rht_dereference(head, ht), \ - typeof(*(pos)), member); \ - pos; \ - pos = rht_next_entry_safe(pos, ht, member)) +#define rht_for_each_entry(tpos, pos, tbl, hash, member) \ + rht_for_each_entry_continue(tpos, pos, (tbl)->buckets[hash], \ + tbl, hash, member) /** * rht_for_each_entry_safe - safely iterate over hash chain of given type - * @pos: type * to use as a loop cursor. - * @n: type * to use for temporary next object storage - * @head: head of the hash chain (struct rhash_head *) - * @ht: pointer to your struct rhashtable - * @member: name of the rhash_head within the hashable struct. + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @next: the &struct rhash_head to use as next in loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive allows for the looped code to * remove the loop cursor from the list. */ -#define rht_for_each_entry_safe(pos, n, head, ht, member) \ - for (pos = rht_entry_safe(rht_dereference(head, ht), \ - typeof(*(pos)), member), \ - n = rht_next_entry_safe(pos, ht, member); \ - pos; \ - pos = n, \ - n = rht_next_entry_safe(pos, ht, member)) +#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ + for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \ + next = pos ? rht_dereference_bucket(pos->next, tbl, hash) \ + : NULL; \ + pos && rht_entry(tpos, pos, member); \ + pos = next) + +/** + * rht_for_each_rcu_continue - continue iterating over rcu hash chain + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the previous &struct rhash_head to continue from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_rcu_continue(pos, head, tbl, hash) \ + for (({barrier(); }), \ + pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos; \ + pos = rcu_dereference_raw(pos->next)) /** * rht_for_each_rcu - iterate over rcu hash chain - * @pos: &struct rhash_head to use as a loop cursor. - * @head: head of the hash chain (struct rhash_head *) - * @ht: pointer to your struct rhashtable + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index * * This hash chain list-traversal primitive may safely run concurrently with - * the _rcu fkht mutation primitives such as rht_insert() as long as the + * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_rcu(pos, head, ht) \ - for (pos = rht_dereference_rcu(head, ht); \ - pos; \ - pos = rht_dereference_rcu((pos)->next, ht)) +#define rht_for_each_rcu(pos, tbl, hash) \ + rht_for_each_rcu_continue(pos, (tbl)->buckets[hash], tbl, hash) + +/** + * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the previous &struct rhash_head to continue from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \ + for (({barrier(); }), \ + pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos && rht_entry(tpos, pos, member); \ + pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) /** * rht_for_each_entry_rcu - iterate over rcu hash chain of given type - * @pos: type * to use as a loop cursor. - * @head: head of the hash chain (struct rhash_head *) - * @member: name of the rhash_head within the hashable struct. + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. * * This hash chain list-traversal primitive may safely run concurrently with - * the _rcu fkht mutation primitives such as rht_insert() as long as the + * the _rcu mutation primitives such as rhashtable_insert() as long as the * traversal is guarded by rcu_read_lock(). */ -#define rht_for_each_entry_rcu(pos, head, member) \ - for (pos = rht_entry_safe(rcu_dereference_raw(head), \ - typeof(*(pos)), member); \ - pos; \ - pos = rht_entry_safe(rcu_dereference_raw((pos)->member.next), \ - typeof(*(pos)), member)) +#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ + rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ + tbl, hash, member) #endif /* _LINUX_RHASHTABLE_H */ -- cgit v1.2.3 From 897362e446436d245972e72c6bc5b33bd7a5c659 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:18 +0100 Subject: nft_hash: Remove rhashtable_remove_pprev() The removal function of nft_hash currently stores a reference to the previous element during lookup which is used to optimize removal later on. This was possible because a lock is held throughout calling rhashtable_lookup() and rhashtable_remove(). With the introdution of deferred table resizing in parallel to lookups and insertions, the nftables lock will no longer synchronize all table mutations and the stored pprev may become invalid. Removing this optimization makes removal slightly more expensive on average but allows taking the resize cost out of the insert and remove path. Signed-off-by: Thomas Graf Cc: netfilter-devel@vger.kernel.org Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index b54e24a08806..f624d4b5045f 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -105,8 +105,6 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); -void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj, - struct rhash_head __rcu **pprev); bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size); bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size); -- cgit v1.2.3 From 113948d841e8d78039e5dbbb5248f5b73e99eafa Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:19 +0100 Subject: spinlock: Add spin_lock_bh_nested() Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/spinlock.h | 8 ++++++++ include/linux/spinlock_api_smp.h | 2 ++ include/linux/spinlock_api_up.h | 1 + 3 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 262ba4ef9a8e..3e18379dfa6f 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -190,6 +190,8 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) +# define raw_spin_lock_bh_nested(lock, subclass) \ + _raw_spin_lock_bh_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ @@ -205,6 +207,7 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) +# define raw_spin_lock_bh_nested(lock, subclass) _raw_spin_lock_bh(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) @@ -324,6 +327,11 @@ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) +#define spin_lock_bh_nested(lock, subclass) \ +do { \ + raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\ +} while (0) + #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 42dfab89e740..5344268e6e62 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -22,6 +22,8 @@ int in_lock_functions(unsigned long addr); void __lockfunc _raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) __acquires(lock); +void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass) + __acquires(lock); void __lockfunc _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map) __acquires(lock); diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d0d188861ad6..d3afef9d8dbe 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -57,6 +57,7 @@ #define _raw_spin_lock(lock) __LOCK(lock) #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) +#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) -- cgit v1.2.3 From 97defe1ecf868b8127f8e62395499d6a06e4c4b1 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:20 +0100 Subject: rhashtable: Per bucket locks & deferred expansion/shrinking Introduces an array of spinlocks to protect bucket mutations. The number of spinlocks per CPU is configurable and selected based on the hash of the bucket. This allows for parallel insertions and removals of entries which do not share a lock. The patch also defers expansion and shrinking to a worker queue which allows insertion and removal from atomic context. Insertions and deletions may occur in parallel to it and are only held up briefly while the particular bucket is linked or unzipped. Mutations of the bucket table pointer is protected by a new mutex, read access is RCU protected. In the event of an expansion or shrinking, the new bucket table allocated is exposed as a so called future table as soon as the resize process starts. Lookups, deletions, and insertions will briefly use both tables. The future table becomes the main table after an RCU grace period and initial linking of the old to the new table was performed. Optimization of the chains to make use of the new number of buckets follows only the new table is in use. The side effect of this is that during that RCU grace period, a bucket traversal using any rht_for_each() variant on the main table will not see any insertions performed during the RCU grace period which would at that point land in the future table. The lookup will see them as it searches both tables if needed. Having multiple insertions and removals occur in parallel requires nelems to become an atomic counter. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index f624d4b5045f..a1688f0a6193 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #define _LINUX_RHASHTABLE_H #include +#include struct rhash_head { struct rhash_head __rcu *next; @@ -26,8 +27,17 @@ struct rhash_head { #define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL) +/** + * struct bucket_table - Table of hash buckets + * @size: Number of hash buckets + * @locks_mask: Mask to apply before accessing locks[] + * @locks: Array of spinlocks protecting individual buckets + * @buckets: size * hash buckets + */ struct bucket_table { size_t size; + unsigned int locks_mask; + spinlock_t *locks; struct rhash_head __rcu *buckets[]; }; @@ -45,11 +55,11 @@ struct rhashtable; * @hash_rnd: Seed to use while hashing * @max_shift: Maximum number of shifts while expanding * @min_shift: Minimum number of shifts while shrinking + * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Function to hash key * @obj_hashfn: Function to hash object * @grow_decision: If defined, may return true if table should expand * @shrink_decision: If defined, may return true if table should shrink - * @mutex_is_held: Must return true if protecting mutex is held */ struct rhashtable_params { size_t nelem_hint; @@ -59,37 +69,42 @@ struct rhashtable_params { u32 hash_rnd; size_t max_shift; size_t min_shift; + size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; bool (*grow_decision)(const struct rhashtable *ht, size_t new_size); bool (*shrink_decision)(const struct rhashtable *ht, size_t new_size); -#ifdef CONFIG_PROVE_LOCKING - int (*mutex_is_held)(void *parent); - void *parent; -#endif }; /** * struct rhashtable - Hash table handle * @tbl: Bucket table + * @future_tbl: Table under construction during expansion/shrinking * @nelems: Number of elements in table * @shift: Current size (1 << shift) * @p: Configuration parameters + * @run_work: Deferred worker to expand/shrink asynchronously + * @mutex: Mutex to protect current/future table swapping + * @being_destroyed: True if table is set up for destruction */ struct rhashtable { struct bucket_table __rcu *tbl; - size_t nelems; + struct bucket_table __rcu *future_tbl; + atomic_t nelems; size_t shift; struct rhashtable_params p; + struct delayed_work run_work; + struct mutex mutex; + bool being_destroyed; }; #ifdef CONFIG_PROVE_LOCKING -int lockdep_rht_mutex_is_held(const struct rhashtable *ht); +int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); #else -static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht) +static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht) { return 1; } @@ -112,11 +127,11 @@ bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size); int rhashtable_expand(struct rhashtable *ht); int rhashtable_shrink(struct rhashtable *ht); -void *rhashtable_lookup(const struct rhashtable *ht, const void *key); -void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key, +void *rhashtable_lookup(struct rhashtable *ht, const void *key); +void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, bool (*compare)(void *, void *), void *arg); -void rhashtable_destroy(const struct rhashtable *ht); +void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht)) -- cgit v1.2.3 From f89bd6f87a53ce5a7d60662429591ebac2745c10 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 2 Jan 2015 23:00:21 +0100 Subject: rhashtable: Supports for nulls marker In order to allow for wider usage of rhashtable, use a special nulls marker to terminate each chain. The reason for not using the existing nulls_list is that the prev pointer usage would not be valid as entries can be linked in two different buckets at the same time. The 4 nulls base bits can be set through the rhashtable_params structure like this: struct rhashtable_params params = { [...] .nulls_base = (1U << RHT_BASE_SHIFT), }; This reduces the hash length from 32 bits to 27 bits. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/list_nulls.h | 3 ++- include/linux/rhashtable.h | 57 ++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 49 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 5d10ae364b5e..e8c300e06438 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -21,8 +21,9 @@ struct hlist_nulls_head { struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; +#define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ - ((ptr)->first = (struct hlist_nulls_node *) (1UL | (((long)nulls) << 1))) + ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) /** diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index a1688f0a6193..de7cac753b09 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -18,15 +18,32 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H -#include +#include #include +/* + * The end of the chain is marked with a special nulls marks which has + * the following format: + * + * +-------+-----------------------------------------------------+-+ + * | Base | Hash |1| + * +-------+-----------------------------------------------------+-+ + * + * Base (4 bits) : Reserved to distinguish between multiple tables. + * Specified via &struct rhashtable_params.nulls_base. + * Hash (27 bits): Full hash (unmasked) of first element added to bucket + * 1 (1 bit) : Nulls marker (always set) + * + * The remaining bits of the next pointer remain unused for now. + */ +#define RHT_BASE_BITS 4 +#define RHT_HASH_BITS 27 +#define RHT_BASE_SHIFT RHT_HASH_BITS + struct rhash_head { struct rhash_head __rcu *next; }; -#define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL) - /** * struct bucket_table - Table of hash buckets * @size: Number of hash buckets @@ -55,6 +72,7 @@ struct rhashtable; * @hash_rnd: Seed to use while hashing * @max_shift: Maximum number of shifts while expanding * @min_shift: Minimum number of shifts while shrinking + * @nulls_base: Base value to generate nulls marker * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Function to hash key * @obj_hashfn: Function to hash object @@ -69,6 +87,7 @@ struct rhashtable_params { u32 hash_rnd; size_t max_shift; size_t min_shift; + u32 nulls_base; size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; @@ -100,6 +119,24 @@ struct rhashtable { bool being_destroyed; }; +static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) +{ + return NULLS_MARKER(ht->p.nulls_base + hash); +} + +#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ + ((ptr) = (typeof(ptr)) rht_marker(ht, hash)) + +static inline bool rht_is_a_nulls(const struct rhash_head *ptr) +{ + return ((unsigned long) ptr & 1); +} + +static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr) +{ + return ((unsigned long) ptr) >> 1; +} + #ifdef CONFIG_PROVE_LOCKING int lockdep_rht_mutex_is_held(struct rhashtable *ht); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); @@ -157,7 +194,7 @@ void rhashtable_destroy(struct rhashtable *ht); */ #define rht_for_each_continue(pos, head, tbl, hash) \ for (pos = rht_dereference_bucket(head, tbl, hash); \ - pos; \ + !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** @@ -180,7 +217,7 @@ void rhashtable_destroy(struct rhashtable *ht); */ #define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member) \ for (pos = rht_dereference_bucket(head, tbl, hash); \ - pos && rht_entry(tpos, pos, member); \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) /** @@ -209,9 +246,9 @@ void rhashtable_destroy(struct rhashtable *ht); */ #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \ - next = pos ? rht_dereference_bucket(pos->next, tbl, hash) \ - : NULL; \ - pos && rht_entry(tpos, pos, member); \ + next = !rht_is_a_nulls(pos) ? \ + rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = next) /** @@ -228,7 +265,7 @@ void rhashtable_destroy(struct rhashtable *ht); #define rht_for_each_rcu_continue(pos, head, tbl, hash) \ for (({barrier(); }), \ pos = rht_dereference_bucket_rcu(head, tbl, hash); \ - pos; \ + !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) /** @@ -260,7 +297,7 @@ void rhashtable_destroy(struct rhashtable *ht); #define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ pos = rht_dereference_bucket_rcu(head, tbl, hash); \ - pos && rht_entry(tpos, pos, member); \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) /** -- cgit v1.2.3 From 86b35b64ed7b6b38305dee67a0f2ddff2ca5455d Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Sun, 4 Jan 2015 15:25:09 +0800 Subject: rhashtable: fix missing header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixup below build error: include/linux/rhashtable.h: At top level: include/linux/rhashtable.h:118:34: error: field ‘mutex’ has incomplete type Signed-off-by: Ying Xue Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index de7cac753b09..de1459c74c4d 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -20,6 +20,7 @@ #include #include +#include /* * The end of the chain is marked with a special nulls marks which has -- cgit v1.2.3 From a3449ded128d037e6b2bd7a59b0741de56506066 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Sun, 4 Jan 2015 15:24:35 +0800 Subject: list_nulls: fix missing header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixup below build error: include/linux/list_nulls.h: In function ‘hlist_nulls_del’: include/linux/list_nulls.h:84:13: error: ‘LIST_POISON2’ undeclared (first use in this function) Signed-off-by: Ying Xue Signed-off-by: David S. Miller --- include/linux/list_nulls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index e8c300e06438..f266661d2666 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -1,6 +1,9 @@ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H +#include +#include + /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. -- cgit v1.2.3 From 224d019c4fbba242041e9b25a926ba873b7da1e2 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 5 Jan 2015 13:56:14 -0800 Subject: ip: Move checksum convert defines to inet Move convert_csum from udp_sock to inet_sock. This allows the possibility that we can use convert checksum for different types of sockets and also allows convert checksum to be enabled from inet layer (what we'll want to do when enabling IP_CHECKSUM cmsg). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/udp.h | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index ee3277593222..247cfdcc4b08 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -49,11 +49,7 @@ struct udp_sock { unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - convert_csum:1;/* On receive, convert checksum - * unnecessary to checksum complete - * if possible. - */ + no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -102,16 +98,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk) return udp_sk(sk)->no_check6_rx; } -static inline void udp_set_convert_csum(struct sock *sk, bool val) -{ - udp_sk(sk)->convert_csum = val; -} - -static inline bool udp_get_convert_csum(struct sock *sk) -{ - return udp_sk(sk)->convert_csum; -} - #define udp_portaddr_for_each_entry(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node) -- cgit v1.2.3 From 6810e4a394f9d781050107529b8d1465c00b7b13 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 10:26:10 -0500 Subject: percpu_ref: remove unnecessary ACCESS_ONCE() in percpu_ref_tryget_live() __ref_is_percpu() needs the implied ACCESS_ONCE() in lockless_dereference() on @ref->percpu_count_ptr because the value is tested for !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then used as a pointer. If the compiler generates a separate fetch when using it as a pointer, __PERCPU_REF_ATOMIC may be set in between contaminating the pointer value. percpu_ref_tryget_live() also uses ACCESS_ONCE() to test __PERCPU_REF_DEAD; however, there's no reason for this. I just copied ACCESS_ONCE() usage blindly from __ref_is_percpu(). All it does is confusing people trying to understand what's going on. This patch removes the unnecessary ACCESS_ONCE() usage from percpu_ref_tryget_live() and adds a comment explaining why __ref_is_percpu() needs it. Signed-off-by: Tejun Heo Cc: Kent Overstreet --- include/linux/percpu-refcount.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b4337646388b..6a7a670366ab 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -128,8 +128,22 @@ static inline void percpu_ref_kill(struct percpu_ref *ref) static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { - /* paired with smp_store_release() in percpu_ref_reinit() */ - unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr); + unsigned long percpu_ptr; + + /* + * The value of @ref->percpu_count_ptr is tested for + * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then + * used as a pointer. If the compiler generates a separate fetch + * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in + * between contaminating the pointer value, meaning that + * ACCESS_ONCE() is required when fetching it. + * + * Also, we need a data dependency barrier to be paired with + * smp_store_release() in __percpu_ref_switch_to_percpu(). + * + * Use lockless deref which contains both. + */ + percpu_ptr = lockless_dereference(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, @@ -233,7 +247,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; - } else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) { + } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->count); } -- cgit v1.2.3 From 4c907baf36d8339f393bb576d0bab29194d0e6ad Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 10:26:10 -0500 Subject: percpu_ref: implement percpu_ref_is_dying() Implement percpu_ref_is_dying() which tests whether the ref is dying or dead. This is useful to determine the current state when a percpu_ref is used as a cyclic on/off switch via kill and reinit. Signed-off-by: Tejun Heo Cc: Kent Overstreet --- include/linux/percpu-refcount.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 6a7a670366ab..12c9b485beb7 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -294,6 +294,20 @@ static inline void percpu_ref_put(struct percpu_ref *ref) percpu_ref_put_many(ref, 1); } +/** + * percpu_ref_is_dying - test whether a percpu refcount is dying or dead + * @ref: percpu_ref to test + * + * Returns %true if @ref is dying or dead. + * + * This function is safe to call as long as @ref is between init and exit + * and the caller is responsible for synchronizing against state changes. + */ +static inline bool percpu_ref_is_dying(struct percpu_ref *ref) +{ + return ref->percpu_count_ptr & __PERCPU_REF_DEAD; +} + /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test -- cgit v1.2.3 From 24dab7a7b3534ef40ecec20cfd7fb3ad99d9ff33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 12:02:46 -0500 Subject: cgroup: reorder SUBSYS(blkio) in cgroup_subsys.h The scheduled cgroup writeback support requires blkio to be initialized before memcg as memcg needs to provide certain blkcg related functionalities. Relocate blkio so that it's right above memory. Signed-off-by: Tejun Heo --- include/linux/cgroup_subsys.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 98c4f9b12b03..e4a96fb14403 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -15,6 +15,10 @@ SUBSYS(cpu) SUBSYS(cpuacct) #endif +#if IS_ENABLED(CONFIG_BLK_CGROUP) +SUBSYS(blkio) +#endif + #if IS_ENABLED(CONFIG_MEMCG) SUBSYS(memory) #endif @@ -31,10 +35,6 @@ SUBSYS(freezer) SUBSYS(net_cls) #endif -#if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) -#endif - #if IS_ENABLED(CONFIG_CGROUP_PERF) SUBSYS(perf_event) #endif -- cgit v1.2.3 From f3ba53802eff25e3eedb60d7afe5262710e20bd5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Jan 2015 12:02:46 -0500 Subject: cgroup: add dummy css_put() for !CONFIG_CGROUPS This will later be depended upon by the scheduled cgroup writeback support. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index da0dae0600e6..b9cb94c3102a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -943,6 +943,8 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, #else /* !CONFIG_CGROUPS */ +struct cgroup_subsys_state; + static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_fork(struct task_struct *p) {} @@ -955,6 +957,8 @@ static inline int cgroupstats_build(struct cgroupstats *stats, return -EINVAL; } +static inline void css_put(struct cgroup_subsys_state *css) {} + /* No cgroups - nothing to do */ static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) -- cgit v1.2.3 From 536fa402221f09633e7c5801b327055ab716a363 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 5 Sep 2014 11:14:48 -0700 Subject: compiler: Allow 1- and 2-byte smp_load_acquire() and smp_store_release() CPUs without single-byte and double-byte loads and stores place some "interesting" requirements on concurrent code. For example (adapted from Peter Hurley's test code), suppose we have the following structure: struct foo { spinlock_t lock1; spinlock_t lock2; char a; /* Protected by lock1. */ char b; /* Protected by lock2. */ }; struct foo *foop; Of course, it is common (and good) practice to place data protected by different locks in separate cache lines. However, if the locks are rarely acquired (for example, only in rare error cases), and there are a great many instances of the data structure, then memory footprint can trump false-sharing concerns, so that it can be better to place them in the same cache cache line as above. But if the CPU does not support single-byte loads and stores, a store to foop->a will do a non-atomic read-modify-write operation on foop->b, which will come as a nasty surprise to someone holding foop->lock2. So we now require CPUs to support single-byte and double-byte loads and stores. Therefore, this commit adjusts the definition of __native_word() to allow these sizes to be used by smp_load_acquire() and smp_store_release(). Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a1c81f80978e..49811cdddaa5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -385,7 +385,7 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int /* Is this type a native word size -- useful for atomic operations */ #ifndef __native_word -# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) +# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) #endif /* Compile time object size, -1 for unknown */ -- cgit v1.2.3 From ac59853c06993a442e8060bc19040b2ca3025aec Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Thu, 13 Nov 2014 14:24:14 -0500 Subject: rcupdate: Replace smp_read_barrier_depends() with lockless_dereference() Recently lockless_dereference() was added which can be used in place of hard-coding smp_read_barrier_depends(). The following PATCH makes the change. Signed-off-by: Pranith Kumar Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ed4f5939a452..386ba288084a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -582,11 +582,11 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_check(p, c, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ @@ -603,10 +603,10 @@ static inline void rcu_preempt_sleep_check(void) }) #define __rcu_dereference_index_check(p, c) \ ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ + /* Dependency order vs. p above. */ \ + typeof(p) _________p1 = lockless_dereference(p); \ rcu_lockdep_assert(c, \ "suspicious rcu_dereference_index_check() usage"); \ - smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3 From f520c98e3e5212d8c282a86d9b7697dd70326192 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 12 Dec 2014 09:36:14 +0800 Subject: rculist: Fix sparse warning This fixes the following sparse warnings: make C=1 CF=-D__CHECK_ENDIAN__ net/ipv6/addrconf.o net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces) To silence these spare complaints, an RCU annotation should be added to "next" pointer of hlist_node structure through hlist_next_rcu() macro when iterating over a hlist with hlist_for_each_entry_continue_rcu_bh(). By the way, this commit also resolves the same error appearing in hlist_for_each_entry_continue_rcu(). Signed-off-by: Ying Xue Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 529bc946f450..a18b16f1dc0e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point @@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n, * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ - for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member); \ + for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member); \ pos; \ - pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\ - typeof(*(pos)), member)) + pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ + &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point -- cgit v1.2.3 From a5c198f4f7da6cc48116ca239c59c9f44b753364 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 23 Nov 2014 20:30:06 -0800 Subject: rcu: Expand SRCU ->completed to 64 bits When rcutorture used only the low-order 32 bits of the grace-period number, it was not a problem for SRCU to use a 32-bit completed field. However, rcutorture now uses the full 64 bits on 64-bit systems, so this commit converts SRCU's ->completed field to unsigned long so as to provide 64 bits on 64-bit systems. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index a2783cb5d275..ef923dd96249 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -45,7 +45,7 @@ struct rcu_batch { #define RCU_BATCH_INIT(name) { NULL, &(name.head) } struct srcu_struct { - unsigned completed; + unsigned long completed; struct srcu_struct_array __percpu *per_cpu_ref; spinlock_t queue_lock; /* protect ->batch_queue, ->running */ bool running; @@ -135,7 +135,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); -long srcu_batches_completed(struct srcu_struct *sp); +unsigned long srcu_batches_completed(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 9735af5c78599703be633c057af3faee26482028 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 26 Nov 2014 10:42:50 -0800 Subject: rcu: Combine DEFINE_SRCU() and DEFINE_STATIC_SRCU() The DEFINE_SRCU() and DEFINE_STATIC_SRCU() definitions are quite similar, so this commit combines them, saving a bit of code and removing redundancy. Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index ef923dd96249..9cfd9623fb03 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work); * define and init a srcu struct at build time. * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it. */ -#define DEFINE_SRCU(name) \ +#define __DEFINE_SRCU(name, is_static) \ static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - struct srcu_struct name = __SRCU_STRUCT_INIT(name); - -#define DEFINE_STATIC_SRCU(name) \ - static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\ - static struct srcu_struct name = __SRCU_STRUCT_INIT(name); + is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name) +#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */) +#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static) /** * call_srcu() - Queue a callback for invocation after an SRCU grace period -- cgit v1.2.3 From 8b3a38daff6f50027039d6979b9eb026907508eb Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Tue, 23 Dec 2014 19:04:23 +0100 Subject: brcmfmac: Add support for bcm43340/1 wireless chipsets This patch adds support for the bcm43340 and bcm43341 wireless chipsets. These two chipsets are identical from wireless parts perspective. As such they use the same firmware image. Cc: Samuel Ortiz Cc: Rob Herring Signed-off-by: John Stultz [arend@broadcom.com: squash to single commit, remove 43341 chipid] Reviewed-by: Pieter-Paul Giesberts Reviewed-by: Hante Meuleman Signed-off-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 0f01fe065424..996807963716 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -24,13 +24,15 @@ * Vendors and devices. Sort key: vendor first, device next. */ #define SDIO_VENDOR_ID_BROADCOM 0x02d0 -#define SDIO_DEVICE_ID_BROADCOM_43143 43143 +#define SDIO_DEVICE_ID_BROADCOM_43143 0xa887 #define SDIO_DEVICE_ID_BROADCOM_43241 0x4324 #define SDIO_DEVICE_ID_BROADCOM_4329 0x4329 #define SDIO_DEVICE_ID_BROADCOM_4330 0x4330 #define SDIO_DEVICE_ID_BROADCOM_4334 0x4334 +#define SDIO_DEVICE_ID_BROADCOM_43340 0xa94c +#define SDIO_DEVICE_ID_BROADCOM_43341 0xa94d #define SDIO_DEVICE_ID_BROADCOM_4335_4339 0x4335 -#define SDIO_DEVICE_ID_BROADCOM_43362 43362 +#define SDIO_DEVICE_ID_BROADCOM_43362 0xa962 #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_VENDOR_ID_INTEL 0x0089 -- cgit v1.2.3 From 2f4383667d57d1c719070db86b14277277752841 Mon Sep 17 00:00:00 2001 From: Ed Swierk Date: Fri, 2 Jan 2015 17:27:56 -0800 Subject: ethtool: Extend ethtool plugin module eeprom API to phylib This patch extends the ethtool plugin module eeprom API to support cards whose phy support is delegated to a separate driver. The handlers for ETHTOOL_GMODULEINFO and ETHTOOL_GMODULEEEPROM call the module_info and module_eeprom functions if the phy driver provides them; otherwise the handlers call the equivalent ethtool_ops functions provided by network drivers with built-in phy support. Signed-off-by: Ed Swierk Signed-off-by: David S. Miller --- include/linux/phy.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 22af8f8f5802..9c189a1fa3a2 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -565,6 +565,15 @@ struct phy_driver { void (*write_mmd_indirect)(struct phy_device *dev, int ptrad, int devnum, int regnum, u32 val); + /* Get the size and type of the eeprom contained within a plug-in + * module */ + int (*module_info)(struct phy_device *dev, + struct ethtool_modinfo *modinfo); + + /* Get the eeprom information from the plug-in module */ + int (*module_eeprom)(struct phy_device *dev, + struct ethtool_eeprom *ee, u8 *data); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) -- cgit v1.2.3 From 9da7dae94fb8adab5cc5f395640e30736a66e910 Mon Sep 17 00:00:00 2001 From: Valentin Rothberg Date: Tue, 6 Jan 2015 17:29:29 +0100 Subject: workqueue.h: remove loops of single statement macros checkpatch.pl complained about two single statement macros in do while (0) loops. The loops and the trailing semicolons are now removed, which makes checkpatch happy and the two macros consistent with the rest of the file. Signed-off-by: Valentin Rothberg Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index b996e6cde6bb..74db135f9957 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -220,14 +220,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif #define INIT_WORK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 0); \ - } while (0) + __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ - do { \ - __INIT_WORK((_work), (_func), 1); \ - } while (0) + __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ -- cgit v1.2.3 From 548cd3ab54da10f896daa7ca422236847a915734 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bean=20Huo=20=E9=9C=8D=E6=96=8C=E6=96=8C=20=28beanhuo=29?= Date: Wed, 17 Dec 2014 07:35:45 +0000 Subject: mtd: spi-nor: Add quad I/O support for Micron SPI NOR This patch adds code which enables Quad I/O mode on Micron SPI NOR flashes. For Micron SPI NOR flash, enabling or disabling quad I/O protocol can be done By two methods, which are to use EVCR (Enhanced Volatile Configuration Register) and the ENTER QUAD I/O MODE command. There is no difference between these two methods. Unfortunately, for some Micron SPI NOR flashes, there no ENTER Quad I/O command (35h), such as n25q064. But for all current Micron SPI NOR, if it support quad I/O mode, using EVCR definitely be supported. It is a recommended method to enable Quad I/O mode by EVCR, Quad I/O protocol bit 7. When EVCR bit 7 is reset to 0, the SPI NOR flash will operate in quad I/O mode. This patch has been tested on N25Q512A and MT25TL256BAA1ESF. Micron SPI NOR of spi_nor_ids[] table all support this method. Signed-off-by: Bean Huo Acked-by: Marek Vasut Signed-off-by: Brian Norris --- include/linux/mtd/spi-nor.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 63aeccf9ddc8..4720b86ee73d 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -56,6 +56,10 @@ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ +/* Used for Micron flashes only. */ +#define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ +#define SPINOR_OP_WD_EVCR 0x61 /* Write EVCR register */ + /* Status Register bits. */ #define SR_WIP 1 /* Write in progress */ #define SR_WEL 2 /* Write enable latch */ @@ -67,6 +71,9 @@ #define SR_QUAD_EN_MX 0x40 /* Macronix Quad I/O */ +/* Enhanced Volatile Configuration Register bits */ +#define EVCR_QUAD_EN_MICRON 0x80 /* Micron Quad I/O */ + /* Flag Status Register bits */ #define FSR_READY 0x80 -- cgit v1.2.3 From 3efe41be224c4441f2a872a25471a14d85ceb7c6 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 26 Nov 2014 01:01:08 -0800 Subject: mtd: implement common reboot notifier boilerplate cfi_cmdset_000{1,2}.c already implement their own reboot notifiers, and we're going to add one for NAND. Let's put the boilerplate in one place. Signed-off-by: Brian Norris Tested-by: Scott Branden --- include/linux/mtd/mtd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 031ff3a9a0bd..c06f5373d870 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -227,6 +227,7 @@ struct mtd_info { int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs); int (*_suspend) (struct mtd_info *mtd); void (*_resume) (struct mtd_info *mtd); + void (*_reboot) (struct mtd_info *mtd); /* * If the driver is something smart, like UBI, it may need to maintain * its own reference counting. The below functions are only for driver. -- cgit v1.2.3 From 26e022727f5e88c6e5054e14d954425deacbe56a Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 18 Dec 2014 16:02:17 +0100 Subject: efi: Rename efi_guid_unparse to efi_guid_to_str Call it what it does - "unparse" is plain-misleading. Signed-off-by: Borislav Petkov Signed-off-by: Ricardo Neri --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 0949f9c7e872..d762c81e62a8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -844,7 +844,7 @@ efi_guidcmp (efi_guid_t left, efi_guid_t right) } static inline char * -efi_guid_unparse(efi_guid_t *guid, char *out) +efi_guid_to_str(efi_guid_t *guid, char *out) { sprintf(out, "%pUl", guid->b); return out; -- cgit v1.2.3 From 15acabfd02e35e270360fbe0def898e48754b3d6 Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Mon, 5 Jan 2015 12:21:45 +0100 Subject: crypto: aead - add check for presence of auth tag The AEAD decryption operation requires the authentication tag to be present as part of the cipher text buffer. The added check verifies that the caller provides a cipher text with at least the authentication tag. Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- include/linux/crypto.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 9c8776d0ada8..90998348e564 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -1412,6 +1412,9 @@ static inline int crypto_aead_encrypt(struct aead_request *req) */ static inline int crypto_aead_decrypt(struct aead_request *req) { + if (req->cryptlen < crypto_aead_authsize(crypto_aead_reqtfm(req))) + return -EINVAL; + return crypto_aead_crt(crypto_aead_reqtfm(req))->decrypt(req); } -- cgit v1.2.3 From bfa21a0dfe6915dc85953b5d40ea9dae5fdf205f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 5 Jan 2015 12:48:42 +0100 Subject: regulator: Allow parsing custom properties when using simplified DT parsing When drivers use simplified DT parsing method (they provide 'regulator_desc.of_match') they still may want to parse custom properties for some of the regulators. For example some of the regulators support GPIO enable control. Add a driver-supplied callback for such case. This way the regulator core parses common bindings offloading a lot of code from drivers and still custom properties may be used. The callback, called for each parsed regulator, may modify the 'regulator_config' initially passed to regulator_register(). Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 5f1e9ca47417..d4ad5b5a02bb 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -21,6 +21,7 @@ struct regmap; struct regulator_dev; +struct regulator_config; struct regulator_init_data; struct regulator_enable_gpio; @@ -205,6 +206,15 @@ enum regulator_type { * @supply_name: Identifying the regulator supply * @of_match: Name used to identify regulator in DT. * @regulators_node: Name of node containing regulator definitions in DT. + * @of_parse_cb: Optional callback called only if of_match is present. + * Will be called for each regulator parsed from DT, during + * init_data parsing. + * The regulator_config passed as argument to the callback will + * be a copy of config passed to regulator_register, valid only + * for this particular call. Callback may freely change the + * config but it cannot store it for later usage. + * Callback should return 0 on success or negative ERRNO + * indicating failure. * @id: Numerical identifier for the regulator. * @ops: Regulator operations table. * @irq: Interrupt number for the regulator. @@ -251,6 +261,9 @@ struct regulator_desc { const char *supply_name; const char *of_match; const char *regulators_node; + int (*of_parse_cb)(struct device_node *, + const struct regulator_desc *, + struct regulator_config *); int id; bool continuous_voltage_range; unsigned n_voltages; -- cgit v1.2.3 From db30485408326a6f466a843b291b23535f63eda0 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 7 Jan 2015 13:41:54 +0800 Subject: rhashtable: involve rhashtable_lookup_insert routine Involve a new function called rhashtable_lookup_insert() which makes lookup and insertion atomic under bucket lock protection, helping us avoid to introduce an extra lock when we search and insert an object into hash table. Signed-off-by: Ying Xue Signed-off-by: Thomas Graf Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index de1459c74c4d..73c913f31574 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -168,6 +168,7 @@ int rhashtable_shrink(struct rhashtable *ht); void *rhashtable_lookup(struct rhashtable *ht, const void *key); void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, bool (*compare)(void *, void *), void *arg); +bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj); void rhashtable_destroy(struct rhashtable *ht); -- cgit v1.2.3 From c0c09bfdc4150b3918526660768585cd477adf35 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 7 Jan 2015 13:41:56 +0800 Subject: rhashtable: avoid unnecessary wakeup for worker queue Move condition statements of verifying whether hash table size exceeds its maximum threshold or reaches its minimum threshold from resizing functions to resizing decision functions, avoiding unnecessary wakeup for worker queue thread. Signed-off-by: Ying Xue Cc: Thomas Graf Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 73c913f31574..326acd8c2e9f 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -113,7 +113,7 @@ struct rhashtable { struct bucket_table __rcu *tbl; struct bucket_table __rcu *future_tbl; atomic_t nelems; - size_t shift; + atomic_t shift; struct rhashtable_params p; struct delayed_work run_work; struct mutex mutex; -- cgit v1.2.3 From e5a7a72cd51a585b8f1a1e299bf88fff44b94440 Mon Sep 17 00:00:00 2001 From: Robin Gong Date: Fri, 9 Jan 2015 09:57:33 +0800 Subject: regulator: pfuze100-regulator: add pfuze3000 support Add pfuze3000 chip support. Signed-off-by: Robin Gong Signed-off-by: Mark Brown --- include/linux/regulator/pfuze100.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h index 364f7a7c43db..70c6c66c5bcf 100644 --- a/include/linux/regulator/pfuze100.h +++ b/include/linux/regulator/pfuze100.h @@ -49,6 +49,20 @@ #define PFUZE200_VGEN5 11 #define PFUZE200_VGEN6 12 +#define PFUZE3000_SW1A 0 +#define PFUZE3000_SW1B 1 +#define PFUZE3000_SW2 2 +#define PFUZE3000_SW3 3 +#define PFUZE3000_SWBST 4 +#define PFUZE3000_VSNVS 5 +#define PFUZE3000_VREFDDR 6 +#define PFUZE3000_VLDO1 7 +#define PFUZE3000_VLDO2 8 +#define PFUZE3000_VCCSD 9 +#define PFUZE3000_V33 10 +#define PFUZE3000_VLDO3 11 +#define PFUZE3000_VLDO4 12 + struct regulator_init_data; struct pfuze_regulator_platform_data { -- cgit v1.2.3 From ed09dcc8bd7fe0991af7737e675996cbd022f38f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:14 -0800 Subject: ses: close potential registration race The slot and address fields have a small window of instability when userspace can read them before initialization. Separate enclosure_component allocation from registration. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/enclosure.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 9a33c5f7e126..a835d335b924 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -120,8 +120,9 @@ enclosure_register(struct device *, const char *, int, struct enclosure_component_callbacks *); void enclosure_unregister(struct enclosure_device *); struct enclosure_component * -enclosure_component_register(struct enclosure_device *, unsigned int, - enum enclosure_component_type, const char *); +enclosure_component_alloc(struct enclosure_device *, unsigned int, + enum enclosure_component_type, const char *); +int enclosure_component_register(struct enclosure_component *); int enclosure_add_device(struct enclosure_device *enclosure, int component, struct device *dev); int enclosure_remove_device(struct enclosure_device *, struct device *); -- cgit v1.2.3 From 967f7bab0eaaa74d7d01a56d45aa309f78fb87dd Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:16 -0800 Subject: ses: add enclosure logical id Export the NAA logical id for the enclosure. This is optionally available from the sas_transport_class, but it is really a property of the enclosure. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/enclosure.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index a835d335b924..807622b252a4 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -79,6 +79,7 @@ struct enclosure_component_callbacks { int (*set_locate)(struct enclosure_device *, struct enclosure_component *, enum enclosure_component_setting); + int (*show_id)(struct enclosure_device *, char *buf); }; -- cgit v1.2.3 From 921ce7f5786052749a22a75780f5ce1a456bcdc6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 30 Dec 2014 14:46:17 -0800 Subject: ses: add reliable slot attribute The name provided by firmware is in a vendor specific format, publish the slot number to have a reliable mechanism for identifying slots across firmware implementations. If the enclosure does not provide a slot number fallback to the component number which is guaranteed unique, and usually mirrors the slot number. Cleaned up the unused ses_component.desc in the process. Signed-off-by: Dan Williams Signed-off-by: Song Liu Reviewed-by: Jens Axboe Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/enclosure.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 807622b252a4..0f826c14a337 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -92,6 +92,7 @@ struct enclosure_component { int fault; int active; int locate; + int slot; enum enclosure_status status; }; -- cgit v1.2.3 From 08024885a2a3ed432716e9d50046a620a5b2df05 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Tue, 30 Dec 2014 14:46:18 -0800 Subject: ses: Add power_status to SES device slot Add power_status to SES device slot, so we can power on/off the HDDs behind the enclosure. Check firmware status in ses_set_* before sending control pages to firmware. Signed-off-by: Song Liu Acked-by: Dan Williams Reviewed-by: Jens Axboe Cc: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/enclosure.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 0f826c14a337..7be22da321f3 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -79,6 +79,11 @@ struct enclosure_component_callbacks { int (*set_locate)(struct enclosure_device *, struct enclosure_component *, enum enclosure_component_setting); + void (*get_power_status)(struct enclosure_device *, + struct enclosure_component *); + int (*set_power_status)(struct enclosure_device *, + struct enclosure_component *, + int); int (*show_id)(struct enclosure_device *, char *buf); }; @@ -94,6 +99,7 @@ struct enclosure_component { int locate; int slot; enum enclosure_status status; + int power_status; }; struct enclosure_device { -- cgit v1.2.3 From 5efd2ea8c9f4f12916ffc8ba636792ce052f6911 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 5 Dec 2014 15:13:54 +0100 Subject: usb: core: buffer: smallest buffer should start at ARCH_DMA_MINALIGN the following error pops up during "testusb -a -t 10" | musb-hdrc musb-hdrc.1.auto: dma_pool_free buffer-128, f134e000/be842000 (bad dma) hcd_buffer_create() creates a few buffers, the smallest has 32 bytes of size. ARCH_KMALLOC_MINALIGN is set to 64 bytes. This combo results in hcd_buffer_alloc() returning memory which is 32 bytes aligned and it might by identified by buffer_offset() as another buffer. This means the buffer which is on a 32 byte boundary will not get freed, instead it tries to free another buffer with the error message. This patch fixes the issue by creating the smallest DMA buffer with the size of ARCH_KMALLOC_MINALIGN (or 32 in case ARCH_KMALLOC_MINALIGN is smaller). This might be 32, 64 or even 128 bytes. The next three pools will have the size 128, 512 and 2048. In case the smallest pool is 128 bytes then we have only three pools instead of four (and zero the first entry in the array). The last pool size is always 2048 bytes which is the assumed PAGE_SIZE / 2 of 4096. I doubt it makes sense to continue using PAGE_SIZE / 2 where we would end up with 8KiB buffer in case we have 16KiB pages. Instead I think it makes sense to have a common size(s) and extend them if there is need to. There is a BUILD_BUG_ON() now in case someone has a minalign of more than 128 bytes. Cc: stable@vger.kernel.org Signed-off-by: Sebastian Andrzej Siewior Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 086bf13307e6..8968f616e414 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -453,6 +453,7 @@ extern const struct dev_pm_ops usb_hcd_pci_pm_ops; #endif /* CONFIG_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ +void usb_init_pool_max(void); int hcd_buffer_create(struct usb_hcd *hcd); void hcd_buffer_destroy(struct usb_hcd *hcd); -- cgit v1.2.3 From 314b41b16a71ee824f55e2791fcb92997672da37 Mon Sep 17 00:00:00 2001 From: Wu Liang feng Date: Wed, 24 Dec 2014 18:22:19 +0800 Subject: USB: ehci-platform: Support ehci reset after resume quirk The Rockchip rk3288 EHCI controller doesn't properly detect the case when a device is removed during suspend. Specifically, when usb resume from suspend, the EHCI controller maintaining the USB state (FLAG_CF is 1, Current Connect Status is 1), but a USB device (like a USB camera on rk3288) may have been disconnected actually. Let's add a quirk to force ehci to go into the usb_root_hub_lost_power() path and reset after resume. This should generally reset the whole controller and all ports and initialize everything cleanly again, and bring the devices back up. As part of this, rename the "hibernation" paramter of ehci_resume() to force_reset since hibernation is simply another case where we can't trust the autodetected status and need to force a reset of devices. Signed-off-by: Wu Liang feng Reviewed-by: Julius Werner Reviewed-by: Doug Anderson Reviewed-by: Tomasz Figa Reviewed-by: Pawel Osciak Reviewed-by: Sonny Rao Acked-by: Alan Stern Tested-by: Doug Anderson Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ehci_pdriver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ehci_pdriver.h b/include/linux/usb/ehci_pdriver.h index 7eb4dcd0d386..6287b398abd9 100644 --- a/include/linux/usb/ehci_pdriver.h +++ b/include/linux/usb/ehci_pdriver.h @@ -34,6 +34,8 @@ struct usb_hcd; * after initialization. * @no_io_watchdog: set to 1 if the controller does not need the I/O * watchdog to run. + * @reset_on_resume: set to 1 if the controller needs to be reset after + * a suspend / resume cycle (but can't detect that itself). * * These are general configuration options for the EHCI controller. All of * these options are activating more or less workarounds for some hardware. @@ -45,6 +47,7 @@ struct usb_ehci_pdata { unsigned big_endian_desc:1; unsigned big_endian_mmio:1; unsigned no_io_watchdog:1; + unsigned reset_on_resume:1; /* Turn on all power and clocks */ int (*power_on)(struct platform_device *pdev); -- cgit v1.2.3 From 4bf4ea9dca4ba1984abeb592f429265b9bacac42 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Tue, 30 Dec 2014 20:28:15 -0500 Subject: serial: omap_8250: Fix RTS handling The OMAP3 UART ignores MCR[1] (ie., UART_MCR_RTS) when in autoRTS mode (UPF_HARD_FLOW + CRTSCTS). This makes it impossible for either the serial core or userspace to manually flow control the sender. Disable autoRTS mode when RTS is lowered and restore the previous mode when RTS is raised. Note that the OMAP3 UART provides no mechanism for switching from autoRTS mode without corrupting incoming data; to access the necessary register, the line control settings must be set to 8-e-2 and thus any data received during that time will be interpreted with those settings. This corruption has been observed in practice. Cc: Sebastian Andrzej Siewior Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 1 + include/linux/serial_core.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index e02acf0a0ec9..245b959f1ff6 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -126,6 +126,7 @@ extern int serial8250_do_startup(struct uart_port *port); extern void serial8250_do_shutdown(struct uart_port *port); extern void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate); +extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); extern int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 057038cf2788..a0c7033d5f91 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -123,6 +123,7 @@ struct uart_port { void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + void (*set_mctrl)(struct uart_port *, unsigned int); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); -- cgit v1.2.3 From a291b7d5f600a068af1e2186ce590a9a39093ddb Mon Sep 17 00:00:00 2001 From: Robert Baldyga Date: Wed, 10 Dec 2014 12:49:24 +0100 Subject: serial: s3c: add missing register definitions This macro definitions are necessary to implement DMA transfers is samsung serial driver. Based on previous work of Sylwester Nawrocki and Lukasz Czerwinski. Signed-off-by: Robert Baldyga Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_s3c.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index e6fc9567690b..a7f004a3c177 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -104,6 +104,31 @@ S3C2410_UCON_RXIRQMODE | \ S3C2410_UCON_RXFIFO_TOI) +#define S3C64XX_UCON_TXBURST_1 (0<<20) +#define S3C64XX_UCON_TXBURST_4 (1<<20) +#define S3C64XX_UCON_TXBURST_8 (2<<20) +#define S3C64XX_UCON_TXBURST_16 (3<<20) +#define S3C64XX_UCON_TXBURST_MASK (0xf<<20) +#define S3C64XX_UCON_RXBURST_1 (0<<16) +#define S3C64XX_UCON_RXBURST_4 (1<<16) +#define S3C64XX_UCON_RXBURST_8 (2<<16) +#define S3C64XX_UCON_RXBURST_16 (3<<16) +#define S3C64XX_UCON_RXBURST_MASK (0xf<<16) +#define S3C64XX_UCON_TIMEOUT_SHIFT (12) +#define S3C64XX_UCON_TIMEOUT_MASK (0xf<<12) +#define S3C64XX_UCON_EMPTYINT_EN (1<<11) +#define S3C64XX_UCON_DMASUS_EN (1<<10) +#define S3C64XX_UCON_TXINT_LEVEL (1<<9) +#define S3C64XX_UCON_RXINT_LEVEL (1<<8) +#define S3C64XX_UCON_TIMEOUT_EN (1<<7) +#define S3C64XX_UCON_ERRINT_EN (1<<6) +#define S3C64XX_UCON_TXMODE_DMA (2<<2) +#define S3C64XX_UCON_TXMODE_CPU (1<<2) +#define S3C64XX_UCON_TXMODE_MASK (3<<2) +#define S3C64XX_UCON_RXMODE_DMA (2<<0) +#define S3C64XX_UCON_RXMODE_CPU (1<<0) +#define S3C64XX_UCON_RXMODE_MASK (3<<0) + #define S3C2410_UFCON_FIFOMODE (1<<0) #define S3C2410_UFCON_TXTRIG0 (0<<6) #define S3C2410_UFCON_RXTRIG8 (1<<4) @@ -155,6 +180,7 @@ #define S3C2440_UFSTAT_TXMASK (63<<8) #define S3C2440_UFSTAT_RXMASK (63) +#define S3C2410_UTRSTAT_TIMEOUT (1<<3) #define S3C2410_UTRSTAT_TXE (1<<2) #define S3C2410_UTRSTAT_TXFE (1<<1) #define S3C2410_UTRSTAT_RXDR (1<<0) @@ -179,8 +205,10 @@ #define S3C64XX_UINTM 0x38 #define S3C64XX_UINTM_RXD (0) +#define S3C64XX_UINTM_ERROR (1) #define S3C64XX_UINTM_TXD (2) #define S3C64XX_UINTM_RXD_MSK (1 << S3C64XX_UINTM_RXD) +#define S3C64XX_UINTM_ERR_MSK (1 << S3C64XX_UINTM_ERROR) #define S3C64XX_UINTM_TXD_MSK (1 << S3C64XX_UINTM_TXD) /* Following are specific to S5PV210 */ -- cgit v1.2.3 From 09eb483e895f36fd002e88c878e9578c359aa468 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Tue, 23 Dec 2014 16:26:31 -0800 Subject: f2fs: fix missing cold bit during recovery In do_recover_data, we find and update previous node pages after updating its new block addresses. After then, we call fill_node_footer without reset field, we erase its cold bit so that this new cold node block is written to wrong log area. This patch fixes not to miss its old flag. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 87f14e90e984..e993b0bc9abf 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -224,6 +224,8 @@ enum { OFFSET_BIT_SHIFT }; +#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */ + struct node_footer { __le32 nid; /* node id */ __le32 ino; /* inode nunmber */ -- cgit v1.2.3 From 9733e4f0a973a354034f5dd603b4142a3095c85f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 12:49:13 -0800 Subject: rcu: Make _batches_completed() functions return unsigned long Long ago, the various ->completed fields were of type long, but now are unsigned long due to signed-integer-overflow concerns. However, the various _batches_completed() functions remained of type long, even though their only purpose in life is to return the corresponding ->completed field. This patch cleans this up by changing these functions' return types to unsigned long. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 4 ++-- include/linux/rcutree.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0e5366200154..91f7e4c37800 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -94,7 +94,7 @@ static inline void rcu_virt_note_context_switch(int cpu) /* * Return the number of grace periods. */ -static inline long rcu_batches_completed(void) +static inline unsigned long rcu_batches_completed(void) { return 0; } @@ -102,7 +102,7 @@ static inline long rcu_batches_completed(void) /* * Return the number of bottom-half grace periods. */ -static inline long rcu_batches_completed_bh(void) +static inline unsigned long rcu_batches_completed_bh(void) { return 0; } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 52953790dcca..9885bfb6b123 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -81,9 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; -long rcu_batches_completed(void); -long rcu_batches_completed_bh(void); -long rcu_batches_completed_sched(void); +unsigned long rcu_batches_completed(void); +unsigned long rcu_batches_completed_bh(void); +unsigned long rcu_batches_completed_sched(void); void show_rcu_gp_kthreads(void); void rcu_force_quiescent_state(void); -- cgit v1.2.3 From c1fe9cde4ae904fffb5b4d975d0a37e99136ff50 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 15:45:27 -0800 Subject: rcu: Provide rcu_batches_completed_sched() for TINY_RCU A bug in rcutorture has caused it to ignore completed batches. In preparation for fixing that bug, this commit provides TINY_RCU with the required rcu_batches_completed_sched(). Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 91f7e4c37800..1ce2d6b8f0c3 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -107,6 +107,14 @@ static inline unsigned long rcu_batches_completed_bh(void) return 0; } +/* + * Return the number of sched grace periods. + */ +static inline unsigned long rcu_batches_completed_sched(void) +{ + return 0; +} + static inline void rcu_force_quiescent_state(void) { } -- cgit v1.2.3 From 917963d0b30f9c4153c372c165178501d97b6b55 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 21 Nov 2014 17:10:16 -0800 Subject: rcutorture: Check from beginning to end of grace period Currently, rcutorture's Reader Batch checks measure from the end of the previous grace period to the end of the current one. This commit tightens up these checks by measuring from the start and end of the same grace period. This involves adding rcu_batches_started() and friends corresponding to the existing rcu_batches_completed() and friends. We leave SRCU alone for the moment, as it does not yet have a way of tracking both ends of its grace periods. Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 30 +++++++++++++++++++++++++++--- include/linux/rcutree.h | 3 +++ 2 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 1ce2d6b8f0c3..984192160e9b 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -92,7 +92,31 @@ static inline void rcu_virt_note_context_switch(int cpu) } /* - * Return the number of grace periods. + * Return the number of grace periods started. + */ +static inline unsigned long rcu_batches_started(void) +{ + return 0; +} + +/* + * Return the number of bottom-half grace periods started. + */ +static inline unsigned long rcu_batches_started_bh(void) +{ + return 0; +} + +/* + * Return the number of sched grace periods started. + */ +static inline unsigned long rcu_batches_started_sched(void) +{ + return 0; +} + +/* + * Return the number of grace periods completed. */ static inline unsigned long rcu_batches_completed(void) { @@ -100,7 +124,7 @@ static inline unsigned long rcu_batches_completed(void) } /* - * Return the number of bottom-half grace periods. + * Return the number of bottom-half grace periods completed. */ static inline unsigned long rcu_batches_completed_bh(void) { @@ -108,7 +132,7 @@ static inline unsigned long rcu_batches_completed_bh(void) } /* - * Return the number of sched grace periods. + * Return the number of sched grace periods completed. */ static inline unsigned long rcu_batches_completed_sched(void) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9885bfb6b123..c0dd124e69ec 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -81,6 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; +unsigned long rcu_batches_started(void); +unsigned long rcu_batches_started_bh(void); +unsigned long rcu_batches_started_sched(void); unsigned long rcu_batches_completed(void); unsigned long rcu_batches_completed_bh(void); unsigned long rcu_batches_completed_sched(void); -- cgit v1.2.3 From 31c89c959667194350f496947b576c149503ce98 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Fri, 9 Jan 2015 07:43:45 -0800 Subject: pinctrl: pinconf-generic: Infer map type from DT property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the new 'groups' property, the DT parser can infer the map type from the fact whether 'pins' or 'groups' is used to specify the pin group to work on. To maintain backwards compatibitliy with current usage of the DT binding, this is only done when PIN_MAP_TYPE_INVALID is passed to the parsing function as type. Also, a new helper 'pinconf_generic_dt_node_to_map_all()' is introduced, which can be used by drivers as generic callback for dt_node_to_map() to leverage the new feature. Changes since v2: - rename dt_pin_specifier to subnode_target_type - add additional comment in header file explaining passing an invalid map type - mention map_all() helper in commit message Changes since RFC v2: - none Signed-off-by: Soren Brinkmann Tested-by: Andreas Färber Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index d578a60eff23..83c89f5ab705 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -174,6 +174,17 @@ static inline int pinconf_generic_dt_node_to_map_pin( PIN_MAP_TYPE_CONFIGS_PIN); } +static inline int pinconf_generic_dt_node_to_map_all( + struct pinctrl_dev *pctldev, struct device_node *np_config, + struct pinctrl_map **map, unsigned *num_maps) +{ + /* + * passing the type as PIN_MAP_TYPE_INVALID causes the underlying parser + * to infer the map type from the DT properties used. + */ + return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, + PIN_MAP_TYPE_INVALID); +} #endif #endif /* CONFIG_GENERIC_PINCONF */ -- cgit v1.2.3 From dd4d01f7bad886c22687224bc7070b87de8deb51 Mon Sep 17 00:00:00 2001 From: Soren Brinkmann Date: Fri, 9 Jan 2015 07:43:46 -0800 Subject: pinctrl: pinconf-generic: Allow driver to specify DT params MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Additionally to the generic DT parameters, allow drivers to provide driver-specific DT parameters to be used with the generic parser infrastructure. To achieve this 'struct pinctrl_desc' is extended to pass custom pinconf option to the core. In order to pass this kind of information, the related data structures - 'struct pinconf_generic_dt_params', 'pin_config_item' - are moved from pinconf internals to the pinconf-generic header. Additionally pinconfg-generic is refactored to not only iterate over the generic pinconf parameters but also take the parameters into account that are provided through the driver's 'struct pinctrl_desc'. In particular 'pinconf_generic_parse_dt_config()' and 'pinconf_generic_dump' helpers are split into two parts each. In order to have a more generic helper that can be used to process the generic parameters as well as the driver-specific ones. v2: - fix typo - add missing documentation for @conf_items member in struct - rebase to pinctrl/devel: conflict in abx500 - rename _pinconf_generic_dump() to pinconf_generic_dump_one() - removed '_' from _parse_dt_cfg() - removed BUG_ONs, error condition is handled in if statements - removed pinconf_generic_dump_group() & pinconf_generic_dump_pin helpers - fixed up corresponding call sites - renamed pinconf_generic_dump() to pinconf_generic_dump_pins() - added kernel-doc to pinconf_generic_dump_pins() - add kernel-doc - more verbose commit message Signed-off-by: Soren Brinkmann Tested-by: Andreas Färber Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 18 ++++++++++++++++++ include/linux/pinctrl/pinctrl.h | 9 +++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 83c89f5ab705..342409f7f3ec 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -115,6 +115,18 @@ enum pin_config_param { PIN_CONFIG_END = 0x7FFF, }; +#ifdef CONFIG_DEBUG_FS +#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \ + .has_arg = d } + +struct pin_config_item { + const enum pin_config_param param; + const char * const display; + const char * const format; + bool has_arg; +}; +#endif /* CONFIG_DEBUG_FS */ + /* * Helpful configuration macro to be used in tables etc. */ @@ -150,6 +162,12 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param struct pinctrl_dev; struct pinctrl_map; +struct pinconf_generic_dt_params { + const char * const property; + enum pin_config_param param; + u32 default_value; +}; + int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, struct pinctrl_map **map, unsigned *reserved_maps, unsigned *num_maps, diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index cc8e1aff0e28..c58b3e11ba8e 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -24,6 +24,7 @@ struct pinctrl_dev; struct pinctrl_map; struct pinmux_ops; struct pinconf_ops; +struct pin_config_item; struct gpio_chip; struct device_node; @@ -117,6 +118,9 @@ struct pinctrl_ops { * @confops: pin config operations vtable, if you support pin configuration in * your driver * @owner: module providing the pin controller, used for refcounting + * @num_dt_params: Number of driver-specific DT parameters + * @params: List of DT parameters + * @conf_items: Information how to print @params in debugfs */ struct pinctrl_desc { const char *name; @@ -126,6 +130,11 @@ struct pinctrl_desc { const struct pinmux_ops *pmxops; const struct pinconf_ops *confops; struct module *owner; +#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF) + unsigned int num_dt_params; + const struct pinconf_generic_dt_params *params; + const struct pin_config_item *conf_items; +#endif }; /* External interface to pin controller */ -- cgit v1.2.3 From 7bb68410ef22067b08fd52887875b8f337f89dcc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 18 Oct 2014 15:04:15 +0200 Subject: efi: split off remapping code from efi_config_init() Split of the remapping code from efi_config_init() so that the caller can perform its own remapping. This is necessary to correctly handle virtually remapped UEFI memory regions under kexec, as efi.systab will have been updated to a virtual address. Acked-by: Matt Fleming Tested-by: Leif Lindholm Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 0238d612750e..5ffe5115951f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -875,6 +875,8 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon #endif extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr); extern int efi_config_init(efi_config_table_type_t *arch_tables); +extern int efi_config_parse_tables(void *config_tables, int count, int sz, + efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); extern u32 efi_mem_type (unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); -- cgit v1.2.3 From 39db74ce1aa83626a0a70ed2abf29a17598fff49 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Thu, 27 Nov 2014 14:07:28 +0200 Subject: mei: bus: use ssize_t as the return type for send and receive Mei bus receive and send function may return either number of transmitted bytes or errno. It is better to use ssize_t type for that purpose that mixing size_t with int. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- include/linux/mei_cl_bus.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 164aad1f9f12..0819d36a3a74 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -25,8 +25,8 @@ int __mei_cl_driver_register(struct mei_cl_driver *driver, void mei_cl_driver_unregister(struct mei_cl_driver *driver); -int mei_cl_send(struct mei_cl_device *device, u8 *buf, size_t length); -int mei_cl_recv(struct mei_cl_device *device, u8 *buf, size_t length); +ssize_t mei_cl_send(struct mei_cl_device *device, u8 *buf, size_t length); +ssize_t mei_cl_recv(struct mei_cl_device *device, u8 *buf, size_t length); typedef void (*mei_cl_event_cb_t)(struct mei_cl_device *device, u32 events, void *context); -- cgit v1.2.3 From 46d0d33350e9b32642d745a8b46a954910196b4d Mon Sep 17 00:00:00 2001 From: Gigi Joseph Date: Fri, 9 Jan 2015 03:45:02 +0000 Subject: ti-st: add device tree support When using device tree, driver configuration data need to be read from device node. Add support for getting the platform data information from the device tree information stored in the .dtb file in case it exists. Signed-off-by: Eyal Reizer Signed-off-by: bvijay Diff rendering mode:inlineside by side Signed-off-by: Gigi Joseph Signed-off-by: Greg Kroah-Hartman --- include/linux/ti_wilink_st.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index 884d6263e962..9072d9f95cff 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -86,6 +86,7 @@ struct st_proto_s { extern long st_register(struct st_proto_s *); extern long st_unregister(struct st_proto_s *); +extern struct ti_st_plat_data *dt_pdata; /* * header information used by st_core.c -- cgit v1.2.3 From f379984f849d729bd2eb076b633200b1c040611e Mon Sep 17 00:00:00 2001 From: Xia Kaixu Date: Fri, 9 Jan 2015 16:57:18 -0700 Subject: coresight: remove the unused macro CORESIGHT_DEBUGFS_ENTRY Debugfs isn't used for coresight configuration, so the macro CORESIGHT_DEBUGFS_ENTRY is unnecessary, just remove it. Signed-off-by: Xia Kaixu Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 5d3c54311f7a..7cbfecbfa643 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -179,15 +179,6 @@ struct coresight_device { #define sink_ops(csdev) csdev->ops->sink_ops #define link_ops(csdev) csdev->ops->link_ops -#define CORESIGHT_DEBUGFS_ENTRY(__name, __entry_name, \ - __mode, __get, __set, __fmt) \ -DEFINE_SIMPLE_ATTRIBUTE(__name ## _ops, __get, __set, __fmt); \ -static const struct coresight_ops_entry __name ## _entry = { \ - .name = __entry_name, \ - .mode = __mode, \ - .ops = &__name ## _ops \ -} - /** * struct coresight_ops_sink - basic operations for a sink * Operations available for sinks -- cgit v1.2.3 From c61c4b5dd2c6b5dbf0f7e299db1e8411ef590f5c Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Fri, 9 Jan 2015 16:57:20 -0700 Subject: coresight: Fixing wrong #ifdef/#endif placement Fixing problem reported by: https://lkml.org/lkml/2015/1/6/86 The #ifdef/#endif is wrong and prevents the stub of function of_get_coresight_platform_data() from being visible when CONFIG_OF is not defined. Moving CONFIG_OF condition out of CONFIG_CORESIGHT, making them both independent. Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7cbfecbfa643..cd6d4c384ca3 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -230,10 +230,6 @@ extern void coresight_disable(struct coresight_device *csdev); extern int coresight_is_bit_set(u32 val, int position, int value); extern int coresight_timeout(void __iomem *addr, u32 offset, int position, int value); -#ifdef CONFIG_OF -extern struct coresight_platform_data *of_get_coresight_platform_data( - struct device *dev, struct device_node *node); -#endif #else static inline struct coresight_device * coresight_register(struct coresight_desc *desc) { return NULL; } @@ -245,10 +241,14 @@ static inline int coresight_is_bit_set(u32 val, int position, int value) { return 0; } static inline int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) { return 1; } +#endif + #ifdef CONFIG_OF +extern struct coresight_platform_data *of_get_coresight_platform_data( + struct device *dev, struct device_node *node); +#else static inline struct coresight_platform_data *of_get_coresight_platform_data( struct device *dev, struct device_node *node) { return NULL; } #endif -#endif #endif -- cgit v1.2.3 From 07673204777abe893092cc6e42ea04e5c0ac8cb7 Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Tue, 30 Dec 2014 14:02:28 +0800 Subject: usb: phy: change some comments - Delete the OTG stuffs - .set_suspend is for controller, not for A-device or B-device. Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index f499c23e6342..bc91b5d380fd 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -1,5 +1,5 @@ -/* USB OTG (On The Go) defines */ /* + * USB PHY defines * * These APIs may be used between USB controllers. USB device drivers * (for either host or peripheral roles) don't use these calls; they @@ -106,7 +106,7 @@ struct usb_phy { int (*set_power)(struct usb_phy *x, unsigned mA); - /* for non-OTG B devices: set transceiver into suspend mode */ + /* Set transceiver into suspend mode */ int (*set_suspend)(struct usb_phy *x, int suspend); -- cgit v1.2.3 From 7acc9973e3c42de9926b28eec8ae3434dfdde3be Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sat, 6 Dec 2014 22:05:15 +0100 Subject: usb: phy: generic: add vbus support Add support for vbus detection and power supply. This code is more or less stolen from phy-gpio-vbus-usb.c, and aims at providing a detection mechanism for VBus (ie. usb cable plug) based on a GPIO line, and a power supply activation which draws current from the VBus. [ balbi@ti.com : fix build break ] Signed-off-by: Robert Jarzmik Signed-off-by: Felipe Balbi --- include/linux/usb/usb_phy_generic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/usb_phy_generic.h b/include/linux/usb/usb_phy_generic.h index 68adae83affc..c13632d5292e 100644 --- a/include/linux/usb/usb_phy_generic.h +++ b/include/linux/usb/usb_phy_generic.h @@ -2,6 +2,7 @@ #define __LINUX_USB_NOP_XCEIV_H #include +#include struct usb_phy_generic_platform_data { enum usb_phy_type type; @@ -11,6 +12,7 @@ struct usb_phy_generic_platform_data { unsigned int needs_vcc:1; unsigned int needs_reset:1; /* deprecated */ int gpio_reset; + struct gpio_desc *gpiod_vbus; }; #if IS_ENABLED(CONFIG_NOP_USB_XCEIV) -- cgit v1.2.3 From cbf6ab52add20b845f903decc973afbd5463c527 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 5 Jan 2015 19:29:32 +0800 Subject: kprobes: Pass the original kprobe for preparing optimized kprobe Pass the original kprobe for preparing an optimized kprobe arch-dep part, since for some architecture (e.g. ARM32) requires the information in original kprobe. Signed-off-by: Masami Hiramatsu Signed-off-by: Wang Nan Signed-off-by: Jon Medhurst --- include/linux/kprobes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 5297f9fa0ef2..1ab54754a86d 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -308,7 +308,8 @@ struct optimized_kprobe { /* Architecture dependent functions for direct jump optimization */ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); -extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); +extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, + struct kprobe *orig); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobes(struct list_head *oplist, -- cgit v1.2.3 From 7a868d1e9ab3c534c5ad44e3e5dc46753a1e5636 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 12 Jan 2015 14:52:22 +0800 Subject: rhashtable: involve rhashtable_lookup_compare_insert routine Introduce a new function called rhashtable_lookup_compare_insert() which is very similar to rhashtable_lookup_insert(). But the former makes use of users' given compare function to look for an object, and then inserts it into hash table if found. As the entire process of search and insertion is under protection of per bucket lock, this can help users to avoid the involvement of extra lock. Signed-off-by: Ying Xue Cc: Thomas Graf Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 326acd8c2e9f..7b9bd77ed684 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -168,7 +168,12 @@ int rhashtable_shrink(struct rhashtable *ht); void *rhashtable_lookup(struct rhashtable *ht, const void *key); void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key, bool (*compare)(void *, void *), void *arg); + bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj); +bool rhashtable_lookup_compare_insert(struct rhashtable *ht, + struct rhash_head *obj, + bool (*compare)(void *, void *), + void *arg); void rhashtable_destroy(struct rhashtable *ht); -- cgit v1.2.3 From 6f73d3b13dc5e16ae06025cd1b12a36b2857caa2 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Mon, 12 Jan 2015 14:52:24 +0800 Subject: rhashtable: add a note for grow and shrink decision functions As commit c0c09bfdc415 ("rhashtable: avoid unnecessary wakeup for worker queue") moves condition statements of verifying whether hash table size exceeds its maximum threshold or reaches its minimum threshold from resizing functions to resizing decision functions, we should add a note in rhashtable.h to indicate the implementation of what the grow and shrink decision function must enforce min/max shift, otherwise, it's failed to take min/max shift's set watermarks into effect. Signed-off-by: Ying Xue Cc: Thomas Graf Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 7b9bd77ed684..9570832ab07c 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -79,6 +79,10 @@ struct rhashtable; * @obj_hashfn: Function to hash object * @grow_decision: If defined, may return true if table should expand * @shrink_decision: If defined, may return true if table should shrink + * + * Note: when implementing the grow and shrink decision function, min/max + * shift must be enforced, otherwise, resizing watermarks they set may be + * useless. */ struct rhashtable_params { size_t nelem_hint; -- cgit v1.2.3 From df8a39defad46b83694ea6dd868d332976d62cc0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 13 Jan 2015 17:13:44 +0100 Subject: net: rename vlan_tx_* helpers since "tx" is misleading there The same macros are used for rx as well. So rename it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 515a35e2a48a..bea465f24ebb 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -78,9 +78,9 @@ static inline bool is_vlan_dev(struct net_device *dev) return dev->priv_flags & IFF_802_1Q_VLAN; } -#define vlan_tx_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) -#define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) -#define vlan_tx_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) +#define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) +#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) +#define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats @@ -376,7 +376,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, - vlan_tx_tag_get(skb)); + skb_vlan_tag_get(skb)); if (likely(skb)) skb->vlan_tci = 0; return skb; @@ -393,7 +393,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) */ static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb) { - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) skb = __vlan_hwaccel_push_inside(skb); return skb; } @@ -442,8 +442,8 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { - if (vlan_tx_tag_present(skb)) { - *vlan_tci = vlan_tx_tag_get(skb); + if (skb_vlan_tag_present(skb)) { + *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; @@ -480,7 +480,7 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { __be16 protocol = 0; - if (vlan_tx_tag_present(skb) || + if (skb_vlan_tag_present(skb) || skb->protocol != cpu_to_be16(ETH_P_8021Q)) protocol = skb->protocol; else { -- cgit v1.2.3 From dd22f551ac0ad366f92f601835f6623b83adc331 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 7 Jan 2015 18:05:34 +0200 Subject: block: Change direct_access calling convention In order to support accesses to larger chunks of memory, pass in a 'size' parameter (counted in bytes), and return the amount available at that address. Add a new helper function, bdev_direct_access(), to handle common functionality including partition handling, checking the length requested is positive, checking for the sector being page-aligned, and checking the length of the request does not pass the end of the partition. Signed-off-by: Matthew Wilcox Reviewed-by: Jan Kara Reviewed-by: Boaz Harrosh Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 92f4b4b288dd..e9086be6d9a0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1601,8 +1601,8 @@ struct block_device_operations { int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*direct_access) (struct block_device *, sector_t, - void **, unsigned long *); + long (*direct_access)(struct block_device *, sector_t, + void **, unsigned long *pfn, long size); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1620,6 +1620,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); +extern long bdev_direct_access(struct block_device *, sector_t, void **addr, + unsigned long *pfn, long size); #else /* CONFIG_BLOCK */ struct block_device; -- cgit v1.2.3 From a7d19057e7160a566bad9b2ba070a391fb78df96 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Sat, 12 Jul 2014 12:10:04 +0200 Subject: clk: sunxi: Remove custom phase function Now that we don't have any user left for our custom phase function, we can safely remove this hack from the code. Signed-off-by: Maxime Ripard Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai --- include/linux/clk/sunxi.h | 22 ---------------------- 1 file changed, 22 deletions(-) delete mode 100644 include/linux/clk/sunxi.h (limited to 'include/linux') diff --git a/include/linux/clk/sunxi.h b/include/linux/clk/sunxi.h deleted file mode 100644 index aed28c4451d9..000000000000 --- a/include/linux/clk/sunxi.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * Copyright 2013 - Hans de Goede - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef __LINUX_CLK_SUNXI_H_ -#define __LINUX_CLK_SUNXI_H_ - -#include - -void clk_sunxi_mmc_phase_control(struct clk *clk, u8 sample, u8 output); - -#endif -- cgit v1.2.3 From f684e4ac9f4bae4e6ecff92eef9645a44764fc04 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 12 Jan 2015 00:45:55 +0100 Subject: pinctrl: pinconf-generic: loose DT dependence New pin controllers such as ACPI-based may also have custom properties to parse, and should be able to use generic pin config. Let's make the code compile on !OF systems and rename members a bit to underscore it is custom parameters and not necessarily DT parameters. This fixes a build regression for x86_64 on the zeroday kernel builds. Reported-by: kbuild test robot Reviewed-and-tested-by: Soren Brinkmann Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 2 +- include/linux/pinctrl/pinctrl.h | 17 ++++++++++------- 2 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 342409f7f3ec..fe65962b264f 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -162,7 +162,7 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param struct pinctrl_dev; struct pinctrl_map; -struct pinconf_generic_dt_params { +struct pinconf_generic_params { const char * const property; enum pin_config_param param; u32 default_value; diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index c58b3e11ba8e..66e4697516de 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -118,9 +118,12 @@ struct pinctrl_ops { * @confops: pin config operations vtable, if you support pin configuration in * your driver * @owner: module providing the pin controller, used for refcounting - * @num_dt_params: Number of driver-specific DT parameters - * @params: List of DT parameters - * @conf_items: Information how to print @params in debugfs + * @num_custom_params: Number of driver-specific custom parameters to be parsed + * from the hardware description + * @custom_params: List of driver_specific custom parameters to be parsed from + * the hardware description + * @custom_conf_items: Information how to print @params in debugfs, must be + * the same size as the @custom_params, i.e. @num_custom_params */ struct pinctrl_desc { const char *name; @@ -130,10 +133,10 @@ struct pinctrl_desc { const struct pinmux_ops *pmxops; const struct pinconf_ops *confops; struct module *owner; -#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF) - unsigned int num_dt_params; - const struct pinconf_generic_dt_params *params; - const struct pin_config_item *conf_items; +#ifdef CONFIG_GENERIC_PINCONF + unsigned int num_custom_params; + const struct pinconf_generic_params *custom_params; + const struct pin_config_item *custom_conf_items; #endif }; -- cgit v1.2.3 From 5a7d2efdd93f6c4bb6cd3d5df3d2f5611c9b87ac Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 16 Dec 2014 10:59:17 +0100 Subject: pinctrl: consumer: use correct retval for placeholder functions These functions are supposed to return an error pointer, not NULL. Signed-off-by: Wolfram Sang Signed-off-by: Linus Walleij --- include/linux/pinctrl/consumer.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 18eccefea06e..72c0415d6c21 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -82,7 +82,7 @@ static inline int pinctrl_gpio_direction_output(unsigned gpio) static inline struct pinctrl * __must_check pinctrl_get(struct device *dev) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline void pinctrl_put(struct pinctrl *p) @@ -93,7 +93,7 @@ static inline struct pinctrl_state * __must_check pinctrl_lookup_state( struct pinctrl *p, const char *name) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline int pinctrl_select_state(struct pinctrl *p, @@ -104,7 +104,7 @@ static inline int pinctrl_select_state(struct pinctrl *p, static inline struct pinctrl * __must_check devm_pinctrl_get(struct device *dev) { - return NULL; + return ERR_PTR(-ENOSYS); } static inline void devm_pinctrl_put(struct pinctrl *p) -- cgit v1.2.3 From d84b6728c54dcf73bcef3e3f7cf6767e2d224e39 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 6 Jan 2015 11:45:07 -0800 Subject: locking/mcs: Better differentiate between MCS variants We have two flavors of the MCS spinlock: standard and cancelable (OSQ). While each one is independent of the other, we currently mix and match them. This patch: - Moves the OSQ code out of mcs_spinlock.h (which only deals with the traditional version) into include/linux/osq_lock.h. No unnecessary code is added to the more global header file, anything locks that make use of OSQ must include it anyway. - Renames mcs_spinlock.c to osq_lock.c. This file only contains osq code. - Introduces a CONFIG_LOCK_SPIN_ON_OWNER in order to only build osq_lock if there is support for it. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Thomas Gleixner Cc: "Paul E. McKenney" Cc: Jason Low Cc: Linus Torvalds Cc: Mikulas Patocka Cc: Waiman Long Link: http://lkml.kernel.org/r/1420573509-24774-5-git-send-email-dave@stgolabs.net Signed-off-by: Ingo Molnar --- include/linux/osq_lock.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 90230d5811c5..3a6490e81b28 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -5,8 +5,11 @@ * An MCS like lock especially tailored for optimistic spinning for sleeping * lock implementations (mutex, rwsem, etc). */ - -#define OSQ_UNLOCKED_VAL (0) +struct optimistic_spin_node { + struct optimistic_spin_node *next, *prev; + int locked; /* 1 if lock acquired */ + int cpu; /* encoded CPU # + 1 value */ +}; struct optimistic_spin_queue { /* @@ -16,6 +19,8 @@ struct optimistic_spin_queue { atomic_t tail; }; +#define OSQ_UNLOCKED_VAL (0) + /* Init macro and function. */ #define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) } @@ -24,4 +29,7 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock) atomic_set(&lock->tail, OSQ_UNLOCKED_VAL); } +extern bool osq_lock(struct optimistic_spin_queue *lock); +extern void osq_unlock(struct optimistic_spin_queue *lock); + #endif -- cgit v1.2.3 From 86038c5ea81b519a8a1fcfcd5e4599aab0cdd119 Mon Sep 17 00:00:00 2001 From: "Peter Zijlstra (Intel)" Date: Tue, 16 Dec 2014 12:47:34 +0100 Subject: perf: Avoid horrible stack usage Both Linus (most recent) and Steve (a while ago) reported that perf related callbacks have massive stack bloat. The problem is that software events need a pt_regs in order to properly report the event location and unwind stack. And because we could not assume one was present we allocated one on stack and filled it with minimal bits required for operation. Now, pt_regs is quite large, so this is undesirable. Furthermore it turns out that most sites actually have a pt_regs pointer available, making this even more onerous, as the stack space is pointless waste. This patch addresses the problem by observing that software events have well defined nesting semantics, therefore we can use static per-cpu storage instead of on-stack. Linus made the further observation that all but the scheduler callers of perf_sw_event() have a pt_regs available, so we change the regular perf_sw_event() to require a valid pt_regs (where it used to be optional) and add perf_sw_event_sched() for the scheduler. We have a scheduler specific call instead of a more generic _noregs() like construct because we can assume non-recursion from the scheduler and thereby simplify the code further (_noregs would have to put the recursion context call inline in order to assertain which __perf_regs element to use). One last note on the implementation of perf_trace_buf_prepare(); we allow .regs = NULL for those cases where we already have a pt_regs pointer available and do not need another. Reported-by: Linus Torvalds Reported-by: Steven Rostedt Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Javi Merino Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Oleg Nesterov Cc: Paul Mackerras Cc: Petr Mladek Cc: Steven Rostedt Cc: Tom Zanussi Cc: Vaibhav Nagarnaik Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/ftrace_event.h | 2 +- include/linux/perf_event.h | 28 +++++++++++++++++++++------- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0bebb5c348b8..d36f68b08acc 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -595,7 +595,7 @@ extern int ftrace_profile_set_filter(struct perf_event *event, int event_id, char *filter_str); extern void ftrace_profile_free_filter(struct perf_event *event); extern void *perf_trace_buf_prepare(int size, unsigned short type, - struct pt_regs *regs, int *rctxp); + struct pt_regs **regs, int *rctxp); static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 4f7a61ca4b39..3a7bd80b4db8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -665,6 +665,7 @@ static inline int is_software_event(struct perf_event *event) extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; +extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs @@ -689,14 +690,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs) static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { - struct pt_regs hot_regs; + if (static_key_false(&perf_swevent_enabled[event_id])) + __perf_sw_event(event_id, nr, regs, addr); +} + +DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); +/* + * 'Special' version for the scheduler, it hard assumes no recursion, + * which is guaranteed by us not actually scheduling inside other swevents + * because those disable preemption. + */ +static __always_inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) +{ if (static_key_false(&perf_swevent_enabled[event_id])) { - if (!regs) { - perf_fetch_caller_regs(&hot_regs); - regs = &hot_regs; - } - __perf_sw_event(event_id, nr, regs, addr); + struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); + + perf_fetch_caller_regs(regs); + ___perf_sw_event(event_id, nr, regs, addr); } } @@ -712,7 +724,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev, static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { - perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0); + perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_key_false(&perf_sched_events.key)) __perf_event_task_sched_out(prev, next); @@ -823,6 +835,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh) static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void +perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } +static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks -- cgit v1.2.3 From a2b12f3c7ac1ea43ae646db74faf0b56c2bba563 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 12 Jan 2015 17:00:37 -0800 Subject: udp: pass udp_offload struct to UDP gro callbacks This patch introduces udp_offload_callbacks which has the same GRO functions (but not a GSO function) as offload_callbacks, except there is an argument to a udp_offload struct passed to gro_receive and gro_complete functions. This additional argument can be used to retrieve the per port structure of the encapsulation for use in gro processing (mostly by doing container_of on the structure). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 679e6e90aa4c..47921c291dd6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1969,7 +1969,7 @@ struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); + struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; @@ -1979,10 +1979,21 @@ struct packet_offload { struct list_head list; }; +struct udp_offload; + +struct udp_offload_callbacks { + struct sk_buff **(*gro_receive)(struct sk_buff **head, + struct sk_buff *skb, + struct udp_offload *uoff); + int (*gro_complete)(struct sk_buff *skb, + int nhoff, + struct udp_offload *uoff); +}; + struct udp_offload { __be16 port; u8 ipproto; - struct offload_callbacks callbacks; + struct udp_offload_callbacks callbacks; }; /* often modified stats are per cpu, other are shared (netdev->stats) */ -- cgit v1.2.3 From c38fda3fe8163898f538a45d3c1419e6870625ed Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 14 Jan 2015 22:59:13 -0800 Subject: jbd: drop jbd_ENOSYS debug A quick search shows that there are no users, drop the macro for both jbd and jbd2. Signed-off-by: Davidlohr Bueso Cc: Jan Kara Signed-off-by: Jan Kara --- include/linux/jbd.h | 9 --------- include/linux/jbd2.h | 9 --------- 2 files changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 31229e0be90b..d32615280be9 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -956,15 +956,6 @@ void __log_wait_for_space(journal_t *journal); extern void __journal_drop_transaction(journal_t *, transaction_t *); extern int cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 704b9a599b26..20e7f78041c8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1251,15 +1251,6 @@ void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) - /* * is_journal_abort * -- cgit v1.2.3 From 37715f556a0776356300391f8ac41ace91bea447 Mon Sep 17 00:00:00 2001 From: David Ung Date: Tue, 13 Jan 2015 19:04:25 -0800 Subject: video: fbdev: Add additional vesa modes Add high resolution modes to vesa_modes struct. Signed-off-by: David Ung Signed-off-by: Tomi Valkeinen --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 09bb7a18d287..882dbd1a87b7 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -726,7 +726,7 @@ extern int fb_videomode_from_videomode(const struct videomode *vm, struct fb_videomode *fbmode); /* drivers/video/modedb.c */ -#define VESA_MODEDB_SIZE 34 +#define VESA_MODEDB_SIZE 43 extern void fb_var_to_videomode(struct fb_videomode *mode, const struct fb_var_screeninfo *var); extern void fb_videomode_to_var(struct fb_var_screeninfo *var, -- cgit v1.2.3 From 8f5ee77bb8d162abe28ff8cd56f36e825d143207 Mon Sep 17 00:00:00 2001 From: David Ung Date: Tue, 13 Jan 2015 19:04:26 -0800 Subject: video: fbdev: Check Standard Timing against DMT Add the VESA Display Monitor Timing (DMT) table. During parsing of Standard Timings, it compare the 2 byte STD code with DMT to see what the VESA mode should be. If there is no entry in the vesa_modes table or no match found, it fallsback to the GTF timings. Signed-off-by: David Ung Signed-off-by: Tomi Valkeinen --- include/linux/fb.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 882dbd1a87b7..043f3283b71c 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -727,6 +727,8 @@ extern int fb_videomode_from_videomode(const struct videomode *vm, /* drivers/video/modedb.c */ #define VESA_MODEDB_SIZE 43 +#define DMT_SIZE 0x50 + extern void fb_var_to_videomode(struct fb_videomode *mode, const struct fb_var_screeninfo *var); extern void fb_videomode_to_var(struct fb_var_screeninfo *var, @@ -777,9 +779,17 @@ struct fb_videomode { u32 flag; }; +struct dmt_videomode { + u32 dmt_id; + u32 std_2byte_code; + u32 cvt_3byte_code; + const struct fb_videomode *mode; +}; + extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; extern const struct fb_videomode cea_modes[64]; +extern const struct dmt_videomode dmt_modes[]; struct fb_modelist { struct list_head list; -- cgit v1.2.3 From 92a8b064fd4412d4dd32ef598b6f9e55feef9e51 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 14 Jan 2015 17:21:53 +0100 Subject: mfd: syscon: Add atmel-matrix registers definition AT91 SoCs have a memory range reserved for internal bus configuration. Expose those registers so that drivers can make use of the matrix syscon declared in at91 DTs. Signed-off-by: Boris Brezillon Acked-by: Lee Jones Signed-off-by: Nicolas Ferre --- include/linux/mfd/syscon/atmel-matrix.h | 117 ++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) create mode 100644 include/linux/mfd/syscon/atmel-matrix.h (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/atmel-matrix.h b/include/linux/mfd/syscon/atmel-matrix.h new file mode 100644 index 000000000000..8293c3e2a82a --- /dev/null +++ b/include/linux/mfd/syscon/atmel-matrix.h @@ -0,0 +1,117 @@ +/* + * Copyright (C) 2014 Atmel Corporation. + * + * Memory Controllers (MATRIX, EBI) - System peripherals registers. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _LINUX_MFD_SYSCON_ATMEL_MATRIX_H +#define _LINUX_MFD_SYSCON_ATMEL_MATRIX_H + +#define AT91SAM9260_MATRIX_MCFG 0x00 +#define AT91SAM9260_MATRIX_SCFG 0x40 +#define AT91SAM9260_MATRIX_PRS 0x80 +#define AT91SAM9260_MATRIX_MRCR 0x100 +#define AT91SAM9260_MATRIX_EBICSA 0x11c + +#define AT91SAM9261_MATRIX_MRCR 0x0 +#define AT91SAM9261_MATRIX_SCFG 0x4 +#define AT91SAM9261_MATRIX_TCR 0x24 +#define AT91SAM9261_MATRIX_EBICSA 0x30 +#define AT91SAM9261_MATRIX_USBPUCR 0x34 + +#define AT91SAM9263_MATRIX_MCFG 0x00 +#define AT91SAM9263_MATRIX_SCFG 0x40 +#define AT91SAM9263_MATRIX_PRS 0x80 +#define AT91SAM9263_MATRIX_MRCR 0x100 +#define AT91SAM9263_MATRIX_TCR 0x114 +#define AT91SAM9263_MATRIX_EBI0CSA 0x120 +#define AT91SAM9263_MATRIX_EBI1CSA 0x124 + +#define AT91SAM9RL_MATRIX_MCFG 0x00 +#define AT91SAM9RL_MATRIX_SCFG 0x40 +#define AT91SAM9RL_MATRIX_PRS 0x80 +#define AT91SAM9RL_MATRIX_MRCR 0x100 +#define AT91SAM9RL_MATRIX_TCR 0x114 +#define AT91SAM9RL_MATRIX_EBICSA 0x120 + +#define AT91SAM9G45_MATRIX_MCFG 0x00 +#define AT91SAM9G45_MATRIX_SCFG 0x40 +#define AT91SAM9G45_MATRIX_PRS 0x80 +#define AT91SAM9G45_MATRIX_MRCR 0x100 +#define AT91SAM9G45_MATRIX_TCR 0x110 +#define AT91SAM9G45_MATRIX_DDRMPR 0x118 +#define AT91SAM9G45_MATRIX_EBICSA 0x128 + +#define AT91SAM9N12_MATRIX_MCFG 0x00 +#define AT91SAM9N12_MATRIX_SCFG 0x40 +#define AT91SAM9N12_MATRIX_PRS 0x80 +#define AT91SAM9N12_MATRIX_MRCR 0x100 +#define AT91SAM9N12_MATRIX_EBICSA 0x118 + +#define AT91SAM9X5_MATRIX_MCFG 0x00 +#define AT91SAM9X5_MATRIX_SCFG 0x40 +#define AT91SAM9X5_MATRIX_PRS 0x80 +#define AT91SAM9X5_MATRIX_MRCR 0x100 +#define AT91SAM9X5_MATRIX_EBICSA 0x120 + +#define SAMA5D3_MATRIX_MCFG 0x00 +#define SAMA5D3_MATRIX_SCFG 0x40 +#define SAMA5D3_MATRIX_PRS 0x80 +#define SAMA5D3_MATRIX_MRCR 0x100 + +#define AT91_MATRIX_MCFG(o, x) ((o) + ((x) * 0x4)) +#define AT91_MATRIX_ULBT GENMASK(2, 0) +#define AT91_MATRIX_ULBT_INFINITE (0 << 0) +#define AT91_MATRIX_ULBT_SINGLE (1 << 0) +#define AT91_MATRIX_ULBT_FOUR (2 << 0) +#define AT91_MATRIX_ULBT_EIGHT (3 << 0) +#define AT91_MATRIX_ULBT_SIXTEEN (4 << 0) + +#define AT91_MATRIX_SCFG(o, x) ((o) + ((x) * 0x4)) +#define AT91_MATRIX_SLOT_CYCLE GENMASK(7, 0) +#define AT91_MATRIX_DEFMSTR_TYPE GENMASK(17, 16) +#define AT91_MATRIX_DEFMSTR_TYPE_NONE (0 << 16) +#define AT91_MATRIX_DEFMSTR_TYPE_LAST (1 << 16) +#define AT91_MATRIX_DEFMSTR_TYPE_FIXED (2 << 16) +#define AT91_MATRIX_FIXED_DEFMSTR GENMASK(20, 18) +#define AT91_MATRIX_ARBT GENMASK(25, 24) +#define AT91_MATRIX_ARBT_ROUND_ROBIN (0 << 24) +#define AT91_MATRIX_ARBT_FIXED_PRIORITY (1 << 24) + +#define AT91_MATRIX_ITCM_SIZE GENMASK(3, 0) +#define AT91_MATRIX_ITCM_0 (0 << 0) +#define AT91_MATRIX_ITCM_16 (5 << 0) +#define AT91_MATRIX_ITCM_32 (6 << 0) +#define AT91_MATRIX_ITCM_64 (7 << 0) +#define AT91_MATRIX_DTCM_SIZE GENMASK(7, 4) +#define AT91_MATRIX_DTCM_0 (0 << 4) +#define AT91_MATRIX_DTCM_16 (5 << 4) +#define AT91_MATRIX_DTCM_32 (6 << 4) +#define AT91_MATRIX_DTCM_64 (7 << 4) + +#define AT91_MATRIX_PRAS(o, x) ((o) + ((x) * 0x8)) +#define AT91_MATRIX_PRBS(o, x) ((o) + ((x) * 0x8) + 0x4) +#define AT91_MATRIX_MPR(x) GENMASK(((x) * 0x4) + 1, ((x) * 0x4)) + +#define AT91_MATRIX_RCB(x) BIT(x) + +#define AT91_MATRIX_CSA(cs, val) (val << (cs)) +#define AT91_MATRIX_DBPUC BIT(8) +#define AT91_MATRIX_DBPDC BIT(9) +#define AT91_MATRIX_VDDIOMSEL BIT(16) +#define AT91_MATRIX_VDDIOMSEL_1_8V (0 << 16) +#define AT91_MATRIX_VDDIOMSEL_3_3V (1 << 16) +#define AT91_MATRIX_EBI_IOSR BIT(17) +#define AT91_MATRIX_DDR_IOSR BIT(18) +#define AT91_MATRIX_NFD0_SELECT BIT(24) +#define AT91_MATRIX_DDR_MP_EN BIT(25) +#define AT91_MATRIX_EBI_NUM_CS 8 + +#define AT91_MATRIX_USBPUCR_PUON BIT(30) + +#endif /* _LINUX_MFD_SYSCON_ATMEL_MATRIX_H */ -- cgit v1.2.3 From 57d8acbacaace9a4d95ebde1c13b94d293ff21f3 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Wed, 14 Jan 2015 17:21:55 +0100 Subject: mfd: syscon: Add atmel-smc registers definition Atmel AT91 SoCs have a memory range reserved for SMC (Static Memory Controller) configuration. Expose those registers so that drivers can make use of the smc syscon declared in at91 DTs. Signed-off-by: Boris Brezillon Acked-by: Lee Jones Signed-off-by: Nicolas Ferre --- include/linux/mfd/syscon/atmel-smc.h | 173 +++++++++++++++++++++++++++++++++++ 1 file changed, 173 insertions(+) create mode 100644 include/linux/mfd/syscon/atmel-smc.h (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h new file mode 100644 index 000000000000..be6ebe64eebe --- /dev/null +++ b/include/linux/mfd/syscon/atmel-smc.h @@ -0,0 +1,173 @@ +/* + * Atmel SMC (Static Memory Controller) register offsets and bit definitions. + * + * Copyright (C) 2014 Atmel + * Copyright (C) 2014 Free Electrons + * + * Author: Boris Brezillon + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MFD_SYSCON_ATMEL_SMC_H_ +#define _LINUX_MFD_SYSCON_ATMEL_SMC_H_ + +#include +#include + +#define AT91SAM9_SMC_GENERIC 0x00 +#define AT91SAM9_SMC_GENERIC_BLK_SZ 0x10 + +#define SAMA5_SMC_GENERIC 0x600 +#define SAMA5_SMC_GENERIC_BLK_SZ 0x14 + +#define AT91SAM9_SMC_SETUP(o) ((o) + 0x00) +#define AT91SAM9_SMC_NWESETUP(x) (x) +#define AT91SAM9_SMC_NCS_WRSETUP(x) ((x) << 8) +#define AT91SAM9_SMC_NRDSETUP(x) ((x) << 16) +#define AT91SAM9_SMC_NCS_NRDSETUP(x) ((x) << 24) + +#define AT91SAM9_SMC_PULSE(o) ((o) + 0x04) +#define AT91SAM9_SMC_NWEPULSE(x) (x) +#define AT91SAM9_SMC_NCS_WRPULSE(x) ((x) << 8) +#define AT91SAM9_SMC_NRDPULSE(x) ((x) << 16) +#define AT91SAM9_SMC_NCS_NRDPULSE(x) ((x) << 24) + +#define AT91SAM9_SMC_CYCLE(o) ((o) + 0x08) +#define AT91SAM9_SMC_NWECYCLE(x) (x) +#define AT91SAM9_SMC_NRDCYCLE(x) ((x) << 16) + +#define AT91SAM9_SMC_MODE(o) ((o) + 0x0c) +#define SAMA5_SMC_MODE(o) ((o) + 0x10) +#define AT91_SMC_READMODE BIT(0) +#define AT91_SMC_READMODE_NCS (0 << 0) +#define AT91_SMC_READMODE_NRD (1 << 0) +#define AT91_SMC_WRITEMODE BIT(1) +#define AT91_SMC_WRITEMODE_NCS (0 << 1) +#define AT91_SMC_WRITEMODE_NWE (1 << 1) +#define AT91_SMC_EXNWMODE GENMASK(5, 4) +#define AT91_SMC_EXNWMODE_DISABLE (0 << 4) +#define AT91_SMC_EXNWMODE_FROZEN (2 << 4) +#define AT91_SMC_EXNWMODE_READY (3 << 4) +#define AT91_SMC_BAT BIT(8) +#define AT91_SMC_BAT_SELECT (0 << 8) +#define AT91_SMC_BAT_WRITE (1 << 8) +#define AT91_SMC_DBW GENMASK(13, 12) +#define AT91_SMC_DBW_8 (0 << 12) +#define AT91_SMC_DBW_16 (1 << 12) +#define AT91_SMC_DBW_32 (2 << 12) +#define AT91_SMC_TDF GENMASK(19, 16) +#define AT91_SMC_TDF_(x) ((((x) - 1) << 16) & AT91_SMC_TDF) +#define AT91_SMC_TDF_MAX 16 +#define AT91_SMC_TDFMODE_OPTIMIZED BIT(20) +#define AT91_SMC_PMEN BIT(24) +#define AT91_SMC_PS GENMASK(29, 28) +#define AT91_SMC_PS_4 (0 << 28) +#define AT91_SMC_PS_8 (1 << 28) +#define AT91_SMC_PS_16 (2 << 28) +#define AT91_SMC_PS_32 (3 << 28) + + +/* + * This function converts a setup timing expressed in nanoseconds into an + * encoded value that can be written in the SMC_SETUP register. + * + * The following formula is described in atmel datasheets (section + * "SMC Setup Register"): + * + * setup length = (128* SETUP[5] + SETUP[4:0]) + * + * where setup length is the timing expressed in cycles. + */ +static inline u32 at91sam9_smc_setup_ns_to_cycles(unsigned int clk_rate, + u32 timing_ns) +{ + u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); + u32 coded_cycles = 0; + u32 cycles; + + cycles = DIV_ROUND_UP(timing_ns, clk_period); + if (cycles / 32) { + coded_cycles |= 1 << 5; + if (cycles < 128) + cycles = 0; + } + + coded_cycles |= cycles % 32; + + return coded_cycles; +} + +/* + * This function converts a pulse timing expressed in nanoseconds into an + * encoded value that can be written in the SMC_PULSE register. + * + * The following formula is described in atmel datasheets (section + * "SMC Pulse Register"): + * + * pulse length = (256* PULSE[6] + PULSE[5:0]) + * + * where pulse length is the timing expressed in cycles. + */ +static inline u32 at91sam9_smc_pulse_ns_to_cycles(unsigned int clk_rate, + u32 timing_ns) +{ + u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); + u32 coded_cycles = 0; + u32 cycles; + + cycles = DIV_ROUND_UP(timing_ns, clk_period); + if (cycles / 64) { + coded_cycles |= 1 << 6; + if (cycles < 256) + cycles = 0; + } + + coded_cycles |= cycles % 64; + + return coded_cycles; +} + +/* + * This function converts a cycle timing expressed in nanoseconds into an + * encoded value that can be written in the SMC_CYCLE register. + * + * The following formula is described in atmel datasheets (section + * "SMC Cycle Register"): + * + * cycle length = (CYCLE[8:7]*256 + CYCLE[6:0]) + * + * where cycle length is the timing expressed in cycles. + */ +static inline u32 at91sam9_smc_cycle_ns_to_cycles(unsigned int clk_rate, + u32 timing_ns) +{ + u32 clk_period = DIV_ROUND_UP(NSEC_PER_SEC, clk_rate); + u32 coded_cycles = 0; + u32 cycles; + + cycles = DIV_ROUND_UP(timing_ns, clk_period); + if (cycles / 128) { + coded_cycles = cycles / 256; + cycles %= 256; + if (cycles >= 128) { + coded_cycles++; + cycles = 0; + } + + if (coded_cycles > 0x3) { + coded_cycles = 0x3; + cycles = 0x7f; + } + + coded_cycles <<= 7; + } + + coded_cycles |= cycles % 128; + + return coded_cycles; +} + +#endif /* _LINUX_MFD_SYSCON_ATMEL_SMC_H_ */ -- cgit v1.2.3 From d621e8bae5ac9c67de4de90c5cded12adc8ee1e1 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Delgado Date: Wed, 17 Dec 2014 16:51:13 +0100 Subject: gpio/gpiolib-of: Create of_mm_gpiochip_remove Create counterpart of of_mm_gpiochip_add(). This way the modules that can be removable do not duplicate the cleanup code. Suggested-by: Alexandre Courbot Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Linus Walleij --- include/linux/of_gpio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h index 38fc05036015..69dbe312b11b 100644 --- a/include/linux/of_gpio.h +++ b/include/linux/of_gpio.h @@ -52,6 +52,7 @@ extern int of_get_named_gpio_flags(struct device_node *np, extern int of_mm_gpiochip_add(struct device_node *np, struct of_mm_gpio_chip *mm_gc); +extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc); extern void of_gpiochip_add(struct gpio_chip *gc); extern void of_gpiochip_remove(struct gpio_chip *gc); -- cgit v1.2.3 From 53e41f554a0cbad139ee5072bbb49b4951f680c2 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 15 Dec 2014 10:39:47 +0100 Subject: gpio: tc3589x: get rid of platform data This device is only used from the device tree, and the startup() and remove() callbacks are not used anywhere in the kernel, so retire them and the pdata altogether. Cc: Samuel Ortiz Acked-by: Lee Jones Signed-off-by: Linus Walleij --- include/linux/mfd/tc3589x.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index e1c12d84c26a..c203c9c56776 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -162,25 +162,13 @@ struct tc3589x_keypad_platform_data { bool no_autorepeat; }; -/** - * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data - * @setup: callback for board-specific initialization - * @remove: callback for board-specific teardown - */ -struct tc3589x_gpio_platform_data { - void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base); - void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base); -}; - /** * struct tc3589x_platform_data - TC3589x platform data * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) - * @gpio: GPIO-specific platform data * @keypad: keypad-specific platform data */ struct tc3589x_platform_data { unsigned int block; - struct tc3589x_gpio_platform_data *gpio; const struct tc3589x_keypad_platform_data *keypad; }; -- cgit v1.2.3 From d34541bc48eb7d7cb2ead5ff0284acf65af96f17 Mon Sep 17 00:00:00 2001 From: Olliver Schinagl Date: Wed, 7 Jan 2015 09:44:57 +0100 Subject: gpio: Make the vararg hacks not pass magic values Right now, in consumer.h, there's some vararg hacks that pass 0 as the flags. What actually is passed however is GPIOD_ASIS, which naturally is also 0. Using the define/enum rather then the magic 0 makes it the define more readable to a passer by. Signed-off-by: Olliver Schinagl Signed-off-by: Linus Walleij --- include/linux/gpio/consumer.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index fd85cb120ee0..45afc2dee560 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -340,31 +340,32 @@ static inline int desc_to_gpio(const struct gpio_desc *desc) * etc. */ #define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags) -#define gpiod_get(varargs...) __gpiod_get(varargs, 0) +#define gpiod_get(varargs...) __gpiod_get(varargs, GPIOD_ASIS) #define __gpiod_get_index(dev, con_id, index, flags, ...) \ __gpiod_get_index(dev, con_id, index, flags) -#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, 0) +#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, GPIOD_ASIS) #define __gpiod_get_optional(dev, con_id, flags, ...) \ __gpiod_get_optional(dev, con_id, flags) -#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, 0) +#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, GPIOD_ASIS) #define __gpiod_get_index_optional(dev, con_id, index, flags, ...) \ __gpiod_get_index_optional(dev, con_id, index, flags) #define gpiod_get_index_optional(varargs...) \ - __gpiod_get_index_optional(varargs, 0) + __gpiod_get_index_optional(varargs, GPIOD_ASIS) #define __devm_gpiod_get(dev, con_id, flags, ...) \ __devm_gpiod_get(dev, con_id, flags) -#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, 0) +#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, GPIOD_ASIS) #define __devm_gpiod_get_index(dev, con_id, index, flags, ...) \ __devm_gpiod_get_index(dev, con_id, index, flags) -#define devm_gpiod_get_index(varargs...) __devm_gpiod_get_index(varargs, 0) +#define devm_gpiod_get_index(varargs...) \ + __devm_gpiod_get_index(varargs, GPIOD_ASIS) #define __devm_gpiod_get_optional(dev, con_id, flags, ...) \ __devm_gpiod_get_optional(dev, con_id, flags) #define devm_gpiod_get_optional(varargs...) \ - __devm_gpiod_get_optional(varargs, 0) + __devm_gpiod_get_optional(varargs, GPIOD_ASIS) #define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...) \ __devm_gpiod_get_index_optional(dev, con_id, index, flags) #define devm_gpiod_get_index_optional(varargs...) \ - __devm_gpiod_get_index_optional(varargs, 0) + __devm_gpiod_get_index_optional(varargs, GPIOD_ASIS) #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS) -- cgit v1.2.3 From 2397aa8b515f7bd77c8d5698170b6a98fdd6721c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 13 Jan 2015 11:02:54 -0500 Subject: svcrdma: Clean up read chunk counting The byte_count argument is not used, and the function is called only from one place. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 975da754c778..2280325e4c88 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -178,8 +178,6 @@ struct svcxprt_rdma { #define RPCRDMA_MAX_REQ_SIZE 4096 /* svc_rdma_marshal.c */ -extern void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *, - int *, int *); extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *); extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *); extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *, -- cgit v1.2.3 From e54524111f51eac1900cf91aca3d38a92a6b11c0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 13 Jan 2015 11:03:20 -0500 Subject: svcrdma: Plant reader function in struct svcxprt_rdma The RDMA reader function doesn't change once an svcxprt_rdma is instantiated. Instead of checking sc_devcap during every incoming RPC, set the reader function once when the connection is accepted. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 2280325e4c88..f161e309f25e 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -150,6 +150,10 @@ struct svcxprt_rdma { struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; struct ib_mr *sc_phys_mr; /* MR for server memory */ + int (*sc_reader)(struct svcxprt_rdma *, + struct svc_rqst *, + struct svc_rdma_op_ctxt *, + int *, u32 *, u32, u32, u64, bool); u32 sc_dev_caps; /* distilled device caps */ u32 sc_dma_lkey; /* local dma key */ unsigned int sc_frmr_pg_list_len; @@ -195,6 +199,12 @@ extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *); /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); +extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, + struct svc_rdma_op_ctxt *, int *, u32 *, + u32, u32, u64, bool); +extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, + struct svc_rdma_op_ctxt *, int *, u32 *, + u32, u32, u64, bool); /* svc_rdma_sendto.c */ extern int svc_rdma_sendto(struct svc_rqst *); -- cgit v1.2.3 From 0b056c224bea63060ce8a981e84193c93fac6f5d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 13 Jan 2015 11:03:37 -0500 Subject: svcrdma: Support RDMA_NOMSG requests Currently the Linux server can not decode RDMA_NOMSG type requests. Operations whose length exceeds the fixed size of RDMA SEND buffers, like large NFSv4 CREATE(NF4LNK) operations, must be conveyed via RDMA_NOMSG. For an RDMA_MSG type request, the client sends the RPC/RDMA, RPC headers, and some or all of the NFS arguments via RDMA SEND. For an RDMA_NOMSG type request, the client sends just the RPC/RDMA header via RDMA SEND. The request's read list contains elements for the entire RPC message, including the RPC header. NFSD expects the RPC/RMDA header and RPC header to be contiguous in page zero of the XDR buffer. Add logic in the RDMA READ path to make the read list contents land where the server prefers, when the incoming message is a type RDMA_NOMSG message. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index f161e309f25e..c343a94bc791 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -79,6 +79,7 @@ struct svc_rdma_op_ctxt { enum ib_wr_opcode wr_op; enum ib_wc_status wc_status; u32 byte_len; + u32 position; struct svcxprt_rdma *xprt; unsigned long flags; enum dma_data_direction direction; -- cgit v1.2.3 From 57699a40b4f2694d3ee63fd5e6465ec8f600b620 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Fri, 16 Jan 2015 11:13:09 +0800 Subject: rhashtable: Fix race in rhashtable_destroy() and use regular work_struct When we put our declared work task in the global workqueue with schedule_delayed_work(), its delay parameter is always zero. Therefore, we should define a regular work in rhashtable structure instead of a delayed work. By the way, we add a condition to check whether resizing functions are NULL before cancelling the work, avoiding to cancel an uninitialized work. Lastly, while we wait for all work items we submitted before to run to completion with cancel_delayed_work(), ht->mutex has been taken in rhashtable_destroy(). Moreover, cancel_delayed_work() doesn't return until all work items are accomplished, and when work items are scheduled, the work's function - rht_deferred_worker() will be called. However, as rht_deferred_worker() also needs to acquire the lock, deadlock might happen at the moment as the lock is already held before. So if the cancel work function is moved out of the lock covered scope, this will avoid the deadlock. Fixes: 97defe1 ("rhashtable: Per bucket locks & deferred expansion/shrinking") Signed-off-by: Ying Xue Cc: Thomas Graf Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 9570832ab07c..a2562ed53ea3 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -119,7 +119,7 @@ struct rhashtable { atomic_t nelems; atomic_t shift; struct rhashtable_params p; - struct delayed_work run_work; + struct work_struct run_work; struct mutex mutex; bool being_destroyed; }; -- cgit v1.2.3 From 5cd37193ce8539be1e6ef76be226f4bcc984e0f5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 13 Dec 2014 20:32:04 -0800 Subject: rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors Although cond_resched_rcu_qs() only applies to TASKS_RCU, it is used in places where it would be useful for it to apply to the normal RCU flavors, rcu_preempt, rcu_sched, and rcu_bh. This is especially the case for workloads that aggressively overload the system, particularly those that generate large numbers of RCU updates on systems running NO_HZ_FULL CPUs. This commit therefore communicates quiescent states from cond_resched_rcu_qs() to the normal RCU flavors. Note that it is unfortunately necessary to leave the old ->passed_quiesce mechanism in place to allow quiescent states that apply to only one flavor to be recorded. (Yes, we could decrement ->rcu_qs_ctr_snap in that case, but that is not so good for debugging of RCU internals.) In addition, if one of the RCU flavor's grace period has stalled, this will invoke rcu_momentary_dyntick_idle(), resulting in a heavy-weight quiescent state visible from other CPUs. Reported-by: Sasha Levin Reported-by: Dave Jones Signed-off-by: Paul E. McKenney [ paulmck: Merge commit from Sasha Levin fixing a bug where __this_cpu() was used in preemptible code. ] --- include/linux/rcupdate.h | 3 ++- include/linux/rcutiny.h | 5 ++++- include/linux/rcutree.h | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ed4f5939a452..468228750299 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void) extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ + rcu_all_qs(); \ if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) -#define rcu_note_voluntary_context_switch(t) do { } while (0) +#define rcu_note_voluntary_context_switch(t) rcu_all_qs() #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 0e5366200154..fabd3fad8516 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -154,7 +154,10 @@ static inline bool rcu_is_watching(void) return true; } - #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */ +static inline void rcu_all_qs(void) +{ +} + #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 52953790dcca..ddba927f7316 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -97,4 +97,6 @@ extern int rcu_scheduler_active __read_mostly; bool rcu_is_watching(void); +void rcu_all_qs(void); + #endif /* __LINUX_RCUTREE_H */ -- cgit v1.2.3 From 076c3b8e03e2737659a89660bb8e54e13587d974 Mon Sep 17 00:00:00 2001 From: James Ban Date: Fri, 16 Jan 2015 12:13:27 +0900 Subject: regulator: da9211: fix unmatched of_node This is a patch for fixing unmatched of_node. Signed-off-by: James Ban Signed-off-by: Mark Brown --- include/linux/regulator/da9211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index 5479394fefce..d1d9d3849bdb 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -32,6 +32,7 @@ struct da9211_pdata { * 2 : 2 phase 2 buck */ int num_buck; + struct device_node *reg_node[DA9211_MAX_REGULATORS]; struct regulator_init_data *init_data[DA9211_MAX_REGULATORS]; }; #endif -- cgit v1.2.3 From ba0513b5b8ffbcb0cc89e2f172c0bcb70497ba2e Mon Sep 17 00:00:00 2001 From: Mario Smarduch Date: Thu, 15 Jan 2015 15:58:53 -0800 Subject: KVM: Add generic support for dirty page logging kvm_get_dirty_log() provides generic handling of dirty bitmap, currently reused by several architectures. Building on that we intrdoduce kvm_get_dirty_log_protect() adding write protection to mark these pages dirty for future write access, before next KVM_GET_DIRTY_LOG ioctl call from user space. Reviewed-by: Christoffer Dall Signed-off-by: Mario Smarduch --- include/linux/kvm_host.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 26f106022c88..3b934cc94cc8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -611,6 +611,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext); int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty); + +int kvm_get_dirty_log_protect(struct kvm *kvm, + struct kvm_dirty_log *log, bool *is_dirty); + +void kvm_arch_mmu_write_protect_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, + unsigned long mask); + int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log); -- cgit v1.2.3 From 67c2b9cb30f561325b010e046b7bbe2a327e69a0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 18 Nov 2014 12:18:18 +0100 Subject: ARM: 8207/1: amba: Use inlines instead of macros for amba_pclk_enable/disable Replace the amba_pclk_enable and amba_pclk_disable macros with static inline functions and remove checks for IS_ERR. The amba bus clock won't be ERR because probe would fail before the use of these functions. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Russell King --- include/linux/amba/bus.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 2afc618b15ce..0ab5f8e0dea2 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -92,11 +92,15 @@ struct amba_device *amba_find_device(const char *, struct device *, unsigned int int amba_request_regions(struct amba_device *, const char *); void amba_release_regions(struct amba_device *); -#define amba_pclk_enable(d) \ - (IS_ERR((d)->pclk) ? 0 : clk_enable((d)->pclk)) +static inline int amba_pclk_enable(struct amba_device *dev) +{ + return clk_enable(dev->pclk); +} -#define amba_pclk_disable(d) \ - do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0) +static inline void amba_pclk_disable(struct amba_device *dev) +{ + clk_disable(dev->pclk); +} static inline int amba_pclk_prepare(struct amba_device *dev) { -- cgit v1.2.3 From 78e1f974dd351ac82d978e3aac2d27422013f914 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sun, 14 Dec 2014 02:37:09 +0200 Subject: iommu/ipmmu-vmsa: Remove platform data support No board file instantiates the IPMMU using platform data. Now that we have DT support, get rid of platform data. Signed-off-by: Laurent Pinchart --- include/linux/platform_data/ipmmu-vmsa.h | 24 ------------------------ 1 file changed, 24 deletions(-) delete mode 100644 include/linux/platform_data/ipmmu-vmsa.h (limited to 'include/linux') diff --git a/include/linux/platform_data/ipmmu-vmsa.h b/include/linux/platform_data/ipmmu-vmsa.h deleted file mode 100644 index 5275b3ac6d37..000000000000 --- a/include/linux/platform_data/ipmmu-vmsa.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * IPMMU VMSA Platform Data - * - * Copyright (C) 2014 Renesas Electronics Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#ifndef __IPMMU_VMSA_H__ -#define __IPMMU_VMSA_H__ - -struct ipmmu_vmsa_master { - const char *name; - unsigned int utlb; -}; - -struct ipmmu_vmsa_platform_data { - const struct ipmmu_vmsa_master *masters; - unsigned int num_masters; -}; - -#endif /* __IPMMU_VMSA_H__ */ -- cgit v1.2.3 From 51e537387990dc1f00752103f314fd135cb94bc6 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 21 Nov 2014 11:24:08 -0700 Subject: PCI: Add flag for devices that don't reset on D3hot->D0 transition Per the PCI Power Management spec r1.2, sec 3.2.4, a device that advertises No_Soft_Reset == 0 in the PMCSR register (reported by lspci as "NoSoftRst-") should perform an internal reset when transitioning from D3hot to D0 via software control. Configuration context is lost and the device requires a full reinitialization sequence. Unfortunately the definition of "internal reset", beyond the application of the configuration context, is largely left to the interpretation of the specific device. Some devices don't seem to perform an "internal reset" even if they report No_Soft_Reset == 0. We still need to honor the PCI specification and restore PCI config context in the event that we do a PM reset, so we don't cache and modify the PCI_PM_CTRL_NO_SOFT_RESET bit for the device, but for interfaces where the intention is to reset the device, like pci_reset_function(), we need a mechanism to flag that PM reset (a D3hot->D0 transition) doesn't perform any significant "internal reset" of the device. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 44627f1df4ca..7bed32b3fd54 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -177,6 +177,8 @@ enum pci_dev_flags { PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), /* Do not use bus resets for device */ PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), + /* Do not use PM reset even if device advertises NoSoftRst- */ + PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 6dee60f69d48fcef021b4b53b3431797ec440764 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add new struct list_head to struct file_lock ...that we can use to queue file_locks to per-ctx list_heads. Go ahead and convert locks_delete_lock and locks_dispose_list to use it instead of the fl_block list. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..cd6818115162 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -934,6 +934,7 @@ int locks_in_grace(struct net *); */ struct file_lock { struct file_lock *fl_next; /* singly linked list for this inode */ + struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; -- cgit v1.2.3 From 4a075e39c86490cc0f0c10ac6abe3592d1689463 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:54 -0500 Subject: locks: add a new struct file_locking_context pointer to struct inode The current scheme of using the i_flock list is really difficult to manage. There is also a legitimate desire for a per-inode spinlock to manage these lists that isn't the i_lock. Start conversion to a new scheme to eventually replace the old i_flock list with a new "file_lock_context" object. We start by adding a new i_flctx to struct inode. For now, it lives in parallel with i_flock list, but will eventually replace it. The idea is to allocate a structure to sit in that pointer and act as a locus for all things file locking. We allocate a file_lock_context for an inode when the first lock is added to it, and it's only freed when the inode is freed. We use the i_lock to protect the assignment, but afterward it should mostly be accessed locklessly. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cd6818115162..dec0d38b05de 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -626,6 +626,7 @@ struct inode { #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; + struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { @@ -965,6 +966,10 @@ struct file_lock { } fl_u; }; +struct file_lock_context { + struct list_head flc_flock; +}; + /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) @@ -991,6 +996,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ +void locks_free_lock_context(struct file_lock_context *ctx); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); @@ -1048,6 +1054,11 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline void +locks_free_lock_context(struct file_lock_context *ctx) +{ +} + static inline void locks_init_lock(struct file_lock *fl) { return; -- cgit v1.2.3 From bd61e0a9c852de2d705b6f1bb2cc54c5774db570 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert posix locks to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dec0d38b05de..571f113588e9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; + struct list_head flc_posix; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1971,7 +1972,7 @@ static inline int locks_verify_truncate(struct inode *inode, struct file *filp, loff_t size) { - if (inode->i_flock && mandatory_lock(inode)) + if (inode->i_flctx && mandatory_lock(inode)) return locks_mandatory_area( FLOCK_VERIFY_WRITE, inode, filp, size < inode->i_size ? size : inode->i_size, -- cgit v1.2.3 From 8634b51f6ca298fb8b07aa4847340764903533ab Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:55 -0500 Subject: locks: convert lease handling to file_lock_context Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 571f113588e9..2ddec3cf81b9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -969,6 +969,7 @@ struct file_lock { struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; + struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ @@ -1990,7 +1991,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } @@ -2003,7 +2004,7 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) * end up racing with tasks trying to set a new lease on this file. */ smp_mb(); - if (inode->i_flock) + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } -- cgit v1.2.3 From a7231a97467d5a0c36f82f581c76c12c034e4b80 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:56 -0500 Subject: locks: remove i_flock field from struct inode Nothing uses it anymore. Also add a forward declaration for struct file_lock to silence some compiler warnings that the removal triggers. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2ddec3cf81b9..ce0873af0b97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -625,7 +625,6 @@ struct inode { atomic_t i_readcount; /* struct files open RO */ #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ - struct file_lock *i_flock; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; @@ -886,6 +885,8 @@ static inline struct file *get_file(struct file *f) /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; +struct file_lock; + struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); -- cgit v1.2.3 From 6109c85037e53443f29fd39c0de69f578a1cf285 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: add a dedicated spinlock to protect i_flctx lists We can now add a dedicated spinlock without expanding struct inode. Change to using that to protect the various i_flctx lists. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ce0873af0b97..32eafa9b5c9f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -968,6 +968,7 @@ struct file_lock { }; struct file_lock_context { + spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; -- cgit v1.2.3 From 7448cc37b1a6b620d948aaee3bb30960c06d5d5d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: clean up the lm_change prototype Now that we use standard list_heads for tracking leases, we can have lm_change take a pointer to the lease to be modified instead of a double pointer. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 32eafa9b5c9f..94e706a0a408 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -900,7 +900,7 @@ struct lock_manager_operations { void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); - int (*lm_change)(struct file_lock **, int, struct list_head *); + int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); }; @@ -1021,7 +1021,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); -extern int lease_modify(struct file_lock **, int, struct list_head *); +extern int lease_modify(struct file_lock *, int, struct list_head *); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) @@ -1153,7 +1153,7 @@ static inline int vfs_setlease(struct file *filp, long arg, return -EINVAL; } -static inline int lease_modify(struct file_lock **before, int arg, +static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; -- cgit v1.2.3 From 9bd0f45b7037fcfa8b575c7e27d0431d6e6dc3bb Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 16 Jan 2015 15:05:57 -0500 Subject: locks: keep a count of locks on the flctx lists This makes things a bit more efficient in the cifs and ceph lock pushing code. Signed-off-by: Jeff Layton Acked-by: Christoph Hellwig --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 94e706a0a408..f87cb2f03103 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -972,6 +972,9 @@ struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; + int flc_flock_cnt; + int flc_posix_cnt; + int flc_lease_cnt; }; /* The following constant reflects the upper bound of the file/locking space */ -- cgit v1.2.3 From 9d5438f462abd6398cdb7b3211bdcec271873a3b Mon Sep 17 00:00:00 2001 From: Mark Salyzyn Date: Fri, 16 Jan 2015 16:01:10 -0800 Subject: pstore: Add pmsg - user-space accessible pstore object A secured user-space accessible pstore object. Writes to /dev/pmsg0 are appended to the buffer, on reboot the persistent contents are available in /sys/fs/pstore/pmsg-ramoops-[ID]. One possible use is syslogd, or other daemon, can write messages, then on reboot provides a means to triage user-space activities leading up to a panic as a companion to the pstore dmesg or console logs. Signed-off-by: Mark Salyzyn Acked-by: Kees Cook Signed-off-by: Tony Luck --- include/linux/pstore.h | 1 + include/linux/pstore_ram.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index ece0c6bbfcc5..8884f6e507f7 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -39,6 +39,7 @@ enum pstore_type_id { PSTORE_TYPE_PPC_RTAS = 4, PSTORE_TYPE_PPC_OF = 5, PSTORE_TYPE_PPC_COMMON = 6, + PSTORE_TYPE_PMSG = 7, PSTORE_TYPE_UNKNOWN = 255 }; diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 4af3fdc85b01..9c9d6c154c8e 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -81,6 +81,7 @@ struct ramoops_platform_data { unsigned long record_size; unsigned long console_size; unsigned long ftrace_size; + unsigned long pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; }; -- cgit v1.2.3 From b9626f32876debc356fadb6e19aebcfe9d70c5ff Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Mon, 1 Dec 2014 19:32:51 +0100 Subject: tpm/tpm_i2c_stm_st33: Add new tpm_stm_dev structure and remove tpm_i2c_buffer[0], [1] buffer. In order to clean big buffers in st33zp24_platform_data structure, replace with tpm_stm_dev for driver internal usage. As only one buffer is really necessary replace with buf field. In the mean time move tpm_i2c_stm_st33.h to include/linux/platform_data. Reviewed-by: Jason Gunthorpe Signed-off-by: Christophe Ricard Signed-off-by: Peter Huewe --- include/linux/platform_data/tpm_i2c_stm_st33.h | 40 ++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 include/linux/platform_data/tpm_i2c_stm_st33.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h new file mode 100644 index 000000000000..88f9cb18113a --- /dev/null +++ b/include/linux/platform_data/tpm_i2c_stm_st33.h @@ -0,0 +1,40 @@ +/* + * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24 + * Copyright (C) 2009, 2010 STMicroelectronics + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + * + * STMicroelectronics version 1.2.0, Copyright (C) 2010 + * STMicroelectronics comes with ABSOLUTELY NO WARRANTY. + * This is free software, and you are welcome to redistribute it + * under certain conditions. + * + * @Author: Christophe RICARD tpmsupport@st.com + * + * @File: stm_st33_tpm_i2c.h + * + * @Date: 09/15/2010 + */ +#ifndef __STM_ST33_TPM_I2C_MAIN_H__ +#define __STM_ST33_TPM_I2C_MAIN_H__ + + +#define TPM_ST33_I2C "st33zp24_i2c" + +struct st33zp24_platform_data { + int io_serirq; + int io_lpcpd; +}; + +#endif /* __STM_ST33_TPM_I2C_MAIN_H__ */ -- cgit v1.2.3 From 76182b6b008b694d095aec1e2eb6c07fae787128 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Mon, 1 Dec 2014 19:32:52 +0100 Subject: tpm/tpm_i2c_stm_st33: Remove reference to io_serirq The serirq gpio pin is used only as interrupt. After driver initialization, the serirq signal is always used through interrupt and never with gpio kernel API. The irq can then be initialized during the platform_data definition within the client->irq pin. Reviewed-by: Jason Gunthorpe Signed-off-by: Christophe Ricard Signed-off-by: Peter Huewe --- include/linux/platform_data/tpm_i2c_stm_st33.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h index 88f9cb18113a..85775cf5f9a5 100644 --- a/include/linux/platform_data/tpm_i2c_stm_st33.h +++ b/include/linux/platform_data/tpm_i2c_stm_st33.h @@ -33,7 +33,6 @@ #define TPM_ST33_I2C "st33zp24_i2c" struct st33zp24_platform_data { - int io_serirq; int io_lpcpd; }; -- cgit v1.2.3 From 3eda7d0ea3a0365aa72a2007f9450f314d92f065 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Tue, 13 Jan 2015 23:13:13 +0100 Subject: tpm/tpm_i2c_stm_st33: Change tpm_i2c_stm_st33.h to tpm_stm_st33.h include/linux/platform_data/tpm_i2c_stm_st33.h can be used by other st33 tpm device driver not using i2c protocol. Reviewed-by: Jason Gunthorpe Signed-off-by: Christophe Ricard Reviewed-by: Peter Huewe Signed-off-by: Peter Huewe --- include/linux/platform_data/tpm_i2c_stm_st33.h | 39 -------------------------- include/linux/platform_data/tpm_stm_st33.h | 39 ++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 39 deletions(-) delete mode 100644 include/linux/platform_data/tpm_i2c_stm_st33.h create mode 100644 include/linux/platform_data/tpm_stm_st33.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h deleted file mode 100644 index 85775cf5f9a5..000000000000 --- a/include/linux/platform_data/tpm_i2c_stm_st33.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24 - * Copyright (C) 2009, 2010 STMicroelectronics - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see . - * - * STMicroelectronics version 1.2.0, Copyright (C) 2010 - * STMicroelectronics comes with ABSOLUTELY NO WARRANTY. - * This is free software, and you are welcome to redistribute it - * under certain conditions. - * - * @Author: Christophe RICARD tpmsupport@st.com - * - * @File: stm_st33_tpm_i2c.h - * - * @Date: 09/15/2010 - */ -#ifndef __STM_ST33_TPM_I2C_MAIN_H__ -#define __STM_ST33_TPM_I2C_MAIN_H__ - - -#define TPM_ST33_I2C "st33zp24_i2c" - -struct st33zp24_platform_data { - int io_lpcpd; -}; - -#endif /* __STM_ST33_TPM_I2C_MAIN_H__ */ diff --git a/include/linux/platform_data/tpm_stm_st33.h b/include/linux/platform_data/tpm_stm_st33.h new file mode 100644 index 000000000000..ff75310c0f47 --- /dev/null +++ b/include/linux/platform_data/tpm_stm_st33.h @@ -0,0 +1,39 @@ +/* + * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24 + * Copyright (C) 2009, 2010 STMicroelectronics + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + * + * STMicroelectronics version 1.2.0, Copyright (C) 2010 + * STMicroelectronics comes with ABSOLUTELY NO WARRANTY. + * This is free software, and you are welcome to redistribute it + * under certain conditions. + * + * @Author: Christophe RICARD tpmsupport@st.com + * + * @File: stm_st33_tpm.h + * + * @Date: 09/15/2010 + */ +#ifndef __STM_ST33_TPM_H__ +#define __STM_ST33_TPM_H__ + +#define TPM_ST33_I2C "st33zp24-i2c" +#define TPM_ST33_SPI "st33zp24-spi" + +struct st33zp24_platform_data { + int io_lpcpd; +}; + +#endif /* __STM_ST33_TPM_H__ */ -- cgit v1.2.3 From 4e3c021fb995bcbb5d1f814d00584cb80eb904a8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 5 Jan 2015 10:52:40 +0100 Subject: clk: Add clk_unregister_{divider, gate, mux} to close memory leak The common clk_register_{divider,gate,mux} functions allocated memory for internal data which wasn't freed anywhere. Drivers using these helpers could only unregister clocks but the memory would still leak. Add corresponding unregister functions which will release all resources. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Stephen Boyd Signed-off-by: Michael Turquette --- include/linux/clk-provider.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d936409520f8..ebb7055a6d84 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -294,6 +294,7 @@ struct clk *clk_register_gate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); +void clk_unregister_gate(struct clk *clk); struct clk_div_table { unsigned int val; @@ -361,6 +362,7 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); +void clk_unregister_divider(struct clk *clk); /** * struct clk_mux - multiplexer clock @@ -411,6 +413,8 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, void __iomem *reg, u8 shift, u32 mask, u8 clk_mux_flags, u32 *table, spinlock_t *lock); +void clk_unregister_mux(struct clk *clk); + void of_fixed_factor_clk_setup(struct device_node *node); /** -- cgit v1.2.3 From 3aeb66176ffa8fefd7a9f7d37bda1d8adcf469a1 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 15 Jan 2015 23:49:37 +0100 Subject: net: replace br_fdb_external_learn_* calls with switchdev notifier events This patch benefits from newly introduced switchdev notifier and uses it to propagate fdb learn events from rocker driver to bridge. That avoids direct function calls and possible use by other listeners (ovs). Suggested-by: Thomas Graf Signed-off-by: Jiri Pirko Signed-off-by: Scott Feldman Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 0a8ce762a47f..a57bca2ea97e 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -50,24 +50,6 @@ extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __use typedef int br_should_route_hook_t(struct sk_buff *skb); extern br_should_route_hook_t __rcu *br_should_route_hook; -#if IS_ENABLED(CONFIG_BRIDGE) -int br_fdb_external_learn_add(struct net_device *dev, - const unsigned char *addr, u16 vid); -int br_fdb_external_learn_del(struct net_device *dev, - const unsigned char *addr, u16 vid); -#else -static inline int br_fdb_external_learn_add(struct net_device *dev, - const unsigned char *addr, u16 vid) -{ - return 0; -} -static inline int br_fdb_external_learn_del(struct net_device *dev, - const unsigned char *addr, u16 vid) -{ - return 0; -} -#endif - #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING) int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); -- cgit v1.2.3 From 0d5484b1c3db8a3870c6100deeb4678594433b2c Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 29 Oct 2014 00:30:58 +0200 Subject: dmaengine: Move dma_get_slave_caps() implementation to dmaengine.c The function is too big to be a static inline. Signed-off-by: Laurent Pinchart Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 32 +------------------------------- 1 file changed, 1 insertion(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 6d34ce91036c..1b4842bb3890 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -758,37 +758,7 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( src_sg, src_nents, flags); } -static inline int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps) -{ - struct dma_device *device; - - if (!chan || !caps) - return -EINVAL; - - device = chan->device; - - /* check if the channel supports slave transactions */ - if (!test_bit(DMA_SLAVE, device->cap_mask.bits)) - return -ENXIO; - - /* - * Check whether it reports it uses the generic slave - * capabilities, if not, that means it doesn't support any - * kind of slave capabilities reporting. - */ - if (!device->directions) - return -ENXIO; - - caps->src_addr_widths = device->src_addr_widths; - caps->dst_addr_widths = device->dst_addr_widths; - caps->directions = device->directions; - caps->residue_granularity = device->residue_granularity; - - caps->cmd_pause = !!device->device_pause; - caps->cmd_terminate = !!device->device_terminate_all; - - return 0; -} +int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps); static inline int dmaengine_terminate_all(struct dma_chan *chan) { -- cgit v1.2.3 From f8c58c1136349fdfa9b605c501f2f911622d3a9a Mon Sep 17 00:00:00 2001 From: Doug Anderson Date: Tue, 2 Dec 2014 15:42:47 -0800 Subject: mmc: dw_mmc: Protect read-modify-write of INTMASK with a lock We're running into cases where our enabling of the SDIO interrupt in dw_mmc doesn't actually take effect. Specifically, adding patch like this: +++ b/drivers/mmc/host/dw_mmc.c @@ -1076,6 +1076,9 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb) mci_writel(host, INTMASK, (int_mask | SDMMC_INT_SDIO(slot->id))); + int_mask = mci_readl(host, INTMASK); + if (!(int_mask & SDMMC_INT_SDIO(slot->id))) + dev_err(&mmc->class_dev, "failed to enable sdio irq\n"); } else { ...actually triggers the error message. That's because the dw_mci_enable_sdio_irq() unsafely does a read-modify-write of the INTMASK register. We can't just use the standard host->lock since that lock is not irq safe and mmc_signal_sdio_irq() (called from interrupt context) calls dw_mci_enable_sdio_irq(). Add a new irq-safe lock to protect INTMASK. An alternate solution to this is to punt mmc_signal_sdio_irq() to the tasklet and then protect INTMASK modifications by the standard host lock. This seemed like a bit more of a high-latency change. Reported-by: Bing Zhao Signed-off-by: Doug Anderson Reviewed-by: James Hogan Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 42b724e8d503..471fb3116dbe 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -106,6 +106,11 @@ struct mmc_data; * @cur_slot, @mrq and @state. These must always be updated * at the same time while holding @lock. * + * @irq_lock is an irq-safe spinlock protecting the INTMASK register + * to allow the interrupt handler to modify it directly. Held for only long + * enough to read-modify-write INTMASK and no other locks are grabbed when + * holding this one. + * * The @mrq field of struct dw_mci_slot is also protected by @lock, * and must always be written at the same time as the slot is added to * @queue. @@ -125,6 +130,7 @@ struct mmc_data; */ struct dw_mci { spinlock_t lock; + spinlock_t irq_lock; void __iomem *regs; struct scatterlist *sg; -- cgit v1.2.3 From 61bd8a04b379e4fefbc0b0d06941d3f91071bb8c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 12 Dec 2014 08:43:08 +1100 Subject: mmc: omap_hsmmc: remove prepare/complete system suspend support. The only function of these 'prepare' and 'complete' is to disable the 'card detect' irq during suspend. The commit which added this, commit a48ce884d5819d5df2cf1139ab3c43f8e9e419b3 mmc: omap_hsmmc: Introduce omap_hsmmc_prepare/complete justified it by the need to avoid the registration of new devices during suspend. However mmc_pm_notify will set ->rescan_disable in the 'prepare' stage and clear it in the 'complete' stage, so no card detection will actually happen. Also the interrupt will be disabled before final suspend as part of common suspend processing. So this disabling of the interrupt is unnecessary, and interferes with a transition to using common code for card-detect management. Cc: Felipe Balbi Cc: Venkatraman S Cc: Chris Ball Signed-off-by: NeilBrown Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-omap.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h index 5c188f4e9bec..929469291406 100644 --- a/include/linux/platform_data/mmc-omap.h +++ b/include/linux/platform_data/mmc-omap.h @@ -31,10 +31,6 @@ struct omap_mmc_platform_data { void (*cleanup)(struct device *dev); void (*shutdown)(struct device *dev); - /* To handle board related suspend/resume functionality for MMC */ - int (*suspend)(struct device *dev, int slot); - int (*resume)(struct device *dev, int slot); - /* Return context loss count due to PM states changing */ int (*get_context_loss_count)(struct device *dev); -- cgit v1.2.3 From eddbc3abc5bf11bdfc92ef84fd97ec4d379b7278 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 18 Dec 2014 15:44:32 +0100 Subject: mmc: slot-gpio: Remove option to explicitly free requested CD/WP GPIOs The slot-gpio uses the devm*_ managed functions. Still it provide APIs to explicitly free requested CD/WP GPIOs, but these API isn't being used. Therefore let's simplify slot-gpio by removing these unused APIs. If it later turns out we need some of them, we can always consider to restore the code. Signed-off-by: Ulf Hansson --- include/linux/mmc/slot-gpio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index e56fa24c9322..4a36d6954631 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -15,12 +15,10 @@ struct mmc_host; int mmc_gpio_get_ro(struct mmc_host *host); int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio); -void mmc_gpio_free_ro(struct mmc_host *host); int mmc_gpio_get_cd(struct mmc_host *host); int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio, unsigned int debounce); -void mmc_gpio_free_cd(struct mmc_host *host); int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, @@ -28,7 +26,6 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert); -void mmc_gpiod_free_cd(struct mmc_host *host); void mmc_gpiod_request_cd_irq(struct mmc_host *host); #endif -- cgit v1.2.3 From df8aca162e5ff2b20c7a4de3e64e5b96ff838ab0 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 18 Dec 2014 15:44:36 +0100 Subject: mmc: slot-gpio: Rework how to handle allocation of slot-gpio data By moving the allocation of the slot-gpio data into mmc_alloc_host(), we can remove the slot-gpio internal calls to mmc_gpio_alloc(). This means mmc_gpio_alloc() has now only one caller left, which consequence allow us to simplify and remove some of the slot-gpio code. Additionally, this makes the slot-gpio mutex redundant, so let's remove it. Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9f322706f7cb..b6bf718c3498 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -166,7 +166,6 @@ struct mmc_async_req { * struct mmc_slot - MMC slot functions * * @cd_irq: MMC/SD-card slot hotplug detection IRQ or -EINVAL - * @lock: protect the @handler_priv pointer * @handler_priv: MMC/SD-card slot context * * Some MMC/SD host controllers implement slot-functions like card and @@ -176,7 +175,6 @@ struct mmc_async_req { */ struct mmc_slot { int cd_irq; - struct mutex lock; void *handler_priv; }; -- cgit v1.2.3 From 04cdbbfa73ebac57a30ec2ebebfd7e9342bbdc44 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 1 Dec 2014 16:53:34 +0100 Subject: mmc: core: Make tuning block patterns static Since previous patches removed the need for the tuning block patterns to be exported, let's move them close to the mmc_send_tuning() API. Those are now intended to be used only by the mmc core. Signed-off-by: Ulf Hansson Reviewed-by: Stephen Boyd Acked-by: Jaehoon Chung --- include/linux/mmc/mmc.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 49ad7a943638..fb97b5cc91cd 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -53,11 +53,6 @@ #define MMC_SEND_TUNING_BLOCK 19 /* adtc R1 */ #define MMC_SEND_TUNING_BLOCK_HS200 21 /* adtc R1 */ -#define MMC_TUNING_BLK_PATTERN_4BIT_SIZE 64 -#define MMC_TUNING_BLK_PATTERN_8BIT_SIZE 128 -extern const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE]; -extern const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE]; - /* class 3 */ #define MMC_WRITE_DAT_UNTIL_STOP 20 /* adtc [31:0] data addr R1 */ -- cgit v1.2.3 From 348487cb28e66b032bae1b38424d81bf5b444408 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Tue, 9 Dec 2014 17:04:05 +0800 Subject: mmc: sdhci: use pipeline mmc requests to improve performance This patch is based on the patches by Per Forlin, Tony Lin and Ryan QIAN. This patch complete the API 'post_req' and 'pre_req' in sdhci host side, Test Env: 1. i.MX6Q-SABREAUTO board, CPU @ 996MHz, use ADMA in uSDHC controller. 2. Test command: $ echo 1 > /proc/sys/vm/drop_caches write to sd card: $ dd if=/dev/zero of=/dev/mmcblk0 bs=1M count=2000 conv=fsync read the sd card: $ dd if=/dev/mmcblk0 of=/dev/null bs=1M count=2000 3. TOSHIBA 16GB SD3.0 card, running at 4 bit, SDR104 @ 198MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~76.7 MB/s | ~23.3 MB/s | |------------------------------------------------ |without this patch | ~60.5 MB/s | ~22.5 MB/s | ------------------------------------------------- 4. SanDisk 8GB SD3.0 card, running at 4 bit, DDR50 @ 50MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~40.5 MB/s | ~15.6 MB/s | |------------------------------------------------ |without this patch | ~36.1 MB/s | ~14.1 MB/s | ------------------------------------------------- 5. Kingston 8GB SD2.0 card, running at 4 bit, High-speed @ 50MHZ Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~22.7 MB/s | ~8.2 MB/s | |------------------------------------------------ |without this patch | ~21.3 MB/s | ~8.0 MB/s | ------------------------------------------------- 6. About eMMC, Sandisk 8GB eMMC on i.MX6DL-sabresd board, CPU @ 792MHZ, eMMC running at 8 bit, DDR52 @ 52MHZ. Performance with and without this patch: ------------------------------------------------- | | read speed | write speed | |------------------------------------------------ | with this patch | ~37.3 MB/s | ~10.5 MB/s | |------------------------------------------------ |without this patch | ~33.4 MB/s | ~10.5 MB/s | ------------------------------------------------- Signed-off-by: Haibo Chen Signed-off-by: Ulf Hansson --- include/linux/mmc/sdhci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index f767a0de611f..cb8b94ff6a26 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -17,6 +17,11 @@ #include #include +struct sdhci_host_next { + unsigned int sg_count; + s32 cookie; +}; + struct sdhci_host { /* Data set by hardware interface driver */ const char *hw_name; /* Hardware bus name */ @@ -203,6 +208,7 @@ struct sdhci_host { #define SDHCI_TUNING_MODE_1 0 struct timer_list tuning_timer; /* Timer for tuning */ + struct sdhci_host_next next_data; unsigned long private[0] ____cacheline_aligned; }; #endif /* LINUX_MMC_SDHCI_H */ -- cgit v1.2.3 From 83533ab28380f6957af39a7b322e639e42dbdaf1 Mon Sep 17 00:00:00 2001 From: Johan Rudholm Date: Mon, 12 Jan 2015 15:38:04 +0100 Subject: mmc: core: always check status after reset Always check if the card is alive after a successful reset. This allows us to remove mmc_hw_reset_check(), leaving mmc_hw_reset() as the only card reset interface. Signed-off-by: Johan Rudholm Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index cb2b0400d284..160448f920ac 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -182,7 +182,6 @@ extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); extern int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount, bool is_rel_write); extern int mmc_hw_reset(struct mmc_host *host); -extern int mmc_hw_reset_check(struct mmc_host *host); extern int mmc_can_reset(struct mmc_card *card); extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *); -- cgit v1.2.3 From c7ea834d81904b71505093f7ec50d036132cf628 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 13 Jan 2015 08:23:18 +1300 Subject: mmc: slot-gpio: Allow host driver to provide isr for card-detect interrupts One of the reasons omap_hsmmc doesn't use the slot-gpio library is that it has some non-standard functionality in the card-detect interrupt service routine. To make it possible for omap_hsmmc (and maybe others) to be converted to use slot-gpio, add 'mmc_gpio_request_cd_isr' which provide an alternate isr to be register by the slot-gpio code. Signed-off-by: NeilBrown Signed-off-by: Ulf Hansson --- include/linux/mmc/slot-gpio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 4a36d6954631..3945a8c9d3cb 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -26,6 +26,8 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce, bool *gpio_invert); +void mmc_gpio_set_cd_isr(struct mmc_host *host, + irqreturn_t (*isr)(int irq, void *dev_id)); void mmc_gpiod_request_cd_irq(struct mmc_host *host); #endif -- cgit v1.2.3 From fdb8df9933632e177621daf60da74fc693a8c7d1 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 19 Jan 2015 13:54:27 +0200 Subject: dmaengine: Add dma_get_slave_caps() inline stub when !CONFIG_DMA_ENGINE Commit 0d5484b1c3db8a38 ("dmaengine: Move dma_get_slave_caps() implementation to dmaengine.c") turned the inline dma_get_slave_caps() function into an external function without adding an inline stub for the cases where CONFIG_DMA_ENGINE isn't set. This breaks compilation of drivers using the DMA engine API when CONFIG_DMA_ENGINE isn't set. Add an inline stub to fix compilation. Signed-off-by: Laurent Pinchart Fixes: 0d5484b1c3db ("dmaengine: Move dma_get_slave_caps() implementation to dmaengine.c") Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 1b4842bb3890..50745e3a8a3f 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -758,8 +758,6 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( src_sg, src_nents, flags); } -int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps); - static inline int dmaengine_terminate_all(struct dma_chan *chan) { if (chan->device->device_terminate_all) @@ -1048,6 +1046,7 @@ struct dma_chan *dma_request_slave_channel_reason(struct device *dev, const char *name); struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); void dma_release_channel(struct dma_chan *chan); +int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps); #else static inline struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) { @@ -1082,6 +1081,11 @@ static inline struct dma_chan *dma_request_slave_channel(struct device *dev, static inline void dma_release_channel(struct dma_chan *chan) { } +static inline int dma_get_slave_caps(struct dma_chan *chan, + struct dma_slave_caps *caps) +{ + return -ENXIO; +} #endif /* --- DMA device --- */ -- cgit v1.2.3 From 927609d622a3773995f84bc03b4564f873cf0e22 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 25 Nov 2014 10:16:39 +0100 Subject: kernel: tighten rules for ACCESS ONCE Now that all non-scalar users of ACCESS_ONCE have been converted to READ_ONCE or ASSIGN once, lets tighten ACCESS_ONCE to only work on scalar types. This variant was proposed by Alexei Starovoitov. Signed-off-by: Christian Borntraeger Reviewed-by: Paul E. McKenney --- include/linux/compiler.h | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index a1c81f80978e..5e186bf6f6c1 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -447,12 +447,23 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int * to make the compiler aware of ordering is to put the two invocations of * ACCESS_ONCE() in different C statements. * - * This macro does absolutely -nothing- to prevent the CPU from reordering, - * merging, or refetching absolutely anything at any time. Its main intended - * use is to mediate communication between process-level code and irq/NMI - * handlers, all running on the same CPU. + * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE + * on a union member will work as long as the size of the member matches the + * size of the union and the size is smaller than word size. + * + * The major use cases of ACCESS_ONCE used to be (1) Mediating communication + * between process-level code and irq/NMI handlers, all running on the same CPU, + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * mutilate accesses that either do not require ordering or that interact + * with an explicit memory barrier or atomic instruction that provides the + * required ordering. + * + * If possible use READ_ONCE/ASSIGN_ONCE instead. */ -#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x)) +#define __ACCESS_ONCE(x) ({ \ + __maybe_unused typeof(x) __var = 0; \ + (volatile typeof(x) *)&(x); }) +#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ #ifdef CONFIG_KPROBES -- cgit v1.2.3 From c5b19946eb76c67566aae6a84bf2b10ad59295ea Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Mon, 12 Jan 2015 12:13:39 +0100 Subject: kernel: Fix sparse warning for ACCESS_ONCE Commit 927609d622a3 ("kernel: tighten rules for ACCESS ONCE") results in sparse warnings like "Using plain integer as NULL pointer" - Let's add a type cast to the dummy assignment. To avoid warnings lik "sparse: warning: cast to restricted __hc32" we also use __force on that cast. Fixes: 927609d622a3 ("kernel: tighten rules for ACCESS ONCE") Signed-off-by: Christian Borntraeger --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5e186bf6f6c1..7bebf0563d18 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -461,7 +461,7 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int * If possible use READ_ONCE/ASSIGN_ONCE instead. */ #define __ACCESS_ONCE(x) ({ \ - __maybe_unused typeof(x) __var = 0; \ + __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \ (volatile typeof(x) *)&(x); }) #define ACCESS_ONCE(x) (*__ACCESS_ONCE(x)) -- cgit v1.2.3 From 85b4545629663486b7f71047ce3b54fa0ad3eb28 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 12 Jan 2015 17:51:14 +0000 Subject: iommu: Consolidate IOVA allocator code In order to share the IOVA allocator with other architectures, break the unnecssary dependency on the Intel IOMMU driver and move the remaining IOVA internals to iova.c Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iova.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 19e81d5ccb6d..ad0507c61cc7 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -39,6 +39,9 @@ static inline unsigned long iova_size(struct iova *iova) return iova->pfn_hi - iova->pfn_lo + 1; } +int iommu_iova_cache_init(void); +void iommu_iova_cache_destroy(void); + struct iova *alloc_iova_mem(void); void free_iova_mem(struct iova *iova); void free_iova(struct iova_domain *iovad, unsigned long pfn); -- cgit v1.2.3 From 1b72250076dde4276acecf3a7da722b185703e78 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 12 Jan 2015 17:51:15 +0000 Subject: iommu: Make IOVA domain low limit flexible To share the IOVA allocator with other architectures, it needs to accommodate more general aperture restrictions; move the lower limit from a compile-time constant to a runtime domain property to allow IOVA domains with different requirements to co-exist. Also reword the slightly unclear description of alloc_iova since we're touching it anyway. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iova.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index ad0507c61cc7..591b19626b46 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -16,9 +16,6 @@ #include #include -/* IO virtual address start page frame number */ -#define IOVA_START_PFN (1) - /* iova structure */ struct iova { struct rb_node node; @@ -31,6 +28,7 @@ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ struct rb_root rbroot; /* iova domain rbtree root */ struct rb_node *cached32_node; /* Save last alloced node */ + unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; }; @@ -52,7 +50,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); -void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit); +void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn, + unsigned long pfn_32bit); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, -- cgit v1.2.3 From 0fb5fe874c42942e16c450ae05da453e13a1c09e Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 12 Jan 2015 17:51:16 +0000 Subject: iommu: Make IOVA domain page size explicit Systems may contain heterogeneous IOMMUs supporting differing minimum page sizes, which may also not be common with the CPU page size. Thus it is practical to have an explicit notion of IOVA granularity to simplify handling of mapping and allocation constraints. As an initial step, move the IOVA page granularity from an implicit compile-time constant to a per-domain property so we can make use of it in IOVA domain context at runtime. To keep the abstraction tidy, extend the little API of inline iova_* helpers to parallel some of the equivalent PAGE_* macros. Signed-off-by: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iova.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 591b19626b46..3920a19d8194 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -28,6 +28,7 @@ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ struct rb_root rbroot; /* iova domain rbtree root */ struct rb_node *cached32_node; /* Save last alloced node */ + unsigned long granule; /* pfn granularity for this domain */ unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; }; @@ -37,6 +38,36 @@ static inline unsigned long iova_size(struct iova *iova) return iova->pfn_hi - iova->pfn_lo + 1; } +static inline unsigned long iova_shift(struct iova_domain *iovad) +{ + return __ffs(iovad->granule); +} + +static inline unsigned long iova_mask(struct iova_domain *iovad) +{ + return iovad->granule - 1; +} + +static inline size_t iova_offset(struct iova_domain *iovad, dma_addr_t iova) +{ + return iova & iova_mask(iovad); +} + +static inline size_t iova_align(struct iova_domain *iovad, size_t size) +{ + return ALIGN(size, iovad->granule); +} + +static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova) +{ + return (dma_addr_t)iova->pfn_lo << iova_shift(iovad); +} + +static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova) +{ + return iova >> iova_shift(iovad); +} + int iommu_iova_cache_init(void); void iommu_iova_cache_destroy(void); @@ -50,8 +81,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); -void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn, - unsigned long pfn_32bit); +void init_iova_domain(struct iova_domain *iovad, unsigned long granule, + unsigned long start_pfn, unsigned long pfn_32bit); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, -- cgit v1.2.3 From c7d7ddee7e24eedde6149eefbcfbfbc7125b9ff0 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 15 Jan 2015 15:09:37 +0100 Subject: ata: libahci: Allow using multiple regulators The current implementation of the libahci allows using multiple PHYs but not multiple regulators. This patch adds the support of multiple regulators. Until now it was mandatory to have a PHY under a subnode, now a port subnode can contain either a regulator or a PHY (or both). In order to be able to asociate a port with a regulator the port are now a platform device in the device tree case. There was only one driver which used directly the regulator field of the ahci_host_priv structure. To preserve the bisectability the change in the ahci_imx driver was done in the same patch. Signed-off-by: Gregory CLEMENT Acked-by: Hans de Goede Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 642d6ae4030c..f65b33809170 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -24,6 +24,8 @@ struct platform_device; int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); +int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv); +void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv); int ahci_platform_enable_resources(struct ahci_host_priv *hpriv); void ahci_platform_disable_resources(struct ahci_host_priv *hpriv); struct ahci_host_priv *ahci_platform_get_resources( -- cgit v1.2.3 From 54c523127bcca986c6f9b04c7b56a949ea011899 Mon Sep 17 00:00:00 2001 From: Matt Wagantall Date: Mon, 15 Dec 2014 23:47:23 +0000 Subject: iopoll: Introduce memory-mapped IO polling macros It is sometimes necessary to poll a memory-mapped register until its value satisfies some condition. Introduce a family of convenience macros that do this. Tight-looping, sleeping, and timing out can all be accomplished using these macros. Cc: Thierry Reding Cc: Andrew Morton Cc: Robert Elliott Acked-by: Arnd Bergmann Acked-by: Will Deacon Signed-off-by: Matt Wagantall Signed-off-by: Mitchel Humpherys Signed-off-by: Will Deacon --- include/linux/iopoll.h | 144 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 144 insertions(+) create mode 100644 include/linux/iopoll.h (limited to 'include/linux') diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h new file mode 100644 index 000000000000..1c30014ed176 --- /dev/null +++ b/include/linux/iopoll.h @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2012-2014 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_IOPOLL_H +#define _LINUX_IOPOLL_H + +#include +#include +#include +#include +#include +#include + +/** + * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + might_sleep_if(sleep_us); \ + for (;;) { \ + (val) = op(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + (val) = op(addr); \ + break; \ + } \ + if (sleep_us) \ + usleep_range((sleep_us >> 2) + 1, sleep_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + +/** + * readx_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs + * @op: accessor function (takes @addr as its only argument) + * @addr: Address to poll + * @val: Variable to read the value into + * @cond: Break condition (usually involving @val) + * @delay_us: Time to udelay between reads in us (0 tight-loops). Should + * be less than ~10us since udelay is used (see + * Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. + * + * When available, you'll probably want to use one of the specialized + * macros defined below rather than this macro directly. + */ +#define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + for (;;) { \ + (val) = op(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + (val) = op(addr); \ + break; \ + } \ + if (delay_us) \ + udelay(delay_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + + +#define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us) + +#define readb_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readb, addr, val, cond, delay_us, timeout_us) + +#define readw_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readw, addr, val, cond, delay_us, timeout_us) + +#define readw_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readw, addr, val, cond, delay_us, timeout_us) + +#define readl_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readl, addr, val, cond, delay_us, timeout_us) + +#define readl_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readl, addr, val, cond, delay_us, timeout_us) + +#define readq_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readq, addr, val, cond, delay_us, timeout_us) + +#define readq_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readq, addr, val, cond, delay_us, timeout_us) + +#define readb_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readb_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readb_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readb_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readw_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readw_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readw_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readw_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readl_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readl_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readl_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readl_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readq_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout(readq_relaxed, addr, val, cond, delay_us, timeout_us) + +#define readq_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \ + readx_poll_timeout_atomic(readq_relaxed, addr, val, cond, delay_us, timeout_us) + +#endif /* _LINUX_IOPOLL_H */ -- cgit v1.2.3 From 379dcfb406002d855fa56f9c3d290c4048f44e9c Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Mon, 19 Jan 2015 00:13:39 +0100 Subject: crypto: doc - remove colons in comments As documented in Documentation/kernel-doc-nano-HOWTO.txt lines terminated with a colon are treated as headings. The current layout of the documentation when compiling the kernel crypto API DocBook documentation is messed up by by treating some lines as headings. The patch removes colons from comments that shall not be treated as headings. Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- include/linux/crypto.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 90998348e564..fb5ef16d6a12 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -1147,7 +1147,7 @@ static inline void ablkcipher_request_free(struct ablkcipher_request *req) * cipher operation completes. * * The callback function is registered with the ablkcipher_request handle and - * must comply with the following template: + * must comply with the following template * * void callback_function(struct crypto_async_request *req, int error) */ @@ -1174,7 +1174,7 @@ static inline void ablkcipher_request_set_callback( * * For encryption, the source is treated as the plaintext and the * destination is the ciphertext. For a decryption operation, the use is - * reversed: the source is the ciphertext and the destination is the plaintext. + * reversed - the source is the ciphertext and the destination is the plaintext. */ static inline void ablkcipher_request_set_crypt( struct ablkcipher_request *req, @@ -1509,7 +1509,7 @@ static inline void aead_request_free(struct aead_request *req) * completes * * The callback function is registered with the aead_request handle and - * must comply with the following template: + * must comply with the following template * * void callback_function(struct crypto_async_request *req, int error) */ @@ -1536,7 +1536,7 @@ static inline void aead_request_set_callback(struct aead_request *req, * * For encryption, the source is treated as the plaintext and the * destination is the ciphertext. For a decryption operation, the use is - * reversed: the source is the ciphertext and the destination is the plaintext. + * reversed - the source is the ciphertext and the destination is the plaintext. * * IMPORTANT NOTE AEAD requires an authentication tag (MAC). For decryption, * the caller must concatenate the ciphertext followed by the -- cgit v1.2.3 From 67d0d04a762db4bd610fd628ad683b5d7dc905e7 Mon Sep 17 00:00:00 2001 From: Vincent Yang Date: Tue, 20 Jan 2015 16:05:16 +0800 Subject: mmc: sdhci: add a quirk for tuning work around This patch defines a quirk for tuning work around for some sdhci host controller. It sets both SDHCI_CTRL_EXEC_TUNING and SDHCI_CTRL_TUNED_CLK for tuning. It is a preparation and will be used by Fujitsu SDHCI controller f_sdh30 driver. Signed-off-by: Vincent Yang Signed-off-by: Ulf Hansson --- include/linux/mmc/sdhci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index cb8b94ff6a26..933b897ca095 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -111,6 +111,8 @@ struct sdhci_host { #define SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD (1<<10) /* Capability register bit-63 indicates HS400 support */ #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 (1<<11) +/* forced tuned clock */ +#define SDHCI_QUIRK2_TUNING_WORK_AROUND (1<<12) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.2.3 From d3fc5d71ac4dfd28a66689cfd1eea84c4dba8bde Mon Sep 17 00:00:00 2001 From: Vincent Yang Date: Tue, 20 Jan 2015 16:05:17 +0800 Subject: mmc: sdhci: add a quirk for single block transactions This patch defines a quirk to disable the block count for single block transactions. It is a preparation and will be used by Fujitsu SDHCI controller f_sdh30 driver. Signed-off-by: Vincent Yang Signed-off-by: Ulf Hansson --- include/linux/mmc/sdhci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 933b897ca095..c3e3db196738 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -113,6 +113,8 @@ struct sdhci_host { #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400 (1<<11) /* forced tuned clock */ #define SDHCI_QUIRK2_TUNING_WORK_AROUND (1<<12) +/* disable the block count for single block transactions */ +#define SDHCI_QUIRK2_SUPPORT_SINGLE (1<<13) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.2.3 From 94b110aff8679b14f46fd6653ea87b42fe1555be Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:22 +0000 Subject: mmc: tmio: add tmio_mmc_host_alloc/free() Current tmio_mmc driver is using tmio_mmc_data for driver/platform specific data/callback, and it is needed for tmio_mmc_host_probe() function. Because of this style, include/linux/mfd/tmio.h header has tmio driver/framework specific data which is not needed from platform. This patch adds new tmio_mmc_host_alloc/free() as cleanup preparation. tmio driver specific data/callback will be implemented in tmio_mmc_host, and platform specific data/callback will be implemented in tmio_mmc_data in this cleanup. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 57388171610d..c7d9af042d09 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -135,7 +135,6 @@ struct tmio_mmc_data { unsigned long bus_shift; u32 ocr_mask; /* available voltages */ struct tmio_mmc_dma *dma; - struct device *dev; unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From 7ecc09bab1e856e6730a4dd8a3bc1c28bb6ab3be Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:33 +0000 Subject: mmc: tmio: tmio_mmc_host has .dma Current .dma is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index c7d9af042d09..8d708c7cf681 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -112,16 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); struct dma_chan; -struct tmio_mmc_dma { - void *chan_priv_tx; - void *chan_priv_rx; - int slave_id_tx; - int slave_id_rx; - int alignment_shift; - dma_addr_t dma_rx_offset; - bool (*filter)(struct dma_chan *chan, void *arg); -}; - struct tmio_mmc_host; /* @@ -134,7 +124,6 @@ struct tmio_mmc_data { unsigned long flags; unsigned long bus_shift; u32 ocr_mask; /* available voltages */ - struct tmio_mmc_dma *dma; unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); -- cgit v1.2.3 From dfe9a229e0a66b6a00439cea2885ad3b5d3e0840 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:42 +0000 Subject: mmc: tmio: tmio_mmc_host has .write16_hook Current .write16_hook is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 8d708c7cf681..0872ca1e5dc2 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -112,8 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); struct dma_chan; -struct tmio_mmc_host; - /* * data for the MMC controller */ @@ -127,7 +125,6 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - int (*write16_hook)(struct tmio_mmc_host *host, int addr); /* clock management callbacks */ int (*clk_enable)(struct platform_device *pdev, unsigned int *f); void (*clk_disable)(struct platform_device *pdev); -- cgit v1.2.3 From 4fe2ec57a15f98c232536cf04e7c139d830955d4 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:57:52 +0000 Subject: mmc: tmio: tmio_mmc_host has .clk_enable Current .clk_enable is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 0872ca1e5dc2..472587a02a42 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -126,7 +126,6 @@ struct tmio_mmc_data { void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); /* clock management callbacks */ - int (*clk_enable)(struct platform_device *pdev, unsigned int *f); void (*clk_disable)(struct platform_device *pdev); int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); -- cgit v1.2.3 From 00452c11ea0e4e5822edf0ac46853933860d0f53 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:01 +0000 Subject: mmc: tmio: tmio_mmc_host has .clk_disable Current .clk_disable is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 472587a02a42..a3f78da70af7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -125,8 +125,7 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - /* clock management callbacks */ - void (*clk_disable)(struct platform_device *pdev); + int (*multi_io_quirk)(struct mmc_card *card, unsigned int direction, int blk_size); }; -- cgit v1.2.3 From 85c02ddd591e5252eb1cbe8743a839638d7415fd Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:10 +0000 Subject: mmc: tmio: tmio_mmc_host has .multi_io_quirk Current .multi_io_quirk is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index a3f78da70af7..3edaa17d1ccd 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -125,9 +125,6 @@ struct tmio_mmc_data { unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); - - int (*multi_io_quirk)(struct mmc_card *card, - unsigned int direction, int blk_size); }; /* -- cgit v1.2.3 From 7445bf9e6f4e5d7755e22c7c9b06f4ae0d6160c6 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:20 +0000 Subject: mmc: tmio: tmio_mmc_host has .bus_shift Current .bus_shift is implemented under tmio_mmc_data. It goes to tmio_mmc_host by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 3edaa17d1ccd..7a5c27948315 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -120,7 +120,6 @@ struct tmio_mmc_data { unsigned long capabilities; unsigned long capabilities2; unsigned long flags; - unsigned long bus_shift; u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; void (*set_pwr)(struct platform_device *host, int state); -- cgit v1.2.3 From e471df0bcaa137f1bbe7c5f75db6ce7566caa292 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:46 +0000 Subject: mmc: tmio: tmio_mmc_data has .alignment_shift Current .alignment_shift is implemented under tmio_mmc_dma. It goes to tmio_mmc_data by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 7a5c27948315..28a12d10e509 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -122,6 +122,7 @@ struct tmio_mmc_data { unsigned long flags; u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; + int alignment_shift; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 8b4c8f32da91681c0dcd321c9e3cd14f866c5517 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:58:56 +0000 Subject: mmc: tmio: tmio_mmc_data has .dma_rx_offset Current .dma_rx_offset is implemented under tmio_mmc_dma. It goes to tmio_mmc_data by this patch. Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 28a12d10e509..807ecfb162d7 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -123,6 +123,7 @@ struct tmio_mmc_data { u32 ocr_mask; /* available voltages */ unsigned int cd_gpio; int alignment_shift; + dma_addr_t dma_rx_offset; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 010f4aa758f437647799b1fd677a5e2cf31714e9 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 04:59:24 +0000 Subject: mmc: sh_mobile_sdhi: remove .init/.cleanup No one is using .init/.cleanup callback function. Let's remove these. sdhi_ops and .cd_wakeup are also removed Signed-off-by: Kuninori Morimoto Signed-off-by: Ulf Hansson --- include/linux/mmc/sh_mobile_sdhi.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index 68927ae50845..da77e5e2041d 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -3,20 +3,10 @@ #include -struct platform_device; - #define SH_MOBILE_SDHI_IRQ_CARD_DETECT "card_detect" #define SH_MOBILE_SDHI_IRQ_SDCARD "sdcard" #define SH_MOBILE_SDHI_IRQ_SDIO "sdio" -/** - * struct sh_mobile_sdhi_ops - SDHI driver callbacks - * @cd_wakeup: trigger a card-detection run - */ -struct sh_mobile_sdhi_ops { - void (*cd_wakeup)(const struct platform_device *pdev); -}; - struct sh_mobile_sdhi_info { int dma_slave_tx; int dma_slave_rx; @@ -25,11 +15,6 @@ struct sh_mobile_sdhi_info { unsigned long tmio_caps2; u32 tmio_ocr_mask; /* available MMC voltages */ unsigned int cd_gpio; - - /* callbacks for board specific setup code */ - int (*init)(struct platform_device *pdev, - const struct sh_mobile_sdhi_ops *ops); - void (*cleanup)(struct platform_device *pdev); }; #endif /* LINUX_MMC_SH_MOBILE_SDHI_H */ -- cgit v1.2.3 From de122cb1745313f331dc7c7923b484343d455e64 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 13 Jan 2015 05:00:39 +0000 Subject: mmc: tmio: remove TMIO_MMC_HAVE_CTL_DMA_REG flag tmio_mmc_host has .enable_dma callback now. We don't need TMIO_MMC_HAVE_CTL_DMA_REG anymore. Let's remove it Signed-off-by: Kuninori Morimoto Acked-by: Lee Jones Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 807ecfb162d7..605812820e48 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -95,11 +95,6 @@ */ #define TMIO_MMC_SDIO_STATUS_QUIRK (1 << 8) -/* - * Some controllers have DMA enable/disable register - */ -#define TMIO_MMC_HAVE_CTL_DMA_REG (1 << 9) - /* * Some controllers allows to set SDx actual clock */ -- cgit v1.2.3 From 1dfb4a0d7615811ec4a61b0a7631c8ddc0baf335 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 13 Jan 2015 08:00:29 +0100 Subject: gpio: stmpe: enforce device tree only mode Require that device tree be used with STMPE (all platforms use this) and enforce OF_GPIO, then delete the platform data. Signed-off-by: Linus Walleij --- include/linux/mfd/stmpe.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index f742b6717d52..c9d869027300 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -117,20 +117,6 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) -/** - * struct stmpe_gpio_platform_data - STMPE GPIO platform data - * @norequest_mask: bitmask specifying which GPIOs should _not_ be - * requestable due to different usage (e.g. touch, keypad) - * STMPE_GPIO_NOREQ_* macros can be used here. - * @setup: board specific setup callback. - * @remove: board specific remove callback - */ -struct stmpe_gpio_platform_data { - unsigned norequest_mask; - void (*setup)(struct stmpe *stmpe, unsigned gpio_base); - void (*remove)(struct stmpe *stmpe, unsigned gpio_base); -}; - /** * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform * data @@ -182,7 +168,6 @@ struct stmpe_ts_platform_data { * @irq_over_gpio: true if gpio is used to get irq * @irq_gpio: gpio number over which irq will be requested (significant only if * irq_over_gpio is true) - * @gpio: GPIO-specific platform data * @ts: touchscreen-specific platform data */ struct stmpe_platform_data { @@ -194,7 +179,6 @@ struct stmpe_platform_data { int irq_gpio; int autosleep_timeout; - struct stmpe_gpio_platform_data *gpio; struct stmpe_ts_platform_data *ts; }; -- cgit v1.2.3 From 4b6eade76ad19183464b739e9af1efacdb1bbda8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 20 Jan 2015 11:00:53 +0100 Subject: mfd: max77693: Add defines for MAX77693 charger driver Prepare for adding support for Maxim 77693 charger by adding necessary new defines. Signed-off-by: Krzysztof Kozlowski Acked-by: Lee Jones Signed-off-by: Sebastian Reichel --- include/linux/mfd/max77693-private.h | 108 +++++++++++++++++++++++++++++++++++ 1 file changed, 108 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h index 08dae01258b9..955dd990beaf 100644 --- a/include/linux/mfd/max77693-private.h +++ b/include/linux/mfd/max77693-private.h @@ -143,10 +143,118 @@ enum max77693_pmic_reg { #define FLASH_INT_FLED1_SHORT BIT(3) #define FLASH_INT_OVER_CURRENT BIT(4) +/* Fast charge timer in in hours */ +#define DEFAULT_FAST_CHARGE_TIMER 4 +/* microamps */ +#define DEFAULT_TOP_OFF_THRESHOLD_CURRENT 150000 +/* minutes */ +#define DEFAULT_TOP_OFF_TIMER 30 +/* microvolts */ +#define DEFAULT_CONSTANT_VOLT 4200000 +/* microvolts */ +#define DEFAULT_MIN_SYSTEM_VOLT 3600000 +/* celsius */ +#define DEFAULT_THERMAL_REGULATION_TEMP 100 +/* microamps */ +#define DEFAULT_BATTERY_OVERCURRENT 3500000 +/* microvolts */ +#define DEFAULT_CHARGER_INPUT_THRESHOLD_VOLT 4300000 + +/* MAX77693_CHG_REG_CHG_INT_OK register */ +#define CHG_INT_OK_BYP_SHIFT 0 +#define CHG_INT_OK_BAT_SHIFT 3 +#define CHG_INT_OK_CHG_SHIFT 4 +#define CHG_INT_OK_CHGIN_SHIFT 6 +#define CHG_INT_OK_DETBAT_SHIFT 7 +#define CHG_INT_OK_BYP_MASK BIT(CHG_INT_OK_BYP_SHIFT) +#define CHG_INT_OK_BAT_MASK BIT(CHG_INT_OK_BAT_SHIFT) +#define CHG_INT_OK_CHG_MASK BIT(CHG_INT_OK_CHG_SHIFT) +#define CHG_INT_OK_CHGIN_MASK BIT(CHG_INT_OK_CHGIN_SHIFT) +#define CHG_INT_OK_DETBAT_MASK BIT(CHG_INT_OK_DETBAT_SHIFT) + +/* MAX77693_CHG_REG_CHG_DETAILS_00 register */ +#define CHG_DETAILS_00_CHGIN_SHIFT 5 +#define CHG_DETAILS_00_CHGIN_MASK (0x3 << CHG_DETAILS_00_CHGIN_SHIFT) + +/* MAX77693_CHG_REG_CHG_DETAILS_01 register */ +#define CHG_DETAILS_01_CHG_SHIFT 0 +#define CHG_DETAILS_01_BAT_SHIFT 4 +#define CHG_DETAILS_01_TREG_SHIFT 7 +#define CHG_DETAILS_01_CHG_MASK (0xf << CHG_DETAILS_01_CHG_SHIFT) +#define CHG_DETAILS_01_BAT_MASK (0x7 << CHG_DETAILS_01_BAT_SHIFT) +#define CHG_DETAILS_01_TREG_MASK BIT(7) + +/* MAX77693_CHG_REG_CHG_DETAILS_01/CHG field */ +enum max77693_charger_charging_state { + MAX77693_CHARGING_PREQUALIFICATION = 0x0, + MAX77693_CHARGING_FAST_CONST_CURRENT, + MAX77693_CHARGING_FAST_CONST_VOLTAGE, + MAX77693_CHARGING_TOP_OFF, + MAX77693_CHARGING_DONE, + MAX77693_CHARGING_HIGH_TEMP, + MAX77693_CHARGING_TIMER_EXPIRED, + MAX77693_CHARGING_THERMISTOR_SUSPEND, + MAX77693_CHARGING_OFF, + MAX77693_CHARGING_RESERVED, + MAX77693_CHARGING_OVER_TEMP, + MAX77693_CHARGING_WATCHDOG_EXPIRED, +}; + +/* MAX77693_CHG_REG_CHG_DETAILS_01/BAT field */ +enum max77693_charger_battery_state { + MAX77693_BATTERY_NOBAT = 0x0, + /* Dead-battery or low-battery prequalification */ + MAX77693_BATTERY_PREQUALIFICATION, + MAX77693_BATTERY_TIMER_EXPIRED, + MAX77693_BATTERY_GOOD, + MAX77693_BATTERY_LOWVOLTAGE, + MAX77693_BATTERY_OVERVOLTAGE, + MAX77693_BATTERY_OVERCURRENT, + MAX77693_BATTERY_RESERVED, +}; + +/* MAX77693_CHG_REG_CHG_DETAILS_02 register */ +#define CHG_DETAILS_02_BYP_SHIFT 0 +#define CHG_DETAILS_02_BYP_MASK (0xf << CHG_DETAILS_02_BYP_SHIFT) + /* MAX77693 CHG_CNFG_00 register */ #define CHG_CNFG_00_CHG_MASK 0x1 #define CHG_CNFG_00_BUCK_MASK 0x4 +/* MAX77693_CHG_REG_CHG_CNFG_01 register */ +#define CHG_CNFG_01_FCHGTIME_SHIFT 0 +#define CHG_CNFG_01_CHGRSTRT_SHIFT 4 +#define CHG_CNFG_01_PQEN_SHIFT 7 +#define CHG_CNFG_01_FCHGTIME_MASK (0x7 << CHG_CNFG_01_FCHGTIME_SHIFT) +#define CHG_CNFG_01_CHGRSTRT_MASK (0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT) +#define CHG_CNFG_01_PQEN_MAKS BIT(CHG_CNFG_01_PQEN_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_03 register */ +#define CHG_CNFG_03_TOITH_SHIFT 0 +#define CHG_CNFG_03_TOTIME_SHIFT 3 +#define CHG_CNFG_03_TOITH_MASK (0x7 << CHG_CNFG_03_TOITH_SHIFT) +#define CHG_CNFG_03_TOTIME_MASK (0x7 << CHG_CNFG_03_TOTIME_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_04 register */ +#define CHG_CNFG_04_CHGCVPRM_SHIFT 0 +#define CHG_CNFG_04_MINVSYS_SHIFT 5 +#define CHG_CNFG_04_CHGCVPRM_MASK (0x1f << CHG_CNFG_04_CHGCVPRM_SHIFT) +#define CHG_CNFG_04_MINVSYS_MASK (0x7 << CHG_CNFG_04_MINVSYS_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_06 register */ +#define CHG_CNFG_06_CHGPROT_SHIFT 2 +#define CHG_CNFG_06_CHGPROT_MASK (0x3 << CHG_CNFG_06_CHGPROT_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_07 register */ +#define CHG_CNFG_07_REGTEMP_SHIFT 5 +#define CHG_CNFG_07_REGTEMP_MASK (0x3 << CHG_CNFG_07_REGTEMP_SHIFT) + +/* MAX77693_CHG_REG_CHG_CNFG_12 register */ +#define CHG_CNFG_12_B2SOVRC_SHIFT 0 +#define CHG_CNFG_12_VCHGINREG_SHIFT 3 +#define CHG_CNFG_12_B2SOVRC_MASK (0x7 << CHG_CNFG_12_B2SOVRC_SHIFT) +#define CHG_CNFG_12_VCHGINREG_MASK (0x3 << CHG_CNFG_12_VCHGINREG_SHIFT) + /* MAX77693 CHG_CNFG_09 Register */ #define CHG_CNFG_09_CHGIN_ILIM_MASK 0x7F -- cgit v1.2.3 From 2fded7f44b8fcf79e274c3f0cfbd0298f95308f3 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Tue, 23 Dec 2014 16:39:54 -0500 Subject: audit: remove vestiges of vers_ops Should have been removed with commit 18900909 ("audit: remove the old depricated kernel interface"). Signed-off-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/linux/audit.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 93331929d643..b481779a8dee 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -46,7 +46,6 @@ struct audit_tree; struct sk_buff; struct audit_krule { - int vers_ops; u32 pflags; u32 flags; u32 listnr; -- cgit v1.2.3 From ea2f83a7de9d0abbd145e37177905aab57fdb835 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Sun, 26 Oct 2014 23:17:00 +0000 Subject: arm/arm64: KVM: move kvm_register_device_ops() into vGIC probing Currently we unconditionally register the GICv2 emulation device during the host's KVM initialization. Since with GICv3 support we may end up with only v2 or only v3 or both supported, we move the registration into the GIC probing function, where we will later know which combination is valid. Signed-off-by: Andre Przywara Acked-by: Christoffer Dall Acked-by: Marc Zyngier Signed-off-by: Christoffer Dall --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3b934cc94cc8..25d7ce31a5d4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1051,6 +1051,7 @@ void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_xics_ops; +extern struct kvm_device_ops kvm_arm_vgic_v2_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT -- cgit v1.2.3 From a0675c25d6392c2197b796a60c4a2a0138c86355 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Sat, 7 Jun 2014 00:54:51 +0200 Subject: arm/arm64: KVM: add virtual GICv3 distributor emulation With everything separated and prepared, we implement a model of a GICv3 distributor and redistributors by using the existing framework to provide handler functions for each register group. Currently we limit the emulation to a model enforcing a single security state, with SRE==1 (forcing system register access) and ARE==1 (allowing more than 8 VCPUs). We share some of the functions provided for GICv2 emulation, but take the different ways of addressing (v)CPUs into account. Save and restore is currently not implemented. Similar to the split-off of the GICv2 specific code, the new emulation code goes into a new file (vgic-v3-emul.c). Signed-off-by: Andre Przywara Signed-off-by: Christoffer Dall --- include/linux/irqchip/arm-gic-v3.h | 32 ++++++++++++++++++++++++++++++++ include/linux/kvm_host.h | 1 + 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 1e8b0cf30792..3fb4d8588a26 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -33,6 +33,7 @@ #define GICD_SETSPI_SR 0x0050 #define GICD_CLRSPI_SR 0x0058 #define GICD_SEIR 0x0068 +#define GICD_IGROUPR 0x0080 #define GICD_ISENABLER 0x0100 #define GICD_ICENABLER 0x0180 #define GICD_ISPENDR 0x0200 @@ -41,14 +42,37 @@ #define GICD_ICACTIVER 0x0380 #define GICD_IPRIORITYR 0x0400 #define GICD_ICFGR 0x0C00 +#define GICD_IGRPMODR 0x0D00 +#define GICD_NSACR 0x0E00 #define GICD_IROUTER 0x6000 +#define GICD_IDREGS 0xFFD0 #define GICD_PIDR2 0xFFE8 +/* + * Those registers are actually from GICv2, but the spec demands that they + * are implemented as RES0 if ARE is 1 (which we do in KVM's emulated GICv3). + */ +#define GICD_ITARGETSR 0x0800 +#define GICD_SGIR 0x0F00 +#define GICD_CPENDSGIR 0x0F10 +#define GICD_SPENDSGIR 0x0F20 + #define GICD_CTLR_RWP (1U << 31) +#define GICD_CTLR_DS (1U << 6) #define GICD_CTLR_ARE_NS (1U << 4) #define GICD_CTLR_ENABLE_G1A (1U << 1) #define GICD_CTLR_ENABLE_G1 (1U << 0) +/* + * In systems with a single security state (what we emulate in KVM) + * the meaning of the interrupt group enable bits is slightly different + */ +#define GICD_CTLR_ENABLE_SS_G1 (1U << 1) +#define GICD_CTLR_ENABLE_SS_G0 (1U << 0) + +#define GICD_TYPER_LPIS (1U << 17) +#define GICD_TYPER_MBIS (1U << 16) + #define GICD_TYPER_ID_BITS(typer) ((((typer) >> 19) & 0x1f) + 1) #define GICD_TYPER_IRQS(typer) ((((typer) & 0x1f) + 1) * 32) #define GICD_TYPER_LPIS (1U << 17) @@ -60,6 +84,8 @@ #define GIC_PIDR2_ARCH_GICv3 0x30 #define GIC_PIDR2_ARCH_GICv4 0x40 +#define GIC_V3_DIST_SIZE 0x10000 + /* * Re-Distributor registers, offsets from RD_base */ @@ -78,6 +104,7 @@ #define GICR_SYNCR 0x00C0 #define GICR_MOVLPIR 0x0100 #define GICR_MOVALLR 0x0110 +#define GICR_IDREGS GICD_IDREGS #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) @@ -104,6 +131,7 @@ /* * Re-Distributor registers, offsets from SGI_base */ +#define GICR_IGROUPR0 GICD_IGROUPR #define GICR_ISENABLER0 GICD_ISENABLER #define GICR_ICENABLER0 GICD_ICENABLER #define GICR_ISPENDR0 GICD_ISPENDR @@ -112,11 +140,15 @@ #define GICR_ICACTIVER0 GICD_ICACTIVER #define GICR_IPRIORITYR0 GICD_IPRIORITYR #define GICR_ICFGR0 GICD_ICFGR +#define GICR_IGRPMODR0 GICD_IGRPMODR +#define GICR_NSACR GICD_NSACR #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) #define GICR_TYPER_LAST (1U << 4) +#define GIC_V3_REDIST_SIZE 0x20000 + #define LPI_PROP_GROUP1 (1 << 1) #define LPI_PROP_ENABLED (1 << 0) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 25d7ce31a5d4..0ef2daa199d8 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1052,6 +1052,7 @@ void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; extern struct kvm_device_ops kvm_xics_ops; extern struct kvm_device_ops kvm_arm_vgic_v2_ops; +extern struct kvm_device_ops kvm_arm_vgic_v3_ops; #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT -- cgit v1.2.3 From 7e5802781c3e109558ddfd8b02155ad24d872ee7 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Wed, 12 Nov 2014 13:46:06 +0000 Subject: arm64: GICv3: introduce symbolic names for GICv3 ICC_SGI1R_EL1 fields The gic_send_sgi() function used hardcoded bit shift values to generate the ICC_SGI1R_EL1 register value. Replace this with symbolic names to allow reusing them later. Signed-off-by: Andre Przywara Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall --- include/linux/irqchip/arm-gic-v3.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 3fb4d8588a26..800544bc7bfd 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -280,6 +280,18 @@ #define ICC_SRE_EL2_SRE (1 << 0) #define ICC_SRE_EL2_ENABLE (1 << 3) +#define ICC_SGI1R_TARGET_LIST_SHIFT 0 +#define ICC_SGI1R_TARGET_LIST_MASK (0xffff << ICC_SGI1R_TARGET_LIST_SHIFT) +#define ICC_SGI1R_AFFINITY_1_SHIFT 16 +#define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_SGI_ID_SHIFT 24 +#define ICC_SGI1R_SGI_ID_MASK (0xff << ICC_SGI1R_SGI_ID_SHIFT) +#define ICC_SGI1R_AFFINITY_2_SHIFT 32 +#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40 +#define ICC_SGI1R_AFFINITY_3_SHIFT 48 +#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) + /* * System register definitions */ -- cgit v1.2.3 From 39e794bff718188cfb9ace2032cbe4fd86048dc6 Mon Sep 17 00:00:00 2001 From: Yaniv Gardi Date: Thu, 15 Jan 2015 16:32:36 +0200 Subject: phy: qcom-ufs: add support for 20nm phy This change adds a support for a 20nm qcom-ufs phy that is required in platforms that use ufs-qcom controller. Signed-off-by: Yaniv Gardi Reviewed-by: Dov Levenglick Signed-off-by: Christoph Hellwig --- include/linux/phy/phy-qcom-ufs.h | 59 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 include/linux/phy/phy-qcom-ufs.h (limited to 'include/linux') diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h new file mode 100644 index 000000000000..9d18e9f948e9 --- /dev/null +++ b/include/linux/phy/phy-qcom-ufs.h @@ -0,0 +1,59 @@ +/* + * Copyright (c) 2013-2015, Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef PHY_QCOM_UFS_H_ +#define PHY_QCOM_UFS_H_ + +#include "phy.h" + +/** + * ufs_qcom_phy_enable_ref_clk() - Enable the phy + * ref clock. + * @phy: reference to a generic phy + * + * returns 0 for success, and non-zero for error. + */ +int ufs_qcom_phy_enable_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_disable_ref_clk() - Disable the phy + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_disable_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy); + +/** + * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device + * ref clock. + * @phy: reference to a generic phy. + */ +void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy); + +int ufs_qcom_phy_enable_iface_clk(struct phy *phy); +void ufs_qcom_phy_disable_iface_clk(struct phy *phy); +int ufs_qcom_phy_start_serdes(struct phy *phy); +int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes); +int ufs_qcom_phy_calibrate_phy(struct phy *phy, bool is_rate_B); +int ufs_qcom_phy_is_pcs_ready(struct phy *phy); +void ufs_qcom_phy_save_controller_version(struct phy *phy, + u8 major, u16 minor, u16 step); + +#endif /* PHY_QCOM_UFS_H_ */ -- cgit v1.2.3 From 3c33f5b99d688deafd21d4a770303691c7c3a320 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 20 Jan 2015 09:26:19 -0600 Subject: livepatch: support for repatching a function Add support for patching a function multiple times. If multiple patches affect a function, the function in the most recently enabled patch "wins". This enables a cumulative patch upgrade path, where each patch is a superset of previous patches. This requires restructuring the data a little bit. With the current design, where each klp_func struct has its own ftrace_ops, we'd have to unregister the old ops and then register the new ops, because FTRACE_OPS_FL_IPMODIFY prevents us from having two ops registered for the same function at the same time. That would leave a regression window where the function isn't patched at all (not good for a patch upgrade path). This patch replaces the per-klp_func ftrace_ops with a global klp_ops list, with one ftrace_ops per original function. A single ftrace_ops is shared between all klp_funcs which have the same old_addr. This allows the switch between function versions to happen instantaneously by updating the klp_ops struct's func_stack list. The winner is the klp_func at the top of the func_stack (front of the list). [ jkosina@suse.cz: turn WARN_ON() into WARN_ON_ONCE() in ftrace handler to avoid storm in pathological cases ] Signed-off-by: Josh Poimboeuf Reviewed-by: Jiri Slaby Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 950bc615842f..f14c6fb262b4 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -40,8 +40,8 @@ enum klp_state { * @old_addr: a hint conveying at what address the old function * can be found (optional, vmlinux patches only) * @kobj: kobject for sysfs resources - * @fops: ftrace operations structure * @state: tracks function-level patch application state + * @stack_node: list node for klp_ops func_stack list */ struct klp_func { /* external */ @@ -59,8 +59,8 @@ struct klp_func { /* internal */ struct kobject kobj; - struct ftrace_ops *fops; enum klp_state state; + struct list_head stack_node; }; /** -- cgit v1.2.3 From 97b713ba3ebaa6c8d84c2c720f5468a7c6a6eb4e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:31 +0100 Subject: fs: kill BDI_CAP_SWAP_BACKED This bdi flag isn't too useful - we can determine that a vma is backed by either swap or shmem trivially in the caller. This also allows removing the backing_dev_info instaces for swap and shmem in favor of noop_backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da6012b7a14..e936cea856dc 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -238,8 +238,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_WRITE_MAP: Can be mapped for writing * BDI_CAP_EXEC_MAP: Can be mapped for execution * - * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed. - * * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 @@ -250,7 +248,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_WRITE_MAP 0x00000020 #define BDI_CAP_EXEC_MAP 0x00000040 #define BDI_CAP_NO_ACCT_WB 0x00000080 -#define BDI_CAP_SWAP_BACKED 0x00000100 #define BDI_CAP_STABLE_WRITES 0x00000200 #define BDI_CAP_STRICTLIMIT 0x00000400 @@ -329,11 +326,6 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) BDI_CAP_NO_WRITEBACK)); } -static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) -{ - return bdi->capabilities & BDI_CAP_SWAP_BACKED; -} - static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); @@ -344,11 +336,6 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping) return bdi_cap_account_dirty(mapping->backing_dev_info); } -static inline bool mapping_cap_swap_backed(struct address_space *mapping) -{ - return bdi_cap_swap_backed(mapping->backing_dev_info); -} - static inline int bdi_sched_wait(void *word) { schedule(); -- cgit v1.2.3 From b4caecd48005fbed3949dde6c1cb233142fd69e9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:32 +0100 Subject: fs: introduce f_op->mmap_capabilities for nommu mmap support Since "BDI: Provide backing device capability information [try #3]" the backing_dev_info structure also provides flags for the kind of mmap operation available in a nommu environment, which is entirely unrelated to it's original purpose. Introduce a new nommu-only file operation to provide this information to the nommu mmap code instead. Splitting this from the backing_dev_info structure allows to remove lots of backing_dev_info instance that aren't otherwise needed, and entirely gets rid of the concept of providing a backing_dev_info for a character device. It also removes the need for the mtd_inodefs filesystem. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Acked-by: Brian Norris Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 33 ++++----------------------------- include/linux/cdev.h | 2 -- include/linux/fs.h | 23 +++++++++++++++++++++++ include/linux/mtd/mtd.h | 2 ++ 4 files changed, 29 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e936cea856dc..478f95d92d73 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -114,7 +114,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); -int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); +int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); @@ -228,42 +228,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages - * - * These flags let !MMU mmap() govern direct device mapping vs immediate - * copying more easily for MAP_PRIVATE, especially for ROM filesystems. - * - * BDI_CAP_MAP_COPY: Copy can be mapped (MAP_PRIVATE) - * BDI_CAP_MAP_DIRECT: Can be mapped directly (MAP_SHARED) - * BDI_CAP_READ_MAP: Can be mapped for reading - * BDI_CAP_WRITE_MAP: Can be mapped for writing - * BDI_CAP_EXEC_MAP: Can be mapped for execution - * * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 -#define BDI_CAP_MAP_COPY 0x00000004 -#define BDI_CAP_MAP_DIRECT 0x00000008 -#define BDI_CAP_READ_MAP 0x00000010 -#define BDI_CAP_WRITE_MAP 0x00000020 -#define BDI_CAP_EXEC_MAP 0x00000040 -#define BDI_CAP_NO_ACCT_WB 0x00000080 -#define BDI_CAP_STABLE_WRITES 0x00000200 -#define BDI_CAP_STRICTLIMIT 0x00000400 - -#define BDI_CAP_VMFLAGS \ - (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) +#define BDI_CAP_NO_ACCT_WB 0x00000004 +#define BDI_CAP_STABLE_WRITES 0x00000008 +#define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -#if defined(VM_MAYREAD) && \ - (BDI_CAP_READ_MAP != VM_MAYREAD || \ - BDI_CAP_WRITE_MAP != VM_MAYWRITE || \ - BDI_CAP_EXEC_MAP != VM_MAYEXEC) -#error please change backing_dev_info::capabilities flags -#endif - extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; diff --git a/include/linux/cdev.h b/include/linux/cdev.h index fb4591977b03..f8763615a5f2 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -30,6 +30,4 @@ void cdev_del(struct cdev *); void cd_forget(struct inode *); -extern struct backing_dev_info directly_mappable_cdev_bdi; - #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..1dada399aa23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1502,6 +1502,26 @@ struct block_device_operations; #define HAVE_COMPAT_IOCTL 1 #define HAVE_UNLOCKED_IOCTL 1 +/* + * These flags let !MMU mmap() govern direct device mapping vs immediate + * copying more easily for MAP_PRIVATE, especially for ROM filesystems. + * + * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) + * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) + * NOMMU_MAP_READ: Can be mapped for reading + * NOMMU_MAP_WRITE: Can be mapped for writing + * NOMMU_MAP_EXEC: Can be mapped for execution + */ +#define NOMMU_MAP_COPY 0x00000001 +#define NOMMU_MAP_DIRECT 0x00000008 +#define NOMMU_MAP_READ VM_MAYREAD +#define NOMMU_MAP_WRITE VM_MAYWRITE +#define NOMMU_MAP_EXEC VM_MAYEXEC + +#define NOMMU_VMFLAGS \ + (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) + + struct iov_iter; struct file_operations { @@ -1536,6 +1556,9 @@ struct file_operations { long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); +#ifndef CONFIG_MMU + unsigned (*mmap_capabilities)(struct file *); +#endif }; struct inode_operations { diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 031ff3a9a0bd..3301c4c289d6 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -408,4 +408,6 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { return mtd_is_bitflip(err) || mtd_is_eccerr(err); } +unsigned mtd_mmap_capabilities(struct mtd_info *mtd); + #endif /* __MTD_MTD_H__ */ -- cgit v1.2.3 From de1414a654e66b81b5348dbc5259ecf2fb61655e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:36 +0100 Subject: fs: export inode_to_bdi and use it in favor of mapping->backing_dev_info Now that we got rid of the bdi abuse on character devices we can always use sb->s_bdi to get at the backing_dev_info for a file, except for the block device special case. Export inode_to_bdi and replace uses of mapping->backing_dev_info with it to prepare for the removal of mapping->backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 478f95d92d73..ed59dee03a71 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,6 +106,8 @@ struct backing_dev_info { #endif }; +struct backing_dev_info *inode_to_bdi(struct inode *inode); + int __must_check bdi_init(struct backing_dev_info *bdi); void bdi_destroy(struct backing_dev_info *bdi); @@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { - return bdi_cap_writeback_dirty(mapping->backing_dev_info); + return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); } static inline bool mapping_cap_account_dirty(struct address_space *mapping) { - return bdi_cap_account_dirty(mapping->backing_dev_info); + return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); } static inline int bdi_sched_wait(void *word) -- cgit v1.2.3 From b83ae6d421435c6204150300f1c25bfbd39cd62b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:37 +0100 Subject: fs: remove mapping->backing_dev_info Now that we never use the backing_dev_info pointer in struct address_space we can simply remove it and save 4 to 8 bytes in every inode. Signed-off-by: Christoph Hellwig Acked-by: Ryusuke Konishi Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1dada399aa23..65d02de342e1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,6 +34,7 @@ #include #include +struct backing_dev_info; struct export_operations; struct hd_geometry; struct iovec; @@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); -struct backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ @@ -409,7 +409,6 @@ struct address_space { pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ - struct backing_dev_info *backing_dev_info; /* device readahead, etc */ spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -- cgit v1.2.3 From df0ce26cb4ee8bc233d50213b97213532aff0a3c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Jan 2015 10:42:41 +0100 Subject: fs: remove default_backing_dev_info Now that default_backing_dev_info is not used for writeback purposes we can git rid of it easily: - instead of using it's name for tracing unregistered bdi we just use "unknown" - btrfs and ceph can just assign the default read ahead window themselves like several other filesystems already do. - we can assign noop_backing_dev_info as the default one in alloc_super. All filesystems already either assigned their own or noop_backing_dev_info. Signed-off-by: Christoph Hellwig Reviewed-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ed59dee03a71..d94077fea1f8 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) -extern struct backing_dev_info default_backing_dev_info; extern struct backing_dev_info noop_backing_dev_info; int writeback_in_progress(struct backing_dev_info *bdi); -- cgit v1.2.3 From 85cdf36e11557dc367c1361e4b7bb2c4619cae91 Mon Sep 17 00:00:00 2001 From: Rickard Strandqvist Date: Thu, 1 Jan 2015 18:04:52 +0100 Subject: power: ab8500_fg.c: Remove unused function Remove the function ab8500_fg_reinit() that is not used anywhere. This was partially found by using a static code analysis program called cppcheck. Signed-off-by: Rickard Strandqvist Acked-by: Arnd Bergmann Signed-off-by: Sebastian Reichel --- include/linux/mfd/abx500/ab8500-bm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h index cc892a8d8d6e..12a5b396921e 100644 --- a/include/linux/mfd/abx500/ab8500-bm.h +++ b/include/linux/mfd/abx500/ab8500-bm.h @@ -461,7 +461,6 @@ struct ab8500_fg; #ifdef CONFIG_AB8500_BM extern struct abx500_bm_data ab8500_bm_data; -void ab8500_fg_reinit(void); void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA); struct ab8500_btemp *ab8500_btemp_get(void); int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp); -- cgit v1.2.3 From d93ba7a5a97c9f315bacdcdb8de4e5f368e7b396 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Tue, 20 Jan 2015 20:06:30 -0500 Subject: block: Add discard flag to blkdev_issue_zeroout() function blkdev_issue_discard() will zero a given block range. This is done by way of explicit writing, thus provisioning or allocating the blocks on disk. There are use cases where the desired behavior is to zero the blocks but unprovision them if possible. The blocks must deterministically contain zeroes when they are subsequently read back. This patch adds a flag to blkdev_issue_zeroout() that provides this variant. If the discard flag is set and a block device guarantees discard_zeroes_data we will use REQ_DISCARD to clear the block range. If the device does not support discard_zeroes_data or if the discard request fails we will fall back to first REQ_WRITE_SAME and then a regular REQ_WRITE. Also update the callers of blkdev_issue_zero() to reflect the new flag and make sb_issue_zeroout() prefer the discard approach. Signed-off-by: Martin K. Petersen Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e9086be6d9a0..4c4b732d7556 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1162,7 +1162,7 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask); + sector_t nr_sects, gfp_t gfp_mask, bool discard); static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { @@ -1176,7 +1176,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - 9), nr_blocks << (sb->s_blocksize_bits - 9), - gfp_mask); + gfp_mask, true); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -- cgit v1.2.3 From 9c45101e88b2bf2ce36b8833fcfa784a9149aa74 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 19 Nov 2014 09:21:58 +0100 Subject: quota: Cleanup flags definitions Currently all quota flags were defined just in kernel-private headers. Export flags readable / writeable from userspace to userspace via include/uapi/linux/quota.h. Signed-off-by: Jan Kara --- include/linux/dqblk_v1.h | 3 --- include/linux/quota.h | 14 ++++++++------ 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h index 3713a7232dd8..c0d4d1e2a45c 100644 --- a/include/linux/dqblk_v1.h +++ b/include/linux/dqblk_v1.h @@ -5,9 +5,6 @@ #ifndef _LINUX_DQBLK_V1_H #define _LINUX_DQBLK_V1_H -/* Root squash turned on */ -#define V1_DQF_RSQUASH 1 - /* Numbers of blocks needed for updates */ #define V1_INIT_ALLOC 1 #define V1_INIT_REWRITE 1 diff --git a/include/linux/quota.h b/include/linux/quota.h index 50978b781a19..0c42113607ce 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,12 +223,14 @@ struct mem_dqinfo { struct super_block; -#define DQF_MASK 0xffff /* Mask for format specific flags */ -#define DQF_GETINFO_MASK 0x1ffff /* Mask for flags passed to userspace */ -#define DQF_SETINFO_MASK 0xffff /* Mask for flags modifiable from userspace */ -#define DQF_SYS_FILE_B 16 -#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B) /* Quota file stored as system file */ -#define DQF_INFO_DIRTY_B 31 +/* Mask for flags passed to userspace */ +#define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE) +/* Mask for flags modifiable from userspace */ +#define DQF_SETINFO_MASK DQF_ROOT_SQUASH + +enum { + DQF_INFO_DIRTY_B = DQF_PRIVATE, +}; #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B) /* Is info dirty? */ extern void mark_info_dirty(struct super_block *sb, int type); -- cgit v1.2.3 From c1155c64e603378dccfc21ee0612cf60dd11725b Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Fri, 19 Dec 2014 17:55:13 +0900 Subject: power: charger-manager: Use alarmtimer for battery monitoring in suspend. To guerantee proper charing and managing batteries even in suspend, charger-manager has used rtc device with rtc framework interface. However, it is better to use alarmtimer for cleaner and more appropriate operation. This patch makes driver to use alarmtimer for polling work in suspend and removes all deprecated codes related with using rtc interface. Signed-off-by: Jonghwa Lee Signed-off-by: Sebastian Reichel --- include/linux/power/charger-manager.h | 32 +------------------------------- 1 file changed, 1 insertion(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h index e97fc656a058..416ebeb6ee1e 100644 --- a/include/linux/power/charger-manager.h +++ b/include/linux/power/charger-manager.h @@ -17,6 +17,7 @@ #include #include +#include enum data_source { CM_BATTERY_PRESENT, @@ -44,29 +45,6 @@ enum cm_event_types { CM_EVENT_OTHERS, }; -/** - * struct charger_global_desc - * @rtc_name: the name of RTC used to wake up the system from suspend. - * @rtc_only_wakeup: - * If the system is woken up by waekup-sources other than the RTC or - * callbacks, Charger Manager should recognize with - * rtc_only_wakeup() returning false. - * If the RTC given to CM is the only wakeup reason, - * rtc_only_wakeup should return true. - * @assume_timer_stops_in_suspend: - * Assume that the jiffy timer stops in suspend-to-RAM. - * When enabled, CM does not rely on jiffies value in - * suspend_again and assumes that jiffies value does not - * change during suspend. - */ -struct charger_global_desc { - char *rtc_name; - - bool (*rtc_only_wakeup)(void); - - bool assume_timer_stops_in_suspend; -}; - /** * struct charger_cable * @extcon_name: the name of extcon device. @@ -266,22 +244,14 @@ struct charger_manager { char psy_name_buf[PSY_NAME_MAX + 1]; struct power_supply charger_psy; - bool status_save_ext_pwr_inserted; - bool status_save_batt; - u64 charging_start_time; u64 charging_end_time; }; #ifdef CONFIG_CHARGER_MANAGER -extern int setup_charger_manager(struct charger_global_desc *gd); -extern bool cm_suspend_again(void); extern void cm_notify_event(struct power_supply *psy, enum cm_event_types type, char *msg); #else -static inline int setup_charger_manager(struct charger_global_desc *gd) -{ return 0; } -static inline bool cm_suspend_again(void) { return false; } static inline void cm_notify_event(struct power_supply *psy, enum cm_event_types type, char *msg) { } #endif -- cgit v1.2.3 From 8116bf4cb62d337c953cfa5369ef4cf83e73140c Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 21 Jan 2015 20:44:01 -0500 Subject: locks: update comments that refer to inode->i_flock Signed-off-by: Jeff Layton --- include/linux/fs.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f87cb2f03103..ddd2fa7cefd3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -925,12 +925,11 @@ int locks_in_grace(struct net *); * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * - * The i_flock list is ordered by: + * The varous i_flctx lists are ordered by: * - * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX - * 2) lock owner - * 3) lock range start - * 4) lock range end + * 1) lock owner + * 2) lock range start + * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ @@ -1992,8 +1991,9 @@ static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) @@ -2005,8 +2005,9 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts - * taken are done before checking inode->i_flock. Otherwise, we could - * end up racing with tasks trying to set a new lease on this file. + * taken are done before checking i_flctx->flc_lease. Otherwise, we + * could end up racing with tasks trying to set a new lease on this + * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) -- cgit v1.2.3 From 30b8b0066cafef274fc92462578ee346211ce7cb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 15 Jan 2015 21:22:39 +0000 Subject: init: Get rid of x86isms The UP local API support can be set up from an early initcall. No need for horrible hackery in the init code. Signed-off-by: Thomas Gleixner Cc: Jiang Liu Cc: Joerg Roedel Cc: Tony Luck Cc: Borislav Petkov Link: http://lkml.kernel.org/r/20150115211703.827943883@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/smp.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/smp.h b/include/linux/smp.h index 93dff5fff524..be91db2a7017 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -151,6 +151,13 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, static inline void kick_all_cpus_sync(void) { } static inline void wake_up_all_idle_cpus(void) { } +#ifdef CONFIG_UP_LATE_INIT +extern void __init up_late_init(void); +static inline void smp_init(void) { up_late_init(); } +#else +static inline void smp_init(void) { } +#endif + #endif /* !SMP */ /* -- cgit v1.2.3 From 0b271258544b3f89f9a14fa3b53e20ec9ce75392 Mon Sep 17 00:00:00 2001 From: Beomho Seo Date: Tue, 9 Dec 2014 21:03:51 +0900 Subject: mfd: rt5033: Add Richtek RT5033 driver core. This patch adds a new driver for Richtek RT5033 driver. RT5033 is a Multifunction device which includes battery charger, fuel gauge, flash LED current source, LDO and synchronous Buck converter. It is interfaced to host controller using I2C interface. Signed-off-by: Beomho Seo Acked-by: Chanwoo Choi Signed-off-by: Lee Jones --- include/linux/mfd/rt5033-private.h | 260 +++++++++++++++++++++++++++++++++++++ include/linux/mfd/rt5033.h | 62 +++++++++ 2 files changed, 322 insertions(+) create mode 100644 include/linux/mfd/rt5033-private.h create mode 100644 include/linux/mfd/rt5033.h (limited to 'include/linux') diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h new file mode 100644 index 000000000000..1b63fc2f42d1 --- /dev/null +++ b/include/linux/mfd/rt5033-private.h @@ -0,0 +1,260 @@ +/* + * MFD core driver for Richtek RT5033 + * + * Copyright (C) 2014 Samsung Electronics, Co., Ltd. + * Author: Beomho Seo + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published bythe Free Software Foundation. + */ + +#ifndef __RT5033_PRIVATE_H__ +#define __RT5033_PRIVATE_H__ + +enum rt5033_reg { + RT5033_REG_CHG_STAT = 0x00, + RT5033_REG_CHG_CTRL1 = 0x01, + RT5033_REG_CHG_CTRL2 = 0x02, + RT5033_REG_DEVICE_ID = 0x03, + RT5033_REG_CHG_CTRL3 = 0x04, + RT5033_REG_CHG_CTRL4 = 0x05, + RT5033_REG_CHG_CTRL5 = 0x06, + RT5033_REG_RT_CTRL0 = 0x07, + RT5033_REG_CHG_RESET = 0x08, + /* Reserved 0x09~0x18 */ + RT5033_REG_RT_CTRL1 = 0x19, + /* Reserved 0x1A~0x20 */ + RT5033_REG_FLED_FUNCTION1 = 0x21, + RT5033_REG_FLED_FUNCTION2 = 0x22, + RT5033_REG_FLED_STROBE_CTRL1 = 0x23, + RT5033_REG_FLED_STROBE_CTRL2 = 0x24, + RT5033_REG_FLED_CTRL1 = 0x25, + RT5033_REG_FLED_CTRL2 = 0x26, + RT5033_REG_FLED_CTRL3 = 0x27, + RT5033_REG_FLED_CTRL4 = 0x28, + RT5033_REG_FLED_CTRL5 = 0x29, + /* Reserved 0x2A~0x40 */ + RT5033_REG_CTRL = 0x41, + RT5033_REG_BUCK_CTRL = 0x42, + RT5033_REG_LDO_CTRL = 0x43, + /* Reserved 0x44~0x46 */ + RT5033_REG_MANUAL_RESET_CTRL = 0x47, + /* Reserved 0x48~0x5F */ + RT5033_REG_CHG_IRQ1 = 0x60, + RT5033_REG_CHG_IRQ2 = 0x61, + RT5033_REG_CHG_IRQ3 = 0x62, + RT5033_REG_CHG_IRQ1_CTRL = 0x63, + RT5033_REG_CHG_IRQ2_CTRL = 0x64, + RT5033_REG_CHG_IRQ3_CTRL = 0x65, + RT5033_REG_LED_IRQ_STAT = 0x66, + RT5033_REG_LED_IRQ_CTRL = 0x67, + RT5033_REG_PMIC_IRQ_STAT = 0x68, + RT5033_REG_PMIC_IRQ_CTRL = 0x69, + RT5033_REG_SHDN_CTRL = 0x6A, + RT5033_REG_OFF_EVENT = 0x6B, + + RT5033_REG_END, +}; + +/* RT5033 Charger state register */ +#define RT5033_CHG_STAT_MASK 0x20 +#define RT5033_CHG_STAT_DISCHARGING 0x00 +#define RT5033_CHG_STAT_FULL 0x10 +#define RT5033_CHG_STAT_CHARGING 0x20 +#define RT5033_CHG_STAT_NOT_CHARGING 0x30 +#define RT5033_CHG_STAT_TYPE_MASK 0x60 +#define RT5033_CHG_STAT_TYPE_PRE 0x20 +#define RT5033_CHG_STAT_TYPE_FAST 0x60 + +/* RT5033 CHGCTRL1 register */ +#define RT5033_CHGCTRL1_IAICR_MASK 0xe0 +#define RT5033_CHGCTRL1_MODE_MASK 0x01 + +/* RT5033 CHGCTRL2 register */ +#define RT5033_CHGCTRL2_CV_MASK 0xfc + +/* RT5033 CHGCTRL3 register */ +#define RT5033_CHGCTRL3_CFO_EN_MASK 0x40 +#define RT5033_CHGCTRL3_TIMER_MASK 0x38 +#define RT5033_CHGCTRL3_TIMER_EN_MASK 0x01 + +/* RT5033 CHGCTRL4 register */ +#define RT5033_CHGCTRL4_EOC_MASK 0x07 +#define RT5033_CHGCTRL4_IPREC_MASK 0x18 + +/* RT5033 CHGCTRL5 register */ +#define RT5033_CHGCTRL5_VPREC_MASK 0x0f +#define RT5033_CHGCTRL5_ICHG_MASK 0xf0 +#define RT5033_CHGCTRL5_ICHG_SHIFT 0x04 +#define RT5033_CHG_MAX_CURRENT 0x0d + +/* RT5033 RT CTRL1 register */ +#define RT5033_RT_CTRL1_UUG_MASK 0x02 +#define RT5033_RT_HZ_MASK 0x01 + +/* RT5033 control register */ +#define RT5033_CTRL_FCCM_BUCK_MASK 0x00 +#define RT5033_CTRL_BUCKOMS_MASK 0x01 +#define RT5033_CTRL_LDOOMS_MASK 0x02 +#define RT5033_CTRL_SLDOOMS_MASK 0x03 +#define RT5033_CTRL_EN_BUCK_MASK 0x04 +#define RT5033_CTRL_EN_LDO_MASK 0x05 +#define RT5033_CTRL_EN_SAFE_LDO_MASK 0x06 +#define RT5033_CTRL_LDO_SLEEP_MASK 0x07 + +/* RT5033 BUCK control register */ +#define RT5033_BUCK_CTRL_MASK 0x1f + +/* RT5033 LDO control register */ +#define RT5033_LDO_CTRL_MASK 0x1f + +/* RT5033 charger property - model, manufacturer */ + +#define RT5033_CHARGER_MODEL "RT5033WSC Charger" +#define RT5033_MANUFACTURER "Richtek Technology Corporation" + +/* + * RT5033 charger fast-charge current lmits (as in CHGCTRL1 register), + * AICR mode limits the input current for example, + * the AIRC 100 mode limits the input current to 100 mA. + */ +#define RT5033_AICR_100_MODE 0x20 +#define RT5033_AICR_500_MODE 0x40 +#define RT5033_AICR_700_MODE 0x60 +#define RT5033_AICR_900_MODE 0x80 +#define RT5033_AICR_1500_MODE 0xc0 +#define RT5033_AICR_2000_MODE 0xe0 +#define RT5033_AICR_MODE_MASK 0xe0 + +/* RT5033 use internal timer need to set time */ +#define RT5033_FAST_CHARGE_TIMER4 0x00 +#define RT5033_FAST_CHARGE_TIMER6 0x01 +#define RT5033_FAST_CHARGE_TIMER8 0x02 +#define RT5033_FAST_CHARGE_TIMER9 0x03 +#define RT5033_FAST_CHARGE_TIMER12 0x04 +#define RT5033_FAST_CHARGE_TIMER14 0x05 +#define RT5033_FAST_CHARGE_TIMER16 0x06 + +#define RT5033_INT_TIMER_ENABLE 0x01 + +/* RT5033 charger termination enable mask */ +#define RT5033_TE_ENABLE_MASK 0x08 + +/* + * RT5033 charger opa mode. RT50300 have two opa mode charger mode + * and boost mode for OTG + */ + +#define RT5033_CHARGER_MODE 0x00 +#define RT5033_BOOST_MODE 0x01 + +/* RT5033 charger termination enable */ +#define RT5033_TE_ENABLE 0x08 + +/* RT5033 charger CFO enable */ +#define RT5033_CFO_ENABLE 0x40 + +/* RT5033 charger constant charge voltage (as in CHGCTRL2 register), uV */ +#define RT5033_CHARGER_CONST_VOLTAGE_LIMIT_MIN 3650000U +#define RT5033_CHARGER_CONST_VOLTAGE_STEP_NUM 25000U +#define RT5033_CHARGER_CONST_VOLTAGE_LIMIT_MAX 4400000U + +/* RT5033 charger pre-charge current limits (as in CHGCTRL4 register), uA */ +#define RT5033_CHARGER_PRE_CURRENT_LIMIT_MIN 350000U +#define RT5033_CHARGER_PRE_CURRENT_STEP_NUM 100000U +#define RT5033_CHARGER_PRE_CURRENT_LIMIT_MAX 650000U + +/* RT5033 charger fast-charge current (as in CHGCTRL5 register), uA */ +#define RT5033_CHARGER_FAST_CURRENT_MIN 700000U +#define RT5033_CHARGER_FAST_CURRENT_STEP_NUM 100000U +#define RT5033_CHARGER_FAST_CURRENT_MAX 2000000U + +/* + * RT5033 charger const-charge end of charger current ( + * as in CHGCTRL4 register), uA + */ +#define RT5033_CHARGER_EOC_MIN 150000U +#define RT5033_CHARGER_EOC_REF 300000U +#define RT5033_CHARGER_EOC_STEP_NUM1 50000U +#define RT5033_CHARGER_EOC_STEP_NUM2 100000U +#define RT5033_CHARGER_EOC_MAX 600000U + +/* + * RT5033 charger pre-charge threshold volt limits + * (as in CHGCTRL5 register), uV + */ + +#define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MIN 2300000U +#define RT5033_CHARGER_PRE_THRESHOLD_STEP_NUM 100000U +#define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MAX 3800000U + +/* + * RT5033 charger enable UUG, If UUG enable MOS auto control by H/W charger + * circuit. + */ +#define RT5033_CHARGER_UUG_ENABLE 0x02 + +/* RT5033 charger High impedance mode */ +#define RT5033_CHARGER_HZ_DISABLE 0x00 +#define RT5033_CHARGER_HZ_ENABLE 0x01 + +/* RT5033 regulator BUCK output voltage uV */ +#define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U +#define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U +#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32 + +/* RT5033 regulator LDO output voltage uV */ +#define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U +#define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U +#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32 + +/* RT5033 regulator SAFE LDO output voltage uV */ +#define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U + +enum rt5033_fuel_reg { + RT5033_FUEL_REG_OCV_H = 0x00, + RT5033_FUEL_REG_OCV_L = 0x01, + RT5033_FUEL_REG_VBAT_H = 0x02, + RT5033_FUEL_REG_VBAT_L = 0x03, + RT5033_FUEL_REG_SOC_H = 0x04, + RT5033_FUEL_REG_SOC_L = 0x05, + RT5033_FUEL_REG_CTRL_H = 0x06, + RT5033_FUEL_REG_CTRL_L = 0x07, + RT5033_FUEL_REG_CRATE = 0x08, + RT5033_FUEL_REG_DEVICE_ID = 0x09, + RT5033_FUEL_REG_AVG_VOLT_H = 0x0A, + RT5033_FUEL_REG_AVG_VOLT_L = 0x0B, + RT5033_FUEL_REG_CONFIG_H = 0x0C, + RT5033_FUEL_REG_CONFIG_L = 0x0D, + /* Reserved 0x0E~0x0F */ + RT5033_FUEL_REG_IRQ_CTRL = 0x10, + RT5033_FUEL_REG_IRQ_FLAG = 0x11, + RT5033_FUEL_VMIN = 0x12, + RT5033_FUEL_SMIN = 0x13, + /* Reserved 0x14~0x1F */ + RT5033_FUEL_VGCOMP1 = 0x20, + RT5033_FUEL_VGCOMP2 = 0x21, + RT5033_FUEL_VGCOMP3 = 0x22, + RT5033_FUEL_VGCOMP4 = 0x23, + /* Reserved 0x24~0xFD */ + RT5033_FUEL_MFA_H = 0xFE, + RT5033_FUEL_MFA_L = 0xFF, + + RT5033_FUEL_REG_END, +}; + +/* RT5033 fuel gauge battery present property */ +#define RT5033_FUEL_BAT_PRESENT 0x02 + +/* RT5033 PMIC interrupts */ +#define RT5033_PMIC_IRQ_BUCKOCP 2 +#define RT5033_PMIC_IRQ_BUCKLV 3 +#define RT5033_PMIC_IRQ_SAFELDOLV 4 +#define RT5033_PMIC_IRQ_LDOLV 5 +#define RT5033_PMIC_IRQ_OT 6 +#define RT5033_PMIC_IRQ_VDDA_UV 7 + +#endif /* __RT5033_PRIVATE_H__ */ diff --git a/include/linux/mfd/rt5033.h b/include/linux/mfd/rt5033.h new file mode 100644 index 000000000000..010cff49a98e --- /dev/null +++ b/include/linux/mfd/rt5033.h @@ -0,0 +1,62 @@ +/* + * MFD core driver for the RT5033 + * + * Copyright (C) 2014 Samsung Electronics + * Author: Beomho Seo + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published bythe Free Software Foundation. + */ + +#ifndef __RT5033_H__ +#define __RT5033_H__ + +#include +#include +#include +#include + +/* RT5033 regulator IDs */ +enum rt5033_regulators { + RT5033_BUCK = 0, + RT5033_LDO, + RT5033_SAFE_LDO, + + RT5033_REGULATOR_NUM, +}; + +struct rt5033_dev { + struct device *dev; + + struct regmap *regmap; + struct regmap_irq_chip_data *irq_data; + int irq; + bool wakeup; +}; + +struct rt5033_battery { + struct i2c_client *client; + struct rt5033_dev *rt5033; + struct regmap *regmap; + struct power_supply psy; +}; + +/* RT5033 charger platform data */ +struct rt5033_charger_data { + unsigned int pre_uamp; + unsigned int pre_uvolt; + unsigned int const_uvolt; + unsigned int eoc_uamp; + unsigned int fast_uamp; +}; + +struct rt5033_charger { + struct device *dev; + struct rt5033_dev *rt5033; + struct power_supply psy; + + struct rt5033_charger_data *chg; +}; + +#endif /* __RT5033_H__ */ -- cgit v1.2.3 From b8fce55c09d3327014191247957d875c9fe5b7ce Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Mon, 22 Dec 2014 16:51:06 +0000 Subject: mfd: Add support for DA9150 combined charger & fuel-gauge device DA9150 is a combined Charger and Fuel-Gauge IC, with additional GPIO and GPADC functionality. Signed-off-by: Adam Thomson Signed-off-by: Lee Jones --- include/linux/mfd/da9150/core.h | 68 ++ include/linux/mfd/da9150/registers.h | 1155 ++++++++++++++++++++++++++++++++++ 2 files changed, 1223 insertions(+) create mode 100644 include/linux/mfd/da9150/core.h create mode 100644 include/linux/mfd/da9150/registers.h (limited to 'include/linux') diff --git a/include/linux/mfd/da9150/core.h b/include/linux/mfd/da9150/core.h new file mode 100644 index 000000000000..76e668933a77 --- /dev/null +++ b/include/linux/mfd/da9150/core.h @@ -0,0 +1,68 @@ +/* + * DA9150 MFD Driver - Core Data + * + * Copyright (c) 2014 Dialog Semiconductor + * + * Author: Adam Thomson + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __DA9150_CORE_H +#define __DA9150_CORE_H + +#include +#include +#include + +/* I2C address paging */ +#define DA9150_REG_PAGE_SHIFT 8 +#define DA9150_REG_PAGE_MASK 0xFF + +/* IRQs */ +#define DA9150_NUM_IRQ_REGS 4 +#define DA9150_IRQ_VBUS 0 +#define DA9150_IRQ_CHG 1 +#define DA9150_IRQ_TCLASS 2 +#define DA9150_IRQ_TJUNC 3 +#define DA9150_IRQ_VFAULT 4 +#define DA9150_IRQ_CONF 5 +#define DA9150_IRQ_DAT 6 +#define DA9150_IRQ_DTYPE 7 +#define DA9150_IRQ_ID 8 +#define DA9150_IRQ_ADP 9 +#define DA9150_IRQ_SESS_END 10 +#define DA9150_IRQ_SESS_VLD 11 +#define DA9150_IRQ_FG 12 +#define DA9150_IRQ_GP 13 +#define DA9150_IRQ_TBAT 14 +#define DA9150_IRQ_GPIOA 15 +#define DA9150_IRQ_GPIOB 16 +#define DA9150_IRQ_GPIOC 17 +#define DA9150_IRQ_GPIOD 18 +#define DA9150_IRQ_GPADC 19 +#define DA9150_IRQ_WKUP 20 + +struct da9150_pdata { + int irq_base; +}; + +struct da9150 { + struct device *dev; + struct regmap *regmap; + struct regmap_irq_chip_data *regmap_irq_data; + int irq; + int irq_base; +}; + +/* Device I/O */ +u8 da9150_reg_read(struct da9150 *da9150, u16 reg); +void da9150_reg_write(struct da9150 *da9150, u16 reg, u8 val); +void da9150_set_bits(struct da9150 *da9150, u16 reg, u8 mask, u8 val); + +void da9150_bulk_read(struct da9150 *da9150, u16 reg, int count, u8 *buf); +void da9150_bulk_write(struct da9150 *da9150, u16 reg, int count, const u8 *buf); +#endif /* __DA9150_CORE_H */ diff --git a/include/linux/mfd/da9150/registers.h b/include/linux/mfd/da9150/registers.h new file mode 100644 index 000000000000..27ca6ee4d840 --- /dev/null +++ b/include/linux/mfd/da9150/registers.h @@ -0,0 +1,1155 @@ +/* + * DA9150 MFD Driver - Registers + * + * Copyright (c) 2014 Dialog Semiconductor + * + * Author: Adam Thomson + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __DA9150_REGISTERS_H +#define __DA9150_REGISTERS_H + +#include + +/* Registers */ +#define DA9150_PAGE_CON 0x000 +#define DA9150_STATUS_A 0x068 +#define DA9150_STATUS_B 0x069 +#define DA9150_STATUS_C 0x06A +#define DA9150_STATUS_D 0x06B +#define DA9150_STATUS_E 0x06C +#define DA9150_STATUS_F 0x06D +#define DA9150_STATUS_G 0x06E +#define DA9150_STATUS_H 0x06F +#define DA9150_STATUS_I 0x070 +#define DA9150_STATUS_J 0x071 +#define DA9150_STATUS_K 0x072 +#define DA9150_STATUS_L 0x073 +#define DA9150_STATUS_N 0x074 +#define DA9150_FAULT_LOG_A 0x076 +#define DA9150_FAULT_LOG_B 0x077 +#define DA9150_EVENT_E 0x078 +#define DA9150_EVENT_F 0x079 +#define DA9150_EVENT_G 0x07A +#define DA9150_EVENT_H 0x07B +#define DA9150_IRQ_MASK_E 0x07C +#define DA9150_IRQ_MASK_F 0x07D +#define DA9150_IRQ_MASK_G 0x07E +#define DA9150_IRQ_MASK_H 0x07F +#define DA9150_PAGE_CON_1 0x080 +#define DA9150_CONFIG_A 0x0E0 +#define DA9150_CONFIG_B 0x0E1 +#define DA9150_CONFIG_C 0x0E2 +#define DA9150_CONFIG_D 0x0E3 +#define DA9150_CONFIG_E 0x0E4 +#define DA9150_CONTROL_A 0x0E5 +#define DA9150_CONTROL_B 0x0E6 +#define DA9150_CONTROL_C 0x0E7 +#define DA9150_GPIO_A_B 0x0E8 +#define DA9150_GPIO_C_D 0x0E9 +#define DA9150_GPIO_MODE_CONT 0x0EA +#define DA9150_GPIO_CTRL_B 0x0EB +#define DA9150_GPIO_CTRL_A 0x0EC +#define DA9150_GPIO_CTRL_C 0x0ED +#define DA9150_GPIO_CFG_A 0x0EE +#define DA9150_GPIO_CFG_B 0x0EF +#define DA9150_GPIO_CFG_C 0x0F0 +#define DA9150_GPADC_MAN 0x0F2 +#define DA9150_GPADC_RES_A 0x0F4 +#define DA9150_GPADC_RES_B 0x0F5 +#define DA9150_PAGE_CON_2 0x100 +#define DA9150_OTP_CONT_SHARED 0x101 +#define DA9150_INTERFACE_SHARED 0x105 +#define DA9150_CONFIG_A_SHARED 0x106 +#define DA9150_CONFIG_D_SHARED 0x109 +#define DA9150_ADETVB_CFG_C 0x150 +#define DA9150_ADETD_STAT 0x151 +#define DA9150_ADET_CMPSTAT 0x152 +#define DA9150_ADET_CTRL_A 0x153 +#define DA9150_ADETVB_CFG_B 0x154 +#define DA9150_ADETVB_CFG_A 0x155 +#define DA9150_ADETAC_CFG_A 0x156 +#define DA9150_ADDETAC_CFG_B 0x157 +#define DA9150_ADETAC_CFG_C 0x158 +#define DA9150_ADETAC_CFG_D 0x159 +#define DA9150_ADETVB_CFG_D 0x15A +#define DA9150_ADETID_CFG_A 0x15B +#define DA9150_ADET_RID_PT_CHG_H 0x15C +#define DA9150_ADET_RID_PT_CHG_L 0x15D +#define DA9150_PPR_TCTR_B 0x160 +#define DA9150_PPR_BKCTRL_A 0x163 +#define DA9150_PPR_BKCFG_A 0x164 +#define DA9150_PPR_BKCFG_B 0x165 +#define DA9150_PPR_CHGCTRL_A 0x166 +#define DA9150_PPR_CHGCTRL_B 0x167 +#define DA9150_PPR_CHGCTRL_C 0x168 +#define DA9150_PPR_TCTR_A 0x169 +#define DA9150_PPR_CHGCTRL_D 0x16A +#define DA9150_PPR_CHGCTRL_E 0x16B +#define DA9150_PPR_CHGCTRL_F 0x16C +#define DA9150_PPR_CHGCTRL_G 0x16D +#define DA9150_PPR_CHGCTRL_H 0x16E +#define DA9150_PPR_CHGCTRL_I 0x16F +#define DA9150_PPR_CHGCTRL_J 0x170 +#define DA9150_PPR_CHGCTRL_K 0x171 +#define DA9150_PPR_CHGCTRL_L 0x172 +#define DA9150_PPR_CHGCTRL_M 0x173 +#define DA9150_PPR_THYST_A 0x174 +#define DA9150_PPR_THYST_B 0x175 +#define DA9150_PPR_THYST_C 0x176 +#define DA9150_PPR_THYST_D 0x177 +#define DA9150_PPR_THYST_E 0x178 +#define DA9150_PPR_THYST_F 0x179 +#define DA9150_PPR_THYST_G 0x17A +#define DA9150_PAGE_CON_3 0x180 +#define DA9150_PAGE_CON_4 0x200 +#define DA9150_PAGE_CON_5 0x280 +#define DA9150_PAGE_CON_6 0x300 +#define DA9150_COREBTLD_STAT_A 0x302 +#define DA9150_COREBTLD_CTRL_A 0x303 +#define DA9150_CORE_CONFIG_A 0x304 +#define DA9150_CORE_CONFIG_C 0x305 +#define DA9150_CORE_CONFIG_B 0x306 +#define DA9150_CORE_CFG_DATA_A 0x307 +#define DA9150_CORE_CFG_DATA_B 0x308 +#define DA9150_CORE_CMD_A 0x309 +#define DA9150_CORE_DATA_A 0x30A +#define DA9150_CORE_DATA_B 0x30B +#define DA9150_CORE_DATA_C 0x30C +#define DA9150_CORE_DATA_D 0x30D +#define DA9150_CORE2WIRE_STAT_A 0x310 +#define DA9150_CORE2WIRE_CTRL_A 0x311 +#define DA9150_FW_CTRL_A 0x312 +#define DA9150_FW_CTRL_C 0x313 +#define DA9150_FW_CTRL_D 0x314 +#define DA9150_FG_CTRL_A 0x315 +#define DA9150_FG_CTRL_B 0x316 +#define DA9150_FW_CTRL_E 0x317 +#define DA9150_FW_CTRL_B 0x318 +#define DA9150_GPADC_CMAN 0x320 +#define DA9150_GPADC_CRES_A 0x322 +#define DA9150_GPADC_CRES_B 0x323 +#define DA9150_CC_CFG_A 0x328 +#define DA9150_CC_CFG_B 0x329 +#define DA9150_CC_ICHG_RES_A 0x32A +#define DA9150_CC_ICHG_RES_B 0x32B +#define DA9150_CC_IAVG_RES_A 0x32C +#define DA9150_CC_IAVG_RES_B 0x32D +#define DA9150_TAUX_CTRL_A 0x330 +#define DA9150_TAUX_RELOAD_H 0x332 +#define DA9150_TAUX_RELOAD_L 0x333 +#define DA9150_TAUX_VALUE_H 0x334 +#define DA9150_TAUX_VALUE_L 0x335 +#define DA9150_AUX_DATA_0 0x338 +#define DA9150_AUX_DATA_1 0x339 +#define DA9150_AUX_DATA_2 0x33A +#define DA9150_AUX_DATA_3 0x33B +#define DA9150_BIF_CTRL 0x340 +#define DA9150_TBAT_CTRL_A 0x342 +#define DA9150_TBAT_CTRL_B 0x343 +#define DA9150_TBAT_RES_A 0x344 +#define DA9150_TBAT_RES_B 0x345 + +/* DA9150_PAGE_CON = 0x000 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_I2C_PAGE_SHIFT 1 +#define DA9150_I2C_PAGE_MASK (0x1f << 1) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_STATUS_A = 0x068 */ +#define DA9150_WKUP_STAT_SHIFT 2 +#define DA9150_WKUP_STAT_MASK (0x0f << 2) +#define DA9150_SLEEP_STAT_SHIFT 6 +#define DA9150_SLEEP_STAT_MASK (0x03 << 6) + +/* DA9150_STATUS_B = 0x069 */ +#define DA9150_VFAULT_STAT_SHIFT 0 +#define DA9150_VFAULT_STAT_MASK BIT(0) +#define DA9150_TFAULT_STAT_SHIFT 1 +#define DA9150_TFAULT_STAT_MASK BIT(1) + +/* DA9150_STATUS_C = 0x06A */ +#define DA9150_VDD33_STAT_SHIFT 0 +#define DA9150_VDD33_STAT_MASK BIT(0) +#define DA9150_VDD33_SLEEP_SHIFT 1 +#define DA9150_VDD33_SLEEP_MASK BIT(1) +#define DA9150_LFOSC_STAT_SHIFT 7 +#define DA9150_LFOSC_STAT_MASK BIT(7) + +/* DA9150_STATUS_D = 0x06B */ +#define DA9150_GPIOA_STAT_SHIFT 0 +#define DA9150_GPIOA_STAT_MASK BIT(0) +#define DA9150_GPIOB_STAT_SHIFT 1 +#define DA9150_GPIOB_STAT_MASK BIT(1) +#define DA9150_GPIOC_STAT_SHIFT 2 +#define DA9150_GPIOC_STAT_MASK BIT(2) +#define DA9150_GPIOD_STAT_SHIFT 3 +#define DA9150_GPIOD_STAT_MASK BIT(3) + +/* DA9150_STATUS_E = 0x06C */ +#define DA9150_DTYPE_SHIFT 0 +#define DA9150_DTYPE_MASK (0x1f << 0) +#define DA9150_DTYPE_DT_NIL (0x00 << 0) +#define DA9150_DTYPE_DT_USB_OTG BIT(0) +#define DA9150_DTYPE_DT_USB_STD (0x02 << 0) +#define DA9150_DTYPE_DT_USB_CHG (0x03 << 0) +#define DA9150_DTYPE_DT_ACA_CHG (0x04 << 0) +#define DA9150_DTYPE_DT_ACA_OTG (0x05 << 0) +#define DA9150_DTYPE_DT_ACA_DOC (0x06 << 0) +#define DA9150_DTYPE_DT_DED_CHG (0x07 << 0) +#define DA9150_DTYPE_DT_CR5_CHG (0x08 << 0) +#define DA9150_DTYPE_DT_CR4_CHG (0x0c << 0) +#define DA9150_DTYPE_DT_PT_CHG (0x11 << 0) +#define DA9150_DTYPE_DT_NN_ACC (0x16 << 0) +#define DA9150_DTYPE_DT_NN_CHG (0x17 << 0) + +/* DA9150_STATUS_F = 0x06D */ +#define DA9150_SESS_VLD_SHIFT 0 +#define DA9150_SESS_VLD_MASK BIT(0) +#define DA9150_ID_ERR_SHIFT 1 +#define DA9150_ID_ERR_MASK BIT(1) +#define DA9150_PT_CHG_SHIFT 2 +#define DA9150_PT_CHG_MASK BIT(2) + +/* DA9150_STATUS_G = 0x06E */ +#define DA9150_RID_SHIFT 0 +#define DA9150_RID_MASK (0xff << 0) + +/* DA9150_STATUS_H = 0x06F */ +#define DA9150_VBUS_STAT_SHIFT 0 +#define DA9150_VBUS_STAT_MASK (0x07 << 0) +#define DA9150_VBUS_STAT_OFF (0x00 << 0) +#define DA9150_VBUS_STAT_WAIT BIT(0) +#define DA9150_VBUS_STAT_CHG (0x02 << 0) +#define DA9150_VBUS_TRED_SHIFT 3 +#define DA9150_VBUS_TRED_MASK BIT(3) +#define DA9150_VBUS_DROP_STAT_SHIFT 4 +#define DA9150_VBUS_DROP_STAT_MASK (0x0f << 4) + +/* DA9150_STATUS_I = 0x070 */ +#define DA9150_VBUS_ISET_STAT_SHIFT 0 +#define DA9150_VBUS_ISET_STAT_MASK (0x1f << 0) +#define DA9150_VBUS_OT_SHIFT 7 +#define DA9150_VBUS_OT_MASK BIT(7) + +/* DA9150_STATUS_J = 0x071 */ +#define DA9150_CHG_STAT_SHIFT 0 +#define DA9150_CHG_STAT_MASK (0x0f << 0) +#define DA9150_CHG_STAT_OFF (0x00 << 0) +#define DA9150_CHG_STAT_SUSP BIT(0) +#define DA9150_CHG_STAT_ACT (0x02 << 0) +#define DA9150_CHG_STAT_PRE (0x03 << 0) +#define DA9150_CHG_STAT_CC (0x04 << 0) +#define DA9150_CHG_STAT_CV (0x05 << 0) +#define DA9150_CHG_STAT_FULL (0x06 << 0) +#define DA9150_CHG_STAT_TEMP (0x07 << 0) +#define DA9150_CHG_STAT_TIME (0x08 << 0) +#define DA9150_CHG_STAT_BAT (0x09 << 0) +#define DA9150_CHG_TEMP_SHIFT 4 +#define DA9150_CHG_TEMP_MASK (0x07 << 4) +#define DA9150_CHG_TEMP_UNDER (0x06 << 4) +#define DA9150_CHG_TEMP_OVER (0x07 << 4) +#define DA9150_CHG_IEND_STAT_SHIFT 7 +#define DA9150_CHG_IEND_STAT_MASK BIT(7) + +/* DA9150_STATUS_K = 0x072 */ +#define DA9150_CHG_IAV_H_SHIFT 0 +#define DA9150_CHG_IAV_H_MASK (0xff << 0) + +/* DA9150_STATUS_L = 0x073 */ +#define DA9150_CHG_IAV_L_SHIFT 5 +#define DA9150_CHG_IAV_L_MASK (0x07 << 5) + +/* DA9150_STATUS_N = 0x074 */ +#define DA9150_CHG_TIME_SHIFT 1 +#define DA9150_CHG_TIME_MASK BIT(1) +#define DA9150_CHG_TRED_SHIFT 2 +#define DA9150_CHG_TRED_MASK BIT(2) +#define DA9150_CHG_TJUNC_CLASS_SHIFT 3 +#define DA9150_CHG_TJUNC_CLASS_MASK (0x07 << 3) +#define DA9150_CHG_TJUNC_CLASS_6 (0x06 << 3) +#define DA9150_EBS_STAT_SHIFT 6 +#define DA9150_EBS_STAT_MASK BIT(6) +#define DA9150_CHG_BAT_REMOVED_SHIFT 7 +#define DA9150_CHG_BAT_REMOVED_MASK BIT(7) + +/* DA9150_FAULT_LOG_A = 0x076 */ +#define DA9150_TEMP_FAULT_SHIFT 0 +#define DA9150_TEMP_FAULT_MASK BIT(0) +#define DA9150_VSYS_FAULT_SHIFT 1 +#define DA9150_VSYS_FAULT_MASK BIT(1) +#define DA9150_START_FAULT_SHIFT 2 +#define DA9150_START_FAULT_MASK BIT(2) +#define DA9150_EXT_FAULT_SHIFT 3 +#define DA9150_EXT_FAULT_MASK BIT(3) +#define DA9150_POR_FAULT_SHIFT 4 +#define DA9150_POR_FAULT_MASK BIT(4) + +/* DA9150_FAULT_LOG_B = 0x077 */ +#define DA9150_VBUS_FAULT_SHIFT 0 +#define DA9150_VBUS_FAULT_MASK BIT(0) +#define DA9150_OTG_FAULT_SHIFT 1 +#define DA9150_OTG_FAULT_MASK BIT(1) + +/* DA9150_EVENT_E = 0x078 */ +#define DA9150_E_VBUS_SHIFT 0 +#define DA9150_E_VBUS_MASK BIT(0) +#define DA9150_E_CHG_SHIFT 1 +#define DA9150_E_CHG_MASK BIT(1) +#define DA9150_E_TCLASS_SHIFT 2 +#define DA9150_E_TCLASS_MASK BIT(2) +#define DA9150_E_TJUNC_SHIFT 3 +#define DA9150_E_TJUNC_MASK BIT(3) +#define DA9150_E_VFAULT_SHIFT 4 +#define DA9150_E_VFAULT_MASK BIT(4) +#define DA9150_EVENTS_H_SHIFT 5 +#define DA9150_EVENTS_H_MASK BIT(5) +#define DA9150_EVENTS_G_SHIFT 6 +#define DA9150_EVENTS_G_MASK BIT(6) +#define DA9150_EVENTS_F_SHIFT 7 +#define DA9150_EVENTS_F_MASK BIT(7) + +/* DA9150_EVENT_F = 0x079 */ +#define DA9150_E_CONF_SHIFT 0 +#define DA9150_E_CONF_MASK BIT(0) +#define DA9150_E_DAT_SHIFT 1 +#define DA9150_E_DAT_MASK BIT(1) +#define DA9150_E_DTYPE_SHIFT 3 +#define DA9150_E_DTYPE_MASK BIT(3) +#define DA9150_E_ID_SHIFT 4 +#define DA9150_E_ID_MASK BIT(4) +#define DA9150_E_ADP_SHIFT 5 +#define DA9150_E_ADP_MASK BIT(5) +#define DA9150_E_SESS_END_SHIFT 6 +#define DA9150_E_SESS_END_MASK BIT(6) +#define DA9150_E_SESS_VLD_SHIFT 7 +#define DA9150_E_SESS_VLD_MASK BIT(7) + +/* DA9150_EVENT_G = 0x07A */ +#define DA9150_E_FG_SHIFT 0 +#define DA9150_E_FG_MASK BIT(0) +#define DA9150_E_GP_SHIFT 1 +#define DA9150_E_GP_MASK BIT(1) +#define DA9150_E_TBAT_SHIFT 2 +#define DA9150_E_TBAT_MASK BIT(2) +#define DA9150_E_GPIOA_SHIFT 3 +#define DA9150_E_GPIOA_MASK BIT(3) +#define DA9150_E_GPIOB_SHIFT 4 +#define DA9150_E_GPIOB_MASK BIT(4) +#define DA9150_E_GPIOC_SHIFT 5 +#define DA9150_E_GPIOC_MASK BIT(5) +#define DA9150_E_GPIOD_SHIFT 6 +#define DA9150_E_GPIOD_MASK BIT(6) +#define DA9150_E_GPADC_SHIFT 7 +#define DA9150_E_GPADC_MASK BIT(7) + +/* DA9150_EVENT_H = 0x07B */ +#define DA9150_E_WKUP_SHIFT 0 +#define DA9150_E_WKUP_MASK BIT(0) + +/* DA9150_IRQ_MASK_E = 0x07C */ +#define DA9150_M_VBUS_SHIFT 0 +#define DA9150_M_VBUS_MASK BIT(0) +#define DA9150_M_CHG_SHIFT 1 +#define DA9150_M_CHG_MASK BIT(1) +#define DA9150_M_TJUNC_SHIFT 3 +#define DA9150_M_TJUNC_MASK BIT(3) +#define DA9150_M_VFAULT_SHIFT 4 +#define DA9150_M_VFAULT_MASK BIT(4) + +/* DA9150_IRQ_MASK_F = 0x07D */ +#define DA9150_M_CONF_SHIFT 0 +#define DA9150_M_CONF_MASK BIT(0) +#define DA9150_M_DAT_SHIFT 1 +#define DA9150_M_DAT_MASK BIT(1) +#define DA9150_M_DTYPE_SHIFT 3 +#define DA9150_M_DTYPE_MASK BIT(3) +#define DA9150_M_ID_SHIFT 4 +#define DA9150_M_ID_MASK BIT(4) +#define DA9150_M_ADP_SHIFT 5 +#define DA9150_M_ADP_MASK BIT(5) +#define DA9150_M_SESS_END_SHIFT 6 +#define DA9150_M_SESS_END_MASK BIT(6) +#define DA9150_M_SESS_VLD_SHIFT 7 +#define DA9150_M_SESS_VLD_MASK BIT(7) + +/* DA9150_IRQ_MASK_G = 0x07E */ +#define DA9150_M_FG_SHIFT 0 +#define DA9150_M_FG_MASK BIT(0) +#define DA9150_M_GP_SHIFT 1 +#define DA9150_M_GP_MASK BIT(1) +#define DA9150_M_TBAT_SHIFT 2 +#define DA9150_M_TBAT_MASK BIT(2) +#define DA9150_M_GPIOA_SHIFT 3 +#define DA9150_M_GPIOA_MASK BIT(3) +#define DA9150_M_GPIOB_SHIFT 4 +#define DA9150_M_GPIOB_MASK BIT(4) +#define DA9150_M_GPIOC_SHIFT 5 +#define DA9150_M_GPIOC_MASK BIT(5) +#define DA9150_M_GPIOD_SHIFT 6 +#define DA9150_M_GPIOD_MASK BIT(6) +#define DA9150_M_GPADC_SHIFT 7 +#define DA9150_M_GPADC_MASK BIT(7) + +/* DA9150_IRQ_MASK_H = 0x07F */ +#define DA9150_M_WKUP_SHIFT 0 +#define DA9150_M_WKUP_MASK BIT(0) + +/* DA9150_PAGE_CON_1 = 0x080 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_CONFIG_A = 0x0E0 */ +#define DA9150_RESET_DUR_SHIFT 0 +#define DA9150_RESET_DUR_MASK (0x03 << 0) +#define DA9150_RESET_EXT_SHIFT 2 +#define DA9150_RESET_EXT_MASK (0x03 << 2) +#define DA9150_START_MAX_SHIFT 4 +#define DA9150_START_MAX_MASK (0x03 << 4) +#define DA9150_PS_WAIT_EN_SHIFT 6 +#define DA9150_PS_WAIT_EN_MASK BIT(6) +#define DA9150_PS_DISABLE_DIRECT_SHIFT 7 +#define DA9150_PS_DISABLE_DIRECT_MASK BIT(7) + +/* DA9150_CONFIG_B = 0x0E1 */ +#define DA9150_VFAULT_ADJ_SHIFT 0 +#define DA9150_VFAULT_ADJ_MASK (0x0f << 0) +#define DA9150_VFAULT_HYST_SHIFT 4 +#define DA9150_VFAULT_HYST_MASK (0x07 << 4) +#define DA9150_VFAULT_EN_SHIFT 7 +#define DA9150_VFAULT_EN_MASK BIT(7) + +/* DA9150_CONFIG_C = 0x0E2 */ +#define DA9150_VSYS_MIN_SHIFT 3 +#define DA9150_VSYS_MIN_MASK (0x1f << 3) + +/* DA9150_CONFIG_D = 0x0E3 */ +#define DA9150_LFOSC_EXT_SHIFT 0 +#define DA9150_LFOSC_EXT_MASK BIT(0) +#define DA9150_VDD33_DWN_SHIFT 1 +#define DA9150_VDD33_DWN_MASK BIT(1) +#define DA9150_WKUP_PM_EN_SHIFT 2 +#define DA9150_WKUP_PM_EN_MASK BIT(2) +#define DA9150_WKUP_CE_SEL_SHIFT 3 +#define DA9150_WKUP_CE_SEL_MASK (0x03 << 3) +#define DA9150_WKUP_CLK32K_EN_SHIFT 5 +#define DA9150_WKUP_CLK32K_EN_MASK BIT(5) +#define DA9150_DISABLE_DEL_SHIFT 7 +#define DA9150_DISABLE_DEL_MASK BIT(7) + +/* DA9150_CONFIG_E = 0x0E4 */ +#define DA9150_PM_SPKSUP_DIS_SHIFT 0 +#define DA9150_PM_SPKSUP_DIS_MASK BIT(0) +#define DA9150_PM_MERGE_SHIFT 1 +#define DA9150_PM_MERGE_MASK BIT(1) +#define DA9150_PM_SR_OFF_SHIFT 2 +#define DA9150_PM_SR_OFF_MASK BIT(2) +#define DA9150_PM_TIMEOUT_EN_SHIFT 3 +#define DA9150_PM_TIMEOUT_EN_MASK BIT(3) +#define DA9150_PM_DLY_SEL_SHIFT 4 +#define DA9150_PM_DLY_SEL_MASK (0x07 << 4) +#define DA9150_PM_OUT_DLY_SEL_SHIFT 7 +#define DA9150_PM_OUT_DLY_SEL_MASK BIT(7) + +/* DA9150_CONTROL_A = 0x0E5 */ +#define DA9150_VDD33_SL_SHIFT 0 +#define DA9150_VDD33_SL_MASK BIT(0) +#define DA9150_VDD33_LPM_SHIFT 1 +#define DA9150_VDD33_LPM_MASK (0x03 << 1) +#define DA9150_VDD33_EN_SHIFT 3 +#define DA9150_VDD33_EN_MASK BIT(3) +#define DA9150_GPI_LPM_SHIFT 6 +#define DA9150_GPI_LPM_MASK BIT(6) +#define DA9150_PM_IF_LPM_SHIFT 7 +#define DA9150_PM_IF_LPM_MASK BIT(7) + +/* DA9150_CONTROL_B = 0x0E6 */ +#define DA9150_LPM_SHIFT 0 +#define DA9150_LPM_MASK BIT(0) +#define DA9150_RESET_SHIFT 1 +#define DA9150_RESET_MASK BIT(1) +#define DA9150_RESET_USRCONF_EN_SHIFT 2 +#define DA9150_RESET_USRCONF_EN_MASK BIT(2) + +/* DA9150_CONTROL_C = 0x0E7 */ +#define DA9150_DISABLE_SHIFT 0 +#define DA9150_DISABLE_MASK BIT(0) + +/* DA9150_GPIO_A_B = 0x0E8 */ +#define DA9150_GPIOA_PIN_SHIFT 0 +#define DA9150_GPIOA_PIN_MASK (0x07 << 0) +#define DA9150_GPIOA_PIN_GPI (0x00 << 0) +#define DA9150_GPIOA_PIN_GPO_OD BIT(0) +#define DA9150_GPIOA_TYPE_SHIFT 3 +#define DA9150_GPIOA_TYPE_MASK BIT(3) +#define DA9150_GPIOB_PIN_SHIFT 4 +#define DA9150_GPIOB_PIN_MASK (0x07 << 4) +#define DA9150_GPIOB_PIN_GPI (0x00 << 4) +#define DA9150_GPIOB_PIN_GPO_OD BIT(4) +#define DA9150_GPIOB_TYPE_SHIFT 7 +#define DA9150_GPIOB_TYPE_MASK BIT(7) + +/* DA9150_GPIO_C_D = 0x0E9 */ +#define DA9150_GPIOC_PIN_SHIFT 0 +#define DA9150_GPIOC_PIN_MASK (0x07 << 0) +#define DA9150_GPIOC_PIN_GPI (0x00 << 0) +#define DA9150_GPIOC_PIN_GPO_OD BIT(0) +#define DA9150_GPIOC_TYPE_SHIFT 3 +#define DA9150_GPIOC_TYPE_MASK BIT(3) +#define DA9150_GPIOD_PIN_SHIFT 4 +#define DA9150_GPIOD_PIN_MASK (0x07 << 4) +#define DA9150_GPIOD_PIN_GPI (0x00 << 4) +#define DA9150_GPIOD_PIN_GPO_OD BIT(4) +#define DA9150_GPIOD_TYPE_SHIFT 7 +#define DA9150_GPIOD_TYPE_MASK BIT(7) + +/* DA9150_GPIO_MODE_CONT = 0x0EA */ +#define DA9150_GPIOA_MODE_SHIFT 0 +#define DA9150_GPIOA_MODE_MASK BIT(0) +#define DA9150_GPIOB_MODE_SHIFT 1 +#define DA9150_GPIOB_MODE_MASK BIT(1) +#define DA9150_GPIOC_MODE_SHIFT 2 +#define DA9150_GPIOC_MODE_MASK BIT(2) +#define DA9150_GPIOD_MODE_SHIFT 3 +#define DA9150_GPIOD_MODE_MASK BIT(3) +#define DA9150_GPIOA_CONT_SHIFT 4 +#define DA9150_GPIOA_CONT_MASK BIT(4) +#define DA9150_GPIOB_CONT_SHIFT 5 +#define DA9150_GPIOB_CONT_MASK BIT(5) +#define DA9150_GPIOC_CONT_SHIFT 6 +#define DA9150_GPIOC_CONT_MASK BIT(6) +#define DA9150_GPIOD_CONT_SHIFT 7 +#define DA9150_GPIOD_CONT_MASK BIT(7) + +/* DA9150_GPIO_CTRL_B = 0x0EB */ +#define DA9150_WAKE_PIN_SHIFT 0 +#define DA9150_WAKE_PIN_MASK (0x03 << 0) +#define DA9150_WAKE_MODE_SHIFT 2 +#define DA9150_WAKE_MODE_MASK BIT(2) +#define DA9150_WAKE_CONT_SHIFT 3 +#define DA9150_WAKE_CONT_MASK BIT(3) +#define DA9150_WAKE_DLY_SHIFT 4 +#define DA9150_WAKE_DLY_MASK BIT(4) + +/* DA9150_GPIO_CTRL_A = 0x0EC */ +#define DA9150_GPIOA_ANAEN_SHIFT 0 +#define DA9150_GPIOA_ANAEN_MASK BIT(0) +#define DA9150_GPIOB_ANAEN_SHIFT 1 +#define DA9150_GPIOB_ANAEN_MASK BIT(1) +#define DA9150_GPIOC_ANAEN_SHIFT 2 +#define DA9150_GPIOC_ANAEN_MASK BIT(2) +#define DA9150_GPIOD_ANAEN_SHIFT 3 +#define DA9150_GPIOD_ANAEN_MASK BIT(3) +#define DA9150_GPIO_ANAEN 0x01 +#define DA9150_GPIO_ANAEN_MASK 0x0F +#define DA9150_CHGLED_PIN_SHIFT 5 +#define DA9150_CHGLED_PIN_MASK (0x07 << 5) + +/* DA9150_GPIO_CTRL_C = 0x0ED */ +#define DA9150_CHGBL_DUR_SHIFT 0 +#define DA9150_CHGBL_DUR_MASK (0x03 << 0) +#define DA9150_CHGBL_DBL_SHIFT 2 +#define DA9150_CHGBL_DBL_MASK BIT(2) +#define DA9150_CHGBL_FRQ_SHIFT 3 +#define DA9150_CHGBL_FRQ_MASK (0x03 << 3) +#define DA9150_CHGBL_FLKR_SHIFT 5 +#define DA9150_CHGBL_FLKR_MASK BIT(5) + +/* DA9150_GPIO_CFG_A = 0x0EE */ +#define DA9150_CE_LPM_DEB_SHIFT 0 +#define DA9150_CE_LPM_DEB_MASK (0x07 << 0) + +/* DA9150_GPIO_CFG_B = 0x0EF */ +#define DA9150_GPIOA_PUPD_SHIFT 0 +#define DA9150_GPIOA_PUPD_MASK BIT(0) +#define DA9150_GPIOB_PUPD_SHIFT 1 +#define DA9150_GPIOB_PUPD_MASK BIT(1) +#define DA9150_GPIOC_PUPD_SHIFT 2 +#define DA9150_GPIOC_PUPD_MASK BIT(2) +#define DA9150_GPIOD_PUPD_SHIFT 3 +#define DA9150_GPIOD_PUPD_MASK BIT(3) +#define DA9150_GPIO_PUPD_MASK (0xF << 0) +#define DA9150_GPI_DEB_SHIFT 4 +#define DA9150_GPI_DEB_MASK (0x07 << 4) +#define DA9150_LPM_EN_SHIFT 7 +#define DA9150_LPM_EN_MASK BIT(7) + +/* DA9150_GPIO_CFG_C = 0x0F0 */ +#define DA9150_GPI_V_SHIFT 0 +#define DA9150_GPI_V_MASK BIT(0) +#define DA9150_VDDIO_INT_SHIFT 1 +#define DA9150_VDDIO_INT_MASK BIT(1) +#define DA9150_FAULT_PIN_SHIFT 3 +#define DA9150_FAULT_PIN_MASK (0x07 << 3) +#define DA9150_FAULT_TYPE_SHIFT 6 +#define DA9150_FAULT_TYPE_MASK BIT(6) +#define DA9150_NIRQ_PUPD_SHIFT 7 +#define DA9150_NIRQ_PUPD_MASK BIT(7) + +/* DA9150_GPADC_MAN = 0x0F2 */ +#define DA9150_GPADC_EN_SHIFT 0 +#define DA9150_GPADC_EN_MASK BIT(0) +#define DA9150_GPADC_MUX_SHIFT 1 +#define DA9150_GPADC_MUX_MASK (0x1f << 1) + +/* DA9150_GPADC_RES_A = 0x0F4 */ +#define DA9150_GPADC_RES_H_SHIFT 0 +#define DA9150_GPADC_RES_H_MASK (0xff << 0) + +/* DA9150_GPADC_RES_B = 0x0F5 */ +#define DA9150_GPADC_RUN_SHIFT 0 +#define DA9150_GPADC_RUN_MASK BIT(0) +#define DA9150_GPADC_RES_L_SHIFT 6 +#define DA9150_GPADC_RES_L_MASK (0x03 << 6) +#define DA9150_GPADC_RES_L_BITS 2 + +/* DA9150_PAGE_CON_2 = 0x100 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_OTP_CONT_SHARED = 0x101 */ +#define DA9150_PC_DONE_SHIFT 3 +#define DA9150_PC_DONE_MASK BIT(3) + +/* DA9150_INTERFACE_SHARED = 0x105 */ +#define DA9150_IF_BASE_ADDR_SHIFT 4 +#define DA9150_IF_BASE_ADDR_MASK (0x0f << 4) + +/* DA9150_CONFIG_A_SHARED = 0x106 */ +#define DA9150_NIRQ_VDD_SHIFT 1 +#define DA9150_NIRQ_VDD_MASK BIT(1) +#define DA9150_NIRQ_PIN_SHIFT 2 +#define DA9150_NIRQ_PIN_MASK BIT(2) +#define DA9150_NIRQ_TYPE_SHIFT 3 +#define DA9150_NIRQ_TYPE_MASK BIT(3) +#define DA9150_PM_IF_V_SHIFT 4 +#define DA9150_PM_IF_V_MASK BIT(4) +#define DA9150_PM_IF_FMP_SHIFT 5 +#define DA9150_PM_IF_FMP_MASK BIT(5) +#define DA9150_PM_IF_HSM_SHIFT 6 +#define DA9150_PM_IF_HSM_MASK BIT(6) + +/* DA9150_CONFIG_D_SHARED = 0x109 */ +#define DA9150_NIRQ_MODE_SHIFT 1 +#define DA9150_NIRQ_MODE_MASK BIT(1) + +/* DA9150_ADETVB_CFG_C = 0x150 */ +#define DA9150_TADP_RISE_SHIFT 0 +#define DA9150_TADP_RISE_MASK (0xff << 0) + +/* DA9150_ADETD_STAT = 0x151 */ +#define DA9150_DCD_STAT_SHIFT 0 +#define DA9150_DCD_STAT_MASK BIT(0) +#define DA9150_PCD_STAT_SHIFT 1 +#define DA9150_PCD_STAT_MASK (0x03 << 1) +#define DA9150_SCD_STAT_SHIFT 3 +#define DA9150_SCD_STAT_MASK (0x03 << 3) +#define DA9150_DP_STAT_SHIFT 5 +#define DA9150_DP_STAT_MASK BIT(5) +#define DA9150_DM_STAT_SHIFT 6 +#define DA9150_DM_STAT_MASK BIT(6) + +/* DA9150_ADET_CMPSTAT = 0x152 */ +#define DA9150_DP_COMP_SHIFT 1 +#define DA9150_DP_COMP_MASK BIT(1) +#define DA9150_DM_COMP_SHIFT 2 +#define DA9150_DM_COMP_MASK BIT(2) +#define DA9150_ADP_SNS_COMP_SHIFT 3 +#define DA9150_ADP_SNS_COMP_MASK BIT(3) +#define DA9150_ADP_PRB_COMP_SHIFT 4 +#define DA9150_ADP_PRB_COMP_MASK BIT(4) +#define DA9150_ID_COMP_SHIFT 5 +#define DA9150_ID_COMP_MASK BIT(5) + +/* DA9150_ADET_CTRL_A = 0x153 */ +#define DA9150_AID_DAT_SHIFT 0 +#define DA9150_AID_DAT_MASK BIT(0) +#define DA9150_AID_ID_SHIFT 1 +#define DA9150_AID_ID_MASK BIT(1) +#define DA9150_AID_TRIG_SHIFT 2 +#define DA9150_AID_TRIG_MASK BIT(2) + +/* DA9150_ADETVB_CFG_B = 0x154 */ +#define DA9150_VB_MODE_SHIFT 0 +#define DA9150_VB_MODE_MASK (0x03 << 0) +#define DA9150_VB_MODE_VB_SESS BIT(0) + +#define DA9150_TADP_PRB_SHIFT 2 +#define DA9150_TADP_PRB_MASK BIT(2) +#define DA9150_DAT_RPD_EXT_SHIFT 5 +#define DA9150_DAT_RPD_EXT_MASK BIT(5) +#define DA9150_CONF_RPD_SHIFT 6 +#define DA9150_CONF_RPD_MASK BIT(6) +#define DA9150_CONF_SRP_SHIFT 7 +#define DA9150_CONF_SRP_MASK BIT(7) + +/* DA9150_ADETVB_CFG_A = 0x155 */ +#define DA9150_AID_MODE_SHIFT 0 +#define DA9150_AID_MODE_MASK (0x03 << 0) +#define DA9150_AID_EXT_POL_SHIFT 2 +#define DA9150_AID_EXT_POL_MASK BIT(2) + +/* DA9150_ADETAC_CFG_A = 0x156 */ +#define DA9150_ISET_CDP_SHIFT 0 +#define DA9150_ISET_CDP_MASK (0x1f << 0) +#define DA9150_CONF_DBP_SHIFT 5 +#define DA9150_CONF_DBP_MASK BIT(5) + +/* DA9150_ADDETAC_CFG_B = 0x157 */ +#define DA9150_ISET_DCHG_SHIFT 0 +#define DA9150_ISET_DCHG_MASK (0x1f << 0) +#define DA9150_CONF_GPIOA_SHIFT 5 +#define DA9150_CONF_GPIOA_MASK BIT(5) +#define DA9150_CONF_GPIOB_SHIFT 6 +#define DA9150_CONF_GPIOB_MASK BIT(6) +#define DA9150_AID_VB_SHIFT 7 +#define DA9150_AID_VB_MASK BIT(7) + +/* DA9150_ADETAC_CFG_C = 0x158 */ +#define DA9150_ISET_DEF_SHIFT 0 +#define DA9150_ISET_DEF_MASK (0x1f << 0) +#define DA9150_CONF_MODE_SHIFT 5 +#define DA9150_CONF_MODE_MASK (0x03 << 5) +#define DA9150_AID_CR_DIS_SHIFT 7 +#define DA9150_AID_CR_DIS_MASK BIT(7) + +/* DA9150_ADETAC_CFG_D = 0x159 */ +#define DA9150_ISET_UNIT_SHIFT 0 +#define DA9150_ISET_UNIT_MASK (0x1f << 0) +#define DA9150_AID_UNCLAMP_SHIFT 5 +#define DA9150_AID_UNCLAMP_MASK BIT(5) + +/* DA9150_ADETVB_CFG_D = 0x15A */ +#define DA9150_ID_MODE_SHIFT 0 +#define DA9150_ID_MODE_MASK (0x03 << 0) +#define DA9150_DAT_MODE_SHIFT 2 +#define DA9150_DAT_MODE_MASK (0x0f << 2) +#define DA9150_DAT_SWP_SHIFT 6 +#define DA9150_DAT_SWP_MASK BIT(6) +#define DA9150_DAT_CLAMP_EXT_SHIFT 7 +#define DA9150_DAT_CLAMP_EXT_MASK BIT(7) + +/* DA9150_ADETID_CFG_A = 0x15B */ +#define DA9150_TID_POLL_SHIFT 0 +#define DA9150_TID_POLL_MASK (0x07 << 0) +#define DA9150_RID_CONV_SHIFT 3 +#define DA9150_RID_CONV_MASK BIT(3) + +/* DA9150_ADET_RID_PT_CHG_H = 0x15C */ +#define DA9150_RID_PT_CHG_H_SHIFT 0 +#define DA9150_RID_PT_CHG_H_MASK (0xff << 0) + +/* DA9150_ADET_RID_PT_CHG_L = 0x15D */ +#define DA9150_RID_PT_CHG_L_SHIFT 6 +#define DA9150_RID_PT_CHG_L_MASK (0x03 << 6) + +/* DA9150_PPR_TCTR_B = 0x160 */ +#define DA9150_CHG_TCTR_VAL_SHIFT 0 +#define DA9150_CHG_TCTR_VAL_MASK (0xff << 0) + +/* DA9150_PPR_BKCTRL_A = 0x163 */ +#define DA9150_VBUS_MODE_SHIFT 0 +#define DA9150_VBUS_MODE_MASK (0x03 << 0) +#define DA9150_VBUS_MODE_CHG BIT(0) +#define DA9150_VBUS_MODE_OTG (0x02 << 0) +#define DA9150_VBUS_LPM_SHIFT 2 +#define DA9150_VBUS_LPM_MASK (0x03 << 2) +#define DA9150_VBUS_SUSP_SHIFT 4 +#define DA9150_VBUS_SUSP_MASK BIT(4) +#define DA9150_VBUS_PWM_SHIFT 5 +#define DA9150_VBUS_PWM_MASK BIT(5) +#define DA9150_VBUS_ISO_SHIFT 6 +#define DA9150_VBUS_ISO_MASK BIT(6) +#define DA9150_VBUS_LDO_SHIFT 7 +#define DA9150_VBUS_LDO_MASK BIT(7) + +/* DA9150_PPR_BKCFG_A = 0x164 */ +#define DA9150_VBUS_ISET_SHIFT 0 +#define DA9150_VBUS_ISET_MASK (0x1f << 0) +#define DA9150_VBUS_IMAX_SHIFT 5 +#define DA9150_VBUS_IMAX_MASK BIT(5) +#define DA9150_VBUS_IOTG_SHIFT 6 +#define DA9150_VBUS_IOTG_MASK (0x03 << 6) + +/* DA9150_PPR_BKCFG_B = 0x165 */ +#define DA9150_VBUS_DROP_SHIFT 0 +#define DA9150_VBUS_DROP_MASK (0x0f << 0) +#define DA9150_VBUS_FAULT_DIS_SHIFT 6 +#define DA9150_VBUS_FAULT_DIS_MASK BIT(6) +#define DA9150_OTG_FAULT_DIS_SHIFT 7 +#define DA9150_OTG_FAULT_DIS_MASK BIT(7) + +/* DA9150_PPR_CHGCTRL_A = 0x166 */ +#define DA9150_CHG_EN_SHIFT 0 +#define DA9150_CHG_EN_MASK BIT(0) + +/* DA9150_PPR_CHGCTRL_B = 0x167 */ +#define DA9150_CHG_VBAT_SHIFT 0 +#define DA9150_CHG_VBAT_MASK (0x1f << 0) +#define DA9150_CHG_VDROP_SHIFT 6 +#define DA9150_CHG_VDROP_MASK (0x03 << 6) + +/* DA9150_PPR_CHGCTRL_C = 0x168 */ +#define DA9150_CHG_VFAULT_SHIFT 0 +#define DA9150_CHG_VFAULT_MASK (0x0f << 0) +#define DA9150_CHG_IPRE_SHIFT 4 +#define DA9150_CHG_IPRE_MASK (0x03 << 4) + +/* DA9150_PPR_TCTR_A = 0x169 */ +#define DA9150_CHG_TCTR_SHIFT 0 +#define DA9150_CHG_TCTR_MASK (0x07 << 0) +#define DA9150_CHG_TCTR_MODE_SHIFT 4 +#define DA9150_CHG_TCTR_MODE_MASK BIT(4) + +/* DA9150_PPR_CHGCTRL_D = 0x16A */ +#define DA9150_CHG_IBAT_SHIFT 0 +#define DA9150_CHG_IBAT_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_E = 0x16B */ +#define DA9150_CHG_IEND_SHIFT 0 +#define DA9150_CHG_IEND_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_F = 0x16C */ +#define DA9150_CHG_VCOLD_SHIFT 0 +#define DA9150_CHG_VCOLD_MASK (0x1f << 0) +#define DA9150_TBAT_TQA_EN_SHIFT 6 +#define DA9150_TBAT_TQA_EN_MASK BIT(6) +#define DA9150_TBAT_TDP_EN_SHIFT 7 +#define DA9150_TBAT_TDP_EN_MASK BIT(7) + +/* DA9150_PPR_CHGCTRL_G = 0x16D */ +#define DA9150_CHG_VWARM_SHIFT 0 +#define DA9150_CHG_VWARM_MASK (0x1f << 0) + +/* DA9150_PPR_CHGCTRL_H = 0x16E */ +#define DA9150_CHG_VHOT_SHIFT 0 +#define DA9150_CHG_VHOT_MASK (0x1f << 0) + +/* DA9150_PPR_CHGCTRL_I = 0x16F */ +#define DA9150_CHG_ICOLD_SHIFT 0 +#define DA9150_CHG_ICOLD_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_J = 0x170 */ +#define DA9150_CHG_IWARM_SHIFT 0 +#define DA9150_CHG_IWARM_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_K = 0x171 */ +#define DA9150_CHG_IHOT_SHIFT 0 +#define DA9150_CHG_IHOT_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_L = 0x172 */ +#define DA9150_CHG_IBAT_TRED_SHIFT 0 +#define DA9150_CHG_IBAT_TRED_MASK (0xff << 0) + +/* DA9150_PPR_CHGCTRL_M = 0x173 */ +#define DA9150_CHG_VFLOAT_SHIFT 0 +#define DA9150_CHG_VFLOAT_MASK (0x0f << 0) +#define DA9150_CHG_LPM_SHIFT 5 +#define DA9150_CHG_LPM_MASK BIT(5) +#define DA9150_CHG_NBLO_SHIFT 6 +#define DA9150_CHG_NBLO_MASK BIT(6) +#define DA9150_EBS_EN_SHIFT 7 +#define DA9150_EBS_EN_MASK BIT(7) + +/* DA9150_PPR_THYST_A = 0x174 */ +#define DA9150_TBAT_T1_SHIFT 0 +#define DA9150_TBAT_T1_MASK (0xff << 0) + +/* DA9150_PPR_THYST_B = 0x175 */ +#define DA9150_TBAT_T2_SHIFT 0 +#define DA9150_TBAT_T2_MASK (0xff << 0) + +/* DA9150_PPR_THYST_C = 0x176 */ +#define DA9150_TBAT_T3_SHIFT 0 +#define DA9150_TBAT_T3_MASK (0xff << 0) + +/* DA9150_PPR_THYST_D = 0x177 */ +#define DA9150_TBAT_T4_SHIFT 0 +#define DA9150_TBAT_T4_MASK (0xff << 0) + +/* DA9150_PPR_THYST_E = 0x178 */ +#define DA9150_TBAT_T5_SHIFT 0 +#define DA9150_TBAT_T5_MASK (0xff << 0) + +/* DA9150_PPR_THYST_F = 0x179 */ +#define DA9150_TBAT_H1_SHIFT 0 +#define DA9150_TBAT_H1_MASK (0xff << 0) + +/* DA9150_PPR_THYST_G = 0x17A */ +#define DA9150_TBAT_H5_SHIFT 0 +#define DA9150_TBAT_H5_MASK (0xff << 0) + +/* DA9150_PAGE_CON_3 = 0x180 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_PAGE_CON_4 = 0x200 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_PAGE_CON_5 = 0x280 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_PAGE_CON_6 = 0x300 */ +#define DA9150_PAGE_SHIFT 0 +#define DA9150_PAGE_MASK (0x3f << 0) +#define DA9150_WRITE_MODE_SHIFT 6 +#define DA9150_WRITE_MODE_MASK BIT(6) +#define DA9150_REVERT_SHIFT 7 +#define DA9150_REVERT_MASK BIT(7) + +/* DA9150_COREBTLD_STAT_A = 0x302 */ +#define DA9150_BOOTLD_STAT_SHIFT 0 +#define DA9150_BOOTLD_STAT_MASK (0x03 << 0) +#define DA9150_CORE_LOCKUP_SHIFT 2 +#define DA9150_CORE_LOCKUP_MASK BIT(2) + +/* DA9150_COREBTLD_CTRL_A = 0x303 */ +#define DA9150_CORE_RESET_SHIFT 0 +#define DA9150_CORE_RESET_MASK BIT(0) +#define DA9150_CORE_STOP_SHIFT 1 +#define DA9150_CORE_STOP_MASK BIT(1) + +/* DA9150_CORE_CONFIG_A = 0x304 */ +#define DA9150_CORE_MEMMUX_SHIFT 0 +#define DA9150_CORE_MEMMUX_MASK (0x03 << 0) +#define DA9150_WDT_AUTO_START_SHIFT 2 +#define DA9150_WDT_AUTO_START_MASK BIT(2) +#define DA9150_WDT_AUTO_LOCK_SHIFT 3 +#define DA9150_WDT_AUTO_LOCK_MASK BIT(3) +#define DA9150_WDT_HLT_NO_CLK_SHIFT 4 +#define DA9150_WDT_HLT_NO_CLK_MASK BIT(4) + +/* DA9150_CORE_CONFIG_C = 0x305 */ +#define DA9150_CORE_SW_SIZE_SHIFT 0 +#define DA9150_CORE_SW_SIZE_MASK (0xff << 0) + +/* DA9150_CORE_CONFIG_B = 0x306 */ +#define DA9150_BOOTLD_EN_SHIFT 0 +#define DA9150_BOOTLD_EN_MASK BIT(0) +#define DA9150_CORE_EN_SHIFT 2 +#define DA9150_CORE_EN_MASK BIT(2) +#define DA9150_CORE_SW_SRC_SHIFT 3 +#define DA9150_CORE_SW_SRC_MASK (0x07 << 3) +#define DA9150_DEEP_SLEEP_EN_SHIFT 7 +#define DA9150_DEEP_SLEEP_EN_MASK BIT(7) + +/* DA9150_CORE_CFG_DATA_A = 0x307 */ +#define DA9150_CORE_CFG_DT_A_SHIFT 0 +#define DA9150_CORE_CFG_DT_A_MASK (0xff << 0) + +/* DA9150_CORE_CFG_DATA_B = 0x308 */ +#define DA9150_CORE_CFG_DT_B_SHIFT 0 +#define DA9150_CORE_CFG_DT_B_MASK (0xff << 0) + +/* DA9150_CORE_CMD_A = 0x309 */ +#define DA9150_CORE_CMD_SHIFT 0 +#define DA9150_CORE_CMD_MASK (0xff << 0) + +/* DA9150_CORE_DATA_A = 0x30A */ +#define DA9150_CORE_DATA_0_SHIFT 0 +#define DA9150_CORE_DATA_0_MASK (0xff << 0) + +/* DA9150_CORE_DATA_B = 0x30B */ +#define DA9150_CORE_DATA_1_SHIFT 0 +#define DA9150_CORE_DATA_1_MASK (0xff << 0) + +/* DA9150_CORE_DATA_C = 0x30C */ +#define DA9150_CORE_DATA_2_SHIFT 0 +#define DA9150_CORE_DATA_2_MASK (0xff << 0) + +/* DA9150_CORE_DATA_D = 0x30D */ +#define DA9150_CORE_DATA_3_SHIFT 0 +#define DA9150_CORE_DATA_3_MASK (0xff << 0) + +/* DA9150_CORE2WIRE_STAT_A = 0x310 */ +#define DA9150_FW_FWDL_ERR_SHIFT 7 +#define DA9150_FW_FWDL_ERR_MASK BIT(7) + +/* DA9150_CORE2WIRE_CTRL_A = 0x311 */ +#define DA9150_FW_FWDL_EN_SHIFT 0 +#define DA9150_FW_FWDL_EN_MASK BIT(0) +#define DA9150_FG_QIF_EN_SHIFT 1 +#define DA9150_FG_QIF_EN_MASK BIT(1) +#define DA9150_CORE_BASE_ADDR_SHIFT 4 +#define DA9150_CORE_BASE_ADDR_MASK (0x0f << 4) + +/* DA9150_FW_CTRL_A = 0x312 */ +#define DA9150_FW_SEAL_SHIFT 0 +#define DA9150_FW_SEAL_MASK (0xff << 0) + +/* DA9150_FW_CTRL_C = 0x313 */ +#define DA9150_FW_FWDL_CRC_SHIFT 0 +#define DA9150_FW_FWDL_CRC_MASK (0xff << 0) + +/* DA9150_FW_CTRL_D = 0x314 */ +#define DA9150_FW_FWDL_BASE_SHIFT 0 +#define DA9150_FW_FWDL_BASE_MASK (0x0f << 0) + +/* DA9150_FG_CTRL_A = 0x315 */ +#define DA9150_FG_QIF_CODE_SHIFT 0 +#define DA9150_FG_QIF_CODE_MASK (0xff << 0) + +/* DA9150_FG_CTRL_B = 0x316 */ +#define DA9150_FG_QIF_VALUE_SHIFT 0 +#define DA9150_FG_QIF_VALUE_MASK (0xff << 0) + +/* DA9150_FW_CTRL_E = 0x317 */ +#define DA9150_FW_FWDL_SEG_SHIFT 0 +#define DA9150_FW_FWDL_SEG_MASK (0xff << 0) + +/* DA9150_FW_CTRL_B = 0x318 */ +#define DA9150_FW_FWDL_VALUE_SHIFT 0 +#define DA9150_FW_FWDL_VALUE_MASK (0xff << 0) + +/* DA9150_GPADC_CMAN = 0x320 */ +#define DA9150_GPADC_CEN_SHIFT 0 +#define DA9150_GPADC_CEN_MASK BIT(0) +#define DA9150_GPADC_CMUX_SHIFT 1 +#define DA9150_GPADC_CMUX_MASK (0x1f << 1) + +/* DA9150_GPADC_CRES_A = 0x322 */ +#define DA9150_GPADC_CRES_H_SHIFT 0 +#define DA9150_GPADC_CRES_H_MASK (0xff << 0) + +/* DA9150_GPADC_CRES_B = 0x323 */ +#define DA9150_GPADC_CRUN_SHIFT 0 +#define DA9150_GPADC_CRUN_MASK BIT(0) +#define DA9150_GPADC_CRES_L_SHIFT 6 +#define DA9150_GPADC_CRES_L_MASK (0x03 << 6) + +/* DA9150_CC_CFG_A = 0x328 */ +#define DA9150_CC_EN_SHIFT 0 +#define DA9150_CC_EN_MASK BIT(0) +#define DA9150_CC_TIMEBASE_SHIFT 1 +#define DA9150_CC_TIMEBASE_MASK (0x03 << 1) +#define DA9150_CC_CFG_SHIFT 5 +#define DA9150_CC_CFG_MASK (0x03 << 5) +#define DA9150_CC_ENDLESS_MODE_SHIFT 7 +#define DA9150_CC_ENDLESS_MODE_MASK BIT(7) + +/* DA9150_CC_CFG_B = 0x329 */ +#define DA9150_CC_OPT_SHIFT 0 +#define DA9150_CC_OPT_MASK (0x03 << 0) +#define DA9150_CC_PREAMP_SHIFT 2 +#define DA9150_CC_PREAMP_MASK (0x03 << 2) + +/* DA9150_CC_ICHG_RES_A = 0x32A */ +#define DA9150_CC_ICHG_RES_H_SHIFT 0 +#define DA9150_CC_ICHG_RES_H_MASK (0xff << 0) + +/* DA9150_CC_ICHG_RES_B = 0x32B */ +#define DA9150_CC_ICHG_RES_L_SHIFT 3 +#define DA9150_CC_ICHG_RES_L_MASK (0x1f << 3) + +/* DA9150_CC_IAVG_RES_A = 0x32C */ +#define DA9150_CC_IAVG_RES_H_SHIFT 0 +#define DA9150_CC_IAVG_RES_H_MASK (0xff << 0) + +/* DA9150_CC_IAVG_RES_B = 0x32D */ +#define DA9150_CC_IAVG_RES_L_SHIFT 0 +#define DA9150_CC_IAVG_RES_L_MASK (0xff << 0) + +/* DA9150_TAUX_CTRL_A = 0x330 */ +#define DA9150_TAUX_EN_SHIFT 0 +#define DA9150_TAUX_EN_MASK BIT(0) +#define DA9150_TAUX_MOD_SHIFT 1 +#define DA9150_TAUX_MOD_MASK BIT(1) +#define DA9150_TAUX_UPDATE_SHIFT 2 +#define DA9150_TAUX_UPDATE_MASK BIT(2) + +/* DA9150_TAUX_RELOAD_H = 0x332 */ +#define DA9150_TAUX_RLD_H_SHIFT 0 +#define DA9150_TAUX_RLD_H_MASK (0xff << 0) + +/* DA9150_TAUX_RELOAD_L = 0x333 */ +#define DA9150_TAUX_RLD_L_SHIFT 3 +#define DA9150_TAUX_RLD_L_MASK (0x1f << 3) + +/* DA9150_TAUX_VALUE_H = 0x334 */ +#define DA9150_TAUX_VAL_H_SHIFT 0 +#define DA9150_TAUX_VAL_H_MASK (0xff << 0) + +/* DA9150_TAUX_VALUE_L = 0x335 */ +#define DA9150_TAUX_VAL_L_SHIFT 3 +#define DA9150_TAUX_VAL_L_MASK (0x1f << 3) + +/* DA9150_AUX_DATA_0 = 0x338 */ +#define DA9150_AUX_DAT_0_SHIFT 0 +#define DA9150_AUX_DAT_0_MASK (0xff << 0) + +/* DA9150_AUX_DATA_1 = 0x339 */ +#define DA9150_AUX_DAT_1_SHIFT 0 +#define DA9150_AUX_DAT_1_MASK (0xff << 0) + +/* DA9150_AUX_DATA_2 = 0x33A */ +#define DA9150_AUX_DAT_2_SHIFT 0 +#define DA9150_AUX_DAT_2_MASK (0xff << 0) + +/* DA9150_AUX_DATA_3 = 0x33B */ +#define DA9150_AUX_DAT_3_SHIFT 0 +#define DA9150_AUX_DAT_3_MASK (0xff << 0) + +/* DA9150_BIF_CTRL = 0x340 */ +#define DA9150_BIF_ISRC_EN_SHIFT 0 +#define DA9150_BIF_ISRC_EN_MASK BIT(0) + +/* DA9150_TBAT_CTRL_A = 0x342 */ +#define DA9150_TBAT_EN_SHIFT 0 +#define DA9150_TBAT_EN_MASK BIT(0) +#define DA9150_TBAT_SW1_SHIFT 1 +#define DA9150_TBAT_SW1_MASK BIT(1) +#define DA9150_TBAT_SW2_SHIFT 2 +#define DA9150_TBAT_SW2_MASK BIT(2) + +/* DA9150_TBAT_CTRL_B = 0x343 */ +#define DA9150_TBAT_SW_FRC_SHIFT 0 +#define DA9150_TBAT_SW_FRC_MASK BIT(0) +#define DA9150_TBAT_STAT_SW1_SHIFT 1 +#define DA9150_TBAT_STAT_SW1_MASK BIT(1) +#define DA9150_TBAT_STAT_SW2_SHIFT 2 +#define DA9150_TBAT_STAT_SW2_MASK BIT(2) +#define DA9150_TBAT_HIGH_CURR_SHIFT 3 +#define DA9150_TBAT_HIGH_CURR_MASK BIT(3) + +/* DA9150_TBAT_RES_A = 0x344 */ +#define DA9150_TBAT_RES_H_SHIFT 0 +#define DA9150_TBAT_RES_H_MASK (0xff << 0) + +/* DA9150_TBAT_RES_B = 0x345 */ +#define DA9150_TBAT_RES_DIS_SHIFT 0 +#define DA9150_TBAT_RES_DIS_MASK BIT(0) +#define DA9150_TBAT_RES_L_SHIFT 6 +#define DA9150_TBAT_RES_L_MASK (0x03 << 6) + +#endif /* __DA9150_REGISTERS_H */ -- cgit v1.2.3 From 774e0b41d485e18e655247441b8ca8b8dbe217c4 Mon Sep 17 00:00:00 2001 From: Todd E Brandt Date: Wed, 7 Jan 2015 13:25:52 -0800 Subject: mfd: axp20x: Add support for fuel gauge cell driver mfd/axp20x: add support for fuel gauge cell Register definitions and platform data structure for fuel gauge cell devices. Signed-off-by: Todd Brandt Acked-by: Jacob Pan Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 43 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 81589d176ae8..dfabd6db7ddf 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -124,10 +124,27 @@ enum { #define AXP288_PMIC_ADC_H 0x56 #define AXP288_PMIC_ADC_L 0x57 #define AXP288_ADC_TS_PIN_CTRL 0x84 - #define AXP288_PMIC_ADC_EN 0x84 -#define AXP288_FG_TUNE5 0xed +/* Fuel Gauge */ +#define AXP288_FG_RDC1_REG 0xba +#define AXP288_FG_RDC0_REG 0xbb +#define AXP288_FG_OCVH_REG 0xbc +#define AXP288_FG_OCVL_REG 0xbd +#define AXP288_FG_OCV_CURVE_REG 0xc0 +#define AXP288_FG_DES_CAP1_REG 0xe0 +#define AXP288_FG_DES_CAP0_REG 0xe1 +#define AXP288_FG_CC_MTR1_REG 0xe2 +#define AXP288_FG_CC_MTR0_REG 0xe3 +#define AXP288_FG_OCV_CAP_REG 0xe4 +#define AXP288_FG_CC_CAP_REG 0xe5 +#define AXP288_FG_LOW_CAP_REG 0xe6 +#define AXP288_FG_TUNE0 0xe8 +#define AXP288_FG_TUNE1 0xe9 +#define AXP288_FG_TUNE2 0xea +#define AXP288_FG_TUNE3 0xeb +#define AXP288_FG_TUNE4 0xec +#define AXP288_FG_TUNE5 0xed /* Regulators IDs */ enum { @@ -236,4 +253,26 @@ struct axp20x_dev { const struct regmap_irq_chip *regmap_irq_chip; }; +#define BATTID_LEN 64 +#define OCV_CURVE_SIZE 32 +#define MAX_THERM_CURVE_SIZE 25 +#define PD_DEF_MIN_TEMP 0 +#define PD_DEF_MAX_TEMP 55 + +struct axp20x_fg_pdata { + char battid[BATTID_LEN + 1]; + int design_cap; + int min_volt; + int max_volt; + int max_temp; + int min_temp; + int cap1; + int cap0; + int rdc1; + int rdc0; + int ocv_curve[OCV_CURVE_SIZE]; + int tcsz; + int thermistor_curve[MAX_THERM_CURVE_SIZE][2]; +}; + #endif /* __LINUX_MFD_AXP20X_H */ -- cgit v1.2.3 From 2b50635ea376c89082ef1f3204bcd7791a6e37d7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 29 Dec 2014 10:09:16 +0100 Subject: mfd: max77686/802: Remove support for board files The driver is used only on Exynos based boards with DTS support. After removal of board file support from max77686 and max77802 regulator drivers, the MFD driver can be converted to DTS-only version. This simplifies a little the code: 1. No dead (unused) entries in platform_data structure. 2. More code removed. 3. Regulator driver does not depend on allocated memory from MFD driver. 4. It makes also easier extending the regulator driver. Add to the max77686 MFD driver dependency on CONFIG_OF because without DTS the regulator drivers (max77686 and max77802) won't bind. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Javier Martinez Canillas Tested-by: Javier Martinez Canillas Signed-off-by: Lee Jones --- include/linux/mfd/max77686-private.h | 1 - include/linux/mfd/max77686.h | 28 ---------------------------- 2 files changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 960b92ad450d..f5043490d67c 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -447,7 +447,6 @@ struct max77686_dev { struct regmap_irq_chip_data *rtc_irq_data; int irq; - bool wakeup; struct mutex irqlock; int irq_masks_cur[MAX77686_IRQ_GROUP_NR]; int irq_masks_cache[MAX77686_IRQ_GROUP_NR]; diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h index 553f7d09258a..bb995ab9a575 100644 --- a/include/linux/mfd/max77686.h +++ b/include/linux/mfd/max77686.h @@ -119,12 +119,6 @@ enum max77802_regulators { MAX77802_REG_MAX, }; -struct max77686_regulator_data { - int id; - struct regulator_init_data *initdata; - struct device_node *of_node; -}; - enum max77686_opmode { MAX77686_OPMODE_NORMAL, MAX77686_OPMODE_LP, @@ -136,26 +130,4 @@ struct max77686_opmode_data { int mode; }; -struct max77686_platform_data { - int ono; - int wakeup; - - /* ---- PMIC ---- */ - struct max77686_regulator_data *regulators; - int num_regulators; - - struct max77686_opmode_data *opmode_data; - - /* - * GPIO-DVS feature is not enabled with the current version of - * MAX77686 driver. Buck2/3/4_voltages[0] is used as the default - * voltage at probe. DVS/SELB gpios are set as OUTPUT-LOW. - */ - int buck234_gpio_dvs[3]; /* GPIO of [0]DVS1, [1]DVS2, [2]DVS3 */ - int buck234_gpio_selb[3]; /* [0]SELB2, [1]SELB3, [2]SELB4 */ - unsigned int buck2_voltage[8]; /* buckx_voltage in uV */ - unsigned int buck3_voltage[8]; - unsigned int buck4_voltage[8]; -}; - #endif /* __LINUX_MFD_MAX77686_H */ -- cgit v1.2.3 From 58e214382bdd1eb48c5a3519182bddcb26edabad Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 26 Nov 2014 13:51:00 -0800 Subject: mfd: qcom-rpm: Driver for the Qualcomm RPM Driver for the Resource Power Manager (RPM) found in Qualcomm 8660, 8960 and 8064 based devices. The driver exposes resources that child drivers can operate on; to implementing regulator, clock and bus frequency drivers. Signed-off-by: Bjorn Andersson Signed-off-by: Lee Jones --- include/linux/mfd/qcom_rpm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/mfd/qcom_rpm.h (limited to 'include/linux') diff --git a/include/linux/mfd/qcom_rpm.h b/include/linux/mfd/qcom_rpm.h new file mode 100644 index 000000000000..742ebf1b76ca --- /dev/null +++ b/include/linux/mfd/qcom_rpm.h @@ -0,0 +1,13 @@ +#ifndef __QCOM_RPM_H__ +#define __QCOM_RPM_H__ + +#include + +struct qcom_rpm; + +#define QCOM_RPM_ACTIVE_STATE 0 +#define QCOM_RPM_SLEEP_STATE 1 + +int qcom_rpm_write(struct qcom_rpm *rpm, int state, int resource, u32 *buf, size_t count); + +#endif -- cgit v1.2.3 From 71e03de46d73b87aab5f80fa55449a9e40c55d17 Mon Sep 17 00:00:00 2001 From: Steve Twiss Date: Tue, 20 Jan 2015 13:54:25 +0000 Subject: mfd: da9063: Add device tree support Add device tree support for DA9063 regulators; Real-Time Clock and Watchdog. Signed-off-by: Steve Twiss Signed-off-by: Lee Jones --- include/linux/mfd/da9063/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index b92a3262f8f6..79f4d822ba13 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -36,6 +36,7 @@ enum da9063_models { enum da9063_variant_codes { PMIC_DA9063_AD = 0x3, PMIC_DA9063_BB = 0x5, + PMIC_DA9063_CA = 0x6, }; /* Interrupts */ -- cgit v1.2.3 From 1f94a94f67e1083e19fb7b436dd7ca7a4ba03f2b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 9 Jan 2015 20:34:39 -0600 Subject: PCI: Add generic config accessors Many PCI controllers' configuration space accesses are memory-mapped and vary only in address calculation and access checks. There are 2 main access methods: a decoded address space such as ECAM or a single address and data register similar to x86. This implementation can support both cases as well as be used in cases that need additional pre- or post-access handling. Add a new pci_ops member, map_bus, which can do access checks and any necessary setup. It returns the address to use for the configuration space access. The access types supported are 32-bit only accesses or correct byte, word, or dword sized accesses. Tested-by: Thierry Reding Signed-off-by: Rob Herring Signed-off-by: Bjorn Helgaas Reviewed-by: Thierry Reding --- include/linux/pci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..e7fd51900182 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -560,6 +560,7 @@ static inline int pcibios_err_to_errno(int err) /* Low-level architecture-dependent routines */ struct pci_ops { + void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where); int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val); int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val); }; @@ -857,6 +858,16 @@ int pci_bus_write_config_word(struct pci_bus *bus, unsigned int devfn, int where, u16 val); int pci_bus_write_config_dword(struct pci_bus *bus, unsigned int devfn, int where, u32 val); + +int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); +int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val); +int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val); + struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops); static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val) -- cgit v1.2.3 From 1862ee22ce2e28087299aebb6556a5cdc122d0ef Mon Sep 17 00:00:00 2001 From: Pawel Moll Date: Fri, 23 Jan 2015 14:45:55 +1030 Subject: virtio-mmio: Update the device to OASIS spec version This patch add a support for second version of the virtio-mmio device, which follows OASIS "Virtual I/O Device (VIRTIO) Version 1.0" specification. Main changes: 1. The control register symbolic names use the new device/driver nomenclature rather than the old guest/host one. 2. The driver detect the device version (version 1 is the pre-OASIS spec, version 2 is compatible with fist revision of the OASIS spec) and drives the device accordingly. 3. New version uses direct addressing (64 bit address split into two low/high register) instead of the guest page size based one, and addresses each part of the queue (descriptors, available, used) separately. 4. The device activity is now explicitly triggered by writing to the "queue ready" register. 5. Whole 64 bit features are properly handled now (both ways). Signed-off-by: Pawel Moll Acked-by: Michael S. Tsirkin Signed-off-by: Rusty Russell --- include/linux/virtio_mmio.h | 44 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_mmio.h b/include/linux/virtio_mmio.h index 5c7b6f0daef8..c4b09689ab64 100644 --- a/include/linux/virtio_mmio.h +++ b/include/linux/virtio_mmio.h @@ -51,23 +51,29 @@ /* Virtio vendor ID - Read Only */ #define VIRTIO_MMIO_VENDOR_ID 0x00c -/* Bitmask of the features supported by the host +/* Bitmask of the features supported by the device (host) * (32 bits per set) - Read Only */ -#define VIRTIO_MMIO_HOST_FEATURES 0x010 +#define VIRTIO_MMIO_DEVICE_FEATURES 0x010 -/* Host features set selector - Write Only */ -#define VIRTIO_MMIO_HOST_FEATURES_SEL 0x014 +/* Device (host) features set selector - Write Only */ +#define VIRTIO_MMIO_DEVICE_FEATURES_SEL 0x014 -/* Bitmask of features activated by the guest +/* Bitmask of features activated by the driver (guest) * (32 bits per set) - Write Only */ -#define VIRTIO_MMIO_GUEST_FEATURES 0x020 +#define VIRTIO_MMIO_DRIVER_FEATURES 0x020 /* Activated features set selector - Write Only */ -#define VIRTIO_MMIO_GUEST_FEATURES_SEL 0x024 +#define VIRTIO_MMIO_DRIVER_FEATURES_SEL 0x024 + + +#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ /* Guest's memory page size in bytes - Write Only */ #define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028 +#endif + + /* Queue selector - Write Only */ #define VIRTIO_MMIO_QUEUE_SEL 0x030 @@ -77,12 +83,21 @@ /* Queue size for the currently selected queue - Write Only */ #define VIRTIO_MMIO_QUEUE_NUM 0x038 + +#ifndef VIRTIO_MMIO_NO_LEGACY /* LEGACY DEVICES ONLY! */ + /* Used Ring alignment for the currently selected queue - Write Only */ #define VIRTIO_MMIO_QUEUE_ALIGN 0x03c /* Guest's PFN for the currently selected queue - Read Write */ #define VIRTIO_MMIO_QUEUE_PFN 0x040 +#endif + + +/* Ready bit for the currently selected queue - Read Write */ +#define VIRTIO_MMIO_QUEUE_READY 0x044 + /* Queue notifier - Write Only */ #define VIRTIO_MMIO_QUEUE_NOTIFY 0x050 @@ -95,6 +110,21 @@ /* Device status register - Read Write */ #define VIRTIO_MMIO_STATUS 0x070 +/* Selected queue's Descriptor Table address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_DESC_LOW 0x080 +#define VIRTIO_MMIO_QUEUE_DESC_HIGH 0x084 + +/* Selected queue's Available Ring address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_AVAIL_LOW 0x090 +#define VIRTIO_MMIO_QUEUE_AVAIL_HIGH 0x094 + +/* Selected queue's Used Ring address, 64 bits in two halves */ +#define VIRTIO_MMIO_QUEUE_USED_LOW 0x0a0 +#define VIRTIO_MMIO_QUEUE_USED_HIGH 0x0a4 + +/* Configuration atomicity value */ +#define VIRTIO_MMIO_CONFIG_GENERATION 0x0fc + /* The config space is defined by each driver as * the per-driver configuration space - Read Write */ #define VIRTIO_MMIO_CONFIG 0x100 -- cgit v1.2.3 From 55422d0bd292f5ad143cc32cb8bb8505257274c4 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Thu, 22 Jan 2015 00:00:23 -0500 Subject: audit: replace getname()/putname() hacks with reference counters In order to ensure that filenames are not released before the audit subsystem is done with the strings there are a number of hacks built into the fs and audit subsystems around getname() and putname(). To say these hacks are "ugly" would be kind. This patch removes the filename hackery in favor of a more conventional reference count based approach. The diffstat below tells most of the story; lots of audit/fs specific code is replaced with a traditional reference count based approach that is easily understood, even by those not familiar with the audit and/or fs subsystems. CC: viro@zeniv.linux.org.uk CC: linux-fsdevel@vger.kernel.org Signed-off-by: Paul Moore Signed-off-by: Al Viro --- include/linux/audit.h | 3 --- include/linux/fs.h | 9 ++------- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index af84234e1f6e..87c2d347d255 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -128,7 +128,6 @@ extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); -extern void audit_putname(struct filename *name); #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ @@ -353,8 +352,6 @@ static inline struct filename *audit_reusename(const __user char *name) } static inline void audit_getname(struct filename *name) { } -static inline void audit_putname(struct filename *name) -{ } static inline void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags) diff --git a/include/linux/fs.h b/include/linux/fs.h index f90c0282c114..b49842fe203f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2080,6 +2080,7 @@ struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ struct audit_names *aname; + int refcnt; bool separate; /* should "name" be freed? */ }; @@ -2101,6 +2102,7 @@ extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); +extern void putname(struct filename *name); enum { FILE_CREATED = 1, @@ -2121,15 +2123,8 @@ extern void __init vfs_caches_init(unsigned long); extern struct kmem_cache *names_cachep; -extern void final_putname(struct filename *name); - #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -#ifndef CONFIG_AUDITSYSCALL -#define putname(name) final_putname(name) -#else -extern void putname(struct filename *name); -#endif #ifdef CONFIG_BLOCK extern int register_blkdev(unsigned int, const char *); -- cgit v1.2.3 From 41fbf3b39d5eca01527338b4d0ee15ee1ae1023c Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Wed, 17 Dec 2014 13:11:35 +0800 Subject: ktime.h: Introduce ktime_ms_delta This patch adds a reusable time difference function which returns the difference in millisecond, as often used in some driver code, e.g. mtd/test, media/rc, etc. Signed-off-by: Chunyan Zhang Acked-by: Arnd Bergmann Cc: zhang.lyra@gmail.com Cc: davem@davemloft.net Cc: john.stultz@linaro.org Cc: dborkman@redhat.com Link: http://lkml.kernel.org/r/1418793095-18780-1-git-send-email-zhang.chunyan@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/ktime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index c9d645ad98ff..891ea92a68b0 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -186,6 +186,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier) return ktime_to_us(ktime_sub(later, earlier)); } +static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier) +{ + return ktime_to_ms(ktime_sub(later, earlier)); +} + static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec) { return ktime_add_ns(kt, usec * NSEC_PER_USEC); -- cgit v1.2.3 From 536e1715226c94037df12f7c6280cbe0f6009f92 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 5 Nov 2014 11:43:26 +0100 Subject: gpu: host1x: Call ->remove() only when a device is bound When a driver's ->probe() function fails, the host1x bus must not call its ->remove() function because the driver will already have cleaned up in the error handling path in ->probe(). Signed-off-by: Thierry Reding --- include/linux/host1x.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index bb9840fd1e18..7890b553d12e 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -272,6 +272,8 @@ struct host1x_device { struct mutex clients_lock; struct list_head clients; + + bool bound; }; static inline struct host1x_device *to_host1x_device(struct device *dev) -- cgit v1.2.3 From 9bc7491906b4113b4c5ae442157c7dfc4e10cd14 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jan 2015 21:24:10 +0100 Subject: hrtimer: Prevent stale expiry time in hrtimer_interrupt() hrtimer_interrupt() has the following subtle issue: hrtimer_interrupt() lock(cpu_base); expires_next = KTIME_MAX; expire_timers(CLOCK_MONOTONIC); expires = get_next_timer(CLOCK_MONOTONIC); if (expires < expires_next) expires_next = expires; expire_timers(CLOCK_REALTIME); unlock(cpu_base); wakeup() hrtimer_start(CLOCK_MONOTONIC, newtimer); lock(cpu_base(); expires = get_next_timer(CLOCK_REALTIME); if (expires < expires_next) expires_next = expires; So because we already evaluated the next expiring timer of CLOCK_MONOTONIC we ignore that the expiry time of newtimer might be earlier than the overall next expiry time in hrtimer_interrupt(). To solve this, remove the caching of the next expiry value from hrtimer_interrupt() and reevaluate all active clock bases for the next expiry value. To avoid another code duplication, create a shared evaluation function and use it for hrtimer_get_next_event(), hrtimer_force_reprogram() and hrtimer_interrupt(). There is another subtlety in this mechanism: While hrtimer_interrupt() is running, we want to avoid to touch the hardware device because we will reprogram it anyway at the end of hrtimer_interrupt(). This works nicely for hrtimers which get rearmed via the HRTIMER_RESTART mechanism, because we drop out when the callback on that CPU is running. But that fails, if a new timer gets enqueued like in the example above. This has another implication: While hrtimer_interrupt() is running we refuse remote enqueueing of timers - see hrtimer_interrupt() and hrtimer_check_target(). hrtimer_interrupt() tries to prevent this by setting cpu_base->expires to KTIME_MAX, but that fails if a new timer gets queued. Prevent both the hardware access and the remote enqueue explicitely. We can loosen the restriction on the remote enqueue now due to reevaluation of the next expiry value, but that needs a seperate patch. Folded in a fix from Vignesh Radhakrishnan. Reported-and-tested-by: Stanislav Fomichev Based-on-patch-by: Stanislav Fomichev Signed-off-by: Thomas Gleixner Cc: vigneshr@codeaurora.org Cc: john.stultz@linaro.org Cc: viresh.kumar@linaro.org Cc: fweisbec@gmail.com Cc: cl@linux.com Cc: stuart.w.hayes@gmail.com Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1501202049190.5526@nanos Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a036d058a249..05f6df1fdf5b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -170,6 +170,7 @@ enum hrtimer_base_type { * @clock_was_set: Indicates that clock was set from irq context. * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang * @nr_events: Total number of hrtimer interrupt events @@ -185,6 +186,7 @@ struct hrtimer_cpu_base { unsigned int clock_was_set; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t expires_next; + int in_hrtirq; int hres_active; int hang_detected; unsigned long nr_events; -- cgit v1.2.3 From 31928aa5863e71535ee942f506ca9ac8ce1c4315 Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Thu, 4 Dec 2014 15:47:07 +0100 Subject: KVM: remove unneeded return value of vcpu_postcreate The return value of kvm_arch_vcpu_postcreate is not checked in its caller. This is okay, because only x86 provides vcpu_postcreate right now and it could only fail if vcpu_load failed. But that is not possible during KVM_CREATE_VCPU (kvm_arch_vcpu_load is void, too), so just get rid of the unchecked return value. Signed-off-by: Dominik Dingel Acked-by: Cornelia Huck Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 26f106022c88..a82432c710c9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -652,7 +652,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id); int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu); -int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_arch_hardware_enable(void); -- cgit v1.2.3 From 3c5199143bc4b35f472c5c2534026d74821e2044 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 22 Jan 2015 08:19:32 -0500 Subject: sunrpc/lockd: fix references to the BKL The BKL is completely out of the picture in the lockd and sunrpc code these days. Update the antiquated comments that refer to it. Signed-off-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6f22cfeef5e3..fae6fb947fc8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -110,7 +110,7 @@ struct svc_serv { * We use sv_nrthreads as a reference count. svc_destroy() drops * this refcount, so we need to bump it up around operations that * change the number of threads. Horrible, but there it is. - * Should be called with the BKL held. + * Should be called with the "service mutex" held. */ static inline void svc_get(struct svc_serv *serv) { -- cgit v1.2.3 From c5ed1df781cb544d4e4d189bb5b6ec7336d8888c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 19 Jan 2015 08:30:30 +0100 Subject: bcma: use standard bus scanning during early register MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Starting with kernel 3.19-rc1 early registration of bcma on MIPS is done a bit later, with memory allocator available. This allows us to simplify code by using standard bus scanning method. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_soc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h index f24d245f8394..1b5fc0c3b1b5 100644 --- a/include/linux/bcma/bcma_soc.h +++ b/include/linux/bcma/bcma_soc.h @@ -5,8 +5,6 @@ struct bcma_soc { struct bcma_bus bus; - struct bcma_device core_cc; - struct bcma_device core_mips; }; int __init bcma_host_soc_register(struct bcma_soc *soc); -- cgit v1.2.3 From ee1b6f7aff94019c09e73837054979063f722046 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 15 Jan 2015 17:32:25 -0800 Subject: block: support different tag allocation policy The libata tag allocation is using a round-robin policy. Next patch will make libata use block generic tag allocation, so let's add a policy to tag allocation. Currently two policies: FIFO (default) and round-robin. Cc: Jens Axboe Cc: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4c4b732d7556..6f388fd1c11c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -272,7 +272,11 @@ struct blk_queue_tag { int max_depth; /* what we will send to device */ int real_max_depth; /* what the array can hold */ atomic_t refcnt; /* map can be shared */ + int alloc_policy; /* tag allocation policy */ + int next_tag; /* next tag */ }; +#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ +#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) @@ -1139,11 +1143,11 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) extern int blk_queue_start_tag(struct request_queue *, struct request *); extern struct request *blk_queue_find_tag(struct request_queue *, int); extern void blk_queue_end_tag(struct request_queue *, struct request *); -extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *); +extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int); extern void blk_queue_free_tags(struct request_queue *); extern int blk_queue_resize_tags(struct request_queue *, int); extern void blk_queue_invalidate_tags(struct request_queue *); -extern struct blk_queue_tag *blk_init_tags(int); +extern struct blk_queue_tag *blk_init_tags(int, int); extern void blk_free_tags(struct blk_queue_tag *); static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, -- cgit v1.2.3 From 24391c0dc57c3756a219defaa781e68637d6ab7d Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Fri, 23 Jan 2015 14:18:00 -0700 Subject: blk-mq: add tag allocation policy This is the blk-mq part to support tag allocation policy. The default allocation policy isn't changed (though it's not a strict FIFO). The new policy is round-robin for libata. But it's a try-best implementation. If multiple tasks are competing, the tags returned will be mixed (which is unavoidable even with !mq, as requests from different tasks can be mixed in queue) Cc: Jens Axboe Cc: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 5b6500c77ed2..86b08b1a5eba 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -147,6 +147,8 @@ enum { BLK_MQ_F_SG_MERGE = 1 << 2, BLK_MQ_F_SYSFS_UP = 1 << 3, BLK_MQ_F_DEFER_ISSUE = 1 << 4, + BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, + BLK_MQ_F_ALLOC_POLICY_BITS = 1, BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, @@ -155,6 +157,12 @@ enum { BLK_MQ_CPU_WORK_BATCH = 8, }; +#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ + ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ + ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) +#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \ + ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ + << BLK_MQ_F_ALLOC_POLICY_START_BIT) struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); void blk_mq_finish_init(struct request_queue *q); -- cgit v1.2.3 From 12cb5ce101abfaf74421f8cc9f196e708209eb79 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 15 Jan 2015 17:32:27 -0800 Subject: libata: use blk taging libata uses its own tag management which is duplication and the implementation is poor. And if we switch to blk-mq, tag is build-in. It's time to switch to generic taging. The SAS driver has its own tag management, and looks we can't directly map the host controler tag to SATA tag. So I just bypassed the SAS case. I changed the code/variable name for the tag management of libata to make it self contained. Only sas will use it. Later if libsas implements its tag management, the tag management code in libata can be deleted easily. Cc: Jens Axboe Cc: Christoph Hellwig Signed-off-by: Shaohua Li Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/libata.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..f23454762717 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -821,10 +821,10 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE]; - unsigned long qc_allocated; + unsigned long sas_tag_allocated; /* for sas tag allocation only */ unsigned int qc_active; int nr_active_links; /* #links with active qcs */ - unsigned int last_tag; /* track next tag hw expects */ + unsigned int sas_last_tag; /* track next tag hw expects */ struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ @@ -1344,6 +1344,7 @@ extern struct device_attribute *ata_common_sdev_attrs[]; .ioctl = ata_scsi_ioctl, \ .queuecommand = ata_scsi_queuecmd, \ .can_queue = ATA_DEF_QUEUE, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .this_id = ATA_SHT_THIS_ID, \ .cmd_per_lun = ATA_SHT_CMD_PER_LUN, \ .emulated = ATA_SHT_EMULATED, \ -- cgit v1.2.3 From a9aaf2915ee265735c28b764551d084e61a694e0 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 13 Jan 2015 11:34:00 +0530 Subject: cpufreq: stats: get rid of per-cpu cpufreq_stats_table All CPUs sharing a cpufreq policy share stats too. For this reason, add a stats pointer to struct cpufreq_policy and drop per-CPU variable cpufreq_stats_table used for accessing cpufreq stats so as to reduce code complexity. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4d078cebafd2..60b7b496565d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -113,6 +113,9 @@ struct cpufreq_policy { wait_queue_head_t transition_wait; struct task_struct *transition_task; /* Task which is doing the transition */ + /* cpufreq-stats */ + struct cpufreq_stats *stats; + /* For cpufreq driver's internal use */ void *driver_data; }; -- cgit v1.2.3 From 7c418ff099110d987846c8c670479a3b90ed1dcb Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Jan 2015 21:09:08 +0530 Subject: cpufreq: Remove (now) unused 'last_cpu' from struct cpufreq_policy 'last_cpu' was used only from cpufreq-stats and isn't used anymore. Get rid of it. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 60b7b496565d..7e1a389b4e92 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -66,8 +66,6 @@ struct cpufreq_policy { unsigned int shared_type; /* ACPI: ANY or ALL affected CPUs should set cpufreq */ unsigned int cpu; /* cpu nr of CPU managing this policy */ - unsigned int last_cpu; /* cpu nr of previous CPU that managed - * this policy */ struct clk *clk; struct cpufreq_cpuinfo cpuinfo;/* see above */ -- cgit v1.2.3 From d9f354460db8b58a8395936d323b4ca6e8428b9d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Tue, 6 Jan 2015 21:09:10 +0530 Subject: cpufreq: remove CPUFREQ_UPDATE_POLICY_CPU notifications CPUFREQ_UPDATE_POLICY_CPU notifications were used only from cpufreq-stats which doesn't use it anymore. Remove them. This also decrements values of other notification macros defined after CPUFREQ_UPDATE_POLICY_CPU by 1 to remove gaps. Hopefully all users are using macro's instead of direct numbers and so they wouldn't break as macro values are changed now. Reviewed-by: Prarit Bhargava Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7e1a389b4e92..2ee4888c1f47 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -368,9 +368,8 @@ static inline void cpufreq_resume(void) {} #define CPUFREQ_INCOMPATIBLE (1) #define CPUFREQ_NOTIFY (2) #define CPUFREQ_START (3) -#define CPUFREQ_UPDATE_POLICY_CPU (4) -#define CPUFREQ_CREATE_POLICY (5) -#define CPUFREQ_REMOVE_POLICY (6) +#define CPUFREQ_CREATE_POLICY (4) +#define CPUFREQ_REMOVE_POLICY (5) #ifdef CONFIG_CPU_FREQ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list); -- cgit v1.2.3 From 382548a62ade2c003c77a1055b6eb2a47ce30084 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 20 Jan 2015 11:33:09 +0100 Subject: PM / Domains: Remove pm_genpd_dev_need_restore() API There are currently no users of this API, let's remove it. Additionally, if such feature would be needed future wise, a better option is likely use pm_runtime_set_active|suspended() in some form. Signed-off-by: Ulf Hansson Acked-by: Geert Uytterhoeven Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a9edab2c787a..ed607760fc20 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -140,7 +140,6 @@ extern int __pm_genpd_name_add_device(const char *domain_name, extern int pm_genpd_remove_device(struct generic_pm_domain *genpd, struct device *dev); -extern void pm_genpd_dev_need_restore(struct device *dev, bool val); extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_add_subdomain_names(const char *master_name, @@ -187,7 +186,6 @@ static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline void pm_genpd_dev_need_restore(struct device *dev, bool val) {} static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_sd) { -- cgit v1.2.3 From 566fcec60b7458784d4ed9bca974c5a56dacf214 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 23 Jan 2015 15:32:46 -0500 Subject: NFSv4: Fix an atomicity problem in CLOSE If we are to remove the serialisation of OPEN/CLOSE, then we need to ensure that the stateid sent as part of a CLOSE operation does not change after we test the state in nfs4_close_prepare. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..7e38d641236e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -389,7 +389,7 @@ struct nfs_open_confirmres { struct nfs_closeargs { struct nfs4_sequence_args seq_args; struct nfs_fh * fh; - nfs4_stateid * stateid; + nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; const u32 * bitmask; -- cgit v1.2.3 From 8b618628b2bf83512fc8df5e8672619d65adfdfb Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 3 Dec 2014 14:43:06 -0500 Subject: ktime: Optimize ktime_divns for constant divisors At least on ARM, do_div() is optimized to turn constant divisors into an inline multiplication by the reciprocal value at compile time. However this optimization is missed entirely whenever ktime_divns() is used and the slow out-of-line division code is used all the time. Let ktime_divns() use do_div() inline whenever the divisor is constant and small enough. This will make things like ktime_to_us() and ktime_to_ms() much faster. Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Nicolas Pitre Acked-by: Arnd Bergmann Signed-off-by: Nicolas Pitre Signed-off-by: John Stultz --- include/linux/ktime.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ktime.h b/include/linux/ktime.h index c9d645ad98ff..411dd8bfe539 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -166,7 +166,17 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2) } #if BITS_PER_LONG < 64 -extern u64 ktime_divns(const ktime_t kt, s64 div); +extern u64 __ktime_divns(const ktime_t kt, s64 div); +static inline u64 ktime_divns(const ktime_t kt, s64 div) +{ + if (__builtin_constant_p(div) && !(div >> 32)) { + u64 ns = kt.tv64; + do_div(ns, div); + return ns; + } else { + return __ktime_divns(kt, div); + } +} #else /* BITS_PER_LONG < 64 */ # define ktime_divns(kt, div) (u64)((kt).tv64 / (div)) #endif -- cgit v1.2.3 From d08c0cdd26d48751c15aa2b4479a410594fee9ac Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 8 Dec 2014 12:00:09 -0800 Subject: time: Expose getboottime64 for in-kernel uses Adds a timespec64 based getboottime64() implementation that can be used as we convert internal users of getboottime away from using timespecs. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: John Stultz --- include/linux/timekeeping.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9b63d13ba82b..91480137aa39 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,6 +33,7 @@ extern time64_t ktime_get_real_seconds(void); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); +extern void getboottime64(struct timespec64 *ts); #if BITS_PER_LONG == 64 /** @@ -72,6 +73,11 @@ static inline struct timespec get_monotonic_coarse(void) { return get_monotonic_coarse64(); } + +static inline void getboottime(struct timespec *ts) +{ + return getboottime64(ts); +} #else /** * Deprecated. Use do_settimeofday64(). @@ -129,9 +135,15 @@ static inline struct timespec get_monotonic_coarse(void) { return timespec64_to_timespec(get_monotonic_coarse64()); } -#endif -extern void getboottime(struct timespec *ts); +static inline void getboottime(struct timespec *ts) +{ + struct timespec64 ts64; + + getboottime64(&ts64); + *ts = timespec64_to_timespec(ts64); +} +#endif #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts) #define ktime_get_real_ts64(ts) getnstimeofday64(ts) -- cgit v1.2.3 From 2e0c78ee5ba4d777ecf22c8f40cc968b4308ca88 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 18 Dec 2014 18:04:34 -0800 Subject: time: Expose get_monotonic_boottime64 for in-kernel use As part of the 2038 conversion process, add a get_monotonic_boottime64 accessor so we can depracate get_monotonic_boottime. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: John Stultz --- include/linux/timekeeping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 91480137aa39..3eaae4754275 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -229,6 +229,11 @@ static inline void get_monotonic_boottime(struct timespec *ts) *ts = ktime_to_timespec(ktime_get_boottime()); } +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai(struct timespec *ts) { *ts = ktime_to_timespec(ktime_get_clocktai()); -- cgit v1.2.3 From 9a4a445e30f0b601ca2d9433274047cbf48ebf9e Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Thu, 22 Jan 2015 02:31:55 +0000 Subject: rtc: Convert rtc_set_ntp_time() to use timespec64 rtc_set_ntp_time() uses timespec which is y2038-unsafe, so modify to use timespec64 which is y2038-safe, then replace rtc_time_to_tm() with rtc_time64_to_tm(). Also adjust all its call sites(only NTP uses it) accordingly. Cc: pang.xunlei Cc: Arnd Bergmann Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Xunlei Pang Signed-off-by: John Stultz --- include/linux/rtc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6d6be09a2fe5..dcad7ee0d746 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -161,7 +161,7 @@ extern void devm_rtc_device_unregister(struct device *dev, extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs); -extern int rtc_set_ntp_time(struct timespec now); +extern int rtc_set_ntp_time(struct timespec64 now); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); -- cgit v1.2.3 From 425c1d4e5b6d4bd700eb94ad8318bdb05431fdc7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 14:57:53 -0500 Subject: NFSv4: Fix lock on-wire reordering issues This patch ensures that the server cannot reorder our LOCK/LOCKU requests if they are sent in parallel on the wire. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7e38d641236e..b6a6953c0f09 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -416,9 +416,9 @@ struct nfs_lock_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * lock_seqid; - nfs4_stateid * lock_stateid; + nfs4_stateid lock_stateid; struct nfs_seqid * open_seqid; - nfs4_stateid * open_stateid; + nfs4_stateid open_stateid; struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; @@ -437,7 +437,7 @@ struct nfs_locku_args { struct nfs_fh * fh; struct file_lock * fl; struct nfs_seqid * seqid; - nfs4_stateid * stateid; + nfs4_stateid stateid; }; struct nfs_locku_res { -- cgit v1.2.3 From c69899a17ca4836230720e65493942d9582a0424 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 24 Jan 2015 16:03:52 -0500 Subject: NFSv4: Update of VFS byte range lock must be atomic with the stateid update Ensure that we test the lock stateid remained unchanged while we were updating the VFS tracking of the byte range lock. Have the process replay the lock to the server if we detect that was not the case. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b6a6953c0f09..e5c3b620a609 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -422,6 +422,7 @@ struct nfs_lock_args { struct nfs_lowner lock_owner; unsigned char block : 1; unsigned char reclaim : 1; + unsigned char new_lock : 1; unsigned char new_lock_owner : 1; }; -- cgit v1.2.3 From 4e88f3de89fbb7b5a5a0aca20376b276d26732ac Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 21 Jan 2015 17:13:00 +0100 Subject: clk: Introduce clk_has_parent() This new function is similar to clk_set_parent(), except that it doesn't actually change the parent. It merely checks that the given parent clock can be a parent for the given clock. A situation where this is useful is to check that a particular setup is valid before switching to it. One specific use-case for this is atomic modesetting in the DRM framework where setting a mode is divided into a check phase where a given configuration is validated before applying changes to the hardware. Cc: Russell King Signed-off-by: Thierry Reding Reviewed-by: Stephen Boyd Signed-off-by: Michael Turquette --- include/linux/clk.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index c7f258a81761..ba7e9eda4347 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -301,6 +301,18 @@ long clk_round_rate(struct clk *clk, unsigned long rate); */ int clk_set_rate(struct clk *clk, unsigned long rate); +/** + * clk_has_parent - check if a clock is a possible parent for another + * @clk: clock source + * @parent: parent clock source + * + * This function can be used in drivers that need to check that a clock can be + * the parent of another without actually changing the parent. + * + * Returns true if @parent is a possible parent for @clk, false otherwise. + */ +bool clk_has_parent(struct clk *clk, struct clk *parent); + /** * clk_set_parent - set the parent clock source for this clock * @clk: clock source @@ -374,6 +386,11 @@ static inline long clk_round_rate(struct clk *clk, unsigned long rate) return 0; } +static inline bool clk_has_parent(struct clk *clk, struct clk *parent) +{ + return true; +} + static inline int clk_set_parent(struct clk *clk, struct clk *parent) { return 0; -- cgit v1.2.3 From c99e76c55f68eaa0c307ba25803c4e59c2fca1ca Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Mon, 12 Jan 2015 16:05:52 +0100 Subject: USB: host: Introduce flag to enable use of 64-bit dma_mask for ehci-platform ehci-octeon driver used a 64-bit dma_mask. With removal of ehci-octeon and usage of ehci-platform ehci dma_mask is now limited to 32 bits (coerced in ehci_platform_probe). Provide a flag in ehci platform data to allow use of 64 bits for dma_mask. Cc: David Daney Cc: Alex Smith Signed-off-by: Andreas Herrmann Tested-by: Aaro Koskinen Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ehci_pdriver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/ehci_pdriver.h b/include/linux/usb/ehci_pdriver.h index 6287b398abd9..db0431b39a63 100644 --- a/include/linux/usb/ehci_pdriver.h +++ b/include/linux/usb/ehci_pdriver.h @@ -48,6 +48,7 @@ struct usb_ehci_pdata { unsigned big_endian_mmio:1; unsigned no_io_watchdog:1; unsigned reset_on_resume:1; + unsigned dma_mask_64:1; /* Turn on all power and clocks */ int (*power_on)(struct platform_device *pdev); -- cgit v1.2.3 From 9636c37843c9355c1ab6adcd8491186cbdc3b950 Mon Sep 17 00:00:00 2001 From: Chris Rorvick Date: Wed, 14 Jan 2015 21:52:28 -0600 Subject: usb: Fix typo in `struct usb_host_interface' comment The descriptor member `bNumEndpoints' is plural. Signed-off-by: Chris Rorvick Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index f89c24a03bd9..4add5661080a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -82,7 +82,7 @@ struct usb_host_interface { int extralen; unsigned char *extra; /* Extra descriptors */ - /* array of desc.bNumEndpoint endpoints associated with this + /* array of desc.bNumEndpoints endpoints associated with this * interface setting. these will be in no particular order. */ struct usb_host_endpoint *endpoint; -- cgit v1.2.3 From 524134d422316a59d5464ccbc12036bbe90c5563 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 21 Jan 2015 14:02:43 -0500 Subject: USB: don't cancel queued resets when unbinding drivers The USB stack provides a mechanism for drivers to request an asynchronous device reset (usb_queue_reset_device()). The mechanism uses a work item (reset_ws) embedded in the usb_interface structure used by the driver, and the reset is carried out by a work queue routine. The asynchronous reset can race with driver unbinding. When this happens, we try to cancel the queued reset before unbinding the driver, on the theory that the driver won't care about any resets once it is unbound. However, thanks to the fact that lockdep now tracks work queue accesses, this can provoke a lockdep warning in situations where the device reset causes another interface's driver to be unbound; see http://marc.info/?l=linux-usb&m=141893165203776&w=2 for an example. The reason is that the work routine for reset_ws in one interface calls cancel_queued_work() for the reset_ws in another interface. Lockdep thinks this might lead to a work routine trying to cancel itself. The simplest solution is not to cancel queued resets when unbinding drivers. This means we now need to acquire a reference to the usb_interface when queuing a reset_ws work item and to drop the reference when the work routine finishes. We also need to make sure that the usb_interface structure doesn't outlive its parent usb_device; this means acquiring and dropping a reference when the interface is created and destroyed. In addition, cancelling a queued reset can fail (if the device is in the middle of an earlier reset), and this can cause usb_reset_device() to try to rebind an interface that has been deallocated (see http://marc.info/?l=linux-usb&m=142175717016628&w=2 for details). Acquiring the extra references prevents this failure. Signed-off-by: Alan Stern Reported-by: Russell King - ARM Linux Reported-by: Olivier Sobrie Tested-by: Olivier Sobrie Cc: stable # 3.19 Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4add5661080a..7ee1b5c3b4cb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -127,10 +127,6 @@ enum usb_interface_condition { * to the sysfs representation for that device. * @pm_usage_cnt: PM usage counter for this interface * @reset_ws: Used for scheduling resets from atomic context. - * @reset_running: set to 1 if the interface is currently running a - * queued reset so that usb_cancel_queued_reset() doesn't try to - * remove from the workqueue when running inside the worker - * thread. See __usb_queue_reset_device(). * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. * @@ -181,7 +177,6 @@ struct usb_interface { unsigned needs_remote_wakeup:1; /* driver requires remote wakeup */ unsigned needs_altsetting0:1; /* switch to altsetting 0 is pending */ unsigned needs_binding:1; /* needs delayed unbind/rebind */ - unsigned reset_running:1; unsigned resetting_device:1; /* true: bandwidth alloc after reset */ struct device dev; /* interface specific device info */ -- cgit v1.2.3 From 79af73079d753b2d04e46f7445716d3b5f914dbd Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Wed, 21 Jan 2015 10:54:10 -0500 Subject: Add security hooks to binder and implement the hooks for SELinux. Add security hooks to the binder and implement the hooks for SELinux. The security hooks enable security modules such as SELinux to implement controls over binder IPC. The security hooks include support for controlling what process can become the binder context manager (binder_set_context_mgr), controlling the ability of a process to invoke a binder transaction/IPC to another process (binder_transaction), controlling the ability of a process to transfer a binder reference to another process (binder_transfer_binder), and controlling the ability of a process to transfer an open file to another process (binder_transfer_file). These hooks have been included in the Android kernel trees since Android 4.3. (Updated to reflect upstream relocation and changes to the binder driver, changes to the LSM audit data structures, coding style cleanups, and to add inline documentation for the hooks). Signed-off-by: Stephen Smalley Acked-by: Nick Kralevich Acked-by: Jeffrey Vander Stoep Signed-off-by: Greg Kroah-Hartman --- include/linux/security.h | 58 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index ba96471c11ba..a1b7dbd127ff 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1281,6 +1281,25 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @alter contains the flag indicating whether changes are to be made. * Return 0 if permission is granted. * + * @binder_set_context_mgr + * Check whether @mgr is allowed to be the binder context manager. + * @mgr contains the task_struct for the task being registered. + * Return 0 if permission is granted. + * @binder_transaction + * Check whether @from is allowed to invoke a binder transaction call + * to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_binder + * Check whether @from is allowed to transfer a binder reference to @to. + * @from contains the task_struct for the sending task. + * @to contains the task_struct for the receiving task. + * @binder_transfer_file + * Check whether @from is allowed to transfer @file to @to. + * @from contains the task_struct for the sending task. + * @file contains the struct file being transferred. + * @to contains the task_struct for the receiving task. + * * @ptrace_access_check: * Check permission before allowing the current process to trace the * @child process. @@ -1441,6 +1460,14 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) struct security_operations { char name[SECURITY_NAME_MAX + 1]; + int (*binder_set_context_mgr) (struct task_struct *mgr); + int (*binder_transaction) (struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_binder) (struct task_struct *from, + struct task_struct *to); + int (*binder_transfer_file) (struct task_struct *from, + struct task_struct *to, struct file *file); + int (*ptrace_access_check) (struct task_struct *child, unsigned int mode); int (*ptrace_traceme) (struct task_struct *parent); int (*capget) (struct task_struct *target, @@ -1739,6 +1766,13 @@ extern void __init security_fixup_ops(struct security_operations *ops); /* Security operations */ +int security_binder_set_context_mgr(struct task_struct *mgr); +int security_binder_transaction(struct task_struct *from, + struct task_struct *to); +int security_binder_transfer_binder(struct task_struct *from, + struct task_struct *to); +int security_binder_transfer_file(struct task_struct *from, + struct task_struct *to, struct file *file); int security_ptrace_access_check(struct task_struct *child, unsigned int mode); int security_ptrace_traceme(struct task_struct *parent); int security_capget(struct task_struct *target, @@ -1927,6 +1961,30 @@ static inline int security_init(void) return 0; } +static inline int security_binder_set_context_mgr(struct task_struct *mgr) +{ + return 0; +} + +static inline int security_binder_transaction(struct task_struct *from, + struct task_struct *to) +{ + return 0; +} + +static inline int security_binder_transfer_binder(struct task_struct *from, + struct task_struct *to) +{ + return 0; +} + +static inline int security_binder_transfer_file(struct task_struct *from, + struct task_struct *to, + struct file *file) +{ + return 0; +} + static inline int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { -- cgit v1.2.3 From d61031ee8df6214d58371a1cc36a0591e242fba0 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 9 Jan 2015 23:54:34 -0800 Subject: Drivers: hv: vmbus: Support a vmbus API for efficiently sending page arrays Currently, the API for sending a multi-page buffer over VMBUS is limited to a maximum pfn array of MAX_MULTIPAGE_BUFFER_COUNT. This limitation is not imposed by the host and unnecessarily limits the maximum payload that can be sent. Implement an API that does not have this restriction. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 476c685ca6f9..259023a34bec 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -57,6 +57,18 @@ struct hv_multipage_buffer { u64 pfn_array[MAX_MULTIPAGE_BUFFER_COUNT]; }; +/* + * Multiple-page buffer array; the pfn array is variable size: + * The number of entries in the PFN array is determined by + * "len" and "offset". + */ +struct hv_mpb_array { + /* Length and Offset determines the # of pfns in the array */ + u32 len; + u32 offset; + u64 pfn_array[]; +}; + /* 0x18 includes the proprietary packet header */ #define MAX_PAGE_BUFFER_PACKET (0x18 + \ (sizeof(struct hv_page_buffer) * \ @@ -814,6 +826,18 @@ struct vmbus_channel_packet_multipage_buffer { struct hv_multipage_buffer range; } __packed; +/* The format must be the same as struct vmdata_gpa_direct */ +struct vmbus_packet_mpb_array { + u16 type; + u16 dataoffset8; + u16 length8; + u16 flags; + u64 transactionid; + u32 reserved; + u32 rangecount; /* Always 1 in this case */ + struct hv_mpb_array range; +} __packed; + extern int vmbus_open(struct vmbus_channel *channel, u32 send_ringbuffersize, @@ -845,6 +869,13 @@ extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, u32 bufferlen, u64 requestid); +extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, + struct vmbus_packet_mpb_array *mpb, + u32 desc_size, + void *buffer, + u32 bufferlen, + u64 requestid); + extern int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 size, -- cgit v1.2.3 From 67fae053bfc6e84144150e4c6c62670abb215c33 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Tue, 20 Jan 2015 16:45:05 +0100 Subject: Drivers: hv: rename sc_lock to the more generic lock sc_lock spinlock in struct vmbus_channel is being used to not only protect the sc_list field, e.g. vmbus_open() function uses it to implement test-and-set access to the state field. Rename it to the more generic 'lock' and add the description. Signed-off-by: Vitaly Kuznetsov Signed-off-by: K. Y. Srinivasan Acked-by: Jason Wang Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 259023a34bec..5a2ba674795e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -734,7 +734,12 @@ struct vmbus_channel { */ void (*sc_creation_callback)(struct vmbus_channel *new_sc); - spinlock_t sc_lock; + /* + * The spinlock to protect the structure. It is being used to protect + * test-and-set access to various attributes of the structure as well + * as all sc_list operations. + */ + spinlock_t lock; /* * All Sub-channels of a primary channel are linked here. */ -- cgit v1.2.3 From 77b3da6e3232d3b4d4b8addb4b05799fe98f3bf8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 25 Jan 2015 15:10:32 -0500 Subject: new primitive: debugfs_create_automount() Signed-off-by: Al Viro --- include/linux/debugfs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index da4c4983adbe..ea149a24a1f2 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -56,6 +56,11 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest); +struct dentry *debugfs_create_automount(const char *name, + struct dentry *parent, + struct vfsmount *(*f)(void *), + void *data); + void debugfs_remove(struct dentry *dentry); void debugfs_remove_recursive(struct dentry *dentry); -- cgit v1.2.3 From 872bf2fb69d90e3619befee842fc26db39d8e475 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:35 +0200 Subject: net/mlx4_core: Maintain a persistent memory for mlx4 device Maintain a persistent memory that should survive reset flow/PCI error. This comes as a preparation for coming series to support above flows. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index f1e41b33462f..1069ce65e8b4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -744,8 +744,15 @@ struct mlx4_vf_dev { u8 n_ports; }; -struct mlx4_dev { +struct mlx4_dev_persistent { struct pci_dev *pdev; + struct mlx4_dev *dev; + int nvfs[MLX4_MAX_PORTS + 1]; + int num_vfs; +}; + +struct mlx4_dev { + struct mlx4_dev_persistent *persist; unsigned long flags; unsigned long num_slaves; struct mlx4_caps caps; @@ -754,13 +761,11 @@ struct mlx4_dev { struct radix_tree_root qp_table_tree; u8 rev_id; char board_id[MLX4_BOARD_ID_LEN]; - int num_vfs; int numa_node; int oper_log_mgm_entry_size; u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; struct mlx4_vf_dev *dev_vfs; - int nvfs[MLX4_MAX_PORTS + 1]; }; struct mlx4_eqe { -- cgit v1.2.3 From dd0eefe3abbf47442db296bf68f27eb2860c1cdf Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:36 +0200 Subject: net/mlx4_core: Set device configuration data to be persistent across reset When an HCA enters an internal error state, this is detected by the driver. The driver then should reset the HCA and restart the software stack. Keep ports information and some SRIOV configuration in a persistent area to have it valid across reset. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 1069ce65e8b4..8c3837ac1a2d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -749,6 +749,8 @@ struct mlx4_dev_persistent { struct mlx4_dev *dev; int nvfs[MLX4_MAX_PORTS + 1]; int num_vfs; + enum mlx4_port_type curr_port_type[MLX4_MAX_PORTS + 1]; + enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1]; }; struct mlx4_dev { -- cgit v1.2.3 From ad9a0bf08ffbf32b8f292c3bb78ca0f24bb8f6b2 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:37 +0200 Subject: net/mlx4_core: Refactor the catas flow to work per device Using a WQ per device instead of a single global WQ, this allows independent reset handling per device even when SRIOV is used. This comes as a pre-patch for supporting chip reset for both native and SRIOV. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 8c3837ac1a2d..da425d2f3708 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -751,6 +751,8 @@ struct mlx4_dev_persistent { int num_vfs; enum mlx4_port_type curr_port_type[MLX4_MAX_PORTS + 1]; enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1]; + struct work_struct catas_work; + struct workqueue_struct *catas_wq; }; struct mlx4_dev { -- cgit v1.2.3 From f6bc11e42646e661e699a5593cbd1e9dba7191d0 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:38 +0200 Subject: net/mlx4_core: Enhance the catas flow to support device reset This includes: - resetting the chip when a fatal error is detected (the current code does not do this). - exposing the ability to enter error state from outside the catas code by calling its functionality. (E.g. FW Command timeout, AER error). - managing a persistent device state. This is needed to sync between reset flow cases. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index da425d2f3708..7d5d317cb7a6 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -411,6 +411,11 @@ enum { MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK = 1 << 4, }; +enum { + MLX4_DEVICE_STATE_UP = 1 << 0, + MLX4_DEVICE_STATE_INTERNAL_ERROR = 1 << 1, +}; + #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK) @@ -753,6 +758,8 @@ struct mlx4_dev_persistent { enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1]; struct work_struct catas_work; struct workqueue_struct *catas_wq; + struct mutex device_state_mutex; /* protect HW state */ + u8 state; }; struct mlx4_dev { -- cgit v1.2.3 From f5aef5aa35063f2b45c3605871cd525d0cb7fb7a Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:39 +0200 Subject: net/mlx4_core: Activate reset flow upon fatal command cases We activate reset flow upon command fatal errors, when the device enters an erroneous state, and must be reset. The cases below are assumed to be fatal: FW command timed-out, an error from FW on closing commands, pci is offline when posting/pending a command. In those cases we place the device into an error state: chip is reset, pending commands are awakened and completed immediately. Subsequent commands will return immediately. The return code in the above cases will depend on the command. Commands which free and close resources will return success (because the chip was reset, so callers may safely free their kernel resources). Other commands will return -EIO. Since the device's state was marked as error, the catas poller will detect this and restart the device's software stack (as is done when a FW internal error is directly detected). The device state is protected by a persistent mutex lives on its mlx4_dev, as such no need any more for the hcr_mutex which is removed. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 64d25941b329..e7543844cc7a 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -279,6 +279,7 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state); int mlx4_config_dev_retrieval(struct mlx4_dev *dev, struct mlx4_config_dev_params *params); +void mlx4_cmd_wake_completions(struct mlx4_dev *dev); /* * mlx4_get_slave_default_vlan - * return true if VST ( default vlan) -- cgit v1.2.3 From c69453e294c9f16da977b68e658a8028b854c209 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:40 +0200 Subject: net/mlx4_core: Manage interface state for Reset flow cases We need to manage interface state to sync between reset flow and some other relative cases such as remove_one. This has to be done to prevent certain races. For example in case software stack is down as a result of unload call, the remove_one should skip the unload phase. Implement the remove_one case, handling AER and other cases comes next. The interface can be up/down, upon remove_one, the state will include an extra bit indicating that the device is cleaned-up, forcing other tasks to finish before the final cleanup. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7d5d317cb7a6..33f9ca71925c 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -416,6 +416,11 @@ enum { MLX4_DEVICE_STATE_INTERNAL_ERROR = 1 << 1, }; +enum { + MLX4_INTERFACE_STATE_UP = 1 << 0, + MLX4_INTERFACE_STATE_DELETION = 1 << 1, +}; + #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK) @@ -760,6 +765,8 @@ struct mlx4_dev_persistent { struct workqueue_struct *catas_wq; struct mutex device_state_mutex; /* protect HW state */ u8 state; + struct mutex interface_state_mutex; /* protect SW state */ + u8 interface_state; }; struct mlx4_dev { -- cgit v1.2.3 From 55ad359225b2232b9b8f04a0dfa169bd3a7d86d2 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 25 Jan 2015 16:59:42 +0200 Subject: net/mlx4_core: Enable device recovery flow with SRIOV In SRIOV, both the PF and the VF may attempt device recovery whenever they assume that the device is not functioning. When the PF driver resets the device, the VF should detect this and attempt to reinitialize itself. The VF must be able to reset itself under all circumstances, even if the PF is not responsive. The VF shall reset itself in the following cases: 1. Commands are not processed within reasonable time over the communication channel. This is done considering device state and the correct return code based on the command as was done in the native mode, done in the next patch. 2. The VF driver receives an internal error event reported by the PF on the communication channel. This occurs when the PF driver resets the device or when VF is out of sync with the PF. Add 'VF reset' capability, which allows the VF to reinitialize itself even when the PF is not responsive. As PF and VF may run their reset flow simulantanisly, there are several cases that are handled: - Prevent freeing VF resources upon FLR, when PF is in its unloading stage. - Prevent PF getting VF commands before it has finished initializing its resources. - Upon VF startup, check that comm-channel is online before sending commands to the PF and getting timed-out. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 2 ++ include/linux/mlx4/device.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index e7543844cc7a..c989442ffc6a 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -280,6 +280,7 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat int mlx4_config_dev_retrieval(struct mlx4_dev *dev, struct mlx4_config_dev_params *params); void mlx4_cmd_wake_completions(struct mlx4_dev *dev); +void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev); /* * mlx4_get_slave_default_vlan - * return true if VST ( default vlan) @@ -289,5 +290,6 @@ bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave, u16 *vlan, u8 *qos); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) +#define COMM_CHAN_EVENT_INTERNAL_ERR (1 << 17) #endif /* MLX4_CMD_H */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 33f9ca71925c..5ef54e145e4d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -208,6 +208,10 @@ enum { MLX4_QUERY_FUNC_FLAGS_A0_RES_QP = 1LL << 1 }; +enum { + MLX4_VF_CAP_FLAG_RESET = 1 << 0 +}; + /* bit enums for an 8-bit flags field indicating special use * QPs which require special handling in qp_reserve_range. * Currently, this only includes QPs used by the ETH interface, @@ -545,6 +549,7 @@ struct mlx4_caps { u8 alloc_res_qp_mask; u32 dmfs_high_rate_qpn_base; u32 dmfs_high_rate_qpn_range; + u32 vf_caps; }; struct mlx4_buf_list { -- cgit v1.2.3 From 03af03ad7c6723e0f87568e4ffe66ceb9608bfe7 Mon Sep 17 00:00:00 2001 From: Karol Wrona Date: Wed, 7 Jan 2015 19:36:11 +0100 Subject: iio: Add new operating mode for non triggered sw buffers There was a need for non triggered software buffer type. It can be used when triggered model does not fit and INDIO_BUFFER_HARDWARE causes confusion because the data stream can be obtained not directly form hardware backend. Suggested-by: Jonathan Cameron Signed-off-by: Karol Wrona Reviewed-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 878d861b0610..590202024857 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -286,10 +286,11 @@ static inline s64 iio_get_time_ns(void) /* Device operating modes */ #define INDIO_DIRECT_MODE 0x01 #define INDIO_BUFFER_TRIGGERED 0x02 +#define INDIO_BUFFER_SOFTWARE 0x04 #define INDIO_BUFFER_HARDWARE 0x08 #define INDIO_ALL_BUFFER_MODES \ - (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE) + (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | INDIO_BUFFER_SOFTWARE) #define INDIO_MAX_RAW_ELEMENTS 4 @@ -593,7 +594,8 @@ void devm_iio_trigger_free(struct device *dev, struct iio_trigger *iio_trig); static inline bool iio_buffer_enabled(struct iio_dev *indio_dev) { return indio_dev->currentmode - & (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE); + & (INDIO_BUFFER_TRIGGERED | INDIO_BUFFER_HARDWARE | + INDIO_BUFFER_SOFTWARE); } /** -- cgit v1.2.3 From c2943f14534bdc4230f4da6dcd4ea03c5d8c8162 Mon Sep 17 00:00:00 2001 From: Harout Hedeshian Date: Tue, 20 Jan 2015 10:06:05 -0700 Subject: net: ipv6: Add sysctl entry to disable MTU updates from RA The kernel forcefully applies MTU values received in router advertisements provided the new MTU is less than the current. This behavior is undesirable when the user space is managing the MTU. Instead a sysctl flag 'accept_ra_mtu' is introduced such that the user space can control whether or not RA provided MTU updates should be applied. The default behavior is unchanged; user space must explicitly set this flag to 0 for RA MTUs to be ignored. Signed-off-by: Harout Hedeshian Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c694e7baa621..2805062c013f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -52,6 +52,7 @@ struct ipv6_devconf { __s32 force_tllao; __s32 ndisc_notify; __s32 suppress_frag_ndisc; + __s32 accept_ra_mtu; void *sysctl; }; -- cgit v1.2.3 From d6cb125b9983e1ea9444f794b2d3ed5e3ad737b7 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 24 Dec 2014 22:47:00 -0500 Subject: kill d_validate() no users left Signed-off-by: Al Viro --- include/linux/dcache.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 5a813988e6d4..92c08cf7670e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -319,9 +319,6 @@ static inline unsigned d_count(const struct dentry *dentry) return dentry->d_lockref.count; } -/* validate "insecure" dentry pointer */ -extern int d_validate(struct dentry *, struct dentry *); - /* * helper function for dentry_operations.d_dname() members */ -- cgit v1.2.3 From 9e251d02041432487d89cb340e72490c4bbc198a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 9 Jan 2015 20:40:02 -0500 Subject: kill pin_put() Signed-off-by: Al Viro --- include/linux/fs_pin.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h index f66525e72ccf..68a54b7741aa 100644 --- a/include/linux/fs_pin.h +++ b/include/linux/fs_pin.h @@ -12,6 +12,5 @@ struct fs_pin { void (*kill)(struct fs_pin *); }; -void pin_put(struct fs_pin *); void pin_remove(struct fs_pin *); void pin_insert(struct fs_pin *, struct vfsmount *); -- cgit v1.2.3 From 360f54796ed65939093ae373b92ebd5ef3341776 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 9 Jan 2015 15:19:03 -0800 Subject: dcache: let the dentry count go down to zero without taking d_lock We can be more aggressive about this, if we are clever and careful. This is subtle. Signed-off-by: Linus Torvalds Signed-off-by: Al Viro --- include/linux/lockref.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 4bfde0e99ed5..b10b122dd099 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -28,12 +28,13 @@ struct lockref { #endif struct { spinlock_t lock; - unsigned int count; + int count; }; }; }; extern void lockref_get(struct lockref *); +extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); -- cgit v1.2.3 From 34cece2e8a1d2b66f00e153a19b80b4d4cec4eb8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 10 Jan 2015 12:47:38 -0500 Subject: take count and rcu_head out of fs_pin Signed-off-by: Al Viro --- include/linux/fs_pin.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h index 68a54b7741aa..a2e71912e758 100644 --- a/include/linux/fs_pin.h +++ b/include/linux/fs_pin.h @@ -1,14 +1,8 @@ #include struct fs_pin { - atomic_long_t count; - union { - struct { - struct hlist_node s_list; - struct hlist_node m_list; - }; - struct rcu_head rcu; - }; + struct hlist_node s_list; + struct hlist_node m_list; void (*kill)(struct fs_pin *); }; -- cgit v1.2.3 From fdab684d7202774bfd8762d4a656a553b787c8ec Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 11 Jan 2015 10:57:27 -0500 Subject: allow attaching fs_pin to a group not associated with some superblock Signed-off-by: Al Viro --- include/linux/fs_pin.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h index a2e71912e758..2be38d1464ae 100644 --- a/include/linux/fs_pin.h +++ b/include/linux/fs_pin.h @@ -7,4 +7,5 @@ struct fs_pin { }; void pin_remove(struct fs_pin *); +void pin_insert_group(struct fs_pin *, struct vfsmount *, struct hlist_head *); void pin_insert(struct fs_pin *, struct vfsmount *); -- cgit v1.2.3 From 59eda0e07f43c950d31756213b607af673e551f0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 10 Jan 2015 17:53:21 -0500 Subject: new fs_pin killing logics Signed-off-by: Al Viro --- include/linux/fs_pin.h | 13 ++++++++++++- include/linux/pid_namespace.h | 4 ++-- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs_pin.h b/include/linux/fs_pin.h index 2be38d1464ae..9dc4e0384bfb 100644 --- a/include/linux/fs_pin.h +++ b/include/linux/fs_pin.h @@ -1,11 +1,22 @@ -#include +#include struct fs_pin { + wait_queue_head_t wait; + int done; struct hlist_node s_list; struct hlist_node m_list; void (*kill)(struct fs_pin *); }; +struct vfsmount; + +static inline void init_fs_pin(struct fs_pin *p, void (*kill)(struct fs_pin *)) +{ + init_waitqueue_head(&p->wait); + p->kill = kill; +} + void pin_remove(struct fs_pin *); void pin_insert_group(struct fs_pin *, struct vfsmount *, struct hlist_head *); void pin_insert(struct fs_pin *, struct vfsmount *); +void pin_kill(struct fs_pin *); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index b9cf6c51b181..918b117a7cd3 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -19,7 +19,7 @@ struct pidmap { #define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1) #define PIDMAP_ENTRIES ((PID_MAX_LIMIT+BITS_PER_PAGE-1)/BITS_PER_PAGE) -struct bsd_acct_struct; +struct fs_pin; struct pid_namespace { struct kref kref; @@ -37,7 +37,7 @@ struct pid_namespace { struct dentry *proc_thread_self; #endif #ifdef CONFIG_BSD_PROCESS_ACCT - struct bsd_acct_struct *bacct; + struct fs_pin *bacct; #endif struct user_namespace *user_ns; struct work_struct proc_work; -- cgit v1.2.3 From 607954b084d4ad5e6a2e0f795de7803d9c6ae37f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 21 Jan 2015 11:12:13 +0000 Subject: rhashtable: fix rht_for_each_entry_safe() endless loop "next" is not updated, causing an endless loop for buckets with more than one element. Fixes: 88d6ed15acff ("rhashtable: Convert bucket iterators to take table and index") Signed-off-by: Patrick McHardy Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index a2562ed53ea3..e0337844358e 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -260,7 +260,9 @@ void rhashtable_destroy(struct rhashtable *ht); next = !rht_is_a_nulls(pos) ? \ rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ - pos = next) + pos = next, \ + next = !rht_is_a_nulls(pos) ? \ + rht_dereference_bucket(pos->next, tbl, hash) : NULL) /** * rht_for_each_rcu_continue - continue iterating over rcu hash chain -- cgit v1.2.3 From 19f92b237b1700d30b788f00b16a627ffbfdf0e5 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 13 Jan 2015 14:23:25 -0800 Subject: irqchip: omap-intc: Fix support for dm814 and dm816 On dm81xx we have 128 interrupts like am33xx has. Let's add compatible flags for dm814x and dm816x, and document the existing binding. As the dm81xx are booting in device tree only mode, we can now also remove ti81xx_init_irq() legacy function. Signed-off-by: Tony Lindgren Reviewed-by: Felipe Balbi Cc: Brian Hutchinson Cc: Jason Cooper Link: http://lkml.kernel.org/r/1421187806-6804-2-git-send-email-tony@atomide.com Signed-off-by: Thomas Gleixner --- include/linux/irqchip/irq-omap-intc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h index e06b370cfc0d..bda426ab0ab7 100644 --- a/include/linux/irqchip/irq-omap-intc.h +++ b/include/linux/irqchip/irq-omap-intc.h @@ -20,7 +20,6 @@ void omap2_init_irq(void); void omap3_init_irq(void); -void ti81xx_init_irq(void); int omap_irq_pending(void); void omap_intc_save_context(void); -- cgit v1.2.3 From c7f2a2ac377626897ad68e63d24d85ee21f47bb1 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 13 Jan 2015 14:23:26 -0800 Subject: irqchip: omap-intc: Remove unused legacy interface for omap2 Nowadays omap2 is booting in device tree only mode so there is no need to keep the legacy interface around for omap2_init_irq(). Signed-off-by: Tony Lindgren Reviewed-by: Felipe Balbi Cc: Jason Cooper Link: http://lkml.kernel.org/r/1421187806-6804-3-git-send-email-tony@atomide.com Signed-off-by: Thomas Gleixner --- include/linux/irqchip/irq-omap-intc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/irq-omap-intc.h b/include/linux/irqchip/irq-omap-intc.h index bda426ab0ab7..2e3d1afeb674 100644 --- a/include/linux/irqchip/irq-omap-intc.h +++ b/include/linux/irqchip/irq-omap-intc.h @@ -18,7 +18,6 @@ #ifndef __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H #define __INCLUDE_LINUX_IRQCHIP_IRQ_OMAP_INTC_H -void omap2_init_irq(void); void omap3_init_irq(void); int omap_irq_pending(void); -- cgit v1.2.3 From 0b35fa7daefe9da6fdef91d95e07eebb714a8fcc Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Jan 2015 23:33:30 +0100 Subject: NFC: st21nfcb: Remove useless include include/linux/platform_data/st21nfcb.h is phy generic. There is no need to include linux/i2c.h Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st21nfcb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st21nfcb.h index c3b432f5b63e..05c54c958cc3 100644 --- a/include/linux/platform_data/st21nfcb.h +++ b/include/linux/platform_data/st21nfcb.h @@ -19,8 +19,6 @@ #ifndef _ST21NFCB_NCI_H_ #define _ST21NFCB_NCI_H_ -#include - #define ST21NFCB_NCI_DRIVER_NAME "st21nfcb_nci" struct st21nfcb_nfc_platform_data { -- cgit v1.2.3 From 6da7c85c75eed769423b428eb654eaaf89d273c1 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Jan 2015 23:33:31 +0100 Subject: NFC: st21nfcb: Fix copy/paste error in comment include/linux/platform_data/st21nfcb.h is based on include/linux/platform_data/st21nfca.h. The endif comment is inacurrate for st21nfcb. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st21nfcb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st21nfcb.h index 05c54c958cc3..b023373d9874 100644 --- a/include/linux/platform_data/st21nfcb.h +++ b/include/linux/platform_data/st21nfcb.h @@ -26,4 +26,4 @@ struct st21nfcb_nfc_platform_data { unsigned int irq_polarity; }; -#endif /* _ST21NFCA_HCI_H_ */ +#endif /* _ST21NFCB_NCI_H_ */ -- cgit v1.2.3 From 7aea8389a77abf9fde254aca2434a605c7704f58 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Fri, 9 Jan 2015 07:22:51 -0800 Subject: leds: Add LED Flash class extension to the LED subsystem Some LED devices support two operation modes - torch and flash. This patch provides support for flash LED devices in the LED subsystem by introducing new sysfs attributes and kernel internal interface. The attributes being introduced are: flash_brightness, flash_strobe, flash_timeout, max_flash_timeout, max_flash_brightness, flash_fault, flash_sync_strobe and available_sync_leds. All the flash related features are placed in a separate module. The modifications aim to be compatible with V4L2 framework requirements related to the flash devices management. The design assumes that V4L2 sub-device can take of the LED class device control and communicate with it through the kernel internal interface. When V4L2 Flash sub-device file is opened, the LED class device sysfs interface is made unavailable. Signed-off-by: Jacek Anaszewski Acked-by: Kyungmin Park Cc: Richard Purdie Acked-by: Pavel Machek Signed-off-by: Bryan Wu --- include/linux/led-class-flash.h | 207 ++++++++++++++++++++++++++++++++++++++++ include/linux/leds.h | 3 + 2 files changed, 210 insertions(+) create mode 100644 include/linux/led-class-flash.h (limited to 'include/linux') diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h new file mode 100644 index 000000000000..5ba2facd7a51 --- /dev/null +++ b/include/linux/led-class-flash.h @@ -0,0 +1,207 @@ +/* + * LED Flash class interface + * + * Copyright (C) 2015 Samsung Electronics Co., Ltd. + * Author: Jacek Anaszewski + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#ifndef __LINUX_FLASH_LEDS_H_INCLUDED +#define __LINUX_FLASH_LEDS_H_INCLUDED + +#include +#include + +struct device_node; +struct led_classdev_flash; + +/* + * Supported led fault bits - must be kept in synch + * with V4L2_FLASH_FAULT bits. + */ +#define LED_FAULT_OVER_VOLTAGE (1 << 0) +#define LED_FAULT_TIMEOUT (1 << 1) +#define LED_FAULT_OVER_TEMPERATURE (1 << 2) +#define LED_FAULT_SHORT_CIRCUIT (1 << 3) +#define LED_FAULT_OVER_CURRENT (1 << 4) +#define LED_FAULT_INDICATOR (1 << 5) +#define LED_FAULT_UNDER_VOLTAGE (1 << 6) +#define LED_FAULT_INPUT_VOLTAGE (1 << 7) +#define LED_FAULT_LED_OVER_TEMPERATURE (1 << 8) +#define LED_NUM_FLASH_FAULTS 9 + +#define LED_FLASH_MAX_SYSFS_GROUPS 7 + +struct led_flash_ops { + /* set flash brightness */ + int (*flash_brightness_set)(struct led_classdev_flash *fled_cdev, + u32 brightness); + /* get flash brightness */ + int (*flash_brightness_get)(struct led_classdev_flash *fled_cdev, + u32 *brightness); + /* set flash strobe state */ + int (*strobe_set)(struct led_classdev_flash *fled_cdev, bool state); + /* get flash strobe state */ + int (*strobe_get)(struct led_classdev_flash *fled_cdev, bool *state); + /* set flash timeout */ + int (*timeout_set)(struct led_classdev_flash *fled_cdev, u32 timeout); + /* get the flash LED fault */ + int (*fault_get)(struct led_classdev_flash *fled_cdev, u32 *fault); +}; + +/* + * Current value of a flash setting along + * with its constraints. + */ +struct led_flash_setting { + /* maximum allowed value */ + u32 min; + /* maximum allowed value */ + u32 max; + /* step value */ + u32 step; + /* current value */ + u32 val; +}; + +struct led_classdev_flash { + /* led class device */ + struct led_classdev led_cdev; + + /* flash led specific ops */ + const struct led_flash_ops *ops; + + /* flash brightness value in microamperes along with its constraints */ + struct led_flash_setting brightness; + + /* flash timeout value in microseconds along with its constraints */ + struct led_flash_setting timeout; + + /* LED Flash class sysfs groups */ + const struct attribute_group *sysfs_groups[LED_FLASH_MAX_SYSFS_GROUPS]; + + /* LEDs available for flash strobe synchronization */ + struct led_classdev_flash **sync_leds; + + /* Number of LEDs available for flash strobe synchronization */ + int num_sync_leds; + + /* + * The identifier of the sub-led to synchronize the flash strobe with. + * Identifiers start from 1, which reflects the first element from the + * sync_leds array. 0 means that the flash strobe should not be + * synchronized. + */ + u32 sync_led_id; +}; + +static inline struct led_classdev_flash *lcdev_to_flcdev( + struct led_classdev *lcdev) +{ + return container_of(lcdev, struct led_classdev_flash, led_cdev); +} + +/** + * led_classdev_flash_register - register a new object of led_classdev class + * with support for flash LEDs + * @parent: the flash LED to register + * @fled_cdev: the led_classdev_flash structure for this device + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_classdev_flash_register(struct device *parent, + struct led_classdev_flash *fled_cdev); + +/** + * led_classdev_flash_unregister - unregisters an object of led_classdev class + * with support for flash LEDs + * @fled_cdev: the flash LED to unregister + * + * Unregister a previously registered via led_classdev_flash_register object + */ +extern void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev); + +/** + * led_set_flash_strobe - setup flash strobe + * @fled_cdev: the flash LED to set strobe on + * @state: 1 - strobe flash, 0 - stop flash strobe + * + * Strobe the flash LED. + * + * Returns: 0 on success or negative error value on failure + */ +static inline int led_set_flash_strobe(struct led_classdev_flash *fled_cdev, + bool state) +{ + return fled_cdev->ops->strobe_set(fled_cdev, state); +} + +/** + * led_get_flash_strobe - get flash strobe status + * @fled_cdev: the flash LED to query + * @state: 1 - flash is strobing, 0 - flash is off + * + * Check whether the flash is strobing at the moment. + * + * Returns: 0 on success or negative error value on failure + */ +static inline int led_get_flash_strobe(struct led_classdev_flash *fled_cdev, + bool *state) +{ + if (fled_cdev->ops->strobe_get) + return fled_cdev->ops->strobe_get(fled_cdev, state); + + return -EINVAL; +} + +/** + * led_set_flash_brightness - set flash LED brightness + * @fled_cdev: the flash LED to set + * @brightness: the brightness to set it to + * + * Set a flash LED's brightness. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_set_flash_brightness(struct led_classdev_flash *fled_cdev, + u32 brightness); + +/** + * led_update_flash_brightness - update flash LED brightness + * @fled_cdev: the flash LED to query + * + * Get a flash LED's current brightness and update led_flash->brightness + * member with the obtained value. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_update_flash_brightness(struct led_classdev_flash *fled_cdev); + +/** + * led_set_flash_timeout - set flash LED timeout + * @fled_cdev: the flash LED to set + * @timeout: the flash timeout to set it to + * + * Set the flash strobe duration. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, + u32 timeout); + +/** + * led_get_flash_fault - get the flash LED fault + * @fled_cdev: the flash LED to query + * @fault: bitmask containing flash faults + * + * Get the flash LED fault. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_get_flash_fault(struct led_classdev_flash *fled_cdev, + u32 *fault); + +#endif /* __LINUX_FLASH_LEDS_H_INCLUDED */ diff --git a/include/linux/leds.h b/include/linux/leds.h index cfceef32c9b3..f70f84f35674 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -46,6 +46,8 @@ struct led_classdev { #define LED_SYSFS_DISABLE (1 << 20) #define SET_BRIGHTNESS_ASYNC (1 << 21) #define SET_BRIGHTNESS_SYNC (1 << 22) +#define LED_DEV_CAP_FLASH (1 << 23) +#define LED_DEV_CAP_SYNC_STROBE (1 << 24) /* Set LED brightness level */ /* Must not sleep, use a workqueue if needed */ @@ -81,6 +83,7 @@ struct led_classdev { unsigned long blink_delay_on, blink_delay_off; struct timer_list blink_timer; int blink_brightness; + void (*flash_resume)(struct led_classdev *led_cdev); struct work_struct set_brightness_work; int delayed_set_value; -- cgit v1.2.3 From a2a15d54ab2d5c816deea306ae8e9101c40fe300 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 3 Jan 2015 09:51:33 -0800 Subject: device: Fix dev_dbg_once macro There is a copy/paste typo in the dev_dbg_once macro. It uses dev_info instead of dev_dbg, so use the correct function instead. Signed-off-by: Joe Perches Noticed-by: Marc Finet Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index fb506738f7b7..7b2532361398 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1156,7 +1156,7 @@ do { \ #define dev_info_once(dev, fmt, ...) \ dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__) #define dev_dbg_once(dev, fmt, ...) \ - dev_level_once(dev_info, dev, fmt, ##__VA_ARGS__) + dev_level_once(dev_dbg, dev, fmt, ##__VA_ARGS__) #define dev_level_ratelimited(dev_level, dev, fmt, ...) \ do { \ -- cgit v1.2.3 From d1f1052c520452494db548b1a701cd9020b5903e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 25 Dec 2014 15:07:04 -0800 Subject: device: Change dev_ logging functions to return void No caller or macro uses the return value so make all the functions return void. Compiled x86 allyesconfig and defconfig w/o CONFIG_PRINTK Signed-off-by: Joe Perches Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 60 ++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 7b2532361398..0eb8ee2dc6d1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1038,22 +1038,22 @@ extern __printf(3, 4) int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...); extern __printf(3, 4) -int dev_printk(const char *level, const struct device *dev, - const char *fmt, ...); +void dev_printk(const char *level, const struct device *dev, + const char *fmt, ...); extern __printf(2, 3) -int dev_emerg(const struct device *dev, const char *fmt, ...); +void dev_emerg(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int dev_alert(const struct device *dev, const char *fmt, ...); +void dev_alert(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int dev_crit(const struct device *dev, const char *fmt, ...); +void dev_crit(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int dev_err(const struct device *dev, const char *fmt, ...); +void dev_err(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int dev_warn(const struct device *dev, const char *fmt, ...); +void dev_warn(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int dev_notice(const struct device *dev, const char *fmt, ...); +void dev_notice(const struct device *dev, const char *fmt, ...); extern __printf(2, 3) -int _dev_info(const struct device *dev, const char *fmt, ...); +void _dev_info(const struct device *dev, const char *fmt, ...); #else @@ -1065,35 +1065,35 @@ static inline __printf(3, 4) int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) { return 0; } -static inline int __dev_printk(const char *level, const struct device *dev, - struct va_format *vaf) -{ return 0; } +static inline void __dev_printk(const char *level, const struct device *dev, + struct va_format *vaf) +{} static inline __printf(3, 4) -int dev_printk(const char *level, const struct device *dev, - const char *fmt, ...) -{ return 0; } +void dev_printk(const char *level, const struct device *dev, + const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_emerg(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_emerg(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_crit(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_crit(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_alert(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_alert(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_err(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_err(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_warn(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_warn(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int dev_notice(const struct device *dev, const char *fmt, ...) -{ return 0; } +void dev_notice(const struct device *dev, const char *fmt, ...) +{} static inline __printf(2, 3) -int _dev_info(const struct device *dev, const char *fmt, ...) -{ return 0; } +void _dev_info(const struct device *dev, const char *fmt, ...) +{} #endif @@ -1119,7 +1119,6 @@ do { \ ({ \ if (0) \ dev_printk(KERN_DEBUG, dev, format, ##arg); \ - 0; \ }) #endif @@ -1215,7 +1214,6 @@ do { \ ({ \ if (0) \ dev_printk(KERN_DEBUG, dev, format, ##arg); \ - 0; \ }) #endif -- cgit v1.2.3 From 32357605ce7bcd36cb6215a21cad12cd8f51b74e Mon Sep 17 00:00:00 2001 From: Sharon Dvir Date: Thu, 22 Jan 2015 12:15:25 +0200 Subject: USB: Add missing word to comment in mod_devicetable.h The documentation of match_flags in struct usb_device_id said: 'Bit mask controlling of the other fields are used to match against new devices.' Changed to: 'Bit mask controlling which of the other fields are used to match against new devices.' By adding the word 'which' and editing the next lines to not exceed 80 chars. Signed-off-by: Sharon Dvir Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 745def862580..470a240f66a1 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -53,9 +53,9 @@ struct ieee1394_device_id { /** * struct usb_device_id - identifies USB devices for probing and hotplugging - * @match_flags: Bit mask controlling of the other fields are used to match - * against new devices. Any field except for driver_info may be used, - * although some only make sense in conjunction with other fields. + * @match_flags: Bit mask controlling which of the other fields are used to + * match against new devices. Any field except for driver_info may be + * used, although some only make sense in conjunction with other fields. * This is usually set by a USB_DEVICE_*() macro, which sets all * other fields in this structure except for driver_info. * @idVendor: USB vendor ID for a device; numbers are assigned -- cgit v1.2.3 From aae88261abd58fffef7ee0e00160ce4ea105b0f3 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 26 Jan 2015 22:05:38 -0800 Subject: net: phy: document has_fixups field has_fixups was introduced to help keeping track of fixups/quirks running on a PHY device, but we did not update the comment above struct phy_device accordingly. Fixes: b0ae009f3dc14 (net: phy: add "has_fixups" boolean property") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 9c189a1fa3a2..1b3690b597d5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,6 +327,7 @@ struct phy_c45_device_ids { * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. + * has_fixups: Set to true if this phy has fixups/quirks. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * addr: Bus address of PHY -- cgit v1.2.3 From 8a477a6fb6a33651adda772360b85fd813569743 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 26 Jan 2015 22:05:39 -0800 Subject: net: phy: keep track of the PHY suspend state In order to avoid double calls to phydev->drv->suspend and resume, keep track of whether the PHY has already been suspended as a consequence of a successful call to phy_suspend(). We will use this in our MDIO bus suspend/resume hooks to avoid a double suspend call. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1b3690b597d5..685809835b5c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -328,6 +328,7 @@ struct phy_c45_device_ids { * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. * has_fixups: Set to true if this phy has fixups/quirks. + * suspended: Set to true if this phy has been suspended successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * addr: Bus address of PHY @@ -365,6 +366,7 @@ struct phy_device { bool is_c45; bool is_internal; bool has_fixups; + bool suspended; enum phy_state state; -- cgit v1.2.3 From f4c5cf88fbd50e4779042268947b2e2f90c20484 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 18 Dec 2014 15:29:14 +0100 Subject: gpu: host1x: Provide a proper struct bus_type Previously the struct bus_type exported by the host1x infrastructure was only a very basic skeleton. Turn that implementation into a more full- fledged bus to support proper probe ordering and power management. Note that the bus infrastructure needs to be available before any of the drivers can be registered. This is automatically ensured if all drivers are built as loadable modules (via symbol dependencies). If all drivers are built-in there are no such guarantees and the link order determines the initcall ordering. Adjust drivers/gpu/Makefile to make sure that the host1x bus infrastructure is initialized prior to any of its users (only drm/tegra currently). v2: Fix building host1x and tegra-drm as modules Reported-by: Dave Airlie Reviewed-by: Sean Paul Reviewed-by: Mark Zhang Signed-off-by: Thierry Reding --- include/linux/host1x.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 7890b553d12e..464f33814a94 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -250,17 +250,29 @@ void host1x_job_unpin(struct host1x_job *job); struct host1x_device; struct host1x_driver { + struct device_driver driver; + const struct of_device_id *subdevs; struct list_head list; - const char *name; int (*probe)(struct host1x_device *device); int (*remove)(struct host1x_device *device); + void (*shutdown)(struct host1x_device *device); }; -int host1x_driver_register(struct host1x_driver *driver); +static inline struct host1x_driver * +to_host1x_driver(struct device_driver *driver) +{ + return container_of(driver, struct host1x_driver, driver); +} + +int host1x_driver_register_full(struct host1x_driver *driver, + struct module *owner); void host1x_driver_unregister(struct host1x_driver *driver); +#define host1x_driver_register(driver) \ + host1x_driver_register_full(driver, THIS_MODULE) + struct host1x_device { struct host1x_driver *driver; struct list_head list; @@ -273,7 +285,7 @@ struct host1x_device { struct mutex clients_lock; struct list_head clients; - bool bound; + bool registered; }; static inline struct host1x_device *to_host1x_device(struct device *dev) -- cgit v1.2.3 From e9fb8b7e4f6af17e3aa4835281e06fdc920341f9 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 6 Jan 2015 16:48:36 +0000 Subject: compat: Declare compat_sys_sigpending and compat_sys_sigprocmask prototypes __ARCH_WANT_SYS_SIGPENDING or __ARCH_WANT_SYS_SIGPROGMASK may be defined for compat support but the corresponding prototypes are missing from linux/compat.h. Signed-off-by: Catalin Marinas Acked-by: Andrew Morton Cc: Arnd Bergmann --- include/linux/compat.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 7450ca2ac1fc..ab25814690bc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -689,6 +689,15 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); +#ifdef __ARCH_WANT_SYS_SIGPENDING +asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); +#endif + +#ifdef __ARCH_WANT_SYS_SIGPROCMASK +asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, + compat_old_sigset_t __user *oset); +#endif + int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define compat_save_altstack_ex(uss, sp) do { \ -- cgit v1.2.3 From 54e45c169dbce43cf46d00eb1521b655b6e4f9e9 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Tue, 6 Jan 2015 16:52:38 +0000 Subject: syscalls: Declare sys_*stat64 prototypes if __ARCH_WANT_(COMPAT_)STAT64 Currently, the sys_stat64, sys_fstat64 and sys_lstat64 prototpyes are only declared if BITS_PER_LONG == 32. Following commit 0753f70f07fb (fs: Build sys_stat64() and friends if __ARCH_WANT_COMPAT_STAT64), the implementation of these functions is allowed on 64-bit systems for compat support. The patch changes the condition on the prototype declaration from BITS_PER_LONG == 32 to defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64). In addition, it moves the sys_fstatat64 prototype under the same #if block Signed-off-by: Catalin Marinas Acked-by: Andrew Morton Cc: Arnd Bergmann --- include/linux/syscalls.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 85893d744901..76d1e38aabe1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -410,12 +410,16 @@ asmlinkage long sys_newlstat(const char __user *filename, struct stat __user *statbuf); asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); -#if BITS_PER_LONG == 32 +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) asmlinkage long sys_stat64(const char __user *filename, struct stat64 __user *statbuf); asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); asmlinkage long sys_lstat64(const char __user *filename, struct stat64 __user *statbuf); +asmlinkage long sys_fstatat64(int dfd, const char __user *filename, + struct stat64 __user *statbuf, int flag); +#endif +#if BITS_PER_LONG == 32 asmlinkage long sys_truncate64(const char __user *path, loff_t length); asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); #endif @@ -771,8 +775,6 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long sys_newfstatat(int dfd, const char __user *filename, struct stat __user *statbuf, int flag); -asmlinkage long sys_fstatat64(int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag); asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, int bufsiz); asmlinkage long sys_utimensat(int dfd, const char __user *filename, -- cgit v1.2.3 From cfcf1682c4ca8f601a4702255958e0b1c9aa12cc Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sat, 24 Jan 2015 19:52:05 +0200 Subject: cfg80211: Add new GCMP, CCMP-256, BIP-GMAC, BIP-CMAC-256 ciphers This makes cfg80211 aware of the GCMP, GCMP-256, CCMP-256, BIP-GMAC-128, BIP-GMAC-256, and BIP-CMAC-256 cipher suites. These new cipher suites were defined in IEEE Std 802.11ac-2013. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 4f4eea8a6288..dbf417bf25bf 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1994,9 +1994,15 @@ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, WLAN_KEY_LEN_WEP104 = 13, WLAN_KEY_LEN_CCMP = 16, + WLAN_KEY_LEN_CCMP_256 = 32, WLAN_KEY_LEN_TKIP = 32, WLAN_KEY_LEN_AES_CMAC = 16, WLAN_KEY_LEN_SMS4 = 32, + WLAN_KEY_LEN_GCMP = 16, + WLAN_KEY_LEN_GCMP_256 = 32, + WLAN_KEY_LEN_BIP_CMAC_256 = 32, + WLAN_KEY_LEN_BIP_GMAC_128 = 16, + WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; #define IEEE80211_WEP_IV_LEN 4 @@ -2004,9 +2010,16 @@ enum ieee80211_key_len { #define IEEE80211_CCMP_HDR_LEN 8 #define IEEE80211_CCMP_MIC_LEN 8 #define IEEE80211_CCMP_PN_LEN 6 +#define IEEE80211_CCMP_256_HDR_LEN 8 +#define IEEE80211_CCMP_256_MIC_LEN 16 +#define IEEE80211_CCMP_256_PN_LEN 6 #define IEEE80211_TKIP_IV_LEN 8 #define IEEE80211_TKIP_ICV_LEN 4 #define IEEE80211_CMAC_PN_LEN 6 +#define IEEE80211_GMAC_PN_LEN 6 +#define IEEE80211_GCMP_HDR_LEN 8 +#define IEEE80211_GCMP_MIC_LEN 16 +#define IEEE80211_GCMP_PN_LEN 6 /* Public action codes */ enum ieee80211_pub_actioncode { @@ -2230,6 +2243,11 @@ enum ieee80211_sa_query_action { #define WLAN_CIPHER_SUITE_WEP104 0x000FAC05 #define WLAN_CIPHER_SUITE_AES_CMAC 0x000FAC06 #define WLAN_CIPHER_SUITE_GCMP 0x000FAC08 +#define WLAN_CIPHER_SUITE_GCMP_256 0x000FAC09 +#define WLAN_CIPHER_SUITE_CCMP_256 0x000FAC0A +#define WLAN_CIPHER_SUITE_BIP_GMAC_128 0x000FAC0B +#define WLAN_CIPHER_SUITE_BIP_GMAC_256 0x000FAC0C +#define WLAN_CIPHER_SUITE_BIP_CMAC_256 0x000FAC0D #define WLAN_CIPHER_SUITE_SMS4 0x00147201 -- cgit v1.2.3 From 56c52da2d554f081e8fce58ecbcf6a40c605b95b Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sat, 24 Jan 2015 19:52:08 +0200 Subject: mac80111: Add BIP-CMAC-256 cipher This allows mac80211 to configure BIP-CMAC-256 to the driver and also use software-implementation within mac80211 when the driver does not support this with hardware accelaration. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index dbf417bf25bf..b9c7897dc566 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1017,6 +1017,15 @@ struct ieee80211_mmie { u8 mic[8]; } __packed; +/* Management MIC information element (IEEE 802.11w) for GMAC and CMAC-256 */ +struct ieee80211_mmie_16 { + u8 element_id; + u8 length; + __le16 key_id; + u8 sequence_number[6]; + u8 mic[16]; +} __packed; + struct ieee80211_vendor_ie { u8 element_id; u8 len; -- cgit v1.2.3 From 05c80d75f10ad7d3f95444b65788d6a0bbb4380d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 19 Dec 2014 09:14:20 -0300 Subject: [media] hdmi: add new HDMI 2.0 defines Add new Video InfoFrame colorspace information introduced in HDMI 2.0 and new Audio Coding Extension Types, also from HDMI 2.0. HDMI_CONTENT_TYPE_NONE was renamed to _GRAPHICS since that's what it is called in CEA-861-F. Signed-off-by: Hans Verkuil Reviewed-by: Thierry Reding Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index cbb5790a35cd..5afc0bff2bbe 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -52,12 +52,18 @@ enum hdmi_colorspace { HDMI_COLORSPACE_RGB, HDMI_COLORSPACE_YUV422, HDMI_COLORSPACE_YUV444, + HDMI_COLORSPACE_YUV420, + HDMI_COLORSPACE_RESERVED4, + HDMI_COLORSPACE_RESERVED5, + HDMI_COLORSPACE_RESERVED6, + HDMI_COLORSPACE_IDO_DEFINED, }; enum hdmi_scan_mode { HDMI_SCAN_MODE_NONE, HDMI_SCAN_MODE_OVERSCAN, HDMI_SCAN_MODE_UNDERSCAN, + HDMI_SCAN_MODE_RESERVED, }; enum hdmi_colorimetry { @@ -71,6 +77,7 @@ enum hdmi_picture_aspect { HDMI_PICTURE_ASPECT_NONE, HDMI_PICTURE_ASPECT_4_3, HDMI_PICTURE_ASPECT_16_9, + HDMI_PICTURE_ASPECT_RESERVED, }; enum hdmi_active_aspect { @@ -92,12 +99,18 @@ enum hdmi_extended_colorimetry { HDMI_EXTENDED_COLORIMETRY_S_YCC_601, HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, + + /* The following EC values are only defined in CEA-861-F. */ + HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM, + HDMI_EXTENDED_COLORIMETRY_BT2020, + HDMI_EXTENDED_COLORIMETRY_RESERVED, }; enum hdmi_quantization_range { HDMI_QUANTIZATION_RANGE_DEFAULT, HDMI_QUANTIZATION_RANGE_LIMITED, HDMI_QUANTIZATION_RANGE_FULL, + HDMI_QUANTIZATION_RANGE_RESERVED, }; /* non-uniform picture scaling */ @@ -114,7 +127,7 @@ enum hdmi_ycc_quantization_range { }; enum hdmi_content_type { - HDMI_CONTENT_TYPE_NONE, + HDMI_CONTENT_TYPE_GRAPHICS, HDMI_CONTENT_TYPE_PHOTO, HDMI_CONTENT_TYPE_CINEMA, HDMI_CONTENT_TYPE_GAME, @@ -194,6 +207,7 @@ enum hdmi_audio_coding_type { HDMI_AUDIO_CODING_TYPE_MLP, HDMI_AUDIO_CODING_TYPE_DST, HDMI_AUDIO_CODING_TYPE_WMA_PRO, + HDMI_AUDIO_CODING_TYPE_CXT, }; enum hdmi_audio_sample_size { @@ -216,9 +230,23 @@ enum hdmi_audio_sample_frequency { enum hdmi_audio_coding_type_ext { HDMI_AUDIO_CODING_TYPE_EXT_STREAM, + + /* + * The next three CXT values are defined in CEA-861-E only. + * They do not exist in older versions, and in CEA-861-F they are + * defined as 'Not in use'. + */ HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC, HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2, HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND, + + /* The following CXT values are only defined in CEA-861-F. */ + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_V2, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC, + HDMI_AUDIO_CODING_TYPE_EXT_DRA, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_SURROUND, + HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC_SURROUND = 10, }; struct hdmi_audio_infoframe { -- cgit v1.2.3 From 2c676f378edb16cb68f7815581c8119fc43a4b85 Mon Sep 17 00:00:00 2001 From: Martin Bugge Date: Fri, 19 Dec 2014 09:14:21 -0300 Subject: [media] hdmi: added unpack and logging functions for InfoFrames When receiving video it is very useful to be able to unpack the InfoFrames. Logging is useful as well, both for transmitters and receivers. Especially when implementing the VIDIOC_LOG_STATUS ioctl (supported by many V4L2 drivers) for a receiver it is important to be able to easily log what the InfoFrame contains. This greatly simplifies debugging. Signed-off-by: Martin Bugge Signed-off-by: Hans Verkuil Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 5afc0bff2bbe..2ff34315a1bb 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -25,6 +25,7 @@ #define __LINUX_HDMI_H_ #include +#include enum hdmi_infoframe_type { HDMI_INFOFRAME_TYPE_VENDOR = 0x81, @@ -327,5 +328,8 @@ union hdmi_infoframe { ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size); +int hdmi_infoframe_unpack(union hdmi_infoframe *frame, void *buffer); +void hdmi_infoframe_log(const char *level, struct device *dev, + union hdmi_infoframe *frame); #endif /* _DRM_HDMI_H */ -- cgit v1.2.3 From dc189053e1a5ae606c56e432dae1afc28261a819 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 19 Dec 2014 09:14:22 -0300 Subject: [media] hdmi: rename HDMI_AUDIO_CODING_TYPE_EXT_STREAM to _EXT_CT As per the suggestion of Thierry Reding rename HDMI_AUDIO_CODING_TYPE_EXT_STREAM to HDMI_AUDIO_CODING_TYPE_EXT_CT to be consistent with the CEA-861 spec. Signed-off-by: Hans Verkuil Acked-by: Thierry Reding Signed-off-by: Mauro Carvalho Chehab --- include/linux/hdmi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index 2ff34315a1bb..e9744202fa29 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -230,7 +230,8 @@ enum hdmi_audio_sample_frequency { }; enum hdmi_audio_coding_type_ext { - HDMI_AUDIO_CODING_TYPE_EXT_STREAM, + /* Refer to Audio Coding Type (CT) field in Data Byte 1 */ + HDMI_AUDIO_CODING_TYPE_EXT_CT, /* * The next three CXT values are defined in CEA-861-E only. -- cgit v1.2.3 From f27b37f5993a080700ccecdce9960d1563eccd36 Mon Sep 17 00:00:00 2001 From: Bintian Wang Date: Tue, 27 Jan 2015 20:50:29 +0800 Subject: regmap: correct the description of structure element in reg_field Fix incorrect description of structure element "msb", which is described as "reg". Signed-off-by: Bintian Wang Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4419b99d8d6e..116655d92269 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -468,7 +468,7 @@ bool regmap_reg_in_ranges(unsigned int reg, * * @reg: Offset of the register within the regmap bank * @lsb: lsb of the register field. - * @reg: msb of the register field. + * @msb: msb of the register field. * @id_size: port size if it has some ports * @id_offset: address offset for each ports */ -- cgit v1.2.3 From 72c66644673a61ad85d293de7a61e54b9bdc9682 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:07 +0200 Subject: iio: core: Introduce ENERGY channel type Human activity sensors report the energy burnt by the user. One of this devices is Freescale's MMA9553L (http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf) that computes the number of calories based on weight and step rate. Introduce a new channel type ENERGY to export these values. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 904dcbbf0e6f..26b8a1c5e2af 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -32,6 +32,7 @@ enum iio_chan_type { IIO_HUMIDITYRELATIVE, IIO_ACTIVITY, IIO_STEPS, + IIO_ENERGY, }; enum iio_modifier { -- cgit v1.2.3 From cc3c9eecaed65b26ee0661e9e9491fd8d48e3907 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:08 +0200 Subject: iio: core: Introduce DISTANCE channel type Some devices export an estimation of the distance the user has covered since the last reset. One of this devices is Freescale's MMA9553L (http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf) that computes the distance based on the stride length and step rate. Introduce a new channel type DISTANCE to export these values. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 26b8a1c5e2af..a7de445222f4 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -33,6 +33,7 @@ enum iio_chan_type { IIO_ACTIVITY, IIO_STEPS, IIO_ENERGY, + IIO_DISTANCE, }; enum iio_modifier { -- cgit v1.2.3 From 5a1a932981415661827f7edd9e99943a2a3b7b67 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:09 +0200 Subject: iio: core: Introduce IIO_VELOCITY and IIO_MOD_ROOT_SUM_SQUARED_X_Y_Z Some devices export the current speed value of the user. One of this devices is Freescale's MMA9553L (http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf) that computes the speed of the user based on the number of steps and stride length. Introduce a new channel type VELOCITY and a modifier for the magniture or norm of the velocity vector, IIO_MOD_ROOT_SUM_SQUARED_X_Y_Z. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index a7de445222f4..c3601c2c0a9d 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -34,6 +34,7 @@ enum iio_chan_type { IIO_STEPS, IIO_ENERGY, IIO_DISTANCE, + IIO_VELOCITY, }; enum iio_modifier { @@ -68,6 +69,7 @@ enum iio_modifier { IIO_MOD_JOGGING, IIO_MOD_WALKING, IIO_MOD_STILL, + IIO_MOD_ROOT_SUM_SQUARED_X_Y_Z, }; enum iio_event_type { -- cgit v1.2.3 From d37f6836fa285882450e28d1cbc5a9b624911e7e Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:10 +0200 Subject: iio: core: Introduce IIO_CHAN_INFO_CALIBWEIGHT Some devices need the weight of the user to compute other parameters. One of this devices is Freescale's MMA9553L (http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf) that needs the weight of the user to compute the number of calories burnt. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 590202024857..51f16437dacc 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -40,6 +40,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_INT_TIME, IIO_CHAN_INFO_ENABLE, IIO_CHAN_INFO_CALIBHEIGHT, + IIO_CHAN_INFO_CALIBWEIGHT, }; enum iio_shared_by { -- cgit v1.2.3 From 27be84236d75c13a83c45d850390f40b58401d97 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:11 +0200 Subject: iio: core: Introduce CHANGE event type A step detector will generate an interrupt each time N step are detected. A device that has such pedometer functionality is Freescale's MMA9553L: http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf. Introduce IIO_EV_TYPE_CHANGE event type for events that are generated when the channel passes a threshold on the absolute change in value. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index c3601c2c0a9d..3ba3d6678412 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -79,6 +79,7 @@ enum iio_event_type { IIO_EV_TYPE_THRESH_ADAPTIVE, IIO_EV_TYPE_MAG_ADAPTIVE, IIO_EV_TYPE_INSTANCE, + IIO_EV_TYPE_CHANGE, }; enum iio_event_info { -- cgit v1.2.3 From 17a2cbc27981b85a09a48425c2614ae0cb7be8cd Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Sun, 11 Jan 2015 21:10:12 +0200 Subject: iio: core: Remove IIO_EV_TYPE_INSTANCE By introducing IIO_EV_TYPE_CHANGE, IIO_EV_TYPE_INSTANCE becomes redundant. The effect of IIO_EV_TYPE_INSTANCE can be obtained by using IIO_EV_TYPE_CHANGE with IIO_EV_INFO_VALUE set to 1. Remove all instances of IIO_EV_TYPE_INSTANCE and replace them with IIO_EV_TYPE_CHANGE where needed. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 3ba3d6678412..580ed5bdb3fa 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -78,7 +78,6 @@ enum iio_event_type { IIO_EV_TYPE_ROC, IIO_EV_TYPE_THRESH_ADAPTIVE, IIO_EV_TYPE_MAG_ADAPTIVE, - IIO_EV_TYPE_INSTANCE, IIO_EV_TYPE_CHANGE, }; -- cgit v1.2.3 From 15a02c1f6dd7c2bb150c61d00ffb33f584ff2288 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 19 Jan 2015 18:05:28 -0800 Subject: clk: Add __clk_mux_determine_rate_closest Some clock drivers want to find the closest rate on the input of a mux instead of a rate that's less than or equal to the desired rate. Add a generic mux function to support this. Signed-off-by: Stephen Boyd Tested-by: Kenneth Westfield Signed-off-by: Michael Turquette --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index ebb7055a6d84..ba858e90d5de 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -384,6 +384,8 @@ void clk_unregister_divider(struct clk *clk); * register, and mask of mux bits are in higher 16-bit of this register. * While setting the mux bits, higher 16-bit should also be updated to * indicate changing mux bits. + * CLK_MUX_ROUND_CLOSEST - Use the parent rate that is closest to the desired + * frequency. */ struct clk_mux { struct clk_hw hw; @@ -398,7 +400,8 @@ struct clk_mux { #define CLK_MUX_INDEX_ONE BIT(0) #define CLK_MUX_INDEX_BIT BIT(1) #define CLK_MUX_HIWORD_MASK BIT(2) -#define CLK_MUX_READ_ONLY BIT(3) /* mux setting cannot be changed */ +#define CLK_MUX_READ_ONLY BIT(3) /* mux can't be changed */ +#define CLK_MUX_ROUND_CLOSEST BIT(4) extern const struct clk_ops clk_mux_ops; extern const struct clk_ops clk_mux_ro_ops; @@ -556,6 +559,9 @@ struct clk *__clk_lookup(const char *name); long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_p); +long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, + unsigned long *best_parent_rate, + struct clk_hw **best_parent_p); /* * FIXME clock api without lock protection -- cgit v1.2.3 From bca9690b942654f668ffb5124b2bbd0ba0f007bb Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 19 Jan 2015 18:05:29 -0800 Subject: clk: divider: Make generic for usage elsewhere Some devices don't use mmio to interact with dividers. Split out the logic from the register read/write parts so that we can reuse the division logic elsewhere. Signed-off-by: Stephen Boyd Tested-by: Kenneth Westfield Signed-off-by: Michael Turquette --- include/linux/clk-provider.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index ba858e90d5de..0ed5bf2209ad 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -353,6 +353,17 @@ struct clk_divider { #define CLK_DIVIDER_READ_ONLY BIT(5) extern const struct clk_ops clk_divider_ops; + +unsigned long divider_recalc_rate(struct clk_hw *hw, unsigned long parent_rate, + unsigned int val, const struct clk_div_table *table, + unsigned long flags); +long divider_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate, const struct clk_div_table *table, + u8 width, unsigned long flags); +int divider_get_val(unsigned long rate, unsigned long parent_rate, + const struct clk_div_table *table, u8 width, + unsigned long flags); + struct clk *clk_register_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, -- cgit v1.2.3 From e387088a03a07583f248a237cb00c5c955a394c9 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 22 Jan 2015 15:40:20 -0800 Subject: clk: ti: Drop use of clk-private.h These modules don't need to include clk-private.h. Replace the include with clk.h because these modules are clock consumers and also include clk-provider.h in clk/ti.h because struct clk_hw_omap has a struct clk_hw embedded in it. Cc: Tero Kristo Cc: Tony Lindgren Signed-off-by: Stephen Boyd Reviewed-by: Paul Walmsley Signed-off-by: Michael Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 55ef529a0dbf..172d13fd8bea 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -15,6 +15,7 @@ #ifndef __LINUX_CLK_TI_H__ #define __LINUX_CLK_TI_H__ +#include #include /** -- cgit v1.2.3 From 2130fb97fecf9a51bb4a21da220cff3f72496a94 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Tue, 27 Jan 2015 01:18:19 +0100 Subject: NFC: st21nfca: Adding support for secure element st21nfca has 1 physical SWP line and can support up to 2 secure elements (UICC & eSE) thanks to an external switch managed with a gpio. The platform integrator needs to specify thanks to 2 initialization properties, uicc-present and ese-present, if it is suppose to have uicc and/or ese. Of course if the platform does not have an external switch, only one kind of secure element can be supported. Those parameters are under platform integrator responsibilities. During initialization, the white_list will be set according to those parameters. The discovery_se function will assume a secure element is physically present according to uicc-present and ese-present values and will add it to the secure element list. On ese activation, the atr is retrieved to calculate a command exchange timeout based on the first atr(TB) value. The se_io will allow to transfer data over SWP. 2 kind of events may appear after a data is sent over: - ST21NFCA_EVT_TRANSMIT_DATA when receiving an apdu answer - ST21NFCA_EVT_WTX_REQUEST when the secure element needs more time than expected to compute a command. If this timeout expired, a first recovery tentative consist to send a simple software reset proprietary command. If this tentative still fail, a second recovery tentative consist to send a hardware reset proprietary command. This function is only relevant for eSE like secure element. This patch also change the way a pipe is referenced. There can be different pipe connected to the same gate with different host destination (ex: CONNECTIVITY). In order to keep host information every pipe are reference with a tuple (gate, host). In order to reduce changes, we are keeping unchanged the way a gate is addressed on the Terminal Host. However, this is working because we consider the apdu reader gate is only present on the eSE slot also the connectivity gate cannot give a reliable value; it will give the latest stored pipe value. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/st21nfca.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h index 5087fff96d86..cc2bdafb0c69 100644 --- a/include/linux/platform_data/st21nfca.h +++ b/include/linux/platform_data/st21nfca.h @@ -26,6 +26,8 @@ struct st21nfca_nfc_platform_data { unsigned int gpio_ena; unsigned int irq_polarity; + bool is_ese_present; + bool is_uicc_present; }; #endif /* _ST21NFCA_HCI_H_ */ -- cgit v1.2.3 From be6a6b43b597a37d96dbf74985f72045ccef0940 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 27 Jan 2015 15:57:59 +0200 Subject: net/mlx4_core: Add bad-cable event support If the firmware can detect a bad cable, allow it to generate an event, and print the problem in the log. Signed-off-by: Jack Morgenstein Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 5ef54e145e4d..c95d659a39f2 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -200,7 +200,8 @@ enum { MLX4_DEV_CAP_FLAG2_CONFIG_DEV = 1LL << 16, MLX4_DEV_CAP_FLAG2_SYS_EQS = 1LL << 17, MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18, - MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19 + MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19, + MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20 }; enum { @@ -280,6 +281,7 @@ enum mlx4_event { MLX4_EVENT_TYPE_FATAL_WARNING = 0x1b, MLX4_EVENT_TYPE_FLR_EVENT = 0x1c, MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d, + MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT = 0x3e, MLX4_EVENT_TYPE_NONE = 0xff, }; @@ -288,6 +290,11 @@ enum { MLX4_PORT_CHANGE_SUBTYPE_ACTIVE = 4 }; +enum { + MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_BAD_CABLE = 1, + MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_UNSUPPORTED_CABLE = 2, +}; + enum { MLX4_FATAL_WARNING_SUBTYPE_WARMING = 0, }; @@ -860,6 +867,11 @@ struct mlx4_eqe { } __packed tbl_change_info; } params; } __packed port_mgmt_change; + struct { + u8 reserved[3]; + u8 port; + u32 reserved1[5]; + } __packed bad_cable; } event; u8 slave_id; u8 reserved3[2]; -- cgit v1.2.3 From 5a03108689c6f3e448a920b42af04e6d28401f80 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Tue, 27 Jan 2015 15:58:02 +0200 Subject: net/mlx4_core: Adjust command timeouts to conform to the firmware spec The firmware spec states that the timeout for all commands should be 60 seconds. In the past, the spec indicated that there were several classes of timeout (short, medium, and long). The driver has these different timeout classes. We leave the class differentiation in the driver as-is (to protect against any future spec changes), but set the timeout for all classes to be 60 seconds. In addition, we fix a few commands which had hard-coded numeric timeouts specified. Signed-off-by: Jack Morgenstein Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index c989442ffc6a..ae95adc78509 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -165,9 +165,9 @@ enum { }; enum { - MLX4_CMD_TIME_CLASS_A = 10000, - MLX4_CMD_TIME_CLASS_B = 10000, - MLX4_CMD_TIME_CLASS_C = 10000, + MLX4_CMD_TIME_CLASS_A = 60000, + MLX4_CMD_TIME_CLASS_B = 60000, + MLX4_CMD_TIME_CLASS_C = 60000, }; enum { -- cgit v1.2.3 From 3aa8793f751d4cfcaca886e75ab30dfb00cf1d88 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 28 Nov 2014 14:38:36 +0100 Subject: mmc: core: Initial support for MMC power sequences System on chip designs may specify a specific MMC power sequence. To successfully detect an (e)MMC/SD/SDIO card, that power sequence must be followed while initializing the card. To be able to handle these SOC specific power sequences, let's add a MMC power sequence interface. It provides the following functions to help the mmc core to deal with these power sequences. mmc_pwrseq_alloc() - Invoked from mmc_of_parse(), to initialize data. mmc_pwrseq_pre_power_on()- Invoked in the beginning of mmc_power_up(). mmc_pwrseq_post_power_on()- Invoked at the end in mmc_power_up(). mmc_pwrseq_power_off()- Invoked from mmc_power_off(). mmc_pwrseq_free() - Invoked from mmc_free_host(), to free data. Each MMC power sequence provider will be responsible to implement a set of callbacks. These callbacks mirrors the functions above. This patch adds the skeleton, following patches will extend the core of the MMC power sequence and add support for a specific simple MMC power sequence. Do note, since the mmc_pwrseq_alloc() is invoked from mmc_of_parse(), host drivers needs to make use of this API to enable the support for MMC power sequences. Moreover the MMC power sequence support depends on CONFIG_OF. Signed-off-by: Ulf Hansson Tested-by: Javier Martinez Canillas Reviewed-by: Javier Martinez Canillas --- include/linux/mmc/host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index b6bf718c3498..0c8cbe5d1550 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -195,6 +195,7 @@ struct mmc_context_info { }; struct regulator; +struct mmc_pwrseq; struct mmc_supply { struct regulator *vmmc; /* Card power supply */ @@ -206,6 +207,7 @@ struct mmc_host { struct device class_dev; int index; const struct mmc_host_ops *ops; + struct mmc_pwrseq *pwrseq; unsigned int f_min; unsigned int f_max; unsigned int f_init; -- cgit v1.2.3 From 667a0a06c99d5291433b869ed35dabdd95ba1453 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 18 Dec 2014 14:48:15 +0000 Subject: mm: provide a find_special_page vma operation The optional find_special_page VMA operation is used to lookup the pages backing a VMA. This is useful in cases where the normal mechanisms for finding the page don't work. This is only called if the PTE is special. One use case is a Xen PV guest mapping foreign pages into userspace. In a Xen PV guest, the PTEs contain MFNs so get_user_pages() (for example) must do an MFN to PFN (M2P) lookup before it can get the page. For foreign pages (those owned by another guest) the M2P lookup returns the PFN as seen by the foreign guest (which would be completely the wrong page for the local guest). This cannot be fixed up improving the M2P lookup since one MFN may be mapped onto two or more pages so getting the right page is impossible given just the MFN. Signed-off-by: David Vrabel Acked-by: Andrew Morton --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80fc92a49649..9269af7349fe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -290,6 +290,14 @@ struct vm_operations_struct { /* called by sys_remap_file_pages() to populate non-linear mapping */ int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff); + + /* + * Called by vm_normal_page() for special PTEs to find the + * page for @addr. This is useful if the default behavior + * (using pte_page()) would not find the correct page. + */ + struct page *(*find_special_page)(struct vm_area_struct *vma, + unsigned long addr); }; struct mmu_gather; -- cgit v1.2.3 From d8ac3dd41aea245f65465449efc35dd3ac71e91d Mon Sep 17 00:00:00 2001 From: Jennifer Herbert Date: Mon, 5 Jan 2015 13:24:09 +0000 Subject: mm: add 'foreign' alias for the 'pinned' page flag The foreign page flag will be used by Xen guests to mark pages that have grant mappings of frames from other (foreign) guests. The foreign flag is an alias for the existing (Xen-specific) pinned flag. This is safe because pinned is only used on pages used for page tables and these cannot also be foreign. Signed-off-by: Jennifer Herbert Acked-by: Andrew Morton Signed-off-by: David Vrabel --- include/linux/page-flags.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e1f5fcd79792..5ed7bdaf22d5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -121,8 +121,12 @@ enum pageflags { PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ + /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, + /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, + /* Has a grant mapping of another (foreign) domain's page. */ + PG_foreign = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, @@ -215,6 +219,7 @@ __PAGEFLAG(Slab, slab) PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ PAGEFLAG(SavePinned, savepinned); /* Xen */ +PAGEFLAG(Foreign, foreign); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __SETPAGEFLAG(SwapBacked, swapbacked) -- cgit v1.2.3 From fafdd2bf2638157670f28462b641150d16dbaeca Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Mon, 24 Nov 2014 22:30:09 +0100 Subject: UBI: Implement UBI_METAONLY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UBI_METAONLY is a new open mode for UBI volumes, it indicates that only meta data is being changed. Meta data in terms of UBI volumes means data which is stored in the UBI volume table but not on the volume itself. While it does not interfere with UBI_READONLY and UBI_READWRITE it is not allowed to use UBI_METAONLY together with UBI_EXCLUSIVE. Cc: Ezequiel Garcia Cc: Andrew Murray Signed-off-by: Richard Weinberger Tested-by: Guido Martínez Reviewed-by: Guido Martínez Tested-by: Christoph Fritz Tested-by: Andrew Murray --- include/linux/mtd/ubi.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index c3918a0684fe..8fa2753316e8 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -34,11 +34,14 @@ * UBI_READONLY: read-only mode * UBI_READWRITE: read-write mode * UBI_EXCLUSIVE: exclusive mode + * UBI_METAONLY: modify only the volume meta-data, + * i.e. the data stored in the volume table, but not in any of volume LEBs. */ enum { UBI_READONLY = 1, UBI_READWRITE, - UBI_EXCLUSIVE + UBI_EXCLUSIVE, + UBI_METAONLY }; /** -- cgit v1.2.3 From 9ff08979e17423f0f691c1d76f35dfec72a5e459 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Sat, 10 Jan 2015 22:52:13 +0100 Subject: UBI: Add initial support for scatter gather Adds a new set of functions to deal with scatter gather. ubi_eba_read_leb_sg() will read from a LEB into a scatter gather list. The new data structure struct ubi_sgl will be used within UBI to hold the scatter gather list itself and metadata to have a cursor within the list. Signed-off-by: Richard Weinberger Tested-by: Ezequiel Garcia Reviewed-by: Ezequiel Garcia --- include/linux/mtd/ubi.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 8fa2753316e8..1e271cb559cd 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -23,11 +23,18 @@ #include #include +#include #include /* All voumes/LEBs */ #define UBI_ALL -1 +/* + * Maximum number of scatter gather list entries, + * we use only 64 to have a lower memory foot print. + */ +#define UBI_MAX_SG_COUNT 64 + /* * enum ubi_open_mode - UBI volume open mode constants. * @@ -118,6 +125,35 @@ struct ubi_volume_info { dev_t cdev; }; +/** + * struct ubi_sgl - UBI scatter gather list data structure. + * @list_pos: current position in @sg[] + * @page_pos: current position in @sg[@list_pos] + * @sg: the scatter gather list itself + * + * ubi_sgl is a wrapper around a scatter list which keeps track of the + * current position in the list and the current list item such that + * it can be used across multiple ubi_leb_read_sg() calls. + */ +struct ubi_sgl { + int list_pos; + int page_pos; + struct scatterlist sg[UBI_MAX_SG_COUNT]; +}; + +/** + * ubi_sgl_init - initialize an UBI scatter gather list data structure. + * @usgl: the UBI scatter gather struct itself + * + * Please note that you still have to use sg_init_table() or any adequate + * function to initialize the unterlaying struct scatterlist. + */ +static inline void ubi_sgl_init(struct ubi_sgl *usgl) +{ + usgl->list_pos = 0; + usgl->page_pos = 0; +} + /** * struct ubi_device_info - UBI device description data structure. * @ubi_num: ubi device number @@ -213,6 +249,8 @@ int ubi_unregister_volume_notifier(struct notifier_block *nb); void ubi_close_volume(struct ubi_volume_desc *desc); int ubi_leb_read(struct ubi_volume_desc *desc, int lnum, char *buf, int offset, int len, int check); +int ubi_leb_read_sg(struct ubi_volume_desc *desc, int lnum, struct ubi_sgl *sgl, + int offset, int len, int check); int ubi_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf, int offset, int len); int ubi_leb_change(struct ubi_volume_desc *desc, int lnum, const void *buf, @@ -233,4 +271,14 @@ static inline int ubi_read(struct ubi_volume_desc *desc, int lnum, char *buf, { return ubi_leb_read(desc, lnum, buf, offset, len, 0); } + +/* + * This function is the same as the 'ubi_leb_read_sg()' function, but it does + * not provide the checking capability. + */ +static inline int ubi_read_sg(struct ubi_volume_desc *desc, int lnum, + struct ubi_sgl *sgl, int offset, int len) +{ + return ubi_leb_read_sg(desc, lnum, sgl, offset, len, 0); +} #endif /* !__LINUX_UBI_H__ */ -- cgit v1.2.3 From 6ea22486ba46bcb665de36514094d74575cd1330 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Wed, 28 Jan 2015 12:48:53 +0000 Subject: tracing: Add array printing helper If a trace event contains an array, there is currently no standard way to format this for text output. Drivers are currently hacking around this by a) local hacks that use the trace_seq functionailty directly, or b) just not printing that information. For fixed size arrays, formatting of the elements can be open-coded, but this gets cumbersome for arrays of non-trivial size. These approaches result in non-standard content of the event format description delivered to userspace, so userland tools needs to be taught to understand and parse each array printing method individually. This patch implements a __print_array() helper that tracepoint implementations can use instead of reinventing it. A simple C-style syntax is used to delimit the array and its elements {like,this}. So that the helpers can be used with large static arrays as well as dynamic arrays, they take a pointer and element count: they can be used with __get_dynamic_array() for use with dynamic arrays. Link: http://lkml.kernel.org/r/1422449335-8289-2-git-send-email-javi.merino@arm.com Cc: Ingo Molnar Signed-off-by: Dave Martin Signed-off-by: Javi Merino Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 0bebb5c348b8..5aa4a9269547 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -44,6 +44,10 @@ const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, const char *ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int len); +const char *ftrace_print_array_seq(struct trace_seq *p, + const void *buf, int buf_len, + size_t el_size); + struct trace_iterator; struct trace_event; -- cgit v1.2.3 From ad9cf3bbd18a94806314741ac8092c3422f5aebe Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 16 Dec 2014 12:54:25 -0500 Subject: block: mark blk-mq devices as stackable Commit 4ee5eaf4 ("block: add a queue flag for request stacking support") introduced the concept of "STACKABLE" and blk-mq devices fit the definition in that they establish q->request_fn. So establish QUEUE_FLAG_STACKABLE in QUEUE_FLAG_MQ_DEFAULT. While not strictly needed (DM _could_ just check for q->mq_ops to assume the device is request-based), request-based DM support for blk-mq devices benefits from the ability to consistently check for QUEUE_FLAG_STACKABLE before allowing a device to be stacked into a request-based DM table. Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6f388fd1c11c..13e16401a7ce 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -520,6 +520,7 @@ struct request_queue { (1 << QUEUE_FLAG_ADD_RANDOM)) #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ + (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP)) static inline void queue_lockdep_assert_held(struct request_queue *q) -- cgit v1.2.3 From 8c7dd8bce05345ca5fe249b64782e8feeb3b9259 Mon Sep 17 00:00:00 2001 From: James Ban Date: Wed, 28 Jan 2015 09:28:08 +0900 Subject: regulator: da9211: Add gpio control for enable/disable of buck This is a patch for adding gpio control about enable/disable of buck. Signed-off-by: James Ban Signed-off-by: Mark Brown --- include/linux/regulator/da9211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index d1d9d3849bdb..5dd65acc2a69 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -32,6 +32,7 @@ struct da9211_pdata { * 2 : 2 phase 2 buck */ int num_buck; + int gpio_ren[DA9211_MAX_REGULATORS]; struct device_node *reg_node[DA9211_MAX_REGULATORS]; struct regulator_init_data *init_data[DA9211_MAX_REGULATORS]; }; -- cgit v1.2.3 From af0f349b2996f9f3d83e5aac1edf58fff727a0e0 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 23 Jan 2015 12:03:29 +0100 Subject: clk: Remove __clk_register As it has never been used. Signed-off-by: Tomeu Vizoso Reviewed-by: Stephen Boyd Signed-off-by: Michael Turquette --- include/linux/clk-private.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h index 0ca5f6046920..c5f40d07686c 100644 --- a/include/linux/clk-private.h +++ b/include/linux/clk-private.h @@ -214,7 +214,5 @@ struct clk { */ int __clk_init(struct device *dev, struct clk *clk); -struct clk *__clk_register(struct device *dev, struct clk_hw *hw); - #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PRIVATE_H */ -- cgit v1.2.3 From 018d5ef2048fcab339467bcbebccf588c9bd2531 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 29 Jan 2015 08:30:29 +0900 Subject: ata: ahci_platform: fix owner module reference mismatch for scsi host The owner module reference of the ahci platform's scsi_host is initialized to libahci_platform's one, because these drivers use a scsi_host_template defined in libahci_platform. So these drivers can be unloaded even if the scsi device is being accessed. This fixes it by pushing the scsi_host_template from libahci_platform to all leaf drivers. The scsi_host_template is passed through a new argument of ahci_platform_init_host(). Signed-off-by: Akinobu Mita Signed-off-by: Tejun Heo Cc: Hans de Goede Cc: Christoph Hellwig Cc: "James E.J. Bottomley" Cc: linux-ide@vger.kernel.org Cc: linux-scsi@vger.kernel.org --- include/linux/ahci_platform.h | 4 +++- include/linux/libata.h | 6 ++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index f65b33809170..a270f25ee7c7 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -21,6 +21,7 @@ struct device; struct ata_port_info; struct ahci_host_priv; struct platform_device; +struct scsi_host_template; int ahci_platform_enable_clks(struct ahci_host_priv *hpriv); void ahci_platform_disable_clks(struct ahci_host_priv *hpriv); @@ -32,7 +33,8 @@ struct ahci_host_priv *ahci_platform_get_resources( struct platform_device *pdev); int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template); + const struct ata_port_info *pi_template, + struct scsi_host_template *sht); int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); diff --git a/include/linux/libata.h b/include/linux/libata.h index 2d182413b1db..11beb4196c32 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1338,6 +1338,12 @@ extern const struct ata_port_operations ata_base_port_ops; extern const struct ata_port_operations sata_port_ops; extern struct device_attribute *ata_common_sdev_attrs[]; +/* + * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated + * by the edge drivers. Because the 'module' field of sht must be the + * edge driver's module reference, otherwise the driver can be unloaded + * even if the scsi_device is being accessed. + */ #define ATA_BASE_SHT(drv_name) \ .module = THIS_MODULE, \ .name = drv_name, \ -- cgit v1.2.3 From 17263905399471016cda6c1975044d14291c5ba5 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 29 Jan 2015 08:30:30 +0900 Subject: ata: pata_platform: fix owner module reference mismatch for scsi host The owner module reference of the pata_of_platform's scsi_host is initialized to pata_platform's one, because pata_of_platform driver use a scsi_host_template defined in pata_platform. So this drivers can be unloaded even if the scsi device is being accessed. This fixes it by propagating the scsi_host_template to pata_of_platform driver. The scsi_host_template is passed through a new argument of __pata_platform_probe(). Signed-off-by: Akinobu Mita Signed-off-by: Tejun Heo Cc: Hans de Goede Cc: Christoph Hellwig Cc: "James E.J. Bottomley" Cc: linux-ide@vger.kernel.org Cc: linux-scsi@vger.kernel.org --- include/linux/ata_platform.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h index 5c618a084225..619d9e78e644 100644 --- a/include/linux/ata_platform.h +++ b/include/linux/ata_platform.h @@ -10,12 +10,15 @@ struct pata_platform_info { unsigned int ioport_shift; }; +struct scsi_host_template; + extern int __pata_platform_probe(struct device *dev, struct resource *io_res, struct resource *ctl_res, struct resource *irq_res, unsigned int ioport_shift, - int __pio_mask); + int __pio_mask, + struct scsi_host_template *sht); /* * Marvell SATA private data -- cgit v1.2.3 From 05afcb77eb4713f46e7ebaa3cb54bc465c5d516e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 23 Jan 2015 01:08:07 -0500 Subject: new helper: iov_iter_bvec() similar to iov_iter_kvec(), for ITER_BVEC ones Signed-off-by: Al Viro --- include/linux/uio.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1c5e453f7ea9..b447402d9737 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -88,7 +88,9 @@ size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *iov, +void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, + unsigned long nr_segs, size_t count); +void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -- cgit v1.2.3 From dbe4e192a234cd6133d86fffb965d0f032c12ccc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 25 Jan 2015 21:11:59 +0100 Subject: fs: add vfs_iter_{read,write} helpers Simple helpers that pass an arbitrary iov_iter to filesystems. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..1f3c43952540 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2494,6 +2494,9 @@ extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t l extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos); +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos); + /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); -- cgit v1.2.3 From 61f552141c9c0e88b3fdc7046265781ffd8fa68a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 18 Jan 2015 16:45:42 +0100 Subject: ftrace: let notrace function attribute disable hotpatching if necessary gcc supports an s390 specific function attribute called "hotpatch". It can be used to specify the number of halfwords that shall be added before and after a function and which shall be filled with nops for runtime patching. s390 will use the hotpatch attribute for function tracing, therefore make sure that the notrace function attribute either disables the mcount call or in case of hotpatch nop generation. Acked-by: Steven Rostedt Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- include/linux/compiler.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index d5ad7b1118fc..1ef679f4b88e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -54,7 +54,11 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif +#ifdef CC_USING_HOTPATCH +#define notrace __attribute__((hotpatch(0,0))) +#else #define notrace __attribute__((no_instrument_function)) +#endif /* Intel compiler defines __GNUC__. So we will overwrite implementations * coming from above header files here -- cgit v1.2.3 From 3c313161353ad527de1a6ecde0f0d41700858fd6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sat, 24 Jan 2015 18:47:20 +0100 Subject: bcma: detect SPROM revision 11 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extracting values from it is still unsupported, but at least we'll display some meaningful error now. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/ssb/ssb_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index f7b9100686c3..c0f707ac192b 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -173,6 +173,7 @@ #define SSB_SPROMSIZE_BYTES_R123 (SSB_SPROMSIZE_WORDS_R123 * sizeof(u16)) #define SSB_SPROMSIZE_BYTES_R4 (SSB_SPROMSIZE_WORDS_R4 * sizeof(u16)) #define SSB_SPROMSIZE_WORDS_R10 230 +#define SSB_SPROMSIZE_WORDS_R11 234 #define SSB_SPROM_BASE1 0x1000 #define SSB_SPROM_BASE31 0x0800 #define SSB_SPROM_REVISION 0x007E -- cgit v1.2.3 From b504075f5903b969a54ef3a6ae994c0872edb259 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 25 Jan 2015 11:11:14 +0100 Subject: bcma: add early_init function for PCIe core and move some fix into it MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are some PCIe core fixes that need to be applied before accessing SPROM, otherwise reading it may fail. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h index 0333e605ea0d..3f809ae372c4 100644 --- a/include/linux/bcma/bcma_driver_pci.h +++ b/include/linux/bcma/bcma_driver_pci.h @@ -223,6 +223,7 @@ struct bcma_drv_pci_host { struct bcma_drv_pci { struct bcma_device *core; + u8 early_setup_done:1; u8 setup_done:1; u8 hostmode:1; @@ -237,6 +238,7 @@ struct bcma_drv_pci { #define pcicore_write16(pc, offset, val) bcma_write16((pc)->core, offset, val) #define pcicore_write32(pc, offset, val) bcma_write32((pc)->core, offset, val) +extern void bcma_core_pci_early_init(struct bcma_drv_pci *pc); extern void bcma_core_pci_init(struct bcma_drv_pci *pc); extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable); -- cgit v1.2.3 From 8be08a39d498d5d93ff5149276e34ccb4ec3757f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 25 Jan 2015 13:41:19 +0100 Subject: bcma: implement host code support for PCIe Gen 2 devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is stil incomplete, so we don't add PCI IDs of new devices yet. Purpose of this patch is to allow testing & adjusting rest of the code. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma.h | 1 + include/linux/bcma/bcma_regs.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index eb1c6a47b67f..994739da827f 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -318,6 +318,7 @@ struct bcma_bus { const struct bcma_host_ops *ops; enum bcma_hosttype hosttype; + bool host_is_pcie2; /* Used for BCMA_HOSTTYPE_PCI only */ union { /* Pointer to the PCI bus (only for BCMA_HOSTTYPE_PCI) */ struct pci_dev *host_pci; diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h index e64ae7bf80a1..ebd5c1fcdea4 100644 --- a/include/linux/bcma/bcma_regs.h +++ b/include/linux/bcma/bcma_regs.h @@ -64,6 +64,8 @@ #define BCMA_PCI_GPIO_XTAL 0x40 /* PCI config space GPIO 14 for Xtal powerup */ #define BCMA_PCI_GPIO_PLL 0x80 /* PCI config space GPIO 15 for PLL powerdown */ +#define BCMA_PCIE2_BAR0_WIN2 0x70 + /* SiliconBackplane Address Map. * All regions may not exist on all chips. */ -- cgit v1.2.3 From 0501be6429e4eb02f417ad83eacd84b8c57b0283 Mon Sep 17 00:00:00 2001 From: Alexey Skidanov Date: Thu, 29 Jan 2015 10:49:43 +0200 Subject: mmc: Resolve BKOPS compatability issue This patch is coming to fix compatibility issue of BKOPS_EN field of EXT_CSD. In eMMC-5.1, BKOPS_EN was changed, and now it has two operational bits: Bit 0 - MANUAL_EN Bit 1 - AUTO_EN In previous eMMC revisions, only Bit 0 was supported. Signed-off-by: Alexey Skidanov Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 2 +- include/linux/mmc/mmc.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 4d69c00497bd..a6cf4c063e4e 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -83,7 +83,7 @@ struct mmc_ext_csd { bool hpi; /* HPI support bit */ unsigned int hpi_cmd; /* cmd used as HPI */ bool bkops; /* background support bit */ - bool bkops_en; /* background enable bit */ + bool man_bkops_en; /* manual bkops enable bit */ unsigned int data_sector_size; /* 512 bytes or 4KB */ unsigned int data_tag_unit_size; /* DATA TAG UNIT size */ unsigned int boot_ro_lock; /* ro lock support */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index fb97b5cc91cd..124f562118b8 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -427,6 +427,11 @@ struct _mmc_csd { */ #define EXT_CSD_BKOPS_LEVEL_2 0x2 +/* + * BKOPS modes + */ +#define EXT_CSD_MANUAL_BKOPS_MASK 0x01 + /* * MMC_SWITCH access modes */ -- cgit v1.2.3 From 3b0f1d01e501792d8d89ab4371bc9e8cd2a10032 Mon Sep 17 00:00:00 2001 From: Kai Huang Date: Wed, 28 Jan 2015 10:54:23 +0800 Subject: KVM: Rename kvm_arch_mmu_write_protect_pt_masked to be more generic for log dirty We don't have to write protect guest memory for dirty logging if architecture supports hardware dirty logging, such as PML on VMX, so rename it to be more generic. Signed-off-by: Kai Huang Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7d6719522f1f..32d057571bf6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -615,7 +615,7 @@ int kvm_get_dirty_log(struct kvm *kvm, int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log, bool *is_dirty); -void kvm_arch_mmu_write_protect_pt_masked(struct kvm *kvm, +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); -- cgit v1.2.3 From 80b2502cea34a965a6b3390691854e753945ca5f Mon Sep 17 00:00:00 2001 From: Peter Chen Date: Wed, 28 Jan 2015 16:32:24 +0800 Subject: usb: gadget: introduce is_selfpowered for usb_gadget Whether the gadget is selfpowerwed or not can be determined by composite core, so we can use a common entry to indicate if the self-powered is supported by gadget, and the related private variable at individual udc driver can be deleted. Signed-off-by: Peter Chen Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 70ddb3943b62..e2f00fd8cd47 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -523,6 +523,7 @@ struct usb_gadget_ops { * enabled HNP support. * @quirk_ep_out_aligned_size: epout requires buffer size to be aligned to * MaxPacketSize. + * @is_selfpowered: if the gadget is self-powered. * * Gadgets have a mostly-portable "gadget driver" implementing device * functions, handling all usb configurations and interfaces. Gadget @@ -563,6 +564,7 @@ struct usb_gadget { unsigned a_hnp_support:1; unsigned a_alt_hnp_support:1; unsigned quirk_ep_out_aligned_size:1; + unsigned is_selfpowered:1; }; #define work_to_gadget(w) (container_of((w), struct usb_gadget, work)) -- cgit v1.2.3 From ac3dd5bd128b1d1ce2a037775766f39d06a4848a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Jan 2015 12:07:58 -0700 Subject: NVMe: avoid kmalloc/kfree for smaller IO Currently we allocate an nvme_iod for each IO, which holds the sg list, prps, and other IO related info. Set a threshold of 2 pages and/or 8KB of data, below which we can just embed this in the per-command pdu in blk-mq. For any IO at or below NVME_INT_PAGES and NVME_INT_BYTES, we save a kmalloc and kfree. For higher IOPS, this saves up to 1% of CPU time. Signed-off-by: Jens Axboe Reviewed-by: Keith Busch --- include/linux/nvme.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 258945fcabf1..19a5d4b23209 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -132,13 +132,12 @@ struct nvme_ns { * allocated to store the PRP list. */ struct nvme_iod { - void *private; /* For the use of the submitter of the I/O */ + unsigned long private; /* For the use of the submitter of the I/O */ int npages; /* In the PRP list. 0 means small pool in use */ int offset; /* Of PRP list */ int nents; /* Used in scatterlist */ int length; /* Of data, in bytes */ dma_addr_t first_dma; - struct list_head node; struct scatterlist sg[0]; }; -- cgit v1.2.3 From 50dd64d57eee8aed1a86e875ce77d078e44fad00 Mon Sep 17 00:00:00 2001 From: Karol Wrona Date: Wed, 28 Jan 2015 15:05:50 +0100 Subject: iio: common: ssp_sensors: Add sensorhub driver Sensorhub is MCU dedicated to collect data and manage several sensors. Sensorhub is a spi device which provides a layer for IIO devices. It provides some data parsing and common mechanism for sensorhub sensors. Adds common sensorhub library for sensorhub driver and iio drivers which uses sensorhub MCU to communicate with sensors. Signed-off-by: Karol Wrona Acked-by: Kyungmin Park Signed-off-by: Jonathan Cameron --- include/linux/iio/common/ssp_sensors.h | 82 ++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 include/linux/iio/common/ssp_sensors.h (limited to 'include/linux') diff --git a/include/linux/iio/common/ssp_sensors.h b/include/linux/iio/common/ssp_sensors.h new file mode 100644 index 000000000000..f4d1b0edb432 --- /dev/null +++ b/include/linux/iio/common/ssp_sensors.h @@ -0,0 +1,82 @@ +/* + * Copyright (C) 2014, Samsung Electronics Co. Ltd. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#ifndef _SSP_SENSORS_H_ +#define _SSP_SENSORS_H_ + +#include + +#define SSP_TIME_SIZE 4 +#define SSP_ACCELEROMETER_SIZE 6 +#define SSP_GYROSCOPE_SIZE 6 +#define SSP_BIO_HRM_RAW_SIZE 8 +#define SSP_BIO_HRM_RAW_FAC_SIZE 36 +#define SSP_BIO_HRM_LIB_SIZE 8 + +/** + * enum ssp_sensor_type - SSP sensor type + */ +enum ssp_sensor_type { + SSP_ACCELEROMETER_SENSOR = 0, + SSP_GYROSCOPE_SENSOR, + SSP_GEOMAGNETIC_UNCALIB_SENSOR, + SSP_GEOMAGNETIC_RAW, + SSP_GEOMAGNETIC_SENSOR, + SSP_PRESSURE_SENSOR, + SSP_GESTURE_SENSOR, + SSP_PROXIMITY_SENSOR, + SSP_TEMPERATURE_HUMIDITY_SENSOR, + SSP_LIGHT_SENSOR, + SSP_PROXIMITY_RAW, + SSP_ORIENTATION_SENSOR, + SSP_STEP_DETECTOR, + SSP_SIG_MOTION_SENSOR, + SSP_GYRO_UNCALIB_SENSOR, + SSP_GAME_ROTATION_VECTOR, + SSP_ROTATION_VECTOR, + SSP_STEP_COUNTER, + SSP_BIO_HRM_RAW, + SSP_BIO_HRM_RAW_FAC, + SSP_BIO_HRM_LIB, + SSP_SENSOR_MAX, +}; + +struct ssp_data; + +/** + * struct ssp_sensor_data - Sensor object + * @process_data: Callback to feed sensor data. + * @type: Used sensor type. + * @buffer: Received data buffer. + */ +struct ssp_sensor_data { + int (*process_data)(struct iio_dev *indio_dev, void *buf, + int64_t timestamp); + enum ssp_sensor_type type; + u8 *buffer; +}; + +void ssp_register_consumer(struct iio_dev *indio_dev, + enum ssp_sensor_type type); + +int ssp_enable_sensor(struct ssp_data *data, enum ssp_sensor_type type, + u32 delay); + +int ssp_disable_sensor(struct ssp_data *data, enum ssp_sensor_type type); + +u32 ssp_get_sensor_delay(struct ssp_data *data, enum ssp_sensor_type); + +int ssp_change_delay(struct ssp_data *data, enum ssp_sensor_type type, + u32 delay); +#endif /* _SSP_SENSORS_H_ */ -- cgit v1.2.3 From 2f0ecb7c6563d711bec15268d56adf1c630e77d1 Mon Sep 17 00:00:00 2001 From: Irina Tirdea Date: Tue, 27 Jan 2015 20:41:52 +0200 Subject: iio: core: Introduce IIO_CHAN_INFO_DEBOUNCE_COUNT and _TIME The pedometer needs to filter out false steps that might be generated by tapping the foot, sitting, etc. To do that it computes the number of steps that occur in a given time and decides the user is moving only if this value is over a threshold. E.g.: the user starts moving only if he takes 4 steps in 3 seconds. This filter is applied only when the user starts moving. A device that has such pedometer functionality is Freescale's MMA9553L: http://www.freescale.com/files/sensors/doc/ref_manual/MMA9553LSWRM.pdf. To export this feature, this patch introduces IIO_CHAN_INFO_DEBOUNCE_COUNT and IIO_CHAN_INFO_DEBOUNCE_TIME. For the pedometer, in_steps_debounce_count will specify the number of steps that need to occur in in_steps_debounce_time seconds so that the pedometer decides the user is moving. Signed-off-by: Irina Tirdea Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 51f16437dacc..80d855061064 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -41,6 +41,8 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_ENABLE, IIO_CHAN_INFO_CALIBHEIGHT, IIO_CHAN_INFO_CALIBWEIGHT, + IIO_CHAN_INFO_DEBOUNCE_COUNT, + IIO_CHAN_INFO_DEBOUNCE_TIME, }; enum iio_shared_by { -- cgit v1.2.3 From 7866a621043fbaca3d7389e9b9f69dd1a2e5a855 Mon Sep 17 00:00:00 2001 From: Salam Noureddine Date: Tue, 27 Jan 2015 11:35:48 -0800 Subject: dev: add per net_device packet type chains When many pf_packet listeners are created on a lot of interfaces the current implementation using global packet type lists scales poorly. This patch adds per net_device packet type lists to fix this problem. The patch was originally written by Eric Biederman for linux-2.6.29. Tested on linux-3.16. Signed-off-by: "Eric W. Biederman" Signed-off-by: Salam Noureddine Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 642d426a668f..3d37c6eb1732 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1514,6 +1514,8 @@ struct net_device { struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; + struct list_head ptype_all; + struct list_head ptype_specific; struct { struct list_head upper; -- cgit v1.2.3 From 712eddf70225ab5ae65e946e22d2dfe6b93e8dd1 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Sat, 24 Jan 2015 14:05:50 +0900 Subject: cpuidle: exynos: add coupled cpuidle support for exynos4210 The following patch adds coupled cpuidle support for Exynos4210 to an existing cpuidle-exynos driver. As a result it enables AFTR mode to be used by default on Exynos4210 without the need to hot unplug CPU1 first. The patch is heavily based on earlier cpuidle-exynos4210 driver from Daniel Lezcano: http://www.spinics.net/lists/linux-samsung-soc/msg28134.html Changes from Daniel's code include: - porting code to current kernels - fixing it to work on my setup (by using S5P_INFORM register instead of S5P_VA_SYSRAM one on Revison 1.1 and retrying poking CPU1 out of the BOOT ROM if necessary) - fixing rare lockup caused by waiting for CPU1 to get stuck in the BOOT ROM (CPU hotplug code in arch/arm/mach-exynos/platsmp.c doesn't require this and works fine) - moving Exynos specific code to arch/arm/mach-exynos/pm.c - using cpu_boot_reg_base() helper instead of BOOT_VECTOR macro - using exynos_cpu_*() helpers instead of accessing registers directly - using arch_send_wakeup_ipi_mask() instead of dsb_sev() (this matches CPU hotplug code in arch/arm/mach-exynos/platsmp.c) - integrating separate exynos4210-cpuidle driver into existing exynos-cpuidle one Cc: Colin Cross Cc: Kukjin Kim Cc: Krzysztof Kozlowski Cc: Tomasz Figa Signed-off-by: Bartlomiej Zolnierkiewicz Signed-off-by: Daniel Lezcano Acked-by: Kyungmin Park Signed-off-by: Kukjin Kim --- include/linux/platform_data/cpuidle-exynos.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/platform_data/cpuidle-exynos.h (limited to 'include/linux') diff --git a/include/linux/platform_data/cpuidle-exynos.h b/include/linux/platform_data/cpuidle-exynos.h new file mode 100644 index 000000000000..bfa40e4c5d5f --- /dev/null +++ b/include/linux/platform_data/cpuidle-exynos.h @@ -0,0 +1,20 @@ +/* + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. +*/ + +#ifndef __CPUIDLE_EXYNOS_H +#define __CPUIDLE_EXYNOS_H + +struct cpuidle_exynos_data { + int (*cpu0_enter_aftr)(void); + int (*cpu1_powerdown)(void); + void (*pre_enter_aftr)(void); + void (*post_enter_aftr)(void); +}; + +#endif -- cgit v1.2.3 From f262f28c147051e7aa6daaf4fb5996833ffadff4 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 26 Jan 2015 13:16:27 +0900 Subject: PM / devfreq: event: Add devfreq_event class This patch adds a new class in devfreq, devfreq_event, which provides raw data (e.g., memory bus utilization, GPU utilization) for devfreq governors. - devfreq_event device : Provides raw data for a governor of a devfreq device - devfreq device : Monitors device state and changes frequency/voltage of the device using the raw data from its devfreq_event device. A devfreq device dertermines performance states (normally the frequency and the voltage vlues) based on the results its designtated devfreq governor: e.g., ondemand, performance, powersave. In order to give such results required by a devfreq device, the devfreq governor requires data that indicates the performance requirement given to the devfreq device. The conventional (previous) implementatino of devfreq subsystem requires a devfreq device driver to implement its own mechanism to acquire performance requirement for its governor. However, there had been issues with such requirements: 1. Although performance requirement of such devices is usually acquired from common devices (PMU/PPMU), we do not have any abstract structure to represent them properly. 2. Such performance requirement devices (PMU/PPMU) are actual hardware pieces that may be represented by Device Tree directly while devfreq device itself is a virtual entity that are not considered to be represented by Device Tree according to Device Tree folks. In order to address such issues, a devferq_event device (represented by this patch) provides a template for device drivers representing performance monitoring unit, which gives the basic or raw data for preformance requirement, which in turn, is required by devfreq governors. The following description explains the feature of two kind of devfreq class: - devfreq class (existing) : devfreq consumer device use raw data from devfreq_event device for determining proper current system state and change voltage/frequency dynamically using various governors. - devfreq_event class (new) : Provide measured raw data to devfreq device for governor Cc: MyungJoo Ham Cc: Kyungmin Park Signed-off-by: Chanwoo Choi [Commit message rewritten & conflict resolved by MyungJoo] Signed-off-by: MyungJoo Ham --- include/linux/devfreq-event.h | 196 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 include/linux/devfreq-event.h (limited to 'include/linux') diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h new file mode 100644 index 000000000000..602fbbfcfeed --- /dev/null +++ b/include/linux/devfreq-event.h @@ -0,0 +1,196 @@ +/* + * devfreq-event: a framework to provide raw data and events of devfreq devices + * + * Copyright (C) 2014 Samsung Electronics + * Author: Chanwoo Choi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __LINUX_DEVFREQ_EVENT_H__ +#define __LINUX_DEVFREQ_EVENT_H__ + +#include + +/** + * struct devfreq_event_dev - the devfreq-event device + * + * @node : Contain the devfreq-event device that have been registered. + * @dev : the device registered by devfreq-event class. dev.parent is + * the device using devfreq-event. + * @lock : a mutex to protect accessing devfreq-event. + * @enable_count: the number of enable function have been called. + * @desc : the description for devfreq-event device. + * + * This structure contains devfreq-event device information. + */ +struct devfreq_event_dev { + struct list_head node; + + struct device dev; + struct mutex lock; + u32 enable_count; + + const struct devfreq_event_desc *desc; +}; + +/** + * struct devfreq_event_data - the devfreq-event data + * + * @load_count : load count of devfreq-event device for the given period. + * @total_count : total count of devfreq-event device for the given period. + * each count may represent a clock cycle, a time unit + * (ns/us/...), or anything the device driver wants. + * Generally, utilization is load_count / total_count. + * + * This structure contains the data of devfreq-event device for polling period. + */ +struct devfreq_event_data { + unsigned long load_count; + unsigned long total_count; +}; + +/** + * struct devfreq_event_ops - the operations of devfreq-event device + * + * @enable : Enable the devfreq-event device. + * @disable : Disable the devfreq-event device. + * @reset : Reset all setting of the devfreq-event device. + * @set_event : Set the specific event type for the devfreq-event device. + * @get_event : Get the result of the devfreq-event devie with specific + * event type. + * + * This structure contains devfreq-event device operations which can be + * implemented by devfreq-event device drivers. + */ +struct devfreq_event_ops { + /* Optional functions */ + int (*enable)(struct devfreq_event_dev *edev); + int (*disable)(struct devfreq_event_dev *edev); + int (*reset)(struct devfreq_event_dev *edev); + + /* Mandatory functions */ + int (*set_event)(struct devfreq_event_dev *edev); + int (*get_event)(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +}; + +/** + * struct devfreq_event_desc - the descriptor of devfreq-event device + * + * @name : the name of devfreq-event device. + * @driver_data : the private data for devfreq-event driver. + * @ops : the operation to control devfreq-event device. + * + * Each devfreq-event device is described with a this structure. + * This structure contains the various data for devfreq-event device. + */ +struct devfreq_event_desc { + const char *name; + void *driver_data; + + struct devfreq_event_ops *ops; +}; + +#if defined(CONFIG_PM_DEVFREQ_EVENT) +extern int devfreq_event_enable_edev(struct devfreq_event_dev *edev); +extern int devfreq_event_disable_edev(struct devfreq_event_dev *edev); +extern bool devfreq_event_is_enabled(struct devfreq_event_dev *edev); +extern int devfreq_event_set_event(struct devfreq_event_dev *edev); +extern int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata); +extern int devfreq_event_reset_event(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index); +extern int devfreq_event_get_edev_count(struct device *dev); +extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev); +extern struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc); +extern void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev); +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return edev->desc->driver_data; +} +#else +static inline int devfreq_event_enable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_disable_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline bool devfreq_event_is_enabled(struct devfreq_event_dev *edev) +{ + return false; +} + +static inline int devfreq_event_set_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline int devfreq_event_get_event(struct devfreq_event_dev *edev, + struct devfreq_event_data *edata) +{ + return -EINVAL; +} + +static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return ERR_PTR(-EINVAL); +} + +static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle( + struct device *dev, int index) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_get_edev_count(struct device *dev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline int devfreq_event_remove_edev(struct devfreq_event_dev *edev) +{ + return -EINVAL; +} + +static inline struct devfreq_event_dev *devm_devfreq_event_add_edev( + struct device *dev, + struct devfreq_event_desc *desc) +{ + return ERR_PTR(-EINVAL); +} + +static inline void devm_devfreq_event_remove_edev(struct device *dev, + struct devfreq_event_dev *edev) +{ +} + +static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev) +{ + return NULL; +} +#endif /* CONFIG_PM_DEVFREQ_EVENT */ + +#endif /* __LINUX_DEVFREQ_EVENT_H__ */ -- cgit v1.2.3 From e4b3d38088df6f3acd40259c8ec32c9bd3bfe3da Mon Sep 17 00:00:00 2001 From: Sylwester Nawrocki Date: Fri, 16 Jan 2015 18:30:37 +0100 Subject: phy: exynos-video-mipi: Fix regression by adding support for PMU regmap After the Exynos Power Management Unit (PMU) driver was converted to the platform device driver in commit 14fc8b93d47323561edf5d482 ("ARM: EXYNOS: Add platform driver support for Exynos PMU") and then PMU device nodes added to Exynos4 DTs in commit 7b9613aca42a5522d269 ("ARM: dts: add PMU syscon node for exynos4") the mipi video phy driver started failing probing, due to overlapping memory mapped register region resources. Now all the Exynos peripheral devices which have registers in the PMU region are supposed to use the regmap provided by the syscon driver. So support for regmap is added in this patch, this unfortunately creates yet another indirection into that supposedly trivial driver. The additional mutex is required because single register is used by PHY pairs (they share bit in a register). An improvement here could be to allow a PHY instance be created with a driver custom mutex, which would then be common for each PHY pair. This would eliminate one of 3 mutexes which need to be taken in the phy_power_on/ phy_power_off code path. However, I tried to keep this bug fix patch possibly simple. This change is needed to make MIPI DSI displays and MIPI CSI-2 camera sensors working again on Exynos4 boards. Cc: Pankaj Dubey Cc: Kukjin Kim Signed-off-by: Sylwester Nawrocki Signed-off-by: Kishon Vijay Abraham I --- include/linux/mfd/syscon/exynos4-pmu.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/mfd/syscon/exynos4-pmu.h (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/exynos4-pmu.h b/include/linux/mfd/syscon/exynos4-pmu.h new file mode 100644 index 000000000000..278b1b1549e9 --- /dev/null +++ b/include/linux/mfd/syscon/exynos4-pmu.h @@ -0,0 +1,21 @@ +/* + * Copyright (C) 2015 Samsung Electronics Co., Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ +#define _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ + +/* Exynos4 PMU register definitions */ + +/* MIPI_PHYn_CONTROL register offset: n = 0..1 */ +#define EXYNOS4_MIPI_PHY_CONTROL(n) (0x710 + (n) * 4) +#define EXYNOS4_MIPI_PHY_ENABLE (1 << 0) +#define EXYNOS4_MIPI_PHY_SRESETN (1 << 1) +#define EXYNOS4_MIPI_PHY_MRESETN (1 << 2) +#define EXYNOS4_MIPI_PHY_RESET_MASK (3 << 1) + +#endif /* _LINUX_MFD_SYSCON_PMU_EXYNOS4_H_ */ -- cgit v1.2.3 From 38e478c4489a845a5e8baf7849c286af5fed5b66 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 15:56:21 +0200 Subject: quota: Split ->set_xstate callback into two Split ->set_xstate callback into two callbacks - one for turning quotas on (->quota_enable) and one for turning quotas off (->quota_disable). That way we don't have to pass quotactl command into the callback which seems cleaner. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quota.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 227f37f463c9..4da497b807c4 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -371,13 +371,14 @@ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); + int (*quota_enable)(struct super_block *, unsigned int); + int (*quota_disable)(struct super_block *, unsigned int); int (*quota_sync)(struct super_block *, int); int (*get_info)(struct super_block *, int, struct if_dqinfo *); int (*set_info)(struct super_block *, int, struct if_dqinfo *); int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *); int (*get_xstate)(struct super_block *, struct fs_quota_stat *); - int (*set_xstate)(struct super_block *, unsigned int, int); int (*get_xstatev)(struct super_block *, struct fs_quota_statv *); int (*rm_xquota)(struct super_block *, unsigned int); }; -- cgit v1.2.3 From d3b863248577504f6eecca2a464d6ddf86b71584 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 16:07:12 +0200 Subject: quota: Wire up ->quota_{enable,disable} callbacks into Q_QUOTA{ON,OFF} Make Q_QUOTAON / Q_QUOTAOFF quotactl call ->quota_enable / ->quota_disable callback when provided. To match current behavior of ocfs2 & ext4 we make these quotactls turn on / off quota enforcement for appropriate quota type. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quotaops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 29e3455f7d41..ff0b665591d0 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -386,4 +386,6 @@ static inline void dquot_release_reservation_block(struct inode *inode, __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } +unsigned int qtype_enforce_flag(int type); + #endif /* _LINUX_QUOTAOPS_ */ -- cgit v1.2.3 From 3e2af67e66ff025796af1a8a1fcbb4236304f90c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 6 Oct 2014 18:40:51 +0200 Subject: quota: Add ->quota_{enable,disable} callbacks for VFS quotas Add functions which translate ->quota_enable / ->quota_disable calls into appropriate changes in VFS quota. This will enable filesystems supporting VFS quota files in system inodes to be controlled via Q_XQUOTA[ON|OFF] quotactls for better userspace compatibility. Also provide a vector for quotactl using these functions which can be used by filesystems with quota files stored in hidden system files. Signed-off-by: Jan Kara --- include/linux/quotaops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index ff0b665591d0..df73258cca47 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -166,6 +166,7 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type) */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_ops; +extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else -- cgit v1.2.3 From aaa3daed156ff3c6acb28c8b18028f8b57d6c91b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Oct 2014 18:35:31 +0200 Subject: quota: Remove quota_on_meta callback There are no more users for quota_on_meta callback. Just remove it. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quota.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 4da497b807c4..0938159d65c8 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -369,7 +369,6 @@ struct qc_dqblk { /* Operations handling requests from userspace */ struct quotactl_ops { int (*quota_on)(struct super_block *, int, int, struct path *); - int (*quota_on_meta)(struct super_block *, int, int); int (*quota_off)(struct super_block *, int); int (*quota_enable)(struct super_block *, unsigned int); int (*quota_disable)(struct super_block *, unsigned int); -- cgit v1.2.3 From b10a08194c2b615955dfab2300331a90ae9344c7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 9 Oct 2014 16:54:13 +0200 Subject: quota: Store maximum space limit in bytes Currently maximum space limit quota format supports is in blocks however since we store space limits in bytes, this is somewhat confusing. So store the maximum limit in bytes as well. Also rename the field to match the new unit and related inode field to match the new naming scheme. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/quota.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 0938159d65c8..d534e8ed308a 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -216,8 +216,8 @@ struct mem_dqinfo { unsigned long dqi_flags; unsigned int dqi_bgrace; unsigned int dqi_igrace; - qsize_t dqi_maxblimit; - qsize_t dqi_maxilimit; + qsize_t dqi_max_spc_limit; + qsize_t dqi_max_ino_limit; void *dqi_priv; }; -- cgit v1.2.3 From 284f4902a632584e8d73cf7d9363f819adf7240c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:13 -0500 Subject: xprtrdma: Modernize htonl and ntohl Clean up: Replace htonl and ntohl with the be32 equivalents. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 9 +++++++++ include/linux/sunrpc/svc_rdma.h | 2 -- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index b78f16b1dea3..1578ed241c19 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -42,6 +42,9 @@ #include +#define RPCRDMA_VERSION 1 +#define rpcrdma_version cpu_to_be32(RPCRDMA_VERSION) + struct rpcrdma_segment { __be32 rs_handle; /* Registered memory handle */ __be32 rs_length; /* Length of the chunk in bytes */ @@ -115,4 +118,10 @@ enum rpcrdma_proc { RDMA_ERROR = 4 /* An RPC RDMA encoding error */ }; +#define rdma_msg cpu_to_be32(RDMA_MSG) +#define rdma_nomsg cpu_to_be32(RDMA_NOMSG) +#define rdma_msgp cpu_to_be32(RDMA_MSGP) +#define rdma_done cpu_to_be32(RDMA_DONE) +#define rdma_error cpu_to_be32(RDMA_ERROR) + #endif /* _LINUX_SUNRPC_RPC_RDMA_H */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 975da754c778..ddfe88f52219 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -63,8 +63,6 @@ extern atomic_t rdma_stat_rq_prod; extern atomic_t rdma_stat_sq_poll; extern atomic_t rdma_stat_sq_prod; -#define RPCRDMA_VERSION 1 - /* * Contexts are built when an RDMA request is created and are a * record of the resources that can be recovered when the request -- cgit v1.2.3 From f2846481b4bf758cf7c3fe8f24b35950306f1db2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 21 Jan 2015 11:02:29 -0500 Subject: xprtrdma: Clean up hdrlen Clean up: Replace naked integers with a documenting macro. Signed-off-by: Chuck Lever Reviewed-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/rpc_rdma.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index 1578ed241c19..f33c5a4d6fe4 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -98,7 +98,10 @@ struct rpcrdma_msg { } rm_body; }; -#define RPCRDMA_HDRLEN_MIN 28 +/* + * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks + */ +#define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) enum rpcrdma_errcode { ERR_VERS = 1, -- cgit v1.2.3 From 74807dffcdd72bb4c0786214e8486ef9bb088156 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 29 Jan 2015 22:25:40 +0200 Subject: clk: ti: add omap3 legacy clock data Introduces omap3 legacy clock data under clock driver. The clock data is also in new format, which makes it possible to get rid of the clk-private.h header. This patch also introduces SoC specific init functions that shall be called from the low level init. The data format used in this file has two possible evolution paths; it can either be removed completely once no longer needed, or it will be possible to retain the format and modify the TI clock driver to be a loadable module at some point. The actual path to be followed will be decided later. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Michael Turquette --- include/linux/clk/ti.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 55ef529a0dbf..13a20bf9e1a5 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -217,6 +217,13 @@ struct ti_dt_clk { /* Maximum number of clock memmaps */ #define CLK_MAX_MEMMAPS 4 +/* Static memmap indices */ +enum { + TI_CLKM_CM = 0, + TI_CLKM_PRM, + TI_CLKM_SCRM, +}; + typedef void (*ti_of_clk_init_cb_t)(struct clk_hw *, struct device_node *); /** @@ -348,4 +355,9 @@ extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait; extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait; extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait; +int omap3430_clk_legacy_init(void); +int omap3430es1_clk_legacy_init(void); +int omap36xx_clk_legacy_init(void); +int am35xx_clk_legacy_init(void); + #endif -- cgit v1.2.3 From 074f9dd55f9cab1b82690ed7e44bcf38b9616ce0 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 29 Jan 2015 15:05:04 -0500 Subject: USB: add flag for HCDs that can't receive wakeup requests (isp1760-hcd) Currently the USB stack assumes that all host controller drivers are capable of receiving wakeup requests from downstream devices. However, this isn't true for the isp1760-hcd driver, which means that it isn't safe to do a runtime suspend of any device attached to a root-hub port if the device requires wakeup. This patch adds a "cant_recv_wakeups" flag to the usb_hcd structure and sets the flag in isp1760-hcd. The core is modified to prevent a direct child of the root hub from being put into runtime suspend with wakeup enabled if the flag is set. Signed-off-by: Alan Stern Tested-by: Nicolas Pitre CC: Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 8968f616e414..68b1e836dff1 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -146,6 +146,8 @@ struct usb_hcd { unsigned amd_resume_bug:1; /* AMD remote wakeup quirk */ unsigned can_do_streams:1; /* HC supports streams */ unsigned tpl_support:1; /* OTG & EH TPL support */ + unsigned cant_recv_wakeups:1; + /* wakeup requests from downstream aren't received */ unsigned int irq; /* irq allocated */ void __iomem *regs; /* device memory/io */ -- cgit v1.2.3 From 448c7f3830ca283e485aa943279acea6bde8b270 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sun, 1 Feb 2015 11:25:14 -0800 Subject: Input: MT - add support for balanced slot assignment Some devices are not fast enough to differentiate between a fast-moving contact and a new contact. This problem cannot be fully resolved because information is truly missing, but it is possible to safe-guard against obvious mistakes by restricting movement with a maximum displacement. The new problem formulation for dmax > 0 cannot benefit from the speedup for positive definite matrices, but since the convergence is faster, the result is about the same. For a handful of contacts, the latency difference is truly negligible. Suggested-by: Benjamin Tissoires Tested-by: Benjamin Tissoires Signed-off-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- include/linux/input/mt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index f583ff639776..d7188de4db96 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -119,7 +119,8 @@ struct input_mt_pos { }; int input_mt_assign_slots(struct input_dev *dev, int *slots, - const struct input_mt_pos *pos, int num_pos); + const struct input_mt_pos *pos, int num_pos, + int dmax); int input_mt_get_slot_by_key(struct input_dev *dev, int key); -- cgit v1.2.3 From fd979c0132074856975a6e79bc2226b99435ec5b Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 30 Jan 2015 13:45:57 -0800 Subject: perf: provide sysfs_show for struct perf_pmu_events_attr (struct perf_pmu_events_attr) is defined in include/linux/perf_event.h, but the only "show" for it is in x86 and contains x86 specific stuff. Make a generic one for those of us who are just using the event_str. Signed-off-by: Cody P Schafer Signed-off-by: Sukadev Bhattiprolu Acked-by: Jiri Olsa Signed-off-by: Michael Ellerman --- include/linux/perf_event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 486e84ccb1f9..58f59bdb590b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -897,6 +897,9 @@ struct perf_pmu_events_attr { const char *event_str; }; +ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); + #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ -- cgit v1.2.3 From f0405b816149665393cc62b9e5082fc2d79714df Mon Sep 17 00:00:00 2001 From: Cody P Schafer Date: Fri, 30 Jan 2015 13:45:58 -0800 Subject: perf: add PMU_EVENT_ATTR_STRING() helper Helper for constructing static struct perf_pmu_events_attr s. Signed-off-by: Cody P Schafer Signed-off-by: Sukadev Bhattiprolu Acked-by: Jiri Olsa Signed-off-by: Michael Ellerman --- include/linux/perf_event.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 58f59bdb590b..1d3631448b91 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -906,6 +906,13 @@ static struct perf_pmu_events_attr _var = { \ .id = _id, \ }; +#define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ +static struct perf_pmu_events_attr _var = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = _str, \ +}; + #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ -- cgit v1.2.3 From aafb3e98b27977148c8c86499684f8f5c3decfbb Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Thu, 29 Jan 2015 22:40:11 -0800 Subject: netdev: introduce new NETIF_F_HW_SWITCH_OFFLOAD feature flag for switch device offloads This is a high level feature flag for all switch asic offloads switch drivers set this flag on switch ports. Logical devices like bridge, bonds, vxlans can inherit this flag from their slaves/ports. The patch also adds the flag to NETIF_F_ONE_FOR_ALL, so that it gets propagated to the upperdevices (bridges and bonds). Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 8e30685affeb..7d59dc6ab789 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -66,6 +66,7 @@ enum { NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */ NETIF_F_HW_L2FW_DOFFLOAD_BIT, /* Allow L2 Forwarding in Hardware */ NETIF_F_BUSY_POLL_BIT, /* Busy poll */ + NETIF_F_HW_SWITCH_OFFLOAD_BIT, /* HW switch offload */ /* * Add your fresh new feature above and remember to update @@ -124,6 +125,7 @@ enum { #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) #define NETIF_F_HW_L2FW_DOFFLOAD __NETIF_F(HW_L2FW_DOFFLOAD) #define NETIF_F_BUSY_POLL __NETIF_F(BUSY_POLL) +#define NETIF_F_HW_SWITCH_OFFLOAD __NETIF_F(HW_SWITCH_OFFLOAD) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ @@ -159,7 +161,9 @@ enum { */ #define NETIF_F_ONE_FOR_ALL (NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \ NETIF_F_SG | NETIF_F_HIGHDMA | \ - NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED) + NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \ + NETIF_F_HW_SWITCH_OFFLOAD) + /* * If one device doesn't support one of these features, then disable it * for all in netdev_increment_features. -- cgit v1.2.3 From add511b38266aa10c1079f9248854e6a415c4dc2 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Thu, 29 Jan 2015 22:40:12 -0800 Subject: bridge: add flags argument to ndo_bridge_setlink and ndo_bridge_dellink bridge flags are needed inside ndo_bridge_setlink/dellink handlers to avoid another call to parse IFLA_AF_SPEC inside these handlers This is used later in this series Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3d37c6eb1732..16251e96e6aa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1154,13 +1154,15 @@ struct net_device_ops { int idx); int (*ndo_bridge_setlink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask); int (*ndo_bridge_dellink)(struct net_device *dev, - struct nlmsghdr *nlh); + struct nlmsghdr *nlh, + u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, -- cgit v1.2.3 From d0a57bd5b53d6b7fe7a6c626023737436b5df630 Mon Sep 17 00:00:00 2001 From: Peter De Schrijver Date: Tue, 16 Dec 2014 12:38:27 -0800 Subject: clk: tegra: make tegra_clocks_apply_init_table() arch_initcall tegra_clocks_apply_init_table() needs to be called after the udelay loop has been calibrated (see commit 441f199a37cfd66c5dd8dd45490bd3ea6971117d ("clk: tegra: defer application of init table") for why that is). On existing Tegra SoCs this was done by calling tegra_clocks_apply_init_table() from tegra_dt_init(). To make this also work on ARM64, we need to change this into an initcall. tegra_dt_init() is called from customize_machine which is an arch_initcall. Therefore this should also work on existing 32bit Tegra SoCs. Tested on Tegra20 (ventana), Tegra30 (beaverboard), Tegra124 (jetson TK1) and Tegra132. Signed-off-by: Peter De Schrijver [paul@pwsan.com: tweaked the commit message] Signed-off-by: Paul Walmsley Signed-off-by: Paul Walmsley Cc: Thierry Reding Cc: Prashant Gaikwad Cc: Mike Turquette Cc: Stephen Boyd Cc: Stephen Warren Cc: Thierry Reding Cc: Alexandre Courbot --- include/linux/clk/tegra.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index 3ca9fca827a2..19c4208f4752 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -120,6 +120,4 @@ static inline void tegra_cpu_clock_resume(void) } #endif -void tegra_clocks_apply_init_table(void); - #endif /* __LINUX_CLK_TEGRA_H_ */ -- cgit v1.2.3 From 15d0f5ea348b9c4e6d41df294dde38a56a39c7bf Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 2 Feb 2015 10:07:59 -0700 Subject: Make super_blocks and sb_lock static The only user outside of fs/super.c is gone now Signed-off-by: Al Viro Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 65d02de342e1..2f717baefdf8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1183,8 +1183,6 @@ struct mm_struct; #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -extern struct list_head super_blocks; -extern spinlock_t sb_lock; /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From 6cae0a4648c0db2a74efb816cd2ce84390c90480 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Aug 2014 13:31:51 +0200 Subject: nfs: add LAYOUT_TYPE_MAX enum value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This gives us a nice upper bound for later use in nfѕd. Signed-off-by: Christoph Hellwig --- include/linux/nfs4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 022b761dbf0a..8a3589c2542c 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -516,6 +516,7 @@ enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, LAYOUT_BLOCK_VOLUME = 3, + LAYOUT_TYPE_MAX }; /* used for both layout return and recall */ -- cgit v1.2.3 From 11afe9f76e121e960445deee5b7f26f0787a1990 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Jan 2015 19:17:03 +0100 Subject: fs: add FL_LAYOUT lease type This (ab-)uses the file locking code to allow filesystems to recall outstanding pNFS layouts on a file. This new lease type is similar but not quite the same as FL_DELEG. A FL_LAYOUT lease can always be granted, an a per-filesystem lock (XFS iolock for the initial implementation) ensures not FL_LAYOUT leases granted when we would need to recall them. Also included are changes that allow multiple outstanding read leases of different types on the same file as long as they have a differnt owner. This wasn't a problem until now as nfsd never set FL_LEASE leases, and no one else used FL_DELEG leases, but given that nfsd will also issues FL_LAYOUT leases we will have to handle it now. Signed-off-by: Christoph Hellwig --- include/linux/fs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index ddd2fa7cefd3..84740145f835 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -875,6 +875,7 @@ static inline struct file *get_file(struct file *f) #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ +#define FL_LAYOUT 2048 /* outstanding pNFS layout */ /* * Special return value from posix_lock_file() and vfs_lock_file() for @@ -2037,6 +2038,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode) return ret; } +static inline int break_layout(struct inode *inode, bool wait) +{ + smp_mb(); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) + return __break_lease(inode, + wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, + FL_LAYOUT); + return 0; +} + #else /* !CONFIG_FILE_LOCKING */ static inline int locks_mandatory_locked(struct file *file) { @@ -2092,6 +2103,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode) return 0; } +static inline int break_layout(struct inode *inode, bool wait) +{ + return 0; +} + #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ -- cgit v1.2.3 From 9cf514ccfacb301f3b1b4509a8ce25dffad55880 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 5 May 2014 13:11:59 +0200 Subject: nfsd: implement pNFS operations Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage outstanding layouts and devices. Layout management is very straight forward, with a nfs4_layout_stateid structure that extends nfs4_stid to manage layout stateids as the top-level structure. It is linked into the nfs4_file and nfs4_client structures like the other stateids, and contains a linked list of layouts that hang of the stateid. The actual layout operations are implemented in layout drivers that are not part of this commit, but will be added later. The worst part of this commit is the management of the pNFS device IDs, which suffers from a specification that is not sanely implementable due to the fact that the device-IDs are global and not bound to an export, and have a small enough size so that we can't store the fsid portion of a file handle, and must never be reused. As we still do need perform all export authentication and validation checks on a device ID passed to GETDEVICEINFO we are caught between a rock and a hard place. To work around this issue we add a new hash that maps from a 64-bit integer to a fsid so that we can look up the export to authenticate against it, a 32-bit integer as a generation that we can bump when changing the device, and a currently unused 32-bit integer that could be used in the future to handle more than a single device per export. Entries in this hash table are never deleted as we can't reuse the ids anyway, and would have a severe lifetime problem anyway as Linux export structures are temporary structures that can go away under load. Parts of the XDR data, structures and marshaling/unmarshaling code, as well as many concepts are derived from the old pNFS server implementation from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman, Mike Sager, Ricardo Labiaga and many others. Signed-off-by: Christoph Hellwig --- include/linux/nfs4.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 8a3589c2542c..bc10d687f2ce 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -411,6 +411,7 @@ enum lock_type4 { #define FATTR4_WORD1_TIME_MODIFY_SET (1UL << 22) #define FATTR4_WORD1_MOUNTED_ON_FILEID (1UL << 23) #define FATTR4_WORD1_FS_LAYOUT_TYPES (1UL << 30) +#define FATTR4_WORD2_LAYOUT_TYPES (1UL << 0) #define FATTR4_WORD2_LAYOUT_BLKSIZE (1UL << 1) #define FATTR4_WORD2_MDSTHRESHOLD (1UL << 4) #define FATTR4_WORD2_SECURITY_LABEL (1UL << 16) -- cgit v1.2.3 From 67dc0d4758e5ced978bb30e8af11bc42cabfa77c Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 29 Jan 2015 14:11:25 +1000 Subject: vt_buffer: drop console buffer copying optimisations These two copy to/from VGA memory, however on the Silicon Motion SMI750 VGA card on a 64-bit system cause console corruption. This is due to the hw being buggy and not handling a 64-bit transaction correctly. We could try and create a 32-bit version of these routines, but I'm not sure the optimisation is worth much today. Fixes https://bugzilla.redhat.com/show_bug.cgi?id=1132826 Tested-by: Huawei engineering. Signed-off-by: Dave Airlie Cc: Linus Torvalds Cc: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_buffer.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 057db7d2f448..f38c10ba3ff5 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -21,10 +21,6 @@ #ifndef VT_BUF_HAVE_RW #define scr_writew(val, addr) (*(addr) = (val)) #define scr_readw(addr) (*(addr)) -#define scr_memcpyw(d, s, c) memcpy(d, s, c) -#define scr_memmovew(d, s, c) memmove(d, s, c) -#define VT_BUF_HAVE_MEMCPYW -#define VT_BUF_HAVE_MEMMOVEW #endif #ifndef VT_BUF_HAVE_MEMSETW -- cgit v1.2.3 From 01395d798452435f19de3bfe5d04325db4e49677 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Thu, 22 Jan 2015 11:50:24 -0500 Subject: PNP: Allow console to override ACPI device sleep If the serial console is an ACPI PNP device, the PNP bus always powers down the device at system suspend, even though the no_console_suspend command line parameter is specified (eg., when debugging suspend/resume). Add PNP_CONSOLE capability, which when set, prevents calling both the ->disable() and ->suspend() PNP protocol methods if console suspend is disabled. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/pnp.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pnp.h b/include/linux/pnp.h index 195aafc6cd07..6512e9cbc6d5 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -12,6 +12,7 @@ #include #include #include +#include #define PNP_NAME_LEN 50 @@ -309,15 +310,22 @@ struct pnp_fixup { #define PNP_DISABLE 0x0004 #define PNP_CONFIGURABLE 0x0008 #define PNP_REMOVABLE 0x0010 +#define PNP_CONSOLE 0x0020 #define pnp_can_read(dev) (((dev)->protocol->get) && \ ((dev)->capabilities & PNP_READ)) #define pnp_can_write(dev) (((dev)->protocol->set) && \ ((dev)->capabilities & PNP_WRITE)) -#define pnp_can_disable(dev) (((dev)->protocol->disable) && \ - ((dev)->capabilities & PNP_DISABLE)) +#define pnp_can_disable(dev) (((dev)->protocol->disable) && \ + ((dev)->capabilities & PNP_DISABLE) && \ + (!((dev)->capabilities & PNP_CONSOLE) || \ + console_suspend_enabled)) #define pnp_can_configure(dev) ((!(dev)->active) && \ ((dev)->capabilities & PNP_CONFIGURABLE)) +#define pnp_can_suspend(dev) (((dev)->protocol->suspend) && \ + (!((dev)->capabilities & PNP_CONSOLE) || \ + console_suspend_enabled)) + #ifdef CONFIG_ISAPNP extern struct pnp_protocol isapnp_protocol; -- cgit v1.2.3 From 3abf87cd3e70009ed70a7f28c2914888a7e27332 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 17 Jan 2015 15:42:04 -0500 Subject: tty: Make lock subclasses available for other tty locks Besides nested legacy_mutex locking which is required on pty pair teardown, other nested pty operations require lock subclassing. Move lock subclass definition to tty interface header, include/linux/tty.h, and document its use. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 7d66ae508e5c..849659908f23 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -14,6 +14,23 @@ #include +/* + * Lock subclasses for tty locks + * + * TTY_LOCK_NORMAL is for normal ttys and master ptys. + * TTY_LOCK_SLAVE is for slave ptys only. + * + * Lock subclasses are necessary for handling nested locking with pty pairs. + * tty locks which use nested locking: + * + * legacy_mutex - Nested tty locks are necessary for releasing pty pairs. + * The stable lock order is master pty first, then slave pty. + */ + +enum { + TTY_LOCK_NORMAL = 0, + TTY_LOCK_SLAVE, +}; /* * (Note: the *_driver.minor_start values 1, 64, 128, 192 are -- cgit v1.2.3 From 1d1d14da12e79a6c05fbe1a975401f0f56c93316 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 17 Jan 2015 15:42:05 -0500 Subject: pty: Fix buffer flush deadlock The pty driver does not clear its write buffer when commanded. This is to avoid an apparent deadlock between parallel flushes from both pty ends; specifically when handling either BRK or INTR input. However, parallel flushes from this source is not possible since the pty master can never be set to BRKINT or ISIG. Parallel flushes from other sources are possible but these do not threaten deadlocks. Annotate the tty buffer mutex for lockdep to represent the nested tty_buffer locking which occurs when the pty slave is processing input (its buffer mutex held) and receives INTR or BRK and acquires the linked tty buffer mutex via tty_buffer_flush(). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 849659908f23..55964b9490dd 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -25,6 +25,9 @@ * * legacy_mutex - Nested tty locks are necessary for releasing pty pairs. * The stable lock order is master pty first, then slave pty. + * tty_buffer lock - slave ptys can claim nested buffer lock when handling + * signal chars. The stable lock order is slave pty, then + * master. */ enum { @@ -460,6 +463,7 @@ extern void tty_flush_to_ldisc(struct tty_struct *tty); extern void tty_buffer_free_all(struct tty_port *port); extern void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld); extern void tty_buffer_init(struct tty_port *port); +extern void tty_buffer_set_lock_subclass(struct tty_port *port); extern speed_t tty_termios_baud_rate(struct ktermios *termios); extern speed_t tty_termios_input_baud_rate(struct ktermios *termios); extern void tty_termios_encode_baud_rate(struct ktermios *termios, -- cgit v1.2.3 From d2b6f44779d3be22d32a5697bd30b59367fd2b33 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sat, 17 Jan 2015 15:42:06 -0500 Subject: n_tty: Fix signal handling flushes BRKINT and ISIG requires input and output flush when a signal char is received. However, the order of operations is significant since parallel i/o may be ongoing. Merge the signal handling for BRKINT with ISIG handling. Process the signal first. This ensures any ongoing i/o is aborted; without this, a waiting writer may continue writing after the flush occurs and after the signal char has been echoed. Write lock the termios_rwsem, which excludes parallel writers from pushing new i/o until after the output buffers are flushed; claiming the write lock is necessary anyway to exclude parallel readers while the read buffer is flushed. Subclass the termios_rwsem for ptys since the slave pty performing the flush may appear to reorder the termios_rwsem->tty buffer lock lock order; adding annotation clarifies that slave tty_buffer lock-> slave termios_rwsem -> master tty_buffer lock is a valid lock order. Flush the echo buffer. In this context, the echo buffer is 'output'. Otherwise, the output will appear discontinuous because the output buffer was cleared which contains older output than the echo buffer. Open-code the read buffer flush since the input worker does not need kicking (this is the input worker). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 55964b9490dd..fe5623c9af71 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -25,6 +25,9 @@ * * legacy_mutex - Nested tty locks are necessary for releasing pty pairs. * The stable lock order is master pty first, then slave pty. + * termios_rwsem - The stable lock order is tty_buffer lock->termios_rwsem. + * Subclassing this lock enables the slave pty to hold its + * termios_rwsem when claiming the master tty_buffer lock. * tty_buffer lock - slave ptys can claim nested buffer lock when handling * signal chars. The stable lock order is slave pty, then * master. -- cgit v1.2.3 From 4516d50aabedbe5ae334155193e4d35c02390d9a Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Thu, 22 Jan 2015 12:24:30 -0500 Subject: serial: 8250: Use canary to restart console after suspend When using no_console_suspend, the serial console may be powered off anyway during system sleep. Upon resume, the port may be in its default power-on state, but is expected to continue console i/o before the device has received its pm callback. The resultant garbage i/o can cause all kinds of havoc on the remote end. Use the scratch register as a canary to discover if the console has been powered-off. Write a non-zero value to the scratch register at port suspend and reprogram the port before any console i/o if the scratch register != canary before port resume. This workaround is disabled for omap_8250 (which uses different divisor programming). Credit to Doug Anderson for the idea of using the scratch register canary to discover port power-down. Cc: Doug Anderson Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 245b959f1ff6..a8efa235b7c1 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -85,6 +85,9 @@ struct uart_8250_port { unsigned char mcr_force; /* mask of forced bits */ unsigned char cur_iotype; /* Running I/O type */ unsigned int rpm_tx_active; + unsigned char canary; /* non-zero during system sleep + * if no_console_suspend + */ /* * Some bits in registers are cleared on a read, so they must -- cgit v1.2.3 From 391f93f2ec9f857c83bdd21a14dcf7e699f38579 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 25 Jan 2015 14:44:51 -0500 Subject: serial: core: Rework hw-assisted flow control support hw-assisted flow control support was added to the serial core in v3.8 with commits, dba05832cbe4f ("SERIAL: core: add hardware assisted h/w flow control support") 2cbacafd7af0f ("SERIAL: core: add hardware assisted s/w flow control support") 9aba8d5b01119 ("SERIAL: core: add throttle/unthrottle callbacks for hardware assisted flow control") Since then, additional requirements for serial core support have arisen. Specifically, 1. Separate tx and rx flow control settings for UARTs which only support tx flow control (ie., autoCTS). 2. Disable sw-assisted CTS flow control in autoCTS mode 3. Support for RTS flow control by serial core and userspace in autoRTS mode Distinguish mode from capability; introduce UPSTAT_AUTORTS, UPSTAT_AUTOCTS and UPSTAT_AUTOXOFF which, when set by the uart driver, enable serial core support for hw-assisted rx, hw-assisted tx and hw-assisted in-band/IXOFF rx flow control, respectively. [Note: hw-assisted in-band/IXON tx flow control does not require serial core support/intervention and can be enabled by the uart driver when required.] These modes must be set/reset in the driver's set_termios() method, based on termios settings, and thus can be safely queried in any context in which one of the port lock, port mutex or termios rwsem are held. Set these modes in the 2 in-tree drivers, omap-serial and 8250_omap, which currently use UPF_HARD_FLOW/UPF_SOFT_FLOW support. Retain UPF_HARD_FLOW and UPF_SOFT_FLOW as capabilities; re-define UPF_HARD_FLOW as both UPF_AUTO_RTS and UPF_AUTO_CTS to allow for distinct and separate rx and tx flow control capabilities. Disable sw-assisted CTS flow control when UPSTAT_AUTOCTS is enabled. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index a0c7033d5f91..baf3e1d08416 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -191,8 +191,10 @@ struct uart_port { #define UPF_NO_TXEN_TEST ((__force upf_t) (1 << 15)) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) -/* Port has hardware-assisted h/w flow control (iow, auto-RTS *not* auto-CTS) */ -#define UPF_HARD_FLOW ((__force upf_t) (1 << 21)) +/* Port has hardware-assisted h/w flow control */ +#define UPF_AUTO_CTS ((__force upf_t) (1 << 20)) +#define UPF_AUTO_RTS ((__force upf_t) (1 << 21)) +#define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) (1 << 22)) #define UPF_CONS_FLOW ((__force upf_t) (1 << 23)) @@ -214,11 +216,17 @@ struct uart_port { #error Change mask not equivalent to userspace-visible bit defines #endif - /* status must be updated while holding port lock */ + /* + * Must hold termios_rwsem, port mutex and port lock to change; + * can hold any one lock to read. + */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) +#define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) +#define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) +#define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) int hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ @@ -392,6 +400,13 @@ static inline bool uart_cts_enabled(struct uart_port *uport) return !!(uport->status & UPSTAT_CTS_ENABLE); } +static inline bool uart_softcts_mode(struct uart_port *uport) +{ + upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; + + return ((uport->status & mask) == UPSTAT_CTS_ENABLE); +} + /* * The following are helper functions for the low level drivers. */ -- cgit v1.2.3 From 632f32e2107d37598e3f6816dcf00c7cab4081ca Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 25 Jan 2015 14:44:54 -0500 Subject: tty: Remove external interface for tty_set_termios() tty_set_termios() is an internal helper intended for file scope use. UART drivers which are capable of driving the RTS pin must properly handle the tiocmset() method, regardless of termios settings. A failure to do so is a UART driver bug and should be fixed there. Do not use this interface to workaround UART driver bugs. Cc: Johan Hedberg Cc: Signed-off-by: Peter Hurley Acked-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index fe5623c9af71..358a337af598 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -491,7 +491,6 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b); -extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); -- cgit v1.2.3 From 035a61c314eb3dab5bcc5683afaf4d412689858a Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 23 Jan 2015 12:03:30 +0100 Subject: clk: Make clk API return per-user struct clk instances Moves clock state to struct clk_core, but takes care to change as little API as possible. struct clk_hw still has a pointer to a struct clk, which is the implementation's per-user clk instance, for backwards compatibility. The struct clk that clk_get_parent() returns isn't owned by the caller, but by the clock implementation, so the former shouldn't call clk_put() on it. Because some boards in mach-omap2 still register clocks statically, their clock registration had to be updated to take into account that the clock information is stored in struct clk_core now. Signed-off-by: Tomeu Vizoso Reviewed-by: Stephen Boyd Tested-by: Tony Lindgren Signed-off-by: Michael Turquette [mturquette@linaro.org: adapted clk_has_parent to struct clk_core applied OMAP3+ DPLL fix from Tero & Tony] --- include/linux/clk-private.h | 35 +++++++++++++++++++++++++++-------- include/linux/clk-provider.h | 12 +++++++----- 2 files changed, 34 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h index c5f40d07686c..ae55d99a2313 100644 --- a/include/linux/clk-private.h +++ b/include/linux/clk-private.h @@ -28,20 +28,20 @@ struct module; -struct clk { +struct clk_core { const char *name; const struct clk_ops *ops; struct clk_hw *hw; struct module *owner; - struct clk *parent; + struct clk_core *parent; const char **parent_names; - struct clk **parents; + struct clk_core **parents; u8 num_parents; u8 new_parent_index; unsigned long rate; unsigned long new_rate; - struct clk *new_parent; - struct clk *new_child; + struct clk_core *new_parent; + struct clk_core *new_child; unsigned long flags; unsigned int enable_count; unsigned int prepare_count; @@ -57,6 +57,12 @@ struct clk { struct kref ref; }; +struct clk { + struct clk_core *core; + const char *dev_id; + const char *con_id; +}; + /* * DOC: Basic clock implementations common to many platforms * @@ -69,6 +75,9 @@ struct clk { #define DEFINE_CLK(_name, _ops, _flags, _parent_names, \ _parents) \ static struct clk _name = { \ + .core = &_name##_core \ + }; \ + static struct clk_core _name##_core = { \ .name = #_name, \ .ops = &_ops, \ .hw = &_name##_hw.hw, \ @@ -81,9 +90,11 @@ struct clk { #define DEFINE_CLK_FIXED_RATE(_name, _flags, _rate, \ _fixed_rate_flags) \ static struct clk _name; \ + static struct clk_core _name##_core; \ static const char *_name##_parent_names[] = {}; \ static struct clk_fixed_rate _name##_hw = { \ .hw = { \ + .core = &_name##_core, \ .clk = &_name, \ }, \ .fixed_rate = _rate, \ @@ -96,14 +107,16 @@ struct clk { _flags, _reg, _bit_idx, \ _gate_flags, _lock) \ static struct clk _name; \ + static struct clk_core _name##_core; \ static const char *_name##_parent_names[] = { \ _parent_name, \ }; \ - static struct clk *_name##_parents[] = { \ + static struct clk_core *_name##_parents[] = { \ _parent_ptr, \ }; \ static struct clk_gate _name##_hw = { \ .hw = { \ + .core = &_name##_core, \ .clk = &_name, \ }, \ .reg = _reg, \ @@ -118,14 +131,16 @@ struct clk { _flags, _reg, _shift, _width, \ _divider_flags, _table, _lock) \ static struct clk _name; \ + static struct clk_core _name##_core; \ static const char *_name##_parent_names[] = { \ _parent_name, \ }; \ - static struct clk *_name##_parents[] = { \ + static struct clk_core *_name##_parents[] = { \ _parent_ptr, \ }; \ static struct clk_divider _name##_hw = { \ .hw = { \ + .core = &_name##_core, \ .clk = &_name, \ }, \ .reg = _reg, \ @@ -157,8 +172,10 @@ struct clk { _reg, _shift, _width, \ _mux_flags, _lock) \ static struct clk _name; \ + static struct clk_core _name##_core; \ static struct clk_mux _name##_hw = { \ .hw = { \ + .core = &_name##_core, \ .clk = &_name, \ }, \ .reg = _reg, \ @@ -174,14 +191,16 @@ struct clk { _parent_ptr, _flags, \ _mult, _div) \ static struct clk _name; \ + static struct clk_core _name##_core; \ static const char *_name##_parent_names[] = { \ _parent_name, \ }; \ - static struct clk *_name##_parents[] = { \ + static struct clk_core *_name##_parents[] = { \ _parent_ptr, \ }; \ static struct clk_fixed_factor _name##_hw = { \ .hw = { \ + .core = &_name##_core, \ .clk = &_name, \ }, \ .mult = _mult, \ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 0ed5bf2209ad..12f13b0673af 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -33,6 +33,7 @@ #define CLK_GET_ACCURACY_NOCACHE BIT(8) /* do not use the cached clk accuracy */ struct clk_hw; +struct clk_core; struct dentry; /** @@ -216,13 +217,17 @@ struct clk_init_data { * clk_foo and then referenced by the struct clk instance that uses struct * clk_foo's clk_ops * - * @clk: pointer to the struct clk instance that points back to this struct - * clk_hw instance + * @core: pointer to the struct clk_core instance that points back to this + * struct clk_hw instance + * + * @clk: pointer to the per-user struct clk instance that can be used to call + * into the clk API * * @init: pointer to struct clk_init_data that contains the init data shared * with the common clock framework. */ struct clk_hw { + struct clk_core *core; struct clk *clk; const struct clk_init_data *init; }; @@ -577,9 +582,6 @@ long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, /* * FIXME clock api without lock protection */ -int __clk_prepare(struct clk *clk); -void __clk_unprepare(struct clk *clk); -void __clk_reparent(struct clk *clk, struct clk *new_parent); unsigned long __clk_round_rate(struct clk *clk, unsigned long rate); struct of_device_id; -- cgit v1.2.3 From b09d6d99102504a929cfaba4cd0e07658d7f01d1 Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Thu, 29 Jan 2015 14:22:50 -0800 Subject: clk: remove clk-private.h Private clock framework data structures should be private, surprisingly. Now that all platforms and drivers have been updated to remove static initializations of struct clk and struct clk_core objects and all references to clk-private.h have been removed we can move the definitions of these structures into drivers/clk/clk.c and delete the header. Additionally the ugly DEFINE_CLK macros have been removed. Those were used for static definitions of struct clk objects. That practice is no longer allowed. Finally __clk_init is staticized as it is no longer declared in any header. Reviewed-by: Stephen Boyd Signed-off-by: Michael Turquette --- include/linux/clk-private.h | 237 -------------------------------------------- 1 file changed, 237 deletions(-) delete mode 100644 include/linux/clk-private.h (limited to 'include/linux') diff --git a/include/linux/clk-private.h b/include/linux/clk-private.h deleted file mode 100644 index ae55d99a2313..000000000000 --- a/include/linux/clk-private.h +++ /dev/null @@ -1,237 +0,0 @@ -/* - * linux/include/linux/clk-private.h - * - * Copyright (c) 2010-2011 Jeremy Kerr - * Copyright (C) 2011-2012 Linaro Ltd - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#ifndef __LINUX_CLK_PRIVATE_H -#define __LINUX_CLK_PRIVATE_H - -#include -#include -#include - -/* - * WARNING: Do not include clk-private.h from any file that implements struct - * clk_ops. Doing so is a layering violation! - * - * This header exists only to allow for statically initialized clock data. Any - * static clock data must be defined in a separate file from the logic that - * implements the clock operations for that same data. - */ - -#ifdef CONFIG_COMMON_CLK - -struct module; - -struct clk_core { - const char *name; - const struct clk_ops *ops; - struct clk_hw *hw; - struct module *owner; - struct clk_core *parent; - const char **parent_names; - struct clk_core **parents; - u8 num_parents; - u8 new_parent_index; - unsigned long rate; - unsigned long new_rate; - struct clk_core *new_parent; - struct clk_core *new_child; - unsigned long flags; - unsigned int enable_count; - unsigned int prepare_count; - unsigned long accuracy; - int phase; - struct hlist_head children; - struct hlist_node child_node; - struct hlist_node debug_node; - unsigned int notifier_count; -#ifdef CONFIG_DEBUG_FS - struct dentry *dentry; -#endif - struct kref ref; -}; - -struct clk { - struct clk_core *core; - const char *dev_id; - const char *con_id; -}; - -/* - * DOC: Basic clock implementations common to many platforms - * - * Each basic clock hardware type is comprised of a structure describing the - * clock hardware, implementations of the relevant callbacks in struct clk_ops, - * unique flags for that hardware type, a registration function and an - * alternative macro for static initialization - */ - -#define DEFINE_CLK(_name, _ops, _flags, _parent_names, \ - _parents) \ - static struct clk _name = { \ - .core = &_name##_core \ - }; \ - static struct clk_core _name##_core = { \ - .name = #_name, \ - .ops = &_ops, \ - .hw = &_name##_hw.hw, \ - .parent_names = _parent_names, \ - .num_parents = ARRAY_SIZE(_parent_names), \ - .parents = _parents, \ - .flags = _flags | CLK_IS_BASIC, \ - } - -#define DEFINE_CLK_FIXED_RATE(_name, _flags, _rate, \ - _fixed_rate_flags) \ - static struct clk _name; \ - static struct clk_core _name##_core; \ - static const char *_name##_parent_names[] = {}; \ - static struct clk_fixed_rate _name##_hw = { \ - .hw = { \ - .core = &_name##_core, \ - .clk = &_name, \ - }, \ - .fixed_rate = _rate, \ - .flags = _fixed_rate_flags, \ - }; \ - DEFINE_CLK(_name, clk_fixed_rate_ops, _flags, \ - _name##_parent_names, NULL); - -#define DEFINE_CLK_GATE(_name, _parent_name, _parent_ptr, \ - _flags, _reg, _bit_idx, \ - _gate_flags, _lock) \ - static struct clk _name; \ - static struct clk_core _name##_core; \ - static const char *_name##_parent_names[] = { \ - _parent_name, \ - }; \ - static struct clk_core *_name##_parents[] = { \ - _parent_ptr, \ - }; \ - static struct clk_gate _name##_hw = { \ - .hw = { \ - .core = &_name##_core, \ - .clk = &_name, \ - }, \ - .reg = _reg, \ - .bit_idx = _bit_idx, \ - .flags = _gate_flags, \ - .lock = _lock, \ - }; \ - DEFINE_CLK(_name, clk_gate_ops, _flags, \ - _name##_parent_names, _name##_parents); - -#define _DEFINE_CLK_DIVIDER(_name, _parent_name, _parent_ptr, \ - _flags, _reg, _shift, _width, \ - _divider_flags, _table, _lock) \ - static struct clk _name; \ - static struct clk_core _name##_core; \ - static const char *_name##_parent_names[] = { \ - _parent_name, \ - }; \ - static struct clk_core *_name##_parents[] = { \ - _parent_ptr, \ - }; \ - static struct clk_divider _name##_hw = { \ - .hw = { \ - .core = &_name##_core, \ - .clk = &_name, \ - }, \ - .reg = _reg, \ - .shift = _shift, \ - .width = _width, \ - .flags = _divider_flags, \ - .table = _table, \ - .lock = _lock, \ - }; \ - DEFINE_CLK(_name, clk_divider_ops, _flags, \ - _name##_parent_names, _name##_parents); - -#define DEFINE_CLK_DIVIDER(_name, _parent_name, _parent_ptr, \ - _flags, _reg, _shift, _width, \ - _divider_flags, _lock) \ - _DEFINE_CLK_DIVIDER(_name, _parent_name, _parent_ptr, \ - _flags, _reg, _shift, _width, \ - _divider_flags, NULL, _lock) - -#define DEFINE_CLK_DIVIDER_TABLE(_name, _parent_name, \ - _parent_ptr, _flags, _reg, \ - _shift, _width, _divider_flags, \ - _table, _lock) \ - _DEFINE_CLK_DIVIDER(_name, _parent_name, _parent_ptr, \ - _flags, _reg, _shift, _width, \ - _divider_flags, _table, _lock) \ - -#define DEFINE_CLK_MUX(_name, _parent_names, _parents, _flags, \ - _reg, _shift, _width, \ - _mux_flags, _lock) \ - static struct clk _name; \ - static struct clk_core _name##_core; \ - static struct clk_mux _name##_hw = { \ - .hw = { \ - .core = &_name##_core, \ - .clk = &_name, \ - }, \ - .reg = _reg, \ - .shift = _shift, \ - .mask = BIT(_width) - 1, \ - .flags = _mux_flags, \ - .lock = _lock, \ - }; \ - DEFINE_CLK(_name, clk_mux_ops, _flags, _parent_names, \ - _parents); - -#define DEFINE_CLK_FIXED_FACTOR(_name, _parent_name, \ - _parent_ptr, _flags, \ - _mult, _div) \ - static struct clk _name; \ - static struct clk_core _name##_core; \ - static const char *_name##_parent_names[] = { \ - _parent_name, \ - }; \ - static struct clk_core *_name##_parents[] = { \ - _parent_ptr, \ - }; \ - static struct clk_fixed_factor _name##_hw = { \ - .hw = { \ - .core = &_name##_core, \ - .clk = &_name, \ - }, \ - .mult = _mult, \ - .div = _div, \ - }; \ - DEFINE_CLK(_name, clk_fixed_factor_ops, _flags, \ - _name##_parent_names, _name##_parents); - -/** - * __clk_init - initialize the data structures in a struct clk - * @dev: device initializing this clk, placeholder for now - * @clk: clk being initialized - * - * Initializes the lists in struct clk, queries the hardware for the - * parent and rate and sets them both. - * - * Any struct clk passed into __clk_init must have the following members - * populated: - * .name - * .ops - * .hw - * .parent_names - * .num_parents - * .flags - * - * It is not necessary to call clk_register if __clk_init is used directly with - * statically initialized clock data. - * - * Returns 0 on success, otherwise an error code. - */ -int __clk_init(struct device *dev, struct clk *clk); - -#endif /* CONFIG_COMMON_CLK */ -#endif /* CLK_PRIVATE_H */ -- cgit v1.2.3 From 1c8e600440c7f5036bd9a94526d01e9c7cb68dca Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 23 Jan 2015 12:03:31 +0100 Subject: clk: Add rate constraints to clocks Adds a way for clock consumers to set maximum and minimum rates. This can be used for thermal drivers to set minimum rates, or by misc. drivers to set maximum rates to assure a minimum performance level. Changes the signature of the determine_rate callback by adding the parameters min_rate and max_rate. Signed-off-by: Tomeu Vizoso Signed-off-by: Stephen Boyd [sboyd@codeaurora.org: set req_rate in __clk_init] Signed-off-by: Michael Turquette [mturquette@linaro.org: min/max rate for sun6i_ahb1_clk_determine_rate migrated clk-private.h changes to clk.c] --- include/linux/clk-provider.h | 17 ++++++++++++++--- include/linux/clk.h | 28 ++++++++++++++++++++++++++++ include/linux/clk/ti.h | 4 ++++ 3 files changed, 46 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 12f13b0673af..17dd6e9439d1 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -175,9 +175,12 @@ struct clk_ops { unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate); - long (*determine_rate)(struct clk_hw *hw, unsigned long rate, - unsigned long *best_parent_rate, - struct clk_hw **best_parent_hw); + long (*determine_rate)(struct clk_hw *hw, + unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, + unsigned long *best_parent_rate, + struct clk_hw **best_parent_hw); int (*set_parent)(struct clk_hw *hw, u8 index); u8 (*get_parent)(struct clk_hw *hw); int (*set_rate)(struct clk_hw *hw, unsigned long rate, @@ -573,9 +576,17 @@ bool __clk_is_prepared(struct clk *clk); bool __clk_is_enabled(struct clk *clk); struct clk *__clk_lookup(const char *name); long __clk_mux_determine_rate(struct clk_hw *hw, unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_p); +unsigned long __clk_determine_rate(struct clk_hw *core, + unsigned long rate, + unsigned long min_rate, + unsigned long max_rate); long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_p); diff --git a/include/linux/clk.h b/include/linux/clk.h index ba7e9eda4347..8381bbfbc308 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -313,6 +313,34 @@ int clk_set_rate(struct clk *clk, unsigned long rate); */ bool clk_has_parent(struct clk *clk, struct clk *parent); +/** + * clk_set_rate_range - set a rate range for a clock source + * @clk: clock source + * @min: desired minimum clock rate in Hz, inclusive + * @max: desired maximum clock rate in Hz, inclusive + * + * Returns success (0) or negative errno. + */ +int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max); + +/** + * clk_set_min_rate - set a minimum clock rate for a clock source + * @clk: clock source + * @rate: desired minimum clock rate in Hz, inclusive + * + * Returns success (0) or negative errno. + */ +int clk_set_min_rate(struct clk *clk, unsigned long rate); + +/** + * clk_set_max_rate - set a maximum clock rate for a clock source + * @clk: clock source + * @rate: desired maximum clock rate in Hz, inclusive + * + * Returns success (0) or negative errno. + */ +int clk_set_max_rate(struct clk *clk, unsigned long rate); + /** * clk_set_parent - set the parent clock source for this clock * @clk: clock source diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 310122dcd9b5..0eac65054283 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -271,6 +271,8 @@ int omap3_noncore_dpll_set_rate_and_parent(struct clk_hw *hw, u8 index); long omap3_noncore_dpll_determine_rate(struct clk_hw *hw, unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_clk); unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw, @@ -280,6 +282,8 @@ long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw, unsigned long *parent_rate); long omap4_dpll_regm4xen_determine_rate(struct clk_hw *hw, unsigned long rate, + unsigned long min_rate, + unsigned long max_rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_clk); u8 omap2_init_dpll_parent(struct clk_hw *hw); -- cgit v1.2.3 From 366e41d9774d7010cb63112b6db2fce6dc7809c0 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Sat, 31 Jan 2015 10:40:13 -0500 Subject: ipv6: pull cork initialization into its own function. Pull IPv6 cork initialization into its own function that can be re-used. IPv6 specific cork data did not have an explicit data structure. This patch creats eone so that just ipv6 cork data can be as arguemts. Also, since IPv6 tries to save the flow label into inet_cork_full tructure, pass the full cork. Adjust ip6_cork_release() to take cork data structures. Signed-off-by: Vladislav Yasevich Signed-off-by: David S. Miller --- include/linux/ipv6.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2805062c013f..4d5169f5d7d1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -125,6 +125,12 @@ struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; +struct inet6_cork { + struct ipv6_txoptions *opt; + u8 hop_limit; + u8 tclass; +}; + /** * struct ipv6_pinfo - ipv6 private area * @@ -217,11 +223,7 @@ struct ipv6_pinfo { struct ipv6_txoptions *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; - struct { - struct ipv6_txoptions *opt; - u8 hop_limit; - u8 tclass; - } cork; + struct inet6_cork cork; }; /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ -- cgit v1.2.3 From f0b66a2cf68ed3613fe72fe01ed309f998e2bbb3 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 3 Feb 2015 09:29:52 -0600 Subject: PCI: Add pci_device_to_OF_node() stub for !CONFIG_OF Add a stub for pci_device_to_OF_node() so drivers don't need to use #ifdef CONFIG_OF around calls to it. Signed-off-by: Kevin Hao Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..fbb5795a8d86 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1847,6 +1847,8 @@ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } static inline void pci_set_bus_of_node(struct pci_bus *bus) { } static inline void pci_release_bus_of_node(struct pci_bus *bus) { } +static inline struct device_node * +pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } #endif /* CONFIG_OF */ #ifdef CONFIG_EEH -- cgit v1.2.3 From 6793a30a0646d2cc269e66782ca30c6025c92e1f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 3 Feb 2015 17:59:32 +0100 Subject: clk: omap: compile legacy omap3 clocks conditionally The 'ARM: OMAP3: legacy clock data move under clk driver' patch series causes build errors when CONFIG_OMAP3 is not set: drivers/clk/ti/dpll.c: In function 'ti_clk_register_dpll': drivers/clk/ti/dpll.c:199:31: error: 'omap3_dpll_ck_ops' undeclared (first use in this function) const struct clk_ops *ops = &omap3_dpll_ck_ops; ^ drivers/clk/ti/dpll.c:199:31: note: each undeclared identifier is reported only once for each function it appears in drivers/clk/ti/dpll.c:259:10: error: 'omap3_dpll_per_ck_ops' undeclared (first use in this function) ops = &omap3_dpll_per_ck_ops; ^ drivers/built-in.o: In function `ti_clk_register_gate': drivers/clk/ti/gate.c:179: undefined reference to `clkhwops_omap3430es2_dss_usbhost_wait' drivers/clk/ti/gate.c:179: undefined reference to `clkhwops_am35xx_ipss_module_wait' -in.o: In function `ti_clk_register_interface': drivers/clk/ti/interface.c:100: undefined reference to `clkhwops_omap3430es2_iclk_hsotgusb_wait' drivers/clk/ti/interface.c:100: undefined reference to `clkhwops_omap3430es2_iclk_dss_usbhost_wait' drivers/clk/ti/interface.c:100: undefined reference to `clkhwops_omap3430es2_iclk_ssi_wait' drivers/clk/ti/interface.c:100: undefined reference to `clkhwops_am35xx_ipss_wait' drivers/built-in.o: In function `ti_clk_register_composite': :(.text+0x3da768): undefined reference to `ti_clk_build_component_gate' In order to fix that problem, this patch makes the omap3 legacy code compiled only when both CONFIG_OMAP3 and CONFIG_ATAGS are set. Signed-off-by: Arnd Bergmann Acked-by: Tony Lindgren Signed-off-by: Michael Turquette --- include/linux/clk/ti.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 0eac65054283..67844003493d 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -360,9 +360,17 @@ extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait; extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait; extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait; +#ifdef CONFIG_ATAGS int omap3430_clk_legacy_init(void); int omap3430es1_clk_legacy_init(void); int omap36xx_clk_legacy_init(void); int am35xx_clk_legacy_init(void); +#else +static inline int omap3430_clk_legacy_init(void) { return -ENXIO; } +static inline int omap3430es1_clk_legacy_init(void) { return -ENXIO; } +static inline int omap36xx_clk_legacy_init(void) { return -ENXIO; } +static inline int am35xx_clk_legacy_init(void) { return -ENXIO; } +#endif + #endif -- cgit v1.2.3 From 1a04c6e1a26a43305fe124a0978a3e4be861af89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Fri, 30 May 2014 18:15:57 +0800 Subject: nfsv3: introduce nfs3_set_ds_client The flexfiles layout wants to create DS connection over NFSv3. Add nfs3_set_ds_client to allow that to happen. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- include/linux/nfs_fs_sb.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index ddea982355f3..5e1273d4de14 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -77,10 +77,6 @@ struct nfs_client { /* Client owner identifier */ const char * cl_owner_id; - /* Our own IP address, as a null-terminated string. - * This is used to generate the mv0 callback address. - */ - char cl_ipaddr[48]; u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; unsigned long cl_mig_gen; @@ -108,6 +104,11 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ #endif /* CONFIG_NFS_V4 */ + /* Our own IP address, as a null-terminated string. + * This is used to generate the mv0 callback address. + */ + char cl_ipaddr[48]; + #ifdef CONFIG_NFS_FSCACHE struct fscache_cookie *fscache; /* client index cache cookie */ #endif -- cgit v1.2.3 From abde71f4d3c027a30f8d725e1e22001313b4481a Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Mon, 9 Jun 2014 13:12:20 -0700 Subject: pnfs: Add nfs_rpc_ops in calls to nfs_initiate_pgio Signed-off-by: Tom Haynes --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 6c3e06ee2fb7..4c3aa809ab95 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -69,6 +69,7 @@ struct nfs_rw_ops { struct inode *); void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *); void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *, + const struct nfs_rpc_ops *, struct rpc_task_setup *, int); }; -- cgit v1.2.3 From 840210fc4872bcbc17ab4f435f28021dce9d0aff Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 24 Jun 2014 10:59:52 -0400 Subject: sunrpc: add rpc_count_iostats_idx Add a call to tally stats for a task under a different statsidx than what's contained in the task structure. This is needed to properly account for pnfs reads/writes when the DS nfs version != the MDS version. Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes --- include/linux/sunrpc/metrics.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index eecb5a71e6c0..89f2ca178873 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -79,6 +79,8 @@ struct rpc_clnt; struct rpc_iostats * rpc_alloc_iostats(struct rpc_clnt *); void rpc_count_iostats(const struct rpc_task *, struct rpc_iostats *); +void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *); void rpc_print_iostats(struct seq_file *, struct rpc_clnt *); void rpc_free_iostats(struct rpc_iostats *); -- cgit v1.2.3 From aabff4ddcac0d36dd26546f5b905c27682e7bf89 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 27 Aug 2014 10:47:14 +0800 Subject: nfs: save server READ/WRITE/COMMIT status Flexfiles layout would want to use them to report DS IO status. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 467c84efb596..962f461c065d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -513,6 +513,7 @@ struct nfs_pgio_res { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; __u32 count; + __u32 op_status; int eof; /* used by read */ struct nfs_writeverf * verf; /* used by write */ const struct nfs_server *server; /* used by write */ @@ -532,6 +533,7 @@ struct nfs_commitargs { struct nfs_commitres { struct nfs4_sequence_res seq_res; + __u32 op_status; struct nfs_fattr *fattr; struct nfs_writeverf *verf; const struct nfs_server *server; -- cgit v1.2.3 From 4579d6b897ee1b2557517fd536fb17eeb13481ad Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 6 Sep 2014 00:53:21 +0800 Subject: nfs41: pass iomode through layoutreturn args So that it is possible to return a specific iomode layouts. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 962f461c065d..4fd7793d45d1 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,6 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; + enum pnfs_iomode iomode; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From 2176bf4269a37a7742230ed6c91668241bfe1b2b Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Wed, 10 Sep 2014 15:44:18 -0400 Subject: nfs: introduce pg_cleanup op for pgio descriptors Add a new operation to nfs_pageio_ops that is called on nfs_pageio_complete. Signed-off-by: Weston Andros Adamson --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 4c3aa809ab95..479c566c4ddc 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,7 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; struct nfs_rw_ops { -- cgit v1.2.3 From 6cccbb6f52dceec5f4faed8846ac05ae830640e6 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Tue, 16 Sep 2014 17:35:51 -0400 Subject: nfs: rename pgio header ds_idx to ds_commit_idx 'ds_commit_idx' is a better name - it is used to select the right commit bucket for pnfs. Signed-off-by: Weston Andros Adamson --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 4fd7793d45d1..5bc99f04a550 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1328,7 +1328,7 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_idx; /* ds index if ds_clp is set */ + int ds_commit_idx; /* ds index if ds_clp is set */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From a7d42ddb3099727f58366fa006f850a219cce6c8 Mon Sep 17 00:00:00 2001 From: Weston Andros Adamson Date: Fri, 19 Sep 2014 10:55:07 -0400 Subject: nfs: add mirroring support to pgio layer This patch adds mirrored write support to the pgio layer. The default is to use one mirror, but pgio callers may define callbacks to change this to any value up to the (arbitrarily selected) limit of 16. The basic idea is to break out members of nfs_pageio_descriptor that cannot be shared between mirrored DSes and put them in a new structure. Signed-off-by: Weston Andros Adamson --- include/linux/nfs_page.h | 20 +++++++++++++++++--- include/linux/nfs_xdr.h | 1 + 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 479c566c4ddc..3eb072dbce83 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -58,6 +58,8 @@ struct nfs_pageio_ops { size_t (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *); int (*pg_doio)(struct nfs_pageio_descriptor *); + unsigned int (*pg_get_mirror_count)(struct nfs_pageio_descriptor *, + struct nfs_page *); void (*pg_cleanup)(struct nfs_pageio_descriptor *); }; @@ -74,15 +76,17 @@ struct nfs_rw_ops { struct rpc_task_setup *, int); }; -struct nfs_pageio_descriptor { +struct nfs_pgio_mirror { struct list_head pg_list; unsigned long pg_bytes_written; size_t pg_count; size_t pg_bsize; unsigned int pg_base; - unsigned char pg_moreio : 1, - pg_recoalesce : 1; + unsigned char pg_recoalesce : 1; +}; +struct nfs_pageio_descriptor { + unsigned char pg_moreio : 1; struct inode *pg_inode; const struct nfs_pageio_ops *pg_ops; const struct nfs_rw_ops *pg_rw_ops; @@ -93,8 +97,18 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_direct_req *pg_dreq; void *pg_layout_private; + unsigned int pg_bsize; /* default bsize for mirrors */ + + u32 pg_mirror_count; + struct nfs_pgio_mirror *pg_mirrors; + struct nfs_pgio_mirror pg_mirrors_static[1]; + struct nfs_pgio_mirror *pg_mirrors_dynamic; + u32 pg_mirror_idx; /* current mirror */ }; +/* arbitrarily selected limit to number of mirrors */ +#define NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX 16 + #define NFS_WBACK_BUSY(req) (test_bit(PG_BUSY,&(req)->wb_flags)) extern struct nfs_page *nfs_create_request(struct nfs_open_context *ctx, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5bc99f04a550..6400a1e01aa4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1329,6 +1329,7 @@ struct nfs_pgio_header { struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ int ds_commit_idx; /* ds index if ds_clp is set */ + int pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { -- cgit v1.2.3 From 15eb67c15342d212b0c8a540b6d6bd2dfad52a63 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Mon, 17 Nov 2014 09:30:36 +0800 Subject: nfs41: add range to layoutreturn args So that callers can specify which range to return. Signed-off-by: Peng Tao Signed-off-by: Tom Haynes --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6400a1e01aa4..363792356d25 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -293,7 +293,7 @@ struct nfs4_layoutreturn_args { struct nfs4_sequence_args seq_args; struct pnfs_layout_hdr *layout; struct inode *inode; - enum pnfs_iomode iomode; + struct pnfs_layout_range range; nfs4_stateid stateid; __u32 layout_type; }; -- cgit v1.2.3 From d67ae825a59d639e4d8b82413af84d854617a87e Mon Sep 17 00:00:00 2001 From: Tom Haynes Date: Thu, 11 Dec 2014 17:02:04 -0500 Subject: pnfs/flexfiles: Add the FlexFile Layout Driver The flexfile layout is a new layout that extends the file layout. It is currently being drafted as a specification at https://datatracker.ietf.org/doc/draft-ietf-nfsv4-layout-types/ Signed-off-by: Weston Andros Adamson Signed-off-by: Tom Haynes Signed-off-by: Tao Peng --- include/linux/nfs4.h | 1 + include/linux/nfs_idmap.h | 2 ++ include/linux/sunrpc/metrics.h | 2 ++ 3 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 022b761dbf0a..de7c91ca427e 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -516,6 +516,7 @@ enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, LAYOUT_BLOCK_VOLUME = 3, + LAYOUT_FLEX_FILES = 4, }; /* used for both layout return and recall */ diff --git a/include/linux/nfs_idmap.h b/include/linux/nfs_idmap.h index 0f4b79da6584..333844e38f66 100644 --- a/include/linux/nfs_idmap.h +++ b/include/linux/nfs_idmap.h @@ -73,5 +73,7 @@ int nfs_map_group_to_gid(const struct nfs_server *, const char *, size_t, kgid_t int nfs_map_uid_to_name(const struct nfs_server *, kuid_t, char *, size_t); int nfs_map_gid_to_group(const struct nfs_server *, kgid_t, char *, size_t); +int nfs_map_string_to_numeric(const char *name, size_t namelen, __u32 *res); + extern unsigned int nfs_idmap_cache_timeout; #endif /* NFS_IDMAP_H */ diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 89f2ca178873..7e61a17030a4 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -89,6 +89,8 @@ void rpc_free_iostats(struct rpc_iostats *); static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; } static inline void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) {} +static inline void rpc_count_iostats_metrics(const struct rpc_task *, + struct rpc_iostats *) {} static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {} static inline void rpc_free_iostats(struct rpc_iostats *stats) {} -- cgit v1.2.3 From 344d635b9a41b19837ccf8083a99ea688027019c Mon Sep 17 00:00:00 2001 From: Brad Griffis Date: Tue, 3 Feb 2015 11:44:12 -0800 Subject: Input: ti_am335x_tsc - remove udelay in interrupt handler TSC interrupt handler had udelay to avoid reporting of false pen-up interrupt to user space. This patch implements workaround suggesting in Advisory 1.0.31 of silicon errata for am335x, thus eliminating udelay and touchscreen lag. This also improves performance of touchscreen and eliminates sudden jump of cursor at touch release. IDLECONFIG and CHARGECONFIG registers are to be configured with same values in order to eliminate false pen-up events. This workaround may result in false pen-down to be detected, hence considerable charge step delay needs to be added. The charge delay is set to 0xB000 (in terms of ADC clock cycles) by default. TSC steps are disabled at the end of every sampling cycle and EOS bit is set. Once the EOS bit is set, the TSC steps need to be re-enabled to begin next sampling cycle. Signed-off-by: Brad Griffis [vigneshr@ti.com: Ported the patch from v3.12 to v3.19rc1] Signed-off-by: Vignesh R Signed-off-by: Dmitry Torokhov --- include/linux/mfd/ti_am335x_tscadc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index e2e70053470e..3f4e994ace2b 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -52,6 +52,7 @@ /* IRQ enable */ #define IRQENB_HW_PEN BIT(0) +#define IRQENB_EOS BIT(1) #define IRQENB_FIFO0THRES BIT(2) #define IRQENB_FIFO0OVRRUN BIT(3) #define IRQENB_FIFO0UNDRFLW BIT(4) @@ -107,7 +108,7 @@ /* Charge delay */ #define CHARGEDLY_OPEN_MASK (0x3FFFF << 0) #define CHARGEDLY_OPEN(val) ((val) << 0) -#define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(1) +#define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ #define CNTRLREG_TSCSSENB BIT(0) -- cgit v1.2.3 From a49170b552423a3e85fc4f0d778c707402ee4863 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:42:58 +0800 Subject: ACPI: Return translation offset when parsing ACPI address space resources Change function acpi_dev_resource_address_space() and acpi_dev_resource_ext_address_space() to return address space translation offset. It's based on a patch from Yinghai Lu . Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d459cd17b477..be9eaee8f4ae 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -285,12 +285,17 @@ extern int pnpacpi_disabled; #define PXM_INVAL (-1) +struct resource_win { + struct resource res; + resource_size_t offset; +}; + bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, - struct resource *res); + struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -- cgit v1.2.3 From 93286f4798590e711aa395503401f8632fb74f9a Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:43:00 +0800 Subject: ACPI: Add field offset to struct resource_list_entry Add field offset to struct resource_list_entry to host address space translation offset so it could be used to represent bridge resources. Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index be9eaee8f4ae..21dac3cb62d2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -303,6 +303,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource_list_entry { struct list_head node; struct resource res; + resource_size_t offset; }; void acpi_dev_free_resource_list(struct list_head *list); -- cgit v1.2.3 From 62d1141ff34e35de496ba06491c8e854b23b3f3e Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 2 Feb 2015 10:43:01 +0800 Subject: ACPI: Introduce helper function acpi_dev_filter_resource_type() Introduce helper function acpi_dev_filter_resource_type(), which may be used by acpi_dev_get_resources() to filer out resource based on resource type. Signed-off-by: Jiang Liu Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 21dac3cb62d2..e818decb631f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -310,6 +310,14 @@ void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); +int acpi_dev_filter_resource_type(struct acpi_resource *ares, + unsigned long types); + +static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, + void *arg) +{ + return acpi_dev_filter_resource_type(ares, (unsigned long)arg); +} int acpi_check_resource_conflict(const struct resource *res); -- cgit v1.2.3 From 03a9a42a1a7e5b3e7919ddfacc1d1cc81882a955 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 18:12:28 -0500 Subject: SUNRPC: NULL utsname dereference on NFS umount during namespace cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix an Oopsable condition when nsm_mon_unmon is called as part of the namespace cleanup, which now apparently happens after the utsname has been freed. Link: http://lkml.kernel.org/r/20150125220604.090121ae@neptune.home Reported-by: Bruno Prémont Cc: stable@vger.kernel.org # 3.18 Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index d86acc63b25f..598ba80ec30c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -57,7 +57,7 @@ struct rpc_clnt { const struct rpc_timeout *cl_timeout; /* Timeout strategy */ int cl_nodelen; /* nodename length */ - char cl_nodename[UNX_MAXNODENAME]; + char cl_nodename[UNX_MAXNODENAME+1]; struct rpc_pipe_dir_head cl_pipedir_objects; struct rpc_clnt * cl_parent; /* Points to parent of clones */ struct rpc_rtt cl_rtt_default; @@ -112,6 +112,7 @@ struct rpc_create_args { struct sockaddr *saddress; const struct rpc_timeout *timeout; const char *servername; + const char *nodename; const struct rpc_program *program; u32 prognumber; /* overrides program->number */ u32 version; -- cgit v1.2.3 From c1dbe2fbb33ef425a81e1a7cffd17c113c87cdbc Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 27 Jan 2015 21:13:39 +0100 Subject: PM / Domains: Remove reference counting for the generic_pm_domain_data The reference counting was needed when genpd supported PM domain device callbacks. Since this option has been removed, let's also remove the reference counting of the struct generic_pm_domain_data. Signed-off-by: Ulf Hansson Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index ed607760fc20..e160a0bba28d 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -114,7 +114,6 @@ struct generic_pm_domain_data { struct gpd_timing_data td; struct notifier_block nb; struct mutex lock; - unsigned int refcount; int need_restore; }; -- cgit v1.2.3 From c0356db7d1b66840882744cbd9d9c5960b2d88c7 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 27 Jan 2015 21:13:42 +0100 Subject: PM / Domains: Eliminate the mutex for the generic_pm_domain_data While adding devices to their PM domains, dev_pm_qos_add_notifier() was invoked while allocating the generic_pm_domain_data for the device. Since the generic_pm_domain_data's device pointer will be assigned after allocation, the ->genpd_dev_pm_qos_notifier() callback could be called prior having a valid pointer to the device. Similar scenario existed while removing a device from a genpd. To cope with these scenarios a mutex was used to protect the pointer to the device. By re-order the sequence for when dev_pm_qos_add|remove_notifier() are invoked, we make sure the ->genpd_dev_pm_qos_notifier() callback are always called with a valid device pointer available. In this way, we eliminate the need for protecting the pointer and thus we can remove the mutex from the struct generic_pm_domain_data. Signed-off-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index e160a0bba28d..080e778118ba 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -113,7 +113,6 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; - struct mutex lock; int need_restore; }; -- cgit v1.2.3 From 1e95e3b2da424db68d0a465273f1901a990c6277 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 29 Jan 2015 18:39:05 +0100 Subject: PM: Convert dev_pm_put_subsys_data() into a void function Clients using the dev_pm_put_subsys_data() API isn't interested of a return value. They care only of decreasing a reference to the device's pm_subsys_data. So, let's convert the API to a void function, which anyway seems like reasonable thing to do. Signed-off-by: Ulf Hansson Acked-by: Geert Uytterhoeven Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8b5976364619..e2f1be6dd9dd 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -597,7 +597,7 @@ struct dev_pm_info { extern void update_pm_runtime_accounting(struct device *dev); extern int dev_pm_get_subsys_data(struct device *dev); -extern int dev_pm_put_subsys_data(struct device *dev); +extern void dev_pm_put_subsys_data(struct device *dev); /* * Power domains provide callbacks that are executed during system suspend, -- cgit v1.2.3 From 63e144c9d6ffa791c1402f4ee4551c1b9f5a336a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 15 Jan 2015 14:42:27 +0300 Subject: ti-st: clean up data types (fix harmless memory corruption) The big issue here is: of_property_read_u32(np, "flow_cntrl", (u32 *)&dt_pdata->flow_cntrl); "->flow_cntrl" is a char so when we write a 32 bit number to it then it corrupts past the end of the char. It's probably hard to notice because the struct has padding so the code works on little endian systems. But on a big endian system the code would fail and on a 64 bit, big endian systems then "nshutdown_gpio" and "baud_rate" would be buggy as well. Signed-off-by: Dan Carpenter Signed-off-by: Greg Kroah-Hartman --- include/linux/ti_wilink_st.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index 9072d9f95cff..c78dcfeaf25f 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -262,7 +262,7 @@ struct kim_data_s { struct completion kim_rcvd, ldisc_installed; char resp_buffer[30]; const struct firmware *fw_entry; - long nshutdown; + unsigned nshutdown; unsigned long rx_state; unsigned long rx_count; struct sk_buff *rx_skb; @@ -270,8 +270,8 @@ struct kim_data_s { struct chip_version version; unsigned char ldisc_install; unsigned char dev_name[UART_DEV_NAME_LEN + 1]; - unsigned char flow_cntrl; - unsigned long baud_rate; + unsigned flow_cntrl; + unsigned baud_rate; }; /** @@ -437,10 +437,10 @@ struct gps_event_hdr { * */ struct ti_st_plat_data { - long nshutdown_gpio; + u32 nshutdown_gpio; unsigned char dev_name[UART_DEV_NAME_LEN]; /* uart name */ - unsigned char flow_cntrl; /* flow control flag */ - unsigned long baud_rate; + u32 flow_cntrl; /* flow control flag */ + u32 baud_rate; int (*suspend)(struct platform_device *, pm_message_t); int (*resume)(struct platform_device *); int (*chip_enable) (struct kim_data_s *); -- cgit v1.2.3 From 2cbf7fe2d5d32a4747c1f8ad163e886dccad930c Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 3 Feb 2015 13:18:55 +0000 Subject: i2o: move to staging The I2O layer deals with a technology that to say the least didn't catch on in the market. The only relevant products are some of the AMI MegaRAID - which supported I2O and its native mode (The native mode is faster and runs on Linux), an obscure crypto ethernet card that's now so many years out of date nobody would use it, the old DPT controllers, which speak their own dialect and have their own driver - and ermm.. thats about it. We also know the code isn't in good shape as recently a patch was proposed and queried as buggy, which in turn showed the existing code was broken already by prior "clean up" and nobody had noticed that either. It's coding style robot code nothing more. Like some forgotten corridor cleaned relentlessly by a lost Roomba but where no user has trodden in years. Move it to staging and then to /dev/null. The headers remain as they are shared with dpt_i2o. Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/i2o.h | 988 ---------------------------------------------------- 1 file changed, 988 deletions(-) delete mode 100644 include/linux/i2o.h (limited to 'include/linux') diff --git a/include/linux/i2o.h b/include/linux/i2o.h deleted file mode 100644 index d23c3c20b201..000000000000 --- a/include/linux/i2o.h +++ /dev/null @@ -1,988 +0,0 @@ -/* - * I2O kernel space accessible structures/APIs - * - * (c) Copyright 1999, 2000 Red Hat Software - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - ************************************************************************* - * - * This header file defined the I2O APIs/structures for use by - * the I2O kernel modules. - * - */ - -#ifndef _I2O_H -#define _I2O_H - -#include - -/* How many different OSM's are we allowing */ -#define I2O_MAX_DRIVERS 8 - -#include -#include -#include -#include -#include -#include /* work_struct */ -#include -#include -#include -#include /* Needed for MUTEX init macros */ - -#include - -/* message queue empty */ -#define I2O_QUEUE_EMPTY 0xffffffff - -/* - * Cache strategies - */ - -/* The NULL strategy leaves everything up to the controller. This tends to be a - * pessimal but functional choice. - */ -#define CACHE_NULL 0 -/* Prefetch data when reading. We continually attempt to load the next 32 sectors - * into the controller cache. - */ -#define CACHE_PREFETCH 1 -/* Prefetch data when reading. We sometimes attempt to load the next 32 sectors - * into the controller cache. When an I/O is less <= 8K we assume its probably - * not sequential and don't prefetch (default) - */ -#define CACHE_SMARTFETCH 2 -/* Data is written to the cache and then out on to the disk. The I/O must be - * physically on the medium before the write is acknowledged (default without - * NVRAM) - */ -#define CACHE_WRITETHROUGH 17 -/* Data is written to the cache and then out on to the disk. The controller - * is permitted to write back the cache any way it wants. (default if battery - * backed NVRAM is present). It can be useful to set this for swap regardless of - * battery state. - */ -#define CACHE_WRITEBACK 18 -/* Optimise for under powered controllers, especially on RAID1 and RAID0. We - * write large I/O's directly to disk bypassing the cache to avoid the extra - * memory copy hits. Small writes are writeback cached - */ -#define CACHE_SMARTBACK 19 -/* Optimise for under powered controllers, especially on RAID1 and RAID0. We - * write large I/O's directly to disk bypassing the cache to avoid the extra - * memory copy hits. Small writes are writethrough cached. Suitable for devices - * lacking battery backup - */ -#define CACHE_SMARTTHROUGH 20 - -/* - * Ioctl structures - */ - -#define BLKI2OGRSTRAT _IOR('2', 1, int) -#define BLKI2OGWSTRAT _IOR('2', 2, int) -#define BLKI2OSRSTRAT _IOW('2', 3, int) -#define BLKI2OSWSTRAT _IOW('2', 4, int) - -/* - * I2O Function codes - */ - -/* - * Executive Class - */ -#define I2O_CMD_ADAPTER_ASSIGN 0xB3 -#define I2O_CMD_ADAPTER_READ 0xB2 -#define I2O_CMD_ADAPTER_RELEASE 0xB5 -#define I2O_CMD_BIOS_INFO_SET 0xA5 -#define I2O_CMD_BOOT_DEVICE_SET 0xA7 -#define I2O_CMD_CONFIG_VALIDATE 0xBB -#define I2O_CMD_CONN_SETUP 0xCA -#define I2O_CMD_DDM_DESTROY 0xB1 -#define I2O_CMD_DDM_ENABLE 0xD5 -#define I2O_CMD_DDM_QUIESCE 0xC7 -#define I2O_CMD_DDM_RESET 0xD9 -#define I2O_CMD_DDM_SUSPEND 0xAF -#define I2O_CMD_DEVICE_ASSIGN 0xB7 -#define I2O_CMD_DEVICE_RELEASE 0xB9 -#define I2O_CMD_HRT_GET 0xA8 -#define I2O_CMD_ADAPTER_CLEAR 0xBE -#define I2O_CMD_ADAPTER_CONNECT 0xC9 -#define I2O_CMD_ADAPTER_RESET 0xBD -#define I2O_CMD_LCT_NOTIFY 0xA2 -#define I2O_CMD_OUTBOUND_INIT 0xA1 -#define I2O_CMD_PATH_ENABLE 0xD3 -#define I2O_CMD_PATH_QUIESCE 0xC5 -#define I2O_CMD_PATH_RESET 0xD7 -#define I2O_CMD_STATIC_MF_CREATE 0xDD -#define I2O_CMD_STATIC_MF_RELEASE 0xDF -#define I2O_CMD_STATUS_GET 0xA0 -#define I2O_CMD_SW_DOWNLOAD 0xA9 -#define I2O_CMD_SW_UPLOAD 0xAB -#define I2O_CMD_SW_REMOVE 0xAD -#define I2O_CMD_SYS_ENABLE 0xD1 -#define I2O_CMD_SYS_MODIFY 0xC1 -#define I2O_CMD_SYS_QUIESCE 0xC3 -#define I2O_CMD_SYS_TAB_SET 0xA3 - -/* - * Utility Class - */ -#define I2O_CMD_UTIL_NOP 0x00 -#define I2O_CMD_UTIL_ABORT 0x01 -#define I2O_CMD_UTIL_CLAIM 0x09 -#define I2O_CMD_UTIL_RELEASE 0x0B -#define I2O_CMD_UTIL_PARAMS_GET 0x06 -#define I2O_CMD_UTIL_PARAMS_SET 0x05 -#define I2O_CMD_UTIL_EVT_REGISTER 0x13 -#define I2O_CMD_UTIL_EVT_ACK 0x14 -#define I2O_CMD_UTIL_CONFIG_DIALOG 0x10 -#define I2O_CMD_UTIL_DEVICE_RESERVE 0x0D -#define I2O_CMD_UTIL_DEVICE_RELEASE 0x0F -#define I2O_CMD_UTIL_LOCK 0x17 -#define I2O_CMD_UTIL_LOCK_RELEASE 0x19 -#define I2O_CMD_UTIL_REPLY_FAULT_NOTIFY 0x15 - -/* - * SCSI Host Bus Adapter Class - */ -#define I2O_CMD_SCSI_EXEC 0x81 -#define I2O_CMD_SCSI_ABORT 0x83 -#define I2O_CMD_SCSI_BUSRESET 0x27 - -/* - * Bus Adapter Class - */ -#define I2O_CMD_BUS_ADAPTER_RESET 0x85 -#define I2O_CMD_BUS_RESET 0x87 -#define I2O_CMD_BUS_SCAN 0x89 -#define I2O_CMD_BUS_QUIESCE 0x8b - -/* - * Random Block Storage Class - */ -#define I2O_CMD_BLOCK_READ 0x30 -#define I2O_CMD_BLOCK_WRITE 0x31 -#define I2O_CMD_BLOCK_CFLUSH 0x37 -#define I2O_CMD_BLOCK_MLOCK 0x49 -#define I2O_CMD_BLOCK_MUNLOCK 0x4B -#define I2O_CMD_BLOCK_MMOUNT 0x41 -#define I2O_CMD_BLOCK_MEJECT 0x43 -#define I2O_CMD_BLOCK_POWER 0x70 - -#define I2O_CMD_PRIVATE 0xFF - -/* Command status values */ - -#define I2O_CMD_IN_PROGRESS 0x01 -#define I2O_CMD_REJECTED 0x02 -#define I2O_CMD_FAILED 0x03 -#define I2O_CMD_COMPLETED 0x04 - -/* I2O API function return values */ - -#define I2O_RTN_NO_ERROR 0 -#define I2O_RTN_NOT_INIT 1 -#define I2O_RTN_FREE_Q_EMPTY 2 -#define I2O_RTN_TCB_ERROR 3 -#define I2O_RTN_TRANSACTION_ERROR 4 -#define I2O_RTN_ADAPTER_ALREADY_INIT 5 -#define I2O_RTN_MALLOC_ERROR 6 -#define I2O_RTN_ADPTR_NOT_REGISTERED 7 -#define I2O_RTN_MSG_REPLY_TIMEOUT 8 -#define I2O_RTN_NO_STATUS 9 -#define I2O_RTN_NO_FIRM_VER 10 -#define I2O_RTN_NO_LINK_SPEED 11 - -/* Reply message status defines for all messages */ - -#define I2O_REPLY_STATUS_SUCCESS 0x00 -#define I2O_REPLY_STATUS_ABORT_DIRTY 0x01 -#define I2O_REPLY_STATUS_ABORT_NO_DATA_TRANSFER 0x02 -#define I2O_REPLY_STATUS_ABORT_PARTIAL_TRANSFER 0x03 -#define I2O_REPLY_STATUS_ERROR_DIRTY 0x04 -#define I2O_REPLY_STATUS_ERROR_NO_DATA_TRANSFER 0x05 -#define I2O_REPLY_STATUS_ERROR_PARTIAL_TRANSFER 0x06 -#define I2O_REPLY_STATUS_PROCESS_ABORT_DIRTY 0x08 -#define I2O_REPLY_STATUS_PROCESS_ABORT_NO_DATA_TRANSFER 0x09 -#define I2O_REPLY_STATUS_PROCESS_ABORT_PARTIAL_TRANSFER 0x0A -#define I2O_REPLY_STATUS_TRANSACTION_ERROR 0x0B -#define I2O_REPLY_STATUS_PROGRESS_REPORT 0x80 - -/* Status codes and Error Information for Parameter functions */ - -#define I2O_PARAMS_STATUS_SUCCESS 0x00 -#define I2O_PARAMS_STATUS_BAD_KEY_ABORT 0x01 -#define I2O_PARAMS_STATUS_BAD_KEY_CONTINUE 0x02 -#define I2O_PARAMS_STATUS_BUFFER_FULL 0x03 -#define I2O_PARAMS_STATUS_BUFFER_TOO_SMALL 0x04 -#define I2O_PARAMS_STATUS_FIELD_UNREADABLE 0x05 -#define I2O_PARAMS_STATUS_FIELD_UNWRITEABLE 0x06 -#define I2O_PARAMS_STATUS_INSUFFICIENT_FIELDS 0x07 -#define I2O_PARAMS_STATUS_INVALID_GROUP_ID 0x08 -#define I2O_PARAMS_STATUS_INVALID_OPERATION 0x09 -#define I2O_PARAMS_STATUS_NO_KEY_FIELD 0x0A -#define I2O_PARAMS_STATUS_NO_SUCH_FIELD 0x0B -#define I2O_PARAMS_STATUS_NON_DYNAMIC_GROUP 0x0C -#define I2O_PARAMS_STATUS_OPERATION_ERROR 0x0D -#define I2O_PARAMS_STATUS_SCALAR_ERROR 0x0E -#define I2O_PARAMS_STATUS_TABLE_ERROR 0x0F -#define I2O_PARAMS_STATUS_WRONG_GROUP_TYPE 0x10 - -/* DetailedStatusCode defines for Executive, DDM, Util and Transaction error - * messages: Table 3-2 Detailed Status Codes.*/ - -#define I2O_DSC_SUCCESS 0x0000 -#define I2O_DSC_BAD_KEY 0x0002 -#define I2O_DSC_TCL_ERROR 0x0003 -#define I2O_DSC_REPLY_BUFFER_FULL 0x0004 -#define I2O_DSC_NO_SUCH_PAGE 0x0005 -#define I2O_DSC_INSUFFICIENT_RESOURCE_SOFT 0x0006 -#define I2O_DSC_INSUFFICIENT_RESOURCE_HARD 0x0007 -#define I2O_DSC_CHAIN_BUFFER_TOO_LARGE 0x0009 -#define I2O_DSC_UNSUPPORTED_FUNCTION 0x000A -#define I2O_DSC_DEVICE_LOCKED 0x000B -#define I2O_DSC_DEVICE_RESET 0x000C -#define I2O_DSC_INAPPROPRIATE_FUNCTION 0x000D -#define I2O_DSC_INVALID_INITIATOR_ADDRESS 0x000E -#define I2O_DSC_INVALID_MESSAGE_FLAGS 0x000F -#define I2O_DSC_INVALID_OFFSET 0x0010 -#define I2O_DSC_INVALID_PARAMETER 0x0011 -#define I2O_DSC_INVALID_REQUEST 0x0012 -#define I2O_DSC_INVALID_TARGET_ADDRESS 0x0013 -#define I2O_DSC_MESSAGE_TOO_LARGE 0x0014 -#define I2O_DSC_MESSAGE_TOO_SMALL 0x0015 -#define I2O_DSC_MISSING_PARAMETER 0x0016 -#define I2O_DSC_TIMEOUT 0x0017 -#define I2O_DSC_UNKNOWN_ERROR 0x0018 -#define I2O_DSC_UNKNOWN_FUNCTION 0x0019 -#define I2O_DSC_UNSUPPORTED_VERSION 0x001A -#define I2O_DSC_DEVICE_BUSY 0x001B -#define I2O_DSC_DEVICE_NOT_AVAILABLE 0x001C - -/* DetailedStatusCode defines for Block Storage Operation: Table 6-7 Detailed - Status Codes.*/ - -#define I2O_BSA_DSC_SUCCESS 0x0000 -#define I2O_BSA_DSC_MEDIA_ERROR 0x0001 -#define I2O_BSA_DSC_ACCESS_ERROR 0x0002 -#define I2O_BSA_DSC_DEVICE_FAILURE 0x0003 -#define I2O_BSA_DSC_DEVICE_NOT_READY 0x0004 -#define I2O_BSA_DSC_MEDIA_NOT_PRESENT 0x0005 -#define I2O_BSA_DSC_MEDIA_LOCKED 0x0006 -#define I2O_BSA_DSC_MEDIA_FAILURE 0x0007 -#define I2O_BSA_DSC_PROTOCOL_FAILURE 0x0008 -#define I2O_BSA_DSC_BUS_FAILURE 0x0009 -#define I2O_BSA_DSC_ACCESS_VIOLATION 0x000A -#define I2O_BSA_DSC_WRITE_PROTECTED 0x000B -#define I2O_BSA_DSC_DEVICE_RESET 0x000C -#define I2O_BSA_DSC_VOLUME_CHANGED 0x000D -#define I2O_BSA_DSC_TIMEOUT 0x000E - -/* FailureStatusCodes, Table 3-3 Message Failure Codes */ - -#define I2O_FSC_TRANSPORT_SERVICE_SUSPENDED 0x81 -#define I2O_FSC_TRANSPORT_SERVICE_TERMINATED 0x82 -#define I2O_FSC_TRANSPORT_CONGESTION 0x83 -#define I2O_FSC_TRANSPORT_FAILURE 0x84 -#define I2O_FSC_TRANSPORT_STATE_ERROR 0x85 -#define I2O_FSC_TRANSPORT_TIME_OUT 0x86 -#define I2O_FSC_TRANSPORT_ROUTING_FAILURE 0x87 -#define I2O_FSC_TRANSPORT_INVALID_VERSION 0x88 -#define I2O_FSC_TRANSPORT_INVALID_OFFSET 0x89 -#define I2O_FSC_TRANSPORT_INVALID_MSG_FLAGS 0x8A -#define I2O_FSC_TRANSPORT_FRAME_TOO_SMALL 0x8B -#define I2O_FSC_TRANSPORT_FRAME_TOO_LARGE 0x8C -#define I2O_FSC_TRANSPORT_INVALID_TARGET_ID 0x8D -#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_ID 0x8E -#define I2O_FSC_TRANSPORT_INVALID_INITIATOR_CONTEXT 0x8F -#define I2O_FSC_TRANSPORT_UNKNOWN_FAILURE 0xFF - -/* Device Claim Types */ -#define I2O_CLAIM_PRIMARY 0x01000000 -#define I2O_CLAIM_MANAGEMENT 0x02000000 -#define I2O_CLAIM_AUTHORIZED 0x03000000 -#define I2O_CLAIM_SECONDARY 0x04000000 - -/* Message header defines for VersionOffset */ -#define I2OVER15 0x0001 -#define I2OVER20 0x0002 - -/* Default is 1.5 */ -#define I2OVERSION I2OVER15 - -#define SGL_OFFSET_0 I2OVERSION -#define SGL_OFFSET_4 (0x0040 | I2OVERSION) -#define SGL_OFFSET_5 (0x0050 | I2OVERSION) -#define SGL_OFFSET_6 (0x0060 | I2OVERSION) -#define SGL_OFFSET_7 (0x0070 | I2OVERSION) -#define SGL_OFFSET_8 (0x0080 | I2OVERSION) -#define SGL_OFFSET_9 (0x0090 | I2OVERSION) -#define SGL_OFFSET_10 (0x00A0 | I2OVERSION) -#define SGL_OFFSET_11 (0x00B0 | I2OVERSION) -#define SGL_OFFSET_12 (0x00C0 | I2OVERSION) -#define SGL_OFFSET(x) (((x)<<4) | I2OVERSION) - -/* Transaction Reply Lists (TRL) Control Word structure */ -#define TRL_SINGLE_FIXED_LENGTH 0x00 -#define TRL_SINGLE_VARIABLE_LENGTH 0x40 -#define TRL_MULTIPLE_FIXED_LENGTH 0x80 - - /* msg header defines for MsgFlags */ -#define MSG_STATIC 0x0100 -#define MSG_64BIT_CNTXT 0x0200 -#define MSG_MULTI_TRANS 0x1000 -#define MSG_FAIL 0x2000 -#define MSG_FINAL 0x4000 -#define MSG_REPLY 0x8000 - - /* minimum size msg */ -#define THREE_WORD_MSG_SIZE 0x00030000 -#define FOUR_WORD_MSG_SIZE 0x00040000 -#define FIVE_WORD_MSG_SIZE 0x00050000 -#define SIX_WORD_MSG_SIZE 0x00060000 -#define SEVEN_WORD_MSG_SIZE 0x00070000 -#define EIGHT_WORD_MSG_SIZE 0x00080000 -#define NINE_WORD_MSG_SIZE 0x00090000 -#define TEN_WORD_MSG_SIZE 0x000A0000 -#define ELEVEN_WORD_MSG_SIZE 0x000B0000 -#define I2O_MESSAGE_SIZE(x) ((x)<<16) - -/* special TID assignments */ -#define ADAPTER_TID 0 -#define HOST_TID 1 - -/* outbound queue defines */ -#define I2O_MAX_OUTBOUND_MSG_FRAMES 128 -#define I2O_OUTBOUND_MSG_FRAME_SIZE 128 /* in 32-bit words */ - -/* inbound queue definitions */ -#define I2O_MSG_INPOOL_MIN 32 -#define I2O_INBOUND_MSG_FRAME_SIZE 128 /* in 32-bit words */ - -#define I2O_POST_WAIT_OK 0 -#define I2O_POST_WAIT_TIMEOUT -ETIMEDOUT - -#define I2O_CONTEXT_LIST_MIN_LENGTH 15 -#define I2O_CONTEXT_LIST_USED 0x01 -#define I2O_CONTEXT_LIST_DELETED 0x02 - -/* timeouts */ -#define I2O_TIMEOUT_INIT_OUTBOUND_QUEUE 15 -#define I2O_TIMEOUT_MESSAGE_GET 5 -#define I2O_TIMEOUT_RESET 30 -#define I2O_TIMEOUT_STATUS_GET 5 -#define I2O_TIMEOUT_LCT_GET 360 -#define I2O_TIMEOUT_SCSI_SCB_ABORT 240 - -/* retries */ -#define I2O_HRT_GET_TRIES 3 -#define I2O_LCT_GET_TRIES 3 - -/* defines for max_sectors and max_phys_segments */ -#define I2O_MAX_SECTORS 1024 -#define I2O_MAX_SECTORS_LIMITED 128 -#define I2O_MAX_PHYS_SEGMENTS BLK_MAX_SEGMENTS - -/* - * Message structures - */ -struct i2o_message { - union { - struct { - u8 version_offset; - u8 flags; - u16 size; - u32 target_tid:12; - u32 init_tid:12; - u32 function:8; - u32 icntxt; /* initiator context */ - u32 tcntxt; /* transaction context */ - } s; - u32 head[4]; - } u; - /* List follows */ - u32 body[0]; -}; - -/* MFA and I2O message used by mempool */ -struct i2o_msg_mfa { - u32 mfa; /* MFA returned by the controller */ - struct i2o_message msg; /* I2O message */ -}; - -/* - * Each I2O device entity has one of these. There is one per device. - */ -struct i2o_device { - i2o_lct_entry lct_data; /* Device LCT information */ - - struct i2o_controller *iop; /* Controlling IOP */ - struct list_head list; /* node in IOP devices list */ - - struct device device; - - struct mutex lock; /* device lock */ -}; - -/* - * Event structure provided to the event handling function - */ -struct i2o_event { - struct work_struct work; - struct i2o_device *i2o_dev; /* I2O device pointer from which the - event reply was initiated */ - u16 size; /* Size of data in 32-bit words */ - u32 tcntxt; /* Transaction context used at - registration */ - u32 event_indicator; /* Event indicator from reply */ - u32 data[0]; /* Event data from reply */ -}; - -/* - * I2O classes which could be handled by the OSM - */ -struct i2o_class_id { - u16 class_id:12; -}; - -/* - * I2O driver structure for OSMs - */ -struct i2o_driver { - char *name; /* OSM name */ - int context; /* Low 8 bits of the transaction info */ - struct i2o_class_id *classes; /* I2O classes that this OSM handles */ - - /* Message reply handler */ - int (*reply) (struct i2o_controller *, u32, struct i2o_message *); - - /* Event handler */ - work_func_t event; - - struct workqueue_struct *event_queue; /* Event queue */ - - struct device_driver driver; - - /* notification of changes */ - void (*notify_controller_add) (struct i2o_controller *); - void (*notify_controller_remove) (struct i2o_controller *); - void (*notify_device_add) (struct i2o_device *); - void (*notify_device_remove) (struct i2o_device *); - - struct semaphore lock; -}; - -/* - * Contains DMA mapped address information - */ -struct i2o_dma { - void *virt; - dma_addr_t phys; - size_t len; -}; - -/* - * Contains slab cache and mempool information - */ -struct i2o_pool { - char *name; - struct kmem_cache *slab; - mempool_t *mempool; -}; - -/* - * Contains IO mapped address information - */ -struct i2o_io { - void __iomem *virt; - unsigned long phys; - unsigned long len; -}; - -/* - * Context queue entry, used for 32-bit context on 64-bit systems - */ -struct i2o_context_list_element { - struct list_head list; - u32 context; - void *ptr; - unsigned long timestamp; -}; - -/* - * Each I2O controller has one of these objects - */ -struct i2o_controller { - char name[16]; - int unit; - int type; - - struct pci_dev *pdev; /* PCI device */ - - unsigned int promise:1; /* Promise controller */ - unsigned int adaptec:1; /* DPT / Adaptec controller */ - unsigned int raptor:1; /* split bar */ - unsigned int no_quiesce:1; /* dont quiesce before reset */ - unsigned int short_req:1; /* use small block sizes */ - unsigned int limit_sectors:1; /* limit number of sectors / request */ - unsigned int pae_support:1; /* controller has 64-bit SGL support */ - - struct list_head devices; /* list of I2O devices */ - struct list_head list; /* Controller list */ - - void __iomem *in_port; /* Inbout port address */ - void __iomem *out_port; /* Outbound port address */ - void __iomem *irq_status; /* Interrupt status register address */ - void __iomem *irq_mask; /* Interrupt mask register address */ - - struct i2o_dma status; /* IOP status block */ - - struct i2o_dma hrt; /* HW Resource Table */ - i2o_lct *lct; /* Logical Config Table */ - struct i2o_dma dlct; /* Temp LCT */ - struct mutex lct_lock; /* Lock for LCT updates */ - struct i2o_dma status_block; /* IOP status block */ - - struct i2o_io base; /* controller messaging unit */ - struct i2o_io in_queue; /* inbound message queue Host->IOP */ - struct i2o_dma out_queue; /* outbound message queue IOP->Host */ - - struct i2o_pool in_msg; /* mempool for inbound messages */ - - unsigned int battery:1; /* Has a battery backup */ - unsigned int io_alloc:1; /* An I/O resource was allocated */ - unsigned int mem_alloc:1; /* A memory resource was allocated */ - - struct resource io_resource; /* I/O resource allocated to the IOP */ - struct resource mem_resource; /* Mem resource allocated to the IOP */ - - struct device device; - struct i2o_device *exec; /* Executive */ -#if BITS_PER_LONG == 64 - spinlock_t context_list_lock; /* lock for context_list */ - atomic_t context_list_counter; /* needed for unique contexts */ - struct list_head context_list; /* list of context id's - and pointers */ -#endif - spinlock_t lock; /* lock for controller - configuration */ - void *driver_data[I2O_MAX_DRIVERS]; /* storage for drivers */ -}; - -/* - * I2O System table entry - * - * The system table contains information about all the IOPs in the - * system. It is sent to all IOPs so that they can create peer2peer - * connections between them. - */ -struct i2o_sys_tbl_entry { - u16 org_id; - u16 reserved1; - u32 iop_id:12; - u32 reserved2:20; - u16 seg_num:12; - u16 i2o_version:4; - u8 iop_state; - u8 msg_type; - u16 frame_size; - u16 reserved3; - u32 last_changed; - u32 iop_capabilities; - u32 inbound_low; - u32 inbound_high; -}; - -struct i2o_sys_tbl { - u8 num_entries; - u8 version; - u16 reserved1; - u32 change_ind; - u32 reserved2; - u32 reserved3; - struct i2o_sys_tbl_entry iops[0]; -}; - -extern struct list_head i2o_controllers; - -/* Message functions */ -extern struct i2o_message *i2o_msg_get_wait(struct i2o_controller *, int); -extern int i2o_msg_post_wait_mem(struct i2o_controller *, struct i2o_message *, - unsigned long, struct i2o_dma *); - -/* IOP functions */ -extern int i2o_status_get(struct i2o_controller *); - -extern int i2o_event_register(struct i2o_device *, struct i2o_driver *, int, - u32); -extern struct i2o_device *i2o_iop_find_device(struct i2o_controller *, u16); -extern struct i2o_controller *i2o_find_iop(int); - -/* Functions needed for handling 64-bit pointers in 32-bit context */ -#if BITS_PER_LONG == 64 -extern u32 i2o_cntxt_list_add(struct i2o_controller *, void *); -extern void *i2o_cntxt_list_get(struct i2o_controller *, u32); -extern u32 i2o_cntxt_list_remove(struct i2o_controller *, void *); -extern u32 i2o_cntxt_list_get_ptr(struct i2o_controller *, void *); - -static inline u32 i2o_ptr_low(void *ptr) -{ - return (u32) (u64) ptr; -}; - -static inline u32 i2o_ptr_high(void *ptr) -{ - return (u32) ((u64) ptr >> 32); -}; - -static inline u32 i2o_dma_low(dma_addr_t dma_addr) -{ - return (u32) (u64) dma_addr; -}; - -static inline u32 i2o_dma_high(dma_addr_t dma_addr) -{ - return (u32) ((u64) dma_addr >> 32); -}; -#else -static inline u32 i2o_cntxt_list_add(struct i2o_controller *c, void *ptr) -{ - return (u32) ptr; -}; - -static inline void *i2o_cntxt_list_get(struct i2o_controller *c, u32 context) -{ - return (void *)context; -}; - -static inline u32 i2o_cntxt_list_remove(struct i2o_controller *c, void *ptr) -{ - return (u32) ptr; -}; - -static inline u32 i2o_cntxt_list_get_ptr(struct i2o_controller *c, void *ptr) -{ - return (u32) ptr; -}; - -static inline u32 i2o_ptr_low(void *ptr) -{ - return (u32) ptr; -}; - -static inline u32 i2o_ptr_high(void *ptr) -{ - return 0; -}; - -static inline u32 i2o_dma_low(dma_addr_t dma_addr) -{ - return (u32) dma_addr; -}; - -static inline u32 i2o_dma_high(dma_addr_t dma_addr) -{ - return 0; -}; -#endif - -extern u16 i2o_sg_tablesize(struct i2o_controller *c, u16 body_size); -extern dma_addr_t i2o_dma_map_single(struct i2o_controller *c, void *ptr, - size_t size, - enum dma_data_direction direction, - u32 ** sg_ptr); -extern int i2o_dma_map_sg(struct i2o_controller *c, - struct scatterlist *sg, int sg_count, - enum dma_data_direction direction, - u32 ** sg_ptr); -extern int i2o_dma_alloc(struct device *dev, struct i2o_dma *addr, size_t len); -extern void i2o_dma_free(struct device *dev, struct i2o_dma *addr); -extern int i2o_dma_realloc(struct device *dev, struct i2o_dma *addr, - size_t len); -extern int i2o_pool_alloc(struct i2o_pool *pool, const char *name, - size_t size, int min_nr); -extern void i2o_pool_free(struct i2o_pool *pool); -/* I2O driver (OSM) functions */ -extern int i2o_driver_register(struct i2o_driver *); -extern void i2o_driver_unregister(struct i2o_driver *); - -/** - * i2o_driver_notify_controller_add - Send notification of added controller - * @drv: I2O driver - * @c: I2O controller - * - * Send notification of added controller to a single registered driver. - */ -static inline void i2o_driver_notify_controller_add(struct i2o_driver *drv, - struct i2o_controller *c) -{ - if (drv->notify_controller_add) - drv->notify_controller_add(c); -}; - -/** - * i2o_driver_notify_controller_remove - Send notification of removed controller - * @drv: I2O driver - * @c: I2O controller - * - * Send notification of removed controller to a single registered driver. - */ -static inline void i2o_driver_notify_controller_remove(struct i2o_driver *drv, - struct i2o_controller *c) -{ - if (drv->notify_controller_remove) - drv->notify_controller_remove(c); -}; - -/** - * i2o_driver_notify_device_add - Send notification of added device - * @drv: I2O driver - * @i2o_dev: the added i2o_device - * - * Send notification of added device to a single registered driver. - */ -static inline void i2o_driver_notify_device_add(struct i2o_driver *drv, - struct i2o_device *i2o_dev) -{ - if (drv->notify_device_add) - drv->notify_device_add(i2o_dev); -}; - -/** - * i2o_driver_notify_device_remove - Send notification of removed device - * @drv: I2O driver - * @i2o_dev: the added i2o_device - * - * Send notification of removed device to a single registered driver. - */ -static inline void i2o_driver_notify_device_remove(struct i2o_driver *drv, - struct i2o_device *i2o_dev) -{ - if (drv->notify_device_remove) - drv->notify_device_remove(i2o_dev); -}; - -extern void i2o_driver_notify_controller_add_all(struct i2o_controller *); -extern void i2o_driver_notify_controller_remove_all(struct i2o_controller *); -extern void i2o_driver_notify_device_add_all(struct i2o_device *); -extern void i2o_driver_notify_device_remove_all(struct i2o_device *); - -/* I2O device functions */ -extern int i2o_device_claim(struct i2o_device *); -extern int i2o_device_claim_release(struct i2o_device *); - -/* Exec OSM functions */ -extern int i2o_exec_lct_get(struct i2o_controller *); - -/* device / driver / kobject conversion functions */ -#define to_i2o_driver(drv) container_of(drv,struct i2o_driver, driver) -#define to_i2o_device(dev) container_of(dev, struct i2o_device, device) -#define to_i2o_controller(dev) container_of(dev, struct i2o_controller, device) - -/** - * i2o_out_to_virt - Turn an I2O message to a virtual address - * @c: controller - * @m: message engine value - * - * Turn a receive message from an I2O controller bus address into - * a Linux virtual address. The shared page frame is a linear block - * so we simply have to shift the offset. This function does not - * work for sender side messages as they are ioremap objects - * provided by the I2O controller. - */ -static inline struct i2o_message *i2o_msg_out_to_virt(struct i2o_controller *c, - u32 m) -{ - BUG_ON(m < c->out_queue.phys - || m >= c->out_queue.phys + c->out_queue.len); - - return c->out_queue.virt + (m - c->out_queue.phys); -}; - -/** - * i2o_msg_in_to_virt - Turn an I2O message to a virtual address - * @c: controller - * @m: message engine value - * - * Turn a send message from an I2O controller bus address into - * a Linux virtual address. The shared page frame is a linear block - * so we simply have to shift the offset. This function does not - * work for receive side messages as they are kmalloc objects - * in a different pool. - */ -static inline struct i2o_message __iomem *i2o_msg_in_to_virt(struct - i2o_controller *c, - u32 m) -{ - return c->in_queue.virt + m; -}; - -/** - * i2o_msg_get - obtain an I2O message from the IOP - * @c: I2O controller - * - * This function tries to get a message frame. If no message frame is - * available do not wait until one is available (see also i2o_msg_get_wait). - * The returned pointer to the message frame is not in I/O memory, it is - * allocated from a mempool. But because a MFA is allocated from the - * controller too it is guaranteed that i2o_msg_post() will never fail. - * - * On a success a pointer to the message frame is returned. If the message - * queue is empty -EBUSY is returned and if no memory is available -ENOMEM - * is returned. - */ -static inline struct i2o_message *i2o_msg_get(struct i2o_controller *c) -{ - struct i2o_msg_mfa *mmsg = mempool_alloc(c->in_msg.mempool, GFP_ATOMIC); - if (!mmsg) - return ERR_PTR(-ENOMEM); - - mmsg->mfa = readl(c->in_port); - if (unlikely(mmsg->mfa >= c->in_queue.len)) { - u32 mfa = mmsg->mfa; - - mempool_free(mmsg, c->in_msg.mempool); - - if (mfa == I2O_QUEUE_EMPTY) - return ERR_PTR(-EBUSY); - return ERR_PTR(-EFAULT); - } - - return &mmsg->msg; -}; - -/** - * i2o_msg_post - Post I2O message to I2O controller - * @c: I2O controller to which the message should be send - * @msg: message returned by i2o_msg_get() - * - * Post the message to the I2O controller and return immediately. - */ -static inline void i2o_msg_post(struct i2o_controller *c, - struct i2o_message *msg) -{ - struct i2o_msg_mfa *mmsg; - - mmsg = container_of(msg, struct i2o_msg_mfa, msg); - memcpy_toio(i2o_msg_in_to_virt(c, mmsg->mfa), msg, - (le32_to_cpu(msg->u.head[0]) >> 16) << 2); - writel(mmsg->mfa, c->in_port); - mempool_free(mmsg, c->in_msg.mempool); -}; - -/** - * i2o_msg_post_wait - Post and wait a message and wait until return - * @c: controller - * @msg: message to post - * @timeout: time in seconds to wait - * - * This API allows an OSM to post a message and then be told whether or - * not the system received a successful reply. If the message times out - * then the value '-ETIMEDOUT' is returned. - * - * Returns 0 on success or negative error code on failure. - */ -static inline int i2o_msg_post_wait(struct i2o_controller *c, - struct i2o_message *msg, - unsigned long timeout) -{ - return i2o_msg_post_wait_mem(c, msg, timeout, NULL); -}; - -/** - * i2o_msg_nop_mfa - Returns a fetched MFA back to the controller - * @c: I2O controller from which the MFA was fetched - * @mfa: MFA which should be returned - * - * This function must be used for preserved messages, because i2o_msg_nop() - * also returns the allocated memory back to the msg_pool mempool. - */ -static inline void i2o_msg_nop_mfa(struct i2o_controller *c, u32 mfa) -{ - struct i2o_message __iomem *msg; - u32 nop[3] = { - THREE_WORD_MSG_SIZE | SGL_OFFSET_0, - I2O_CMD_UTIL_NOP << 24 | HOST_TID << 12 | ADAPTER_TID, - 0x00000000 - }; - - msg = i2o_msg_in_to_virt(c, mfa); - memcpy_toio(msg, nop, sizeof(nop)); - writel(mfa, c->in_port); -}; - -/** - * i2o_msg_nop - Returns a message which is not used - * @c: I2O controller from which the message was created - * @msg: message which should be returned - * - * If you fetch a message via i2o_msg_get, and can't use it, you must - * return the message with this function. Otherwise the MFA is lost as well - * as the allocated memory from the mempool. - */ -static inline void i2o_msg_nop(struct i2o_controller *c, - struct i2o_message *msg) -{ - struct i2o_msg_mfa *mmsg; - mmsg = container_of(msg, struct i2o_msg_mfa, msg); - - i2o_msg_nop_mfa(c, mmsg->mfa); - mempool_free(mmsg, c->in_msg.mempool); -}; - -/** - * i2o_flush_reply - Flush reply from I2O controller - * @c: I2O controller - * @m: the message identifier - * - * The I2O controller must be informed that the reply message is not needed - * anymore. If you forget to flush the reply, the message frame can't be - * used by the controller anymore and is therefore lost. - */ -static inline void i2o_flush_reply(struct i2o_controller *c, u32 m) -{ - writel(m, c->out_port); -}; - -/* - * Endian handling wrapped into the macro - keeps the core code - * cleaner. - */ - -#define i2o_raw_writel(val, mem) __raw_writel(cpu_to_le32(val), mem) - -extern int i2o_parm_field_get(struct i2o_device *, int, int, void *, int); -extern int i2o_parm_table_get(struct i2o_device *, int, int, int, void *, int, - void *, int); - -/* debugging and troubleshooting/diagnostic helpers. */ -#define osm_printk(level, format, arg...) \ - printk(level "%s: " format, OSM_NAME , ## arg) - -#ifdef DEBUG -#define osm_debug(format, arg...) \ - osm_printk(KERN_DEBUG, format , ## arg) -#else -#define osm_debug(format, arg...) \ - do { } while (0) -#endif - -#define osm_err(format, arg...) \ - osm_printk(KERN_ERR, format , ## arg) -#define osm_info(format, arg...) \ - osm_printk(KERN_INFO, format , ## arg) -#define osm_warn(format, arg...) \ - osm_printk(KERN_WARNING, format , ## arg) - -/* debugging functions */ -extern void i2o_report_status(const char *, const char *, struct i2o_message *); -extern void i2o_dump_message(struct i2o_message *); -extern void i2o_dump_hrt(struct i2o_controller *c); -extern void i2o_debug_state(struct i2o_controller *c); - -#endif /* _I2O_H */ -- cgit v1.2.3 From 09aa8ac0f9a76b7d650cf3a27a2cfcb4d3d612fb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 Feb 2015 17:07:35 -0600 Subject: dma: mmp_tdma: Fix build for ARM64 sram_get_gpool is only used for legacy, non-DT MMP/PXA platforms. Provide an empty version in order to build on ARM64. Signed-off-by: Rob Herring Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-mmp_tdma.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-mmp_tdma.h b/include/linux/platform_data/dma-mmp_tdma.h index 66574ea39f97..0c72886030ef 100644 --- a/include/linux/platform_data/dma-mmp_tdma.h +++ b/include/linux/platform_data/dma-mmp_tdma.h @@ -28,6 +28,13 @@ struct sram_platdata { int granularity; }; +#ifdef CONFIG_ARM extern struct gen_pool *sram_get_gpool(char *pool_name); +#else +static inline struct gen_pool *sram_get_gpool(char *pool_name) +{ + return NULL; +} +#endif #endif /* __DMA_MMP_TDMA_H */ -- cgit v1.2.3 From 851c63e3b381fdbf5aca1a797f37d8606b5588d2 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Mon, 5 Jan 2015 15:43:39 +0000 Subject: of: Fix brace position for struct of_device_id definition Currently it is not easy to grep for the definition of struct of_device_id. This is trivially fixed by moving the brace to the right place. Signed-off-by: Daniel Thompson Cc: Grant Likely Cc: Rob Herring Signed-off-by: Rob Herring --- include/linux/mod_devicetable.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 745def862580..bbf85d612be5 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -220,8 +220,7 @@ struct serio_device_id { /* * Struct used for matching a device */ -struct of_device_id -{ +struct of_device_id { char name[32]; char type[32]; char compatible[128]; -- cgit v1.2.3 From 4c946d9c11d173c2ea6b9081b248f8072e6b46f1 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 27 Nov 2014 19:52:04 -0500 Subject: vmci: propagate msghdr all way down to __qp_memcpy_to_queue() Switch from passing msg->iov_iter.iov to passing msg itself Signed-off-by: Al Viro --- include/linux/vmw_vmci_api.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index 5691f752ce8f..63df3a2a8ce5 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -74,7 +74,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size, int mode); ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, - void *iov, size_t iov_size, int mode); + struct msghdr *msg, size_t iov_size, int mode); ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int mode); ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, -- cgit v1.2.3 From af2b040e470b470bfc881981db3c796072853eae Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 27 Nov 2014 21:44:24 -0500 Subject: rxrpc: switch rxrpc_send_data() to iov_iter primitives Convert skb_add_data() to iov_iter; allows to get rid of the explicit messing with iovec in its only caller - skb_add_data() will keep advancing ->msg_iter for us, so there's no need to similate that manually. Signed-off-by: Al Viro --- include/linux/skbuff.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 85ab7d72b54c..9a8bafee1b67 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2484,19 +2484,18 @@ static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) } static inline int skb_add_data(struct sk_buff *skb, - char __user *from, int copy) + struct iov_iter *from, int copy) { const int off = skb->len; if (skb->ip_summed == CHECKSUM_NONE) { - int err = 0; - __wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy), - copy, 0, &err); - if (!err) { + __wsum csum = 0; + if (csum_and_copy_from_iter(skb_put(skb, copy), copy, + &csum, from) == copy) { skb->csum = csum_block_add(skb->csum, csum, off); return 0; } - } else if (!copy_from_user(skb_put(skb, copy), from, copy)) + } else if (copy_from_iter(skb_put(skb, copy), copy, from) == copy) return 0; __skb_trim(skb, off); -- cgit v1.2.3 From 21226abb4e9f14d88238964d89b279e461ddc30c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 28 Nov 2014 15:48:29 -0500 Subject: net: switch memcpy_fromiovec()/memcpy_fromiovecend() users to copy_from_iter() That takes care of the majority of ->sendmsg() instances - most of them via memcpy_to_msg() or assorted getfrag() callbacks. One place where we still keep memcpy_fromiovecend() is tipc - there we potentially read the same data over and over; separate patch, that... Signed-off-by: Al Viro --- include/linux/skbuff.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9a8bafee1b67..b349c96dc80a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2692,8 +2692,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { - /* XXX: stripping const */ - return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len); + return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) -- cgit v1.2.3 From 31a25fae85956e3a9c778141d29e5e803fb0b124 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 28 Nov 2014 15:53:57 -0500 Subject: net: bury net/core/iovec.c - nothing in there is used anymore Signed-off-by: Al Viro --- include/linux/socket.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 6e49a14365dc..5c19cba34dce 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -318,13 +318,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -extern int csum_partial_copy_fromiovecend(unsigned char *kdata, - struct iovec *iov, - int offset, - unsigned int len, __wsum *csump); -extern unsigned long iov_pages(const struct iovec *iov, int offset, - unsigned long nr_segs); - extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); -- cgit v1.2.3 From aad9a1cec7dcd1d45809b64643fce37061b17788 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2014 14:49:01 -0500 Subject: vhost: switch vhost get_indirect() to iov_iter, kill memcpy_fromiovec() Cc: Michael S. Tsirkin Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Al Viro --- include/linux/uio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1c5e453f7ea9..af3439f4ebf2 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -135,7 +135,6 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, -- cgit v1.2.3 From ba7438aed924133df54a60e4cd5499d359bcf2a8 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2014 15:51:28 -0500 Subject: vhost: don't bother copying iovecs in handle_rx(), kill memcpy_toiovecend() Cc: Michael S. Tsirkin Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Al Viro --- include/linux/uio.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index af3439f4ebf2..02bd8a92038a 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -137,7 +137,4 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct io int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); -int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, - int offset, int len); - #endif -- cgit v1.2.3 From 57dd8a0735aabff4862025cf64ad94da3d80e620 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 10 Dec 2014 16:03:43 -0500 Subject: vhost: vhost_scsi_handle_vq() should just use copy_from_user() it has just verified that it asks no more than the length of the first segment of iovec. And with that the last user of stuff in lib/iovec.c is gone. RIP. Cc: Michael S. Tsirkin Cc: Nicholas A. Bellinger Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Al Viro --- include/linux/uio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 02bd8a92038a..3e0cb4ea3905 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -135,6 +135,4 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); -int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len); #endif -- cgit v1.2.3 From 44fc0e5eec00db5fba748803c95920098089c4cc Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Fri, 30 Jan 2015 13:14:36 +0200 Subject: sched/wait: Introduce wait_on_bit_timeout() Add a new wait_on_bit_timeout() helper, basically the same as wait_on_bit() except that it also takes a 'timeout' parameter. All the building blocks like bit_wait_timeout() and out_of_line_wait_on_bit_timeout() are already in place so the addition is rather simple. Signed-off-by: Johan Hedberg Signed-off-by: Peter Zijlstra (Intel) Cc: davem@davemloft.net Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1422616476-2917-2-git-send-email-johan.hedberg@gmail.com Signed-off-by: Ingo Molnar --- include/linux/wait.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 37423e0e1379..537d58eea8a0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -989,6 +989,32 @@ wait_on_bit_io(void *word, int bit, unsigned mode) mode); } +/** + * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * @mode: the task state to sleep in + * @timeout: timeout, in jiffies + * + * Use the standard hashed waitqueue table to wait for a bit + * to be cleared. This is similar to wait_on_bit(), except also takes a + * timeout parameter. + * + * Returned value will be zero if the bit was cleared before the + * @timeout elapsed, or non-zero if the @timeout elapsed or process + * received a signal and the mode permitted wakeup on that signal. + */ +static inline int +wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout) +{ + might_sleep(); + if (!test_bit(bit, word)) + return 0; + return out_of_line_wait_on_bit_timeout(word, bit, + bit_wait_timeout, + mode, timeout); +} + /** * wait_on_bit_action - wait for a bit to be cleared * @word: the word being waited on, a kernel virtual address -- cgit v1.2.3 From 2fde4f94e0a9531251e706fa57131b51b0df042e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 7 Jan 2015 15:01:54 +0000 Subject: perf: Decouple unthrottling and rotating Currently the adjusments made as part of perf_event_task_tick() use the percpu rotation lists to iterate over any active PMU contexts, but these are not used by the context rotation code, having been replaced by separate (per-context) hrtimer callbacks. However, some manipulation of the rotation lists (i.e. removal of contexts) has remained in perf_rotate_context(). This leads to the following issues: * Contexts are not always removed from the rotation lists. Removal of PMUs which have been placed in rotation lists, but have not been removed by a hrtimer callback can result in corruption of the rotation lists (when memory backing the context is freed). This has been observed to result in hangs when PMU drivers built as modules are inserted and removed around the creation of events for said PMUs. * Contexts which do not require rotation may be removed from the rotation lists as a result of a hrtimer, and will not be considered by the unthrottling code in perf_event_task_tick. This patch fixes the issue by updating the rotation ist when events are scheduled in/out, ensuring that each rotation list stays in sync with the HW state. As each event holds a refcount on the module of its PMU, this ensures that when a PMU module is unloaded none of its CPU contexts can be in a rotation list. By maintaining a list of perf_event_contexts rather than perf_event_cpu_contexts, we don't need separate paths to handle the cpu and task contexts, which also makes the code a little simpler. As the rotation_list variables are not used for rotation, these are renamed to active_ctx_list, which better matches their current function. perf_pmu_rotate_{start,stop} are renamed to perf_pmu_ctx_{activate,deactivate}. Reported-by: Johannes Jensen Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Cc: Will Deacon Cc: Arnaldo Carvalho de Melo Cc: Fengguang Wu Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20150129134511.GR17721@leverpostej Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 216653466a67..5cad0e6f3552 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -469,6 +469,7 @@ struct perf_event_context { */ struct mutex mutex; + struct list_head active_ctx_list; struct list_head pinned_groups; struct list_head flexible_groups; struct list_head event_list; @@ -519,7 +520,6 @@ struct perf_cpu_context { int exclusive; struct hrtimer hrtimer; ktime_t hrtimer_interval; - struct list_head rotation_list; struct pmu *unique_pmu; struct perf_cgroup *cgrp; }; -- cgit v1.2.3 From 12cf89b550d13eb7cb86ef182bd6c04345a33a1f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 3 Feb 2015 16:45:18 -0600 Subject: livepatch: rename config to CONFIG_LIVEPATCH Rename CONFIG_LIVE_PATCHING to CONFIG_LIVEPATCH to make the naming of the config and the code more consistent. Signed-off-by: Josh Poimboeuf Reviewed-by: Jingoo Han Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index f14c6fb262b4..95023fd8b00d 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -24,7 +24,7 @@ #include #include -#if IS_ENABLED(CONFIG_LIVE_PATCHING) +#if IS_ENABLED(CONFIG_LIVEPATCH) #include @@ -128,6 +128,6 @@ extern int klp_unregister_patch(struct klp_patch *); extern int klp_enable_patch(struct klp_patch *); extern int klp_disable_patch(struct klp_patch *); -#endif /* CONFIG_LIVE_PATCHING */ +#endif /* CONFIG_LIVEPATCH */ #endif /* _LINUX_LIVEPATCH_H_ */ -- cgit v1.2.3 From 1e0fb9ec679c9273a641f1d6f3d25ea47baef2bb Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 24 Oct 2014 15:58:10 -0700 Subject: perf: Add pmu callbacks to track event mapping and unmapping Signed-off-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Cc: Kees Cook Cc: Andrea Arcangeli Cc: Vince Weaver Cc: "hillf.zj" Cc: Valdis Kletnieks Cc: Linus Torvalds Link: http://lkml.kernel.org/r/266afcba1d1f91ea5501e4e16e94bbbc1a9339b6.1414190806.git.luto@amacapital.net Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5cad0e6f3552..33262004c310 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -202,6 +202,13 @@ struct pmu { */ int (*event_init) (struct perf_event *event); + /* + * Notification that the event was mapped or unmapped. Called + * in the context of the mapping task. + */ + void (*event_mapped) (struct perf_event *event); /*optional*/ + void (*event_unmapped) (struct perf_event *event); /*optional*/ + #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ -- cgit v1.2.3 From 509102760da3a21831e763560ba4715760e3fbda Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 4 Feb 2015 11:45:28 +0100 Subject: regulator: Fix build breakage on !REGULATOR Add missing stubs for regulator_suspend_prepare() and regulator_suspend_finish() to fix exynos_defconfig build without REGULATOR: arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_finish': arch/arm/mach-exynos/suspend.c:537: undefined reference to `regulator_suspend_finish' arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_prepare': arch/arm/mach-exynos/suspend.c:520: undefined reference to `regulator_suspend_prepare' make: *** [vmlinux] Error 1 Signed-off-by: Krzysztof Kozlowski Reported-by: Joerg Roedel Reported-by: Marek Szyprowski Signed-off-by: Mark Brown --- include/linux/regulator/machine.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h index 0b08d05d470b..b07562e082c4 100644 --- a/include/linux/regulator/machine.h +++ b/include/linux/regulator/machine.h @@ -191,15 +191,22 @@ struct regulator_init_data { void *driver_data; /* core does not touch this */ }; -int regulator_suspend_prepare(suspend_state_t state); -int regulator_suspend_finish(void); - #ifdef CONFIG_REGULATOR void regulator_has_full_constraints(void); +int regulator_suspend_prepare(suspend_state_t state); +int regulator_suspend_finish(void); #else static inline void regulator_has_full_constraints(void) { } +static inline int regulator_suspend_prepare(suspend_state_t state) +{ + return 0; +} +static inline int regulator_suspend_finish(void) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 6ae373394c4257bad562817aa60464ff7fe8f9c4 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Jan 2015 14:21:14 -0500 Subject: NFSv4.1: Ask for no delegation on OPEN if using O_DIRECT If we're using NFSv4.1, then we have the ability to let the server know whether or not we believe that returning a delegation as part of our OPEN request would be useful. The feature needs to be used with care, since the client sending the request doesn't necessarily know how other clients are using that file, and how they may be affected by the delegation. For this reason, our initial use of the feature will be to let the server know when the client believes that handing out a delegation would not be useful. The first application for this function is when opening the file using O_DIRECT. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 81401125ab2d..2c35e2affa6f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -326,6 +326,7 @@ struct nfs_openargs { struct nfs_seqid * seqid; int open_flags; fmode_t fmode; + u32 share_access; u32 access; __u64 clientid; struct stateowner_id id; @@ -393,6 +394,7 @@ struct nfs_closeargs { nfs4_stateid stateid; struct nfs_seqid * seqid; fmode_t fmode; + u32 share_access; const u32 * bitmask; }; -- cgit v1.2.3 From 2c561246524c3319473bf47b558354f7ff47f0cf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 Feb 2015 12:55:31 +0100 Subject: block: Simplify bsg complete all It took me a few tries to figure out what this code did; lets rewrite it into a more regular form. The thing that makes this one 'special' is the BSG_F_BLOCK flag, if that is not set we're not supposed/allowed to block and should spin wait for completion. The (new) io_wait_event() will never see a false condition in case of the spinning and we will therefore not block. Cc: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Jens Axboe --- include/linux/wait.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 2232ed16635a..71fc1d31e48d 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -267,6 +267,21 @@ do { \ __wait_event(wq, condition); \ } while (0) +#define __io_wait_event(wq, condition) \ + (void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ + io_schedule()) + +/* + * io_wait_event() -- like wait_event() but with io_schedule() + */ +#define io_wait_event(wq, condition) \ +do { \ + might_sleep(); \ + if (condition) \ + break; \ + __io_wait_event(wq, condition); \ +} while (0) + #define __wait_event_freezable(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0, \ schedule(); try_to_freeze()) -- cgit v1.2.3 From c4546f246636ccf4cda092bcfcafcb5f5f752ec7 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Mon, 26 Jan 2015 09:22:22 -0700 Subject: coresight: remove the unnecessary function coresight_is_bit_set() This function coresight_is_bit_set() isn't called, so we should remove it. Signed-off-by: Kaixu Xia Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight.h b/include/linux/coresight.h index cd6d4c384ca3..3486b9082adb 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -227,7 +227,6 @@ coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); extern int coresight_enable(struct coresight_device *csdev); extern void coresight_disable(struct coresight_device *csdev); -extern int coresight_is_bit_set(u32 val, int position, int value); extern int coresight_timeout(void __iomem *addr, u32 offset, int position, int value); #else @@ -237,8 +236,6 @@ static inline void coresight_unregister(struct coresight_device *csdev) {} static inline int coresight_enable(struct coresight_device *csdev) { return -ENOSYS; } static inline void coresight_disable(struct coresight_device *csdev) {} -static inline int coresight_is_bit_set(u32 val, int position, int value) - { return 0; } static inline int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) { return 1; } #endif -- cgit v1.2.3 From 9064bf3c3cdf92f6b9ac6634ff570dedf0035992 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 Feb 2015 17:03:35 -0600 Subject: spi: spi-pxa2xx: only include mach/dma.h for legacy DMA Move the include of mach/dma.h to the legacy PXA DMA code where it is used. This enables building spi-pxa2xx on ARM64. Signed-off-by: Rob Herring Signed-off-by: Mark Brown --- include/linux/spi/pxa2xx_spi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index d5a316550177..46d8fa942631 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -57,7 +57,6 @@ struct pxa2xx_spi_chip { #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) #include -#include extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); -- cgit v1.2.3 From 2bd82484bb4c5db1d5dc983ac7c409b2782e0154 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 3 Feb 2015 23:48:24 -0800 Subject: xps: fix xps for stacked devices A typical qdisc setup is the following : bond0 : bonding device, using HTB hierarchy eth1/eth2 : slaves, multiqueue NIC, using MQ + FQ qdisc XPS allows to spread packets on specific tx queues, based on the cpu doing the send. Problem is that dequeues from bond0 qdisc can happen on random cpus, due to the fact that qdisc_run() can dequeue a batch of packets. CPUA -> queue packet P1 on bond0 qdisc, P1->ooo_okay=1 CPUA -> queue packet P2 on bond0 qdisc, P2->ooo_okay=0 CPUB -> dequeue packet P1 from bond0 enqueue packet on eth1/eth2 CPUC -> dequeue packet P2 from bond0 enqueue packet on eth1/eth2 using sk cache (ooo_okay is 0) get_xps_queue() then might select wrong queue for P1, since current cpu might be different than CPUA. P2 might be sent on the old queue (stored in sk->sk_tx_queue_mapping), if CPUC runs a bit faster (or CPUB spins a bit on qdisc lock) Effect of this bug is TCP reorders, and more generally not optimal TX queue placement. (A victim bulk flow can be migrated to the wrong TX queue for a while) To fix this, we have to record sender cpu number the first time dev_queue_xmit() is called for one tx skb. We can union napi_id (used on receive path) and sender_cpu, granted we clear sender_cpu in skb_scrub_packet() (credit to Willem for this union idea) Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Cc: Nandita Dukkipati Cc: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 85ab7d72b54c..2748ff639144 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -626,8 +626,11 @@ struct sk_buff { __u32 hash; __be16 vlan_proto; __u16 vlan_tci; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int napi_id; +#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) + union { + unsigned int napi_id; + unsigned int sender_cpu; + }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; -- cgit v1.2.3 From dcdc8994697faa789669c3fdaca1a8bc27a8f356 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 2 Feb 2015 16:07:34 -0800 Subject: net: add skb functions to process remote checksum offload This patch adds skb_remcsum_process and skb_gro_remcsum_process to perform the appropriate adjustments to the skb when receiving remote checksum offload. Updated vxlan and gue to use these functions. Tested: Ran TCP_RR and TCP_STREAM netperf for VXLAN and GUE, did not see any change in performance. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 15 +++++++++++++++ include/linux/skbuff.h | 21 +++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 16251e96e6aa..1347ac50d2af 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2318,6 +2318,21 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + int start, int offset) +{ + __wsum delta; + + BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + + delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); +} + + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2748ff639144..5405dfe02572 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3099,6 +3099,27 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +/* Update skbuf and packet to reflect the remote checksum offload operation. + * When called, ptr indicates the starting point for skb->csum when + * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete + * here, skb_postpull_rcsum is done so skb->csum start is ptr. + */ +static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, + int start, int offset) +{ + __wsum delta; + + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + __skb_checksum_complete(skb); + skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); + } + + delta = remcsum_adjust(ptr, skb->csum, start, offset); + + /* Adjust skb->csum since we changed the packet */ + skb->csum = csum_add(skb->csum, delta); +} + #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) -- cgit v1.2.3 From 61bd3857ff2c7daf756d49b41e6277bbdaa8f789 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 3 Feb 2015 16:48:29 +0200 Subject: net/core: Add event for a change in slave state Add event which provides an indication on a change in the state of a bonding slave. The event handler should cast the pointer to the appropriate type (struct netdev_bonding_info) in order to get the full info about the slave. Signed-off-by: Moni Shoua Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/netdevice.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1347ac50d2af..ce784d5018e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -51,6 +51,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -2056,6 +2057,7 @@ struct pcpu_sw_netstats { #define NETDEV_RESEND_IGMP 0x0016 #define NETDEV_PRECHANGEMTU 0x0017 /* notify before mtu change happened */ #define NETDEV_CHANGEINFODATA 0x0018 +#define NETDEV_BONDING_INFO 0x0019 int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -3494,6 +3496,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); +struct netdev_bonding_info { + ifslave slave; + ifbond master; +}; + +struct netdev_notifier_bonding_info { + struct netdev_notifier_info info; /* must be first */ + struct netdev_bonding_info bonding_info; +}; + +void netdev_bonding_info_change(struct net_device *dev, + struct netdev_bonding_info *bonding_info); + static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { -- cgit v1.2.3 From 59e14e325066be49b49b6c2503337c69a9ee29fc Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 3 Feb 2015 16:48:32 +0200 Subject: net/mlx4_core: Port aggregation low level interface Implement the hardware interface required for port aggregation. 1. Disable RX port check on receive - don't perform a validity check that matches to QP's port and the port where the packet is received. 2. Virtual to physical port remap - configure virtual to physical port mapping. Port remap capability for virtual functions. Signed-off-by: Moni Shoua Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/cmd.h | 7 +++++++ include/linux/mlx4/device.h | 10 +++++++++- include/linux/mlx4/qp.h | 1 + 3 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index ae95adc78509..7b6d4e9ff603 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -71,6 +71,7 @@ enum { /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, + MLX4_CMD_VIRT_PORT_MAP = 0x5c, MLX4_CMD_GET_OP_REQ = 0x59, /* TPT commands */ @@ -170,6 +171,12 @@ enum { MLX4_CMD_TIME_CLASS_C = 60000, }; +enum { + /* virtual to physical port mapping opcode modifiers */ + MLX4_GET_PORT_VIRT2PHY = 0x0, + MLX4_SET_PORT_VIRT2PHY = 0x1, +}; + enum { MLX4_MAILBOX_SIZE = 4096, MLX4_ACCESS_MEM_ALIGN = 256, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c95d659a39f2..d9afd99dde39 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -201,7 +201,8 @@ enum { MLX4_DEV_CAP_FLAG2_SYS_EQS = 1LL << 17, MLX4_DEV_CAP_FLAG2_80_VFS = 1LL << 18, MLX4_DEV_CAP_FLAG2_FS_A0 = 1LL << 19, - MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20 + MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20, + MLX4_DEV_CAP_FLAG2_PORT_REMAP = 1LL << 21 }; enum { @@ -253,9 +254,14 @@ enum { MLX4_BMME_FLAG_TYPE_2_WIN = 1 << 9, MLX4_BMME_FLAG_RESERVED_LKEY = 1 << 10, MLX4_BMME_FLAG_FAST_REG_WR = 1 << 11, + MLX4_BMME_FLAG_PORT_REMAP = 1 << 24, MLX4_BMME_FLAG_VSD_INIT2RTR = 1 << 28, }; +enum { + MLX4_FLAG_PORT_REMAP = MLX4_BMME_FLAG_PORT_REMAP +}; + enum mlx4_event { MLX4_EVENT_TYPE_COMP = 0x00, MLX4_EVENT_TYPE_PATH_MIG = 0x01, @@ -1378,6 +1384,8 @@ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port); int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port); int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port); +int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis); +int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2); int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port); int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 467ccdf94c98..2bbc62aa818a 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -96,6 +96,7 @@ enum { MLX4_QP_BIT_RRE = 1 << 15, MLX4_QP_BIT_RWE = 1 << 14, MLX4_QP_BIT_RAE = 1 << 13, + MLX4_QP_BIT_FPP = 1 << 3, MLX4_QP_BIT_RIC = 1 << 4, }; -- cgit v1.2.3 From 53f33ae295a5098f12218da1400f55ad7df7447c Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Tue, 3 Feb 2015 16:48:33 +0200 Subject: net/mlx4_core: Port aggregation upper layer interface Supply interface functions to bond and unbond ports of a mlx4 internal interfaces. Example for such an interface is the one registered by the mlx4 IB driver under RoCE. There are 1. Functions to go in/out to/from bonded mode 2. Function to remap virtual ports to physical ports The bond_mutex prevents simultaneous access to data that keep status of the device in bonded mode. The upper mlx4 interface marks to the mlx4 core module that they want to be subject for such bonding by setting the MLX4_INTFF_BONDING flag. Interface which goes to/from bonded mode is re-created. The mlx4 Ethernet driver does not set this flag when registering the interface, the IB driver does. Signed-off-by: Moni Shoua Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 1 + include/linux/mlx4/driver.h | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index d9afd99dde39..977b0b164431 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -70,6 +70,7 @@ enum { MLX4_FLAG_SLAVE = 1 << 3, MLX4_FLAG_SRIOV = 1 << 4, MLX4_FLAG_OLD_REG_MAC = 1 << 6, + MLX4_FLAG_BONDED = 1 << 7 }; enum { diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 022055c8fb26..9553a73d2049 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -49,6 +49,10 @@ enum mlx4_dev_event { MLX4_DEV_EVENT_SLAVE_SHUTDOWN, }; +enum { + MLX4_INTFF_BONDING = 1 << 0 +}; + struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); @@ -57,11 +61,26 @@ struct mlx4_interface { void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); struct list_head list; enum mlx4_protocol protocol; + int flags; }; int mlx4_register_interface(struct mlx4_interface *intf); void mlx4_unregister_interface(struct mlx4_interface *intf); +int mlx4_bond(struct mlx4_dev *dev); +int mlx4_unbond(struct mlx4_dev *dev); +static inline int mlx4_is_bonded(struct mlx4_dev *dev) +{ + return !!(dev->flags & MLX4_FLAG_BONDED); +} + +struct mlx4_port_map { + u8 port1; + u8 port2; +}; + +int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p); + void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); static inline u64 mlx4_mac_to_u64(u8 *addr) -- cgit v1.2.3 From f2dba9c6ff0d9a515b4c3f1b037cd65c8b2a868c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 4 Feb 2015 07:33:23 +1100 Subject: rhashtable: Introduce rhashtable_walk_* Some existing rhashtable users get too intimate with it by walking the buckets directly. This prevents us from easily changing the internals of rhashtable. This patch adds the helpers rhashtable_walk_init/exit/start/next/stop which will replace these custom walkers. They are meant to be usable for both procfs seq_file walks as well as walking by a netlink dump. The iterator structure should fit inside a netlink dump cb structure, with at least one element to spare. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e0337844358e..58851275fed9 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -18,6 +18,7 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H +#include #include #include #include @@ -111,6 +112,7 @@ struct rhashtable_params { * @p: Configuration parameters * @run_work: Deferred worker to expand/shrink asynchronously * @mutex: Mutex to protect current/future table swapping + * @walkers: List of active walkers * @being_destroyed: True if table is set up for destruction */ struct rhashtable { @@ -121,9 +123,36 @@ struct rhashtable { struct rhashtable_params p; struct work_struct run_work; struct mutex mutex; + struct list_head walkers; bool being_destroyed; }; +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @resize: Resize event occured + */ +struct rhashtable_walker { + struct list_head list; + bool resize; +}; + +/** + * struct rhashtable_iter - Hash table iterator, fits into netlink cb + * @ht: Table to iterate through + * @p: Current pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhashtable_walker *walker; + unsigned int slot; + unsigned int skip; +}; + static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) { return NULLS_MARKER(ht->p.nulls_base + hash); @@ -179,6 +208,12 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht, bool (*compare)(void *, void *), void *arg); +int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); +void rhashtable_walk_exit(struct rhashtable_iter *iter); +int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU); +void *rhashtable_walk_next(struct rhashtable_iter *iter); +void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); + void rhashtable_destroy(struct rhashtable *ht); #define rht_dereference(p, ht) \ -- cgit v1.2.3 From cfd8fef322305bbe9955817464f0d2054ce545c0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 13 Jan 2015 19:08:13 +0200 Subject: dmaengine: dw: amend description of dma_dev field The dma_dev field is widely used in filter functions to mach with a proper DMA controller device. Thus it's not deprecated. The patch fixes the description of that field. There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index d8155c005242..359127d290e7 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -16,7 +16,7 @@ /** * struct dw_dma_slave - Controller-specific information about a slave * - * @dma_dev: required DMA master device. Depricated. + * @dma_dev: required DMA master device * @src_id: src request line * @dst_id: dst request line * @src_master: src master for transfers on allocated channel. -- cgit v1.2.3 From d8ded50f8b26a224df48f9f93e49440c6a39b77f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 13 Jan 2015 19:08:14 +0200 Subject: dmaengine: dw: define DW_DMA_MAX_NR_MASTERS Instead of using magic number in the code the patch provides DW_DMA_MAX_NR_MASTERS constant. While here, restrict the reading of data width array by amount of the actual number of AHB masters. Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-dw.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h index 359127d290e7..87ac14c584f2 100644 --- a/include/linux/platform_data/dma-dw.h +++ b/include/linux/platform_data/dma-dw.h @@ -13,6 +13,8 @@ #include +#define DW_DMA_MAX_NR_MASTERS 4 + /** * struct dw_dma_slave - Controller-specific information about a slave * @@ -53,7 +55,7 @@ struct dw_dma_platform_data { unsigned char chan_priority; unsigned short block_size; unsigned char nr_masters; - unsigned char data_width[4]; + unsigned char data_width[DW_DMA_MAX_NR_MASTERS]; }; #endif /* _PLATFORM_DATA_DMA_DW_H */ -- cgit v1.2.3 From 0ae45f63d4ef8d8eeec49c7d8b44a1775fff13e8 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 2 Feb 2015 00:37:00 -0500 Subject: vfs: add support for a lazytime mount option Add a new mount option which enables a new "lazytime" mode. This mode causes atime, mtime, and ctime updates to only be made to the in-memory version of the inode. The on-disk times will only get updated when (a) if the inode needs to be updated for some non-time related change, (b) if userspace calls fsync(), syncfs() or sync(), or (c) just before an undeleted inode is evicted from memory. This is OK according to POSIX because there are no guarantees after a crash unless userspace explicitly requests via a fsync(2) call. For workloads which feature a large number of random write to a preallocated file, the lazytime mount option significantly reduces writes to the inode table. The repeated 4k writes to a single block will result in undesirable stress on flash devices and SMR disk drives. Even on conventional HDD's, the repeated writes to the inode table block will trigger Adjacent Track Interference (ATI) remediation latencies, which very negatively impact long tail latencies --- which is a very big deal for web serving tiers (for example). Google-Bug-Id: 18297052 Signed-off-by: Theodore Ts'o Signed-off-by: Al Viro --- include/linux/backing-dev.h | 1 + include/linux/fs.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5da6012b7a14..4cdf7336f64a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -55,6 +55,7 @@ struct bdi_writeback { struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ + struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..cd027ce2c705 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1746,8 +1746,12 @@ struct super_operations { #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) +#define I_DIRTY_TIME (1 << 11) +#define __I_DIRTY_TIME_EXPIRED 12 +#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) +#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) @@ -1910,6 +1914,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); +extern int generic_update_time(struct inode *, struct timespec *, int); static inline struct inode *file_inode(const struct file *f) { -- cgit v1.2.3 From fe032c422c5ba562ba9c2d316f55e258e03259c6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 2 Feb 2015 00:37:01 -0500 Subject: vfs: add find_inode_nowait() function Add a new function find_inode_nowait() which is an even more general version of ilookup5_nowait(). It is designed for callers which need very fine grained control over when the function is allowed to block or increment the inode's reference count. Signed-off-by: Theodore Ts'o Signed-off-by: Al Viro --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cd027ce2c705..5ea8b6e46a3d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2441,6 +2441,11 @@ extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); +extern struct inode *find_inode_nowait(struct super_block *, + unsigned long, + int (*match)(struct inode *, + unsigned long, void *), + void *data); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 1c2b364b225a5a93dbd1f317bd000d2fec2694be Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Thu, 5 Feb 2015 17:22:26 +0800 Subject: kvm: remove KVM_MMIO_SIZE After f78146b0f923, "KVM: Fix page-crossing MMIO", and 87da7e66a405, "KVM: x86: fix vcpu->mmio_fragments overflow", actually KVM_MMIO_SIZE is gone. Signed-off-by: Tiejun Chen Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 32d057571bf6..8a82838034f1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -33,10 +33,6 @@ #include -#ifndef KVM_MMIO_SIZE -#define KVM_MMIO_SIZE 8 -#endif - /* * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used * in kvm, other bits are visible for userspace which are defined in -- cgit v1.2.3 From 7fbc1067f06098c6b674e672fbb17e758fcc9402 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Oct 2013 10:32:35 +0100 Subject: exportfs: add methods for block layout exports Add three methods to allow exporting pnfs block layout volumes: - get_uuid: get a filesystem unique signature exposed to clients - map_blocks: map and if nessecary allocate blocks for a layout - commit_blocks: commit blocks in a layout once the client is done with them For now we stick the external pnfs block layout interfaces into s_export_op to avoid mixing them up with the internal interface between the NFS server and the layout drivers. Once we've fully internalized the latter interface we can redecide if these methods should stay in s_export_ops. Signed-off-by: Christoph Hellwig --- include/linux/exportfs.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 41b223a59a63..fa05e04c5531 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -4,6 +4,7 @@ #include struct dentry; +struct iattr; struct inode; struct super_block; struct vfsmount; @@ -180,6 +181,21 @@ struct fid { * get_name is not (which is possibly inconsistent) */ +/* types of block ranges for multipage write mappings. */ +#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ +#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ +#define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ +#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ + +#define IOMAP_NULL_BLOCK -1LL /* blkno is not valid */ + +struct iomap { + sector_t blkno; /* first sector of mapping */ + loff_t offset; /* file offset of mapping, bytes */ + u64 length; /* length of mapping, bytes */ + int type; /* type of mapping */ +}; + struct export_operations { int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); @@ -191,6 +207,13 @@ struct export_operations { struct dentry *child); struct dentry * (*get_parent)(struct dentry *child); int (*commit_metadata)(struct inode *inode); + + int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset); + int (*map_blocks)(struct inode *inode, loff_t offset, + u64 len, struct iomap *iomap, + bool write, u32 *device_generation); + int (*commit_blocks)(struct inode *inode, struct iomap *iomaps, + int nr_iomaps, struct iattr *iattr); }; extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, -- cgit v1.2.3 From ae58d882bfd3e537b1ed4a4c3577ca9ba853f0d8 Mon Sep 17 00:00:00 2001 From: James Hogan Date: Mon, 19 Jan 2015 12:00:55 +0000 Subject: MIPS: cevt-r4k: Drop GIC special case The cevt-r4k driver used to call into the GIC driver to find whether the timer was pending, but only with External Interrupt Controller (EIC) mode, where the Cause.IP bits can't be used as they encode the interrupt priority level (Cause.RIPL) instead. However commit e9de688dac65 ("irqchip: mips-gic: Support local interrupts") changed the condition from cpu_has_veic to gic_present. This fails on cores such as P5600 which have a GIC but the local interrupts aren't routable by the GIC, causing c0_compare_int_usable() to consider the interrupt unusable so r4k_clockevent_init() fails. The previous behaviour, added in commit 98b67c37db33 ("MIPS: Add EIC support for GIC."), wasn't really correct either as far as I can tell, since P5600 apparently supports EIC mode too, and in any case the use of Cause.TI with r2 should have been sufficient anyway since commit 010c108d7af7 ("MIPS: PowerTV: Fix support for timer interrupts with > 64 external IRQs"). Therefore drop the call into the gic driver altogether, and add a comment in c0_compare_int_pending() to clarify that Cause.TI does get checked since MIPS r2. Signed-off-by: James Hogan Fixes: e9de688dac65 ("irqchip: mips-gic: Support local interrupts") Reviewed-by: Andrew Bresticker Cc: Ralf Baechle Cc: Steven J. Hill Cc: Qais Yousef Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/9077/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 420f77b34d02..e6a6aac451db 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -243,7 +243,6 @@ extern void gic_write_cpu_compare(cycle_t cnt, int cpu); extern void gic_send_ipi(unsigned int intr); extern unsigned int plat_ipi_call_int_xlate(unsigned int); extern unsigned int plat_ipi_resched_int_xlate(unsigned int); -extern unsigned int gic_get_timer_pending(void); extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From 90e97820619dc912b52cc9d103272819d8b51259 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 5 Feb 2015 13:44:43 +0800 Subject: resources: Move struct resource_list_entry from ACPI into resource core Currently ACPI, PCI and pnp all implement the same resource list management with different data structure. We need to transfer from one data structure into another when passing resources from one subsystem into another subsystem. So move struct resource_list_entry from ACPI into resource core and rename it as resource_entry, then it could be reused by different subystems and avoid the data structure conversion. Introduce dedicated header file resource_ext.h instead of embedding it into ioport.h to avoid header file inclusion order issues. Signed-off-by: Jiang Liu Acked-by: Vinod Koul Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 12 +------ include/linux/resource_ext.h | 77 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+), 11 deletions(-) create mode 100644 include/linux/resource_ext.h (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e818decb631f..e53822148b6a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -27,6 +27,7 @@ #include #include /* for struct resource */ +#include #include #include @@ -285,11 +286,6 @@ extern int pnpacpi_disabled; #define PXM_INVAL (-1) -struct resource_win { - struct resource res; - resource_size_t offset; -}; - bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, @@ -300,12 +296,6 @@ unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -struct resource_list_entry { - struct list_head node; - struct resource res; - resource_size_t offset; -}; - void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h new file mode 100644 index 000000000000..e2bf63d881d4 --- /dev/null +++ b/include/linux/resource_ext.h @@ -0,0 +1,77 @@ +/* + * Copyright (C) 2015, Intel Corporation + * Author: Jiang Liu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#ifndef _LINUX_RESOURCE_EXT_H +#define _LINUX_RESOURCE_EXT_H +#include +#include +#include +#include + +/* Represent resource window for bridge devices */ +struct resource_win { + struct resource res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ +}; + +/* + * Common resource list management data structure and interfaces to support + * ACPI, PNP and PCI host bridge etc. + */ +struct resource_entry { + struct list_head node; + struct resource *res; /* In master (CPU) address space */ + resource_size_t offset; /* Translation offset for bridge */ + struct resource __res; /* Default storage for res */ +}; + +extern struct resource_entry * +resource_list_create_entry(struct resource *res, size_t extra_size); +extern void resource_list_free(struct list_head *head); + +static inline void resource_list_add(struct resource_entry *entry, + struct list_head *head) +{ + list_add(&entry->node, head); +} + +static inline void resource_list_add_tail(struct resource_entry *entry, + struct list_head *head) +{ + list_add_tail(&entry->node, head); +} + +static inline void resource_list_del(struct resource_entry *entry) +{ + list_del(&entry->node); +} + +static inline void resource_list_free_entry(struct resource_entry *entry) +{ + kfree(entry); +} + +static inline void +resource_list_destroy_entry(struct resource_entry *entry) +{ + resource_list_del(entry); + resource_list_free_entry(entry); +} + +#define resource_list_for_each_entry(entry, list) \ + list_for_each_entry((entry), (list), node) + +#define resource_list_for_each_entry_safe(entry, tmp, list) \ + list_for_each_entry_safe((entry), (tmp), (list), node) + +#endif /* _LINUX_RESOURCE_EXT_H */ -- cgit v1.2.3 From 14d76b68f2819a1d0b50236a7e9e9f2ea69869d9 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Thu, 5 Feb 2015 13:44:44 +0800 Subject: PCI: Use common resource list management code instead of private implementation Use common resource list management data structure and interfaces instead of private implementation. Signed-off-by: Jiang Liu Acked-by: Will Deacon Acked-by: Bjorn Helgaas Signed-off-by: Rafael J. Wysocki --- include/linux/pci.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9603094ed59b..faa60fa26314 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -397,16 +398,10 @@ static inline int pci_channel_offline(struct pci_dev *pdev) return (pdev->error_state != pci_channel_io_normal); } -struct pci_host_bridge_window { - struct list_head list; - struct resource *res; /* host bridge aperture (CPU address) */ - resource_size_t offset; /* bus address + offset = CPU address */ -}; - struct pci_host_bridge { struct device dev; struct pci_bus *bus; /* root bus */ - struct list_head windows; /* pci_host_bridge_windows */ + struct list_head windows; /* resource_entry */ void (*release_fn)(struct pci_host_bridge *); void *release_data; }; -- cgit v1.2.3 From ecf5636dcd59cd5508641f995cc4c2bafedbb995 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 5 Feb 2015 13:44:48 +0800 Subject: ACPI: Add interfaces to parse IOAPIC ID for IOAPIC hotplug We need to parse APIC ID for IOAPIC registration for IOAPIC hotplug. ACPI _MAT method and MADT table are used to figure out IOAPIC ID, just like parsing CPU APIC ID for CPU hotplug. [ tglx: Fixed docbook comment ] Signed-off-by: Yinghai Lu Signed-off-by: Jiang Liu Cc: Konrad Rzeszutek Wilk Cc: Tony Luck Cc: Joerg Roedel Cc: Greg Kroah-Hartman Cc: Benjamin Herrenschmidt Cc: Rafael J. Wysocki Cc: Bjorn Helgaas Cc: Randy Dunlap Cc: Borislav Petkov Cc: Len Brown Link: http://lkml.kernel.org/r/1414387308-27148-8-git-send-email-jiang.liu@linux.intel.com Signed-off-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index e53822148b6a..24c7aa8b1d20 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -152,6 +152,10 @@ int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC +int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); +#endif + int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); -- cgit v1.2.3 From ddad8dd0a162fde61646a627a3017c258601dc8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Jan 2015 16:16:29 +0100 Subject: block: use blk_rq_map_user_iov to implement blk_rq_map_user Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index efead0b532c4..d0d6735d61da 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -428,8 +428,6 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); extern int bio_get_nr_vecs(struct block_device *); -extern struct bio *bio_map_user(struct request_queue *, struct block_device *, - unsigned long, unsigned int, int, gfp_t); struct sg_iovec; struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, @@ -462,8 +460,6 @@ static inline void bio_flush_dcache_pages(struct bio *bi) extern void bio_copy_data(struct bio *dst, struct bio *src); extern int bio_alloc_pages(struct bio *bio, gfp_t gfp); -extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *, - unsigned long, unsigned int, int, gfp_t); extern struct bio *bio_copy_user_iov(struct request_queue *, struct rq_map_data *, const struct sg_iovec *, -- cgit v1.2.3 From 26e49cfc7e988a76bf1e55cef0d9e438e5489180 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 18 Jan 2015 16:16:31 +0100 Subject: block: pass iov_iter to the BLOCK_PC mapping functions Make use of a new interface provided by iov_iter, backed by scatter-gather list of iovec, instead of the old interface based on sg_iovec. Also use iov_iter_advance() instead of manual iteration. This commit should contain only literal replacements, without functional changes. Cc: Christoph Hellwig Cc: Jens Axboe Cc: Doug Gilbert Cc: "James E.J. Bottomley" Signed-off-by: Kent Overstreet [dpark: add more description in commit message] Signed-off-by: Dongsu Park [hch: fixed to do a deep clone of the iov_iter, and to properly use the iov_iter direction] Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 +++---- include/linux/blkdev.h | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index d0d6735d61da..0d6105b34ffa 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -428,11 +428,10 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); extern int bio_get_nr_vecs(struct block_device *); -struct sg_iovec; struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, struct block_device *, - const struct sg_iovec *, int, int, gfp_t); + const struct iov_iter *, gfp_t); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, gfp_t); @@ -462,8 +461,8 @@ extern int bio_alloc_pages(struct bio *bio, gfp_t gfp); extern struct bio *bio_copy_user_iov(struct request_queue *, struct rq_map_data *, - const struct sg_iovec *, - int, int, gfp_t); + const struct iov_iter *, + gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio(struct bio *bio); extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 13e16401a7ce..bf4ef666d191 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -855,8 +855,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *, extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, - struct rq_map_data *, const struct sg_iovec *, - int, unsigned int, gfp_t); + struct rq_map_data *, const struct iov_iter *, + gfp_t); extern int blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, -- cgit v1.2.3 From 37f19e57a0de3c4a3417aa13ff4d04f1e0dee4b3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 18 Jan 2015 16:16:33 +0100 Subject: block: merge __bio_map_user_iov into bio_map_user_iov And also remove the unused bdev argument. Signed-off-by: Christoph Hellwig Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0d6105b34ffa..da3a127c9958 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -430,7 +430,6 @@ extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, extern int bio_get_nr_vecs(struct block_device *); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, - struct block_device *, const struct iov_iter *, gfp_t); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, -- cgit v1.2.3 From 472e259449819d939b5a5188b6f4c7d59aa4304c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:50:30 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutcommit If we're sending an asynchronous layoutcommit, then we need to ensure that the inode and the super block remain pinned. Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 2c35e2affa6f..bb0d56f737e0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -285,6 +285,7 @@ struct nfs4_layoutcommit_data { struct nfs_fattr fattr; struct list_head lseg_list; struct rpc_cred *cred; + struct inode *inode; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; }; -- cgit v1.2.3 From 5a0ec8acb945e302ce819b4a9787796ccf284548 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 5 Feb 2015 16:35:16 -0500 Subject: NFSv4.1: Pin the inode and super block in asynchronous layoutreturns If we're sending an asynchronous layoutreturn, then we need to ensure that the inode and the super block remain pinned. Cc: Peng Tao Signed-off-by: Trond Myklebust Reviewed-by: Peng Tao --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index bb0d56f737e0..38d96ba935c2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -310,6 +310,7 @@ struct nfs4_layoutreturn { struct nfs4_layoutreturn_res res; struct rpc_cred *cred; struct nfs_client *clp; + struct inode *inode; int rpc_status; }; -- cgit v1.2.3 From a9b2c06dbef48ed31cff1764c5ce824829106f4f Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Fri, 6 Feb 2015 16:04:39 -0500 Subject: tcp: mitigate ACK loops for connections as tcp_request_sock In the SYN_RECV state, where the TCP connection is represented by tcp_request_sock, we now rate-limit SYNACKs in response to a client's retransmitted SYNs: we do not send a SYNACK in response to client SYN if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a SYNACK in response to a client's retransmitted SYN. This allows the vast majority of legitimate client connections to proceed unimpeded, even for the most aggressive platforms, iOS and MacOS, which actually retransmit SYNs 1-second intervals for several times in a row. They use SYN RTO timeouts following the progression: 1,1,1,1,1,2,4,8,16,32. Reported-by: Avery Fay Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 67309ece0772..bcc828d3b9b9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -115,6 +115,7 @@ struct tcp_request_sock { u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ + u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# * after data-in-SYN. -- cgit v1.2.3 From f2b2c582e82429270d5818fbabe653f4359d7024 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Fri, 6 Feb 2015 16:04:40 -0500 Subject: tcp: mitigate ACK loops for connections as tcp_sock Ensure that in state ESTABLISHED, where the connection is represented by a tcp_sock, we rate limit dupacks in response to incoming packets (a) with TCP timestamps that fail PAWS checks, or (b) with sequence numbers or ACK numbers that are out of the acceptable window. We do not send a dupack in response to out-of-window packets if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a dupack in response to an out-of-window packet. There is already a similar (although global) rate-limiting mechanism for "challenge ACKs". When deciding whether to send a challence ACK, we first consult the new per-connection rate limit, and then the global rate limit. Reported-by: Avery Fay Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index bcc828d3b9b9..66d85a80a1ec 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -153,6 +153,7 @@ struct tcp_sock { u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ + u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ u32 tsoffset; /* timestamp offset */ -- cgit v1.2.3 From 4fb17a6091674f469e8ac85dc770fbf9a9ba7cc8 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Fri, 6 Feb 2015 16:04:41 -0500 Subject: tcp: mitigate ACK loops for connections as tcp_timewait_sock Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is represented by a tcp_timewait_sock, we rate limit dupacks in response to incoming packets (a) with TCP timestamps that fail PAWS checks, or (b) with sequence numbers that are out of the acceptable window. We do not send a dupack in response to out-of-window packets if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we last sent a dupack in response to an out-of-window packet. Reported-by: Avery Fay Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 66d85a80a1ec..1a7adb411647 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -342,6 +342,10 @@ struct tcp_timewait_sock { u32 tw_rcv_wnd; u32 tw_ts_offset; u32 tw_ts_recent; + + /* The time we sent the last out-of-window ACK: */ + u32 tw_last_oow_ack_time; + long tw_ts_recent_stamp; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; -- cgit v1.2.3 From 096a4cfa5807aa89c78ce12309c0b1c10cf88184 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 6 Feb 2015 18:54:19 +0100 Subject: net: fix a typo in skb_checksum_validate_zero_check Remove trailing underscore. Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 111e665455c3..1bb36edb66b9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3072,7 +3072,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ - __skb_checksum_validate_(skb, proto, true, true, check, compute_pseudo) + __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) -- cgit v1.2.3 From 567e4b79731c352a17d73c483959f795d3593e03 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Feb 2015 12:59:01 -0800 Subject: net: rfs: add hash collision detection Receive Flow Steering is a nice solution but suffers from hash collisions when a mix of connected and unconnected traffic is received on the host, when flow hash table is populated. Also, clearing flow in inet_release() makes RFS not very good for short lived flows, as many packets can follow close(). (FIN , ACK packets, ...) This patch extends the information stored into global hash table to not only include cpu number, but upper part of the hash value. I use a 32bit value, and dynamically split it in two parts. For host with less than 64 possible cpus, this gives 6 bits for the cpu number, and 26 (32-6) bits for the upper part of the hash. Since hash bucket selection use low order bits of the hash, we have a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big enough. If the hash found in flow table does not match, we fallback to RPS (if it is enabled for the rxqueue). This means that a packet for an non connected flow can avoid the IPI through a unrelated/victim CPU. This also means we no longer have to clear the table at socket close time, and this helps short lived flows performance. Signed-off-by: Eric Dumazet Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ce784d5018e0..ab3b7cef4638 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -644,39 +644,39 @@ struct rps_dev_flow_table { /* * The rps_sock_flow_table contains mappings of flows to the last CPU * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high order bits + * of flow hash, lower part is cpu number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. */ struct rps_sock_flow_table { - unsigned int mask; - u16 ents[0]; + u32 mask; + u32 ents[0]; }; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ - ((_num) * sizeof(u16))) +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) #define RPS_NO_CPU 0xffff +extern u32 rps_cpu_mask; +extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; + static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash) { if (table && hash) { - unsigned int cpu, index = hash & table->mask; + unsigned int index = hash & table->mask; + u32 val = hash & ~rps_cpu_mask; /* We only give a hint, preemption can change cpu under us */ - cpu = raw_smp_processor_id(); + val |= raw_smp_processor_id(); - if (table->ents[index] != cpu) - table->ents[index] = cpu; + if (table->ents[index] != val) + table->ents[index] = val; } } -static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) - table->ents[hash & table->mask] = RPS_NO_CPU; -} - -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); -- cgit v1.2.3 From 718ba5b87343df303017585200ee182e937eabfc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 18:19:25 -0500 Subject: SUNRPC: Add helpers to prevent socket create from racing The socket lock is currently held by the task that is requesting the connection be established. While that is efficient in the case where the connection happens quickly, it is racy in the case where it doesn't. What we really want is for the connect helper to be able to block access to the socket while it is being set up. This patch does so by arranging to transfer the socket lock from the task that is requesting the connect attempt, and then releasing that lock once everything is done. This scheme also gives us automatic protection against collisions with the RPC close code, so we can kill the cancel_delayed_work_sync() call in xs_close(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 9d27ac45b909..2926e618dbc6 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -347,6 +347,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); int xs_swapper(struct rpc_xprt *xprt, int enable); +bool xprt_lock_connect(struct rpc_xprt *, struct rpc_task *, void *); +void xprt_unlock_connect(struct rpc_xprt *, void *); + /* * Reserved bit positions in xprt->state */ -- cgit v1.2.3 From 4efdd92c921135175a85452cd41273d9e2788db3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 15:34:28 -0500 Subject: SUNRPC: Remove TCP client connection reset hack Instead we rely on SO_REUSEPORT to provide the reconnection semantics that we need for NFSv2/v3. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 2926e618dbc6..86af854338b5 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -363,7 +363,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) -#define XPRT_CONNECTION_REUSE (10) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.2.3 From 93c1af6ca94c1e763efba76a127b5c135e3d23a6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 8 Feb 2015 20:39:13 -0800 Subject: net:rfs: adjust table size checking Make sure root user does not try something stupid. Also make sure mask field in struct rps_sock_flow_table does not share a cache line with the potentially often dirtied flow table. Signed-off-by: Eric Dumazet Fixes: 567e4b79731c ("net: rfs: add hash collision detection") Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ab3b7cef4638..d115256ed5a2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -653,7 +653,8 @@ struct rps_dev_flow_table { */ struct rps_sock_flow_table { u32 mask; - u32 ents[0]; + + u32 ents[0] ____cacheline_aligned_in_smp; }; #define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) -- cgit v1.2.3 From 505936f59f1e4cd0ff92ae5abc7aae64fb74dbdb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 16:00:01 -0500 Subject: SUNRPC: Cleanup to remove remaining uses of XPRT_CONNECTION_ABORT Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 86af854338b5..ae39d478a272 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) -- cgit v1.2.3 From 9e2b9f37760e129cee053cc7b6e7288acc2a7134 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 8 Feb 2015 19:21:27 -0500 Subject: SUNRPC: Remove the redundant XPRT_CONNECTION_CLOSE flag Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index ae39d478a272..8b93ef53df3c 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -360,7 +360,6 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_BOUND (4) #define XPRT_BINDING (5) #define XPRT_CLOSING (6) -#define XPRT_CONNECTION_CLOSE (8) #define XPRT_CONGESTED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) -- cgit v1.2.3 From dbf9782c1078c537831201c73ac60c9623ae9370 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 16 Dec 2014 18:44:36 -0500 Subject: dm: remove exports for request-based interfaces without external callers Remove exports for dm_dispatch_request, dm_requeue_unmapped_request, and dm_kill_unmapped_request. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ca6d2acc5eb7..19296fba58e8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -600,9 +600,6 @@ static inline unsigned long to_bytes(sector_t n) /*----------------------------------------------------------------- * Helper for block layer and dm core operations *---------------------------------------------------------------*/ -void dm_dispatch_request(struct request *rq); -void dm_requeue_unmapped_request(struct request *rq); -void dm_kill_unmapped_request(struct request *rq, int error); int dm_underlying_device_busy(struct request_queue *q); #endif /* _LINUX_DEVICE_MAPPER_H */ -- cgit v1.2.3 From e5863d9ad754926e7d3f38b43ac8bd48ef73b097 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 17 Dec 2014 21:08:12 -0500 Subject: dm: allocate requests in target when stacking on blk-mq devices For blk-mq request-based DM the responsibility of allocating a cloned request is transfered from DM core to the target type. Doing so enables the cloned request to be allocated from the appropriate blk-mq request_queue's pool (only the DM target, e.g. multipath, can know which block device to send a given cloned request to). Care was taken to preserve compatibility with old-style block request completion that requires request-based DM _not_ acquire the clone request's queue lock in the completion path. As such, there are now 2 different request-based DM target_type interfaces: 1) the original .map_rq() interface will continue to be used for non-blk-mq devices -- the preallocated clone request is passed in from DM core. 2) a new .clone_and_map_rq() and .release_clone_rq() will be used for blk-mq devices -- blk_get_request() and blk_put_request() are used respectively from these hooks. dm_table_set_type() was updated to detect if the request-based target is being stacked on blk-mq devices, if so DM_TYPE_MQ_REQUEST_BASED is set. DM core disallows switching the DM table's type after it is set. This means that there is no mixing of non-blk-mq and blk-mq devices within the same request-based DM table. [This patch was started by Keith and later heavily modified by Mike] Tested-by: Bart Van Assche Signed-off-by: Keith Busch Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 19296fba58e8..2646aed1d3fe 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -48,6 +48,11 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti); typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio); typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone, union map_info *map_context); +typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti, + struct request *rq, + union map_info *map_context, + struct request **clone); +typedef void (*dm_release_clone_request_fn) (struct request *clone); /* * Returns: @@ -143,6 +148,8 @@ struct target_type { dm_dtr_fn dtr; dm_map_fn map; dm_map_request_fn map_rq; + dm_clone_and_map_request_fn clone_and_map_rq; + dm_release_clone_request_fn release_clone_rq; dm_endio_fn end_io; dm_request_endio_fn rq_end_io; dm_presuspend_fn presuspend; -- cgit v1.2.3 From 35f05dabf95ac3ebc4c15bafd6833f7a3046e66f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 8 Feb 2015 11:49:34 +0200 Subject: IB/mlx4: Reset flow support for IB kernel ULPs The driver exposes interfaces that directly relate to HW state. Upon fatal error, consumers of these interfaces (ULPs) that rely on completion of all their posted work-request could hang, thereby introducing dependencies in shutdown order. To prevent this from happening, we manage the relevant resources (CQs, QPs) that are used by the device. Upon a fatal error, we now generate simulated completions for outstanding WQEs that were not completed at the time the HW was reset. It includes invoking the completion event handler for all involved CQs so that the ULPs will poll those CQs. When polled we return simulated CQEs with IB_WC_WR_FLUSH_ERR return code enabling ULPs to clean up their resources and not wait forever for completions upon receiving remove_one. The above change requires an extra check in the data path to make sure that when device is in error state, the simulated CQEs will be returned and no further WQEs will be posted. Signed-off-by: Yishai Hadas Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index c116cb02475c..e4ebff7e9d02 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -689,6 +689,8 @@ struct mlx4_cq { void (*comp)(struct mlx4_cq *); void *priv; } tasklet_ctx; + int reset_notify_added; + struct list_head reset_notify; }; struct mlx4_qp { -- cgit v1.2.3 From 3cf385713460eb2bb4cb7ceb8ed89833b00b594b Mon Sep 17 00:00:00 2001 From: Antonios Motakis Date: Tue, 6 Jan 2015 11:15:11 +0100 Subject: ARM: 8256/1: driver coamba: add device binding path 'driver_override' As already demonstrated with PCI [1] and the platform bus [2], a driver_override property in sysfs can be used to bypass the id matching of a device to a AMBA driver. This can be used by VFIO to bind to any AMBA device requested by the user. [1] http://lists-archives.com/linux-kernel/28030441-pci-introduce-new-device-binding-path-using-pci_dev-driver_override.html [2] https://www.redhat.com/archives/libvir-list/2014-April/msg00382.html Signed-off-by: Antonios Motakis Reviewed-by: Kim Phillips Signed-off-by: Russell King --- include/linux/amba/bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 0ab5f8e0dea2..50fc66868402 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -33,6 +33,7 @@ struct amba_device { struct clk *pclk; unsigned int periphid; unsigned int irq[AMBA_NR_IRQS]; + char *driver_override; }; struct amba_driver { -- cgit v1.2.3 From 13060b64b819c194909121b90b5f8dd9abb5ea4e Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 6 Feb 2015 15:05:07 -0700 Subject: vfio: Add and use device request op for vfio bus drivers When a request is made to unbind a device from a vfio bus driver, we need to wait for the device to become unused, ie. for userspace to release the device. However, we have a long standing TODO in the code to do something proactive to make that happen. To enable this, we add a request callback on the vfio bus driver struct, which is intended to signal the user through the vfio device interface to release the device. Instead of passively waiting for the device to become unused, we can now pester the user to give it up. Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index d3204115f15d..2d67b8998fd8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -26,6 +26,7 @@ * @ioctl: Perform ioctl(2) on device file descriptor, supporting VFIO_DEVICE_* * operations documented below * @mmap: Perform mmap(2) on a region of the device file descriptor + * @request: Request for the bus driver to release the device */ struct vfio_device_ops { char *name; @@ -38,6 +39,7 @@ struct vfio_device_ops { long (*ioctl)(void *device_data, unsigned int cmd, unsigned long arg); int (*mmap)(void *device_data, struct vm_area_struct *vma); + void (*request)(void *device_data, unsigned int count); }; extern int vfio_add_group_dev(struct device *dev, -- cgit v1.2.3 From 201f201c33220f53856fd300e1990b779538d67f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 10 Feb 2015 13:31:34 -0700 Subject: blk-mq: make blk_mq_run_queues() static We no longer use it outside of blk-mq.c, so we can make it static and stop exporting it. Additionally, kill the 'async' argument, as there's only one used of it. Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 86b08b1a5eba..ac6c7f534de1 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -175,7 +175,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_insert_request(struct request *, bool, bool, bool); -void blk_mq_run_queues(struct request_queue *q, bool async); void blk_mq_free_request(struct request *rq); void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); -- cgit v1.2.3 From 6ee8e25fc3e916193bce4ebb43d5439e1e2144ab Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 10 Feb 2015 14:08:32 -0800 Subject: fsnotify: fix handling of renames in audit Commit e9fd702a58c4 ("audit: convert audit watches to use fsnotify instead of inotify") broke handling of renames in audit. Audit code wants to update inode number of an inode corresponding to watched name in a directory. When something gets renamed into a directory to a watched name, inotify previously passed moved inode to audit code however new fsnotify code passes directory inode where the change happened. That confuses audit and it starts watching parent directory instead of a file in a directory. This can be observed for example by doing: cd /tmp touch foo bar auditctl -w /tmp/foo touch foo mv bar foo touch foo In audit log we see events like: type=CONFIG_CHANGE msg=audit(1423563584.155:90): auid=1000 ses=2 op="updated rules" path="/tmp/foo" key=(null) list=4 res=1 ... type=PATH msg=audit(1423563584.155:91): item=2 name="bar" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE type=PATH msg=audit(1423563584.155:91): item=3 name="foo" inode=1046842 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE type=PATH msg=audit(1423563584.155:91): item=4 name="foo" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=CREATE ... and that's it - we see event for the first touch after creating the audit rule, we see events for rename but we don't see any event for the last touch. However we start seeing events for unrelated stuff happening in /tmp. Fix the problem by passing moved inode as data in the FS_MOVED_FROM and FS_MOVED_TO events instead of the directory where the change happens. This doesn't introduce any new problems because noone besides audit_watch.c cares about the passed value: fs/notify/fanotify/fanotify.c cares only about FSNOTIFY_EVENT_PATH events. fs/notify/dnotify/dnotify.c doesn't care about passed 'data' value at all. fs/notify/inotify/inotify_fsnotify.c uses 'data' only for FSNOTIFY_EVENT_PATH. kernel/audit_tree.c doesn't care about passed 'data' at all. kernel/audit_watch.c expects moved inode as 'data'. Fixes: e9fd702a58c49db ("audit: convert audit watches to use fsnotify instead of inotify") Signed-off-by: Jan Kara Cc: Paul Moore Cc: Eric Paris Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fsnotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1c804b057fb1..7ee1774edee5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie); - fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie); + fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name, + fs_cookie); + fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name, + fs_cookie); if (target) fsnotify_link_count(target); -- cgit v1.2.3 From ccaafd7fd039aebc9359a9799f8558b01f1c2adc Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 10 Feb 2015 14:09:35 -0800 Subject: mm: don't use compound_head() in virt_to_head_page() compound_head() is implemented with assumption that there would be race condition when checking tail flag. This assumption is only true when we try to access arbitrary positioned struct page. The situation that virt_to_head_page() is called is different case. We call virt_to_head_page() only in the range of allocated pages, so there is no race condition on tail flag. In this case, we don't need to handle race condition and we can reduce overhead slightly. This patch implements compound_head_fast() which is similar with compound_head() except tail flag race handling. And then, virt_to_head_page() uses this optimized function to improve performance. I saw 1.8% win in a fast-path loop over kmem_cache_alloc/free, (14.063 ns -> 13.810 ns) if target object is on tail page. Signed-off-by: Joonsoo Kim Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index dd5ea3016fc4..2c6fd3c5424a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -446,6 +446,12 @@ static inline struct page *compound_head_by_tail(struct page *tail) return tail; } +/* + * Since either compound page could be dismantled asynchronously in THP + * or we access asynchronously arbitrary positioned struct page, there + * would be tail flag race. To handle this race, we should call + * smp_rmb() before checking tail flag. compound_head_by_tail() did it. + */ static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) @@ -453,6 +459,18 @@ static inline struct page *compound_head(struct page *page) return page; } +/* + * If we access compound page synchronously such as access to + * allocated page, there is no need to handle tail flag race, so we can + * check tail flag directly without any synchronization primitive. + */ +static inline struct page *compound_head_fast(struct page *page) +{ + if (unlikely(PageTail(page))) + return page->first_page; + return page; +} + /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test @@ -531,7 +549,14 @@ static inline void get_page(struct page *page) static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); - return compound_head(page); + + /* + * We don't need to worry about synchronization of tail flag + * when we call virt_to_head_page() since it is only called for + * already allocated page and this page won't be freed until + * this virt_to_head_page() is finished. So use _fast variant. + */ + return compound_head_fast(page); } /* -- cgit v1.2.3 From c8d78c1823f46519473949d33f0d1d33fe21ea16 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:46 -0800 Subject: mm: replace remap_file_pages() syscall with emulation remap_file_pages(2) was invented to be able efficiently map parts of huge file into limited 32-bit virtual address space such as in database workloads. Nonlinear mappings are pain to support and it seems there's no legitimate use-cases nowadays since 64-bit systems are widely available. Let's drop it and get rid of all these special-cased code. The patch replaces the syscall with emulation which creates new VMA on each remap_file_pages(), unless they it can be merged with an adjacent one. I didn't find *any* real code that uses remap_file_pages(2) to test emulation impact on. I've checked Debian code search and source of all packages in ALT Linux. No real users: libc wrappers, mentions in strace, gdb, valgrind and this kind of stuff. There are few basic tests in LTP for the syscall. They work just fine with emulation. To test performance impact, I've written small test case which demonstrate pretty much worst case scenario: map 4G shmfs file, write to begin of every page pgoff of the page, remap pages in reverse order, read every page. The test creates 1 million of VMAs if emulation is in use, so I had to set vm.max_map_count to 1100000 to avoid -ENOMEM. Before: 23.3 ( +- 4.31% ) seconds After: 43.9 ( +- 0.85% ) seconds Slowdown: 1.88x I believe we can live with that. Test case: #define _GNU_SOURCE #include #include #include #include #define MB (1024UL * 1024) #define SIZE (4096 * MB) int main(int argc, char **argv) { unsigned long *p; long i, pass; for (pass = 0; pass < 10; pass++) { p = mmap(NULL, SIZE, PROT_READ|PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (p == MAP_FAILED) { perror("mmap"); return -1; } for (i = 0; i < SIZE / 4096; i++) p[i * 4096 / sizeof(*p)] = i; for (i = 0; i < SIZE / 4096; i++) { if (remap_file_pages(p + i * 4096 / sizeof(*p), 4096, 0, (SIZE - 4096 * (i + 1)) >> 12, 0)) { perror("remap_file_pages"); return -1; } } for (i = SIZE / 4096 - 1; i >= 0; i--) assert(p[i * 4096 / sizeof(*p)] == SIZE / 4096 - i - 1); munmap(p, SIZE); } return 0; } [akpm@linux-foundation.org: fix spello] [sasha.levin@oracle.com: initialize populate before usage] [sasha.levin@oracle.com: grab file ref to prevent race while mmaping] Signed-off-by: "Kirill A. Shutemov" Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Dave Jones Cc: Linus Torvalds Cc: Armin Rigo Signed-off-by: Sasha Levin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 42efe13077b6..60c4996df7f3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2481,8 +2481,12 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, - unsigned long size, pgoff_t pgoff); +static inline int generic_file_remap_pages(struct vm_area_struct *vma, + unsigned long addr, unsigned long size, pgoff_t pgoff) +{ + BUG(); + return 0; +} int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); -- cgit v1.2.3 From 8a5f14a23177061ec11daeaa3d09d0765d785c47 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:49 -0800 Subject: mm: drop support of non-linear mapping from unmap/zap codepath We have remap_file_pages(2) emulation in -mm tree for few release cycles and we plan to have it mainline in v3.20. This patchset removes rest of VM_NONLINEAR infrastructure. Patches 1-8 take care about generic code. They are pretty straight-forward and can be applied without other of patches. Rest patches removes pte_file()-related stuff from architecture-specific code. It usually frees up one bit in non-present pte. I've tried to reuse that bit for swap offset, where I was able to figure out how to do that. For obvious reason I cannot test all that arch-specific code and would like to see acks from maintainers. In total, remap_file_pages(2) required about 1.4K lines of not-so-trivial kernel code. That's too much for functionality nobody uses. Tested-by: Felipe Balbi This patch (of 38): We don't create non-linear mappings anymore. Let's drop code which handles them on unmap/zap. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2c6fd3c5424a..600ef5ed4698 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1146,7 +1146,6 @@ extern void user_shm_unlock(size_t, struct user_struct *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct vm_area_struct *nonlinear_vma; /* Check page->index if set */ struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ -- cgit v1.2.3 From 9b4bdd2ffab9557ac43af7dff02e7dab1c8c58bd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:51 -0800 Subject: mm: drop support of non-linear mapping from fault codepath We don't create non-linear mappings anymore. Let's drop code which handles them on page fault. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 600ef5ed4698..376e5c325dee 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -206,21 +206,19 @@ extern unsigned int kobjsize(const void *objp); extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ -#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ -#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ -#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ -#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ -#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ -#define FAULT_FLAG_TRIED 0x40 /* second try */ -#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */ +#define FAULT_FLAG_MKWRITE 0x02 /* Fault was mkwrite of existing pte */ +#define FAULT_FLAG_ALLOW_RETRY 0x04 /* Retry fault if blocking */ +#define FAULT_FLAG_RETRY_NOWAIT 0x08 /* Don't drop mmap_sem and wait when retrying */ +#define FAULT_FLAG_KILLABLE 0x10 /* The fault task is in SIGKILL killable region */ +#define FAULT_FLAG_TRIED 0x20 /* Second try */ +#define FAULT_FLAG_USER 0x40 /* The fault originated in userspace */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * - * pgoff should be used in favour of virtual_address, if possible. If pgoff - * is used, one may implement ->remap_pages to get nonlinear mapping support. + * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ -- cgit v1.2.3 From d83a08db5ba6072caa658745881f4baa9bad6a08 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:54 -0800 Subject: mm: drop vm_ops->remap_pages and generic_file_remap_pages() stub Nobody uses it anymore. [akpm@linux-foundation.org: fix filemap_xip.c] Signed-off-by: Kirill A. Shutemov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ------ include/linux/mm.h | 3 --- 2 files changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 60c4996df7f3..47f557c7ef7e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2481,12 +2481,6 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); -static inline int generic_file_remap_pages(struct vm_area_struct *vma, - unsigned long addr, unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/include/linux/mm.h b/include/linux/mm.h index 376e5c325dee..2ddd9d1d6268 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -285,9 +285,6 @@ struct vm_operations_struct { struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif - /* called by sys_remap_file_pages() to populate non-linear mapping */ - int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff); }; struct mmu_gather; -- cgit v1.2.3 From 27ba0644ea9dfe6e7693abc85837b60e40583b96 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:09:59 -0800 Subject: rmap: drop support of non-linear mappings We don't create non-linear mappings anymore. Let's drop code which handles them in rmap. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 +--- include/linux/mm.h | 6 ------ include/linux/mm_types.h | 4 +--- include/linux/rmap.h | 2 -- 4 files changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 47f557c7ef7e..60acab209701 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -401,7 +401,6 @@ struct address_space { spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root i_mmap; /* tree of private and shared mappings */ - struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -493,8 +492,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap) || - !list_empty(&mapping->i_mmap_nonlinear); + return !RB_EMPTY_ROOT(&mapping->i_mmap); } /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ddd9d1d6268..18391eec4864 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1796,12 +1796,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) -static inline void vma_nonlinear_insert(struct vm_area_struct *vma, - struct list_head *list) -{ - list_add_tail(&vma->shared.nonlinear, list); -} - void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6d34aa266a8c..3b1d20fb0848 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -273,15 +273,13 @@ struct vm_area_struct { /* * For areas with an address space and backing store, - * linkage into the address_space->i_mmap interval tree, or - * linkage of vma in the address_space->i_mmap_nonlinear list. + * linkage into the address_space->i_mmap interval tree. */ union { struct { struct rb_node rb; unsigned long rb_subtree_last; } linear; - struct list_head nonlinear; } shared; /* diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d9d7e7e56352..b38f559130d5 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -246,7 +246,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition - * file_nonlinear: for handling file nonlinear mapping * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ @@ -255,7 +254,6 @@ struct rmap_walk_control { int (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); - int (*file_nonlinear)(struct page *, struct address_space *, void *arg); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -- cgit v1.2.3 From ac51b934f3912582d3c897c6c4d09b32ea57b2c7 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:10:02 -0800 Subject: mm: replace vma->sharead.linear with vma->shared After removing vma->shared.nonlinear we have only one member of vma->shared union, which doesn't make much sense. This patch drops the union and move struct vma->shared.linear to vma->shared. Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3b1d20fb0848..07c8bd3f7b48 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -275,11 +275,9 @@ struct vm_area_struct { * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. */ - union { - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } linear; + struct { + struct rb_node rb; + unsigned long rb_subtree_last; } shared; /* -- cgit v1.2.3 From 0661a33611fca12570cba48d9344ce68834ee86c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 10 Feb 2015 14:10:04 -0800 Subject: mm: remove rest usage of VM_NONLINEAR and pte_file() One bit in ->vm_flags is unused now! Signed-off-by: Kirill A. Shutemov Cc: Dan Carpenter Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - include/linux/swapops.h | 4 +--- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 18391eec4864..a0da685bdb82 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -138,7 +138,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ -#define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_ARCH_2 0x02000000 #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6adfb7bfbf44..50cbc876be56 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry) /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { - return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte); + return !pte_none(pte) && !pte_present_nonuma(pte); } #endif @@ -66,7 +66,6 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; - BUG_ON(pte_file(pte)); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); arch_entry = __pte_to_swp_entry(pte); @@ -82,7 +81,6 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry) swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); - BUG_ON(pte_file(__swp_entry_to_pte(arch_entry))); return __swp_entry_to_pte(arch_entry); } -- cgit v1.2.3 From 753162cd849c45580fb5aaa7f3597c81e74e391c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 10 Feb 2015 14:11:36 -0800 Subject: mm: hugetlb: fix type of hugetlb_treat_as_movable variable hugetlb_treat_as_movable declared as unsigned long, but proc_dointvec() used for parsing it: static struct ctl_table vm_table[] = { ... { .procname = "hugepages_treat_as_movable", .data = &hugepages_treat_as_movable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, This seems harmless, but it's better to use int type here. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Manfred Spraul Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 431b7fc605c9..7d7856359920 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -86,7 +86,7 @@ void free_huge_page(struct page *page); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); #endif -extern unsigned long hugepages_treat_as_movable; +extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages; -- cgit v1.2.3 From dbf22eb6d8675fc173154d9f1bd1bd0fda53a001 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:41 -0800 Subject: memcg: zap __memcg_{charge,uncharge}_slab They are simple wrappers around memcg_{charge,uncharge}_kmem, so let's zap them and call these functions directly. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7c95af8d552c..18ccb2988979 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -403,8 +403,9 @@ void memcg_update_array_size(int num_groups); struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order); -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order); +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages); +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); int __memcg_cleanup_cache_params(struct kmem_cache *s); -- cgit v1.2.3 From 3e0350a36414a73c5c2d1e354f8c0ab4ace1296d Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:44 -0800 Subject: memcg: zap memcg_name argument of memcg_create_kmem_cache Instead of passing the name of the memory cgroup which the cache is created for in the memcg_name_argument, let's obtain it immediately in memcg_create_kmem_cache. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 9a139b637069..eca9ed303a1b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -117,8 +117,7 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, - struct kmem_cache *, - const char *); + struct kmem_cache *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); -- cgit v1.2.3 From d5b3cf7139b8770af4ed8bb36a1ab9d290ac39e9 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 10 Feb 2015 14:11:47 -0800 Subject: memcg: zap memcg_slab_caches and memcg_slab_mutex mem_cgroup->memcg_slab_caches is a list of kmem caches corresponding to the given cgroup. Currently, it is only used on css free in order to destroy all caches corresponding to the memory cgroup being freed. The list is protected by memcg_slab_mutex. The mutex is also used to protect kmem_cache->memcg_params->memcg_caches arrays and synchronizes kmem_cache_destroy vs memcg_unregister_all_caches. However, we can perfectly get on without these two. To destroy all caches corresponding to a memory cgroup, we can walk over the global list of kmem caches, slab_caches, and we can do all the synchronization stuff using the slab_mutex instead of the memcg_slab_mutex. This patch therefore gets rid of the memcg_slab_caches and memcg_slab_mutex. Apart from this nice cleanup, it also: - assures that rcu_barrier() is called once at max when a root cache is destroyed or a memory cgroup is freed, no matter how many caches have SLAB_DESTROY_BY_RCU flag set; - fixes the race between kmem_cache_destroy and kmem_cache_create that exists, because memcg_cleanup_cache_params, which is called from kmem_cache_destroy after checking that kmem_cache->refcount=0, releases the slab_mutex, which gives kmem_cache_create a chance to make an alias to a cache doomed to be destroyed. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Acked-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 -- include/linux/slab.h | 6 ++---- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 18ccb2988979..fb212e1d700d 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -407,8 +407,6 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, unsigned long nr_pages); void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); -int __memcg_cleanup_cache_params(struct kmem_cache *s); - /** * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed. * @gfp: the gfp allocation flags. diff --git a/include/linux/slab.h b/include/linux/slab.h index eca9ed303a1b..2e3b448cfa2d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -116,8 +116,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); #ifdef CONFIG_MEMCG_KMEM -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *, - struct kmem_cache *); +void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); +void memcg_destroy_kmem_caches(struct mem_cgroup *); #endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); @@ -490,7 +490,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * Child caches will hold extra metadata needed for its operation. Fields are: * * @memcg: pointer to the memcg this cache belongs to - * @list: list_head for the list of all caches in this memcg * @root_cache: pointer to the global, root cache, this cache was derived from */ struct memcg_cache_params { @@ -502,7 +501,6 @@ struct memcg_cache_params { }; struct { struct mem_cgroup *memcg; - struct list_head list; struct kmem_cache *root_cache; }; }; -- cgit v1.2.3 From 18c137371b2ea86d263b75665a4904a0b8872990 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:09 +1030 Subject: lguest: add operations to get/set a register from the Launcher. We use the ptrace API struct, and we currently don't let them set anything but the normal registers (we'd have to filter the others). Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 495203ff221c..f27cae27b0c1 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -63,6 +63,8 @@ enum lguest_req LHREQ_IRQ, /* + irq */ LHREQ_BREAK, /* No longer used */ LHREQ_EVENTFD, /* + address, fd. */ + LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ + LHREQ_SETREG, /* + offset within struct pt_regs, value. */ }; /* -- cgit v1.2.3 From 69a09dc1742ffbb3b02f3a1e03da4801e96452e9 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:09 +1030 Subject: lguest: write more information to userspace about pending traps. This is preparation for userspace handling MMIO and ioport accesses. Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index f27cae27b0c1..c4451ebece47 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -67,6 +67,19 @@ enum lguest_req LHREQ_SETREG, /* + offset within struct pt_regs, value. */ }; +/* + * This is what read() of the lguest fd populates. trap == + * LGUEST_TRAP_ENTRY for an LHCALL_NOTIFY (addr is the + * argument), 14 for a page fault in the MMIO region (addr is + * the trap address, insn is the instruction), or 13 for a GPF + * (insn is the instruction). + */ +struct lguest_pending { + __u8 trap; + __u8 insn[7]; + __u32 addr; +}; + /* * The alignment to use between consumer and producer parts of vring. * x86 pagesize for historical reasons. -- cgit v1.2.3 From 8ed313001a892f240269dea05d4b925cbd150492 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:15:09 +1030 Subject: lguest: add infrastructure for userspace to deliver a trap to the guest. This is required for instruction emulation to move to userspace. Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index c4451ebece47..3c402b843e03 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -65,6 +65,7 @@ enum lguest_req LHREQ_EVENTFD, /* + address, fd. */ LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ LHREQ_SETREG, /* + offset within struct pt_regs, value. */ + LHREQ_TRAP, /* + trap number to deliver to guest. */ }; /* -- cgit v1.2.3 From b3e28b65de254570140832cf7c95255ab4d501bb Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:22:01 +1030 Subject: lguest: remove lguest bus definitions from header. Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 49 ++--------------------------------------- 1 file changed, 2 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 3c402b843e03..677cde735d4b 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -8,52 +8,13 @@ * * The Guest needs devices to do anything useful. Since we don't let it touch * real devices (think of the damage it could do!) we provide virtual devices. - * We could emulate a PCI bus with various devices on it, but that is a fairly - * complex burden for the Host and suboptimal for the Guest, so we have our own - * simple lguest bus and we use "virtio" drivers. These drivers need a set of - * routines from us which will actually do the virtual I/O, but they handle all - * the net/block/console stuff themselves. This means that if we want to add - * a new device, we simply need to write a new virtio driver and create support - * for it in the Launcher: this code won't need to change. + * We emulate a PCI bus with virtio devices on it; we used to have our own + * lguest bus which was far simpler, but this tests the virtio 1.0 standard. * * Virtio devices are also used by kvm, so we can simply reuse their optimized * device drivers. And one day when everyone uses virtio, my plan will be * complete. Bwahahahah! - * - * Devices are described by a simplified ID, a status byte, and some "config" - * bytes which describe this device's configuration. This is placed by the - * Launcher just above the top of physical memory: - */ -struct lguest_device_desc { - /* The device type: console, network, disk etc. Type 0 terminates. */ - __u8 type; - /* The number of virtqueues (first in config array) */ - __u8 num_vq; - /* - * The number of bytes of feature bits. Multiply by 2: one for host - * features and one for Guest acknowledgements. - */ - __u8 feature_len; - /* The number of bytes of the config array after virtqueues. */ - __u8 config_len; - /* A status byte, written by the Guest. */ - __u8 status; - __u8 config[0]; -}; - -/*D:135 - * This is how we expect the device configuration field for a virtqueue - * to be laid out in config space. */ -struct lguest_vqconfig { - /* The number of entries in the virtio_ring */ - __u16 num; - /* The interrupt we get when something happens. */ - __u16 irq; - /* The page number of the virtio ring for this device. */ - __u32 pfn; -}; -/*:*/ /* Write command first word is a request. */ enum lguest_req @@ -80,10 +41,4 @@ struct lguest_pending { __u8 insn[7]; __u32 addr; }; - -/* - * The alignment to use between consumer and producer parts of vring. - * x86 pagesize for historical reasons. - */ -#define LGUEST_VRING_ALIGN 4096 #endif /* _LINUX_LGUEST_LAUNCHER */ -- cgit v1.2.3 From d9bab50aa46ce46dd4537d455eb13b200cdac516 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Wed, 11 Feb 2015 15:28:01 +1030 Subject: lguest: remove NOTIFY call and eventfd facility. Disappointing, as this was kind of neat (especially getting to use RCU to manage the address -> eventfd mapping). But now the devices are PCI handled in userspace, we get rid of both the NOTIFY hypercall and the interface to connect an eventfd. Signed-off-by: Rusty Russell --- include/linux/lguest_launcher.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h index 677cde735d4b..acd5b12565cc 100644 --- a/include/linux/lguest_launcher.h +++ b/include/linux/lguest_launcher.h @@ -23,7 +23,7 @@ enum lguest_req LHREQ_GETDMA, /* No longer used */ LHREQ_IRQ, /* + irq */ LHREQ_BREAK, /* No longer used */ - LHREQ_EVENTFD, /* + address, fd. */ + LHREQ_EVENTFD, /* No longer used. */ LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ LHREQ_SETREG, /* + offset within struct pt_regs, value. */ LHREQ_TRAP, /* + trap number to deliver to guest. */ -- cgit v1.2.3 From d427e3c82ef4fc5fbb22c0cef0b040e6767b1028 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Feb 2015 14:07:50 +0100 Subject: block: remove unused function blk_bio_map_sg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bf4ef666d191..7f9a516f24de 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1049,8 +1049,6 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); -extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio, - struct scatterlist *sglist); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); -- cgit v1.2.3 From f7219b527b5710ae0c4add8faa4d0ea529722cb5 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 10 Feb 2015 12:55:03 -0800 Subject: treewide: Remove unnecessary BCMA_CORETABLE_END macro Use the normal {} instead of a macro to terminate an array. Remove the macro too. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 745def862580..6711d57f9c05 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -381,8 +381,6 @@ struct bcma_device_id { } __attribute__((packed,aligned(2))); #define BCMA_CORE(_manuf, _id, _rev, _class) \ { .manuf = _manuf, .id = _id, .rev = _rev, .class = _class, } -#define BCMA_CORETABLE_END \ - { 0, }, #define BCMA_ANY_MANUF 0xFFFF #define BCMA_ANY_ID 0xFFFF -- cgit v1.2.3 From 673e2baaa6d986e2fcd9c867661d8113f6c7dc7b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 10 Feb 2015 13:19:24 -0800 Subject: treewide: Remove unnecessary SSB_DEVTABLE_END macro Use the normal {} instead of a macro to terminate an array. Remove the macro too. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/mod_devicetable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 6711d57f9c05..2bb97175b6cc 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -365,8 +365,6 @@ struct ssb_device_id { } __attribute__((packed, aligned(2))); #define SSB_DEVICE(_vendor, _coreid, _revision) \ { .vendor = _vendor, .coreid = _coreid, .revision = _revision, } -#define SSB_DEVTABLE_END \ - { 0, }, #define SSB_ANY_VENDOR 0xFFFF #define SSB_ANY_ID 0xFFFF -- cgit v1.2.3 From 26c4f7da3e413da697a7beb22ad496390eda7da0 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:27 -0800 Subject: net: Fix remcsum in GRO path to not change packet Remote checksum offload processing is currently the same for both the GRO and non-GRO path. When the remote checksum offload option is encountered, the checksum field referred to is modified in the packet. So in the GRO case, the packet is modified in the GRO path and then the operation is skipped when the packet goes through the normal path based on skb->remcsum_offload. There is a problem in that the packet may be modified in the GRO path, but then forwarded off host still containing the remote checksum option. A remote host will again perform RCO but now the checksum verification will fail since GRO RCO already modified the checksum. To fix this, we ensure that GRO restores a packet to it's original state before returning. In this model, when GRO processes a remote checksum option it still changes the checksum per the algorithm but on return from lower layer processing the checksum is restored to its original value. In this patch we add define gro_remcsum structure which is passed to skb_gro_remcsum_process to save offset and delta for the checksum being changed. After lower layer processing, skb_gro_remcsum_cleanup is called to restore the checksum before returning from GRO. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d115256ed5a2..3aa02457fe4f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2321,8 +2321,19 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +struct gro_remcsum { + int offset; + __wsum delta; +}; + +static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) +{ + grc->delta = 0; +} + static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - int start, int offset) + int start, int offset, + struct gro_remcsum *grc) { __wsum delta; @@ -2331,10 +2342,20 @@ static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); /* Adjust skb->csum since we changed the packet */ - skb->csum = csum_add(skb->csum, delta); NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + + grc->offset = (ptr + offset) - (void *)skb->head; + grc->delta = delta; } +static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, + struct gro_remcsum *grc) +{ + if (!grc->delta) + return; + + remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta); +} static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, -- cgit v1.2.3 From 6edec0e61b1e52f9144935d28c9088f5b202e61c Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:28 -0800 Subject: net: Clarify meaning of CHECKSUM_PARTIAL for receive path The current meaning of CHECKSUM_PARTIAL for validating checksums is that _all_ checksums in the packet are considered valid. However, in the manner that CHECKSUM_PARTIAL is set only the checksum at csum_start+csum_offset and any preceding checksums may be considered valid. If there are checksums in the packet after csum_offset it is possible they have not been verfied. This patch changes CHECKSUM_PARTIAL logic in skb_csum_unnecessary and __skb_gro_checksum_validate_needed to only considered checksums referring to csum_start and any preceding checksums (with starting offset before csum_start) to be verified. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- include/linux/skbuff.h | 17 ++++++++++++----- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3aa02457fe4f..9e9be221e4bf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2246,7 +2246,9 @@ static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { - return (skb->ip_summed != CHECKSUM_PARTIAL && + return ((skb->ip_summed != CHECKSUM_PARTIAL || + skb_checksum_start_offset(skb) < + skb_gro_offset(skb)) && NAPI_GRO_CB(skb)->csum_cnt == 0 && (!zero_okay || check)); } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1bb36edb66b9..da6028a50687 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -83,11 +83,15 @@ * * CHECKSUM_PARTIAL: * - * This is identical to the case for output below. This may occur on a packet + * A checksum is set up to be offloaded to a device as described in the + * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel - * on the same host. The packet can be treated in the same way as - * CHECKSUM_UNNECESSARY, except that on output (i.e., forwarding) the - * checksum must be filled in by the OS or the hardware. + * on the same host, or it may be set in the input path in GRO or remote + * checksum offload. For the purposes of checksum verification, the checksum + * referred to by skb->csum_start + skb->csum_offset and any preceding + * checksums in the packet are considered verified. Any checksums in the + * packet that are after the checksum being offloaded are not considered to + * be verified. * * B. Checksumming on output. * @@ -2915,7 +2919,10 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { - return ((skb->ip_summed & CHECKSUM_UNNECESSARY) || skb->csum_valid); + return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || + skb->csum_valid || + (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) >= 0)); } /** -- cgit v1.2.3 From baa32ff42871f2d4aca9c08c9403d0e497325564 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:30 -0800 Subject: net: Use more bit fields in napi_gro_cb This patch moves the free and same_flow fields to be bit fields (2 and 1 bit sized respectively). This frees up some space for u16's. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9e9be221e4bf..43fd0a4dcd04 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1923,20 +1923,15 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow; - - /* Free the skb? */ - u8 free; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* jiffies when first packet was created/queued */ unsigned long age; /* Used in ipv6_gro_receive() and foo-over-udp */ u16 proto; + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; + /* Used in udp_gro_receive */ u8 udp_mark:1; @@ -1946,9 +1941,16 @@ struct napi_gro_cb { /* Number of checksums via CHECKSUM_UNNECESSARY */ u8 csum_cnt:3; + /* Free the skb? */ + u8 free:2; +#define NAPI_GRO_FREE 1 +#define NAPI_GRO_FREE_STOLEN_HEAD 2 + /* Used in foo-over-udp, set in udp[46]_gro_receive */ u8 is_ipv6:1; + /* 7 bit hole */ + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; -- cgit v1.2.3 From 15e2396d4e3ce23188852b74d924107982c63b42 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 10 Feb 2015 16:30:31 -0800 Subject: net: Infrastructure for CHECKSUM_PARTIAL with remote checsum offload This patch adds infrastructure so that remote checksum offload can set CHECKSUM_PARTIAL instead of calling csum_partial and writing the modfied checksum field. Add skb_remcsum_adjust_partial function to set an skb for using CHECKSUM_PARTIAL with remote checksum offload. Changed skb_remcsum_process and skb_gro_remcsum_process to take a boolean argument to indicate if checksum partial can be set or the checksum needs to be modified using the normal algorithm. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 19 ++++++++++++++++++- include/linux/skbuff.h | 15 ++++++++++++++- 2 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 43fd0a4dcd04..5897b4ea5a3f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1923,6 +1923,9 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; + /* jiffies when first packet was created/queued */ unsigned long age; @@ -2244,6 +2247,12 @@ static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, __sum16 __skb_gro_checksum_complete(struct sk_buff *skb); +static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) == + skb_gro_offset(skb)); +} + static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) @@ -2251,6 +2260,7 @@ static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, return ((skb->ip_summed != CHECKSUM_PARTIAL || skb_checksum_start_offset(skb) < skb_gro_offset(skb)) && + !skb_at_gro_remcsum_start(skb) && NAPI_GRO_CB(skb)->csum_cnt == 0 && (!zero_okay || check)); } @@ -2337,12 +2347,19 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, - struct gro_remcsum *grc) + struct gro_remcsum *grc, + bool nopartial) { __wsum delta; BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + if (!nopartial) { + NAPI_GRO_CB(skb)->gro_remcsum_start = + ((unsigned char *)ptr + start) - skb->head; + return; + } + delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset); /* Adjust skb->csum since we changed the packet */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index da6028a50687..30007afe70b3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3104,16 +3104,29 @@ do { \ compute_pseudo(skb, proto)); \ } while (0) +static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, + u16 start, u16 offset) +{ + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = ((unsigned char *)ptr + start) - skb->head; + skb->csum_offset = offset - start; +} + /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, - int start, int offset) + int start, int offset, bool nopartial) { __wsum delta; + if (!nopartial) { + skb_remcsum_adjust_partial(skb, ptr, start, offset); + return; + } + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); -- cgit v1.2.3 From 119ee9144534141822462e3e8a5ccc8dc537f712 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 29 Jan 2015 11:45:33 -0800 Subject: f2fs: split UMOUNT and FASTBOOT flags This patch adds FASTBOOT flag into checkpoint as follows. - CP_UMOUNT_FLAG is set when system is umounted. - CP_FASTBOOT_FLAG is set when intermediate checkpoint having node summaries was done. So, if you get CP_UMOUNT_FLAG from checkpoint, the system was umounted cleanly. Instead, if there was sudden-power-off, you can get CP_FASTBOOT_FLAG or nothing. Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index e993b0bc9abf..09805720f4bf 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -87,6 +87,7 @@ struct f2fs_super_block { /* * For checkpoint */ +#define CP_FASTBOOT_FLAG 0x00000020 #define CP_FSCK_FLAG 0x00000010 #define CP_ERROR_FLAG 0x00000008 #define CP_COMPACT_SUM_FLAG 0x00000004 -- cgit v1.2.3 From f7ef9b83b583640111039b30e13263b71c3a6ed5 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 9 Feb 2015 12:02:44 -0800 Subject: f2fs: introduce macros to convert bytes and blocks in f2fs This patch adds two macros for transition between byte and block offsets. Currently, f2fs only supports 4KB blocks, so use the default size for now. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 09805720f4bf..a23556c32703 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -19,12 +19,16 @@ #define F2FS_MAX_LOG_SECTOR_SIZE 12 /* 12 bits for 4096 bytes */ #define F2FS_LOG_SECTORS_PER_BLOCK 3 /* log number for sector/blk */ #define F2FS_BLKSIZE 4096 /* support only 4KB block */ +#define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ #define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ #define NEW_ADDR ((block_t)-1) /* used as block_t addresses */ +#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) +#define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) + /* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3 -- cgit v1.2.3 From e4b294c2d8f73af4cd41ff30638ad0e4769dc56a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:24:46 -0800 Subject: mm: add fields for compound destructor and order into struct page Currently, we use lru.next/lru.prev plus cast to access or set destructor and order of compound page. Let's replace it with explicit fields in struct page. Signed-off-by: Kirill A. Shutemov Acked-by: Jerome Marchand Acked-by: Christoph Lameter Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++----- include/linux/mm_types.h | 8 ++++++++ 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 65db4aee738a..8dd4fde9d2e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -627,29 +627,28 @@ int split_free_page(struct page *page); * prototype for that function and accessor functions. * These are _only_ valid on the head of a PG_compound page. */ -typedef void compound_page_dtor(struct page *); static inline void set_compound_page_dtor(struct page *page, compound_page_dtor *dtor) { - page[1].lru.next = (void *)dtor; + page[1].compound_dtor = dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { - return (compound_page_dtor *)page[1].lru.next; + return page[1].compound_dtor; } static inline int compound_order(struct page *page) { if (!PageHead(page)) return 0; - return (unsigned long)page[1].lru.prev; + return page[1].compound_order; } static inline void set_compound_order(struct page *page, unsigned long order) { - page[1].lru.prev = (void *)order; + page[1].compound_order = order; } #ifdef CONFIG_MMU diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 07c8bd3f7b48..20ff2105b564 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -28,6 +28,8 @@ struct mem_cgroup; IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) +typedef void compound_page_dtor(struct page *); + /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -142,6 +144,12 @@ struct page { struct rcu_head rcu_head; /* Used by SLAB * when destroying via RCU */ + /* First tail page of compound page */ + struct { + compound_page_dtor *compound_dtor; + unsigned long compound_order; + }; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page->ptl */ #endif -- cgit v1.2.3 From 1d148e218a0d0566b1c06f2f45f1436d53b049b2 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:48 -0800 Subject: mm: add VM_BUG_ON_PAGE() to page_mapcount() Add VM_BUG_ON_PAGE() for slab pages. _mapcount is an union with slab struct in struct page, so we must avoid accessing _mapcount if this page is a slab page. Also remove the unneeded bracket. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8dd4fde9d2e5..c6bf813a6b3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -484,7 +484,8 @@ static inline void page_mapcount_reset(struct page *page) static inline int page_mapcount(struct page *page) { - return atomic_read(&(page)->_mapcount) + 1; + VM_BUG_ON_PAGE(PageSlab(page), page); + return atomic_read(&page->_mapcount) + 1; } static inline int page_count(struct page *page) -- cgit v1.2.3 From 56873f43abdcd574b25105867a990f067747b2f4 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:51 -0800 Subject: mm:add KPF_ZERO_PAGE flag for /proc/kpageflags Add KPF_ZERO_PAGE flag for zero_page, so that userspace processes can detect zero_page in /proc/kpageflags, and then do memory analysis more accurately. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ad9051bab267..f10b20f05159 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,6 +157,13 @@ static inline int hpage_nr_pages(struct page *page) extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); +extern struct page *huge_zero_page; + +static inline bool is_huge_zero_page(struct page *page) +{ + return ACCESS_ONCE(huge_zero_page) == page; +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -206,6 +213,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str return 0; } +static inline bool is_huge_zero_page(struct page *page) +{ + return false; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ -- cgit v1.2.3 From 93aa7d95248d04b934eb8e89717c7b8d6400bf2b Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:24:59 -0800 Subject: swap: remove unused mem_cgroup_uncharge_swapcache declaration The body of this function was removed by commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API"). Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 34e8b60ab973..7067eca501e2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -437,16 +437,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_MEMCG -extern void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); -#else -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) -{ -} -#endif - #else /* CONFIG_SWAP */ #define swap_address_space(entry) (NULL) @@ -547,11 +537,6 @@ static inline swp_entry_t get_swap_page(void) return entry; } -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) -{ -} - #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ -- cgit v1.2.3 From 6de226191d12fce30331ebf024ca3ed24834f0ee Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:25:01 -0800 Subject: mm: memcontrol: track move_lock state internally The complexity of memcg page stat synchronization is currently leaking into the callsites, forcing them to keep track of the move_lock state and the IRQ flags. Simplify the API by tracking it in the memcg. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fb212e1d700d..76b4084b8d08 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -138,12 +138,10 @@ static inline bool mem_cgroup_disabled(void) return false; } -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, - unsigned long *flags); -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags); +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val); +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) @@ -285,14 +283,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, unsigned long *flags) +static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { return NULL; } -static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, - bool *locked, unsigned long *flags) +static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 44628d9755e249aab9a6e1a17407d2f4278047ee Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 11 Feb 2015 15:25:10 -0800 Subject: mm: fix typo of MIGRATE_RESERVE in comment Found it when I want to jump to the definition of MIGRATE_RESERVE ctags. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f0856d14b21..b41829701334 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -426,7 +426,7 @@ struct zone { const char *name; /* - * Number of MIGRATE_RESEVE page block. To maintain for just + * Number of MIGRATE_RESERVE page block. To maintain for just * optimization. Protected by zone->lock. */ int nr_migrate_reserve_block; -- cgit v1.2.3 From e66f17ff71772b209eed39de35aaa99ba819c93d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:25:22 -0800 Subject: mm/hugetlb: take page table lock in follow_huge_pmd() We have a race condition between move_pages() and freeing hugepages, where move_pages() calls follow_page(FOLL_GET) for hugepages internally and tries to get its refcount without preventing concurrent freeing. This race crashes the kernel, so this patch fixes it by moving FOLL_GET code for hugepages into follow_huge_pmd() with taking the page table lock. This patch intentionally removes page==NULL check after pte_page. This is justified because pte_page() never returns NULL for any architectures or configurations. This patch changes the behavior of follow_huge_pmd() for tail pages and then tail pages can be pinned/returned. So the caller must be changed to properly handle the returned tail pages. We could have a choice to add the similar locking to follow_huge_(addr|pud) for consistency, but it's not necessary because currently these functions don't support FOLL_GET flag, so let's leave it for future development. Here is the reproducer: $ cat movepages.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 #define PS 0x1000 int main(int argc, char *argv[]) { int i; int nr_hp = strtol(argv[1], NULL, 0); int nr_p = nr_hp * HPS / PS; int ret; void **addrs; int *status; int *nodes; pid_t pid; pid = strtol(argv[2], NULL, 0); addrs = malloc(sizeof(char *) * nr_p + 1); status = malloc(sizeof(char *) * nr_p + 1); nodes = malloc(sizeof(char *) * nr_p + 1); while (1) { for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 1; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 0; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); } return 0; } $ cat hugepage.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 int main(int argc, char *argv[]) { int nr_hp = strtol(argv[1], NULL, 0); char *p; while (1) { p = mmap((void *)ADDR_INPUT, nr_hp * HPS, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (p != (void *)ADDR_INPUT) { perror("mmap"); break; } memset(p, 0, nr_hp * HPS); munmap(p, nr_hp * HPS); } } $ sysctl vm.nr_hugepages=40 $ ./hugepage 10 & $ ./movepages 10 $(pgrep -f hugepage) Fixes: e632a938d914 ("mm: migrate: add hugepage migration code to move_pages()") Signed-off-by: Naoya Horiguchi Reported-by: Hugh Dickins Cc: James Hogan Cc: David Rientjes Cc: Mel Gorman Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Luiz Capitulino Cc: Nishanth Aravamudan Cc: Lee Schermerhorn Cc: Steve Capper Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 ++++---- include/linux/swapops.h | 4 ++++ 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7d7856359920..7b5785032049 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write); + pmd_t *pmd, int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write); + pud_t *pud, int flags); int pmd_huge(pmd_t pmd); int pud_huge(pud_t pmd); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, @@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) static inline void hugetlb_show_meminfo(void) { } -#define follow_huge_pmd(mm, addr, pmd, write) NULL -#define follow_huge_pud(mm, addr, pud, write) NULL +#define follow_huge_pmd(mm, addr, pmd, flags) NULL +#define follow_huge_pud(mm, addr, pud, flags) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define pud_huge(x) 0 diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 50cbc876be56..831a3168ab35 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -135,6 +135,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry) *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); } +extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, @@ -148,6 +150,8 @@ static inline int is_migration_entry(swp_entry_t swp) } #define migration_entry_to_page(swp) NULL static inline void make_migration_entry_read(swp_entry_t *entryp) { } +static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, -- cgit v1.2.3 From 1a6d53a105406d97396c87511afd6f09b4dc8ad2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:44 -0800 Subject: mm: reduce try_to_compact_pages parameters Expand the usage of the struct alloc_context introduced in the previous patch also for calling try_to_compact_pages(), to reduce the number of its parameters. Since the function is in different compilation unit, we need to move alloc_context definition in the shared mm/internal.h header. With this change we get simpler code and small savings of code size and stack usage: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-27 (-27) function old new delta __alloc_pages_direct_compact 283 256 -27 add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-13 (-13) function old new delta try_to_compact_pages 582 569 -13 Stack usage of __alloc_pages_direct_compact goes from 24 to none (per scripts/checkstack.pl). Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3238ffa33f68..f2efda2e6ac6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,6 +21,8 @@ /* Zone lock or lru_lock was contended in async compaction */ #define COMPACT_CONTENDED_LOCK 2 +struct alloc_context; /* in mm/internal.h */ + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -30,10 +32,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); extern int fragmentation_index(struct zone *zone, unsigned int order); -extern unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *mask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx); +extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, @@ -101,10 +102,10 @@ static inline bool compaction_restarting(struct zone *zone, int order) } #else -static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, + unsigned int order, int alloc_flags, + const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { return COMPACT_CONTINUE; } -- cgit v1.2.3 From 05891fb06517d19ae5357c9dc44e96bbe0300a3c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:47 -0800 Subject: mm: microoptimize zonelist operations next_zones_zonelist() returns a zoneref pointer, as well as a zone pointer via extra parameter. Since the latter can be trivially obtained by dereferencing the former, the overhead of the extra parameter is unjustified. This patch thus removes the zone parameter from next_zones_zonelist(). Both callers happen to be in the same header file, so it's simple to add the zoneref dereference inline. We save some bytes of code size. add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-105 (-105) function old new delta nr_free_zone_pages 129 115 -14 __alloc_pages_nodemask 2300 2285 -15 get_page_from_freelist 2652 2576 -76 add/remove: 0/0 grow/shrink: 1/0 up/down: 10/0 (10) function old new delta try_to_compact_pages 569 579 +10 Signed-off-by: Vlastimil Babka Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b41829701334..f279d9c158cd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -970,7 +970,6 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the @@ -980,8 +979,7 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone); + nodemask_t *nodes); /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist @@ -1000,8 +998,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, nodemask_t *nodes, struct zone **zone) { - return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes, - zone); + struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs, + highest_zoneidx, nodes); + *zone = zonelist_zone(z); + return z; } /** @@ -1018,7 +1018,8 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ zone; \ - z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \ + z = next_zones_zonelist(++z, highidx, nodemask), \ + zone = zonelist_zone(z)) \ /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index -- cgit v1.2.3 From 90cbc2508827e1e15dca23361c33cc26dd2b9e99 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:25:55 -0800 Subject: vmscan: force scan offline memory cgroups Since commit b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined groups") pages charged to a memory cgroup are not reparented when the cgroup is removed. Instead, they are supposed to be reclaimed in a regular way, along with pages accounted to online memory cgroups. However, an lruvec of an offline memory cgroup will sooner or later get so small that it will be scanned only at low scan priorities (see get_scan_count()). Therefore, if there are enough reclaimable pages in big lruvecs, pages accounted to offline memory cgroups will never be scanned at all, wasting memory. Fix this by unconditionally forcing scanning dead lruvecs from kswapd. [akpm@linux-foundation.org: fix build] Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 76b4084b8d08..353537a5981a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -102,6 +102,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); +bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -266,6 +267,11 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + return true; +} + static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { -- cgit v1.2.3 From 650c5e565492f9092552bfe4d65935196c7d9567 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:03 -0800 Subject: mm: page_counter: pull "-1" handling out of page_counter_memparse() The unified hierarchy interface for memory cgroups will no longer use "-1" to mean maximum possible resource value. In preparation for this, make the string an argument and let the caller supply it. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 955421575d16..17fa4f8de3a6 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -41,7 +41,8 @@ int page_counter_try_charge(struct page_counter *counter, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_limit(struct page_counter *counter, unsigned long limit); -int page_counter_memparse(const char *buf, unsigned long *nr_pages); +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages); static inline void page_counter_reset_watermark(struct page_counter *counter) { -- cgit v1.2.3 From 241994ed8649f7300667be8b13a9e04ae04e05a1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:06 -0800 Subject: mm: memcontrol: default hierarchy interface for memory Introduce the basic control files to account, partition, and limit memory using cgroups in default hierarchy mode. This interface versioning allows us to address fundamental design issues in the existing memory cgroup interface, further explained below. The old interface will be maintained indefinitely, but a clearer model and improved workload performance should encourage existing users to switch over to the new one eventually. The control files are thus: - memory.current shows the current consumption of the cgroup and its descendants, in bytes. - memory.low configures the lower end of the cgroup's expected memory consumption range. The kernel considers memory below that boundary to be a reserve - the minimum that the workload needs in order to make forward progress - and generally avoids reclaiming it, unless there is an imminent risk of entering an OOM situation. - memory.high configures the upper end of the cgroup's expected memory consumption range. A cgroup whose consumption grows beyond this threshold is forced into direct reclaim, to work off the excess and to throttle new allocations heavily, but is generally allowed to continue and the OOM killer is not invoked. - memory.max configures the hard maximum amount of memory that the cgroup is allowed to consume before the OOM killer is invoked. - memory.events shows event counters that indicate how often the cgroup was reclaimed while below memory.low, how often it was forced to reclaim excess beyond memory.high, how often it hit memory.max, and how often it entered OOM due to memory.max. This allows users to identify configuration problems when observing a degradation in workload performance. An overcommitted system will have an increased rate of low boundary breaches, whereas increased rates of high limit breaches, maximum hits, or even OOM situations will indicate internally overcommitted cgroups. For existing users of memory cgroups, the following deviations from the current interface are worth pointing out and explaining: - The original lower boundary, the soft limit, is defined as a limit that is per default unset. As a result, the set of cgroups that global reclaim prefers is opt-in, rather than opt-out. The costs for optimizing these mostly negative lookups are so high that the implementation, despite its enormous size, does not even provide the basic desirable behavior. First off, the soft limit has no hierarchical meaning. All configured groups are organized in a global rbtree and treated like equal peers, regardless where they are located in the hierarchy. This makes subtree delegation impossible. Second, the soft limit reclaim pass is so aggressive that it not just introduces high allocation latencies into the system, but also impacts system performance due to overreclaim, to the point where the feature becomes self-defeating. The memory.low boundary on the other hand is a top-down allocated reserve. A cgroup enjoys reclaim protection when it and all its ancestors are below their low boundaries, which makes delegation of subtrees possible. Secondly, new cgroups have no reserve per default and in the common case most cgroups are eligible for the preferred reclaim pass. This allows the new low boundary to be efficiently implemented with just a minor addition to the generic reclaim code, without the need for out-of-band data structures and reclaim passes. Because the generic reclaim code considers all cgroups except for the ones running low in the preferred first reclaim pass, overreclaim of individual groups is eliminated as well, resulting in much better overall workload performance. - The original high boundary, the hard limit, is defined as a strict limit that can not budge, even if the OOM killer has to be called. But this generally goes against the goal of making the most out of the available memory. The memory consumption of workloads varies during runtime, and that requires users to overcommit. But doing that with a strict upper limit requires either a fairly accurate prediction of the working set size or adding slack to the limit. Since working set size estimation is hard and error prone, and getting it wrong results in OOM kills, most users tend to err on the side of a looser limit and end up wasting precious resources. The memory.high boundary on the other hand can be set much more conservatively. When hit, it throttles allocations by forcing them into direct reclaim to work off the excess, but it never invokes the OOM killer. As a result, a high boundary that is chosen too aggressively will not terminate the processes, but instead it will lead to gradual performance degradation. The user can monitor this and make corrections until the minimal memory footprint that still gives acceptable performance is found. In extreme cases, with many concurrent allocations and a complete breakdown of reclaim progress within the group, the high boundary can be exceeded. But even then it's mostly better to satisfy the allocation from the slack available in other groups or the rest of the system than killing the group. Otherwise, memory.max is there to limit this type of spillover and ultimately contain buggy or even malicious applications. - The original control file names are unwieldy and inconsistent in many different ways. For example, the upper boundary hit count is exported in the memory.failcnt file, but an OOM event count has to be manually counted by listening to memory.oom_control events, and lower boundary / soft limit events have to be counted by first setting a threshold for that value and then counting those events. Also, usage and limit files encode their units in the filename. That makes the filenames very long, even though this is not information that a user needs to be reminded of every time they type out those names. To address these naming issues, as well as to signal clearly that the new interface carries a new configuration model, the naming conventions in it necessarily differ from the old interface. - The original limit files indicate the state of an unset limit with a very high number, and a configured limit can be unset by echoing -1 into those files. But that very high number is implementation and architecture dependent and not very descriptive. And while -1 can be understood as an underflow into the highest possible value, -2 or -10M etc. do not work, so it's not inconsistent. memory.low, memory.high, and memory.max will use the string "infinity" to indicate and set the highest possible value. [akpm@linux-foundation.org: use seq_puts() for basic strings] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 353537a5981a..6cfd934c7c9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,7 +52,27 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; +enum mem_cgroup_events_index { + MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ + MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ + MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ + MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ + MEM_CGROUP_EVENTS_NSTATS, + /* default hierarchy events */ + MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS, + MEMCG_HIGH, + MEMCG_MAX, + MEMCG_OOM, + MEMCG_NR_EVENTS, +}; + #ifdef CONFIG_MEMCG +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr); + +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); + int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -175,6 +195,18 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; +static inline void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ +} + +static inline bool mem_cgroup_low(struct mem_cgroup *root, + struct mem_cgroup *memcg) +{ + return false; +} + static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp) -- cgit v1.2.3 From 49550b605587924b3336386caae53200c68969d3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:12 -0800 Subject: oom: add helpers for setting and clearing TIF_MEMDIE This patchset addresses a race which was described in the changelog for 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend"): : PM freezer relies on having all tasks frozen by the time devices are : getting frozen so that no task will touch them while they are getting : frozen. But OOM killer is allowed to kill an already frozen task in order : to handle OOM situtation. In order to protect from late wake ups OOM : killer is disabled after all tasks are frozen. This, however, still keeps : a window open when a killed task didn't manage to die by the time : freeze_processes finishes. The original patch hasn't closed the race window completely because that would require a more complex solution as it can be seen by this patchset. The primary motivation was to close the race condition between OOM killer and PM freezer _completely_. As Tejun pointed out, even though the race condition is unlikely the harder it would be to debug weird bugs deep in the PM freezer when the debugging options are reduced considerably. I can only speculate what might happen when a task is still runnable unexpectedly. On a plus side and as a side effect the oom enable/disable has a better (full barrier) semantic without polluting hot paths. I have tested the series in KVM with 100M RAM: - many small tasks (20M anon mmap) which are triggering OOM continually - s2ram which resumes automatically is triggered in a loop echo processors > /sys/power/pm_test while true do echo mem > /sys/power/state sleep 1s done - simple module which allocates and frees 20M in 8K chunks. If it sees freezing(current) then it tries another round of allocation before calling try_to_freeze - debugging messages of PM stages and OOM killer enable/disable/fail added and unmark_oom_victim is delayed by 1s after it clears TIF_MEMDIE and before it wakes up waiters. - rebased on top of the current mmotm which means some necessary updates in mm/oom_kill.c. mark_tsk_oom_victim is now called under task_lock but I think this should be OK because __thaw_task shouldn't interfere with any locking down wake_up_process. Oleg? As expected there are no OOM killed tasks after oom is disabled and allocations requested by the kernel thread are failing after all the tasks are frozen and OOM disabled. I wasn't able to catch a race where oom_killer_disable would really have to wait but I kinda expected the race is really unlikely. [ 242.609330] Killed process 2992 (mem_eater) total-vm:24412kB, anon-rss:2164kB, file-rss:4kB [ 243.628071] Unmarking 2992 OOM victim. oom_victims: 1 [ 243.636072] (elapsed 2.837 seconds) done. [ 243.641985] Trying to disable OOM killer [ 243.643032] Waiting for concurent OOM victims [ 243.644342] OOM killer disabled [ 243.645447] Freezing remaining freezable tasks ... (elapsed 0.005 seconds) done. [ 243.652983] Suspending console(s) (use no_console_suspend to debug) [ 243.903299] kmem_eater: page allocation failure: order:1, mode:0x204010 [...] [ 243.992600] PM: suspend of devices complete after 336.667 msecs [ 243.993264] PM: late suspend of devices complete after 0.660 msecs [ 243.994713] PM: noirq suspend of devices complete after 1.446 msecs [ 243.994717] ACPI: Preparing to enter system sleep state S3 [ 243.994795] PM: Saving platform NVS memory [ 243.994796] Disabling non-boot CPUs ... The first 2 patches are simple cleanups for OOM. They should go in regardless the rest IMO. Patches 3 and 4 are trivial printk -> pr_info conversion and they should go in ditto. The main patch is the last one and I would appreciate acks from Tejun and Rafael. I think the OOM part should be OK (except for __thaw_task vs. task_lock where a look from Oleg would appreciated) but I am not so sure I haven't screwed anything in the freezer code. I have found several surprises there. This patch (of 5): This patch is just a preparatory and it doesn't introduce any functional change. Note: I am utterly unhappy about lowmemory killer abusing TIF_MEMDIE just to wait for the oom victim and to prevent from new killing. This is just a side effect of the flag. The primary meaning is to give the oom victim access to the memory reserves and that shouldn't be necessary here. Signed-off-by: Michal Hocko Cc: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 76200984d1e2..b42b80f88c3a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -47,6 +47,10 @@ static inline bool oom_task_origin(const struct task_struct *p) return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); } +extern void mark_tsk_oom_victim(struct task_struct *tsk); + +extern void unmark_oom_victim(void); + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -- cgit v1.2.3 From c32b3cbe0d067a9cfae85aa70ba1e97ceba0ced7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:24 -0800 Subject: oom, PM: make OOM detection in the freezer path raceless Commit 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend") has left a race window when OOM killer manages to note_oom_kill after freeze_processes checks the counter. The race window is quite small and really unlikely and partial solution deemed sufficient at the time of submission. Tejun wasn't happy about this partial solution though and insisted on a full solution. That requires the full OOM and freezer's task freezing exclusion, though. This is done by this patch which introduces oom_sem RW lock and turns oom_killer_disable() into a full OOM barrier. oom_killer_disabled check is moved from the allocation path to the OOM level and we take oom_sem for reading for both the check and the whole OOM invocation. oom_killer_disable() takes oom_sem for writing so it waits for all currently running OOM killer invocations. Then it disable all the further OOMs by setting oom_killer_disabled and checks for any oom victims. Victims are counted via mark_tsk_oom_victim resp. unmark_oom_victim. The last victim wakes up all waiters enqueued by oom_killer_disable(). Therefore this function acts as the full OOM barrier. The page fault path is covered now as well although it was assumed to be safe before. As per Tejun, "We used to have freezing points deep in file system code which may be reacheable from page fault." so it would be better and more robust to not rely on freezing points here. Same applies to the memcg OOM killer. out_of_memory tells the caller whether the OOM was allowed to trigger and the callers are supposed to handle the situation. The page allocation path simply fails the allocation same as before. The page fault path will retry the fault (more on that later) and Sysrq OOM trigger will simply complain to the log. Normally there wouldn't be any unfrozen user tasks after try_to_freeze_tasks so the function will not block. But if there was an OOM killer racing with try_to_freeze_tasks and the OOM victim didn't finish yet then we have to wait for it. This should complete in a finite time, though, because - the victim cannot loop in the page fault handler (it would die on the way out from the exception) - it cannot loop in the page allocator because all the further allocation would fail and __GFP_NOFAIL allocations are not acceptable at this stage - it shouldn't be blocked on any locks held by frozen tasks (try_to_freeze expects lockless context) and kernel threads and work queues are not frozen yet Signed-off-by: Michal Hocko Suggested-by: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index b42b80f88c3a..d5771bed59c9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -72,22 +72,14 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill); -extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disabled; - -static inline void oom_killer_disable(void) -{ - oom_killer_disabled = true; -} - -static inline void oom_killer_enable(void) -{ - oom_killer_disabled = false; -} +extern bool oom_killer_disable(void); +extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -- cgit v1.2.3 From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:26:50 -0800 Subject: mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include #include #include #include #include #include #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov Reported-by: Dave Hansen Cc: Hugh Dickins Reviewed-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: David Rientjes Tested-by: Sedat Dilek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 24 ++++++++++++++++++++++++ include/linux/mm_types.h | 3 ++- 2 files changed, 26 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c6bf813a6b3d..644990b83cda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, { return 0; } + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return 0; +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} +static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} + #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return atomic_long_read(&mm->nr_pmds); +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) +{ + atomic_long_inc(&mm->nr_pmds); +} + +static inline void mm_dec_nr_pmds(struct mm_struct *mm) +{ + atomic_long_dec(&mm->nr_pmds); +} #endif int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 20ff2105b564..199a03aab8dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -363,7 +363,8 @@ struct mm_struct { pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - atomic_long_t nr_ptes; /* Page table pages */ + atomic_long_t nr_ptes; /* PTE page table pages */ + atomic_long_t nr_pmds; /* PMD page table pages */ int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some counters */ -- cgit v1.2.3 From 16c4a097a035c01809aa0c0abd458ca1fe4ff3d0 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:01 -0800 Subject: mm/compaction: enhance tracepoint output for compaction begin/end We now have tracepoint for begin event of compaction and it prints start position of both scanners, but, tracepoint for end event of compaction doesn't print finish position of both scanners. It'd be also useful to know finish position of both scanners so this patch add it. It will help to find odd behavior or problem on compaction internal logic. And mode is added to both begin/end tracepoint output, since according to mode, compaction behavior is quite different. And lastly, status format is changed to string rather than status number for readability. [akpm@linux-foundation.org: fix sparse warning] Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index f2efda2e6ac6..db64cae06530 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,7 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ /* No contention detected */ -- cgit v1.2.3 From 837d026d560c5ef26abeca0441713d82e4e82cad Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:06 -0800 Subject: mm/compaction: more trace to understand when/why compaction start/finish It is not well analyzed that when/why compaction start/finish or not. With these new tracepoints, we can know much more about start/finish reason of compaction. I can find following bug with these tracepoint. http://www.spinics.net/lists/linux-mm/msg81582.html Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index db64cae06530..501d7513aac1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,9 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* For more detailed tracepoint output */ +#define COMPACT_NO_SUITABLE_PAGE 5 +#define COMPACT_NOT_SUITABLE_ZONE 6 /* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ -- cgit v1.2.3 From 24e2716f63e613cf15d3beba3faa0711bcacc427 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:09 -0800 Subject: mm/compaction: add tracepoint to observe behaviour of compaction defer Compaction deferring logic is heavy hammer that block the way to the compaction. It doesn't consider overall system state, so it could prevent user from doing compaction falsely. In other words, even if system has enough range of memory to compact, compaction would be skipped due to compaction deferring logic. This patch add new tracepoint to understand work of deferring logic. This will also help to check compaction success and fail. Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 65 ++++------------------------------------------ 1 file changed, 5 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 501d7513aac1..a014559e4a49 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -44,66 +44,11 @@ extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx); -/* Do not skip compaction more than 64 times */ -#define COMPACT_MAX_DEFER_SHIFT 6 - -/* - * Compaction is deferred when compaction fails to result in a page - * allocation success. 1 << compact_defer_limit compactions are skipped up - * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT - */ -static inline void defer_compaction(struct zone *zone, int order) -{ - zone->compact_considered = 0; - zone->compact_defer_shift++; - - if (order < zone->compact_order_failed) - zone->compact_order_failed = order; - - if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) - zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; -} - -/* Returns true if compaction should be skipped this time */ -static inline bool compaction_deferred(struct zone *zone, int order) -{ - unsigned long defer_limit = 1UL << zone->compact_defer_shift; - - if (order < zone->compact_order_failed) - return false; - - /* Avoid possible overflow */ - if (++zone->compact_considered > defer_limit) - zone->compact_considered = defer_limit; - - return zone->compact_considered < defer_limit; -} - -/* - * Update defer tracking counters after successful compaction of given order, - * which means an allocation either succeeded (alloc_success == true) or is - * expected to succeed. - */ -static inline void compaction_defer_reset(struct zone *zone, int order, - bool alloc_success) -{ - if (alloc_success) { - zone->compact_considered = 0; - zone->compact_defer_shift = 0; - } - if (order >= zone->compact_order_failed) - zone->compact_order_failed = order + 1; -} - -/* Returns true if restarting compaction after many failures */ -static inline bool compaction_restarting(struct zone *zone, int order) -{ - if (order < zone->compact_order_failed) - return false; - - return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && - zone->compact_considered >= 1UL << zone->compact_defer_shift; -} +extern void defer_compaction(struct zone *zone, int order); +extern bool compaction_deferred(struct zone *zone, int order); +extern void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success); +extern bool compaction_restarting(struct zone *zone, int order); #else static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, -- cgit v1.2.3 From 077fcf116c8c2bd7ee9487b645aa3b50368db7e1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 11 Feb 2015 15:27:12 -0800 Subject: mm/thp: allocate transparent hugepages on local node This make sure that we try to allocate hugepages from local node if allowed by mempolicy. If we can't, we fallback to small page allocation based on mempolicy. This is based on the observation that allocating pages on local node is more beneficial than allocating hugepages on remote node. With this patch applied we may find transparent huge page allocation failures if the current node doesn't have enough freee hugepages. Before this patch such failures result in us retrying the allocation on other nodes in the numa node mask. [akpm@linux-foundation.org: fix comment, add CONFIG_TRANSPARENT_HUGEPAGE dependency] Signed-off-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b840e3b2770d..60110e06419d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -335,11 +335,15 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node); +extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) #define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ -- cgit v1.2.3 From be97a41b291e495d6cb767b3ee0f84ed05804892 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:27:15 -0800 Subject: mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma The previous commit ("mm/thp: Allocate transparent hugepages on local node") introduced alloc_hugepage_vma() to mm/mempolicy.c to perform a special policy for THP allocations. The function has the same interface as alloc_pages_vma(), shares a lot of boilerplate code and a long comment. This patch merges the hugepage special case into alloc_pages_vma. The extra if condition should be cheap enough price to pay. We also prevent a (however unlikely) race with parallel mems_allowed update, which could make hugepage allocation restart only within the fallback call to alloc_hugepage_vma() and not reconsider the special rule in alloc_hugepage_vma(). Also by making sure mpol_cond_put(pol) is always called before actual allocation attempt, we can use a single exit path within the function. Also update the comment for missing node parameter and obsolete reference to mm_sem. Signed-off-by: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 60110e06419d..51bd1e72a917 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -334,22 +334,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); -extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, - unsigned long addr, int order); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order); extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, -- cgit v1.2.3 From f0818f472d8d527a96ec9cc2c3a56223497f9dd3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:17 -0800 Subject: mm: gup: add get_user_pages_locked and get_user_pages_unlocked FAULT_FOLL_ALLOW_RETRY allows the page fault to drop the mmap_sem for reading to reduce the mmap_sem contention (for writing), like while waiting for I/O completion. The problem is that right now practically no get_user_pages call uses FAULT_FOLL_ALLOW_RETRY, so we're not leveraging that nifty feature. Andres fixed it for the KVM page fault. However get_user_pages_fast remains uncovered, and 99% of other get_user_pages aren't using it either (the only exception being FOLL_NOWAIT in KVM which is really nonblocking and in fact it doesn't even release the mmap_sem). So this patchsets extends the optimization Andres did in the KVM page fault to the whole kernel. It makes most important places (including gup_fast) to use FAULT_FOLL_ALLOW_RETRY to reduce the mmap_sem hold times during I/O. The only few places that remains uncovered are drivers like v4l and other exceptions that tends to work on their own memory and they're not working on random user memory (for example like O_DIRECT that uses gup_fast and is fully covered by this patch). A follow up patch should probably also add a printk_once warning to get_user_pages that should go obsolete and be phased out eventually. The "vmas" parameter of get_user_pages makes it fundamentally incompatible with FAULT_FOLL_ALLOW_RETRY (vmas array becomes meaningless the moment the mmap_sem is released). While this is just an optimization, this becomes an absolute requirement for the userfaultfd feature http://lwn.net/Articles/615086/ . The userfaultfd allows to block the page fault, and in order to do so I need to drop the mmap_sem first. So this patch also ensures that all memory where userfaultfd could be registered by KVM, the very first fault (no matter if it is a regular page fault, or a get_user_pages) always has FAULT_FOLL_ALLOW_RETRY set. Then the userfaultfd blocks and it is waken only when the pagetable is already mapped. The second fault attempt after the wakeup doesn't need FAULT_FOLL_ALLOW_RETRY, so it's ok to retry without it. This patch (of 5): We can leverage the VM_FAULT_RETRY functionality in the page fault paths better by using either get_user_pages_locked or get_user_pages_unlocked. The former allows conversion of get_user_pages invocations that will have to pass a "&locked" parameter to know if the mmap_sem was dropped during the call. Example from: down_read(&mm->mmap_sem); do_something() get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); to: int locked = 1; down_read(&mm->mmap_sem); do_something() get_user_pages_locked(tsk, mm, ..., pages, &locked); if (locked) up_read(&mm->mmap_sem); The latter is suitable only as a drop in replacement of the form: down_read(&mm->mmap_sem); get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); into: get_user_pages_unlocked(tsk, mm, ..., pages); Where tsk, mm, the intermediate "..." paramters and "pages" can be any value as before. Just the last parameter of get_user_pages (vmas) must be NULL for get_user_pages_locked|unlocked to be usable (the latter original form wouldn't have been safe anyway if vmas wasn't null, for the former we just make it explicit by dropping the parameter). If vmas is not NULL these two methods cannot be used. Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Peter Feiner Reviewed-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 644990b83cda..fc499e675475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1261,6 +1261,13 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked); +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct kvec; -- cgit v1.2.3 From 0fd71a56f41d4ffabeda1dae9ff5ed4f34d4e935 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:20 -0800 Subject: mm: gup: add __get_user_pages_unlocked to customize gup_flags Some callers (like KVM) may want to set the gup_flags like FOLL_HWPOSION to get a proper -EHWPOSION retval instead of -EFAULT to take a more appropriate action if get_user_pages runs into a memory failure. Signed-off-by: Andrea Arcangeli Reviewed-by: Kirill A. Shutemov Cc: Andres Lagar-Cavilla Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index fc499e675475..3696b3bd1d7e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1265,6 +1265,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, int *locked); +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags); long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages); -- cgit v1.2.3 From 0664e57ff0c68cbca012a45a38288fa277eb6795 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:28 -0800 Subject: mm: gup: kvm use get_user_pages_unlocked Use the more generic get_user_pages_unlocked which has the additional benefit of passing FAULT_FLAG_ALLOW_RETRY at the very first page fault (which allows the first page fault in an unmapped area to be always able to block indefinitely by being allowed to release the mmap_sem). Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Kirill A. Shutemov Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kvm_host.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 26f106022c88..d189ee098aa2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -200,17 +200,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -/* - * Carry out a gup that requires IO. Allow the mm to relinquish the mmap - * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL - * controls whether we retry the gup one more time to completion in that case. - * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp - * handler. - */ -int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, bool write_fault, - struct page **pagep); - enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, -- cgit v1.2.3 From 0b1fbfe50006c41014cc25660c0e735d21c34939 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:34 -0800 Subject: mm/pagewalk: remove pgd_entry() and pud_entry() Currently no user of page table walker sets ->pgd_entry() or ->pud_entry(), so checking their existence in each loop is just wasting CPU cycle. So let's remove it to reduce overhead. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3696b3bd1d7e..f6106d3f3dab 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1164,8 +1164,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, /** * mm_walk - callbacks for walk_page_range - * @pgd_entry: if set, called for each non-empty PGD (top-level) entry - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to @@ -1179,10 +1177,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *pgd, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pud_entry)(pud_t *pud, unsigned long addr, - unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_entry)(pte_t *pte, unsigned long addr, -- cgit v1.2.3 From fafaa4264eba49fd10695c193a82760558d093f4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:37 -0800 Subject: pagewalk: improve vma handling Current implementation of page table walker has a fundamental problem in vma handling, which started when we tried to handle vma(VM_HUGETLB). Because it's done in pgd loop, considering vma boundary makes code complicated and bug-prone. From the users viewpoint, some user checks some vma-related condition to determine whether the user really does page walk over the vma. In order to solve these, this patch moves vma check outside pgd loop and introduce a new callback ->test_walk(). Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6106d3f3dab..3891a368e5e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1171,10 +1171,16 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry - * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry - * is used. + * @test_walk: caller specific callback function to determine whether + * we walk over the current vma or not. A positive returned + * value means "do page table walk over the current vma," + * and a negative one means "abort current page table walk + * right now." 0 means "skip the current vma." + * @mm: mm_struct representing the target process of page table walk + * @vma: vma currently walked (NULL if walking outside vmas) + * @private: private data for callbacks' usage * - * (see walk_page_range for more details) + * (see the comment on walk_page_range() for more details) */ struct mm_walk { int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -1186,7 +1192,10 @@ struct mm_walk { int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); + int (*test_walk)(unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; + struct vm_area_struct *vma; void *private; }; -- cgit v1.2.3 From 900fc5f197b05253ae9433fb9a066c3f37d08f69 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:40 -0800 Subject: pagewalk: add walk_page_vma() Introduce walk_page_vma(), which is useful for the callers which want to walk over a given vma. It's used by later patches. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3891a368e5e0..a4d24f3c5430 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1201,6 +1201,7 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, -- cgit v1.2.3 From 94f759d62b2c6a9d124b0622077b1ddcfac43fb5 Mon Sep 17 00:00:00 2001 From: Sergei Rogachev Date: Wed, 11 Feb 2015 15:28:34 -0800 Subject: mm/page_owner.c: remove unnecessary stack_trace field Page owner uses the page_ext structure to keep meta-information for every page in the system. The structure also contains a field of type 'struct stack_trace', page owner uses this field during invocation of the function save_stack_trace. It is easy to notice that keeping a copy of this structure for every page in the system is very inefficiently in terms of memory. The patch removes this unnecessary field of page_ext and forces page owner to use a stack_trace structure allocated on the stack. [akpm@linux-foundation.org: use struct initializers] Signed-off-by: Sergei Rogachev Acked-by: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index d2a2c84c72d0..c42981cd99aa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -40,7 +40,7 @@ struct page_ext { #ifdef CONFIG_PAGE_OWNER unsigned int order; gfp_t gfp_mask; - struct stack_trace trace; + unsigned int nr_entries; unsigned long trace_entries[8]; #endif }; -- cgit v1.2.3 From 54d7e72a758609da5936d7452320d799cfc6a25c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 12 Feb 2015 08:28:12 -0500 Subject: SUNRPC: Fix a compile error when #undef CONFIG_PROC_FS The definition of rpc_count_iostats_metrics() is borked. Reported by: Jim Davis Fixes: d67ae825a59d6 ("pnfs/flexfiles: Add the FlexFile Layout Driver") Cc: Tom Haynes Signed-off-by: Trond Myklebust --- include/linux/sunrpc/metrics.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/metrics.h b/include/linux/sunrpc/metrics.h index 7e61a17030a4..694eecb2f1b5 100644 --- a/include/linux/sunrpc/metrics.h +++ b/include/linux/sunrpc/metrics.h @@ -89,8 +89,11 @@ void rpc_free_iostats(struct rpc_iostats *); static inline struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt) { return NULL; } static inline void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats) {} -static inline void rpc_count_iostats_metrics(const struct rpc_task *, - struct rpc_iostats *) {} +static inline void rpc_count_iostats_metrics(const struct rpc_task *task, + struct rpc_iostats *stats) +{ +} + static inline void rpc_print_iostats(struct seq_file *seq, struct rpc_clnt *clnt) {} static inline void rpc_free_iostats(struct rpc_iostats *stats) {} -- cgit v1.2.3 From 5d833062139d290adb8b62c093b654a01a353448 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Feb 2015 14:58:16 -0800 Subject: mm: numa: do not dereference pmd outside of the lock during NUMA hinting fault Automatic NUMA balancing depends on being able to protect PTEs to trap a fault and gather reference locality information. Very broadly speaking it would mark PTEs as not present and use another bit to distinguish between NUMA hinting faults and other types of faults. It was universally loved by everybody and caused no problems whatsoever. That last sentence might be a lie. This series is very heavily based on patches from Linus and Aneesh to replace the existing PTE/PMD NUMA helper functions with normal change protections. I did alter and add parts of it but I consider them relatively minor contributions. At their suggestion, acked-bys are in there but I've no problem converting them to Signed-off-by if requested. AFAIK, this has received no testing on ppc64 and I'm depending on Aneesh for that. I tested trinity under kvm-tool and passed and ran a few other basic tests. At the time of writing, only the short-lived tests have completed but testing of V2 indicated that long-term testing had no surprises. In most cases I'm leaving out detail as it's not that interesting. specjbb single JVM: There was negligible performance difference in the benchmark itself for short runs. However, system activity is higher and interrupts are much higher over time -- possibly TLB flushes. Migrations are also higher. Overall, this is more overhead but considering the problems faced with the old approach I think we just have to suck it up and find another way of reducing the overhead. specjbb multi JVM: Negligible performance difference to the actual benchmark but like the single JVM case, the system overhead is noticeably higher. Again, interrupts are a major factor. autonumabench: This was all over the place and about all that can be reasonably concluded is that it's different but not necessarily better or worse. autonumabench 3.18.0-rc5 3.18.0-rc5 mmotm-20141119 protnone-v3r3 User NUMA01 32380.24 ( 0.00%) 21642.92 ( 33.16%) User NUMA01_THEADLOCAL 22481.02 ( 0.00%) 22283.22 ( 0.88%) User NUMA02 3137.00 ( 0.00%) 3116.54 ( 0.65%) User NUMA02_SMT 1614.03 ( 0.00%) 1543.53 ( 4.37%) System NUMA01 322.97 ( 0.00%) 1465.89 (-353.88%) System NUMA01_THEADLOCAL 91.87 ( 0.00%) 49.32 ( 46.32%) System NUMA02 37.83 ( 0.00%) 14.61 ( 61.38%) System NUMA02_SMT 7.36 ( 0.00%) 7.45 ( -1.22%) Elapsed NUMA01 716.63 ( 0.00%) 599.29 ( 16.37%) Elapsed NUMA01_THEADLOCAL 553.98 ( 0.00%) 539.94 ( 2.53%) Elapsed NUMA02 83.85 ( 0.00%) 83.04 ( 0.97%) Elapsed NUMA02_SMT 86.57 ( 0.00%) 79.15 ( 8.57%) CPU NUMA01 4563.00 ( 0.00%) 3855.00 ( 15.52%) CPU NUMA01_THEADLOCAL 4074.00 ( 0.00%) 4136.00 ( -1.52%) CPU NUMA02 3785.00 ( 0.00%) 3770.00 ( 0.40%) CPU NUMA02_SMT 1872.00 ( 0.00%) 1959.00 ( -4.65%) System CPU usage of NUMA01 is worse but it's an adverse workload on this machine so I'm reluctant to conclude that it's a problem that matters. On the other workloads that are sensible on this machine, system CPU usage is great. Overall time to complete the benchmark is comparable 3.18.0-rc5 3.18.0-rc5 mmotm-20141119protnone-v3r3 User 59612.50 48586.44 System 460.22 1537.45 Elapsed 1442.20 1304.29 NUMA alloc hit 5075182 5743353 NUMA alloc miss 0 0 NUMA interleave hit 0 0 NUMA alloc local 5075174 5743339 NUMA base PTE updates 637061448 443106883 NUMA huge PMD updates 1243434 864747 NUMA page range updates 1273699656 885857347 NUMA hint faults 1658116 1214277 NUMA hint local faults 959487 754113 NUMA hint local percent 57 62 NUMA pages migrated 5467056 61676398 The NUMA pages migrated look terrible but when I looked at a graph of the activity over time I see that the massive spike in migration activity was during NUMA01. This correlates with high system CPU usage and could be simply down to bad luck but any modifications that affect that workload would be related to scan rates and migrations, not the protection mechanism. For all other workloads, migration activity was comparable. Overall, headline performance figures are comparable but the overhead is higher, mostly in interrupts. To some extent, higher overhead from this approach was anticipated but not to this degree. It's going to be necessary to reduce this again with a separate series in the future. It's still worth going ahead with this series though as it's likely to avoid constant headaches with Xen and is probably easier to maintain. This patch (of 10): A transhuge NUMA hinting fault may find the page is migrating and should wait until migration completes. The check is race-prone because the pmd is deferenced outside of the page lock and while the race is tiny, it'll be larger if the PMD is cleared while marking PMDs for hinting fault. This patch closes the race. Signed-off-by: Mel Gorman Cc: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Dave Jones Cc: Hugh Dickins Cc: Ingo Molnar Cc: Kirill Shutemov Cc: Linus Torvalds Cc: Paul Mackerras Cc: Rik van Riel Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index fab9b32ace8e..78baed5f2952 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -67,7 +67,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #ifdef CONFIG_NUMA_BALANCING extern bool pmd_trans_migrating(pmd_t pmd); -extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); extern bool migrate_ratelimited(int node); @@ -76,9 +75,6 @@ static inline bool pmd_trans_migrating(pmd_t pmd) { return false; } -static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) -{ -} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { -- cgit v1.2.3 From 4d9424669946532be754a6e116618dcb58430cb4 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Feb 2015 14:58:28 -0800 Subject: mm: convert p[te|md]_mknonnuma and remaining page table manipulations With PROT_NONE, the traditional page table manipulation functions are sufficient. [andre.przywara@arm.com: fix compiler warning in pmdp_invalidate()] [akpm@linux-foundation.org: fix build with STRICT_MM_TYPECHECKS] Signed-off-by: Mel Gorman Acked-by: Linus Torvalds Acked-by: Aneesh Kumar Tested-by: Sasha Levin Cc: Benjamin Herrenschmidt Cc: Dave Jones Cc: Hugh Dickins Cc: Ingo Molnar Cc: Kirill Shutemov Cc: Paul Mackerras Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f10b20f05159..062bd252e994 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -31,8 +31,7 @@ extern int move_huge_pmd(struct vm_area_struct *vma, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot, - int prot_numa); + unsigned long addr, pgprot_t newprot); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, -- cgit v1.2.3 From 21d9ee3eda7792c45880b2f11bff8e95c9a061fb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Feb 2015 14:58:32 -0800 Subject: mm: remove remaining references to NUMA hinting bits and helpers This patch removes the NUMA PTE bits and associated helpers. As a side-effect it increases the maximum possible swap space on x86-64. One potential source of problems is races between the marking of PTEs PROT_NONE, NUMA hinting faults and migration. It must be guaranteed that a PTE being protected is not faulted in parallel, seen as a pte_none and corrupting memory. The base case is safe but transhuge has problems in the past due to an different migration mechanism and a dependance on page lock to serialise migrations and warrants a closer look. task_work hinting update parallel fault ------------------------ -------------- change_pmd_range change_huge_pmd __pmd_trans_huge_lock pmdp_get_and_clear __handle_mm_fault pmd_none do_huge_pmd_anonymous_page read? pmd_lock blocks until hinting complete, fail !pmd_none test write? __do_huge_pmd_anonymous_page acquires pmd_lock, checks pmd_none pmd_modify set_pmd_at task_work hinting update parallel migration ------------------------ ------------------ change_pmd_range change_huge_pmd __pmd_trans_huge_lock pmdp_get_and_clear __handle_mm_fault do_huge_pmd_numa_page migrate_misplaced_transhuge_page pmd_lock waits for updates to complete, recheck pmd_same pmd_modify set_pmd_at Both of those are safe and the case where a transhuge page is inserted during a protection update is unchanged. The case where two processes try migrating at the same time is unchanged by this series so should still be ok. I could not find a case where we are accidentally depending on the PTE not being cleared and flushed. If one is missed, it'll manifest as corruption problems that start triggering shortly after this series is merged and only happen when NUMA balancing is enabled. Signed-off-by: Mel Gorman Tested-by: Sasha Levin Cc: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Dave Jones Cc: Hugh Dickins Cc: Ingo Molnar Cc: Kirill Shutemov Cc: Linus Torvalds Cc: Paul Mackerras Cc: Rik van Riel Cc: Mark Brown Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 831a3168ab35..cedf3d3c373f 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry) /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { - return !pte_none(pte) && !pte_present_nonuma(pte); + return !pte_none(pte) && !pte_present(pte); } #endif -- cgit v1.2.3 From e944fd67b625c02bda4a78ddf85e413c5e401474 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 12 Feb 2015 14:58:35 -0800 Subject: mm: numa: do not trap faults on the huge zero page Faults on the huge zero page are pointless and there is a BUG_ON to catch them during fault time. This patch reintroduces a check that avoids marking the zero page PAGE_NONE. Signed-off-by: Mel Gorman Cc: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Dave Jones Cc: Hugh Dickins Cc: Ingo Molnar Cc: Kirill Shutemov Cc: Linus Torvalds Cc: Paul Mackerras Cc: Rik van Riel Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 062bd252e994..f10b20f05159 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -31,7 +31,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot); + unsigned long addr, pgprot_t newprot, + int prot_numa); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, -- cgit v1.2.3 From 503c358cf1925853195ee39ec437e51138bbb7df Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:58:47 -0800 Subject: list_lru: introduce list_lru_shrink_{count,walk} Kmem accounting of memcg is unusable now, because it lacks slab shrinker support. That means when we hit the limit we will get ENOMEM w/o any chance to recover. What we should do then is to call shrink_slab, which would reclaim old inode/dentry caches from this cgroup. This is what this patch set is intended to do. Basically, it does two things. First, it introduces the notion of per-memcg slab shrinker. A shrinker that wants to reclaim objects per cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be passed the memory cgroup to scan from in shrink_control->memcg. For such shrinkers shrink_slab iterates over the whole cgroup subtree under the target cgroup and calls the shrinker for each kmem-active memory cgroup. Secondly, this patch set makes the list_lru structure per-memcg. It's done transparently to list_lru users - everything they have to do is to tell list_lru_init that they want memcg-aware list_lru. Then the list_lru will automatically distribute objects among per-memcg lists basing on which cgroup the object is accounted to. This way to make FS shrinkers (icache, dcache) memcg-aware we only need to make them use memcg-aware list_lru, and this is what this patch set does. As before, this patch set only enables per-memcg kmem reclaim when the pressure goes from memory.limit, not from memory.kmem.limit. Handling memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and it is still unclear whether we will have this knob in the unified hierarchy. This patch (of 9): NUMA aware slab shrinkers use the list_lru structure to distribute objects coming from different NUMA nodes to different lists. Whenever such a shrinker needs to count or scan objects from a particular node, it issues commands like this: count = list_lru_count_node(lru, sc->nid); freed = list_lru_walk_node(lru, sc->nid, isolate_func, isolate_arg, &sc->nr_to_scan); where sc is an instance of the shrink_control structure passed to it from vmscan. To simplify this, let's add special list_lru functions to be used by shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which consolidate the nid and nr_to_scan arguments in the shrink_control structure. This will also allow us to avoid patching shrinkers that use list_lru when we make shrink_slab() per-memcg - all we will have to do is extend the shrink_control structure to include the target memcg and make list_lru_shrink_{count,walk} handle this appropriately. Signed-off-by: Vladimir Davydov Suggested-by: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index f3434533fbf8..f500a2e39b13 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -9,6 +9,7 @@ #include #include +#include /* list_lru_walk_cb has to always return one of those */ enum lru_status { @@ -81,6 +82,13 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item); * Callers that want such a guarantee need to provide an outer lock. */ unsigned long list_lru_count_node(struct list_lru *lru, int nid); + +static inline unsigned long list_lru_shrink_count(struct list_lru *lru, + struct shrink_control *sc) +{ + return list_lru_count_node(lru, sc->nid); +} + static inline unsigned long list_lru_count(struct list_lru *lru) { long count = 0; @@ -119,6 +127,14 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); +static inline unsigned long +list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, + list_lru_walk_cb isolate, void *cb_arg) +{ + return list_lru_walk_node(lru, sc->nid, isolate, cb_arg, + &sc->nr_to_scan); +} + static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) -- cgit v1.2.3 From 4101b624352fddb5ed72e7a1b6f8be8cffaa20fa Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:58:51 -0800 Subject: fs: consolidate {nr,free}_cached_objects args in shrink_control We are going to make FS shrinkers memcg-aware. To achieve that, we will have to pass the memcg to scan to the nr_cached_objects and free_cached_objects VFS methods, which currently take only the NUMA node to scan. Since the shrink_control structure already holds the node, and the memcg to scan will be added to it when we introduce memcg-aware vmscan, let us consolidate the methods' arguments in this structure to keep things clean. Signed-off-by: Vladimir Davydov Suggested-by: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cdcb1e9d9613..a20d6586e517 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1635,8 +1635,10 @@ struct super_operations { struct dquot **(*get_dquots)(struct inode *); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); - long (*nr_cached_objects)(struct super_block *, int); - long (*free_cached_objects)(struct super_block *, long, int); + long (*nr_cached_objects)(struct super_block *, + struct shrink_control *); + long (*free_cached_objects)(struct super_block *, + struct shrink_control *); }; /* -- cgit v1.2.3 From cb731d6c62bbc2f890b08ea3d0386d5dad887326 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:58:54 -0800 Subject: vmscan: per memory cgroup slab shrinkers This patch adds SHRINKER_MEMCG_AWARE flag. If a shrinker has this flag set, it will be called per memory cgroup. The memory cgroup to scan objects from is passed in shrink_control->memcg. If the memory cgroup is NULL, a memcg aware shrinker is supposed to scan objects from the global list. Unaware shrinkers are only called on global pressure with memcg=NULL. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 +++++++ include/linux/mm.h | 5 ++--- include/linux/shrinker.h | 6 +++++- 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6cfd934c7c9b..54992fe0959f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -413,6 +413,8 @@ static inline bool memcg_kmem_enabled(void) return static_key_false(&memcg_kmem_enabled_key); } +bool memcg_kmem_is_active(struct mem_cgroup *memcg); + /* * In general, we'll do everything in our power to not incur in any overhead * for non-memcg users for the kmem functions. Not even a function call, if we @@ -542,6 +544,11 @@ static inline bool memcg_kmem_enabled(void) return false; } +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return false; +} + static inline bool memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) { diff --git a/include/linux/mm.h b/include/linux/mm.h index a4d24f3c5430..af4ff88a11e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2168,9 +2168,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); #endif -unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, - unsigned long nr_scanned, - unsigned long nr_eligible); +void drop_slab(void); +void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index f4aee75f00b1..4fcacd915d45 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -20,6 +20,9 @@ struct shrink_control { /* current node being shrunk (for NUMA aware shrinkers) */ int nid; + + /* current memcg being shrunk (for memcg aware shrinkers) */ + struct mem_cgroup *memcg; }; #define SHRINK_STOP (~0UL) @@ -61,7 +64,8 @@ struct shrinker { #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ /* Flags */ -#define SHRINKER_NUMA_AWARE (1 << 0) +#define SHRINKER_NUMA_AWARE (1 << 0) +#define SHRINKER_MEMCG_AWARE (1 << 1) extern int register_shrinker(struct shrinker *); extern void unregister_shrinker(struct shrinker *); -- cgit v1.2.3 From dbcf73e26cd0b3d66e6db65ab595e664a55e58ff Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:58:57 -0800 Subject: memcg: rename some cache id related variables memcg_limited_groups_array_size, which defines the size of memcg_caches arrays, sounds rather cumbersome. Also it doesn't point anyhow that it's related to kmem/caches stuff. So let's rename it to memcg_nr_cache_ids. It's concise and points us directly to memcg_cache_id. Also, rename kmem_limited_groups to memcg_cache_ida. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 54992fe0959f..2607c91230af 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -398,7 +398,7 @@ static inline void sock_release_memcg(struct sock *sk) #ifdef CONFIG_MEMCG_KMEM extern struct static_key memcg_kmem_enabled_key; -extern int memcg_limited_groups_array_size; +extern int memcg_nr_cache_ids; /* * Helper macro to loop through all memcg-specific caches. Callers must still @@ -406,7 +406,7 @@ extern int memcg_limited_groups_array_size; * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_limited_groups_array_size; (_idx)++) + for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) static inline bool memcg_kmem_enabled(void) { -- cgit v1.2.3 From 05257a1a3dcc196c197714b5c9a8dd35b7f6aefc Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:01 -0800 Subject: memcg: add rwsem to synchronize against memcg_caches arrays relocation We need a stable value of memcg_nr_cache_ids in kmem_cache_create() (memcg_alloc_cache_params() wants it for root caches), where we only hold the slab_mutex and no memcg-related locks. As a result, we have to update memcg_nr_cache_ids under the slab_mutex, which we can only take on the slab's side (see memcg_update_array_size). This looks awkward and will become even worse when per-memcg list_lru is introduced, which also wants stable access to memcg_nr_cache_ids. To get rid of this dependency between the memcg_nr_cache_ids and the slab_mutex, this patch introduces a special rwsem. The rwsem is held for writing during memcg_caches arrays relocation and memcg_nr_cache_ids updates. Therefore one can take it for reading to get a stable access to memcg_caches arrays and/or memcg_nr_cache_ids. Currently the semaphore is taken for reading only from kmem_cache_create, right before taking the slab_mutex, so right now there's no much point in using rwsem instead of mutex. However, once list_lru is made per-memcg it will allow list_lru initializations to proceed concurrently. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2607c91230af..dbc4baa3619c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -399,6 +399,8 @@ static inline void sock_release_memcg(struct sock *sk) extern struct static_key memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; +extern void memcg_get_cache_ids(void); +extern void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still @@ -434,8 +436,6 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order); int memcg_cache_id(struct mem_cgroup *memcg); -void memcg_update_array_size(int num_groups); - struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); @@ -569,6 +569,14 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return -1; } +static inline void memcg_get_cache_ids(void) +{ +} + +static inline void memcg_put_cache_ids(void) +{ +} + static inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { -- cgit v1.2.3 From ff0b67ef5b1687692bc1fd3ce4bc3d1ff83587c7 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:04 -0800 Subject: list_lru: get rid of ->active_nodes The active_nodes mask allows us to skip empty nodes when walking over list_lru items from all nodes in list_lru_count/walk. However, these functions are never called from hot paths, so it doesn't seem we need such kind of optimization there. OTOH, removing the mask will make it easier to make list_lru per-memcg. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index f500a2e39b13..53c1d6b78270 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -31,7 +31,6 @@ struct list_lru_node { struct list_lru { struct list_lru_node *node; - nodemask_t active_nodes; }; void list_lru_destroy(struct list_lru *lru); @@ -94,7 +93,7 @@ static inline unsigned long list_lru_count(struct list_lru *lru) long count = 0; int nid; - for_each_node_mask(nid, lru->active_nodes) + for_each_node_state(nid, N_NORMAL_MEMORY) count += list_lru_count_node(lru, nid); return count; @@ -142,7 +141,7 @@ list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, long isolated = 0; int nid; - for_each_node_mask(nid, lru->active_nodes) { + for_each_node_state(nid, N_NORMAL_MEMORY) { isolated += list_lru_walk_node(lru, nid, isolate, cb_arg, &nr_to_walk); if (nr_to_walk <= 0) -- cgit v1.2.3 From c0a5b560938a0f2fd2fbf66ddc446c7c2b41383a Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:07 -0800 Subject: list_lru: organize all list_lrus to list To make list_lru memcg aware, we need all list_lrus to be kept on a list protected by a mutex, so that we could sleep while walking over the list. Therefore after this change list_lru_destroy may sleep. Fortunately, there is only one user that calls it from an atomic context - it's put_super - and we can easily fix it by calling list_lru_destroy before put_super in destroy_locked_super - anyway we don't longer need lrus by that time. Another point that should be noted is that list_lru_destroy is allowed to be called on an uninitialized zeroed-out object, in which case it is a no-op. Before this patch this was guaranteed by kfree, but now we need an explicit check there. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 53c1d6b78270..ee9486ac0621 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -31,6 +31,9 @@ struct list_lru_node { struct list_lru { struct list_lru_node *node; +#ifdef CONFIG_MEMCG_KMEM + struct list_head list; +#endif }; void list_lru_destroy(struct list_lru *lru); -- cgit v1.2.3 From 60d3fd32a7a9da4c8c93a9f89cfda22a0b4c65ce Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:10 -0800 Subject: list_lru: introduce per-memcg lists There are several FS shrinkers, including super_block::s_shrink, that keep reclaimable objects in the list_lru structure. Hence to turn them to memcg-aware shrinkers, it is enough to make list_lru per-memcg. This patch does the trick. It adds an array of lru lists to the list_lru_node structure (per-node part of the list_lru), one for each kmem-active memcg, and dispatches every item addition or removal to the list corresponding to the memcg which the item is accounted to. So now the list_lru structure is not just per node, but per node and per memcg. Not all list_lrus need this feature, so this patch also adds a new method, list_lru_init_memcg, which initializes a list_lru as memcg aware. Otherwise (i.e. if initialized with old list_lru_init), the list_lru won't have per memcg lists. Just like per memcg caches arrays, the arrays of per-memcg lists are indexed by memcg_cache_id, so we must grow them whenever memcg_nr_cache_ids is increased. So we introduce a callback, memcg_update_all_list_lrus, invoked by memcg_alloc_cache_id if the id space is full. The locking is implemented in a manner similar to lruvecs, i.e. we have one lock per node that protects all lists (both global and per cgroup) on the node. Signed-off-by: Vladimir Davydov Cc: Dave Chinner Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Glauber Costa Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 52 +++++++++++++++++++++++++++++++++++----------- include/linux/memcontrol.h | 14 +++++++++++++ 2 files changed, 54 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index ee9486ac0621..305b598abac2 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,8 @@ #include #include +struct mem_cgroup; + /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ @@ -22,11 +24,26 @@ enum lru_status { internally, but has to return locked. */ }; -struct list_lru_node { - spinlock_t lock; +struct list_lru_one { struct list_head list; /* kept as signed so we can catch imbalance bugs */ long nr_items; +}; + +struct list_lru_memcg { + /* array of per cgroup lists, indexed by memcg_cache_id */ + struct list_lru_one *lru[0]; +}; + +struct list_lru_node { + /* protects all lists on the node, including per cgroup */ + spinlock_t lock; + /* global list, used for the root cgroup in cgroup aware lrus */ + struct list_lru_one lru; +#ifdef CONFIG_MEMCG_KMEM + /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ + struct list_lru_memcg *memcg_lrus; +#endif } ____cacheline_aligned_in_smp; struct list_lru { @@ -37,11 +54,14 @@ struct list_lru { }; void list_lru_destroy(struct list_lru *lru); -int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key); -static inline int list_lru_init(struct list_lru *lru) -{ - return list_lru_init_key(lru, NULL); -} +int __list_lru_init(struct list_lru *lru, bool memcg_aware, + struct lock_class_key *key); + +#define list_lru_init(lru) __list_lru_init((lru), false, NULL) +#define list_lru_init_key(lru, key) __list_lru_init((lru), false, (key)) +#define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL) + +int memcg_update_all_list_lrus(int num_memcgs); /** * list_lru_add: add an element to the lru list's tail @@ -75,20 +95,23 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item); bool list_lru_del(struct list_lru *lru, struct list_head *item); /** - * list_lru_count_node: return the number of objects currently held by @lru + * list_lru_count_one: return the number of objects currently held by @lru * @lru: the lru pointer. * @nid: the node id to count from. + * @memcg: the cgroup to count from. * * Always return a non-negative number, 0 for empty lists. There is no * guarantee that the list is not updated while the count is being computed. * Callers that want such a guarantee need to provide an outer lock. */ +unsigned long list_lru_count_one(struct list_lru *lru, + int nid, struct mem_cgroup *memcg); unsigned long list_lru_count_node(struct list_lru *lru, int nid); static inline unsigned long list_lru_shrink_count(struct list_lru *lru, struct shrink_control *sc) { - return list_lru_count_node(lru, sc->nid); + return list_lru_count_one(lru, sc->nid, sc->memcg); } static inline unsigned long list_lru_count(struct list_lru *lru) @@ -105,9 +128,10 @@ static inline unsigned long list_lru_count(struct list_lru *lru) typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); /** - * list_lru_walk_node: walk a list_lru, isolating and disposing freeable items. + * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. + * @memcg: the cgroup to scan from. * @isolate: callback function that is resposible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate @@ -125,6 +149,10 @@ typedef enum lru_status * * Return value: the number of objects effectively removed from the LRU. */ +unsigned long list_lru_walk_one(struct list_lru *lru, + int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); @@ -133,8 +161,8 @@ static inline unsigned long list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { - return list_lru_walk_node(lru, sc->nid, isolate, cb_arg, - &sc->nr_to_scan); + return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg, + &sc->nr_to_scan); } static inline unsigned long diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index dbc4baa3619c..72dff5fb0d0c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -439,6 +439,8 @@ int memcg_cache_id(struct mem_cgroup *memcg); struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); +struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr); + int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, unsigned long nr_pages); void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages); @@ -535,6 +537,13 @@ static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) if (memcg_kmem_enabled()) __memcg_kmem_put_cache(cachep); } + +static __always_inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr) +{ + if (!memcg_kmem_enabled()) + return NULL; + return __mem_cgroup_from_kmem(ptr); +} #else #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) @@ -586,6 +595,11 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) static inline void memcg_kmem_put_cache(struct kmem_cache *cachep) { } + +static inline struct mem_cgroup *mem_cgroup_from_kmem(void *ptr) +{ + return NULL; +} #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ -- cgit v1.2.3 From f7ce3190c4a35bf887adb7a1aa1ba899b679872d Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:20 -0800 Subject: slab: embed memcg_cache_params to kmem_cache Currently, kmem_cache stores a pointer to struct memcg_cache_params instead of embedding it. The rationale is to save memory when kmem accounting is disabled. However, the memcg_cache_params has shrivelled drastically since it was first introduced: * Initially: struct memcg_cache_params { bool is_root_cache; union { struct kmem_cache *memcg_caches[0]; struct { struct mem_cgroup *memcg; struct list_head list; struct kmem_cache *root_cache; bool dead; atomic_t nr_pages; struct work_struct destroy; }; }; }; * Now: struct memcg_cache_params { bool is_root_cache; union { struct { struct rcu_head rcu_head; struct kmem_cache *memcg_caches[0]; }; struct { struct mem_cgroup *memcg; struct kmem_cache *root_cache; }; }; }; So the memory saving does not seem to be a clear win anymore. OTOH, keeping a pointer to memcg_cache_params struct instead of embedding it results in touching one more cache line on kmem alloc/free hot paths. Besides, it makes linking kmem caches in a list chained by a field of struct memcg_cache_params really painful due to a level of indirection, while I want to make them linked in the following patch. That said, let us embed it. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Dave Chinner Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 17 +++++++---------- include/linux/slab_def.h | 2 +- include/linux/slub_def.h | 2 +- 3 files changed, 9 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2e3b448cfa2d..1e03c11bbfbd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -473,14 +473,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif + +struct memcg_cache_array { + struct rcu_head rcu; + struct kmem_cache *entries[0]; +}; + /* * This is the main placeholder for memcg-related information in kmem caches. - * struct kmem_cache will hold a pointer to it, so the memory cost while - * disabled is 1 pointer. The runtime cost while enabled, gets bigger than it - * would otherwise be if that would be bundled in kmem_cache: we'll need an - * extra pointer chase. But the trade off clearly lays in favor of not - * penalizing non-users. - * * Both the root cache and the child caches will have it. For the root cache, * this will hold a dynamically allocated array large enough to hold * information about the currently limited memcgs in the system. To allow the @@ -495,10 +495,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) struct memcg_cache_params { bool is_root_cache; union { - struct { - struct rcu_head rcu_head; - struct kmem_cache *memcg_caches[0]; - }; + struct memcg_cache_array __rcu *memcg_caches; struct { struct mem_cgroup *memcg; struct kmem_cache *root_cache; diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index b869d1662ba3..33d049066c3d 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -70,7 +70,7 @@ struct kmem_cache { int obj_offset; #endif /* CONFIG_DEBUG_SLAB */ #ifdef CONFIG_MEMCG_KMEM - struct memcg_cache_params *memcg_params; + struct memcg_cache_params memcg_params; #endif struct kmem_cache_node *node[MAX_NUMNODES]; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d82abd40a3c0..9abf04ed0999 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -85,7 +85,7 @@ struct kmem_cache { struct kobject kobj; /* For sysfs */ #endif #ifdef CONFIG_MEMCG_KMEM - struct memcg_cache_params *memcg_params; + struct memcg_cache_params memcg_params; int max_attr_size; /* for propagation, maximum size of a stored attr */ #ifdef CONFIG_SYSFS struct kset *memcg_kset; -- cgit v1.2.3 From 426589f571f7d6d5ab2ca33ece73164149279ca1 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:23 -0800 Subject: slab: link memcg caches of the same kind into a list Sometimes, we need to iterate over all memcg copies of a particular root kmem cache. Currently, we use memcg_cache_params->memcg_caches array for that, because it contains all existing memcg caches. However, it's a bad practice to keep all caches, including those that belong to offline cgroups, in this array, because it will be growing beyond any bounds then. I'm going to wipe away dead caches from it to save space. To still be able to perform iterations over all memcg caches of the same kind, let us link them into a list. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 1e03c11bbfbd..26d99f41b410 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -491,9 +491,13 @@ struct memcg_cache_array { * * @memcg: pointer to the memcg this cache belongs to * @root_cache: pointer to the global, root cache, this cache was derived from + * + * Both root and child caches of the same kind are linked into a list chained + * through @list. */ struct memcg_cache_params { bool is_root_cache; + struct list_head list; union { struct memcg_cache_array __rcu *memcg_caches; struct { -- cgit v1.2.3 From 2a4db7eb9391a544ff58f4fa11d35246e87c87af Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:32 -0800 Subject: memcg: free memcg_caches slot on css offline We need to look up a kmem_cache in ->memcg_params.memcg_caches arrays only on allocations, so there is no need to have the array entries set until css free - we can clear them on css offline. This will allow us to reuse array entries more efficiently and avoid costly array relocations. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 26d99f41b410..ed2ffaab59ea 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -115,13 +115,12 @@ int slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *, size_t, size_t, unsigned long, void (*)(void *)); -#ifdef CONFIG_MEMCG_KMEM -void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); -void memcg_destroy_kmem_caches(struct mem_cgroup *); -#endif void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); -void kmem_cache_free(struct kmem_cache *, void *); + +void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *); +void memcg_deactivate_kmem_caches(struct mem_cgroup *); +void memcg_destroy_kmem_caches(struct mem_cgroup *); /* * Please use this macro to create slab caches. Simply specify the @@ -288,6 +287,7 @@ static __always_inline int kmalloc_index(size_t size) void *__kmalloc(size_t size, gfp_t flags); void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); +void kmem_cache_free(struct kmem_cache *, void *); #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node); -- cgit v1.2.3 From 3f97b163207c67a3b35931494ad3db1de66356f0 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:35 -0800 Subject: list_lru: add helpers to isolate items Currently, the isolate callback passed to the list_lru_walk family of functions is supposed to just delete an item from the list upon returning LRU_REMOVED or LRU_REMOVED_RETRY, while nr_items counter is fixed by __list_lru_walk_one after the callback returns. Since the callback is allowed to drop the lock after removing an item (it has to return LRU_REMOVED_RETRY then), the nr_items can be less than the actual number of elements on the list even if we check them under the lock. This makes it difficult to move items from one list_lru_one to another, which is required for per-memcg list_lru reparenting - we can't just splice the lists, we have to move entries one by one. This patch therefore introduces helpers that must be used by callback functions to isolate items instead of raw list_del/list_move. These are list_lru_isolate and list_lru_isolate_move. They not only remove the entry from the list, but also fix the nr_items counter, making sure nr_items always reflects the actual number of elements on the list if checked under the appropriate lock. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 305b598abac2..7edf9c9ab9eb 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -125,8 +125,13 @@ static inline unsigned long list_lru_count(struct list_lru *lru) return count; } -typedef enum lru_status -(*list_lru_walk_cb)(struct list_head *item, spinlock_t *lock, void *cb_arg); +void list_lru_isolate(struct list_lru_one *list, struct list_head *item); +void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, + struct list_head *head); + +typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, + struct list_lru_one *list, spinlock_t *lock, void *cb_arg); + /** * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items. * @lru: the lru pointer. -- cgit v1.2.3 From 2788cf0c401c268b4819c5407493a8769b7007aa Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 12 Feb 2015 14:59:38 -0800 Subject: memcg: reparent list_lrus and free kmemcg_id on css offline Now, the only reason to keep kmemcg_id till css free is list_lru, which uses it to distribute elements between per-memcg lists. However, it can be easily sorted out - we only need to change kmemcg_id of an offline cgroup to its parent's id, making further list_lru_add()'s add elements to the parent's list, and then move all elements from the offline cgroup's list to the one of its parent. It will work, because a racing list_lru_del() does not need to know the list it is deleting the element from. It can decrement the wrong nr_items counter though, but the ongoing reparenting will fix it. After list_lru reparenting is done we are free to release kmemcg_id saving a valuable slot in a per-memcg array for new cgroups. Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 7edf9c9ab9eb..2a6b9947aaa3 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -26,7 +26,7 @@ enum lru_status { struct list_lru_one { struct list_head list; - /* kept as signed so we can catch imbalance bugs */ + /* may become negative during memcg reparenting */ long nr_items; }; @@ -62,6 +62,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL) int memcg_update_all_list_lrus(int num_memcgs); +void memcg_drain_all_list_lrus(int src_idx, int dst_idx); /** * list_lru_add: add an element to the lru list's tail -- cgit v1.2.3 From 2d2f5119b8bb057595e18f5b2f07aa097ea1b233 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 12 Feb 2015 14:59:59 -0800 Subject: mm: do not use mm->nr_pmds on !MMU configurations mm->nr_pmds doesn't make sense on !MMU configurations Signed-off-by: Kirill A. Shutemov Cc: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index af4ff88a11e0..bd52e2f14027 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1447,13 +1447,15 @@ static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif -#ifdef __PAGETABLE_PMD_FOLDED +#if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } +static inline void mm_nr_pmds_init(struct mm_struct *mm) {} + static inline unsigned long mm_nr_pmds(struct mm_struct *mm) { return 0; @@ -1465,6 +1467,11 @@ static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); +static inline void mm_nr_pmds_init(struct mm_struct *mm) +{ + atomic_long_set(&mm->nr_pmds, 0); +} + static inline unsigned long mm_nr_pmds(struct mm_struct *mm) { return atomic_long_read(&mm->nr_pmds); -- cgit v1.2.3 From 3eba0c6a56c04f2b017b43641a821f1ebfb7fb4c Mon Sep 17 00:00:00 2001 From: Ganesh Mahendran Date: Thu, 12 Feb 2015 15:00:51 -0800 Subject: mm/zpool: add name argument to create zpool Currently the underlay of zpool: zsmalloc/zbud, do not know who creates them. There is not a method to let zsmalloc/zbud find which caller they belong to. Now we want to add statistics collection in zsmalloc. We need to name the debugfs dir for each pool created. The way suggested by Minchan Kim is to use a name passed by caller(such as zram) to create the zsmalloc pool. /sys/kernel/debug/zsmalloc/zram0 This patch adds an argument `name' to zs_create_pool() and other related functions. Signed-off-by: Ganesh Mahendran Acked-by: Minchan Kim Cc: Seth Jennings Cc: Nitin Gupta Cc: Dan Streetman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zpool.h | 5 +++-- include/linux/zsmalloc.h | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/zpool.h b/include/linux/zpool.h index f14bd75f08b3..56529b34dc63 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -36,7 +36,8 @@ enum zpool_mapmode { ZPOOL_MM_DEFAULT = ZPOOL_MM_RW }; -struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops); +struct zpool *zpool_create_pool(char *type, char *name, + gfp_t gfp, struct zpool_ops *ops); char *zpool_get_type(struct zpool *pool); @@ -80,7 +81,7 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(gfp_t gfp, struct zpool_ops *ops); + void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops); void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 05c214760977..3283c6a55425 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -36,7 +36,7 @@ enum zs_mapmode { struct zs_pool; -struct zs_pool *zs_create_pool(gfp_t flags); +struct zs_pool *zs_create_pool(char *name, gfp_t flags); void zs_destroy_pool(struct zs_pool *pool); unsigned long zs_malloc(struct zs_pool *pool, size_t size); -- cgit v1.2.3 From 695f055936938c674473ea071ca7359a863551e7 Mon Sep 17 00:00:00 2001 From: Petr Cermak Date: Thu, 12 Feb 2015 15:01:00 -0800 Subject: fs/proc/task_mmu.c: add user-space support for resetting mm->hiwater_rss (peak RSS) Peak resident size of a process can be reset back to the process's current rss value by writing "5" to /proc/pid/clear_refs. The driving use-case for this would be getting the peak RSS value, which can be retrieved from the VmHWM field in /proc/pid/status, per benchmark iteration or test scenario. [akpm@linux-foundation.org: clarify behaviour in documentation] Signed-off-by: Petr Cermak Cc: Bjorn Helgaas Cc: Primiano Tucci Cc: Petr Cermak Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bd52e2f14027..9bee7ec0c31f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1408,6 +1408,11 @@ static inline void update_hiwater_vm(struct mm_struct *mm) mm->hiwater_vm = mm->total_vm; } +static inline void reset_mm_hiwater_rss(struct mm_struct *mm) +{ + mm->hiwater_rss = get_mm_rss(mm); +} + static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { -- cgit v1.2.3 From f56141e3e2d9aabf7e6b89680ab572c2cdbb2a24 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 12 Feb 2015 15:01:14 -0800 Subject: all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski Cc: Thomas Gleixner Cc: Al Viro Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Kees Cook Cc: David Miller Acked-by: Richard Weinberger Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Vineet Gupta Cc: Russell King Cc: Catalin Marinas Cc: Will Deacon Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Steven Miao Cc: Mark Salter Cc: Aurelien Jacquiot Cc: Mikael Starvik Cc: Jesper Nilsson Cc: David Howells Cc: Richard Kuo Cc: "Luck, Tony" Cc: Geert Uytterhoeven Cc: Michal Simek Cc: Ralf Baechle Cc: Jonas Bonn Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Acked-by: Michael Ellerman (powerpc) Tested-by: Michael Ellerman (powerpc) Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Chen Liqin Cc: Lennox Wu Cc: Chris Metcalf Cc: Guan Xuetao Cc: Chris Zankel Cc: Max Filippov Cc: Oleg Nesterov Cc: Guenter Roeck Signed-off-by: James Hogan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 3 +++ include/linux/sched.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 3037fc085e8e..d3d43ecf148c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -193,6 +193,9 @@ extern struct task_group root_task_group; .nr_cpus_allowed= NR_CPUS, \ .mm = NULL, \ .active_mm = &init_mm, \ + .restart_block = { \ + .fn = do_no_restart_syscall, \ + }, \ .se = { \ .group_node = LIST_HEAD_INIT(tsk.se.group_node), \ }, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 8db31ef98d2f..22ee0d5d7f8c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1370,6 +1370,8 @@ struct task_struct { unsigned long atomic_flags; /* Flags needing atomic access. */ + struct restart_block restart_block; + pid_t pid; pid_t tgid; -- cgit v1.2.3 From dd4a5c1e6531b9c6ba6ee1f3cb11f0aeea25881e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 12 Feb 2015 15:01:22 -0800 Subject: linux/types.h: Always use unsigned long for pgoff_t Everybody uses unsigned long for pgoff_t, and no one ever overrode the definition of pgoff_t. Keep it that way, and remove the option of overriding it. Signed-off-by: Geert Uytterhoeven Cc: Randy Dunlap Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/types.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/types.h b/include/linux/types.h index 62323825cff9..6747247e3f9f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -135,12 +135,9 @@ typedef unsigned long blkcnt_t; #endif /* - * The type of an index into the pagecache. Use a #define so asm/types.h - * can override it. + * The type of an index into the pagecache. */ -#ifndef pgoff_t #define pgoff_t unsigned long -#endif /* A dma_addr_t can hold any valid DMA or bus address for the platform */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT -- cgit v1.2.3 From 545a2bf742fb41f17d03486dd8a8c74ad511dec2 Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Thu, 12 Feb 2015 15:01:24 -0800 Subject: kernel/sched/clock.c: add another clock for use with the soft lockup watchdog When the hypervisor pauses a virtualised kernel the kernel will observe a jump in timebase, this can cause spurious messages from the softlockup detector. Whilst these messages are harmless, they are accompanied with a stack trace which causes undue concern and more problematically the stack trace in the guest has nothing to do with the observed problem and can only be misleading. Futhermore, on POWER8 this is completely avoidable with the introduction of the Virtual Time Base (VTB) register. This patch (of 2): This permits the use of arch specific clocks for which virtualised kernels can use their notion of 'running' time, not the elpased wall time which will include host execution time. Signed-off-by: Cyril Bur Cc: Michael Ellerman Cc: Andrew Jones Acked-by: Don Zickus Cc: Ingo Molnar Cc: Ulrich Obergfell Cc: chai wen Cc: Fabian Frederick Cc: Aaron Tomlin Cc: Ben Zhang Cc: Martin Schwidefsky Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 22ee0d5d7f8c..048b91b983ed 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2147,6 +2147,7 @@ extern unsigned long long notrace sched_clock(void); */ extern u64 cpu_clock(int cpu); extern u64 local_clock(void); +extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); -- cgit v1.2.3 From 02f1f2170d2831b3233e91091c60a66622f29e82 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:31 -0800 Subject: kernel.h: remove ancient __FUNCTION__ hack __FUNCTION__ hasn't been treated as a string literal since gcc 3.4, so this only helps people who only test-compile using 3.3 (compiler-gcc3.h barks at anything older than that). Besides, there are almost no occurrences of __FUNCTION__ left in the tree. [akpm@linux-foundation.org: convert remaining __FUNCTION__ references] Signed-off-by: Rasmus Villemoes Cc: Michal Nazarewicz Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e42e7dc34c68..d6d630d31ef3 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -800,9 +800,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -/* Trap pasters of __FUNCTION__ at compile-time */ -#define __FUNCTION__ (__func__) - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3 From d1214c65c02d503330ce86bd38e344a36599e055 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:50 -0800 Subject: libstring_helpers.c:string_get_size(): return void string_get_size() was documented to return an error, but in fact always returned 0. Since the output always fits in 9 bytes, just document that and let callers do what they do now: pass a small stack buffer and ignore the return value. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 6eb567ac56bc..657571817260 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -10,8 +10,8 @@ enum string_size_units { STRING_UNITS_2, /* use binary powers of 2^10 */ }; -int string_get_size(u64 size, enum string_size_units units, - char *buf, int len); +void string_get_size(u64 size, enum string_size_units units, + char *buf, int len); #define UNESCAPE_SPACE 0x01 #define UNESCAPE_OCTAL 0x02 -- cgit v1.2.3 From 8b4daad52fee7731ea4bae22a99ece2d4ba7ba43 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:53 -0800 Subject: lib/bitmap.c: more signed->unsigned conversions For consistency with the other bitmap_* functions, also make the nbits parameter of bitmap_zero, bitmap_fill and bitmap_copy unsigned. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 202e4034fe26..1406d5453781 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -185,33 +185,33 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) -static inline void bitmap_zero(unsigned long *dst, int nbits) +static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); memset(dst, 0, len); } } -static inline void bitmap_fill(unsigned long *dst, int nbits) +static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - size_t nlongs = BITS_TO_LONGS(nbits); + unsigned int nlongs = BITS_TO_LONGS(nbits); if (!small_const_nbits(nbits)) { - int len = (nlongs - 1) * sizeof(unsigned long); + unsigned int len = (nlongs - 1) * sizeof(unsigned long); memset(dst, 0xff, len); } dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, - int nbits) + unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); memcpy(dst, src, len); } } -- cgit v1.2.3 From 33c4fa8c6763f1ba9f4ea64079882eaa6d7957b7 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:56 -0800 Subject: linux/nodemask.h: update bitmap wrappers to take unsigned int Since the various bitmap_* functions now take an unsigned int as nbits parameter, it makes sense to also update the various wrappers. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 83a6aeda899d..21cef483dc1b 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -120,13 +120,13 @@ static inline void __node_clear(int node, volatile nodemask_t *dstp) } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) -static inline void __nodes_setall(nodemask_t *dstp, int nbits) +static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) -static inline void __nodes_clear(nodemask_t *dstp, int nbits) +static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -144,7 +144,7 @@ static inline int __node_test_and_set(int node, nodemask_t *addr) #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } @@ -152,7 +152,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } @@ -160,7 +160,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } @@ -168,7 +168,7 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } @@ -176,7 +176,7 @@ static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static inline void __nodes_complement(nodemask_t *dstp, - const nodemask_t *srcp, int nbits) + const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } @@ -184,7 +184,7 @@ static inline void __nodes_complement(nodemask_t *dstp, #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_equal(const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } @@ -192,7 +192,7 @@ static inline int __nodes_equal(const nodemask_t *src1p, #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_intersects(const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } @@ -200,25 +200,25 @@ static inline int __nodes_intersects(const nodemask_t *src1p, #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static inline int __nodes_subset(const nodemask_t *src1p, - const nodemask_t *src2p, int nbits) + const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) -static inline int __nodes_empty(const nodemask_t *srcp, int nbits) +static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) -static inline int __nodes_full(const nodemask_t *srcp, int nbits) +static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) -static inline int __nodes_weight(const nodemask_t *srcp, int nbits) +static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } -- cgit v1.2.3 From f5ac1f55204fec9d9c63644bc1de0ab6a59af9f1 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:59 -0800 Subject: linux/cpumask.h: update bitmap wrappers to take unsigned int Since the various bitmap_* functions now take an unsigned int as nbits parameter, it makes sense to also update the various wrappers, even though they're marked as obsolete. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b950e9d6008b..ff9044286d88 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -905,13 +905,13 @@ static inline void __cpu_clear(int cpu, volatile cpumask_t *dstp) } #define cpus_setall(dst) __cpus_setall(&(dst), NR_CPUS) -static inline void __cpus_setall(cpumask_t *dstp, int nbits) +static inline void __cpus_setall(cpumask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define cpus_clear(dst) __cpus_clear(&(dst), NR_CPUS) -static inline void __cpus_clear(cpumask_t *dstp, int nbits) +static inline void __cpus_clear(cpumask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } @@ -927,21 +927,21 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr) #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS) static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS) static inline void __cpus_or(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_xor(dst, src1, src2) __cpus_xor(&(dst), &(src1), &(src2), NR_CPUS) static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } @@ -949,40 +949,40 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p, #define cpus_andnot(dst, src1, src2) \ __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS) static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define cpus_equal(src1, src2) __cpus_equal(&(src1), &(src2), NR_CPUS) static inline int __cpus_equal(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define cpus_intersects(src1, src2) __cpus_intersects(&(src1), &(src2), NR_CPUS) static inline int __cpus_intersects(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define cpus_subset(src1, src2) __cpus_subset(&(src1), &(src2), NR_CPUS) static inline int __cpus_subset(const cpumask_t *src1p, - const cpumask_t *src2p, int nbits) + const cpumask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define cpus_empty(src) __cpus_empty(&(src), NR_CPUS) -static inline int __cpus_empty(const cpumask_t *srcp, int nbits) +static inline int __cpus_empty(const cpumask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define cpus_weight(cpumask) __cpus_weight(&(cpumask), NR_CPUS) -static inline int __cpus_weight(const cpumask_t *srcp, int nbits) +static inline int __cpus_weight(const cpumask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } -- cgit v1.2.3 From eb5698837881687841c9e477e4162ac3387c6b59 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:01 -0800 Subject: lib/bitmap.c: update bitmap_onto to unsigned Change the nbits parameter of bitmap_onto to unsigned int for consistency with other bitmap_* functions. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 1406d5453781..d0c6214eb190 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -164,7 +164,7 @@ extern void bitmap_remap(unsigned long *dst, const unsigned long *src, extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, - const unsigned long *relmap, int bits); + const unsigned long *relmap, unsigned int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, int sz, int bits); extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); -- cgit v1.2.3 From b26ad5836c3a0a9d456eb60b9f841ca15403ee59 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:04 -0800 Subject: lib/bitmap.c: change parameters of bitmap_fold to unsigned Change the sz and nbits parameters of bitmap_fold to unsigned int for consistency with other bitmap_* functions, and to save another few bytes in the generated code. [akpm@linux-foundation.org: fix kerneldoc] Signed-off-by: Rasmus Villemoes Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index d0c6214eb190..95dcd2f76e1a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -166,7 +166,7 @@ extern int bitmap_bitremap(int oldbit, extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, - int sz, int bits); + unsigned int sz, unsigned int nbits); extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); -- cgit v1.2.3 From f6a1f5db8d7a7a94ff07251996959d27daba4ee7 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:10 -0800 Subject: lib/bitmap.c: simplify bitmap_ord_to_pos Make the return value and the ord and nbits parameters of bitmap_ord_to_pos unsigned. Also, simplify the implementation and as a side effect make the result fully defined, returning nbits for ord >= weight, in analogy with what find_{first,next}_bit does. This is a better sentinel than the former ("unofficial") 0. No current users are affected by this change. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 95dcd2f76e1a..1e74fe7aa167 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -171,7 +171,7 @@ extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); -extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); +extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); -- cgit v1.2.3 From 9814ec135dedb70a9daa41e68798d540d7ba71f2 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:13 -0800 Subject: lib/bitmap.c: make the bits parameter of bitmap_remap unsigned Also, rename bits to nbits. Both changes for consistency with other bitmap_* functions. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 1e74fe7aa167..5f5c00de39f0 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -160,7 +160,7 @@ extern int bitmap_parselist(const char *buf, unsigned long *maskp, extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern void bitmap_remap(unsigned long *dst, const unsigned long *src, - const unsigned long *old, const unsigned long *new, int bits); + const unsigned long *old, const unsigned long *new, unsigned int nbits); extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, -- cgit v1.2.3 From af3cd13501eb04ca61d017ff4406f1cbffafdc04 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:15 -0800 Subject: lib/string.c: remove strnicmp() Now that all in-tree users of strnicmp have been converted to strncasecmp, the wrapper can be removed. Signed-off-by: Rasmus Villemoes Cc: David Howells Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 2e22a2e58f3a..b9bc9a5d9e21 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -40,9 +40,6 @@ extern int strcmp(const char *,const char *); #ifndef __HAVE_ARCH_STRNCMP extern int strncmp(const char *,const char *,__kernel_size_t); #endif -#ifndef __HAVE_ARCH_STRNICMP -#define strnicmp strncasecmp -#endif #ifndef __HAVE_ARCH_STRCASECMP extern int strcasecmp(const char *s1, const char *s2); #endif -- cgit v1.2.3 From 114fc1afb2de7dec40da137dc2a55cd38fc220f2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 12 Feb 2015 15:02:29 -0800 Subject: hexdump: make it return number of bytes placed in buffer This patch makes hexdump return the number of bytes placed in the buffer excluding trailing NUL. In the case of overflow it returns the desired amount of bytes to produce the entire dump. Thus, it mimics snprintf(). This will be useful for users that would like to repeat with a bigger buffer. [akpm@linux-foundation.org: fix printk warning] Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 4d5bf5726578..baa3f97d8ce8 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -417,9 +417,9 @@ enum { DUMP_PREFIX_ADDRESS, DUMP_PREFIX_OFFSET }; -extern void hex_dump_to_buffer(const void *buf, size_t len, - int rowsize, int groupsize, - char *linebuf, size_t linebuflen, bool ascii); +extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, + int groupsize, char *linebuf, size_t linebuflen, + bool ascii); #ifdef CONFIG_PRINTK extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, -- cgit v1.2.3 From 3248340d3f10871d2ae2d1df9e323f284fa1fdb6 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:02:40 -0800 Subject: lib/halfmd4.c: simplify includes We only need EXPORT_SYMBOL, so compiler.h and export.h suffice. This means linux/types.h is no longer implicitly included, so add an include of uapi/linux/types.h to linux/cryptohash.h for __u32. Other users of cryptohash.h cannot be affected, since they must already have been including uapi/linux/types.h in order for gcc not to complain about unknown types. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cryptohash.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h index 2cd9f1cf9fa3..f4754282c9c2 100644 --- a/include/linux/cryptohash.h +++ b/include/linux/cryptohash.h @@ -1,6 +1,8 @@ #ifndef __CRYPTOHASH_H #define __CRYPTOHASH_H +#include + #define SHA_DIGEST_WORDS 5 #define SHA_MESSAGE_BYTES (512 /*bits*/ / 8) #define SHA_WORKSPACE_WORDS 16 -- cgit v1.2.3 From 3810631332465d967ba5e27ea2c7dff2c9afac6c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 12 Feb 2015 23:33:15 +0100 Subject: PM / sleep: Re-implement suspend-to-idle handling In preparation for adding support for quiescing timers in the final stage of suspend-to-idle transitions, rework the freeze_enter() function making the system wait on a wakeup event, the freeze_wake() function terminating the suspend-to-idle loop and the mechanism by which deep idle states are entered during suspend-to-idle. First of all, introduce a simple state machine for suspend-to-idle and make the code in question use it. Second, prevent freeze_enter() from losing wakeup events due to race conditions and ensure that the number of online CPUs won't change while it is being executed. In addition to that, make it force all of the CPUs re-enter the idle loop in case they are in idle states already (so they can enter deeper idle states if possible). Next, drop cpuidle_use_deepest_state() and replace use_deepest_state checks in cpuidle_select() and cpuidle_reflect() with a single suspend-to-idle state check in cpuidle_idle_call(). Finally, introduce cpuidle_enter_freeze() that will simply find the deepest idle state available to the given CPU and enter it using cpuidle_enter(). Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- include/linux/cpuidle.h | 4 ++-- include/linux/suspend.h | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index ab70f3bc44ad..f63aabf4ee90 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -141,7 +141,7 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); -extern void cpuidle_use_deepest_state(bool enable); +extern void cpuidle_enter_freeze(void); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else @@ -174,7 +174,7 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } -static inline void cpuidle_use_deepest_state(bool enable) {} +static inline void cpuidle_enter_freeze(void) { } static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } #endif diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 3388c1b6f7d8..5efe743ce1e8 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -201,6 +201,21 @@ struct platform_freeze_ops { */ extern void suspend_set_ops(const struct platform_suspend_ops *ops); extern int suspend_valid_only_mem(suspend_state_t state); + +/* Suspend-to-idle state machnine. */ +enum freeze_state { + FREEZE_STATE_NONE, /* Not suspended/suspending. */ + FREEZE_STATE_ENTER, /* Enter suspend-to-idle. */ + FREEZE_STATE_WAKE, /* Wake up from suspend-to-idle. */ +}; + +extern enum freeze_state __read_mostly suspend_freeze_state; + +static inline bool idle_should_freeze(void) +{ + return unlikely(suspend_freeze_state == FREEZE_STATE_ENTER); +} + extern void freeze_set_ops(const struct platform_freeze_ops *ops); extern void freeze_wake(void); @@ -228,6 +243,7 @@ extern int pm_suspend(suspend_state_t state); static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } +static inline bool idle_should_freeze(void) { return false; } static inline void freeze_set_ops(const struct platform_freeze_ops *ops) {} static inline void freeze_wake(void) {} #endif /* !CONFIG_SUSPEND */ -- cgit v1.2.3 From f4086a3d789dbe18949862276d83b8f49fce6d2f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 13 Feb 2015 21:03:16 -0500 Subject: NFS: struct nfs_commit_info.lock must always point to inode->i_lock Commit 411a99adffb4f (nfs: clear_request_commit while holding i_lock) assumes that the nfs_commit_info always points to the inode->i_lock. For historical reasons, that is not the case for O_DIRECT writes. Cc: Weston Andros Adamson Fixes: 411a99adffb4f ("nfs: clear_request_commit while holding i_lock") Cc: stable@vger.kernel.org # 3.17.x Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 38d96ba935c2..9a39132fda49 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1351,7 +1351,7 @@ struct nfs_commit_completion_ops { }; struct nfs_commit_info { - spinlock_t *lock; + spinlock_t *lock; /* inode->i_lock */ struct nfs_mds_commit_info *mds; struct pnfs_ds_commit_info *ds; struct nfs_direct_req *dreq; /* O_DIRECT request */ -- cgit v1.2.3 From bf40e5561fd288a505d5d8d8bf45eef96fe7253d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 13 Feb 2015 21:40:27 -0500 Subject: NFSv4: Kill unused nfs_inode->delegation_state field Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6d627b92df53..2f77e0c651c8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -180,7 +180,6 @@ struct nfs_inode { /* NFSv4 state */ struct list_head open_states; struct nfs_delegation __rcu *delegation; - fmode_t delegation_state; struct rw_semaphore rwsem; /* pNFS layout information */ -- cgit v1.2.3 From 9b6c2d2e2ba5280649eb043cbc7e3483c77e5d69 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 13 Feb 2015 14:35:57 -0800 Subject: lib/bitmap.c: change prototype of bitmap_copy_le Make the prototype of bitmap_copy_le the same as bitmap_copy's. All other bitmap_* functions take unsigned long* parameters; there's no reason this should be special. The only current user is the static inline uwb_mas_bm_copy_le, which already does the void* laundering, so the end users can pass their u8 or __le32 buffers without a cast. Furthermore, this allows us to simply let bitmap_copy_le be an alias for bitmap_copy on little-endian; see next patch. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5f5c00de39f0..334fe32d8f0e 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -170,7 +170,7 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); -extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); -- cgit v1.2.3 From e8f24278329dc31b3b8223c83a5465c9df153d9d Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 13 Feb 2015 14:36:00 -0800 Subject: lib/bitmap.c: elide bitmap_copy_le on little-endian On little-endian, there's no reason to have an extra, presumably less efficient, way of copying a bitmap. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 334fe32d8f0e..cffc89c23c02 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -170,7 +170,11 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); +#ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); +#else +#define bitmap_copy_le bitmap_copy +#endif extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); -- cgit v1.2.3 From 2fbad29917c9852fa018d572cd3d43a13465d0f8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 13 Feb 2015 14:36:02 -0800 Subject: lib: bitmap: change bitmap_shift_right to take unsigned parameters I've previously changed the nbits parameter of most bitmap_* functions to unsigned; now it is bitmap_shift_{left,right}'s turn. This alone saves some .text, but while at it I found that there were a few other things one could do. The end result of these seven patches is $ scripts/bloat-o-meter /tmp/bitmap.o.{old,new} add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-328 (-328) function old new delta __bitmap_shift_right 384 226 -158 __bitmap_shift_left 306 136 -170 and less importantly also a smaller stack footprint $ stack-o-meter.pl master bitmap file function old new delta lib/bitmap.o __bitmap_shift_right 24 8 -16 lib/bitmap.o __bitmap_shift_left 24 0 -24 For each pair of 0 <= shift <= nbits <= 256 I've tested the end result with a few randomly filled src buffers (including garbage beyond nbits), in each case verifying that the shift {left,right}-most bits of dst are zero and the remaining nbits-shift bits correspond to src, so I'm fairly confident I didn't screw up. That hasn't stopped me from being wrong before, though. This patch (of 7): gcc can generate slightly better code for stuff like "nbits % BITS_PER_LONG" when it knows nbits is not negative. Since negative size bitmaps or shift amounts don't make sense, change these parameters of bitmap_shift_right to unsigned. The expressions involving "lim - 1" are still ok, since if lim is 0 the loop is never executed. Also use "shift" and "nbits" consistently for the parameter names. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index cffc89c23c02..c168a807ab9a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -96,8 +96,8 @@ extern int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); -extern void __bitmap_shift_right(unsigned long *dst, - const unsigned long *src, int shift, int bits); +extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, int shift, int bits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, @@ -313,13 +313,13 @@ static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) return __bitmap_weight(src, nbits); } -static inline void bitmap_shift_right(unsigned long *dst, - const unsigned long *src, int n, int nbits) +static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, + unsigned int shift, int nbits) { if (small_const_nbits(nbits)) - *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> n; + *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; else - __bitmap_shift_right(dst, src, n, nbits); + __bitmap_shift_right(dst, src, shift, nbits); } static inline void bitmap_shift_left(unsigned long *dst, -- cgit v1.2.3 From dba94c2553da1928303c2a6c6410247c88cafc1d Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Fri, 13 Feb 2015 14:36:13 -0800 Subject: lib: bitmap: change bitmap_shift_left to take unsigned parameters gcc can generate slightly better code for stuff like "nbits % BITS_PER_LONG" when it knows nbits is not negative. Since negative size bitmaps or shift amounts don't make sense, change these parameters of bitmap_shift_right to unsigned. If off >= lim (which requires shift >= nbits), k is initialized with a large positive value, but since I've let k continue to be signed, the loop will never run and dst will be zeroed as expected. Inside the loop, k is guaranteed to be non-negative, so the fact that it is promoted to unsigned in the various expressions it appears in is harmless. Also use "shift" and "nbits" consistently for the parameter names. Signed-off-by: Rasmus Villemoes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index c168a807ab9a..5e7f75a6d7d0 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -98,8 +98,8 @@ extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); -extern void __bitmap_shift_left(unsigned long *dst, - const unsigned long *src, int shift, int bits); +extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, @@ -322,13 +322,13 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s __bitmap_shift_right(dst, src, shift, nbits); } -static inline void bitmap_shift_left(unsigned long *dst, - const unsigned long *src, int n, int nbits) +static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) - *dst = (*src << n) & BITMAP_LAST_WORD_MASK(nbits); + *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); else - __bitmap_shift_left(dst, src, n, nbits); + __bitmap_shift_left(dst, src, shift, nbits); } static inline int bitmap_parse(const char *buf, unsigned int buflen, -- cgit v1.2.3 From a4bb1e43e22d3cade8f942fc6f95920248eb2fd0 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Fri, 13 Feb 2015 14:36:24 -0800 Subject: mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda Cc: Marek Szyprowski Cc: Kyungmin Park Cc: Mike Turquette Cc: Alexander Viro Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Tejun Heo Cc: Greg KH Cc: Geert Uytterhoeven Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index b9bc9a5d9e21..e40099e585c9 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -112,7 +112,10 @@ extern void * memchr(const void *,int,__kernel_size_t); #endif void *memchr_inv(const void *s, int c, size_t n); +extern void kfree_const(const void *x); + extern char *kstrdup(const char *s, gfp_t gfp); +extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); -- cgit v1.2.3 From dfeb0750b630b72b5d4fb2461bc7179eceb54666 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:36:31 -0800 Subject: kernfs: remove KERNFS_STATIC_NAME When a new kernfs node is created, KERNFS_STATIC_NAME is used to avoid making a separate copy of its name. It's currently only used for sysfs attributes whose filenames are required to stay accessible and unchanged. There are rare exceptions where these names are allocated and formatted dynamically but for the vast majority of cases they're consts in the rodata section. Now that kernfs is converted to use kstrdup_const() and kfree_const(), there's little point in keeping KERNFS_STATIC_NAME around. Remove it. Signed-off-by: Tejun Heo Cc: Andrzej Hajda Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernfs.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index d4e01b358341..71ecdab1671b 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -43,7 +43,6 @@ enum kernfs_node_flag { KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, - KERNFS_STATIC_NAME = 0x0200, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, }; @@ -291,7 +290,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, umode_t mode, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, - bool name_is_static, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, @@ -369,8 +367,7 @@ kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, const struct kernfs_ops *ops, - void *priv, const void *ns, bool name_is_static, - struct lock_class_key *key) + void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * @@ -439,7 +436,7 @@ kernfs_create_file_ns(struct kernfs_node *parent, const char *name, key = (struct lock_class_key *)&ops->lockdep_key; #endif return __kernfs_create_file(parent, name, mode, size, ops, priv, ns, - false, key); + key); } static inline struct kernfs_node * -- cgit v1.2.3 From 513e3d2d11c9f05db1edc70deb18a82555cf9309 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:36:50 -0800 Subject: cpumask: always use nr_cpu_ids in formatting and parsing functions bitmap implements two variants of scnprintf functions to format a bitmap into a string and cpumask and nodemask wrap them to provide equivalent interfaces. The scnprintf family of functions require a string buffer as an output target which complicates code paths which just want to print out the mask through printk for informational or debug purposes as they have to worry about how large the buffer should be and whether it's too large to allocate on stack. Neither cpumask or nodemask provides a guildeline on how large the target buffer should be forcing users come up with their own solutions - some allocate an arbitrarily sized buffer which is small enough to allocate on stack but may be too short in corner cases, other come up with a custom upper limit calculation considering the output format, some allocate the buffer dynamically while one resorted to using lock to synchronize access to a static buffer. This is an artificial problem which is being solved repeatedly for no benefit. In a lot of cases, the output area already exists and can be targeted directly making the intermediate buffer unnecessary. This patchset teaches printf family of functions how to format bitmaps and replace the dedicated formatting functions with it. Pointer formatting is extended to cover bitmap formatting. It uses the field width for the number of bits instead of precision. The format used is '%*pb[l]', with the optional trailing 'l' specifying list format instead of hex masks. For more details, please see 0002. This patch (of 31): Currently, the formatting and parsing functions in cpumask.h use nr_cpumask_bits like other cpumask functions; however, nr_cpumask_bits is either NR_CPUS or nr_cpu_ids depending on CONFIG_CPUMASK_OFFSTACK. This leads to inconsistent behaviors. With CONFIG_NR_CPUS=512 and !CONFIG_CPUMASK_OFFSTACK # cat /sys/devices/virtual/net/lo/queues/rx-0/rps_cpus 00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000 # cat /proc/self/status | grep Cpus_allowed: Cpus_allowed: f With CONFIG_NR_CPUS=1024 and CONFIG_CPUMASK_OFFSTACK (fedora default) # cat /sys/devices/virtual/net/lo/queues/rx-0/rps_cpus 0 # cat /proc/self/status | grep Cpus_allowed: Cpus_allowed: f Note that /proc/self/status is always using nr_cpu_ids regardless of config. This is because seq cpumask formattings functions always use nr_cpu_ids. Given that the same output fields may switch between the two forms, converging on nr_cpu_ids always isn't too likely to surprise userland. This patch updates the formatting and parsing functions in cpumask.h to always use nr_cpu_ids. There's no point in dealing with CPUs which aren't even possible on the machine. Signed-off-by: Tejun Heo Cc: "David S. Miller" Cc: "James E.J. Bottomley" Cc: "John W. Linville" Cc: "Paul E. McKenney" Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Chris Zankel Cc: Christoph Lameter Cc: Dmitry Torokhov Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Li Zefan Cc: Max Filippov Cc: Mike Travis Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Russell King Acked-by: Rusty Russell Cc: Steffen Klassert Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ff9044286d88..ee9acb0ce542 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -550,7 +550,7 @@ static inline void cpumask_copy(struct cpumask *dstp, static inline int cpumask_scnprintf(char *buf, int len, const struct cpumask *srcp) { - return bitmap_scnprintf(buf, len, cpumask_bits(srcp), nr_cpumask_bits); + return bitmap_scnprintf(buf, len, cpumask_bits(srcp), nr_cpu_ids); } /** @@ -564,7 +564,7 @@ static inline int cpumask_scnprintf(char *buf, int len, static inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { - return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); + return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids); } /** @@ -579,7 +579,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), - nr_cpumask_bits); + nr_cpu_ids); } /** @@ -595,7 +595,7 @@ static inline int cpulist_scnprintf(char *buf, int len, const struct cpumask *srcp) { return bitmap_scnlistprintf(buf, len, cpumask_bits(srcp), - nr_cpumask_bits); + nr_cpu_ids); } /** @@ -610,7 +610,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) char *nl = strchr(buf, '\n'); unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf); - return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); + return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids); } /** @@ -622,7 +622,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) */ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) { - return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); + return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids); } /** @@ -817,7 +817,7 @@ static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), - nr_cpumask_bits); + nr_cpu_ids); } /* -- cgit v1.2.3 From f1bbc032e45106400905ebb47550983af4690b0b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:36:57 -0800 Subject: cpumask, nodemask: implement cpumask/nodemask_pr_args() printf family of functions can now format bitmaps using '%*pb[l]' and all cpumask and nodemask formatting will be converted to use it. To ease printing these masks with '%*pb[l]' which require two params - the number of bits and the actual bitmap, this patch implement cpumask_pr_args() and nodemask_pr_args() which can be used to provide arguments for '%*pb[l]' Signed-off-by: Tejun Heo Cc: Rusty Russell Cc: "David S. Miller" Cc: "James E.J. Bottomley" Cc: "John W. Linville" Cc: "Paul E. McKenney" Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Chris Zankel Cc: Christoph Lameter Cc: Dmitry Torokhov Cc: Fenghua Yu Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Li Zefan Cc: Max Filippov Cc: Mike Travis Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Russell King Cc: Steffen Klassert Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 8 ++++++++ include/linux/nodemask.h | 8 ++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ee9acb0ce542..a9b3d00915a0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -22,6 +22,14 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; */ #define cpumask_bits(maskp) ((maskp)->bits) +/** + * cpumask_pr_args - printf args to output a cpumask + * @maskp: cpumask to be printed + * + * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. + */ +#define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) + #if NR_CPUS == 1 #define nr_cpu_ids 1 #else diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 21cef483dc1b..10f8e556ba07 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -98,6 +98,14 @@ typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; +/** + * nodemask_pr_args - printf args to output a nodemask + * @maskp: nodemask to be printed + * + * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. + */ +#define nodemask_pr_args(maskp) MAX_NUMNODES, (maskp)->bits + /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions -- cgit v1.2.3 From 46385326cc1577587ed3e7432c2425cf6d3e4308 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 13 Feb 2015 14:38:15 -0800 Subject: bitmap, cpumask, nodemask: remove dedicated formatting functions Now that all bitmap formatting usages have been converted to '%*pb[l]', the separate formatting functions are unnecessary. The following functions are removed. * bitmap_scn[list]printf() * cpumask_scnprintf(), cpulist_scnprintf() * [__]nodemask_scnprintf(), [__]nodelist_scnprintf() * seq_bitmap[_list](), seq_cpumask[_list](), seq_nodemask[_list]() * seq_buf_bitmask() Signed-off-by: Tejun Heo Cc: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 ------- include/linux/cpumask.h | 31 ------------------------------- include/linux/nodemask.h | 33 +++++++-------------------------- include/linux/seq_buf.h | 3 --- include/linux/seq_file.h | 25 ------------------------- 5 files changed, 7 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5e7f75a6d7d0..dbfbf4990005 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -52,16 +52,13 @@ * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz - * bitmap_scnprintf(buf, len, src, nbits) Print bitmap src to buf * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf - * bitmap_scnlistprintf(buf, len, src, nbits) Print bitmap src as list to buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region - * bitmap_print_to_pagebuf(list, buf, mask, nbits) Print bitmap src as list/hex */ /* @@ -147,14 +144,10 @@ bitmap_find_next_zero_area(unsigned long *map, align_mask, 0); } -extern int bitmap_scnprintf(char *buf, unsigned int len, - const unsigned long *src, int nbits); extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); -extern int bitmap_scnlistprintf(char *buf, unsigned int len, - const unsigned long *src, int nbits); extern int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index a9b3d00915a0..086549a665e2 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -546,21 +546,6 @@ static inline void cpumask_copy(struct cpumask *dstp, */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) -/** - * cpumask_scnprintf - print a cpumask into a string as comma-separated hex - * @buf: the buffer to sprintf into - * @len: the length of the buffer - * @srcp: the cpumask to print - * - * If len is zero, returns zero. Otherwise returns the length of the - * (nul-terminated) @buf string. - */ -static inline int cpumask_scnprintf(char *buf, int len, - const struct cpumask *srcp) -{ - return bitmap_scnprintf(buf, len, cpumask_bits(srcp), nr_cpu_ids); -} - /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from @@ -590,22 +575,6 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, nr_cpu_ids); } -/** - * cpulist_scnprintf - print a cpumask into a string as comma-separated list - * @buf: the buffer to sprintf into - * @len: the length of the buffer - * @srcp: the cpumask to print - * - * If len is zero, returns zero. Otherwise returns the length of the - * (nul-terminated) @buf string. - */ -static inline int cpulist_scnprintf(char *buf, int len, - const struct cpumask *srcp) -{ - return bitmap_scnlistprintf(buf, len, cpumask_bits(srcp), - nr_cpu_ids); -} - /** * cpumask_parse - extract a cpumask from from a string * @buf: the buffer to extract from diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 10f8e556ba07..6e85889cf9ab 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -8,14 +8,13 @@ * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * - * For details of nodemask_scnprintf() and nodemask_parse_user(), - * see bitmap_scnprintf() and bitmap_parse_user() in lib/bitmap.c. - * For details of nodelist_scnprintf() and nodelist_parse(), see - * bitmap_scnlistprintf() and bitmap_parselist(), also in bitmap.c. - * For details of node_remap(), see bitmap_bitremap in lib/bitmap.c. - * For details of nodes_remap(), see bitmap_remap in lib/bitmap.c. - * For details of nodes_onto(), see bitmap_onto in lib/bitmap.c. - * For details of nodes_fold(), see bitmap_fold in lib/bitmap.c. + * For details of nodemask_parse_user(), see bitmap_parse_user() in + * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), + * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in + * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in + * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in + * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in + * lib/bitmap.c. * * The available nodemask operations are: * @@ -52,9 +51,7 @@ * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * - * int nodemask_scnprintf(buf, len, mask) Format nodemask for printing * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask - * int nodelist_scnprintf(buf, len, mask) Format nodemask as list for printing * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) @@ -312,14 +309,6 @@ static inline int __first_unset_node(const nodemask_t *maskp) #define nodes_addr(src) ((src).bits) -#define nodemask_scnprintf(buf, len, src) \ - __nodemask_scnprintf((buf), (len), &(src), MAX_NUMNODES) -static inline int __nodemask_scnprintf(char *buf, int len, - const nodemask_t *srcp, int nbits) -{ - return bitmap_scnprintf(buf, len, srcp->bits, nbits); -} - #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static inline int __nodemask_parse_user(const char __user *buf, int len, @@ -328,14 +317,6 @@ static inline int __nodemask_parse_user(const char __user *buf, int len, return bitmap_parse_user(buf, len, dstp->bits, nbits); } -#define nodelist_scnprintf(buf, len, src) \ - __nodelist_scnprintf((buf), (len), &(src), MAX_NUMNODES) -static inline int __nodelist_scnprintf(char *buf, int len, - const nodemask_t *srcp, int nbits) -{ - return bitmap_scnlistprintf(buf, len, srcp->bits, nbits); -} - #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 9aafe0e24c68..fb7eb9ccb1cd 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -125,9 +125,6 @@ extern int seq_buf_putmem_hex(struct seq_buf *s, const void *mem, unsigned int len); extern int seq_buf_path(struct seq_buf *s, const struct path *path, const char *esc); -extern int seq_buf_bitmask(struct seq_buf *s, const unsigned long *maskp, - int nmaskbits); - #ifdef CONFIG_BINARY_PRINTF extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index cf6a9daaaf6d..afbb1fd77c77 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -126,31 +126,6 @@ int seq_path(struct seq_file *, const struct path *, const char *); int seq_dentry(struct seq_file *, struct dentry *, const char *); int seq_path_root(struct seq_file *m, const struct path *path, const struct path *root, const char *esc); -int seq_bitmap(struct seq_file *m, const unsigned long *bits, - unsigned int nr_bits); -static inline int seq_cpumask(struct seq_file *m, const struct cpumask *mask) -{ - return seq_bitmap(m, cpumask_bits(mask), nr_cpu_ids); -} - -static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask) -{ - return seq_bitmap(m, mask->bits, MAX_NUMNODES); -} - -int seq_bitmap_list(struct seq_file *m, const unsigned long *bits, - unsigned int nr_bits); - -static inline int seq_cpumask_list(struct seq_file *m, - const struct cpumask *mask) -{ - return seq_bitmap_list(m, cpumask_bits(mask), nr_cpu_ids); -} - -static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask) -{ - return seq_bitmap_list(m, mask->bits, MAX_NUMNODES); -} int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_open_size(struct file *, int (*)(struct seq_file *, void *), void *, size_t); -- cgit v1.2.3 From cb4188ac8e5779f66b9f55888ac2c75b391cde44 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:14 -0800 Subject: compiler: introduce __alias(symbol) shortcut To be consistent with other compiler attributes introduce __alias(symbol) macro expanding into __attribute__((alias(#symbol))) Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 02ae99e8e6d3..cdf13ca7cac3 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -66,6 +66,7 @@ #define __deprecated __attribute__((deprecated)) #define __packed __attribute__((packed)) #define __weak __attribute__((weak)) +#define __alias(symbol) __attribute__((alias(#symbol))) /* * it doesn't make sense on ARM (currently the only user of __naked) to trace -- cgit v1.2.3 From 0b24becc810dc3be6e3f94103a866f214c282394 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:17 -0800 Subject: kasan: add kernel address sanitizer infrastructure Kernel Address sanitizer (KASan) is a dynamic memory error detector. It provides fast and comprehensive solution for finding use-after-free and out-of-bounds bugs. KASAN uses compile-time instrumentation for checking every memory access, therefore GCC > v4.9.2 required. v4.9.2 almost works, but has issues with putting symbol aliases into the wrong section, which breaks kasan instrumentation of globals. This patch only adds infrastructure for kernel address sanitizer. It's not available for use yet. The idea and some code was borrowed from [1]. Basic idea: The main idea of KASAN is to use shadow memory to record whether each byte of memory is safe to access or not, and use compiler's instrumentation to check the shadow memory on each memory access. Address sanitizer uses 1/8 of the memory addressable in kernel for shadow memory and uses direct mapping with a scale and offset to translate a memory address to its corresponding shadow address. Here is function to translate address to corresponding shadow address: unsigned long kasan_mem_to_shadow(unsigned long addr) { return (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET; } where KASAN_SHADOW_SCALE_SHIFT = 3. So for every 8 bytes there is one corresponding byte of shadow memory. The following encoding used for each shadow byte: 0 means that all 8 bytes of the corresponding memory region are valid for access; k (1 <= k <= 7) means that the first k bytes are valid for access, and other (8 - k) bytes are not; Any negative value indicates that the entire 8-bytes are inaccessible. Different negative values used to distinguish between different kinds of inaccessible memory (redzones, freed memory) (see mm/kasan/kasan.h). To be able to detect accesses to bad memory we need a special compiler. Such compiler inserts a specific function calls (__asan_load*(addr), __asan_store*(addr)) before each memory access of size 1, 2, 4, 8 or 16. These functions check whether memory region is valid to access or not by checking corresponding shadow memory. If access is not valid an error printed. Historical background of the address sanitizer from Dmitry Vyukov: "We've developed the set of tools, AddressSanitizer (Asan), ThreadSanitizer and MemorySanitizer, for user space. We actively use them for testing inside of Google (continuous testing, fuzzing, running prod services). To date the tools have found more than 10'000 scary bugs in Chromium, Google internal codebase and various open-source projects (Firefox, OpenSSL, gcc, clang, ffmpeg, MySQL and lots of others): [2] [3] [4]. The tools are part of both gcc and clang compilers. We have not yet done massive testing under the Kernel AddressSanitizer (it's kind of chicken and egg problem, you need it to be upstream to start applying it extensively). To date it has found about 50 bugs. Bugs that we've found in upstream kernel are listed in [5]. We've also found ~20 bugs in out internal version of the kernel. Also people from Samsung and Oracle have found some. [...] As others noted, the main feature of AddressSanitizer is its performance due to inline compiler instrumentation and simple linear shadow memory. User-space Asan has ~2x slowdown on computational programs and ~2x memory consumption increase. Taking into account that kernel usually consumes only small fraction of CPU and memory when running real user-space programs, I would expect that kernel Asan will have ~10-30% slowdown and similar memory consumption increase (when we finish all tuning). I agree that Asan can well replace kmemcheck. We have plans to start working on Kernel MemorySanitizer that finds uses of unitialized memory. Asan+Msan will provide feature-parity with kmemcheck. As others noted, Asan will unlikely replace debug slab and pagealloc that can be enabled at runtime. Asan uses compiler instrumentation, so even if it is disabled, it still incurs visible overheads. Asan technology is easily portable to other architectures. Compiler instrumentation is fully portable. Runtime has some arch-dependent parts like shadow mapping and atomic operation interception. They are relatively easy to port." Comparison with other debugging features: ======================================== KMEMCHECK: - KASan can do almost everything that kmemcheck can. KASan uses compile-time instrumentation, which makes it significantly faster than kmemcheck. The only advantage of kmemcheck over KASan is detection of uninitialized memory reads. Some brief performance testing showed that kasan could be x500-x600 times faster than kmemcheck: $ netperf -l 30 MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to localhost (127.0.0.1) port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec no debug: 87380 16384 16384 30.00 41624.72 kasan inline: 87380 16384 16384 30.00 12870.54 kasan outline: 87380 16384 16384 30.00 10586.39 kmemcheck: 87380 16384 16384 30.03 20.23 - Also kmemcheck couldn't work on several CPUs. It always sets number of CPUs to 1. KASan doesn't have such limitation. DEBUG_PAGEALLOC: - KASan is slower than DEBUG_PAGEALLOC, but KASan works on sub-page granularity level, so it able to find more bugs. SLUB_DEBUG (poisoning, redzones): - SLUB_DEBUG has lower overhead than KASan. - SLUB_DEBUG in most cases are not able to detect bad reads, KASan able to detect both reads and writes. - In some cases (e.g. redzone overwritten) SLUB_DEBUG detect bugs only on allocation/freeing of object. KASan catch bugs right before it will happen, so we always know exact place of first bad read/write. [1] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel [2] https://code.google.com/p/address-sanitizer/wiki/FoundBugs [3] https://code.google.com/p/thread-sanitizer/wiki/FoundBugs [4] https://code.google.com/p/memory-sanitizer/wiki/FoundBugs [5] https://code.google.com/p/address-sanitizer/wiki/AddressSanitizerForKernel#Trophies Based on work by Andrey Konovalov. Signed-off-by: Andrey Ryabinin Acked-by: Michal Marek Signed-off-by: Andrey Konovalov Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 3 +++ 2 files changed, 49 insertions(+) create mode 100644 include/linux/kasan.h (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h new file mode 100644 index 000000000000..9102fda60def --- /dev/null +++ b/include/linux/kasan.h @@ -0,0 +1,46 @@ +#ifndef _LINUX_KASAN_H +#define _LINUX_KASAN_H + +#include + +struct kmem_cache; +struct page; + +#ifdef CONFIG_KASAN + +#define KASAN_SHADOW_SCALE_SHIFT 3 +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) + +#include +#include + +static inline void *kasan_mem_to_shadow(const void *addr) +{ + return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT) + + KASAN_SHADOW_OFFSET; +} + +/* Enable reporting bugs after kasan_disable_current() */ +static inline void kasan_enable_current(void) +{ + current->kasan_depth++; +} + +/* Disable reporting bugs for current task */ +static inline void kasan_disable_current(void) +{ + current->kasan_depth--; +} + +void kasan_unpoison_shadow(const void *address, size_t size); + +#else /* CONFIG_KASAN */ + +static inline void kasan_unpoison_shadow(const void *address, size_t size) {} + +static inline void kasan_enable_current(void) {} +static inline void kasan_disable_current(void) {} + +#endif /* CONFIG_KASAN */ + +#endif /* LINUX_KASAN_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 048b91b983ed..41c60e5302d7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1664,6 +1664,9 @@ struct task_struct { unsigned long timer_slack_ns; unsigned long default_timer_slack_ns; +#ifdef CONFIG_KASAN + unsigned int kasan_depth; +#endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack */ int curr_ret_stack; -- cgit v1.2.3 From b8c73fc2493d42517be95cf2c89659fc6c6f4d02 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:28 -0800 Subject: mm: page_alloc: add kasan hooks on alloc and free paths Add kernel address sanitizer hooks to mark allocated page's addresses as accessible in corresponding shadow region. Mark freed pages as inaccessible. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 9102fda60def..f00c15c41235 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -34,6 +34,9 @@ static inline void kasan_disable_current(void) void kasan_unpoison_shadow(const void *address, size_t size); +void kasan_alloc_pages(struct page *page, unsigned int order); +void kasan_free_pages(struct page *page, unsigned int order); + #else /* CONFIG_KASAN */ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} @@ -41,6 +44,9 @@ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} static inline void kasan_enable_current(void) {} static inline void kasan_disable_current(void) {} +static inline void kasan_alloc_pages(struct page *page, unsigned int order) {} +static inline void kasan_free_pages(struct page *page, unsigned int order) {} + #endif /* CONFIG_KASAN */ #endif /* LINUX_KASAN_H */ -- cgit v1.2.3 From 912f5fbf1d3060f25d6994aed0265c55b974b2e9 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:31 -0800 Subject: mm: slub: introduce virt_to_obj function virt_to_obj takes kmem_cache address, address of slab page, address x pointing somewhere inside slab object, and returns address of the beginning of object. Signed-off-by: Andrey Ryabinin Acked-by: Christoph Lameter Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 9abf04ed0999..db7d5de00c5f 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -110,4 +110,20 @@ static inline void sysfs_slab_remove(struct kmem_cache *s) } #endif + +/** + * virt_to_obj - returns address of the beginning of object. + * @s: object's kmem_cache + * @slab_page: address of slab page + * @x: address within object memory range + * + * Returns address of the beginning of object + */ +static inline void *virt_to_obj(struct kmem_cache *s, + const void *slab_page, + const void *x) +{ + return (void *)x - ((x - slab_page) % s->size); +} + #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 75c66def8d815201aa0386ecc7c66a5c8dbca1ee Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:35 -0800 Subject: mm: slub: share object_err function Remove static and add function declarations to linux/slub_def.h so it could be used by kernel address sanitizer. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index db7d5de00c5f..33885118523c 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -126,4 +126,7 @@ static inline void *virt_to_obj(struct kmem_cache *s, return (void *)x - ((x - slab_page) % s->size); } +void object_err(struct kmem_cache *s, struct page *page, + u8 *object, char *reason); + #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 0316bec22ec95ea2faca6406437b0b5950553b7c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:42 -0800 Subject: mm: slub: add kernel address sanitizer support for slub allocator With this patch kasan will be able to catch bugs in memory allocated by slub. Initially all objects in newly allocated slab page, marked as redzone. Later, when allocation of slub object happens, requested by caller number of bytes marked as accessible, and the rest of the object (including slub's metadata) marked as redzone (inaccessible). We also mark object as accessible if ksize was called for this object. There is some places in kernel where ksize function is called to inquire size of really allocated area. Such callers could validly access whole allocated memory, so it should be marked as accessible. Code in slub.c and slab_common.c files could validly access to object's metadata, so instrumentation for this files are disabled. Signed-off-by: Andrey Ryabinin Signed-off-by: Dmitry Chernenkov Cc: Dmitry Vyukov Cc: Konstantin Serebryany Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 27 +++++++++++++++++++++++++++ include/linux/slab.h | 11 +++++++++-- 2 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index f00c15c41235..d5310eef3e38 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -37,6 +37,18 @@ void kasan_unpoison_shadow(const void *address, size_t size); void kasan_alloc_pages(struct page *page, unsigned int order); void kasan_free_pages(struct page *page, unsigned int order); +void kasan_poison_slab(struct page *page); +void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); +void kasan_poison_object_data(struct kmem_cache *cache, void *object); + +void kasan_kmalloc_large(const void *ptr, size_t size); +void kasan_kfree_large(const void *ptr); +void kasan_kmalloc(struct kmem_cache *s, const void *object, size_t size); +void kasan_krealloc(const void *object, size_t new_size); + +void kasan_slab_alloc(struct kmem_cache *s, void *object); +void kasan_slab_free(struct kmem_cache *s, void *object); + #else /* CONFIG_KASAN */ static inline void kasan_unpoison_shadow(const void *address, size_t size) {} @@ -47,6 +59,21 @@ static inline void kasan_disable_current(void) {} static inline void kasan_alloc_pages(struct page *page, unsigned int order) {} static inline void kasan_free_pages(struct page *page, unsigned int order) {} +static inline void kasan_poison_slab(struct page *page) {} +static inline void kasan_unpoison_object_data(struct kmem_cache *cache, + void *object) {} +static inline void kasan_poison_object_data(struct kmem_cache *cache, + void *object) {} + +static inline void kasan_kmalloc_large(void *ptr, size_t size) {} +static inline void kasan_kfree_large(const void *ptr) {} +static inline void kasan_kmalloc(struct kmem_cache *s, const void *object, + size_t size) {} +static inline void kasan_krealloc(const void *object, size_t new_size) {} + +static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {} +static inline void kasan_slab_free(struct kmem_cache *s, void *object) {} + #endif /* CONFIG_KASAN */ #endif /* LINUX_KASAN_H */ diff --git a/include/linux/slab.h b/include/linux/slab.h index ed2ffaab59ea..76f1feeabd38 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -104,6 +104,7 @@ (unsigned long)ZERO_SIZE_PTR) #include +#include struct mem_cgroup; /* @@ -325,7 +326,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { - return kmem_cache_alloc(s, flags); + void *ret = kmem_cache_alloc(s, flags); + + kasan_kmalloc(s, ret, size); + return ret; } static __always_inline void * @@ -333,7 +337,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { - return kmem_cache_alloc_node(s, gfpflags, node); + void *ret = kmem_cache_alloc_node(s, gfpflags, node); + + kasan_kmalloc(s, ret, size); + return ret; } #endif /* CONFIG_TRACING */ -- cgit v1.2.3 From c420f167db8c799d69fe43a801c58a7f02e9d57c Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:39:59 -0800 Subject: kasan: enable stack instrumentation Stack instrumentation allows to detect out of bounds memory accesses for variables allocated on stack. Compiler adds redzones around every variable on stack and poisons redzones in function's prologue. Such approach significantly increases stack usage, so all in-kernel stacks size were doubled. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d3d43ecf148c..696d22312b31 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -175,6 +175,13 @@ extern struct task_group root_task_group; # define INIT_NUMA_BALANCING(tsk) #endif +#ifdef CONFIG_KASAN +# define INIT_KASAN(tsk) \ + .kasan_depth = 1, +#else +# define INIT_KASAN(tsk) +#endif + /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -250,6 +257,7 @@ extern struct task_group root_task_group; INIT_RT_MUTEXES(tsk) \ INIT_VTIME(tsk) \ INIT_NUMA_BALANCING(tsk) \ + INIT_KASAN(tsk) \ } -- cgit v1.2.3 From 71394fe50146202f2c8d92cf50f5ebc761acf254 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:40:03 -0800 Subject: mm: vmalloc: add flag preventing guard hole allocation For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Add a new vm_struct flag 'VM_NO_GUARD' indicating that vm area doesn't have a guard hole. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index b87696fdf06a..1526fe712ca0 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -16,6 +16,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ +#define VM_NO_GUARD 0x00000040 /* don't add guard page */ /* bits [20..32] reserved for arch specific ioremap internals */ /* @@ -96,8 +97,12 @@ void vmalloc_sync_all(void); static inline size_t get_vm_area_size(const struct vm_struct *area) { - /* return actual size without guard page */ - return area->size - PAGE_SIZE; + if (!(area->flags & VM_NO_GUARD)) + /* return actual size without guard page */ + return area->size - PAGE_SIZE; + else + return area->size; + } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); -- cgit v1.2.3 From cb9e3c292d0115499c660028ad35ac5501d722b5 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:40:07 -0800 Subject: mm: vmalloc: pass additional vm_flags to __vmalloc_node_range() For instrumenting global variables KASan will shadow memory backing memory for modules. So on module loading we will need to allocate memory for shadow and map it at address in shadow that corresponds to the address allocated in module_alloc(). __vmalloc_node_range() could be used for this purpose, except it puts a guard hole after allocated area. Guard hole in shadow memory should be a problem because at some future point we might need to have a shadow memory at address occupied by guard hole. So we could fail to allocate shadow for module_alloc(). Now we have VM_NO_GUARD flag disabling guard page, so we need to pass into __vmalloc_node_range(). Add new parameter 'vm_flags' to __vmalloc_node_range() function. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1526fe712ca0..7d7acb35603d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -76,7 +76,9 @@ extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, - pgprot_t prot, int node, const void *caller); + pgprot_t prot, unsigned long vm_flags, int node, + const void *caller); + extern void vfree(const void *addr); extern void *vmap(struct page **pages, unsigned int count, -- cgit v1.2.3 From 6301939d97d079f0d3dbe71e750f4daf5d39fc33 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:40:13 -0800 Subject: module: fix types of device tables aliases MODULE_DEVICE_TABLE() macro used to create aliases to device tables. Normally alias should have the same type as aliased symbol. Device tables are arrays, so they have 'struct type##_device_id[x]' types. Alias created by MODULE_DEVICE_TABLE() will have non-array type - 'struct type##_device_id'. This inconsistency confuses compiler, it could make a wrong assumption about variable's size which leads KASan to produce a false positive report about out of bounds access. For every global variable compiler calls __asan_register_globals() passing information about global variable (address, size, size with redzone, name ...) __asan_register_globals() poison symbols redzone to detect possible out of bounds accesses. When symbol has an alias __asan_register_globals() will be called as for symbol so for alias. Compiler determines size of variable by size of variable's type. Alias and symbol have the same address, so if alias have the wrong size part of memory that actually belongs to the symbol could be poisoned as redzone of alias symbol. By fixing type of alias symbol we will fix size of it, so __asan_register_globals() will not poison valid memory. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index b653d7c0a05a..42999fe2dbd0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -135,7 +135,7 @@ void trim_init_extable(struct module *m); #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ - extern const struct type##_device_id __mod_##type##__##name##_device_table \ +extern const typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) -- cgit v1.2.3 From bebf56a1b176c2e1c9efe44e7e6915532cc682cf Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 13 Feb 2015 14:40:17 -0800 Subject: kasan: enable instrumentation of global variables This feature let us to detect accesses out of bounds of global variables. This will work as for globals in kernel image, so for globals in modules. Currently this won't work for symbols in user-specified sections (e.g. __init, __read_mostly, ...) The idea of this is simple. Compiler increases each global variable by redzone size and add constructors invoking __asan_register_globals() function. Information about global variable (address, size, size with redzone ...) passed to __asan_register_globals() so we could poison variable's redzone. This patch also forces module_alloc() to return 8*PAGE_SIZE aligned address making shadow memory handling ( kasan_module_alloc()/kasan_module_free() ) more simple. Such alignment guarantees that each shadow page backing modules address space correspond to only one module_alloc() allocation. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Konstantin Serebryany Cc: Dmitry Chernenkov Signed-off-by: Andrey Konovalov Cc: Yuri Gribov Cc: Konstantin Khlebnikov Cc: Sasha Levin Cc: Christoph Lameter Cc: Joonsoo Kim Cc: Dave Hansen Cc: Andi Kleen Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc4.h | 4 ++++ include/linux/compiler-gcc5.h | 2 ++ include/linux/kasan.h | 10 ++++++++++ 3 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index d1a558239b1a..769e19864632 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -85,3 +85,7 @@ #define __HAVE_BUILTIN_BSWAP16__ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#if GCC_VERSION >= 40902 +#define KASAN_ABI_VERSION 3 +#endif diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h index c8c565952548..efee493714eb 100644 --- a/include/linux/compiler-gcc5.h +++ b/include/linux/compiler-gcc5.h @@ -63,3 +63,5 @@ #define __HAVE_BUILTIN_BSWAP64__ #define __HAVE_BUILTIN_BSWAP16__ #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ + +#define KASAN_ABI_VERSION 4 diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d5310eef3e38..72ba725ddf9c 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -49,8 +49,15 @@ void kasan_krealloc(const void *object, size_t new_size); void kasan_slab_alloc(struct kmem_cache *s, void *object); void kasan_slab_free(struct kmem_cache *s, void *object); +#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) + +int kasan_module_alloc(void *addr, size_t size); +void kasan_module_free(void *addr); + #else /* CONFIG_KASAN */ +#define MODULE_ALIGN 1 + static inline void kasan_unpoison_shadow(const void *address, size_t size) {} static inline void kasan_enable_current(void) {} @@ -74,6 +81,9 @@ static inline void kasan_krealloc(const void *object, size_t new_size) {} static inline void kasan_slab_alloc(struct kmem_cache *s, void *object) {} static inline void kasan_slab_free(struct kmem_cache *s, void *object) {} +static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline void kasan_module_free(void *addr) {} + #endif /* CONFIG_KASAN */ #endif /* LINUX_KASAN_H */ -- cgit v1.2.3 From d347efeb16d3d5150cb7f8d50b05f388b572840e Mon Sep 17 00:00:00 2001 From: Adrien Schildknecht Date: Thu, 12 Feb 2015 14:01:37 +0100 Subject: mutex: remove unused field "name" in debug mode This field is unused and uninitialized since commit 9a11b49a8056 ("[PATCH] lockdep: better lock debugging") Signed-off-by: Adrien Schildknecht Signed-off-by: Linus Torvalds --- include/linux/mutex.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index cc31498fc526..2cb7531e7d7a 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -59,7 +59,6 @@ struct mutex { struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_MUTEXES - const char *name; void *magic; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC -- cgit v1.2.3 From 124cf9117c5f93cc5b324530b7e105b09c729d5d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 13 Feb 2015 23:50:43 +0100 Subject: PM / sleep: Make it possible to quiesce timers during suspend-to-idle The efficiency of suspend-to-idle depends on being able to keep CPUs in the deepest available idle states for as much time as possible. Ideally, they should only be brought out of idle by system wakeup interrupts. However, timer interrupts occurring periodically prevent that from happening and it is not practical to chase all of the "misbehaving" timers in a whack-a-mole fashion. A much more effective approach is to suspend the local ticks for all CPUs and the entire timekeeping along the lines of what is done during full suspend, which also helps to keep suspend-to-idle and full suspend reasonably similar. The idea is to suspend the local tick on each CPU executing cpuidle_enter_freeze() and to make the last of them suspend the entire timekeeping. That should prevent timer interrupts from triggering until an IO interrupt wakes up one of the CPUs. It needs to be done with interrupts disabled on all of the CPUs, though, because otherwise the suspended clocksource might be accessed by an interrupt handler which might lead to fatal consequences. Unfortunately, the existing ->enter callbacks provided by cpuidle drivers generally cannot be used for implementing that, because some of them re-enable interrupts temporarily and some idle entry methods cause interrupts to be re-enabled automatically on exit. Also some of these callbacks manipulate local clock event devices of the CPUs which really shouldn't be done after suspending their ticks. To overcome that difficulty, introduce a new cpuidle state callback, ->enter_freeze, that will be guaranteed (1) to keep interrupts disabled all the time (and return with interrupts disabled) and (2) not to touch the CPU timer devices. Modify cpuidle_enter_freeze() to look for the deepest available idle state with ->enter_freeze present and to make the CPU execute that callback with suspended tick (and the last of the online CPUs to execute it with suspended timekeeping). Suggested-by: Thomas Gleixner Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- include/linux/cpuidle.h | 9 +++++++++ include/linux/tick.h | 6 +++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index f63aabf4ee90..f551a9299ac9 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -50,6 +50,15 @@ struct cpuidle_state { int index); int (*enter_dead) (struct cpuidle_device *dev, int index); + + /* + * CPUs execute ->enter_freeze with the local tick or entire timekeeping + * suspended, so it must not re-enable interrupts at any point (even + * temporarily) or attempt to change states of clock event devices. + */ + void (*enter_freeze) (struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index); }; /* Idle State Flags */ diff --git a/include/linux/tick.h b/include/linux/tick.h index eda850ca757a..9c085dc12ae9 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -79,6 +79,9 @@ extern void __init tick_init(void); extern int tick_is_oneshot_available(void); extern struct tick_device *tick_get_device(int cpu); +extern void tick_freeze(void); +extern void tick_unfreeze(void); + # ifdef CONFIG_HIGH_RES_TIMERS extern int tick_init_highres(void); extern int tick_program_event(ktime_t expires, int force); @@ -119,6 +122,8 @@ static inline int tick_oneshot_mode_active(void) { return 0; } #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } +static inline void tick_freeze(void) { } +static inline void tick_unfreeze(void) { } static inline void tick_cancel_sched_timer(int cpu) { } static inline void tick_clock_notify(void) { } static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } @@ -226,5 +231,4 @@ static inline void tick_nohz_task_switch(struct task_struct *tsk) __tick_nohz_task_switch(tsk); } - #endif -- cgit v1.2.3 From 1ea74014aba7cd3ddcc3cf3eef92270d2e8429e8 Mon Sep 17 00:00:00 2001 From: Sonic Zhang Date: Tue, 3 Feb 2015 17:12:17 -0800 Subject: Input: bfin_rotary - move platform header to linux/platform_data The platform data definition of the rotary driver should be generic for all architectures. Signed-off-by: Sonic Zhang Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/bfin_rotary.h | 116 ++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/linux/platform_data/bfin_rotary.h (limited to 'include/linux') diff --git a/include/linux/platform_data/bfin_rotary.h b/include/linux/platform_data/bfin_rotary.h new file mode 100644 index 000000000000..8895a750c70c --- /dev/null +++ b/include/linux/platform_data/bfin_rotary.h @@ -0,0 +1,116 @@ +/* + * board initialization should put one of these structures into platform_data + * and place the bfin-rotary onto platform_bus named "bfin-rotary". + * + * Copyright 2008-2010 Analog Devices Inc. + * + * Licensed under the GPL-2 or later. + */ + +#ifndef _BFIN_ROTARY_H +#define _BFIN_ROTARY_H + +/* mode bitmasks */ +#define ROT_QUAD_ENC CNTMODE_QUADENC /* quadrature/grey code encoder mode */ +#define ROT_BIN_ENC CNTMODE_BINENC /* binary encoder mode */ +#define ROT_UD_CNT CNTMODE_UDCNT /* rotary counter mode */ +#define ROT_DIR_CNT CNTMODE_DIRCNT /* direction counter mode */ + +#define ROT_DEBE DEBE /* Debounce Enable */ + +#define ROT_CDGINV CDGINV /* CDG Pin Polarity Invert */ +#define ROT_CUDINV CUDINV /* CUD Pin Polarity Invert */ +#define ROT_CZMINV CZMINV /* CZM Pin Polarity Invert */ + +struct bfin_rotary_platform_data { + /* set rotary UP KEY_### or BTN_### in case you prefer + * bfin-rotary to send EV_KEY otherwise set 0 + */ + unsigned int rotary_up_key; + /* set rotary DOWN KEY_### or BTN_### in case you prefer + * bfin-rotary to send EV_KEY otherwise set 0 + */ + unsigned int rotary_down_key; + /* set rotary BUTTON KEY_### or BTN_### */ + unsigned int rotary_button_key; + /* set rotary Relative Axis REL_### in case you prefer + * bfin-rotary to send EV_REL otherwise set 0 + */ + unsigned int rotary_rel_code; + unsigned short debounce; /* 0..17 */ + unsigned short mode; + unsigned short pm_wakeup; +}; + +/* CNT_CONFIG bitmasks */ +#define CNTE (1 << 0) /* Counter Enable */ +#define DEBE (1 << 1) /* Debounce Enable */ +#define CDGINV (1 << 4) /* CDG Pin Polarity Invert */ +#define CUDINV (1 << 5) /* CUD Pin Polarity Invert */ +#define CZMINV (1 << 6) /* CZM Pin Polarity Invert */ +#define CNTMODE_SHIFT 8 +#define CNTMODE (0x7 << CNTMODE_SHIFT) /* Counter Operating Mode */ +#define ZMZC (1 << 1) /* CZM Zeroes Counter Enable */ +#define BNDMODE_SHIFT 12 +#define BNDMODE (0x3 << BNDMODE_SHIFT) /* Boundary register Mode */ +#define INPDIS (1 << 15) /* CUG and CDG Input Disable */ + +#define CNTMODE_QUADENC (0 << CNTMODE_SHIFT) /* quadrature encoder mode */ +#define CNTMODE_BINENC (1 << CNTMODE_SHIFT) /* binary encoder mode */ +#define CNTMODE_UDCNT (2 << CNTMODE_SHIFT) /* up/down counter mode */ +#define CNTMODE_DIRCNT (4 << CNTMODE_SHIFT) /* direction counter mode */ +#define CNTMODE_DIRTMR (5 << CNTMODE_SHIFT) /* direction timer mode */ + +#define BNDMODE_COMP (0 << BNDMODE_SHIFT) /* boundary compare mode */ +#define BNDMODE_ZERO (1 << BNDMODE_SHIFT) /* boundary compare and zero mode */ +#define BNDMODE_CAPT (2 << BNDMODE_SHIFT) /* boundary capture mode */ +#define BNDMODE_AEXT (3 << BNDMODE_SHIFT) /* boundary auto-extend mode */ + +/* CNT_IMASK bitmasks */ +#define ICIE (1 << 0) /* Illegal Gray/Binary Code Interrupt Enable */ +#define UCIE (1 << 1) /* Up count Interrupt Enable */ +#define DCIE (1 << 2) /* Down count Interrupt Enable */ +#define MINCIE (1 << 3) /* Min Count Interrupt Enable */ +#define MAXCIE (1 << 4) /* Max Count Interrupt Enable */ +#define COV31IE (1 << 5) /* Bit 31 Overflow Interrupt Enable */ +#define COV15IE (1 << 6) /* Bit 15 Overflow Interrupt Enable */ +#define CZEROIE (1 << 7) /* Count to Zero Interrupt Enable */ +#define CZMIE (1 << 8) /* CZM Pin Interrupt Enable */ +#define CZMEIE (1 << 9) /* CZM Error Interrupt Enable */ +#define CZMZIE (1 << 10) /* CZM Zeroes Counter Interrupt Enable */ + +/* CNT_STATUS bitmasks */ +#define ICII (1 << 0) /* Illegal Gray/Binary Code Interrupt Identifier */ +#define UCII (1 << 1) /* Up count Interrupt Identifier */ +#define DCII (1 << 2) /* Down count Interrupt Identifier */ +#define MINCII (1 << 3) /* Min Count Interrupt Identifier */ +#define MAXCII (1 << 4) /* Max Count Interrupt Identifier */ +#define COV31II (1 << 5) /* Bit 31 Overflow Interrupt Identifier */ +#define COV15II (1 << 6) /* Bit 15 Overflow Interrupt Identifier */ +#define CZEROII (1 << 7) /* Count to Zero Interrupt Identifier */ +#define CZMII (1 << 8) /* CZM Pin Interrupt Identifier */ +#define CZMEII (1 << 9) /* CZM Error Interrupt Identifier */ +#define CZMZII (1 << 10) /* CZM Zeroes Counter Interrupt Identifier */ + +/* CNT_COMMAND bitmasks */ +#define W1LCNT 0xf /* Load Counter Register */ +#define W1LMIN 0xf0 /* Load Min Register */ +#define W1LMAX 0xf00 /* Load Max Register */ +#define W1ZMONCE (1 << 12) /* Enable CZM Clear Counter Once */ + +#define W1LCNT_ZERO (1 << 0) /* write 1 to load CNT_COUNTER with zero */ +#define W1LCNT_MIN (1 << 2) /* write 1 to load CNT_COUNTER from CNT_MIN */ +#define W1LCNT_MAX (1 << 3) /* write 1 to load CNT_COUNTER from CNT_MAX */ + +#define W1LMIN_ZERO (1 << 4) /* write 1 to load CNT_MIN with zero */ +#define W1LMIN_CNT (1 << 5) /* write 1 to load CNT_MIN from CNT_COUNTER */ +#define W1LMIN_MAX (1 << 7) /* write 1 to load CNT_MIN from CNT_MAX */ + +#define W1LMAX_ZERO (1 << 8) /* write 1 to load CNT_MAX with zero */ +#define W1LMAX_CNT (1 << 9) /* write 1 to load CNT_MAX from CNT_COUNTER */ +#define W1LMAX_MIN (1 << 10) /* write 1 to load CNT_MAX from CNT_MIN */ + +/* CNT_DEBOUNCE bitmasks */ +#define DPRESCALE 0xf /* Load Counter Register */ + +#endif -- cgit v1.2.3 From 5ea0699a7b452c9e1ecdc81e354fa91dfe8da4f6 Mon Sep 17 00:00:00 2001 From: Sonic Zhang Date: Thu, 5 Feb 2015 21:23:10 -0800 Subject: Input: bfin_rotary - move pin lists into into platform data Newer Blackfin boards use pinctrl API to manage pins and the legacy peripherial lists are not useful on them. Let's move pin lists into platform data so older boards can still use them and newer boards can use the modern API. Signed-off-by: Sonic Zhang Signed-off-by: Dmitry Torokhov --- include/linux/platform_data/bfin_rotary.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/bfin_rotary.h b/include/linux/platform_data/bfin_rotary.h index 8895a750c70c..98829370fee2 100644 --- a/include/linux/platform_data/bfin_rotary.h +++ b/include/linux/platform_data/bfin_rotary.h @@ -40,6 +40,7 @@ struct bfin_rotary_platform_data { unsigned short debounce; /* 0..17 */ unsigned short mode; unsigned short pm_wakeup; + unsigned short *pin_list; }; /* CNT_CONFIG bitmasks */ -- cgit v1.2.3 From e084c1bd40926938ff8d26af3bde34396dd4d06d Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 16 Feb 2015 14:32:03 -0500 Subject: Revert "locks: keep a count of locks on the flctx lists" This reverts commit 9bd0f45b7037fcfa8b575c7e27d0431d6e6dc3bb. Linus rightly pointed out that I failed to initialize the counters when adding them, so they don't work as expected. Just revert this patch for now. Reported-by: Linus Torvalds Signed-off-by: Jeff Layton --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e49f10cc8a73..a5a303e8a33c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -969,9 +969,6 @@ struct file_lock_context { struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; - int flc_flock_cnt; - int flc_posix_cnt; - int flc_lease_cnt; }; /* The following constant reflects the upper bound of the file/locking space */ -- cgit v1.2.3 From 2e4cdab0584fa884e0a81c4f45b93ce875c9fcaa Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:58:50 -0800 Subject: mm: allow page fault handlers to perform the COW Currently COW of an XIP file is done by first bringing in a read-only mapping, then retrying the fault and copying the page. It is much more efficient to tell the fault handler that a COW is being attempted (by passing in the pre-allocated page in the vm_fault structure), and allow the handler to perform the COW operation itself. The handler cannot insert the page itself if there is already a read-only mapping at that address, so allow the handler to return VM_FAULT_LOCKED and set the fault_page to be NULL. This indicates to the MM code that the i_mmap_lock is held instead of the page lock. Signed-off-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9bee7ec0c31f..47a93928b90f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -224,6 +224,7 @@ struct vm_fault { pgoff_t pgoff; /* Logical page offset based on vma */ void __user *virtual_address; /* Faulting virtual address */ + struct page *cow_page; /* Handler may choose to COW */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by -- cgit v1.2.3 From fbbbad4bc2101e452b24e6e65d3d5e11314a0b5f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:58:53 -0800 Subject: vfs,ext2: introduce IS_DAX(inode) Use an inode flag to tag inodes which should avoid using the page cache. Convert ext2 to use it instead of mapping_is_xip(). Prevent I/Os to files tagged with the DAX flag from falling back to buffered I/O. Signed-off-by: Matthew Wilcox Reviewed-by: Jan Kara Reviewed-by: Mathieu Desnoyers Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e49f10cc8a73..fb373bb5cf03 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1677,6 +1677,11 @@ struct super_operations { #define S_IMA 1024 /* Inode has an associated IMA struct */ #define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ #define S_NOSEC 4096 /* no suid or xattr security attributes */ +#ifdef CONFIG_FS_XIP +#define S_DAX 8192 /* Direct Access, avoiding the page cache */ +#else +#define S_DAX 0 /* Make all the DAX code disappear */ +#endif /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -1714,6 +1719,7 @@ struct super_operations { #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) +#define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) -- cgit v1.2.3 From d475c6346a38aef3058eba96867bfa726a3cc940 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:58:56 -0800 Subject: dax,ext2: replace XIP read and write with DAX I/O Use the generic AIO infrastructure instead of custom read and write methods. In addition to giving us support for AIO, this adds the missing locking between read() and truncate(). Signed-off-by: Matthew Wilcox Reviewed-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index fb373bb5cf03..241c3c030fb5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2587,12 +2587,11 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); +ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, + loff_t, get_block_t, dio_iodone_t, int flags); + #ifdef CONFIG_FS_XIP -extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len, - loff_t *ppos); extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); -extern ssize_t xip_file_write(struct file *filp, const char __user *buf, - size_t len, loff_t *ppos); extern int xip_truncate_page(struct address_space *mapping, loff_t from); #else static inline int xip_truncate_page(struct address_space *mapping, loff_t from) @@ -2756,6 +2755,11 @@ extern int generic_show_options(struct seq_file *m, struct dentry *root); extern void save_mount_options(struct super_block *sb, char *options); extern void replace_mount_options(struct super_block *sb, char *options); +static inline bool io_is_direct(struct file *filp) +{ + return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp)); +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; -- cgit v1.2.3 From 289c6aedac981533331428bc933fff21ae332c9e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:58:59 -0800 Subject: dax,ext2: replace ext2_clear_xip_target with dax_clear_blocks This is practically generic code; other filesystems will want to call it from other places, but there's nothing ext2-specific about it. Make it a little more generic by allowing it to take a count of the number of bytes to zero rather than fixing it to a single page. Thanks to Dave Hansen for suggesting that I need to call cond_resched() if zeroing more than one page. Signed-off-by: Matthew Wilcox Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 241c3c030fb5..8084934a5676 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2589,6 +2589,7 @@ extern int nonseekable_open(struct inode * inode, struct file * filp); ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); +int dax_clear_blocks(struct inode *, sector_t block, long size); #ifdef CONFIG_FS_XIP extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); -- cgit v1.2.3 From f7ca90b160307d63aaedab8bd451c24a182db20f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:59:02 -0800 Subject: dax,ext2: replace the XIP page fault handler with the DAX page fault handler Instead of calling aops->get_xip_mem from the fault handler, the filesystem passes a get_block_t that is used to find the appropriate blocks. This requires that all architectures implement copy_user_page(). At the time of writing, mips and arm do not. Patches exist and are in progress. [akpm@linux-foundation.org: remap_file_pages went away] Signed-off-by: Matthew Wilcox Reviewed-by: Jan Kara Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Cc: Russell King Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 8084934a5676..6bad6d4c579b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -51,6 +51,7 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; +struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2590,9 +2591,10 @@ extern int nonseekable_open(struct inode * inode, struct file * filp); ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); +#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) #ifdef CONFIG_FS_XIP -extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma); extern int xip_truncate_page(struct address_space *mapping, loff_t from); #else static inline int xip_truncate_page(struct address_space *mapping, loff_t from) -- cgit v1.2.3 From 4c0ccfef2e9f7418a6eb0bf07a2fc8f216365b18 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:59:06 -0800 Subject: dax,ext2: replace xip_truncate_page with dax_truncate_page It takes a get_block parameter just like nobh_truncate_page() and block_truncate_page() Signed-off-by: Matthew Wilcox Reviewed-by: Mathieu Desnoyers Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6bad6d4c579b..2c8f9055af38 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2591,18 +2591,10 @@ extern int nonseekable_open(struct inode * inode, struct file * filp); ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -#ifdef CONFIG_FS_XIP -extern int xip_truncate_page(struct address_space *mapping, loff_t from); -#else -static inline int xip_truncate_page(struct address_space *mapping, loff_t from) -{ - return 0; -} -#endif - #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); -- cgit v1.2.3 From e748dcd095ddee50e7a7deda2e26247715318a2e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:59:12 -0800 Subject: vfs: remove get_xip_mem All callers of get_xip_mem() are now gone. Remove checks for it, initialisers of it, documentation of it and the only implementation of it. Also remove mm/filemap_xip.c as it is now empty. Also remove documentation of the long-gone get_xip_page(). Signed-off-by: Matthew Wilcox Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- include/linux/rmap.h | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c8f9055af38..9772d655f444 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -362,8 +362,6 @@ struct address_space_operations { int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset); - int (*get_xip_mem)(struct address_space *, pgoff_t, int, - void **, unsigned long *); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b38f559130d5..c4c559a45dc8 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -198,7 +198,7 @@ int page_referenced(struct page *, int is_locked, int try_to_unmap(struct page *, enum ttu_flags flags); /* - * Called from mm/filemap_xip.c to unmap empty zero page + * Used by uprobes to replace a userspace page safely */ pte_t *__page_check_address(struct page *, struct mm_struct *, unsigned long, spinlock_t **, int); -- cgit v1.2.3 From 6cd176a51e52e5218b1aa97e1ec916bac25a9b7e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:59:25 -0800 Subject: vfs,ext2: remove CONFIG_EXT2_FS_XIP and rename CONFIG_FS_XIP to CONFIG_FS_DAX The fewer Kconfig options we have the better. Use the generic CONFIG_FS_DAX to enable XIP support in ext2 as well as in the core. Signed-off-by: Matthew Wilcox Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9772d655f444..d46f8fe6a0ea 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1676,7 +1676,7 @@ struct super_operations { #define S_IMA 1024 /* Inode has an associated IMA struct */ #define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ #define S_NOSEC 4096 /* no suid or xattr security attributes */ -#ifdef CONFIG_FS_XIP +#ifdef CONFIG_FS_DAX #define S_DAX 8192 /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ -- cgit v1.2.3 From 25726bc15731d42112b579cf73f30edbc43d3973 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 16 Feb 2015 15:59:35 -0800 Subject: dax: add dax_zero_page_range This new function allows us to support hole-punch for DAX files by zeroing a partial page, as opposed to the dax_truncate_page() function which can only truncate to the end of the page. Reimplement dax_truncate_page() to call dax_zero_page_range(). [ross.zwisler@linux.intel.com: ported to 3.13-rc2] [akpm@linux-foundation.org: fix typos in comments] Signed-off-by: Matthew Wilcox Signed-off-by: Ross Zwisler Cc: Andreas Dilger Cc: Boaz Harrosh Cc: Christoph Hellwig Cc: Dave Chinner Cc: Jan Kara Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Mathieu Desnoyers Cc: Randy Dunlap Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d46f8fe6a0ea..ed5a0900b94d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2589,6 +2589,7 @@ extern int nonseekable_open(struct inode * inode, struct file * filp); ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -- cgit v1.2.3 From aaaf5fbf56f16c81a653713cc333b18ad6e25ea9 Mon Sep 17 00:00:00 2001 From: Joshua Kinard Date: Mon, 16 Feb 2015 16:00:26 -0800 Subject: rtc: add driver for DS1685 family of real time clocks This adds a driver for the Dallas/Maxim DS1685-family of RTC chips. It supports the DS1685/DS1687, DS1688/DS1691, DS1689/DS1693, DS17285/DS17287, DS17485/DS17487, and DS17885/DS17887 RTC chips. These chips are commonly found in SGI O2 and SGI Octane systems. It was originally derived from a driver patch submitted by Matthias Fuchs many years ago for use in EPPC-405-UC modules, which also used these RTCs. In addition to the time-keeping functions, this RTC also handles the shutdown mechanism of the O2 and Octane and acts as a partial NVRAM for the boot PROMS in these systems. Verified on both an SGI O2 and an SGI Octane. Signed-off-by: Joshua Kinard Cc: Ralf Baechle Cc: Alessandro Zummo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rtc/ds1685.h | 375 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 375 insertions(+) create mode 100644 include/linux/rtc/ds1685.h (limited to 'include/linux') diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h new file mode 100644 index 000000000000..e6337a56d741 --- /dev/null +++ b/include/linux/rtc/ds1685.h @@ -0,0 +1,375 @@ +/* + * Definitions for the registers, addresses, and platform data of the + * DS1685/DS1687-series RTC chips. + * + * This Driver also works for the DS17X85/DS17X87 RTC chips. Functionally + * similar to the DS1685/DS1687, they support a few extra features which + * include larger, battery-backed NV-SRAM, burst-mode access, and an RTC + * write counter. + * + * Copyright (C) 2011-2014 Joshua Kinard . + * Copyright (C) 2009 Matthias Fuchs . + * + * References: + * DS1685/DS1687 3V/5V Real-Time Clocks, 19-5215, Rev 4/10. + * DS17x85/DS17x87 3V/5V Real-Time Clocks, 19-5222, Rev 4/10. + * DS1689/DS1693 3V/5V Serialized Real-Time Clocks, Rev 112105. + * Application Note 90, Using the Multiplex Bus RTC Extended Features. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_RTC_DS1685_H_ +#define _LINUX_RTC_DS1685_H_ + +#include +#include +#include + +/** + * struct ds1685_priv - DS1685 private data structure. + * @dev: pointer to the rtc_device structure. + * @regs: iomapped base address pointer of the RTC registers. + * @regstep: padding/step size between registers (optional). + * @baseaddr: base address of the RTC device. + * @size: resource size. + * @lock: private lock variable for spin locking/unlocking. + * @work: private workqueue. + * @irq: IRQ number assigned to the RTC device. + * @prepare_poweroff: pointer to platform pre-poweroff function. + * @wake_alarm: pointer to platform wake alarm function. + * @post_ram_clear: pointer to platform post ram-clear function. + */ +struct ds1685_priv { + struct rtc_device *dev; + void __iomem *regs; + u32 regstep; + resource_size_t baseaddr; + size_t size; + spinlock_t lock; + struct work_struct work; + int irq_num; + bool bcd_mode; + bool no_irq; + bool uie_unsupported; + bool alloc_io_resources; + u8 (*read)(struct ds1685_priv *, int); + void (*write)(struct ds1685_priv *, int, u8); + void (*prepare_poweroff)(void); + void (*wake_alarm)(void); + void (*post_ram_clear)(void); +}; + + +/** + * struct ds1685_rtc_platform_data - platform data structure. + * @plat_prepare_poweroff: platform-specific pre-poweroff function. + * @plat_wake_alarm: platform-specific wake alarm function. + * @plat_post_ram_clear: platform-specific post ram-clear function. + * + * If your platform needs to use a custom padding/step size between + * registers, or uses one or more of the extended interrupts and needs special + * handling, then include this header file in your platform definition and + * set regstep and the plat_* pointers as appropriate. + */ +struct ds1685_rtc_platform_data { + const u32 regstep; + const bool bcd_mode; + const bool no_irq; + const bool uie_unsupported; + const bool alloc_io_resources; + u8 (*plat_read)(struct ds1685_priv *, int); + void (*plat_write)(struct ds1685_priv *, int, u8); + void (*plat_prepare_poweroff)(void); + void (*plat_wake_alarm)(void); + void (*plat_post_ram_clear)(void); +}; + + +/* + * Time Registers. + */ +#define RTC_SECS 0x00 /* Seconds 00-59 */ +#define RTC_SECS_ALARM 0x01 /* Alarm Seconds 00-59 */ +#define RTC_MINS 0x02 /* Minutes 00-59 */ +#define RTC_MINS_ALARM 0x03 /* Alarm Minutes 00-59 */ +#define RTC_HRS 0x04 /* Hours 01-12 AM/PM || 00-23 */ +#define RTC_HRS_ALARM 0x05 /* Alarm Hours 01-12 AM/PM || 00-23 */ +#define RTC_WDAY 0x06 /* Day of Week 01-07 */ +#define RTC_MDAY 0x07 /* Day of Month 01-31 */ +#define RTC_MONTH 0x08 /* Month 01-12 */ +#define RTC_YEAR 0x09 /* Year 00-99 */ +#define RTC_CENTURY 0x48 /* Century 00-99 */ +#define RTC_MDAY_ALARM 0x49 /* Alarm Day of Month 01-31 */ + + +/* + * Bit masks for the Time registers in BCD Mode (DM = 0). + */ +#define RTC_SECS_BCD_MASK 0x7f /* - x x x x x x x */ +#define RTC_MINS_BCD_MASK 0x7f /* - x x x x x x x */ +#define RTC_HRS_12_BCD_MASK 0x1f /* - - - x x x x x */ +#define RTC_HRS_24_BCD_MASK 0x3f /* - - x x x x x x */ +#define RTC_MDAY_BCD_MASK 0x3f /* - - x x x x x x */ +#define RTC_MONTH_BCD_MASK 0x1f /* - - - x x x x x */ +#define RTC_YEAR_BCD_MASK 0xff /* x x x x x x x x */ + +/* + * Bit masks for the Time registers in BIN Mode (DM = 1). + */ +#define RTC_SECS_BIN_MASK 0x3f /* - - x x x x x x */ +#define RTC_MINS_BIN_MASK 0x3f /* - - x x x x x x */ +#define RTC_HRS_12_BIN_MASK 0x0f /* - - - - x x x x */ +#define RTC_HRS_24_BIN_MASK 0x1f /* - - - x x x x x */ +#define RTC_MDAY_BIN_MASK 0x1f /* - - - x x x x x */ +#define RTC_MONTH_BIN_MASK 0x0f /* - - - - x x x x */ +#define RTC_YEAR_BIN_MASK 0x7f /* - x x x x x x x */ + +/* + * Bit masks common for the Time registers in BCD or BIN Mode. + */ +#define RTC_WDAY_MASK 0x07 /* - - - - - x x x */ +#define RTC_CENTURY_MASK 0xff /* x x x x x x x x */ +#define RTC_MDAY_ALARM_MASK 0xff /* x x x x x x x x */ +#define RTC_HRS_AMPM_MASK BIT(7) /* Mask for the AM/PM bit */ + + + +/* + * Control Registers. + */ +#define RTC_CTRL_A 0x0a /* Control Register A */ +#define RTC_CTRL_B 0x0b /* Control Register B */ +#define RTC_CTRL_C 0x0c /* Control Register C */ +#define RTC_CTRL_D 0x0d /* Control Register D */ +#define RTC_EXT_CTRL_4A 0x4a /* Extended Control Register 4A */ +#define RTC_EXT_CTRL_4B 0x4b /* Extended Control Register 4B */ + + +/* + * Bit names in Control Register A. + */ +#define RTC_CTRL_A_UIP BIT(7) /* Update In Progress */ +#define RTC_CTRL_A_DV2 BIT(6) /* Countdown Chain */ +#define RTC_CTRL_A_DV1 BIT(5) /* Oscillator Enable */ +#define RTC_CTRL_A_DV0 BIT(4) /* Bank Select */ +#define RTC_CTRL_A_RS2 BIT(2) /* Rate-Selection Bit 2 */ +#define RTC_CTRL_A_RS3 BIT(3) /* Rate-Selection Bit 3 */ +#define RTC_CTRL_A_RS1 BIT(1) /* Rate-Selection Bit 1 */ +#define RTC_CTRL_A_RS0 BIT(0) /* Rate-Selection Bit 0 */ +#define RTC_CTRL_A_RS_MASK 0x0f /* RS3 + RS2 + RS1 + RS0 */ + +/* + * Bit names in Control Register B. + */ +#define RTC_CTRL_B_SET BIT(7) /* SET Bit */ +#define RTC_CTRL_B_PIE BIT(6) /* Periodic-Interrupt Enable */ +#define RTC_CTRL_B_AIE BIT(5) /* Alarm-Interrupt Enable */ +#define RTC_CTRL_B_UIE BIT(4) /* Update-Ended Interrupt-Enable */ +#define RTC_CTRL_B_SQWE BIT(3) /* Square-Wave Enable */ +#define RTC_CTRL_B_DM BIT(2) /* Data Mode */ +#define RTC_CTRL_B_2412 BIT(1) /* 12-Hr/24-Hr Mode */ +#define RTC_CTRL_B_DSE BIT(0) /* Daylight Savings Enable */ +#define RTC_CTRL_B_PAU_MASK 0x70 /* PIE + AIE + UIE */ + + +/* + * Bit names in Control Register C. + * + * BIT(0), BIT(1), BIT(2), & BIT(3) are unused, always return 0, and cannot + * be written to. + */ +#define RTC_CTRL_C_IRQF BIT(7) /* Interrupt-Request Flag */ +#define RTC_CTRL_C_PF BIT(6) /* Periodic-Interrupt Flag */ +#define RTC_CTRL_C_AF BIT(5) /* Alarm-Interrupt Flag */ +#define RTC_CTRL_C_UF BIT(4) /* Update-Ended Interrupt Flag */ +#define RTC_CTRL_C_PAU_MASK 0x70 /* PF + AF + UF */ + + +/* + * Bit names in Control Register D. + * + * BIT(0) through BIT(6) are unused, always return 0, and cannot + * be written to. + */ +#define RTC_CTRL_D_VRT BIT(7) /* Valid RAM and Time */ + + +/* + * Bit names in Extended Control Register 4A. + * + * On the DS1685/DS1687/DS1689/DS1693, BIT(4) and BIT(5) are reserved for + * future use. They can be read from and written to, but have no effect + * on the RTC's operation. + * + * On the DS17x85/DS17x87, BIT(5) is Burst-Mode Enable (BME), and allows + * access to the extended NV-SRAM by automatically incrementing the address + * register when they are read from or written to. + */ +#define RTC_CTRL_4A_VRT2 BIT(7) /* Auxillary Battery Status */ +#define RTC_CTRL_4A_INCR BIT(6) /* Increment-in-Progress Status */ +#define RTC_CTRL_4A_PAB BIT(3) /* Power-Active Bar Control */ +#define RTC_CTRL_4A_RF BIT(2) /* RAM-Clear Flag */ +#define RTC_CTRL_4A_WF BIT(1) /* Wake-Up Alarm Flag */ +#define RTC_CTRL_4A_KF BIT(0) /* Kickstart Flag */ +#if !defined(CONFIG_RTC_DRV_DS1685) && !defined(CONFIG_RTC_DRV_DS1689) +#define RTC_CTRL_4A_BME BIT(5) /* Burst-Mode Enable */ +#endif +#define RTC_CTRL_4A_RWK_MASK 0x07 /* RF + WF + KF */ + + +/* + * Bit names in Extended Control Register 4B. + */ +#define RTC_CTRL_4B_ABE BIT(7) /* Auxillary Battery Enable */ +#define RTC_CTRL_4B_E32K BIT(6) /* Enable 32.768Hz on SQW Pin */ +#define RTC_CTRL_4B_CS BIT(5) /* Crystal Select */ +#define RTC_CTRL_4B_RCE BIT(4) /* RAM Clear-Enable */ +#define RTC_CTRL_4B_PRS BIT(3) /* PAB Reset-Select */ +#define RTC_CTRL_4B_RIE BIT(2) /* RAM Clear-Interrupt Enable */ +#define RTC_CTRL_4B_WIE BIT(1) /* Wake-Up Alarm-Interrupt Enable */ +#define RTC_CTRL_4B_KSE BIT(0) /* Kickstart Interrupt-Enable */ +#define RTC_CTRL_4B_RWK_MASK 0x07 /* RIE + WIE + KSE */ + + +/* + * Misc register names in Bank 1. + * + * The DV0 bit in Control Register A must be set to 1 for these registers + * to become available, including Extended Control Registers 4A & 4B. + */ +#define RTC_BANK1_SSN_MODEL 0x40 /* Model Number */ +#define RTC_BANK1_SSN_BYTE_1 0x41 /* 1st Byte of Serial Number */ +#define RTC_BANK1_SSN_BYTE_2 0x42 /* 2nd Byte of Serial Number */ +#define RTC_BANK1_SSN_BYTE_3 0x43 /* 3rd Byte of Serial Number */ +#define RTC_BANK1_SSN_BYTE_4 0x44 /* 4th Byte of Serial Number */ +#define RTC_BANK1_SSN_BYTE_5 0x45 /* 5th Byte of Serial Number */ +#define RTC_BANK1_SSN_BYTE_6 0x46 /* 6th Byte of Serial Number */ +#define RTC_BANK1_SSN_CRC 0x47 /* Serial CRC Byte */ +#define RTC_BANK1_RAM_DATA_PORT 0x53 /* Extended RAM Data Port */ + + +/* + * Model-specific registers in Bank 1. + * + * The addresses below differ depending on the model of the RTC chip + * selected in the kernel configuration. Not all of these features are + * supported in the main driver at present. + * + * DS1685/DS1687 - Extended NV-SRAM address (LSB only). + * DS1689/DS1693 - Vcc, Vbat, Pwr Cycle Counters & Customer-specific S/N. + * DS17x85/DS17x87 - Extended NV-SRAM addresses (MSB & LSB) & Write counter. + */ +#if defined(CONFIG_RTC_DRV_DS1685) +#define RTC_BANK1_RAM_ADDR 0x50 /* NV-SRAM Addr */ +#elif defined(CONFIG_RTC_DRV_DS1689) +#define RTC_BANK1_VCC_CTR_LSB 0x54 /* Vcc Counter Addr (LSB) */ +#define RTC_BANK1_VCC_CTR_MSB 0x57 /* Vcc Counter Addr (MSB) */ +#define RTC_BANK1_VBAT_CTR_LSB 0x58 /* Vbat Counter Addr (LSB) */ +#define RTC_BANK1_VBAT_CTR_MSB 0x5b /* Vbat Counter Addr (MSB) */ +#define RTC_BANK1_PWR_CTR_LSB 0x5c /* Pwr Cycle Counter Addr (LSB) */ +#define RTC_BANK1_PWR_CTR_MSB 0x5d /* Pwr Cycle Counter Addr (MSB) */ +#define RTC_BANK1_UNIQ_SN 0x60 /* Customer-specific S/N */ +#else /* DS17x85/DS17x87 */ +#define RTC_BANK1_RAM_ADDR_LSB 0x50 /* NV-SRAM Addr (LSB) */ +#define RTC_BANK1_RAM_ADDR_MSB 0x51 /* NV-SRAM Addr (MSB) */ +#define RTC_BANK1_WRITE_CTR 0x5e /* RTC Write Counter */ +#endif + + +/* + * Model numbers. + * + * The DS1688/DS1691 and DS1689/DS1693 chips share the same model number + * and the manual doesn't indicate any major differences. As such, they + * are regarded as the same chip in this driver. + */ +#define RTC_MODEL_DS1685 0x71 /* DS1685/DS1687 */ +#define RTC_MODEL_DS17285 0x72 /* DS17285/DS17287 */ +#define RTC_MODEL_DS1689 0x73 /* DS1688/DS1691/DS1689/DS1693 */ +#define RTC_MODEL_DS17485 0x74 /* DS17485/DS17487 */ +#define RTC_MODEL_DS17885 0x78 /* DS17885/DS17887 */ + + +/* + * Periodic Interrupt Rates / Square-Wave Output Frequency + * + * Periodic rates are selected by setting the RS3-RS0 bits in Control + * Register A and enabled via either the E32K bit in Extended Control + * Register 4B or the SQWE bit in Control Register B. + * + * E32K overrides the settings of RS3-RS0 and outputs a frequency of 32768Hz + * on the SQW pin of the RTC chip. While there are 16 possible selections, + * the 1-of-16 decoder is only able to divide the base 32768Hz signal into 13 + * smaller frequencies. The values 0x01 and 0x02 are not used and are + * synonymous with 0x08 and 0x09, respectively. + * + * When E32K is set to a logic 1, periodic interrupts are disabled and reading + * /dev/rtc will return -EINVAL. This also applies if the periodic interrupt + * frequency is set to 0Hz. + * + * Not currently used by the rtc-ds1685 driver because the RTC core removed + * support for hardware-generated periodic-interrupts in favour of + * hrtimer-generated interrupts. But these defines are kept around for use + * in userland, as documentation to the hardware, and possible future use if + * hardware-generated periodic interrupts are ever added back. + */ + /* E32K RS3 RS2 RS1 RS0 */ +#define RTC_SQW_8192HZ 0x03 /* 0 0 0 1 1 */ +#define RTC_SQW_4096HZ 0x04 /* 0 0 1 0 0 */ +#define RTC_SQW_2048HZ 0x05 /* 0 0 1 0 1 */ +#define RTC_SQW_1024HZ 0x06 /* 0 0 1 1 0 */ +#define RTC_SQW_512HZ 0x07 /* 0 0 1 1 1 */ +#define RTC_SQW_256HZ 0x08 /* 0 1 0 0 0 */ +#define RTC_SQW_128HZ 0x09 /* 0 1 0 0 1 */ +#define RTC_SQW_64HZ 0x0a /* 0 1 0 1 0 */ +#define RTC_SQW_32HZ 0x0b /* 0 1 0 1 1 */ +#define RTC_SQW_16HZ 0x0c /* 0 1 1 0 0 */ +#define RTC_SQW_8HZ 0x0d /* 0 1 1 0 1 */ +#define RTC_SQW_4HZ 0x0e /* 0 1 1 1 0 */ +#define RTC_SQW_2HZ 0x0f /* 0 1 1 1 1 */ +#define RTC_SQW_0HZ 0x00 /* 0 0 0 0 0 */ +#define RTC_SQW_32768HZ 32768 /* 1 - - - - */ +#define RTC_MAX_USER_FREQ 8192 + + +/* + * NVRAM data & addresses: + * - 50 bytes of NVRAM are available just past the clock registers. + * - 64 additional bytes are available in Bank0. + * + * Extended, battery-backed NV-SRAM: + * - DS1685/DS1687 - 128 bytes. + * - DS1689/DS1693 - 0 bytes. + * - DS17285/DS17287 - 2048 bytes. + * - DS17485/DS17487 - 4096 bytes. + * - DS17885/DS17887 - 8192 bytes. + */ +#define NVRAM_TIME_BASE 0x0e /* NVRAM Addr in Time regs */ +#define NVRAM_BANK0_BASE 0x40 /* NVRAM Addr in Bank0 regs */ +#define NVRAM_SZ_TIME 50 +#define NVRAM_SZ_BANK0 64 +#if defined(CONFIG_RTC_DRV_DS1685) +# define NVRAM_SZ_EXTND 128 +#elif defined(CONFIG_RTC_DRV_DS1689) +# define NVRAM_SZ_EXTND 0 +#elif defined(CONFIG_RTC_DRV_DS17285) +# define NVRAM_SZ_EXTND 2048 +#elif defined(CONFIG_RTC_DRV_DS17485) +# define NVRAM_SZ_EXTND 4096 +#elif defined(CONFIG_RTC_DRV_DS17885) +# define NVRAM_SZ_EXTND 8192 +#endif +#define NVRAM_TOTAL_SZ_BANK0 (NVRAM_SZ_TIME + NVRAM_SZ_BANK0) +#define NVRAM_TOTAL_SZ (NVRAM_TOTAL_SZ_BANK0 + NVRAM_SZ_EXTND) + + +/* + * Function Prototypes. + */ +extern void __noreturn +ds1685_rtc_poweroff(struct platform_device *pdev); + +#endif /* _LINUX_RTC_DS1685_H_ */ -- cgit v1.2.3 From f9d904acb3e7e9edb470cd824fe2a21bb0df86b8 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 7 Jan 2015 10:14:43 -0800 Subject: HID: hid-sensor-hub: Correct documentation During changes to the interface, some documentation field comments were missed. Added missing comments. Signed-off-by: Srinivas Pandruvada Signed-off-by: Jiri Kosina --- include/linux/hid-sensor-hub.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 51f7ccadf923..4173a8fdad9e 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -33,6 +33,8 @@ * @units: Measurment unit for this attribute. * @unit_expo: Exponent used in the data. * @size: Size in bytes for data size. + * @logical_minimum: Logical minimum value for this attribute. + * @logical_maximum: Logical maximum value for this attribute. */ struct hid_sensor_hub_attribute_info { u32 usage_id; @@ -146,6 +148,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, /** * sensor_hub_input_attr_get_raw_value() - Synchronous read request +* @hsdev: Hub device instance. * @usage_id: Attribute usage id of parent physical device as per spec * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for @@ -160,6 +163,7 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 attr_usage_id, u32 report_id); /** * sensor_hub_set_feature() - Feature set request +* @hsdev: Hub device instance. * @report_id: Report id to look for * @field_index: Field index inside a report * @value: Value to set @@ -172,6 +176,7 @@ int sensor_hub_set_feature(struct hid_sensor_hub_device *hsdev, u32 report_id, /** * sensor_hub_get_feature() - Feature get request +* @hsdev: Hub device instance. * @report_id: Report id to look for * @field_index: Field index inside a report * @value: Place holder for return value -- cgit v1.2.3 From e59b4e9187bd5175b9845dc10fedb0879b7efbfd Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 21 Jan 2015 20:03:40 +0000 Subject: debugfs: Provide a file creation function that also takes an initial size Provide a file creation function that also takes an initial size so that the caller doesn't have to set i_size, thus meaning that we don't have to call deal with ->d_inode in the callers. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/debugfs.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index ea149a24a1f2..cb25af461054 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -51,6 +51,11 @@ struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops); +struct dentry *debugfs_create_file_size(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops, + loff_t file_size); + struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, @@ -129,6 +134,14 @@ static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_file_size(const char *name, umode_t mode, + struct dentry *parent, void *data, + const struct file_operations *fops, + loff_t file_size) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { -- cgit v1.2.3 From 1cc7495c60879eeeda52385a70c99c4cbaace7ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 25 Jan 2015 11:40:57 +0100 Subject: watchdog: bcm47xx_wdt.c: add restart handler support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just like in case of other watchdog drivers, use the new kernel core API to provide restart support. Signed-off-by: Rafał Miłecki Reviewed-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/bcm47xx_wdt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcm47xx_wdt.h b/include/linux/bcm47xx_wdt.h index b708786d4cbf..5582c211f594 100644 --- a/include/linux/bcm47xx_wdt.h +++ b/include/linux/bcm47xx_wdt.h @@ -16,6 +16,7 @@ struct bcm47xx_wdt { struct watchdog_device wdd; struct notifier_block notifier; + struct notifier_block restart_handler; struct timer_list soft_timer; atomic_t soft_ticks; -- cgit v1.2.3 From 73d7e3eac01da3cef32ab25cbc6a36a6202c4ea6 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Tue, 17 Feb 2015 13:45:44 -0800 Subject: kexec: remove never used member destination in kimage struct kimage has a member destination which is used to store the real destination address of each page when load segment from user space buffer to kernel. But we never retrieve the value stored in kimage->destination, so this member variable in kimage and its assignment operation are redundent code. I guess for_each_kimage_entry just does the work that kimage->destination is expected to do. So in this patch just make a cleanup to remove it. Signed-off-by: Baoquan He Cc: "Eric W. Biederman" Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 9d957b7ae095..10da8e246317 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -122,8 +122,6 @@ struct kimage { kimage_entry_t *entry; kimage_entry_t *last_entry; - unsigned long destination; - unsigned long start; struct page *control_code_page; struct page *swap_page; -- cgit v1.2.3 From cf2df6396ba78014289f322839a5cc785f09e1fd Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Tue, 17 Feb 2015 13:45:56 -0800 Subject: kexec: add bit definitions for kimage entry flags Define new kexec preprocessor macros IND_*_BIT that define the bit position of the kimage entry flags. Change the existing IND_* flag macros to be defined as bit shifts of the corresponding IND_*_BIT macros. Also wrap all C language code in kexec.h with #if !defined(__ASSEMBLY__) so assembly files can include kexec.h to get the IND_* and IND_*_BIT macros. Some CPU instruction sets have tests for bit position which are convenient in implementing routines that operate on the kimage entry list. The addition of these bit position macros in a common location will avoid duplicate definitions and the chance that changes to the IND_* flags will not be propagated to assembly files. Signed-off-by: Geoff Levand Acked-by: Vivek Goyal Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: H. Peter Anvin Cc: Maximilian Attems Cc: Michal Marek Cc: Paul Bolle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 10da8e246317..1fd980cc481b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -1,6 +1,18 @@ #ifndef LINUX_KEXEC_H #define LINUX_KEXEC_H +#define IND_DESTINATION_BIT 0 +#define IND_INDIRECTION_BIT 1 +#define IND_DONE_BIT 2 +#define IND_SOURCE_BIT 3 + +#define IND_DESTINATION (1 << IND_DESTINATION_BIT) +#define IND_INDIRECTION (1 << IND_INDIRECTION_BIT) +#define IND_DONE (1 << IND_DONE_BIT) +#define IND_SOURCE (1 << IND_SOURCE_BIT) + +#if !defined(__ASSEMBLY__) + #include #ifdef CONFIG_KEXEC @@ -64,10 +76,6 @@ */ typedef unsigned long kimage_entry_t; -#define IND_DESTINATION 0x1 -#define IND_INDIRECTION 0x2 -#define IND_DONE 0x4 -#define IND_SOURCE 0x8 struct kexec_segment { /* @@ -311,4 +319,7 @@ struct task_struct; static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } #endif /* CONFIG_KEXEC */ + +#endif /* !defined(__ASSEBMLY__) */ + #endif /* LINUX_KEXEC_H */ -- cgit v1.2.3 From b28c2ee868dbdc0baa89c60fb520be85d5e90a72 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Tue, 17 Feb 2015 13:45:58 -0800 Subject: kexec: add IND_FLAGS macro Add a new kexec preprocessor macro IND_FLAGS, which is the bitwise OR of all the possible kexec IND_ kimage_entry indirection flags. Having this macro allows for simplified code in the prosessing of the kexec kimage_entry items. Also, remove the local powerpc definition and use the generic one. Signed-off-by: Geoff Levand Acked-by: Benjamin Herrenschmidt Acked-by: Vivek Goyal Cc: Arnd Bergmann Cc: Maximilian Attems Cc: Michal Marek Cc: H. Peter Anvin Cc: Paul Bolle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 1fd980cc481b..e60a745ac198 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -10,6 +10,7 @@ #define IND_INDIRECTION (1 << IND_INDIRECTION_BIT) #define IND_DONE (1 << IND_DONE_BIT) #define IND_SOURCE (1 << IND_SOURCE_BIT) +#define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE) #if !defined(__ASSEMBLY__) -- cgit v1.2.3 From 7647f14fe4cd98151f8e90656c01fe61044de714 Mon Sep 17 00:00:00 2001 From: John de la Garza Date: Tue, 17 Feb 2015 13:46:04 -0800 Subject: lib/rbtree.c: fix typo in comment Signed-off-by: John de la Garza Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 57e75ae9910f..fb31765e935a 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -51,7 +51,7 @@ struct rb_root { #define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL) -/* 'empty' nodes are nodes that are known not to be inserted in an rbree */ +/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ ((node)->__rb_parent_color == (unsigned long)(node)) #define RB_CLEAR_NODE(node) \ -- cgit v1.2.3 From 9cff8adeaa34b5d2802f03f89803da57856b3b72 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 13 Feb 2015 15:49:17 +1100 Subject: sched: Prevent recursion in io_schedule() io_schedule() calls blk_flush_plug() which, depending on the contents of current->plug, can initiate arbitrary blk-io requests. Note that this contrasts with blk_schedule_flush_plug() which requires all non-trivial work to be handed off to a separate thread. This makes it possible for io_schedule() to recurse, and initiating block requests could possibly call mempool_alloc() which, in times of memory pressure, uses io_schedule(). Apart from any stack usage issues, io_schedule() will not behave correctly when called recursively as delayacct_blkio_start() does not allow for repeated calls. So: - use ->in_iowait to detect recursion. Set it earlier, and restore it to the old value. - move the call to "raw_rq" after the call to blk_flush_plug(). As this is some sort of per-cpu thing, we want some chance that we are on the right CPU - When io_schedule() is called recurively, use blk_schedule_flush_plug() which cannot further recurse. - as this makes io_schedule() a lot more complex and as io_schedule() must match io_schedule_timeout(), but all the changes in io_schedule_timeout() and make io_schedule a simple wrapper for that. Signed-off-by: NeilBrown Signed-off-by: Peter Zijlstra (Intel) [ Moved the now rudimentary io_schedule() into sched.h. ] Cc: Jens Axboe Cc: Linus Torvalds Cc: Tony Battersby Link: http://lkml.kernel.org/r/20150213162600.059fffb2@notabene.brown Signed-off-by: Ingo Molnar --- include/linux/sched.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8db31ef98d2f..cb5cdc777c8a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -363,9 +363,6 @@ extern void show_regs(struct pt_regs *); */ extern void show_stack(struct task_struct *task, unsigned long *sp); -void io_schedule(void); -long io_schedule_timeout(long timeout); - extern void cpu_init (void); extern void trap_init(void); extern void update_process_times(int user); @@ -422,6 +419,13 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +extern long io_schedule_timeout(long timeout); + +static inline void io_schedule(void) +{ + io_schedule_timeout(MAX_SCHEDULE_TIMEOUT); +} + struct nsproxy; struct user_namespace; -- cgit v1.2.3 From 2e65d8bfe80be51af2f84c904f85bac1437a5545 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Thu, 12 Feb 2015 14:58:29 +0100 Subject: clk: Add __clk_hw_set_clk helper function After the clk API change to return a per-user clock instance, both the struct clk_core and struct clk pointers from the hw clock needs to be assigned to clock that share the same state. In the future the struct clk_core will be removed and this is going to change again so to avoid having to change the assignments twice in all the drivers, add a helper function to have an indirection level. Signed-off-by: Javier Martinez Canillas Reviewed-by: Stephen Boyd Signed-off-by: Michael Turquette --- include/linux/clk-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 17dd6e9439d1..5591ea71a8d1 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -590,6 +590,12 @@ long __clk_mux_determine_rate_closest(struct clk_hw *hw, unsigned long rate, unsigned long *best_parent_rate, struct clk_hw **best_parent_p); +static inline void __clk_hw_set_clk(struct clk_hw *dst, struct clk_hw *src) +{ + dst->clk = src->clk; + dst->core = src->core; +} + /* * FIXME clock api without lock protection */ -- cgit v1.2.3 From 79969dd12e8756f64a999992c0536ccd91bf6e54 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 18 Feb 2015 11:30:18 -0800 Subject: NFSv4.1: Clean up create_session Don't decode directly into the shared struct session Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9a39132fda49..1af12fc16e98 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1185,6 +1185,8 @@ struct nfs41_exchange_id_res { struct nfs41_create_session_args { struct nfs_client *client; + u64 clientid; + uint32_t seqid; uint32_t flags; uint32_t cb_program; struct nfs4_channel_attrs fc_attrs; /* Fore Channel */ @@ -1192,7 +1194,11 @@ struct nfs41_create_session_args { }; struct nfs41_create_session_res { - struct nfs_client *client; + struct nfs4_sessionid sessionid; + uint32_t seqid; + uint32_t flags; + struct nfs4_channel_attrs fc_attrs; /* Fore Channel */ + struct nfs4_channel_attrs bc_attrs; /* Back Channel */ }; struct nfs41_reclaim_complete_args { -- cgit v1.2.3 From 71a097c6de9a49afd0f96b3ecef70c4eb04efde7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 18 Feb 2015 09:27:18 -0800 Subject: NFSv4.1: Clean up bind_conn_to_session We don't need to fake up an entire session in order retrieve the arguments. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 1af12fc16e98..4cb3eaa89cf7 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1167,8 +1167,15 @@ struct nfs41_impl_id { struct nfstime4 date; }; +struct nfs41_bind_conn_to_session_args { + struct nfs_client *client; + struct nfs4_sessionid sessionid; + u32 dir; + bool use_conn_in_rdma_mode; +}; + struct nfs41_bind_conn_to_session_res { - struct nfs4_session *session; + struct nfs4_sessionid sessionid; u32 dir; bool use_conn_in_rdma_mode; }; -- cgit v1.2.3 From 7a6fdeb2b1e93548854063c46c9724458564c76b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 22 Dec 2014 19:14:26 +0300 Subject: libceph: nuke pool op infrastructure On Mon, Dec 22, 2014 at 5:35 PM, Sage Weil wrote: > On Mon, 22 Dec 2014, Ilya Dryomov wrote: >> Actually, pool op stuff has been unused for over two years - looks like >> it was added for rbd create_snap and that got ripped out in 2012. It's >> unlikely we'd ever need to manage pools or snaps from the kernel client >> so I think it makes sense to nuke it. Sage? > > Yep! Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 36 ------------------------------------ include/linux/ceph/mon_client.h | 9 +-------- 2 files changed, 1 insertion(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index c0dadaac26e3..69e2c9e2305b 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -158,17 +158,6 @@ enum { }; -/* pool operations */ -enum { - POOL_OP_CREATE = 0x01, - POOL_OP_DELETE = 0x02, - POOL_OP_AUID_CHANGE = 0x03, - POOL_OP_CREATE_SNAP = 0x11, - POOL_OP_DELETE_SNAP = 0x12, - POOL_OP_CREATE_UNMANAGED_SNAP = 0x21, - POOL_OP_DELETE_UNMANAGED_SNAP = 0x22, -}; - struct ceph_mon_request_header { __le64 have_version; __le16 session_mon; @@ -191,31 +180,6 @@ struct ceph_mon_statfs_reply { struct ceph_statfs st; } __attribute__ ((packed)); -const char *ceph_pool_op_name(int op); - -struct ceph_mon_poolop { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; - __le32 pool; - __le32 op; - __le64 auid; - __le64 snapid; - __le32 name_len; -} __attribute__ ((packed)); - -struct ceph_mon_poolop_reply { - struct ceph_mon_request_header monhdr; - struct ceph_fsid fsid; - __le32 reply_code; - __le32 epoch; - char has_data; - char data[0]; -} __attribute__ ((packed)); - -struct ceph_mon_unmanaged_snap { - __le64 snapid; -} __attribute__ ((packed)); - struct ceph_osd_getmap { struct ceph_mon_request_header monhdr; struct ceph_fsid fsid; diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index deb47e45ac7c..81810dc21f06 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -40,7 +40,7 @@ struct ceph_mon_request { }; /* - * ceph_mon_generic_request is being used for the statfs, poolop and + * ceph_mon_generic_request is being used for the statfs and * mon_get_version requests which are being done a bit differently * because we need to get data back to the caller */ @@ -50,7 +50,6 @@ struct ceph_mon_generic_request { struct rb_node node; int result; void *buf; - int buf_len; struct completion completion; struct ceph_msg *request; /* original request */ struct ceph_msg *reply; /* and reply */ @@ -117,10 +116,4 @@ extern int ceph_monc_open_session(struct ceph_mon_client *monc); extern int ceph_monc_validate_auth(struct ceph_mon_client *monc); -extern int ceph_monc_create_snapid(struct ceph_mon_client *monc, - u32 pool, u64 *snapid); - -extern int ceph_monc_delete_snapid(struct ceph_mon_client *monc, - u32 pool, u64 snapid); - #endif -- cgit v1.2.3 From 03f4fcb02884859b584c709652bb48f8125ceb45 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 5 Jan 2015 11:04:04 +0800 Subject: ceph: handle SESSION_FORCE_RO message mark session as readonly and wake up all cap waiters. Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 69e2c9e2305b..31eb03d0c766 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -271,6 +271,7 @@ enum { CEPH_SESSION_RECALL_STATE, CEPH_SESSION_FLUSHMSG, CEPH_SESSION_FLUSHMSG_ACK, + CEPH_SESSION_FORCE_RO, }; extern const char *ceph_session_op_name(int op); -- cgit v1.2.3 From ba988f87f532cd2b8c4740aa8ec49056521ae833 Mon Sep 17 00:00:00 2001 From: Chaitanya Huilgol Date: Fri, 23 Jan 2015 16:41:25 +0530 Subject: libceph: tcp_nodelay support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit TCP_NODELAY socket option set on connection sockets, disables Nagle’s algorithm and improves latency characteristics. tcp_nodelay(default)/notcp_nodelay option flags provided to enable/disable setting the socket option. Signed-off-by: Chaitanya Huilgol [idryomov@redhat.com: NO_TCP_NODELAY -> TCP_NODELAY, minor adjustments] Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 3 ++- include/linux/ceph/messenger.h | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 8b11a79ca1cb..16fff9608848 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -30,8 +30,9 @@ #define CEPH_OPT_MYIP (1<<2) /* specified my ip */ #define CEPH_OPT_NOCRC (1<<3) /* no data crc on writes */ #define CEPH_OPT_NOMSGAUTH (1<<4) /* not require cephx message signature */ +#define CEPH_OPT_TCP_NODELAY (1<<5) /* TCP_NODELAY on TCP sockets */ -#define CEPH_OPT_DEFAULT (0) +#define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) #define ceph_set_opt(client, opt) \ (client)->options->flags |= CEPH_OPT_##opt; diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index d9d396c16503..e15499422fdc 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -57,6 +57,7 @@ struct ceph_messenger { atomic_t stopping; bool nocrc; + bool tcp_nodelay; /* * the global_seq counts connections i (attempt to) initiate @@ -264,7 +265,8 @@ extern void ceph_messenger_init(struct ceph_messenger *msgr, struct ceph_entity_addr *myaddr, u64 supported_features, u64 required_features, - bool nocrc); + bool nocrc, + bool tcp_nodelay); extern void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, -- cgit v1.2.3 From f7d4ca8bbfda23b4f1eae9b6757ff64166b093d5 Mon Sep 17 00:00:00 2001 From: Daniel Thompson Date: Fri, 7 Nov 2014 18:37:57 +0000 Subject: kdb: Avoid printing KERN_ levels to consoles Currently when kdb traps printk messages then the raw log level prefix (consisting of '\001' followed by a numeral) does not get stripped off before the message is issued to the various I/O handlers supported by kdb. This causes annoying visual noise as well as causing problems grepping for ^. It is also a change of behaviour compared to normal usage of printk() usage. For example -h ends up with different output to that of kdb's "sr h". This patch addresses the problem by stripping log levels from messages before they are issued to the I/O handlers. printk() which can also act as an i/o handler in some cases is special cased; if the caller provided a log level then the prefix will be preserved when sent to printk(). The addition of non-printable characters to the output of kdb commands is a regression, albeit and extremely elderly one, introduced by commit 04d2c8c83d0e ("printk: convert the format for KERN_ to a 2 byte pattern"). Note also that this patch does *not* restore the original behaviour from v3.5. Instead it makes printk() from within a kdb command display the message without any prefix (i.e. like printk() normally does). Signed-off-by: Daniel Thompson Cc: Joe Perches Cc: stable@vger.kernel.org Signed-off-by: Jason Wessel --- include/linux/kdb.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 75ae2e2631fc..a19bcf9e762e 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -156,8 +156,14 @@ typedef enum { KDB_REASON_SYSTEM_NMI, /* In NMI due to SYSTEM cmd; regs valid */ } kdb_reason_t; +enum kdb_msgsrc { + KDB_MSGSRC_INTERNAL, /* direct call to kdb_printf() */ + KDB_MSGSRC_PRINTK, /* trapped from printk() */ +}; + extern int kdb_trap_printk; -extern __printf(1, 0) int vkdb_printf(const char *fmt, va_list args); +extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt, + va_list args); extern __printf(1, 2) int kdb_printf(const char *, ...); typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); -- cgit v1.2.3 From e1e5e5641e6f271321aec257ed26a72715e4a8c2 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 19 Feb 2015 13:39:03 -0700 Subject: NVMe: Metadata format support Adds support for NVMe metadata formats and exposes block devices for all namespaces regardless of their format. Namespace formats that are unusable will have disk capacity set to 0, but a handle to the block device is created to simplify device management. A namespace is not usable when the format requires host interleave block and metadata in single buffer, has no provisioned storage, or has better data but failed to register with blk integrity. The namespace has to be scanned in two phases to support separate metadata formats. The first establishes the sector size and capacity prior to invoking add_disk. If metadata is required, the capacity will be temporarilly set to 0 until it can be revalidated and registered with the integrity extenstions after add_disk completes. The driver relies on the integrity extensions to provide the metadata buffer. NVMe requires this be a single physically contiguous region, so only one integrity segment is allowed per command. If the metadata is used for T10 PI, the driver provides mappings to save and restore the reftag physical block translation. The driver provides no-op functions for generate and verify if metadata is not used for protection information. This way the setup is always provided by the block layer. If a request does not supply a required metadata buffer, the command is failed with bad address. This could only happen if a user manually disables verify/generate on such a disk. The only exception to where this is okay is if the controller is capable of stripping/generating the metadata, which is possible on some types of formats. The metadata scatter gather list now occupies the spot in the nvme_iod that used to be used to link retryable IOD's, but we don't do that anymore, so the field was unused. Signed-off-by: Keith Busch --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 19a5d4b23209..cca264db2478 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -121,6 +121,7 @@ struct nvme_ns { unsigned ns_id; int lba_shift; int ms; + int pi_type; u64 mode_select_num_blocks; u32 mode_select_block_len; }; @@ -138,6 +139,7 @@ struct nvme_iod { int nents; /* Used in scatterlist */ int length; /* Of data, in bytes */ dma_addr_t first_dma; + struct scatterlist meta_sg[1]; /* metadata requires single contiguous buffer */ struct scatterlist sg[0]; }; -- cgit v1.2.3 From 4f1982b4e262c45475a91b4253e9bc7f7c991c13 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 19 Feb 2015 13:42:14 -0700 Subject: NVMe: Update SCSI Inquiry VPD 83h translation The original translation created collisions on Inquiry VPD 83 for many existing devices. Newer specifications provide other ways to translate based on the device's version can be used to create unique identifiers. Version 1.1 provides an EUI64 field that uniquely identifies each namespace, and 1.2 added the longer NGUID field for the same reason. Both follow the IEEE EUI format and readily translate to the SCSI device identification EUI designator type 2h. For devices implementing either, the translation will use this type, defaulting to the EUI64 8-byte type if implemented then NGUID's 16 byte version if not. If neither are provided, the 1.0 translation is used, and is updated to use the SCSI String format to guarantee a unique identifier. Knowing when to use the new fields depends on the nvme controller's revision. The NVME_VS macro was not decoding this correctly, so that is fixed in this patch and moved to a more appropriate place. Since the Identify Namespace structure required an update for the NGUID field, this patch adds the remaining new 1.2 fields to the structure. Signed-off-by: Keith Busch --- include/linux/nvme.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index cca264db2478..1f062a9e521d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -62,8 +62,6 @@ enum { NVME_CSTS_SHST_MASK = 3 << 2, }; -#define NVME_VS(major, minor) (major << 16 | minor) - extern unsigned char nvme_io_timeout; #define NVME_IO_TIMEOUT (nvme_io_timeout * HZ) -- cgit v1.2.3 From b3fffdefabab266ae5176a136d93b6670b07bb30 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 3 Feb 2015 11:21:42 -0700 Subject: NVMe: Register management handle under nvme class This creates a new class type for nvme devices to register their management character devices with. This is so we do not rely on miscdev to provide enough minors for as many nvme devices some people plan to use. The previous limit was approximately 60 NVMe controllers, depending on the platform and kernel. Now the limit is 1M, which ought to be enough for anybody. Since we have a new device class, it makes sense to attach the block devices under this as well, so part of this patch moves the management handle initialization prior to the namespaces discovery. Signed-off-by: Keith Busch --- include/linux/nvme.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 1f062a9e521d..383d495c5e4c 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -17,7 +17,6 @@ #include #include -#include #include #include @@ -89,7 +88,7 @@ struct nvme_dev { struct nvme_bar __iomem *bar; struct list_head namespaces; struct kref kref; - struct miscdevice miscdev; + struct device *device; work_func_t reset_workfn; struct work_struct reset_work; char name[12]; -- cgit v1.2.3 From 2e1d8448196ba85cd78a18723413a3c92aabe0f3 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 12 Feb 2015 15:33:00 -0700 Subject: NVMe: Asynchronous controller probe This performs the longest parts of nvme device probe in scheduled work. This speeds up probe significantly when multiple devices are in use. Signed-off-by: Keith Busch --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 383d495c5e4c..e2429e8cdab4 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -91,6 +91,7 @@ struct nvme_dev { struct device *device; work_func_t reset_workfn; struct work_struct reset_work; + struct work_struct probe_work; char name[12]; char serial[20]; char model[40]; -- cgit v1.2.3 From 07836e659c81ec6b0d683dfbf7958339a22a7b69 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 19 Feb 2015 10:34:48 -0700 Subject: NVMe: Fix potential corruption during shutdown The driver has to end unreturned commands at some point even if the controller has not provided a completion. The driver tried to be safe by deleting IO queues prior to ending all unreturned commands. That should cause the controller to internally abort inflight commands, but IO queue deletion request does not have to be successful, so all bets are off. We still have to make progress, so to be extra safe, this patch doesn't clear a queue to release the dma mapping for a command until after the pci device has been disabled. This patch removes the special handling during device initialization so controller recovery can be done all the time. This is possible since initialization is not inlined with pci probe anymore. Reported-by: Nilish Choudhury Signed-off-by: Keith Busch --- include/linux/nvme.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index e2429e8cdab4..0adad4a5419b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -103,7 +103,6 @@ struct nvme_dev { u16 abort_limit; u8 event_limit; u8 vwc; - u8 initialized; }; /* -- cgit v1.2.3 From 846cd66788b11105a62785078360c8854aa98310 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 18 Feb 2015 11:38:06 +0100 Subject: net: Initialize all members in skb_gro_remcsum_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit skb_gro_remcsum_init() initializes the gro_remcsum.delta member only, leading to compiler warnings about a possibly uninitialized gro_remcsum.offset member: drivers/net/vxlan.c: In function ‘vxlan_gro_receive’: drivers/net/vxlan.c:602: warning: ‘grc.offset’ may be used uninitialized in this function net/ipv4/fou.c: In function ‘gue_gro_receive’: net/ipv4/fou.c:262: warning: ‘grc.offset’ may be used uninitialized in this function While these are harmless for now: - skb_gro_remcsum_process() sets offset before changing delta, - skb_gro_remcsum_cleanup() checks if delta is non-zero before accessing offset, it's safer to let the initialization function initialize all members. Signed-off-by: Geert Uytterhoeven Acked-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5897b4ea5a3f..429d1790a27e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2342,6 +2342,7 @@ struct gro_remcsum { static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) { + grc->offset = 0; grc->delta = 0; } -- cgit v1.2.3 From dd36929720f40f17685e841ae0d4c581c165ea60 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 20 Feb 2015 15:46:31 -0800 Subject: kernel: make READ_ONCE() valid on const arguments The use of READ_ONCE() causes lots of warnings witht he pending paravirt spinlock fixes, because those ends up having passing a member to a 'const' structure to READ_ONCE(). There should certainly be nothing wrong with using READ_ONCE() with a const source, but the helper function __read_once_size() would cause warnings because it would drop the 'const' qualifier, but also because the destination would be marked 'const' too due to the use of 'typeof'. Use a union of types in READ_ONCE() to avoid this issue. Also make sure to use parenthesis around the macro arguments to avoid possible operator precedence issues. Tested-by: Ingo Molnar Cc: Christian Borntraeger Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index d1ec10a940ff..1b45e4a0519b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -202,7 +202,7 @@ static __always_inline void data_access_exceeds_word_size(void) { } -static __always_inline void __read_once_size(volatile void *p, void *res, int size) +static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { switch (size) { case 1: *(__u8 *)res = *(volatile __u8 *)p; break; @@ -259,10 +259,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s */ #define READ_ONCE(x) \ - ({ typeof(x) __val; __read_once_size(&x, &__val, sizeof(__val)); __val; }) + ({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; }) #define WRITE_ONCE(x, val) \ - ({ typeof(x) __val; __val = val; __write_once_size(&x, &__val, sizeof(__val)); __val; }) + ({ typeof(x) __val = (val); __write_once_size(&(x), &__val, sizeof(__val)); __val; }) #endif /* __KERNEL__ */ -- cgit v1.2.3 From b9ebafbe8cfeeddec881504c446cccd0d87a51b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Feb 2015 06:48:57 -0800 Subject: rhashtable: ensure cache line alignment on bucket_table struct bucket_table contains mostly read fields : size, locks_mask, locks. Make sure these are not sharing a cache line with buckets[] Signed-off-by: Eric Dumazet Acked-by: Daniel Borkmann Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 58851275fed9..cb2104be2135 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -54,10 +54,11 @@ struct rhash_head { * @buckets: size * hash buckets */ struct bucket_table { - size_t size; - unsigned int locks_mask; - spinlock_t *locks; - struct rhash_head __rcu *buckets[]; + size_t size; + unsigned int locks_mask; + spinlock_t *locks; + + struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -- cgit v1.2.3 From 155e35d4daa804582f75acaa2c74ec797a89c615 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 29 Jan 2015 12:02:27 +0000 Subject: VFS: Introduce inode-getting helpers for layered/unioned fs environments Introduce some function for getting the inode (and also the dentry) in an environment where layered/unioned filesystems are in operation. The problem is that we have places where we need *both* the union dentry and the lower source or workspace inode or dentry available, but we can only have a handle on one of them. Therefore we need to derive the handle to the other from that. The idea is to introduce an extra field in struct dentry that allows the union dentry to refer to and pin the lower dentry. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 92c08cf7670e..047c0db5763f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -464,4 +464,61 @@ static inline unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, 100); } + +/** + * d_inode - Get the actual inode of this dentry + * @dentry: The dentry to query + * + * This is the helper normal filesystems should use to get at their own inodes + * in their own dentries and ignore the layering superimposed upon them. + */ +static inline struct inode *d_inode(const struct dentry *dentry) +{ + return dentry->d_inode; +} + +/** + * d_inode_rcu - Get the actual inode of this dentry with ACCESS_ONCE() + * @dentry: The dentry to query + * + * This is the helper normal filesystems should use to get at their own inodes + * in their own dentries and ignore the layering superimposed upon them. + */ +static inline struct inode *d_inode_rcu(const struct dentry *dentry) +{ + return ACCESS_ONCE(dentry->d_inode); +} + +/** + * d_backing_inode - Get upper or lower inode we should be using + * @upper: The upper layer + * + * This is the helper that should be used to get at the inode that will be used + * if this dentry were to be opened as a file. The inode may be on the upper + * dentry or it may be on a lower dentry pinned by the upper. + * + * Normal filesystems should not use this to access their own inodes. + */ +static inline struct inode *d_backing_inode(const struct dentry *upper) +{ + struct inode *inode = upper->d_inode; + + return inode; +} + +/** + * d_backing_dentry - Get upper or lower dentry we should be using + * @upper: The upper layer + * + * This is the helper that should be used to get the dentry of the inode that + * will be used if this dentry were opened as a file. It may be the upper + * dentry or it may be a lower dentry pinned by the upper. + * + * Normal filesystems should not use this to access their own dentries. + */ +static inline struct dentry *d_backing_dentry(struct dentry *upper) +{ + return upper; +} + #endif /* __LINUX_DCACHE_H */ -- cgit v1.2.3 From e7f7d2253c05143ed76ddc5e11f4cf0a9b814a27 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 29 Jan 2015 12:02:27 +0000 Subject: VFS: Add a whiteout dentry type Add DCACHE_WHITEOUT_TYPE and provide a d_is_whiteout() accessor function. A d_is_miss() accessor is also added for ordinary cache misses and d_is_negative() is modified to indicate either an ordinary miss or an enforced miss (whiteout). Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 047c0db5763f..98d2a948a08e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -215,11 +215,12 @@ struct dentry_operations { #define DCACHE_LRU_LIST 0x00080000 #define DCACHE_ENTRY_TYPE 0x00700000 -#define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry */ -#define DCACHE_DIRECTORY_TYPE 0x00100000 /* Normal directory */ -#define DCACHE_AUTODIR_TYPE 0x00200000 /* Lookupless directory (presumed automount) */ -#define DCACHE_SYMLINK_TYPE 0x00300000 /* Symlink */ -#define DCACHE_FILE_TYPE 0x00400000 /* Other file type */ +#define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry (maybe fallthru to nowhere) */ +#define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ +#define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ +#define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ +#define DCACHE_SYMLINK_TYPE 0x00400000 /* Symlink (or fallthru to such) */ +#define DCACHE_FILE_TYPE 0x00500000 /* Other file type (or fallthru to such) */ #define DCACHE_MAY_FREE 0x00800000 @@ -423,6 +424,16 @@ static inline unsigned __d_entry_type(const struct dentry *dentry) return dentry->d_flags & DCACHE_ENTRY_TYPE; } +static inline bool d_is_miss(const struct dentry *dentry) +{ + return __d_entry_type(dentry) == DCACHE_MISS_TYPE; +} + +static inline bool d_is_whiteout(const struct dentry *dentry) +{ + return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; +} + static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; @@ -450,7 +461,8 @@ static inline bool d_is_file(const struct dentry *dentry) static inline bool d_is_negative(const struct dentry *dentry) { - return __d_entry_type(dentry) == DCACHE_MISS_TYPE; + // TODO: check d_is_whiteout(dentry) also. + return d_is_miss(dentry); } static inline bool d_is_positive(const struct dentry *dentry) -- cgit v1.2.3 From df1a085af1f652a02238168c4f2b730c8c90dd4a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 29 Jan 2015 12:02:28 +0000 Subject: VFS: Add a fallthrough flag for marking virtual dentries Add a DCACHE_FALLTHRU flag to indicate that, in a layered filesystem, this is a virtual dentry that covers another one in a lower layer that should be used instead. This may be recorded on medium if directory integration is stored there. The flag can be set with d_set_fallthru() and tested with d_is_fallthru(). Original-author: Valerie Aurora Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 98d2a948a08e..728f5d31b5e6 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -223,6 +223,7 @@ struct dentry_operations { #define DCACHE_FILE_TYPE 0x00500000 /* Other file type (or fallthru to such) */ #define DCACHE_MAY_FREE 0x00800000 +#define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ extern seqlock_t rename_lock; @@ -470,6 +471,14 @@ static inline bool d_is_positive(const struct dentry *dentry) return !d_is_negative(dentry); } +extern void d_set_fallthru(struct dentry *dentry); + +static inline bool d_is_fallthru(const struct dentry *dentry) +{ + return dentry->d_flags & DCACHE_FALLTHRU; +} + + extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) -- cgit v1.2.3 From 44bdb5e5f6382ba88f7678d6f535f879324522ae Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 29 Jan 2015 12:02:29 +0000 Subject: VFS: Split DCACHE_FILE_TYPE into regular and special types Split DCACHE_FILE_TYPE into DCACHE_REGULAR_TYPE (dentries representing regular files) and DCACHE_SPECIAL_TYPE (representing blockdev, chardev, FIFO and socket files). d_is_reg() and d_is_special() are added to detect these subtypes and d_is_file() is left as the union of the two. This allows a number of places that use S_ISREG(dentry->d_inode->i_mode) to use d_is_reg(dentry) instead. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 728f5d31b5e6..d8358799c594 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -219,8 +219,9 @@ struct dentry_operations { #define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ #define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ #define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ -#define DCACHE_SYMLINK_TYPE 0x00400000 /* Symlink (or fallthru to such) */ -#define DCACHE_FILE_TYPE 0x00500000 /* Other file type (or fallthru to such) */ +#define DCACHE_REGULAR_TYPE 0x00400000 /* Regular file type (or fallthru to such) */ +#define DCACHE_SPECIAL_TYPE 0x00500000 /* Other file type (or fallthru to such) */ +#define DCACHE_SYMLINK_TYPE 0x00600000 /* Symlink (or fallthru to such) */ #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ @@ -455,9 +456,19 @@ static inline bool d_is_symlink(const struct dentry *dentry) return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } +static inline bool d_is_reg(const struct dentry *dentry) +{ + return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; +} + +static inline bool d_is_special(const struct dentry *dentry) +{ + return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; +} + static inline bool d_is_file(const struct dentry *dentry) { - return __d_entry_type(dentry) == DCACHE_FILE_TYPE; + return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) -- cgit v1.2.3 From 12ca7188468ee29c4e717f73db4bf43c90954fc7 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 13 Feb 2015 19:28:02 -0600 Subject: thermal: Introduce dummy functions when thermal is not defined When CONFIG_THERMAL is not enabled, it is better to introduce equivalent dummy functions in the exported header than to introduce #ifdeffery in drivers using the function. This will prevent issues such as that reported in: http://www.spinics.net/lists/linux-next/msg31573.html While at it switch over to IS_ENABLED for thermal macros to allow for thermal framework to be built as framework and relevant APIs be usable by relevant drivers as a result. Reported-by: Guenter Roeck Signed-off-by: Nishanth Menon Signed-off-by: Eduardo Valentin --- include/linux/thermal.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 54 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index fc52e307efab..5eac316490ea 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -314,6 +314,8 @@ void thermal_zone_of_sensor_unregister(struct device *dev, } #endif + +#if IS_ENABLED(CONFIG_THERMAL) struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, void *, struct thermal_zone_device_ops *, const struct thermal_zone_params *, int, int); @@ -340,8 +342,58 @@ struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, struct thermal_cooling_device *, int); void thermal_cdev_update(struct thermal_cooling_device *); void thermal_notify_framework(struct thermal_zone_device *, int); - -#ifdef CONFIG_NET +#else +static inline struct thermal_zone_device *thermal_zone_device_register( + const char *type, int trips, int mask, void *devdata, + struct thermal_zone_device_ops *ops, + const struct thermal_zone_params *tzp, + int passive_delay, int polling_delay) +{ return ERR_PTR(-ENODEV); } +static inline void thermal_zone_device_unregister( + struct thermal_zone_device *tz) +{ } +static inline int thermal_zone_bind_cooling_device( + struct thermal_zone_device *tz, int trip, + struct thermal_cooling_device *cdev, + unsigned long upper, unsigned long lower) +{ return -ENODEV; } +static inline int thermal_zone_unbind_cooling_device( + struct thermal_zone_device *tz, int trip, + struct thermal_cooling_device *cdev) +{ return -ENODEV; } +static inline void thermal_zone_device_update(struct thermal_zone_device *tz) +{ } +static inline struct thermal_cooling_device * +thermal_cooling_device_register(char *type, void *devdata, + const struct thermal_cooling_device_ops *ops) +{ return ERR_PTR(-ENODEV); } +static inline struct thermal_cooling_device * +thermal_of_cooling_device_register(struct device_node *np, + char *type, void *devdata, const struct thermal_cooling_device_ops *ops) +{ return ERR_PTR(-ENODEV); } +static inline void thermal_cooling_device_unregister( + struct thermal_cooling_device *cdev) +{ } +static inline struct thermal_zone_device *thermal_zone_get_zone_by_name( + const char *name) +{ return ERR_PTR(-ENODEV); } +static inline int thermal_zone_get_temp( + struct thermal_zone_device *tz, unsigned long *temp) +{ return -ENODEV; } +static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) +{ return -ENODEV; } +static inline struct thermal_instance * +get_thermal_instance(struct thermal_zone_device *tz, + struct thermal_cooling_device *cdev, int trip) +{ return ERR_PTR(-ENODEV); } +static inline void thermal_cdev_update(struct thermal_cooling_device *cdev) +{ } +static inline void thermal_notify_framework(struct thermal_zone_device *tz, + int trip) +{ } +#endif /* CONFIG_THERMAL */ + +#if defined(CONFIG_NET) && IS_ENABLED(CONFIG_THERMAL) extern int thermal_generate_netlink_event(struct thermal_zone_device *tz, enum events event); #else -- cgit v1.2.3 From 737eb0301f296d55c22350c6968ff1ef51bacb5f Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 20 Feb 2015 14:53:46 +0000 Subject: genirq / PM: better describe IRQF_NO_SUSPEND semantics The IRQF_NO_SUSPEND flag is intended to be used for interrupts required to be enabled during the suspend-resume cycle. This mostly consists of IPIs and timer interrupts, potentially including chained irqchip interrupts if these are necessary to handle timers or IPIs. If an interrupt does not fall into one of the aforementioned categories, requesting it with IRQF_NO_SUSPEND is likely incorrect. Using IRQF_NO_SUSPEND does not guarantee that the interrupt can wake the system from a suspended state. For an interrupt to be able to trigger a wakeup, it may be necessary to program various components of the system. In these cases it is necessary to use {enable,disabled}_irq_wake. Unfortunately, several drivers assume that IRQF_NO_SUSPEND ensures that an IRQ can wake up the system, and the documentation can be read ambiguously w.r.t. this property. This patch updates the documentation regarding IRQF_NO_SUSPEND to make this caveat explicit, hopefully making future misuse rarer. Cleanup of existing misuse will occur as part of later patch series. Signed-off-by: Mark Rutland Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- include/linux/interrupt.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index d9b05b5bf8c7..606771c7cac2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -52,7 +52,9 @@ * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the * irq line disabled until the threaded handler has been run. - * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend + * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend. Does not guarantee + * that this interrupt will wake the system from a suspended + * state. See Documentation/power/suspend-and-interrupts.txt * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device -- cgit v1.2.3 From bc4b1f486fe69b86769e07c8edce472327a8462b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Sun, 15 Feb 2015 11:57:53 +0700 Subject: Revert "USB: serial: make bulk_out_size a lower limit" This reverts commit 5083fd7bdfe6760577235a724cf6dccae13652c2. A bulk-out size smaller than the end-point size is indeed valid. The offending commit broke the usb-debug driver for EHCI debug devices, which use 8-byte buffers. Fixes: 5083fd7bdfe6 ("USB: serial: make bulk_out_size a lower limit") Reported-by: "Li, Elvin" Cc: stable # v3.15 Signed-off-by: Johan Hovold --- include/linux/usb/serial.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index 9bb547c7bce7..704a1ab8240c 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -190,8 +190,7 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data) * @num_ports: the number of different ports this device will have. * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer * (0 = end-point size) - * @bulk_out_size: minimum number of bytes to allocate for bulk-out buffer - * (0 = end-point size) + * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size) * @calc_num_ports: pointer to a function to determine how many ports this * device has dynamically. It will be called after the probe() * callback is called, but before attach() -- cgit v1.2.3 From 4c4b52d9b2df45e8216d3e30b5452e4a364d2cac Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 25 Feb 2015 16:31:54 +0100 Subject: rhashtable: remove indirection for grow/shrink decision functions Currently, all real users of rhashtable default their grow and shrink decision functions to rht_grow_above_75() and rht_shrink_below_30(), so that there's currently no need to have this explicitly selectable. It can/should be generic and private inside rhashtable until a real use case pops up. Since we can make this private, we'll save us this additional indirection layer and can improve insertion/deletion time as well. Reference: http://patchwork.ozlabs.org/patch/443040/ Suggested-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index cb2104be2135..d438eeb08bff 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -79,12 +79,6 @@ struct rhashtable; * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) * @hashfn: Function to hash key * @obj_hashfn: Function to hash object - * @grow_decision: If defined, may return true if table should expand - * @shrink_decision: If defined, may return true if table should shrink - * - * Note: when implementing the grow and shrink decision function, min/max - * shift must be enforced, otherwise, resizing watermarks they set may be - * useless. */ struct rhashtable_params { size_t nelem_hint; @@ -98,10 +92,6 @@ struct rhashtable_params { size_t locks_mul; rht_hashfn_t hashfn; rht_obj_hashfn_t obj_hashfn; - bool (*grow_decision)(const struct rhashtable *ht, - size_t new_size); - bool (*shrink_decision)(const struct rhashtable *ht, - size_t new_size); }; /** @@ -193,9 +183,6 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params); void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node); bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node); -bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size); -bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size); - int rhashtable_expand(struct rhashtable *ht); int rhashtable_shrink(struct rhashtable *ht); -- cgit v1.2.3 From 140e049c64ce848392adbf4678983ecc76888dde Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 26 Feb 2015 17:42:42 -0500 Subject: NFS: Add a helper to set attribute barriers Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 2f77e0c651c8..3a4ffb5856cd 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -369,6 +369,7 @@ extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ct extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx); extern u64 nfs_compat_user_ino64(u64 fileid); extern void nfs_fattr_init(struct nfs_fattr *fattr); +extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); -- cgit v1.2.3 From f044636d972246d451e06226cc1675d5da389762 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 26 Feb 2015 16:09:04 -0500 Subject: NFS: Add attribute update barriers to nfs_setattr_update_inode() Ensure that other operations which raced with our setattr RPC call cannot revert the file attribute changes that were made on the server. To do so, we artificially bump the attribute generation counter on the inode so that all calls to nfs_fattr_init() that precede ours will be dropped. The motivation for the patch came from Chuck Lever's reports of readaheads racing with truncate operations and causing the file size to be reverted. Reported-by: Chuck Lever Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- include/linux/nfs_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 3a4ffb5856cd..f26e64e0aff8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -356,7 +356,7 @@ extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *ino extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); -extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); +extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); -- cgit v1.2.3 From a08a8cd375db9769588257e7782f6b6b68561b88 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 26 Feb 2015 17:36:09 -0500 Subject: NFS: Add attribute update barriers to NFS writebacks Ensure that other operations that race with our write RPC calls cannot revert the file size updates that were made on the server. Signed-off-by: Trond Myklebust Tested-by: Chuck Lever --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f26e64e0aff8..59b1516b9fd4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -343,6 +343,7 @@ extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); +extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); -- cgit v1.2.3 From f5956fafb00afab474c3886b6297f9b5e7aff722 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Mon, 2 Mar 2015 18:22:15 +0200 Subject: net/mlx4_core: Fix wrong mask and error flow for the update-qp command The bit mask for currently supported driver features (MLX4_UPDATE_QP_SUPPORTED_ATTRS) of the update-qp command was defined twice (using enum value and pre-processor define directive) and wrong. The return value of the call to mlx4_update_qp() from within the SRIOV resource-tracker was wrongly voided down. Fix both issues. issue: none Fixes: 09e05c3f78e9 ('net/mlx4: Set vlan stripping policy by the right command') Fixes: ce8d9e0d6746 ('net/mlx4_core: Add UPDATE_QP SRIOV wrapper support') Signed-off-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/qp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 2bbc62aa818a..551f85456c11 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -427,7 +427,7 @@ struct mlx4_wqe_inline_seg { enum mlx4_update_qp_attr { MLX4_UPDATE_QP_SMAC = 1 << 0, - MLX4_UPDATE_QP_VSD = 1 << 2, + MLX4_UPDATE_QP_VSD = 1 << 1, MLX4_UPDATE_QP_SUPPORTED_ATTRS = (1 << 2) - 1 }; -- cgit v1.2.3 From 874f946376de57c8d6230b30ad71f742883fee3a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 2 Mar 2015 23:32:08 -0500 Subject: NFS: Fix a regression in the read() syscall When invalidating the page cache for a regular file, we want to first sync all dirty data to disk and then call invalidate_inode_pages2(). The latter relies on nfs_launder_page() and nfs_release_page() to deal respectively with dirty pages, and unstable written pages. When commit 9590544694bec ("NFS: avoid deadlocks with loop-back mounted NFS filesystems.") changed the behaviour of nfs_release_page(), then it made it possible for invalidate_inode_pages2() to fail with an EBUSY. Unfortunately, that error is then propagated back to read(). Let's therefore work around the problem for now by protecting the call to sync the data and invalidate_inode_pages2() so that they are atomic w.r.t. the addition of new writes. Later on, we can revisit whether or not we still need nfs_launder_page() and nfs_release_page(). Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 59b1516b9fd4..b01ccf371fdc 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -356,6 +356,7 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); +extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, -- cgit v1.2.3 From 17f480342026e54000731acaa69bf32787ce46cb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 27 Feb 2015 00:07:55 +0100 Subject: genirq / PM: Add flag for shared NO_SUSPEND interrupt lines It currently is required that all users of NO_SUSPEND interrupt lines pass the IRQF_NO_SUSPEND flag when requesting the IRQ or the WARN_ON_ONCE() in irq_pm_install_action() will trigger. That is done to warn about situations in which unprepared interrupt handlers may be run unnecessarily for suspended devices and may attempt to access those devices by mistake. However, it may cause drivers that have no technical reasons for using IRQF_NO_SUSPEND to set that flag just because they happen to share the interrupt line with something like a timer. Moreover, the generic handling of wakeup interrupts introduced by commit 9ce7a25849e8 (genirq: Simplify wakeup mechanism) only works for IRQs without any NO_SUSPEND users, so the drivers of wakeup devices needing to use shared NO_SUSPEND interrupt lines for signaling system wakeup generally have to detect wakeup in their interrupt handlers. Thus if they happen to share an interrupt line with a NO_SUSPEND user, they also need to request that their interrupt handlers be run after suspend_device_irqs(). In both cases the reason for using IRQF_NO_SUSPEND is not because the driver in question has a genuine need to run its interrupt handler after suspend_device_irqs(), but because it happens to share the line with some other NO_SUSPEND user. Otherwise, the driver would do without IRQF_NO_SUSPEND just fine. To make it possible to specify that condition explicitly, introduce a new IRQ action handler flag for shared IRQs, IRQF_COND_SUSPEND, that, when set, will indicate to the IRQ core that the interrupt user is generally fine with suspending the IRQ, but it also can tolerate handler invocations after suspend_device_irqs() and, in particular, it is capable of detecting system wakeup and triggering it as appropriate from its interrupt handler. That will allow us to work around a problem with a shared timer interrupt line on at91 platforms. Link: http://marc.info/?l=linux-kernel&m=142252777602084&w=2 Link: http://marc.info/?t=142252775300011&r=1&w=2 Link: https://lkml.org/lkml/2014/12/15/552 Reported-by: Boris Brezillon Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) Acked-by: Mark Rutland --- include/linux/interrupt.h | 5 +++++ include/linux/irqdesc.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 606771c7cac2..2e88580194f0 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -59,6 +59,10 @@ * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device * resume time. + * IRQF_COND_SUSPEND - If the IRQ is shared with a NO_SUSPEND user, execute this + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. */ #define IRQF_DISABLED 0x00000020 #define IRQF_SHARED 0x00000080 @@ -72,6 +76,7 @@ #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 +#define IRQF_COND_SUSPEND 0x00040000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index faf433af425e..dd1109fb241e 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -78,6 +78,7 @@ struct irq_desc { #ifdef CONFIG_PM_SLEEP unsigned int nr_actions; unsigned int no_suspend_depth; + unsigned int cond_suspend_depth; unsigned int force_resume_depth; #endif #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From ef2b22ac540c018bd574d1846ab95b9bfcf38702 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 2 Mar 2015 22:26:55 +0100 Subject: cpuidle / sleep: Use broadcast timer for states that stop local timer Commit 381063133246 (PM / sleep: Re-implement suspend-to-idle handling) overlooked the fact that entering some sufficiently deep idle states by CPUs may cause their local timers to stop and in those cases it is necessary to switch over to a broadcast timer prior to entering the idle state. If the cpuidle driver in use does not provide the new ->enter_freeze callback for any of the idle states, that problem affects suspend-to-idle too, but it is not taken into account after the changes made by commit 381063133246. Fix that by changing the definition of cpuidle_enter_freeze() and re-arranging of the code in cpuidle_idle_call(), so the former does not call cpuidle_enter() any more and the fallback case is handled by cpuidle_idle_call() directly. Fixes: 381063133246 (PM / sleep: Re-implement suspend-to-idle handling) Reported-and-tested-by: Lorenzo Pieralisi Signed-off-by: Rafael J. Wysocki Acked-by: Peter Zijlstra (Intel) --- include/linux/cpuidle.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index f551a9299ac9..306178d7309f 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -126,6 +126,8 @@ struct cpuidle_driver { #ifdef CONFIG_CPU_IDLE extern void disable_cpuidle(void); +extern bool cpuidle_not_available(struct cpuidle_driver *drv, + struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev); @@ -150,11 +152,17 @@ extern void cpuidle_resume(void); extern int cpuidle_enable_device(struct cpuidle_device *dev); extern void cpuidle_disable_device(struct cpuidle_device *dev); extern int cpuidle_play_dead(void); -extern void cpuidle_enter_freeze(void); +extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev); +extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, + struct cpuidle_device *dev); extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev); #else static inline void disable_cpuidle(void) { } +static inline bool cpuidle_not_available(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{return true; } static inline int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } @@ -183,7 +191,12 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_disable_device(struct cpuidle_device *dev) { } static inline int cpuidle_play_dead(void) {return -ENODEV; } -static inline void cpuidle_enter_freeze(void) { } +static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{return -ENODEV; } +static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{return -ENODEV; } static inline struct cpuidle_driver *cpuidle_get_cpu_driver( struct cpuidle_device *dev) {return NULL; } #endif -- cgit v1.2.3 From 2bb785169e9709d41220e5c18b0270883a82f85c Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 1 Mar 2015 10:18:16 -0500 Subject: serial: core: Fix iotype userspace breakage commit 3ffb1a8193bea ("serial: core: Add big-endian iotype") re-numbered userspace-dependent values; ioctl(TIOCSSERIAL) can assign the port iotype (which is expected to match the selected i/o accessors), so iotype values must not be changed. Cc: Kevin Cernekee Cc: # 3.19+ Signed-off-by: Peter Hurley Reviewed-by: Kevin Cernekee Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index baf3e1d08416..1094f2d9cadb 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -147,9 +147,9 @@ struct uart_port { #define UPIO_HUB6 (1) /* Hub6 ISA card */ #define UPIO_MEM (2) /* 8b MMIO access */ #define UPIO_MEM32 (3) /* 32b little endian */ -#define UPIO_MEM32BE (4) /* 32b big endian */ -#define UPIO_AU (5) /* Au1x00 and RT288x type IO */ -#define UPIO_TSI (6) /* Tsi108/109 type IO */ +#define UPIO_AU (4) /* Au1x00 and RT288x type IO */ +#define UPIO_TSI (5) /* Tsi108/109 type IO */ +#define UPIO_MEM32BE (6) /* 32b big endian */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ -- cgit v1.2.3 From 647f162b8e7e446c4bade031eb8a1a0a83d3de82 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 1 Mar 2015 10:24:28 -0500 Subject: serial: uapi: Declare all userspace-visible io types ioctl(TIOCGSERIAL|TIOCSSERIAL) report and can change the port->iotype. UART drivers use the UPIO_* definitions, but the uapi header defines parallel values and userspace uses these parallel values for ioctls; thus the userspace values are definitive. Define UPIO_* iotypes in terms of the uapi defines, SERIAL_IO_*; extend the uapi defines to include all values in use by the serial core. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 1094f2d9cadb..d10965f0d8a4 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -143,13 +143,13 @@ struct uart_port { unsigned char iotype; /* io access style */ unsigned char unused1; -#define UPIO_PORT (0) /* 8b I/O port access */ -#define UPIO_HUB6 (1) /* Hub6 ISA card */ -#define UPIO_MEM (2) /* 8b MMIO access */ -#define UPIO_MEM32 (3) /* 32b little endian */ -#define UPIO_AU (4) /* Au1x00 and RT288x type IO */ -#define UPIO_TSI (5) /* Tsi108/109 type IO */ -#define UPIO_MEM32BE (6) /* 32b big endian */ +#define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ +#define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ +#define UPIO_MEM (SERIAL_IO_MEM) /* 8b MMIO access */ +#define UPIO_MEM32 (SERIAL_IO_MEM32) /* 32b little endian */ +#define UPIO_AU (SERIAL_IO_AU) /* Au1x00 and RT288x type IO */ +#define UPIO_TSI (SERIAL_IO_TSI) /* Tsi108/109 type IO */ +#define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ -- cgit v1.2.3