From e08e19c331fb249e6dc86365ee80d16045c4aeb1 Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Fri, 16 Oct 2015 14:53:38 +0200 Subject: iio:adc: add iio driver for Palmas (twl6035/7) gpadc This driver code was found as: https://android.googlesource.com/kernel/tegra/+/aaabb2e045f31e5a970109ffdaae900dd403d17e/drivers/staging/iio/adc Fixed various compilation issues and test this driver on omap5 evm. Signed-off-by: Pradeep Goudagunta Signed-off-by: H. Nikolaus Schaller Signed-off-by: Marek Belisko Acked-by: Laxman Dewangan Reviewed-by: Jonathan Cameron Acked-by: Lee Jones Signed-off-by: Jonathan Cameron --- include/linux/mfd/palmas.h | 75 +++++++++++++++++++++++++++++++--------------- 1 file changed, 51 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 13e1d96935ed..c800dbc42079 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -134,21 +134,32 @@ struct palmas_pmic_driver_data { struct regulator_config config); }; +struct palmas_adc_wakeup_property { + int adc_channel_number; + int adc_high_threshold; + int adc_low_threshold; +}; + struct palmas_gpadc_platform_data { /* Channel 3 current source is only enabled during conversion */ - int ch3_current; + int ch3_current; /* 0: off; 1: 10uA; 2: 400uA; 3: 800 uA */ /* Channel 0 current source can be used for battery detection. * If used for battery detection this will cause a permanent current * consumption depending on current level set here. */ - int ch0_current; + int ch0_current; /* 0: off; 1: 5uA; 2: 15uA; 3: 20 uA */ + bool extended_delay; /* use extended delay for conversion */ /* default BAT_REMOVAL_DAT setting on device probe */ int bat_removal; /* Sets the START_POLARITY bit in the RT_CTRL register */ int start_polarity; + + int auto_conversion_period_ms; + struct palmas_adc_wakeup_property *adc_wakeup1_data; + struct palmas_adc_wakeup_property *adc_wakeup2_data; }; struct palmas_reg_init { @@ -405,28 +416,7 @@ struct palmas_gpadc_calibration { s32 offset_error; }; -struct palmas_gpadc { - struct device *dev; - struct palmas *palmas; - - int ch3_current; - int ch0_current; - - int gpadc_force; - - int bat_removal; - - struct mutex reading_lock; - struct completion irq_complete; - - int eoc_sw_irq; - - struct palmas_gpadc_calibration *palmas_cal_tbl; - - int conv0_channel; - int conv1_channel; - int rt_channel; -}; +#define PALMAS_DATASHEET_NAME(_name) "palmas-gpadc-chan-"#_name struct palmas_gpadc_result { s32 raw_code; @@ -520,6 +510,43 @@ enum palmas_irqs { PALMAS_NUM_IRQ, }; +/* Palmas GPADC Channels */ +enum { + PALMAS_ADC_CH_IN0, + PALMAS_ADC_CH_IN1, + PALMAS_ADC_CH_IN2, + PALMAS_ADC_CH_IN3, + PALMAS_ADC_CH_IN4, + PALMAS_ADC_CH_IN5, + PALMAS_ADC_CH_IN6, + PALMAS_ADC_CH_IN7, + PALMAS_ADC_CH_IN8, + PALMAS_ADC_CH_IN9, + PALMAS_ADC_CH_IN10, + PALMAS_ADC_CH_IN11, + PALMAS_ADC_CH_IN12, + PALMAS_ADC_CH_IN13, + PALMAS_ADC_CH_IN14, + PALMAS_ADC_CH_IN15, + PALMAS_ADC_CH_MAX, +}; + +/* Palmas GPADC Channel0 Current Source */ +enum { + PALMAS_ADC_CH0_CURRENT_SRC_0, + PALMAS_ADC_CH0_CURRENT_SRC_5, + PALMAS_ADC_CH0_CURRENT_SRC_15, + PALMAS_ADC_CH0_CURRENT_SRC_20, +}; + +/* Palmas GPADC Channel3 Current Source */ +enum { + PALMAS_ADC_CH3_CURRENT_SRC_0, + PALMAS_ADC_CH3_CURRENT_SRC_10, + PALMAS_ADC_CH3_CURRENT_SRC_400, + PALMAS_ADC_CH3_CURRENT_SRC_800, +}; + struct palmas_pmic { struct palmas *palmas; struct device *dev; -- cgit v1.2.3 From b440655b896b2d5a2fb5f918801fb0e281a537cd Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 13 Oct 2015 18:10:26 +0200 Subject: iio: Add support for indicating fixed watermarks For buffers which have a fixed wake-up watermark the watermark attribute should be read-only. Add a new FIXED_WATERMARK flag to the struct iio_buffer_access_funcs, which can be set by a buffer implementation. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 5 +++++ include/linux/iio/buffer.h | 8 ++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 5f2c8c8c436e..98a6447a61d3 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -998,6 +998,8 @@ static DEVICE_ATTR(enable, S_IRUGO | S_IWUSR, iio_buffer_show_enable, iio_buffer_store_enable); static DEVICE_ATTR(watermark, S_IRUGO | S_IWUSR, iio_buffer_show_watermark, iio_buffer_store_watermark); +static struct device_attribute dev_attr_watermark_ro = __ATTR(watermark, + S_IRUGO, iio_buffer_show_watermark, NULL); static struct attribute *iio_buffer_attrs[] = { &dev_attr_length.attr, @@ -1040,6 +1042,9 @@ int iio_buffer_alloc_sysfs_and_mask(struct iio_dev *indio_dev) if (!buffer->access->set_length) attr[0] = &dev_attr_length_ro.attr; + if (buffer->access->flags & INDIO_BUFFER_FLAG_FIXED_WATERMARK) + attr[2] = &dev_attr_watermark_ro.attr; + if (buffer->attrs) memcpy(&attr[ARRAY_SIZE(iio_buffer_attrs)], buffer->attrs, sizeof(struct attribute *) * attrcount); diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 1600c55828e0..4d99a53d1fe7 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -17,6 +17,12 @@ struct iio_buffer; +/** + * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be + * configured. It has a fixed value which will be buffer specific. + */ +#define INDIO_BUFFER_FLAG_FIXED_WATERMARK BIT(0) + /** * struct iio_buffer_access_funcs - access functions for buffers. * @store_to: actually store stuff to the buffer @@ -30,6 +36,7 @@ struct iio_buffer; * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. * @modes: Supported operating modes by this buffer type + * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* * * The purpose of this structure is to make the buffer element * modular as event for a given driver, different usecases may require @@ -54,6 +61,7 @@ struct iio_buffer_access_funcs { void (*release)(struct iio_buffer *buffer); unsigned int modes; + unsigned int flags; }; /** -- cgit v1.2.3 From e18a2ad45caeb11226e49c25068d0f2efe2adf6c Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 13 Oct 2015 18:10:27 +0200 Subject: iio: Add buffer enable/disable callbacks This patch adds a enable and disable callback that is called when the buffer is enabled/disabled. This can be used by buffer implementations that need to do some setup or teardown work. E.g. a DMA based buffer can use this to start/stop the DMA transfer. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-buffer.c | 36 +++++++++++++++++++++++++++++++++++- include/linux/iio/buffer.h | 8 ++++++++ 2 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 98a6447a61d3..a4b164a478c4 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -568,6 +568,22 @@ static void iio_buffer_deactivate_all(struct iio_dev *indio_dev) iio_buffer_deactivate(buffer); } +static int iio_buffer_enable(struct iio_buffer *buffer, + struct iio_dev *indio_dev) +{ + if (!buffer->access->enable) + return 0; + return buffer->access->enable(buffer, indio_dev); +} + +static int iio_buffer_disable(struct iio_buffer *buffer, + struct iio_dev *indio_dev) +{ + if (!buffer->access->disable) + return 0; + return buffer->access->disable(buffer, indio_dev); +} + static void iio_buffer_update_bytes_per_datum(struct iio_dev *indio_dev, struct iio_buffer *buffer) { @@ -719,6 +735,7 @@ static int iio_verify_update(struct iio_dev *indio_dev, static int iio_enable_buffers(struct iio_dev *indio_dev, struct iio_device_config *config) { + struct iio_buffer *buffer; int ret; indio_dev->active_scan_mask = config->scan_mask; @@ -753,6 +770,12 @@ static int iio_enable_buffers(struct iio_dev *indio_dev, indio_dev->info->hwfifo_set_watermark(indio_dev, config->watermark); + list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) { + ret = iio_buffer_enable(buffer, indio_dev); + if (ret) + goto err_disable_buffers; + } + indio_dev->currentmode = config->mode; if (indio_dev->setup_ops->postenable) { @@ -760,12 +783,16 @@ static int iio_enable_buffers(struct iio_dev *indio_dev, if (ret) { dev_dbg(&indio_dev->dev, "Buffer not started: postenable failed (%d)\n", ret); - goto err_run_postdisable; + goto err_disable_buffers; } } return 0; +err_disable_buffers: + list_for_each_entry_continue_reverse(buffer, &indio_dev->buffer_list, + buffer_list) + iio_buffer_disable(buffer, indio_dev); err_run_postdisable: indio_dev->currentmode = INDIO_DIRECT_MODE; if (indio_dev->setup_ops->postdisable) @@ -778,6 +805,7 @@ err_undo_config: static int iio_disable_buffers(struct iio_dev *indio_dev) { + struct iio_buffer *buffer; int ret = 0; int ret2; @@ -798,6 +826,12 @@ static int iio_disable_buffers(struct iio_dev *indio_dev) ret = ret2; } + list_for_each_entry(buffer, &indio_dev->buffer_list, buffer_list) { + ret2 = iio_buffer_disable(buffer, indio_dev); + if (ret2 && !ret) + ret = ret2; + } + indio_dev->currentmode = INDIO_DIRECT_MODE; if (indio_dev->setup_ops->postdisable) { diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 4d99a53d1fe7..2ec3ad58e8a0 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -33,6 +33,11 @@ struct iio_buffer; * storage. * @set_bytes_per_datum:set number of bytes per datum * @set_length: set number of datums in buffer + * @enable: called if the buffer is attached to a device and the + * device starts sampling. Calls are balanced with + * @disable. + * @disable: called if the buffer is attached to a device and the + * device stops sampling. Calles are balanced with @enable. * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. * @modes: Supported operating modes by this buffer type @@ -58,6 +63,9 @@ struct iio_buffer_access_funcs { int (*set_bytes_per_datum)(struct iio_buffer *buffer, size_t bpd); int (*set_length)(struct iio_buffer *buffer, int length); + int (*enable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); + int (*disable)(struct iio_buffer *buffer, struct iio_dev *indio_dev); + void (*release)(struct iio_buffer *buffer); unsigned int modes; -- cgit v1.2.3 From 670b19ae9bfdbcb4ce2c2ffb2ec1659a7f4a2074 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 13 Oct 2015 18:10:28 +0200 Subject: iio: Add generic DMA buffer infrastructure The traditional approach used in IIO to implement buffered capture requires the generation of at least one interrupt per sample. In the interrupt handler the driver reads the sample from the device and copies it to a software buffer. This approach has a rather large per sample overhead associated with it. And while it works fine for samplerates in the range of up to 1000 samples per second it starts to consume a rather large share of the available CPU processing time once we go beyond that, this is especially true on an embedded system with limited processing power. The regular interrupt also causes increased power consumption by not allowing the hardware into deeper sleep states, which is something that becomes more and more important on mobile battery powered devices. And while the recently added watermark support mitigates some of the issues by allowing the device to generate interrupts at a rate lower than the data output rate, this still requires a storage buffer inside the device and even if it exists it is only a few 100 samples deep at most. DMA support on the other hand allows to capture multiple millions or even more samples without any CPU interaction. This allows the CPU to either go to sleep for longer periods or focus on other tasks which increases overall system performance and power consumption. In addition to that some devices might not even offer a way to read the data other than using DMA, which makes DMA mandatory to use for them. The tasks involved in implementing a DMA buffer can be divided into two categories. The first category is memory buffer management (allocation, mapping, etc.) and hooking this up the IIO buffer callbacks like read(), enable(), disable(), etc. The second category of tasks is to setup the DMA hardware and manage the DMA transfers. Tasks from the first category will be very similar for all IIO drivers supporting DMA buffers, while the tasks from the second category will be hardware specific. This patch implements a generic infrastructure that take care of the former tasks. It provides a set of functions that implement the standard IIO buffer iio_buffer_access_funcs callbacks. These can either be used as is or be overloaded and augmented with driver specific code where necessary. For the DMA buffer support infrastructure that is introduced in this series sample data is grouped by so called blocks. A block is the basic unit at which data is exchanged between the application and the hardware. The application is responsible for allocating the memory associated with the block and then passes the block to the hardware. When the hardware has captured the amount of samples equal to size of a block it will notify the application, which can then read the data from the block and process it. The block size can freely chosen (within the constraints of the hardware). This allows to make a trade-off between latency and management overhead. The larger the block size the lower the per sample overhead but the latency between when the data was captured and when the application will be able to access it increases, in a similar way smaller block sizes have a larger per sample management overhead but a lower latency. The ideal block size thus depends on system and application requirements. For the time being the infrastructure only implements a simple double buffered scheme which allocates two blocks each with half the size of the configured buffer size. This provides basic support for capturing continuous uninterrupted data over the existing file-IO ABI. Future extensions to the DMA buffer infrastructure will give applications a more fine grained control over how many blocks are allocated and the size of each block. But this requires userspace ABI additions which are intentionally not part of this patch and will be added separately. Tasks of the second category need to be implemented by a device specific driver. They can be hooked up into the generic infrastructure using two simple callbacks, submit() and abort(). The submit() callback is used to schedule DMA transfers for blocks. Once a DMA transfer has been completed it is expected that the buffer driver calls iio_dma_buffer_block_done() to notify. The abort() callback is used for stopping all pending and active DMA transfers when the buffer is disabled. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- drivers/iio/buffer/Kconfig | 9 + drivers/iio/buffer/Makefile | 1 + drivers/iio/buffer/industrialio-buffer-dma.c | 683 +++++++++++++++++++++++++++ include/linux/iio/buffer-dma.h | 152 ++++++ 4 files changed, 845 insertions(+) create mode 100644 drivers/iio/buffer/industrialio-buffer-dma.c create mode 100644 include/linux/iio/buffer-dma.h (limited to 'include/linux') diff --git a/drivers/iio/buffer/Kconfig b/drivers/iio/buffer/Kconfig index 0a7b2fd3699b..b2fda1afc03e 100644 --- a/drivers/iio/buffer/Kconfig +++ b/drivers/iio/buffer/Kconfig @@ -9,6 +9,15 @@ config IIO_BUFFER_CB Should be selected by any drivers that do in-kernel push usage. That is, those where the data is pushed to the consumer. +config IIO_BUFFER_DMA + tristate + help + Provides the generic IIO DMA buffer infrastructure that can be used by + drivers for devices with DMA support to implement the IIO buffer. + + Should be selected by drivers that want to use the generic DMA buffer + infrastructure. + config IIO_KFIFO_BUF tristate "Industrial I/O buffering based on kfifo" help diff --git a/drivers/iio/buffer/Makefile b/drivers/iio/buffer/Makefile index 4d193b9a9123..bda3f1143e72 100644 --- a/drivers/iio/buffer/Makefile +++ b/drivers/iio/buffer/Makefile @@ -4,5 +4,6 @@ # When adding new entries keep the list in alphabetical order obj-$(CONFIG_IIO_BUFFER_CB) += industrialio-buffer-cb.o +obj-$(CONFIG_IIO_BUFFER_DMA) += industrialio-buffer-dma.o obj-$(CONFIG_IIO_TRIGGERED_BUFFER) += industrialio-triggered-buffer.o obj-$(CONFIG_IIO_KFIFO_BUF) += kfifo_buf.o diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c new file mode 100644 index 000000000000..212cbedc7abb --- /dev/null +++ b/drivers/iio/buffer/industrialio-buffer-dma.c @@ -0,0 +1,683 @@ +/* + * Copyright 2013-2015 Analog Devices Inc. + * Author: Lars-Peter Clausen + * + * Licensed under the GPL-2. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * For DMA buffers the storage is sub-divided into so called blocks. Each block + * has its own memory buffer. The size of the block is the granularity at which + * memory is exchanged between the hardware and the application. Increasing the + * basic unit of data exchange from one sample to one block decreases the + * management overhead that is associated with each sample. E.g. if we say the + * management overhead for one exchange is x and the unit of exchange is one + * sample the overhead will be x for each sample. Whereas when using a block + * which contains n samples the overhead per sample is reduced to x/n. This + * allows to achieve much higher samplerates than what can be sustained with + * the one sample approach. + * + * Blocks are exchanged between the DMA controller and the application via the + * means of two queues. The incoming queue and the outgoing queue. Blocks on the + * incoming queue are waiting for the DMA controller to pick them up and fill + * them with data. Block on the outgoing queue have been filled with data and + * are waiting for the application to dequeue them and read the data. + * + * A block can be in one of the following states: + * * Owned by the application. In this state the application can read data from + * the block. + * * On the incoming list: Blocks on the incoming list are queued up to be + * processed by the DMA controller. + * * Owned by the DMA controller: The DMA controller is processing the block + * and filling it with data. + * * On the outgoing list: Blocks on the outgoing list have been successfully + * processed by the DMA controller and contain data. They can be dequeued by + * the application. + * * Dead: A block that is dead has been marked as to be freed. It might still + * be owned by either the application or the DMA controller at the moment. + * But once they are done processing it instead of going to either the + * incoming or outgoing queue the block will be freed. + * + * In addition to this blocks are reference counted and the memory associated + * with both the block structure as well as the storage memory for the block + * will be freed when the last reference to the block is dropped. This means a + * block must not be accessed without holding a reference. + * + * The iio_dma_buffer implementation provides a generic infrastructure for + * managing the blocks. + * + * A driver for a specific piece of hardware that has DMA capabilities need to + * implement the submit() callback from the iio_dma_buffer_ops structure. This + * callback is supposed to initiate the DMA transfer copying data from the + * converter to the memory region of the block. Once the DMA transfer has been + * completed the driver must call iio_dma_buffer_block_done() for the completed + * block. + * + * Prior to this it must set the bytes_used field of the block contains + * the actual number of bytes in the buffer. Typically this will be equal to the + * size of the block, but if the DMA hardware has certain alignment requirements + * for the transfer length it might choose to use less than the full size. In + * either case it is expected that bytes_used is a multiple of the bytes per + * datum, i.e. the block must not contain partial samples. + * + * The driver must call iio_dma_buffer_block_done() for each block it has + * received through its submit_block() callback, even if it does not actually + * perform a DMA transfer for the block, e.g. because the buffer was disabled + * before the block transfer was started. In this case it should set bytes_used + * to 0. + * + * In addition it is recommended that a driver implements the abort() callback. + * It will be called when the buffer is disabled and can be used to cancel + * pending and stop active transfers. + * + * The specific driver implementation should use the default callback + * implementations provided by this module for the iio_buffer_access_funcs + * struct. It may overload some callbacks with custom variants if the hardware + * has special requirements that are not handled by the generic functions. If a + * driver chooses to overload a callback it has to ensure that the generic + * callback is called from within the custom callback. + */ + +static void iio_buffer_block_release(struct kref *kref) +{ + struct iio_dma_buffer_block *block = container_of(kref, + struct iio_dma_buffer_block, kref); + + WARN_ON(block->state != IIO_BLOCK_STATE_DEAD); + + dma_free_coherent(block->queue->dev, PAGE_ALIGN(block->size), + block->vaddr, block->phys_addr); + + iio_buffer_put(&block->queue->buffer); + kfree(block); +} + +static void iio_buffer_block_get(struct iio_dma_buffer_block *block) +{ + kref_get(&block->kref); +} + +static void iio_buffer_block_put(struct iio_dma_buffer_block *block) +{ + kref_put(&block->kref, iio_buffer_block_release); +} + +/* + * dma_free_coherent can sleep, hence we need to take some special care to be + * able to drop a reference from an atomic context. + */ +static LIST_HEAD(iio_dma_buffer_dead_blocks); +static DEFINE_SPINLOCK(iio_dma_buffer_dead_blocks_lock); + +static void iio_dma_buffer_cleanup_worker(struct work_struct *work) +{ + struct iio_dma_buffer_block *block, *_block; + LIST_HEAD(block_list); + + spin_lock_irq(&iio_dma_buffer_dead_blocks_lock); + list_splice_tail_init(&iio_dma_buffer_dead_blocks, &block_list); + spin_unlock_irq(&iio_dma_buffer_dead_blocks_lock); + + list_for_each_entry_safe(block, _block, &block_list, head) + iio_buffer_block_release(&block->kref); +} +static DECLARE_WORK(iio_dma_buffer_cleanup_work, iio_dma_buffer_cleanup_worker); + +static void iio_buffer_block_release_atomic(struct kref *kref) +{ + struct iio_dma_buffer_block *block; + unsigned long flags; + + block = container_of(kref, struct iio_dma_buffer_block, kref); + + spin_lock_irqsave(&iio_dma_buffer_dead_blocks_lock, flags); + list_add_tail(&block->head, &iio_dma_buffer_dead_blocks); + spin_unlock_irqrestore(&iio_dma_buffer_dead_blocks_lock, flags); + + schedule_work(&iio_dma_buffer_cleanup_work); +} + +/* + * Version of iio_buffer_block_put() that can be called from atomic context + */ +static void iio_buffer_block_put_atomic(struct iio_dma_buffer_block *block) +{ + kref_put(&block->kref, iio_buffer_block_release_atomic); +} + +static struct iio_dma_buffer_queue *iio_buffer_to_queue(struct iio_buffer *buf) +{ + return container_of(buf, struct iio_dma_buffer_queue, buffer); +} + +static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block( + struct iio_dma_buffer_queue *queue, size_t size) +{ + struct iio_dma_buffer_block *block; + + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) + return NULL; + + block->vaddr = dma_alloc_coherent(queue->dev, PAGE_ALIGN(size), + &block->phys_addr, GFP_KERNEL); + if (!block->vaddr) { + kfree(block); + return NULL; + } + + block->size = size; + block->state = IIO_BLOCK_STATE_DEQUEUED; + block->queue = queue; + INIT_LIST_HEAD(&block->head); + kref_init(&block->kref); + + iio_buffer_get(&queue->buffer); + + return block; +} + +static void _iio_dma_buffer_block_done(struct iio_dma_buffer_block *block) +{ + struct iio_dma_buffer_queue *queue = block->queue; + + /* + * The buffer has already been freed by the application, just drop the + * reference. + */ + if (block->state != IIO_BLOCK_STATE_DEAD) { + block->state = IIO_BLOCK_STATE_DONE; + list_add_tail(&block->head, &queue->outgoing); + } +} + +/** + * iio_dma_buffer_block_done() - Indicate that a block has been completed + * @block: The completed block + * + * Should be called when the DMA controller has finished handling the block to + * pass back ownership of the block to the queue. + */ +void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block) +{ + struct iio_dma_buffer_queue *queue = block->queue; + unsigned long flags; + + spin_lock_irqsave(&queue->list_lock, flags); + _iio_dma_buffer_block_done(block); + spin_unlock_irqrestore(&queue->list_lock, flags); + + iio_buffer_block_put_atomic(block); + wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM); +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_block_done); + +/** + * iio_dma_buffer_block_list_abort() - Indicate that a list block has been + * aborted + * @queue: Queue for which to complete blocks. + * @list: List of aborted blocks. All blocks in this list must be from @queue. + * + * Typically called from the abort() callback after the DMA controller has been + * stopped. This will set bytes_used to 0 for each block in the list and then + * hand the blocks back to the queue. + */ +void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue, + struct list_head *list) +{ + struct iio_dma_buffer_block *block, *_block; + unsigned long flags; + + spin_lock_irqsave(&queue->list_lock, flags); + list_for_each_entry_safe(block, _block, list, head) { + list_del(&block->head); + block->bytes_used = 0; + _iio_dma_buffer_block_done(block); + iio_buffer_block_put_atomic(block); + } + spin_unlock_irqrestore(&queue->list_lock, flags); + + wake_up_interruptible_poll(&queue->buffer.pollq, POLLIN | POLLRDNORM); +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_block_list_abort); + +static bool iio_dma_block_reusable(struct iio_dma_buffer_block *block) +{ + /* + * If the core owns the block it can be re-used. This should be the + * default case when enabling the buffer, unless the DMA controller does + * not support abort and has not given back the block yet. + */ + switch (block->state) { + case IIO_BLOCK_STATE_DEQUEUED: + case IIO_BLOCK_STATE_QUEUED: + case IIO_BLOCK_STATE_DONE: + return true; + default: + return false; + } +} + +/** + * iio_dma_buffer_request_update() - DMA buffer request_update callback + * @buffer: The buffer which to request an update + * + * Should be used as the iio_dma_buffer_request_update() callback for + * iio_buffer_access_ops struct for DMA buffers. + */ +int iio_dma_buffer_request_update(struct iio_buffer *buffer) +{ + struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer); + struct iio_dma_buffer_block *block; + bool try_reuse = false; + size_t size; + int ret = 0; + int i; + + /* + * Split the buffer into two even parts. This is used as a double + * buffering scheme with usually one block at a time being used by the + * DMA and the other one by the application. + */ + size = DIV_ROUND_UP(queue->buffer.bytes_per_datum * + queue->buffer.length, 2); + + mutex_lock(&queue->lock); + + /* Allocations are page aligned */ + if (PAGE_ALIGN(queue->fileio.block_size) == PAGE_ALIGN(size)) + try_reuse = true; + + queue->fileio.block_size = size; + queue->fileio.active_block = NULL; + + spin_lock_irq(&queue->list_lock); + for (i = 0; i < 2; i++) { + block = queue->fileio.blocks[i]; + + /* If we can't re-use it free it */ + if (block && (!iio_dma_block_reusable(block) || !try_reuse)) + block->state = IIO_BLOCK_STATE_DEAD; + } + + /* + * At this point all blocks are either owned by the core or marked as + * dead. This means we can reset the lists without having to fear + * corrution. + */ + INIT_LIST_HEAD(&queue->outgoing); + spin_unlock_irq(&queue->list_lock); + + INIT_LIST_HEAD(&queue->incoming); + + for (i = 0; i < 2; i++) { + if (queue->fileio.blocks[i]) { + block = queue->fileio.blocks[i]; + if (block->state == IIO_BLOCK_STATE_DEAD) { + /* Could not reuse it */ + iio_buffer_block_put(block); + block = NULL; + } else { + block->size = size; + } + } else { + block = NULL; + } + + if (!block) { + block = iio_dma_buffer_alloc_block(queue, size); + if (!block) { + ret = -ENOMEM; + goto out_unlock; + } + queue->fileio.blocks[i] = block; + } + + block->state = IIO_BLOCK_STATE_QUEUED; + list_add_tail(&block->head, &queue->incoming); + } + +out_unlock: + mutex_unlock(&queue->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_request_update); + +static void iio_dma_buffer_submit_block(struct iio_dma_buffer_queue *queue, + struct iio_dma_buffer_block *block) +{ + int ret; + + /* + * If the hardware has already been removed we put the block into + * limbo. It will neither be on the incoming nor outgoing list, nor will + * it ever complete. It will just wait to be freed eventually. + */ + if (!queue->ops) + return; + + block->state = IIO_BLOCK_STATE_ACTIVE; + iio_buffer_block_get(block); + ret = queue->ops->submit(queue, block); + if (ret) { + /* + * This is a bit of a problem and there is not much we can do + * other then wait for the buffer to be disabled and re-enabled + * and try again. But it should not really happen unless we run + * out of memory or something similar. + * + * TODO: Implement support in the IIO core to allow buffers to + * notify consumers that something went wrong and the buffer + * should be disabled. + */ + iio_buffer_block_put(block); + } +} + +/** + * iio_dma_buffer_enable() - Enable DMA buffer + * @buffer: IIO buffer to enable + * @indio_dev: IIO device the buffer is attached to + * + * Needs to be called when the device that the buffer is attached to starts + * sampling. Typically should be the iio_buffer_access_ops enable callback. + * + * This will allocate the DMA buffers and start the DMA transfers. + */ +int iio_dma_buffer_enable(struct iio_buffer *buffer, + struct iio_dev *indio_dev) +{ + struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer); + struct iio_dma_buffer_block *block, *_block; + + mutex_lock(&queue->lock); + queue->active = true; + list_for_each_entry_safe(block, _block, &queue->incoming, head) { + list_del(&block->head); + iio_dma_buffer_submit_block(queue, block); + } + mutex_unlock(&queue->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_enable); + +/** + * iio_dma_buffer_disable() - Disable DMA buffer + * @buffer: IIO DMA buffer to disable + * @indio_dev: IIO device the buffer is attached to + * + * Needs to be called when the device that the buffer is attached to stops + * sampling. Typically should be the iio_buffer_access_ops disable callback. + */ +int iio_dma_buffer_disable(struct iio_buffer *buffer, + struct iio_dev *indio_dev) +{ + struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer); + + mutex_lock(&queue->lock); + queue->active = false; + + if (queue->ops && queue->ops->abort) + queue->ops->abort(queue); + mutex_unlock(&queue->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_disable); + +static void iio_dma_buffer_enqueue(struct iio_dma_buffer_queue *queue, + struct iio_dma_buffer_block *block) +{ + if (block->state == IIO_BLOCK_STATE_DEAD) { + iio_buffer_block_put(block); + } else if (queue->active) { + iio_dma_buffer_submit_block(queue, block); + } else { + block->state = IIO_BLOCK_STATE_QUEUED; + list_add_tail(&block->head, &queue->incoming); + } +} + +static struct iio_dma_buffer_block *iio_dma_buffer_dequeue( + struct iio_dma_buffer_queue *queue) +{ + struct iio_dma_buffer_block *block; + + spin_lock_irq(&queue->list_lock); + block = list_first_entry_or_null(&queue->outgoing, struct + iio_dma_buffer_block, head); + if (block != NULL) { + list_del(&block->head); + block->state = IIO_BLOCK_STATE_DEQUEUED; + } + spin_unlock_irq(&queue->list_lock); + + return block; +} + +/** + * iio_dma_buffer_read() - DMA buffer read callback + * @buffer: Buffer to read form + * @n: Number of bytes to read + * @user_buffer: Userspace buffer to copy the data to + * + * Should be used as the read_first_n callback for iio_buffer_access_ops + * struct for DMA buffers. + */ +int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, + char __user *user_buffer) +{ + struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer); + struct iio_dma_buffer_block *block; + int ret; + + if (n < buffer->bytes_per_datum) + return -EINVAL; + + mutex_lock(&queue->lock); + + if (!queue->fileio.active_block) { + block = iio_dma_buffer_dequeue(queue); + if (block == NULL) { + ret = 0; + goto out_unlock; + } + queue->fileio.pos = 0; + queue->fileio.active_block = block; + } else { + block = queue->fileio.active_block; + } + + n = rounddown(n, buffer->bytes_per_datum); + if (n > block->bytes_used - queue->fileio.pos) + n = block->bytes_used - queue->fileio.pos; + + if (copy_to_user(user_buffer, block->vaddr + queue->fileio.pos, n)) { + ret = -EFAULT; + goto out_unlock; + } + + queue->fileio.pos += n; + + if (queue->fileio.pos == block->bytes_used) { + queue->fileio.active_block = NULL; + iio_dma_buffer_enqueue(queue, block); + } + + ret = n; + +out_unlock: + mutex_unlock(&queue->lock); + + return ret; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_read); + +/** + * iio_dma_buffer_data_available() - DMA buffer data_available callback + * @buf: Buffer to check for data availability + * + * Should be used as the data_available callback for iio_buffer_access_ops + * struct for DMA buffers. + */ +size_t iio_dma_buffer_data_available(struct iio_buffer *buf) +{ + struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buf); + struct iio_dma_buffer_block *block; + size_t data_available = 0; + + /* + * For counting the available bytes we'll use the size of the block not + * the number of actual bytes available in the block. Otherwise it is + * possible that we end up with a value that is lower than the watermark + * but won't increase since all blocks are in use. + */ + + mutex_lock(&queue->lock); + if (queue->fileio.active_block) + data_available += queue->fileio.active_block->size; + + spin_lock_irq(&queue->list_lock); + list_for_each_entry(block, &queue->outgoing, head) + data_available += block->size; + spin_unlock_irq(&queue->list_lock); + mutex_unlock(&queue->lock); + + return data_available; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_data_available); + +/** + * iio_dma_buffer_set_bytes_per_datum() - DMA buffer set_bytes_per_datum callback + * @buffer: Buffer to set the bytes-per-datum for + * @bpd: The new bytes-per-datum value + * + * Should be used as the set_bytes_per_datum callback for iio_buffer_access_ops + * struct for DMA buffers. + */ +int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd) +{ + buffer->bytes_per_datum = bpd; + + return 0; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_set_bytes_per_datum); + +/** + * iio_dma_buffer_set_length - DMA buffer set_length callback + * @buffer: Buffer to set the length for + * @length: The new buffer length + * + * Should be used as the set_length callback for iio_buffer_access_ops + * struct for DMA buffers. + */ +int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length) +{ + /* Avoid an invalid state */ + if (length < 2) + length = 2; + buffer->length = length; + buffer->watermark = length / 2; + + return 0; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_set_length); + +/** + * iio_dma_buffer_init() - Initialize DMA buffer queue + * @queue: Buffer to initialize + * @dev: DMA device + * @ops: DMA buffer queue callback operations + * + * The DMA device will be used by the queue to do DMA memory allocations. So it + * should refer to the device that will perform the DMA to ensure that + * allocations are done from a memory region that can be accessed by the device. + */ +int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, + struct device *dev, const struct iio_dma_buffer_ops *ops) +{ + iio_buffer_init(&queue->buffer); + queue->buffer.length = PAGE_SIZE; + queue->buffer.watermark = queue->buffer.length / 2; + queue->dev = dev; + queue->ops = ops; + + INIT_LIST_HEAD(&queue->incoming); + INIT_LIST_HEAD(&queue->outgoing); + + mutex_init(&queue->lock); + spin_lock_init(&queue->list_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_init); + +/** + * iio_dma_buffer_exit() - Cleanup DMA buffer queue + * @queue: Buffer to cleanup + * + * After this function has completed it is safe to free any resources that are + * associated with the buffer and are accessed inside the callback operations. + */ +void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue) +{ + unsigned int i; + + mutex_lock(&queue->lock); + + spin_lock_irq(&queue->list_lock); + for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) { + if (!queue->fileio.blocks[i]) + continue; + queue->fileio.blocks[i]->state = IIO_BLOCK_STATE_DEAD; + } + INIT_LIST_HEAD(&queue->outgoing); + spin_unlock_irq(&queue->list_lock); + + INIT_LIST_HEAD(&queue->incoming); + + for (i = 0; i < ARRAY_SIZE(queue->fileio.blocks); i++) { + if (!queue->fileio.blocks[i]) + continue; + iio_buffer_block_put(queue->fileio.blocks[i]); + queue->fileio.blocks[i] = NULL; + } + queue->fileio.active_block = NULL; + queue->ops = NULL; + + mutex_unlock(&queue->lock); +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_exit); + +/** + * iio_dma_buffer_release() - Release final buffer resources + * @queue: Buffer to release + * + * Frees resources that can't yet be freed in iio_dma_buffer_exit(). Should be + * called in the buffers release callback implementation right before freeing + * the memory associated with the buffer. + */ +void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue) +{ + mutex_destroy(&queue->lock); +} +EXPORT_SYMBOL_GPL(iio_dma_buffer_release); + +MODULE_AUTHOR("Lars-Peter Clausen "); +MODULE_DESCRIPTION("DMA buffer for the IIO framework"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h new file mode 100644 index 000000000000..767467d886de --- /dev/null +++ b/include/linux/iio/buffer-dma.h @@ -0,0 +1,152 @@ +/* + * Copyright 2013-2015 Analog Devices Inc. + * Author: Lars-Peter Clausen + * + * Licensed under the GPL-2. + */ + +#ifndef __INDUSTRIALIO_DMA_BUFFER_H__ +#define __INDUSTRIALIO_DMA_BUFFER_H__ + +#include +#include +#include +#include +#include + +struct iio_dma_buffer_queue; +struct iio_dma_buffer_ops; +struct device; + +struct iio_buffer_block { + u32 size; + u32 bytes_used; +}; + +/** + * enum iio_block_state - State of a struct iio_dma_buffer_block + * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued + * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue + * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA + * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue + * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed + */ +enum iio_block_state { + IIO_BLOCK_STATE_DEQUEUED, + IIO_BLOCK_STATE_QUEUED, + IIO_BLOCK_STATE_ACTIVE, + IIO_BLOCK_STATE_DONE, + IIO_BLOCK_STATE_DEAD, +}; + +/** + * struct iio_dma_buffer_block - IIO buffer block + * @head: List head + * @size: Total size of the block in bytes + * @bytes_used: Number of bytes that contain valid data + * @vaddr: Virutal address of the blocks memory + * @phys_addr: Physical address of the blocks memory + * @queue: Parent DMA buffer queue + * @kref: kref used to manage the lifetime of block + * @state: Current state of the block + */ +struct iio_dma_buffer_block { + /* May only be accessed by the owner of the block */ + struct list_head head; + size_t bytes_used; + + /* + * Set during allocation, constant thereafter. May be accessed read-only + * by anybody holding a reference to the block. + */ + void *vaddr; + dma_addr_t phys_addr; + size_t size; + struct iio_dma_buffer_queue *queue; + + /* Must not be accessed outside the core. */ + struct kref kref; + /* + * Must not be accessed outside the core. Access needs to hold + * queue->list_lock if the block is not owned by the core. + */ + enum iio_block_state state; +}; + +/** + * struct iio_dma_buffer_queue_fileio - FileIO state for the DMA buffer + * @blocks: Buffer blocks used for fileio + * @active_block: Block being used in read() + * @pos: Read offset in the active block + * @block_size: Size of each block + */ +struct iio_dma_buffer_queue_fileio { + struct iio_dma_buffer_block *blocks[2]; + struct iio_dma_buffer_block *active_block; + size_t pos; + size_t block_size; +}; + +/** + * struct iio_dma_buffer_queue - DMA buffer base structure + * @buffer: IIO buffer base structure + * @dev: Parent device + * @ops: DMA buffer callbacks + * @lock: Protects the incoming list, active and the fields in the fileio + * substruct + * @list_lock: Protects lists that contain blocks which can be modified in + * atomic context as well as blocks on those lists. This is the outgoing queue + * list and typically also a list of active blocks in the part that handles + * the DMA controller + * @incoming: List of buffers on the incoming queue + * @outgoing: List of buffers on the outgoing queue + * @active: Whether the buffer is currently active + * @fileio: FileIO state + */ +struct iio_dma_buffer_queue { + struct iio_buffer buffer; + struct device *dev; + const struct iio_dma_buffer_ops *ops; + + struct mutex lock; + spinlock_t list_lock; + struct list_head incoming; + struct list_head outgoing; + + bool active; + + struct iio_dma_buffer_queue_fileio fileio; +}; + +/** + * struct iio_dma_buffer_ops - DMA buffer callback operations + * @submit: Called when a block is submitted to the DMA controller + * @abort: Should abort all pending transfers + */ +struct iio_dma_buffer_ops { + int (*submit)(struct iio_dma_buffer_queue *queue, + struct iio_dma_buffer_block *block); + void (*abort)(struct iio_dma_buffer_queue *queue); +}; + +void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block); +void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue, + struct list_head *list); + +int iio_dma_buffer_enable(struct iio_buffer *buffer, + struct iio_dev *indio_dev); +int iio_dma_buffer_disable(struct iio_buffer *buffer, + struct iio_dev *indio_dev); +int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, + char __user *user_buffer); +size_t iio_dma_buffer_data_available(struct iio_buffer *buffer); +int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd); +int iio_dma_buffer_set_length(struct iio_buffer *buffer, int length); +int iio_dma_buffer_request_update(struct iio_buffer *buffer); + +int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, + struct device *dma_dev, const struct iio_dma_buffer_ops *ops); +void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue); +void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue); + +#endif -- cgit v1.2.3 From 2d6ca60f328450ff5c7802d0857d12e3711348ce Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 13 Oct 2015 18:10:29 +0200 Subject: iio: Add a DMAengine framework based buffer Add a generic fully device independent DMA buffer implementation that uses the DMAegnine framework to perform the DMA transfers. This can be used by converter drivers that whish to provide a DMA buffer for converters that are connected to a DMA core that implements the DMAengine API. Apart from allocating the buffer using iio_dmaengine_buffer_alloc() and freeing it using iio_dmaengine_buffer_free() no additional converter driver specific code is required when using this DMA buffer implementation. Signed-off-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron --- drivers/iio/buffer/Kconfig | 11 ++ drivers/iio/buffer/Makefile | 1 + drivers/iio/buffer/industrialio-buffer-dmaengine.c | 213 +++++++++++++++++++++ include/linux/iio/buffer-dmaengine.h | 18 ++ 4 files changed, 243 insertions(+) create mode 100644 drivers/iio/buffer/industrialio-buffer-dmaengine.c create mode 100644 include/linux/iio/buffer-dmaengine.h (limited to 'include/linux') diff --git a/drivers/iio/buffer/Kconfig b/drivers/iio/buffer/Kconfig index b2fda1afc03e..4ffd3db7817f 100644 --- a/drivers/iio/buffer/Kconfig +++ b/drivers/iio/buffer/Kconfig @@ -18,6 +18,17 @@ config IIO_BUFFER_DMA Should be selected by drivers that want to use the generic DMA buffer infrastructure. +config IIO_BUFFER_DMAENGINE + tristate + select IIO_BUFFER_DMA + help + Provides a bonding of the generic IIO DMA buffer infrastructure with the + DMAengine framework. This can be used by converter drivers with a DMA port + connected to an external DMA controller which is supported by the + DMAengine framework. + + Should be selected by drivers that want to use this functionality. + config IIO_KFIFO_BUF tristate "Industrial I/O buffering based on kfifo" help diff --git a/drivers/iio/buffer/Makefile b/drivers/iio/buffer/Makefile index bda3f1143e72..85beaae831ae 100644 --- a/drivers/iio/buffer/Makefile +++ b/drivers/iio/buffer/Makefile @@ -5,5 +5,6 @@ # When adding new entries keep the list in alphabetical order obj-$(CONFIG_IIO_BUFFER_CB) += industrialio-buffer-cb.o obj-$(CONFIG_IIO_BUFFER_DMA) += industrialio-buffer-dma.o +obj-$(CONFIG_IIO_BUFFER_DMAENGINE) += industrialio-buffer-dmaengine.o obj-$(CONFIG_IIO_TRIGGERED_BUFFER) += industrialio-triggered-buffer.o obj-$(CONFIG_IIO_KFIFO_BUF) += kfifo_buf.o diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c new file mode 100644 index 000000000000..ebdb838d3a1c --- /dev/null +++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c @@ -0,0 +1,213 @@ +/* + * Copyright 2014-2015 Analog Devices Inc. + * Author: Lars-Peter Clausen + * + * Licensed under the GPL-2 or later. + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* + * The IIO DMAengine buffer combines the generic IIO DMA buffer infrastructure + * with the DMAengine framework. The generic IIO DMA buffer infrastructure is + * used to manage the buffer memory and implement the IIO buffer operations + * while the DMAengine framework is used to perform the DMA transfers. Combined + * this results in a device independent fully functional DMA buffer + * implementation that can be used by device drivers for peripherals which are + * connected to a DMA controller which has a DMAengine driver implementation. + */ + +struct dmaengine_buffer { + struct iio_dma_buffer_queue queue; + + struct dma_chan *chan; + struct list_head active; + + size_t align; + size_t max_size; +}; + +static struct dmaengine_buffer *iio_buffer_to_dmaengine_buffer( + struct iio_buffer *buffer) +{ + return container_of(buffer, struct dmaengine_buffer, queue.buffer); +} + +static void iio_dmaengine_buffer_block_done(void *data) +{ + struct iio_dma_buffer_block *block = data; + unsigned long flags; + + spin_lock_irqsave(&block->queue->list_lock, flags); + list_del(&block->head); + spin_unlock_irqrestore(&block->queue->list_lock, flags); + iio_dma_buffer_block_done(block); +} + +static int iio_dmaengine_buffer_submit_block(struct iio_dma_buffer_queue *queue, + struct iio_dma_buffer_block *block) +{ + struct dmaengine_buffer *dmaengine_buffer = + iio_buffer_to_dmaengine_buffer(&queue->buffer); + struct dma_async_tx_descriptor *desc; + dma_cookie_t cookie; + + block->bytes_used = min(block->size, dmaengine_buffer->max_size); + block->bytes_used = rounddown(block->bytes_used, + dmaengine_buffer->align); + + desc = dmaengine_prep_slave_single(dmaengine_buffer->chan, + block->phys_addr, block->bytes_used, DMA_DEV_TO_MEM, + DMA_PREP_INTERRUPT); + if (!desc) + return -ENOMEM; + + desc->callback = iio_dmaengine_buffer_block_done; + desc->callback_param = block; + + cookie = dmaengine_submit(desc); + if (dma_submit_error(cookie)) + return dma_submit_error(cookie); + + spin_lock_irq(&dmaengine_buffer->queue.list_lock); + list_add_tail(&block->head, &dmaengine_buffer->active); + spin_unlock_irq(&dmaengine_buffer->queue.list_lock); + + dma_async_issue_pending(dmaengine_buffer->chan); + + return 0; +} + +static void iio_dmaengine_buffer_abort(struct iio_dma_buffer_queue *queue) +{ + struct dmaengine_buffer *dmaengine_buffer = + iio_buffer_to_dmaengine_buffer(&queue->buffer); + + dmaengine_terminate_all(dmaengine_buffer->chan); + /* FIXME: There is a slight chance of a race condition here. + * dmaengine_terminate_all() does not guarantee that all transfer + * callbacks have finished running. Need to introduce a + * dmaengine_terminate_all_sync(). + */ + iio_dma_buffer_block_list_abort(queue, &dmaengine_buffer->active); +} + +static void iio_dmaengine_buffer_release(struct iio_buffer *buf) +{ + struct dmaengine_buffer *dmaengine_buffer = + iio_buffer_to_dmaengine_buffer(buf); + + iio_dma_buffer_release(&dmaengine_buffer->queue); + kfree(dmaengine_buffer); +} + +static const struct iio_buffer_access_funcs iio_dmaengine_buffer_ops = { + .read_first_n = iio_dma_buffer_read, + .set_bytes_per_datum = iio_dma_buffer_set_bytes_per_datum, + .set_length = iio_dma_buffer_set_length, + .request_update = iio_dma_buffer_request_update, + .enable = iio_dma_buffer_enable, + .disable = iio_dma_buffer_disable, + .data_available = iio_dma_buffer_data_available, + .release = iio_dmaengine_buffer_release, + + .modes = INDIO_BUFFER_HARDWARE, + .flags = INDIO_BUFFER_FLAG_FIXED_WATERMARK, +}; + +static const struct iio_dma_buffer_ops iio_dmaengine_default_ops = { + .submit = iio_dmaengine_buffer_submit_block, + .abort = iio_dmaengine_buffer_abort, +}; + +/** + * iio_dmaengine_buffer_alloc() - Allocate new buffer which uses DMAengine + * @dev: Parent device for the buffer + * @channel: DMA channel name, typically "rx". + * + * This allocates a new IIO buffer which internally uses the DMAengine framework + * to perform its transfers. The parent device will be used to request the DMA + * channel. + * + * Once done using the buffer iio_dmaengine_buffer_free() should be used to + * release it. + */ +struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel) +{ + struct dmaengine_buffer *dmaengine_buffer; + unsigned int width, src_width, dest_width; + struct dma_slave_caps caps; + struct dma_chan *chan; + int ret; + + dmaengine_buffer = kzalloc(sizeof(*dmaengine_buffer), GFP_KERNEL); + if (!dmaengine_buffer) + return ERR_PTR(-ENOMEM); + + chan = dma_request_slave_channel_reason(dev, channel); + if (IS_ERR(chan)) { + ret = PTR_ERR(chan); + goto err_free; + } + + ret = dma_get_slave_caps(chan, &caps); + if (ret < 0) + goto err_free; + + /* Needs to be aligned to the maximum of the minimums */ + if (caps.src_addr_widths) + src_width = __ffs(caps.src_addr_widths); + else + src_width = 1; + if (caps.dst_addr_widths) + dest_width = __ffs(caps.dst_addr_widths); + else + dest_width = 1; + width = max(src_width, dest_width); + + INIT_LIST_HEAD(&dmaengine_buffer->active); + dmaengine_buffer->chan = chan; + dmaengine_buffer->align = width; + dmaengine_buffer->max_size = dma_get_max_seg_size(chan->device->dev); + + iio_dma_buffer_init(&dmaengine_buffer->queue, chan->device->dev, + &iio_dmaengine_default_ops); + + dmaengine_buffer->queue.buffer.access = &iio_dmaengine_buffer_ops; + + return &dmaengine_buffer->queue.buffer; + +err_free: + kfree(dmaengine_buffer); + return ERR_PTR(ret); +} +EXPORT_SYMBOL(iio_dmaengine_buffer_alloc); + +/** + * iio_dmaengine_buffer_free() - Free dmaengine buffer + * @buffer: Buffer to free + * + * Frees a buffer previously allocated with iio_dmaengine_buffer_alloc(). + */ +void iio_dmaengine_buffer_free(struct iio_buffer *buffer) +{ + struct dmaengine_buffer *dmaengine_buffer = + iio_buffer_to_dmaengine_buffer(buffer); + + iio_dma_buffer_exit(&dmaengine_buffer->queue); + dma_release_channel(dmaengine_buffer->chan); + + iio_buffer_put(buffer); +} +EXPORT_SYMBOL_GPL(iio_dmaengine_buffer_free); diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h new file mode 100644 index 000000000000..5dcddf427bb0 --- /dev/null +++ b/include/linux/iio/buffer-dmaengine.h @@ -0,0 +1,18 @@ +/* + * Copyright 2014-2015 Analog Devices Inc. + * Author: Lars-Peter Clausen + * + * Licensed under the GPL-2 or later. + */ + +#ifndef __IIO_DMAENGINE_H__ +#define __IIO_DMAENGINE_H__ + +struct iio_buffer; +struct device; + +struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, + const char *channel); +void iio_dmaengine_buffer_free(struct iio_buffer *buffer); + +#endif -- cgit v1.2.3 From 28b8b26b308e656edfa9467867d5f79212da2ec3 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Oct 2015 20:33:20 -0700 Subject: mtd: add get/set of_node/flash_node helpers We are going to begin using the mtd->dev.of_node field for MTD device nodes, so let's add helpers for it. Also, we'll be making some conversions on spi_nor (and nand_chip eventually) too, so get that ready with their own helpers. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- include/linux/mtd/mtd.h | 11 +++++++++++ include/linux/mtd/nand.h | 11 +++++++++++ include/linux/mtd/spi-nor.h | 11 +++++++++++ 3 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f17fa75809aa..cc84923011c0 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -254,6 +254,17 @@ struct mtd_info { int usecount; }; +static inline void mtd_set_of_node(struct mtd_info *mtd, + struct device_node *np) +{ + mtd->dev.of_node = np; +} + +static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd) +{ + return mtd->dev.of_node; +} + int mtd_erase(struct mtd_info *mtd, struct erase_info *instr); int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, void **virt, resource_size_t *phys); diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 5a9d1d4c2487..4f7c9b97982f 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -719,6 +719,17 @@ struct nand_chip { void *priv; }; +static inline void nand_set_flash_node(struct nand_chip *chip, + struct device_node *np) +{ + chip->flash_node = np; +} + +static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) +{ + return chip->flash_node; +} + /* * NAND Flash Manufacturer ID Codes */ diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c8723b62c4cd..6d991df8f986 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -185,6 +185,17 @@ struct spi_nor { void *priv; }; +static inline void spi_nor_set_flash_node(struct spi_nor *nor, + struct device_node *np) +{ + nor->flash_node = np; +} + +static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) +{ + return nor->flash_node; +} + /** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure -- cgit v1.2.3 From 3b6521eab0386a4854d47b1a01947d7dc46ec98d Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Oct 2015 20:33:21 -0700 Subject: mtd: ofpart: grab device tree node directly from master device node It seems more logical to use a device node directly associated with the MTD master device (i.e., mtd->dev.of_node field) rather than requiring auxiliary partition parser information to be passed in by the driver in a separate struct. This patch supports the mtd->dev.of_node field and deprecates the parser data 'of_node' field Driver conversions may now follow. Additional side benefit to assigning mtd->dev.of_node rather than using parser data: the driver core will automatically create a device -> node symlink for us. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- drivers/mtd/ofpart.c | 18 ++++++++++-------- include/linux/mtd/partitions.h | 4 +++- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c index 669c3452f278..7bf996a4cf5e 100644 --- a/drivers/mtd/ofpart.c +++ b/drivers/mtd/ofpart.c @@ -37,10 +37,11 @@ static int parse_ofpart_partitions(struct mtd_info *master, bool dedicated = true; - if (!data) - return 0; - - mtd_node = data->of_node; + /* + * of_node can be provided through auxiliary parser data or (preferred) + * by assigning the master device node + */ + mtd_node = data && data->of_node ? data->of_node : mtd_get_of_node(master); if (!mtd_node) return 0; @@ -149,10 +150,11 @@ static int parse_ofoldpart_partitions(struct mtd_info *master, } *part; const char *names; - if (!data) - return 0; - - dp = data->of_node; + /* + * of_node can be provided through auxiliary parser data or (preferred) + * by assigning the master device node + */ + dp = data && data->of_node ? data->of_node : mtd_get_of_node(master); if (!dp) return 0; diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 6a35e6de5da1..e742f34b67eb 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -56,7 +56,9 @@ struct device_node; /** * struct mtd_part_parser_data - used to pass data to MTD partition parsers. * @origin: for RedBoot, start address of MTD device - * @of_node: for OF parsers, device node containing partitioning information + * @of_node: for OF parsers, device node containing partitioning information. + * This field is deprecated, as the device node should simply be + * assigned to the master struct device. */ struct mtd_part_parser_data { unsigned long origin; -- cgit v1.2.3 From 30069af7348b56eb8c5e1dda7788a531c5f24ca2 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Oct 2015 20:33:27 -0700 Subject: mtd: spi-nor: drop flash_node field We can just alias to the MTD of_node. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- drivers/mtd/spi-nor/spi-nor.c | 1 - include/linux/mtd/spi-nor.h | 6 ++---- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 924d455dadb5..12041e181630 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1258,7 +1258,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) mtd->flags |= MTD_NO_ERASE; mtd->dev.parent = dev; - mtd_set_of_node(mtd, np); nor->page_size = info->page_size; mtd->writebufsize = nor->page_size; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 6d991df8f986..955f268d159a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -124,7 +124,6 @@ struct mtd_info; * @mtd: point to a mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations * @dev: point to a spi device, or a spi nor controller device. - * @flash_node: point to a device node describing this flash instance. * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector @@ -155,7 +154,6 @@ struct spi_nor { struct mtd_info mtd; struct mutex lock; struct device *dev; - struct device_node *flash_node; u32 page_size; u8 addr_width; u8 erase_opcode; @@ -188,12 +186,12 @@ struct spi_nor { static inline void spi_nor_set_flash_node(struct spi_nor *nor, struct device_node *np) { - nor->flash_node = np; + mtd_set_of_node(&nor->mtd, np); } static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) { - return nor->flash_node; + return mtd_get_of_node(&nor->mtd); } /** -- cgit v1.2.3 From e270bca531b40cd0a143176eb093d173b9c6f418 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 30 Oct 2015 20:33:29 -0700 Subject: mtd: ofpart: drop 'of_node' partition parser data This field is no longer used anywhere, as it is superseded by mtd->dev.of_node. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- drivers/mtd/ofpart.c | 14 ++++---------- include/linux/mtd/partitions.h | 4 ---- 2 files changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c index 7bf996a4cf5e..f78d2aea5545 100644 --- a/drivers/mtd/ofpart.c +++ b/drivers/mtd/ofpart.c @@ -37,11 +37,8 @@ static int parse_ofpart_partitions(struct mtd_info *master, bool dedicated = true; - /* - * of_node can be provided through auxiliary parser data or (preferred) - * by assigning the master device node - */ - mtd_node = data && data->of_node ? data->of_node : mtd_get_of_node(master); + /* Pull of_node from the master device node */ + mtd_node = mtd_get_of_node(master); if (!mtd_node) return 0; @@ -150,11 +147,8 @@ static int parse_ofoldpart_partitions(struct mtd_info *master, } *part; const char *names; - /* - * of_node can be provided through auxiliary parser data or (preferred) - * by assigning the master device node - */ - dp = data && data->of_node ? data->of_node : mtd_get_of_node(master); + /* Pull of_node from the master device node */ + dp = mtd_get_of_node(master); if (!dp) return 0; diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index e742f34b67eb..773975a3c9e6 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -56,13 +56,9 @@ struct device_node; /** * struct mtd_part_parser_data - used to pass data to MTD partition parsers. * @origin: for RedBoot, start address of MTD device - * @of_node: for OF parsers, device node containing partitioning information. - * This field is deprecated, as the device node should simply be - * assigned to the master struct device. */ struct mtd_part_parser_data { unsigned long origin; - struct device_node *of_node; }; -- cgit v1.2.3 From 26add94cd535d1e000e7871fe69c7bb89e942d67 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 11 Nov 2015 17:05:56 -0800 Subject: mtd: partitions: kill unused ecclayout struct This field is not used. Reported here: http://lists.infradead.org/pipermail/linux-mtd/2015-October/062417.html Reported-by: Brian Foster Cc: Brian Foster Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- include/linux/mtd/partitions.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 773975a3c9e6..8421520c10eb 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -41,7 +41,6 @@ struct mtd_partition { uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ - struct nand_ecclayout *ecclayout; /* out of band layout for this partition (NAND only) */ }; #define MTDPART_OFS_RETAIN (-3) -- cgit v1.2.3 From b36f09c3c441a6e59eab9315032e7d546571de3f Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Tue, 20 Oct 2015 11:46:28 +0200 Subject: dmaengine: Add transfer termination synchronization support The DMAengine API has a long standing race condition that is inherent to the API itself. Calling dmaengine_terminate_all() is supposed to stop and abort any pending or active transfers that have previously been submitted. Unfortunately it is possible that this operation races against a currently running (or with some drivers also scheduled) completion callback. Since the API allows dmaengine_terminate_all() to be called from atomic context as well as from within a completion callback it is not possible to synchronize to the execution of the completion callback from within dmaengine_terminate_all() itself. This means that a user of the DMAengine API does not know when it is safe to free resources used in the completion callback, which can result in a use-after-free race condition. This patch addresses the issue by introducing an explicit synchronization primitive to the DMAengine API called dmaengine_synchronize(). The existing dmaengine_terminate_all() is deprecated in favor of dmaengine_terminate_sync() and dmaengine_terminate_async(). The former aborts all pending and active transfers and synchronizes to the current context, meaning it will wait until all running completion callbacks have finished. This means it is only possible to call this function from non-atomic context. The later function does not synchronize, but can still be used in atomic context or from within a complete callback. It has to be followed up by dmaengine_synchronize() before a client can free the resources used in a completion callback. In addition to this the semantics of the device_terminate_all() callback are slightly relaxed by this patch. It is now OK for a driver to only schedule the termination of the active transfer, but does not necessarily have to wait until the DMA controller has completely stopped. The driver must ensure though that the controller has stopped and no longer accesses any memory when the device_synchronize() callback returns. This was in part done since most drivers do not pay attention to this anyway at the moment and to emphasize that this needs to be done when the device_synchronize() callback is implemented. But it also helps with implementing support for devices where stopping the controller can require operations that may sleep. Signed-off-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- Documentation/dmaengine/client.txt | 38 ++++++++++++++- Documentation/dmaengine/provider.txt | 20 +++++++- drivers/dma/dmaengine.c | 5 +- include/linux/dmaengine.h | 90 ++++++++++++++++++++++++++++++++++++ 4 files changed, 148 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dmaengine/client.txt b/Documentation/dmaengine/client.txt index 11fb87ff6cd0..d9f9f461102a 100644 --- a/Documentation/dmaengine/client.txt +++ b/Documentation/dmaengine/client.txt @@ -128,7 +128,7 @@ The slave DMA usage consists of following steps: transaction. For cyclic DMA, a callback function may wish to terminate the - DMA via dmaengine_terminate_all(). + DMA via dmaengine_terminate_async(). Therefore, it is important that DMA engine drivers drop any locks before calling the callback function which may cause a @@ -166,12 +166,29 @@ The slave DMA usage consists of following steps: Further APIs: -1. int dmaengine_terminate_all(struct dma_chan *chan) +1. int dmaengine_terminate_sync(struct dma_chan *chan) + int dmaengine_terminate_async(struct dma_chan *chan) + int dmaengine_terminate_all(struct dma_chan *chan) /* DEPRECATED */ This causes all activity for the DMA channel to be stopped, and may discard data in the DMA FIFO which hasn't been fully transferred. No callback functions will be called for any incomplete transfers. + Two variants of this function are available. + + dmaengine_terminate_async() might not wait until the DMA has been fully + stopped or until any running complete callbacks have finished. But it is + possible to call dmaengine_terminate_async() from atomic context or from + within a complete callback. dmaengine_synchronize() must be called before it + is safe to free the memory accessed by the DMA transfer or free resources + accessed from within the complete callback. + + dmaengine_terminate_sync() will wait for the transfer and any running + complete callbacks to finish before it returns. But the function must not be + called from atomic context or from within a complete callback. + + dmaengine_terminate_all() is deprecated and should not be used in new code. + 2. int dmaengine_pause(struct dma_chan *chan) This pauses activity on the DMA channel without data loss. @@ -197,3 +214,20 @@ Further APIs: a running DMA channel. It is recommended that DMA engine users pause or stop (via dmaengine_terminate_all()) the channel before using this API. + +5. void dmaengine_synchronize(struct dma_chan *chan) + + Synchronize the termination of the DMA channel to the current context. + + This function should be used after dmaengine_terminate_async() to synchronize + the termination of the DMA channel to the current context. The function will + wait for the transfer and any running complete callbacks to finish before it + returns. + + If dmaengine_terminate_async() is used to stop the DMA channel this function + must be called before it is safe to free memory accessed by previously + submitted descriptors or to free any resources accessed within the complete + callback of previously submitted descriptors. + + The behavior of this function is undefined if dma_async_issue_pending() has + been called between dmaengine_terminate_async() and this function. diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt index 67d4ce4df109..122b7f4876bb 100644 --- a/Documentation/dmaengine/provider.txt +++ b/Documentation/dmaengine/provider.txt @@ -327,8 +327,24 @@ supported. * device_terminate_all - Aborts all the pending and ongoing transfers on the channel - - This command should operate synchronously on the channel, - terminating right away all the channels + - For aborted transfers the complete callback should not be called + - Can be called from atomic context or from within a complete + callback of a descriptor. Must not sleep. Drivers must be able + to handle this correctly. + - Termination may be asynchronous. The driver does not have to + wait until the currently active transfer has completely stopped. + See device_synchronize. + + * device_synchronize + - Must synchronize the termination of a channel to the current + context. + - Must make sure that memory for previously submitted + descriptors is no longer accessed by the DMA controller. + - Must make sure that all complete callbacks for previously + submitted descriptors have finished running and none are + scheduled to run. + - May sleep. + Misc notes (stuff that should be documented, but don't really know where to put them) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 3ecec1445adf..d6fc82e3986f 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -265,8 +265,11 @@ static void dma_chan_put(struct dma_chan *chan) module_put(dma_chan_to_owner(chan)); /* This channel is not in use anymore, free it */ - if (!chan->client_count && chan->device->device_free_chan_resources) + if (!chan->client_count && chan->device->device_free_chan_resources) { + /* Make sure all operations have completed */ + dmaengine_synchronize(chan); chan->device->device_free_chan_resources(chan); + } /* If the channel is used via a DMA request router, free the mapping */ if (chan->router && chan->router->route_free) { diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c47c68e535e8..4662d9aa6d5a 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -654,6 +654,8 @@ enum dmaengine_alignment { * paused. Returns 0 or an error code * @device_terminate_all: Aborts all transfers on a channel. Returns 0 * or an error code + * @device_synchronize: Synchronizes the termination of a transfers to the + * current context. * @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 @@ -737,6 +739,7 @@ struct dma_device { int (*device_pause)(struct dma_chan *chan); int (*device_resume)(struct dma_chan *chan); int (*device_terminate_all)(struct dma_chan *chan); + void (*device_synchronize)(struct dma_chan *chan); enum dma_status (*device_tx_status)(struct dma_chan *chan, dma_cookie_t cookie, @@ -828,6 +831,13 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( src_sg, src_nents, flags); } +/** + * dmaengine_terminate_all() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * This function is DEPRECATED use either dmaengine_terminate_sync() or + * dmaengine_terminate_async() instead. + */ static inline int dmaengine_terminate_all(struct dma_chan *chan) { if (chan->device->device_terminate_all) @@ -836,6 +846,86 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan) return -ENOSYS; } +/** + * dmaengine_terminate_async() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * Calling this function will terminate all active and pending descriptors + * that have previously been submitted to the channel. It is not guaranteed + * though that the transfer for the active descriptor has stopped when the + * function returns. Furthermore it is possible the complete callback of a + * submitted transfer is still running when this function returns. + * + * dmaengine_synchronize() needs to be called before it is safe to free + * any memory that is accessed by previously submitted descriptors or before + * freeing any resources accessed from within the completion callback of any + * perviously submitted descriptors. + * + * This function can be called from atomic context as well as from within a + * complete callback of a descriptor submitted on the same channel. + * + * If none of the two conditions above apply consider using + * dmaengine_terminate_sync() instead. + */ +static inline int dmaengine_terminate_async(struct dma_chan *chan) +{ + if (chan->device->device_terminate_all) + return chan->device->device_terminate_all(chan); + + return -EINVAL; +} + +/** + * dmaengine_synchronize() - Synchronize DMA channel termination + * @chan: The channel to synchronize + * + * Synchronizes to the DMA channel termination to the current context. When this + * function returns it is guaranteed that all transfers for previously issued + * descriptors have stopped and and it is safe to free the memory assoicated + * with them. Furthermore it is guaranteed that all complete callback functions + * for a previously submitted descriptor have finished running and it is safe to + * free resources accessed from within the complete callbacks. + * + * The behavior of this function is undefined if dma_async_issue_pending() has + * been called between dmaengine_terminate_async() and this function. + * + * This function must only be called from non-atomic context and must not be + * called from within a complete callback of a descriptor submitted on the same + * channel. + */ +static inline void dmaengine_synchronize(struct dma_chan *chan) +{ + if (chan->device->device_synchronize) + chan->device->device_synchronize(chan); +} + +/** + * dmaengine_terminate_sync() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * Calling this function will terminate all active and pending transfers + * that have previously been submitted to the channel. It is similar to + * dmaengine_terminate_async() but guarantees that the DMA transfer has actually + * stopped and that all complete callbacks have finished running when the + * function returns. + * + * This function must only be called from non-atomic context and must not be + * called from within a complete callback of a descriptor submitted on the same + * channel. + */ +static inline int dmaengine_terminate_sync(struct dma_chan *chan) +{ + int ret; + + ret = dmaengine_terminate_async(chan); + if (ret) + return ret; + + dmaengine_synchronize(chan); + + return 0; +} + static inline int dmaengine_pause(struct dma_chan *chan) { if (chan->device->device_pause) -- cgit v1.2.3 From 9eeacd3a2f17438d9d286ff2f78c4709a4148be7 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Tue, 13 Oct 2015 21:54:29 +0200 Subject: dmaengine: enable DMA_CTRL_REUSE In the current state, the capability of transfer reuse can neither be set by a slave dmaengine driver, nor used by a client driver, because the capability is not available to dma_get_slave_caps(). Fix this by adding a way to declare the capability. Fixes: 272420214d26 ("dmaengine: Add DMA_CTRL_REUSE") Signed-off-by: Robert Jarzmik Signed-off-by: Vinod Koul --- drivers/dma/dmaengine.c | 1 + include/linux/dmaengine.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 3ecec1445adf..4aced6689734 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -493,6 +493,7 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps) caps->dst_addr_widths = device->dst_addr_widths; caps->directions = device->directions; caps->residue_granularity = device->residue_granularity; + caps->descriptor_reuse = device->descriptor_reuse; /* * Some devices implement only pause (e.g. to get residuum) but no diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c47c68e535e8..6f94b5cbd97c 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -659,6 +659,7 @@ enum dmaengine_alignment { * struct with auxiliary transfer status information, otherwise the call * will just return a simple status code * @device_issue_pending: push pending transactions to hardware + * @descriptor_reuse: a submitted transfer can be resubmitted after completion */ struct dma_device { @@ -681,6 +682,7 @@ struct dma_device { u32 src_addr_widths; u32 dst_addr_widths; u32 directions; + bool descriptor_reuse; enum dma_residue_granularity residue_granularity; int (*device_alloc_chan_resources)(struct dma_chan *chan); -- cgit v1.2.3 From 2bb129ebb23d2dfec3cd9c22dc7defd681cfcd58 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Fri, 13 Nov 2015 12:46:00 +0100 Subject: dmaengine: ioatdma: constify dca_ops structures The dca_ops structure is never modified, so declare it as const. Done with the help of Coccinelle. Signed-off-by: Julia Lawall Acked-by: Dan Williams Signed-off-by: Vinod Koul --- drivers/dca/dca-core.c | 3 ++- drivers/dma/ioat/dca.c | 2 +- include/linux/dca.h | 5 +++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c index 819dfda88236..7afbb28d6a0f 100644 --- a/drivers/dca/dca-core.c +++ b/drivers/dca/dca-core.c @@ -321,7 +321,8 @@ EXPORT_SYMBOL_GPL(dca_get_tag); * @ops - pointer to struct of dca operation function pointers * @priv_size - size of extra mem to be added for provider's needs */ -struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size) +struct dca_provider *alloc_dca_provider(const struct dca_ops *ops, + int priv_size) { struct dca_provider *dca; int alloc_size; diff --git a/drivers/dma/ioat/dca.c b/drivers/dma/ioat/dca.c index 2cb7c308d5c7..0b9b6b07db9e 100644 --- a/drivers/dma/ioat/dca.c +++ b/drivers/dma/ioat/dca.c @@ -224,7 +224,7 @@ static u8 ioat_dca_get_tag(struct dca_provider *dca, return tag; } -static struct dca_ops ioat_dca_ops = { +static const struct dca_ops ioat_dca_ops = { .add_requester = ioat_dca_add_requester, .remove_requester = ioat_dca_remove_requester, .get_tag = ioat_dca_get_tag, diff --git a/include/linux/dca.h b/include/linux/dca.h index d27a7a05718d..ad956c2e07a8 100644 --- a/include/linux/dca.h +++ b/include/linux/dca.h @@ -34,7 +34,7 @@ void dca_unregister_notify(struct notifier_block *nb); struct dca_provider { struct list_head node; - struct dca_ops *ops; + const struct dca_ops *ops; struct device *cd; int id; }; @@ -53,7 +53,8 @@ struct dca_ops { int (*dev_managed) (struct dca_provider *, struct device *); }; -struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size); +struct dca_provider *alloc_dca_provider(const struct dca_ops *ops, + int priv_size); void free_dca_provider(struct dca_provider *dca); int register_dca_provider(struct dca_provider *dca, struct device *dev); void unregister_dca_provider(struct dca_provider *dca, struct device *dev); -- cgit v1.2.3 From 3ff3f518a135fa4592fe2817e9ac2cce1fa23dc2 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 9 Nov 2015 22:20:37 -0800 Subject: regulator: Make bulk API support optional supplies Make it possible to use the bulk API with optional supplies, by allowing the consumer to marking supplies as optional in the regulator_bulk_data. Signed-off-by: Bjorn Andersson Signed-off-by: Mark Brown --- drivers/regulator/core.c | 6 ++++-- drivers/regulator/devres.c | 7 +++++-- include/linux/regulator/consumer.h | 3 +++ 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 73b7683355cd..4cf1390784e5 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -3451,8 +3451,10 @@ int regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].consumer = NULL; for (i = 0; i < num_consumers; i++) { - consumers[i].consumer = regulator_get(dev, - consumers[i].supply); + consumers[i].consumer = _regulator_get(dev, + consumers[i].supply, + false, + !consumers[i].optional); if (IS_ERR(consumers[i].consumer)) { ret = PTR_ERR(consumers[i].consumer); dev_err(dev, "Failed to get supply '%s': %d\n", diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index 6ec1d400adae..6ad8ab4c578d 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -164,8 +164,11 @@ int devm_regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].consumer = NULL; for (i = 0; i < num_consumers; i++) { - consumers[i].consumer = devm_regulator_get(dev, - consumers[i].supply); + consumers[i].consumer = _devm_regulator_get(dev, + consumers[i].supply, + consumers[i].optional ? + OPTIONAL_GET : + NORMAL_GET); if (IS_ERR(consumers[i].consumer)) { ret = PTR_ERR(consumers[i].consumer); dev_err(dev, "Failed to get supply '%s': %d\n", diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 9e0e76992be0..48603506f8de 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -140,6 +140,8 @@ struct regulator; * * @supply: The name of the supply. Initialised by the user before * using the bulk regulator APIs. + * @optional: The supply should be considered optional. Initialised by the user + * before using the bulk regulator APIs. * @consumer: The regulator consumer for the supply. This will be managed * by the bulk API. * @@ -149,6 +151,7 @@ struct regulator; */ struct regulator_bulk_data { const char *supply; + bool optional; struct regulator *consumer; /* private: Internal use */ -- cgit v1.2.3 From a0067db36a2f9733a2e956a44ef8145e6a809bdb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Nov 2015 15:21:32 +0100 Subject: spi: s3c64xx: pass DMA arguments in platform data The s3c64xx platform data already contains a pointer to the DMA filter function, but not to the associated data. This simplifies the code and makes it more generic by passing the data along with the filter function like we do for other drivers. Signed-off-by: Arnd Bergmann Signed-off-by: Mark Brown --- arch/arm/plat-samsung/devs.c | 19 ++++++++++--------- drivers/spi/spi-s3c64xx.c | 27 +++++++-------------------- include/linux/platform_data/spi-s3c64xx.h | 2 ++ 3 files changed, 19 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 82074625de5c..4c64ece1a308 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -1100,9 +1100,7 @@ struct platform_device s3c_device_wdt = { #ifdef CONFIG_S3C64XX_DEV_SPI0 static struct resource s3c64xx_spi0_resource[] = { [0] = DEFINE_RES_MEM(S3C_PA_SPI0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_SPI0_TX), - [2] = DEFINE_RES_DMA(DMACH_SPI0_RX), - [3] = DEFINE_RES_IRQ(IRQ_SPI0), + [1] = DEFINE_RES_IRQ(IRQ_SPI0), }; struct platform_device s3c64xx_device_spi0 = { @@ -1130,6 +1128,8 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi0_cfg_gpio; + pd.dma_tx = (void *)DMACH_SPI0_TX; + pd.dma_rx = (void *)DMACH_SPI0_RX; #if defined(CONFIG_PL330_DMA) pd.filter = pl330_filter; #elif defined(CONFIG_S3C64XX_PL080) @@ -1145,9 +1145,7 @@ void __init s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, #ifdef CONFIG_S3C64XX_DEV_SPI1 static struct resource s3c64xx_spi1_resource[] = { [0] = DEFINE_RES_MEM(S3C_PA_SPI1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_SPI1_TX), - [2] = DEFINE_RES_DMA(DMACH_SPI1_RX), - [3] = DEFINE_RES_IRQ(IRQ_SPI1), + [1] = DEFINE_RES_IRQ(IRQ_SPI1), }; struct platform_device s3c64xx_device_spi1 = { @@ -1175,12 +1173,15 @@ void __init s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi1_cfg_gpio; + pd.dma_tx = (void *)DMACH_SPI1_TX; + pd.dma_rx = (void *)DMACH_SPI1_RX; #if defined(CONFIG_PL330_DMA) pd.filter = pl330_filter; #elif defined(CONFIG_S3C64XX_PL080) pd.filter = pl08x_filter_id; #endif + s3c_set_platdata(&pd, sizeof(pd), &s3c64xx_device_spi1); } #endif /* CONFIG_S3C64XX_DEV_SPI1 */ @@ -1188,9 +1189,7 @@ void __init s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, #ifdef CONFIG_S3C64XX_DEV_SPI2 static struct resource s3c64xx_spi2_resource[] = { [0] = DEFINE_RES_MEM(S3C_PA_SPI2, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_SPI2_TX), - [2] = DEFINE_RES_DMA(DMACH_SPI2_RX), - [3] = DEFINE_RES_IRQ(IRQ_SPI2), + [1] = DEFINE_RES_IRQ(IRQ_SPI2), }; struct platform_device s3c64xx_device_spi2 = { @@ -1218,6 +1217,8 @@ void __init s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, pd.num_cs = num_cs; pd.src_clk_nr = src_clk_nr; pd.cfg_gpio = (cfg_gpio) ? cfg_gpio : s3c64xx_spi2_cfg_gpio; + pd.dma_tx = (void *)DMACH_SPI2_TX; + pd.dma_rx = (void *)DMACH_SPI2_RX; #if defined(CONFIG_PL330_DMA) pd.filter = pl330_filter; #elif defined(CONFIG_S3C64XX_PL080) diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index 8e86e7f6663a..b954c5444cca 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -133,7 +133,6 @@ struct s3c64xx_spi_dma_data { struct dma_chan *ch; enum dma_transfer_direction direction; - unsigned int dmach; }; /** @@ -325,7 +324,7 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi) /* Acquire DMA channels */ sdd->rx_dma.ch = dma_request_slave_channel_compat(mask, filter, - (void *)(long)sdd->rx_dma.dmach, dev, "rx"); + sdd->cntrlr_info->dma_rx, dev, "rx"); if (!sdd->rx_dma.ch) { dev_err(dev, "Failed to get RX DMA channel\n"); ret = -EBUSY; @@ -334,7 +333,7 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi) spi->dma_rx = sdd->rx_dma.ch; sdd->tx_dma.ch = dma_request_slave_channel_compat(mask, filter, - (void *)(long)sdd->tx_dma.dmach, dev, "tx"); + sdd->cntrlr_info->dma_tx, dev, "tx"); if (!sdd->tx_dma.ch) { dev_err(dev, "Failed to get TX DMA channel\n"); ret = -EBUSY; @@ -1028,7 +1027,6 @@ static inline struct s3c64xx_spi_port_config *s3c64xx_spi_get_port_config( static int s3c64xx_spi_probe(struct platform_device *pdev) { struct resource *mem_res; - struct resource *res; struct s3c64xx_spi_driver_data *sdd; struct s3c64xx_spi_info *sci = dev_get_platdata(&pdev->dev); struct spi_master *master; @@ -1087,20 +1085,9 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) sdd->cur_bpw = 8; - if (!sdd->pdev->dev.of_node) { - res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (!res) { - dev_warn(&pdev->dev, "Unable to get SPI tx dma resource. Switching to poll mode\n"); - sdd->port_conf->quirks = S3C64XX_SPI_QUIRK_POLL; - } else - sdd->tx_dma.dmach = res->start; - - res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (!res) { - dev_warn(&pdev->dev, "Unable to get SPI rx dma resource. Switching to poll mode\n"); - sdd->port_conf->quirks = S3C64XX_SPI_QUIRK_POLL; - } else - sdd->rx_dma.dmach = res->start; + if (!sdd->pdev->dev.of_node && (!sci->dma_tx || !sci->dma_rx)) { + dev_warn(&pdev->dev, "Unable to get SPI tx/rx DMA data. Switching to poll mode\n"); + sdd->port_conf->quirks = S3C64XX_SPI_QUIRK_POLL; } sdd->tx_dma.direction = DMA_MEM_TO_DEV; @@ -1197,9 +1184,9 @@ static int s3c64xx_spi_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d with %d Slaves attached\n", sdd->port_id, master->num_chipselect); - dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\tDMA=[Rx-%d, Tx-%d]\n", + dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\tDMA=[Rx-%p, Tx-%p]\n", mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1, - sdd->rx_dma.dmach, sdd->tx_dma.dmach); + sci->dma_rx, sci->dma_tx); pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_put_autosuspend(&pdev->dev); diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index d3889b98a1a1..fb5625bcca9a 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -40,6 +40,8 @@ struct s3c64xx_spi_info { int num_cs; int (*cfg_gpio)(void); dma_filter_fn filter; + void *dma_tx; + void *dma_rx; }; /** -- cgit v1.2.3 From 9eba47ddd8fee8a21f45e6e1d707103f040d90c7 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 16 Nov 2015 14:37:35 +0100 Subject: mtd: nand: add an mtd_to_nand() helper Some drivers are retrieving the nand_chip pointer using the container_of macro on a struct wrapping both the nand_chip and the mtd_info struct while the standard way of retrieving this pointer is through mtd->priv. Provide an helper to do that. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 5a9d1d4c2487..a4839b3f27da 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -719,6 +719,11 @@ struct nand_chip { void *priv; }; +static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) +{ + return mtd->priv; +} + /* * NAND Flash Manufacturer ID Codes */ -- cgit v1.2.3 From c67cbb839da9cc2757eabfa128556db6a2baf160 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 10 Nov 2015 12:15:27 -0800 Subject: mtd: spi-nor: provide default erase_sector implementation Some spi-nor drivers perform sector erase by duplicating their write_reg() command. Let's not require that the driver fill this out, and provide a default instead. Tested on m25p80.c and Medatek's MT8173 SPI NOR flash driver. Signed-off-by: Brian Norris --- drivers/mtd/spi-nor/spi-nor.c | 37 +++++++++++++++++++++++++++++++++---- include/linux/mtd/spi-nor.h | 3 ++- 2 files changed, 35 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 16c9f5522b8f..a38ec01a1e06 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -38,6 +38,7 @@ #define CHIP_ERASE_2MB_READY_WAIT_JIFFIES (40UL * HZ) #define SPI_NOR_MAX_ID_LEN 6 +#define SPI_NOR_MAX_ADDR_WIDTH 4 struct flash_info { char *name; @@ -312,6 +313,29 @@ static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops) mutex_unlock(&nor->lock); } +/* + * Initiate the erasure of a single sector + */ +static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr) +{ + u8 buf[SPI_NOR_MAX_ADDR_WIDTH]; + int i; + + if (nor->erase) + return nor->erase(nor, addr); + + /* + * Default implementation, if driver doesn't have a specialized HW + * control + */ + for (i = nor->addr_width - 1; i >= 0; i--) { + buf[i] = addr & 0xff; + addr >>= 8; + } + + return nor->write_reg(nor, nor->erase_opcode, buf, nor->addr_width); +} + /* * Erase an address range on the nor chip. The address range may extend * one or more erase sectors. Return an error is there is a problem erasing. @@ -371,10 +395,9 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr) while (len) { write_enable(nor); - if (nor->erase(nor, addr)) { - ret = -EIO; + ret = spi_nor_erase_sector(nor, addr); + if (ret) goto erase_err; - } addr += mtd->erasesize; len -= mtd->erasesize; @@ -1138,7 +1161,7 @@ static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info) static int spi_nor_check(struct spi_nor *nor) { if (!nor->dev || !nor->read || !nor->write || - !nor->read_reg || !nor->write_reg || !nor->erase) { + !nor->read_reg || !nor->write_reg) { pr_err("spi-nor: please fill all the necessary fields!\n"); return -EINVAL; } @@ -1340,6 +1363,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) nor->addr_width = 3; } + if (nor->addr_width > SPI_NOR_MAX_ADDR_WIDTH) { + dev_err(dev, "address width is too large: %u\n", + nor->addr_width); + return -EINVAL; + } + nor->read_dummy = spi_nor_read_dummy_cycles(nor); dev_info(dev, "%s (%lld Kbytes)\n", info->name, diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 955f268d159a..7bed97471e53 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -143,7 +143,8 @@ struct mtd_info; * @read: [DRIVER-SPECIFIC] read data from the SPI NOR * @write: [DRIVER-SPECIFIC] write data to the SPI NOR * @erase: [DRIVER-SPECIFIC] erase a sector of the SPI NOR - * at the offset @offs + * at the offset @offs; if not provided by the driver, + * spi-nor will send the erase opcode via write_reg() * @flash_lock: [FLASH-SPECIFIC] lock a region of the SPI NOR * @flash_unlock: [FLASH-SPECIFIC] unlock a region of the SPI NOR * @flash_is_locked: [FLASH-SPECIFIC] check if a region of the SPI NOR is -- cgit v1.2.3 From b9eab01125bf3cb6f5fbab1811402d16c9fcf4ec Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 11 Nov 2015 19:13:29 -0800 Subject: mtd: partitions: add module_mtd_part_parser() helper This can help eliminate some boilerplate by generating the module_init() and module_exit() functions, and by automatically assigning the module owner. Signed-off-by: Brian Norris --- drivers/mtd/mtdpart.c | 8 ++++++-- include/linux/mtd/partitions.h | 14 +++++++++++++- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 46dfbf5629c3..1fa3ca95d9c1 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -703,13 +703,17 @@ static struct mtd_part_parser *get_partition_parser(const char *name) #define put_partition_parser(p) do { module_put((p)->owner); } while (0) -void register_mtd_parser(struct mtd_part_parser *p) +int __register_mtd_parser(struct mtd_part_parser *p, struct module *owner) { + p->owner = owner; + spin_lock(&part_parser_lock); list_add(&p->list, &part_parsers); spin_unlock(&part_parser_lock); + + return 0; } -EXPORT_SYMBOL_GPL(register_mtd_parser); +EXPORT_SYMBOL_GPL(__register_mtd_parser); void deregister_mtd_parser(struct mtd_part_parser *p) { diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 8421520c10eb..d002d9b5d797 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -73,9 +73,21 @@ struct mtd_part_parser { struct mtd_part_parser_data *); }; -extern void register_mtd_parser(struct mtd_part_parser *parser); +extern int __register_mtd_parser(struct mtd_part_parser *parser, + struct module *owner); +#define register_mtd_parser(parser) __register_mtd_parser(parser, THIS_MODULE) + extern void deregister_mtd_parser(struct mtd_part_parser *parser); +/* + * module_mtd_part_parser() - Helper macro for MTD partition parsers that don't + * do anything special in module init/exit. Each driver may only use this macro + * once, and calling it replaces module_init() and module_exit(). + */ +#define module_mtd_part_parser(__mtd_part_parser) \ + module_driver(__mtd_part_parser, register_mtd_parser, \ + deregister_mtd_parser) + int mtd_is_partition(const struct mtd_info *mtd); int mtd_add_partition(struct mtd_info *master, const char *name, long long offset, long long length); -- cgit v1.2.3 From b466c1dd73d5303a313fb0c962e4eb5879bc1336 Mon Sep 17 00:00:00 2001 From: Simon Wood Date: Thu, 19 Nov 2015 16:42:14 -0700 Subject: HID: Add vendor specific usage pages for Logitech G920 The Logitech G920 uses a couple of vendor specific usage pages, which results in incorrect number of axis/buttons being detected. This patch adds these pages to the 'ignore' list. Reported-by: Elias Vanderstuyft Signed-off-by: Simon Wood Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-input.c | 4 ++++ include/linux/hid.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 2ba6bf69b7d0..f4eeb6bcb9ac 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -960,6 +960,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel goto ignore; case HID_UP_LOGIVENDOR: + /* intentional fallback */ + case HID_UP_LOGIVENDOR2: + /* intentional fallback */ + case HID_UP_LOGIVENDOR3: goto ignore; case HID_UP_PID: diff --git a/include/linux/hid.h b/include/linux/hid.h index 251a1d382e23..a6d7a3fc2cb3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -168,6 +168,8 @@ struct hid_item { #define HID_UP_MSVENDOR 0xff000000 #define HID_UP_CUSTOM 0x00ff0000 #define HID_UP_LOGIVENDOR 0xffbc0000 +#define HID_UP_LOGIVENDOR2 0xff090000 +#define HID_UP_LOGIVENDOR3 0xff430000 #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 -- cgit v1.2.3 From 403c5c0650816375527a6feecfb255d9b494dda3 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Thu, 8 Oct 2015 09:11:48 +0200 Subject: HSI: Remove struct hsi_client private fields from kernel-doc The kernel-doc how to says that structure fields that are inside a "private:" area shouldn't be listed in the generated documentation but the private fields for struct hsi_client private are listed. This also fixes the following make htmldocs warnings: .//include/linux/hsi/hsi.h:150: warning: Excess struct/union/enum/typedef member 'e_handler' description in 'hsi_client' .//include/linux/hsi/hsi.h:150: warning: Excess struct/union/enum/typedef member 'pclaimed' description in 'hsi_client' .//include/linux/hsi/hsi.h:150: warning: Excess struct/union/enum/typedef member 'nb' description in 'hsi_client' Signed-off-by: Javier Martinez Canillas Signed-off-by: Sebastian Reichel --- include/linux/hsi/hsi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h index 5dd60c2e120f..2790591c77cf 100644 --- a/include/linux/hsi/hsi.h +++ b/include/linux/hsi/hsi.h @@ -135,9 +135,6 @@ static inline int hsi_register_board_info(struct hsi_board_info const *info, * @device: Driver model representation of the device * @tx_cfg: HSI TX configuration * @rx_cfg: HSI RX configuration - * @e_handler: Callback for handling port events (RX Wake High/Low) - * @pclaimed: Keeps tracks if the clients claimed its associated HSI port - * @nb: Notifier block for port events */ struct hsi_client { struct device device; -- cgit v1.2.3 From 9e4808d2c6a6660d5d2cd572e689570df14a8472 Mon Sep 17 00:00:00 2001 From: Thomas Abraham Date: Fri, 20 Nov 2015 16:07:51 +0530 Subject: mfd: sec: Add support for S2MPS15 PMIC Add support for S2MPS15 PMIC which is similar to S2MPS11 PMIC. The S2MPS15 PMIC supports 27 LDO regulators, 10 buck regulators, RTC, three 32.768KHz clock outputs and battery charger. This patch adds initial support for LDO and buck regulators of S2MPS15 device. Signed-off-by: Thomas Abraham Signed-off-by: Alim Akhtar Reviewed-by: Krzysztof Kozlowski [Alim: Added s2mps15_devs like rtc and clk and related changes] Signed-off-by: Lee Jones --- drivers/mfd/sec-core.c | 31 +++++++ drivers/mfd/sec-irq.c | 8 ++ include/linux/mfd/samsung/core.h | 1 + include/linux/mfd/samsung/s2mps15.h | 158 ++++++++++++++++++++++++++++++++++++ 4 files changed, 198 insertions(+) create mode 100644 include/linux/mfd/samsung/s2mps15.h (limited to 'include/linux') diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index 989076d6cb83..7c4e7be17f1e 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -96,6 +97,17 @@ static const struct mfd_cell s2mps14_devs[] = { } }; +static const struct mfd_cell s2mps15_devs[] = { + { + .name = "s2mps15-regulator", + }, { + .name = "s2mps15-rtc", + }, { + .name = "s2mps13-clk", + .of_compatible = "samsung,s2mps13-clk", + }, +}; + static const struct mfd_cell s2mpa01_devs[] = { { .name = "s2mpa01-pmic", @@ -121,6 +133,9 @@ static const struct of_device_id sec_dt_match[] = { }, { .compatible = "samsung,s2mps14-pmic", .data = (void *)S2MPS14X, + }, { + .compatible = "samsung,s2mps15-pmic", + .data = (void *)S2MPS15X, }, { .compatible = "samsung,s2mpa01-pmic", .data = (void *)S2MPA01, @@ -223,6 +238,15 @@ static const struct regmap_config s2mps14_regmap_config = { .cache_type = REGCACHE_FLAT, }; +static const struct regmap_config s2mps15_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + + .max_register = S2MPS15_REG_LDODSCH4, + .volatile_reg = s2mps11_volatile, + .cache_type = REGCACHE_FLAT, +}; + static const struct regmap_config s2mpu02_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -384,6 +408,9 @@ static int sec_pmic_probe(struct i2c_client *i2c, case S2MPS14X: regmap = &s2mps14_regmap_config; break; + case S2MPS15X: + regmap = &s2mps15_regmap_config; + break; case S5M8763X: regmap = &s5m8763_regmap_config; break; @@ -442,6 +469,10 @@ static int sec_pmic_probe(struct i2c_client *i2c, sec_devs = s2mps14_devs; num_sec_devs = ARRAY_SIZE(s2mps14_devs); break; + case S2MPS15X: + sec_devs = s2mps15_devs; + num_sec_devs = ARRAY_SIZE(s2mps15_devs); + break; case S2MPU02: sec_devs = s2mpu02_devs; num_sec_devs = ARRAY_SIZE(s2mpu02_devs); diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c index 806fa8dbb22d..d77de431cc50 100644 --- a/drivers/mfd/sec-irq.c +++ b/drivers/mfd/sec-irq.c @@ -407,6 +407,11 @@ static const struct regmap_irq_chip s2mps14_irq_chip = { S2MPS1X_IRQ_CHIP_COMMON_DATA, }; +static const struct regmap_irq_chip s2mps15_irq_chip = { + .name = "s2mps15", + S2MPS1X_IRQ_CHIP_COMMON_DATA, +}; + static const struct regmap_irq_chip s2mpu02_irq_chip = { .name = "s2mpu02", .irqs = s2mpu02_irqs, @@ -466,6 +471,9 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic) case S2MPS14X: sec_irq_chip = &s2mps14_irq_chip; break; + case S2MPS15X: + sec_irq_chip = &s2mps15_irq_chip; + break; case S2MPU02: sec_irq_chip = &s2mpu02_irq_chip; break; diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index a06098639399..6bc4bcd488ac 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -44,6 +44,7 @@ enum sec_device_type { S2MPS11X, S2MPS13X, S2MPS14X, + S2MPS15X, S2MPU02, }; diff --git a/include/linux/mfd/samsung/s2mps15.h b/include/linux/mfd/samsung/s2mps15.h new file mode 100644 index 000000000000..36d35287c3c0 --- /dev/null +++ b/include/linux/mfd/samsung/s2mps15.h @@ -0,0 +1,158 @@ +/* + * Copyright (c) 2015 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 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_MFD_S2MPS15_H +#define __LINUX_MFD_S2MPS15_H + +/* S2MPS15 registers */ +enum s2mps15_reg { + S2MPS15_REG_ID, + S2MPS15_REG_INT1, + S2MPS15_REG_INT2, + S2MPS15_REG_INT3, + S2MPS15_REG_INT1M, + S2MPS15_REG_INT2M, + S2MPS15_REG_INT3M, + S2MPS15_REG_ST1, + S2MPS15_REG_ST2, + S2MPS15_REG_PWRONSRC, + S2MPS15_REG_OFFSRC, + S2MPS15_REG_BU_CHG, + S2MPS15_REG_RTC_BUF, + S2MPS15_REG_CTRL1, + S2MPS15_REG_CTRL2, + S2MPS15_REG_RSVD1, + S2MPS15_REG_RSVD2, + S2MPS15_REG_RSVD3, + S2MPS15_REG_RSVD4, + S2MPS15_REG_RSVD5, + S2MPS15_REG_RSVD6, + S2MPS15_REG_CTRL3, + S2MPS15_REG_RSVD7, + S2MPS15_REG_RSVD8, + S2MPS15_REG_RSVD9, + S2MPS15_REG_B1CTRL1, + S2MPS15_REG_B1CTRL2, + S2MPS15_REG_B2CTRL1, + S2MPS15_REG_B2CTRL2, + S2MPS15_REG_B3CTRL1, + S2MPS15_REG_B3CTRL2, + S2MPS15_REG_B4CTRL1, + S2MPS15_REG_B4CTRL2, + S2MPS15_REG_B5CTRL1, + S2MPS15_REG_B5CTRL2, + S2MPS15_REG_B6CTRL1, + S2MPS15_REG_B6CTRL2, + S2MPS15_REG_B7CTRL1, + S2MPS15_REG_B7CTRL2, + S2MPS15_REG_B8CTRL1, + S2MPS15_REG_B8CTRL2, + S2MPS15_REG_B9CTRL1, + S2MPS15_REG_B9CTRL2, + S2MPS15_REG_B10CTRL1, + S2MPS15_REG_B10CTRL2, + S2MPS15_REG_BBCTRL1, + S2MPS15_REG_BBCTRL2, + S2MPS15_REG_BRAMP, + S2MPS15_REG_LDODVS1, + S2MPS15_REG_LDODVS2, + S2MPS15_REG_LDODVS3, + S2MPS15_REG_LDODVS4, + S2MPS15_REG_L1CTRL, + S2MPS15_REG_L2CTRL, + S2MPS15_REG_L3CTRL, + S2MPS15_REG_L4CTRL, + S2MPS15_REG_L5CTRL, + S2MPS15_REG_L6CTRL, + S2MPS15_REG_L7CTRL, + S2MPS15_REG_L8CTRL, + S2MPS15_REG_L9CTRL, + S2MPS15_REG_L10CTRL, + S2MPS15_REG_L11CTRL, + S2MPS15_REG_L12CTRL, + S2MPS15_REG_L13CTRL, + S2MPS15_REG_L14CTRL, + S2MPS15_REG_L15CTRL, + S2MPS15_REG_L16CTRL, + S2MPS15_REG_L17CTRL, + S2MPS15_REG_L18CTRL, + S2MPS15_REG_L19CTRL, + S2MPS15_REG_L20CTRL, + S2MPS15_REG_L21CTRL, + S2MPS15_REG_L22CTRL, + S2MPS15_REG_L23CTRL, + S2MPS15_REG_L24CTRL, + S2MPS15_REG_L25CTRL, + S2MPS15_REG_L26CTRL, + S2MPS15_REG_L27CTRL, + S2MPS15_REG_LDODSCH1, + S2MPS15_REG_LDODSCH2, + S2MPS15_REG_LDODSCH3, + S2MPS15_REG_LDODSCH4, +}; + +/* S2MPS15 regulator ids */ +enum s2mps15_regulators { + S2MPS15_LDO1, + S2MPS15_LDO2, + S2MPS15_LDO3, + S2MPS15_LDO4, + S2MPS15_LDO5, + S2MPS15_LDO6, + S2MPS15_LDO7, + S2MPS15_LDO8, + S2MPS15_LDO9, + S2MPS15_LDO10, + S2MPS15_LDO11, + S2MPS15_LDO12, + S2MPS15_LDO13, + S2MPS15_LDO14, + S2MPS15_LDO15, + S2MPS15_LDO16, + S2MPS15_LDO17, + S2MPS15_LDO18, + S2MPS15_LDO19, + S2MPS15_LDO20, + S2MPS15_LDO21, + S2MPS15_LDO22, + S2MPS15_LDO23, + S2MPS15_LDO24, + S2MPS15_LDO25, + S2MPS15_LDO26, + S2MPS15_LDO27, + S2MPS15_BUCK1, + S2MPS15_BUCK2, + S2MPS15_BUCK3, + S2MPS15_BUCK4, + S2MPS15_BUCK5, + S2MPS15_BUCK6, + S2MPS15_BUCK7, + S2MPS15_BUCK8, + S2MPS15_BUCK9, + S2MPS15_BUCK10, + S2MPS15_BUCK11, + S2MPS15_REGULATOR_MAX, +}; + +#define S2MPS15_LDO_VSEL_MASK (0x3F) +#define S2MPS15_BUCK_VSEL_MASK (0xFF) + +#define S2MPS15_ENABLE_SHIFT (0x06) +#define S2MPS15_ENABLE_MASK (0x03 << S2MPS15_ENABLE_SHIFT) + +#define S2MPS15_LDO_N_VOLTAGES (S2MPS15_LDO_VSEL_MASK + 1) +#define S2MPS15_BUCK_N_VOLTAGES (S2MPS15_BUCK_VSEL_MASK + 1) + +#endif /* __LINUX_MFD_S2MPS15_H */ -- cgit v1.2.3 From a65e5efa7c5faa8c320fe56cc351d47fcd006749 Mon Sep 17 00:00:00 2001 From: Alim Akhtar Date: Fri, 20 Nov 2015 16:07:53 +0530 Subject: rtc: s5m.c: Add support for S2MPS15 RTC RTC found in s2mps15 is almost same as one found on s2mps13 with few differences in RTC_UPDATE register fields, like: 1> Bit[4] and Bit[1] are reversed - On s2mps13 WUDR -> bit[4], AUDR -> bit[1] - On s2mps15 WUDR -> bit[1], AUDR -> bit[4] 2> In case of s2mps13, for alarm register, need to set both WDUR and ADUR high, whereas for s2mps15 only set AUDR to high. 3> On s2mps15, WUDR, RUDR and AUDR functions should never be used at the same time. This patch add required changes to enable s2mps15 rtc timer. Signed-off-by: Alim Akhtar Reviewed-by: Krzysztof Kozlowski Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- drivers/rtc/rtc-s5m.c | 37 +++++++++++++++++++++++++++++++++---- include/linux/mfd/samsung/rtc.h | 2 ++ 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index f2504b4eef34..0d68a85dd429 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -188,6 +188,7 @@ static inline int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val); val &= S5M_ALARM0_STATUS; break; + case S2MPS15X: case S2MPS14X: case S2MPS13X: ret = regmap_read(info->s5m87xx->regmap_pmic, S2MPS14_REG_ST2, @@ -219,9 +220,22 @@ static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info) return ret; } - data |= info->regs->rtc_udr_mask; - if (info->device_type == S5M8763X || info->device_type == S5M8767X) - data |= S5M_RTC_TIME_EN_MASK; + switch (info->device_type) { + case S5M8763X: + case S5M8767X: + data |= info->regs->rtc_udr_mask | S5M_RTC_TIME_EN_MASK; + case S2MPS15X: + /* As per UM, for write time register, set WUDR bit to high */ + data |= S2MPS15_RTC_WUDR_MASK; + break; + case S2MPS14X: + case S2MPS13X: + data |= info->regs->rtc_udr_mask; + break; + default: + return -EINVAL; + } + ret = regmap_write(info->regmap, info->regs->rtc_udr_update, data); if (ret < 0) { @@ -252,6 +266,11 @@ static inline int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) case S5M8767X: data &= ~S5M_RTC_TIME_EN_MASK; break; + case S2MPS15X: + /* As per UM, for write alarm, set A_UDR(bit[4]) to high + * rtc_udr_mask above sets bit[4] + */ + break; case S2MPS14X: data |= S2MPS_RTC_RUDR_MASK; break; @@ -317,7 +336,8 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) u8 data[info->regs->regs_count]; int ret; - if (info->device_type == S2MPS14X || info->device_type == S2MPS13X) { + if (info->device_type == S2MPS15X || info->device_type == S2MPS14X || + info->device_type == S2MPS13X) { ret = regmap_update_bits(info->regmap, info->regs->rtc_udr_update, S2MPS_RTC_RUDR_MASK, S2MPS_RTC_RUDR_MASK); @@ -339,6 +359,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_data_to_tm(data, tm, info->rtc_24hr_mode); @@ -366,6 +387,7 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm) s5m8763_tm_to_data(tm, data); break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: ret = s5m8767_tm_to_data(tm, data); @@ -414,6 +436,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_data_to_tm(data, &alrm->time, info->rtc_24hr_mode); @@ -463,6 +486,7 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: for (i = 0; i < info->regs->regs_count; i++) @@ -508,6 +532,7 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: data[RTC_SEC] |= ALARM_ENABLE_MASK; @@ -548,6 +573,7 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) break; case S5M8767X: + case S2MPS15X: case S2MPS14X: case S2MPS13X: s5m8767_tm_to_data(&alrm->time, data); @@ -631,6 +657,7 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info) ret = regmap_raw_write(info->regmap, S5M_ALARM0_CONF, data, 2); break; + case S2MPS15X: case S2MPS14X: case S2MPS13X: data[0] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT); @@ -679,6 +706,7 @@ static int s5m_rtc_probe(struct platform_device *pdev) return -ENOMEM; switch (platform_get_device_id(pdev)->driver_data) { + case S2MPS15X: case S2MPS14X: case S2MPS13X: regmap_cfg = &s2mps14_rtc_regmap_config; @@ -805,6 +833,7 @@ static const struct platform_device_id s5m_rtc_id[] = { { "s5m-rtc", S5M8767X }, { "s2mps13-rtc", S2MPS13X }, { "s2mps14-rtc", S2MPS14X }, + { "s2mps15-rtc", S2MPS15X }, { }, }; MODULE_DEVICE_TABLE(platform, s5m_rtc_id); diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 29c30ac36020..a65e4655d470 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -107,6 +107,8 @@ enum s2mps_rtc_reg { #define S2MPS_RTC_WUDR_MASK (1 << S2MPS_RTC_WUDR_SHIFT) #define S2MPS13_RTC_AUDR_SHIFT 1 #define S2MPS13_RTC_AUDR_MASK (1 << S2MPS13_RTC_AUDR_SHIFT) +#define S2MPS15_RTC_WUDR_SHIFT 1 +#define S2MPS15_RTC_WUDR_MASK (1 << S2MPS15_RTC_WUDR_SHIFT) #define S2MPS_RTC_RUDR_SHIFT 0 #define S2MPS_RTC_RUDR_MASK (1 << S2MPS_RTC_RUDR_SHIFT) #define RTC_TCON_SHIFT 1 -- cgit v1.2.3 From 414ca017a54d26c3a58ed1504884e51448d22ae1 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 20 Nov 2015 10:48:02 -0500 Subject: nfsd4: fix gss-proxy 4.1 mounts for some AD principals The principal name on a gss cred is used to setup the NFSv4.0 callback, which has to have a client principal name to authenticate to. That code wants the name to be in the form servicetype@hostname. rpc.svcgssd passes down such names (and passes down no principal name at all in the case the principal isn't a service principal). gss-proxy always passes down the principal name, and passes it down in the form servicetype/hostname@REALM. So we've been munging the name gss-proxy passes down into the format the NFSv4.0 callback code expects, or throwing away the name if we can't. Since the introduction of the MACH_CRED enforcement in NFSv4.1, we've also been using the principal name to verify that certain operations are done as the same principal as was used on the original EXCHANGE_ID call. For that application, the original name passed down by gss-proxy is also useful. Lack of that name in some cases was causing some kerberized NFSv4.1 mount failures in an Active Directory environment. This fix only works in the gss-proxy case. The fix for legacy rpc.svcgssd would be more involved, and rpc.svcgssd already has other problems in the AD case. Reported-and-tested-by: James Ralston Acked-by: Simo Sorce Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4state.c | 10 +++++++++- include/linux/sunrpc/svcauth.h | 9 ++++++++- net/sunrpc/auth_gss/gss_rpc_upcall.c | 3 +++ 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index ed58ced6fa8b..113ecbfac25c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1873,6 +1873,10 @@ static int copy_cred(struct svc_cred *target, struct svc_cred *source) int ret; ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal); + if (ret) + return ret; + ret = strdup_if_nonnull(&target->cr_raw_principal, + source->cr_raw_principal); if (ret) return ret; target->cr_flavor = source->cr_flavor; @@ -1978,6 +1982,9 @@ static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp) return false; if (!svc_rqst_integrity_protected(rqstp)) return false; + if (cl->cl_cred.cr_raw_principal) + return 0 == strcmp(cl->cl_cred.cr_raw_principal, + cr->cr_raw_principal); if (!cr->cr_principal) return false; return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal); @@ -2390,7 +2397,8 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, * Which is a bug, really. Anyway, we can't enforce * MACH_CRED in that case, better to give up now: */ - if (!new->cl_cred.cr_principal) { + if (!new->cl_cred.cr_principal && + !new->cl_cred.cr_raw_principal) { status = nfserr_serverfault; goto out_nolock; } diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 8d71d6577459..c00f53a4ccdd 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -23,13 +23,19 @@ struct svc_cred { kgid_t cr_gid; struct group_info *cr_group_info; u32 cr_flavor; /* pseudoflavor */ - char *cr_principal; /* for gss */ + /* name of form servicetype/hostname@REALM, passed down by + * gss-proxy: */ + char *cr_raw_principal; + /* name of form servicetype@hostname, passed down by + * rpc.svcgssd, or computed from the above: */ + char *cr_principal; struct gss_api_mech *cr_gss_mech; }; static inline void init_svc_cred(struct svc_cred *cred) { cred->cr_group_info = NULL; + cred->cr_raw_principal = NULL; cred->cr_principal = NULL; cred->cr_gss_mech = NULL; } @@ -38,6 +44,7 @@ static inline void free_svc_cred(struct svc_cred *cred) { if (cred->cr_group_info) put_group_info(cred->cr_group_info); + kfree(cred->cr_raw_principal); kfree(cred->cr_principal); gss_mech_put(cred->cr_gss_mech); init_svc_cred(cred); diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 59eeed43eda2..f0c6a8c78a56 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -326,6 +326,9 @@ int gssp_accept_sec_context_upcall(struct net *net, if (data->found_creds && client_name.data != NULL) { char *c; + data->creds.cr_raw_principal = kstrndup(client_name.data, + client_name.len, GFP_KERNEL); + data->creds.cr_principal = kstrndup(client_name.data, client_name.len, GFP_KERNEL); if (data->creds.cr_principal) { -- cgit v1.2.3 From c0ea88b890d67cff2667188f14189d8346e89a0f Mon Sep 17 00:00:00 2001 From: Nikita Kiryanov Date: Wed, 25 Nov 2015 13:59:04 +0200 Subject: regulator: tps65218: add support for LS3 current regulator Add support for TPS65218 LS3 current regulator, which is capable of 4 current input limit modes: 100, 200, 500, and 1000 uA. Signed-off-by: Nikita Kiryanov Signed-off-by: Mark Brown --- drivers/regulator/tps65218-regulator.c | 137 +++++++++++++++++++++++++-------- include/linux/mfd/tps65218.h | 7 +- include/linux/regulator/driver.h | 2 + 3 files changed, 115 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c index a02c1b961039..a5e5634eeb9e 100644 --- a/drivers/regulator/tps65218-regulator.c +++ b/drivers/regulator/tps65218-regulator.c @@ -27,19 +27,22 @@ #include #include -enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4, DCDC5, DCDC6, LDO1 }; +enum tps65218_regulators { DCDC1, DCDC2, DCDC3, DCDC4, + DCDC5, DCDC6, LDO1, LS3 }; -#define TPS65218_REGULATOR(_name, _id, _ops, _n, _vr, _vm, _er, _em, \ - _lr, _nlr, _delay, _fuv) \ +#define TPS65218_REGULATOR(_name, _id, _type, _ops, _n, _vr, _vm, _er, _em, \ + _cr, _cm, _lr, _nlr, _delay, _fuv) \ { \ .name = _name, \ .id = _id, \ .ops = &_ops, \ .n_voltages = _n, \ - .type = REGULATOR_VOLTAGE, \ + .type = _type, \ .owner = THIS_MODULE, \ .vsel_reg = _vr, \ .vsel_mask = _vm, \ + .csel_reg = _cr, \ + .csel_mask = _cm, \ .enable_reg = _er, \ .enable_mask = _em, \ .volt_table = NULL, \ @@ -80,6 +83,7 @@ static struct tps_info tps65218_pmic_regs[] = { TPS65218_INFO(DCDC5, "DCDC5", 1000000, 1000000), TPS65218_INFO(DCDC6, "DCDC6", 1800000, 1800000), TPS65218_INFO(LDO1, "LDO1", 900000, 3400000), + TPS65218_INFO(LS3, "LS3", -1, -1), }; #define TPS65218_OF_MATCH(comp, label) \ @@ -96,6 +100,7 @@ static const struct of_device_id tps65218_of_match[] = { TPS65218_OF_MATCH("ti,tps65218-dcdc5", tps65218_pmic_regs[DCDC5]), TPS65218_OF_MATCH("ti,tps65218-dcdc6", tps65218_pmic_regs[DCDC6]), TPS65218_OF_MATCH("ti,tps65218-ldo1", tps65218_pmic_regs[LDO1]), + TPS65218_OF_MATCH("ti,tps65218-ls3", tps65218_pmic_regs[LS3]), { } }; MODULE_DEVICE_TABLE(of, tps65218_of_match); @@ -175,6 +180,68 @@ static struct regulator_ops tps65218_ldo1_dcdc34_ops = { .map_voltage = regulator_map_voltage_linear_range, }; +static const int ls3_currents[] = { 100, 200, 500, 1000 }; + +static int tps65218_pmic_set_input_current_lim(struct regulator_dev *dev, + int lim_uA) +{ + unsigned int index = 0; + unsigned int num_currents = ARRAY_SIZE(ls3_currents); + struct tps65218 *tps = rdev_get_drvdata(dev); + + while (index < num_currents && ls3_currents[index] != lim_uA) + index++; + + if (index == num_currents) + return -EINVAL; + + return tps65218_set_bits(tps, dev->desc->csel_reg, dev->desc->csel_mask, + index << 2, TPS65218_PROTECT_L1); +} + +static int tps65218_pmic_set_current_limit(struct regulator_dev *dev, + int min_uA, int max_uA) +{ + int index = 0; + unsigned int num_currents = ARRAY_SIZE(ls3_currents); + struct tps65218 *tps = rdev_get_drvdata(dev); + + while (index < num_currents && ls3_currents[index] < max_uA) + index++; + + index--; + + if (index < 0 || ls3_currents[index] < min_uA) + return -EINVAL; + + return tps65218_set_bits(tps, dev->desc->csel_reg, dev->desc->csel_mask, + index << 2, TPS65218_PROTECT_L1); +} + +static int tps65218_pmic_get_current_limit(struct regulator_dev *dev) +{ + int retval; + unsigned int index; + struct tps65218 *tps = rdev_get_drvdata(dev); + + retval = tps65218_reg_read(tps, dev->desc->csel_reg, &index); + if (retval < 0) + return retval; + + index = (index & dev->desc->csel_mask) >> 2; + + return ls3_currents[index]; +} + +static struct regulator_ops tps65218_ls3_ops = { + .is_enabled = regulator_is_enabled_regmap, + .enable = tps65218_pmic_enable, + .disable = tps65218_pmic_disable, + .set_input_current_limit = tps65218_pmic_set_input_current_lim, + .set_current_limit = tps65218_pmic_set_current_limit, + .get_current_limit = tps65218_pmic_get_current_limit, +}; + /* Operations permitted on DCDC5, DCDC6 */ static struct regulator_ops tps65218_dcdc56_pmic_ops = { .is_enabled = regulator_is_enabled_regmap, @@ -183,36 +250,46 @@ static struct regulator_ops tps65218_dcdc56_pmic_ops = { }; static const struct regulator_desc regulators[] = { - TPS65218_REGULATOR("DCDC1", TPS65218_DCDC_1, tps65218_dcdc12_ops, 64, - TPS65218_REG_CONTROL_DCDC1, - TPS65218_CONTROL_DCDC1_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC1_EN, - dcdc1_dcdc2_ranges, 2, 4000, 0), - TPS65218_REGULATOR("DCDC2", TPS65218_DCDC_2, tps65218_dcdc12_ops, 64, - TPS65218_REG_CONTROL_DCDC2, - TPS65218_CONTROL_DCDC2_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC2_EN, - dcdc1_dcdc2_ranges, 2, 4000, 0), - TPS65218_REGULATOR("DCDC3", TPS65218_DCDC_3, tps65218_ldo1_dcdc34_ops, - 64, TPS65218_REG_CONTROL_DCDC3, + TPS65218_REGULATOR("DCDC1", TPS65218_DCDC_1, REGULATOR_VOLTAGE, + tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC1, + TPS65218_CONTROL_DCDC1_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC1_EN, 0, 0, dcdc1_dcdc2_ranges, + 2, 4000, 0), + TPS65218_REGULATOR("DCDC2", TPS65218_DCDC_2, REGULATOR_VOLTAGE, + tps65218_dcdc12_ops, 64, TPS65218_REG_CONTROL_DCDC2, + TPS65218_CONTROL_DCDC2_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC2_EN, 0, 0, dcdc1_dcdc2_ranges, + 2, 4000, 0), + TPS65218_REGULATOR("DCDC3", TPS65218_DCDC_3, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 64, + TPS65218_REG_CONTROL_DCDC3, TPS65218_CONTROL_DCDC3_MASK, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC3_EN, ldo1_dcdc3_ranges, 2, 0, 0), - TPS65218_REGULATOR("DCDC4", TPS65218_DCDC_4, tps65218_ldo1_dcdc34_ops, - 53, TPS65218_REG_CONTROL_DCDC4, - TPS65218_CONTROL_DCDC4_MASK, - TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC4_EN, - dcdc4_ranges, 2, 0, 0), - TPS65218_REGULATOR("DCDC5", TPS65218_DCDC_5, tps65218_dcdc56_pmic_ops, - 1, -1, -1, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC5_EN, NULL, 0, 0, 1000000), - TPS65218_REGULATOR("DCDC6", TPS65218_DCDC_6, tps65218_dcdc56_pmic_ops, - 1, -1, -1, TPS65218_REG_ENABLE1, - TPS65218_ENABLE1_DC6_EN, NULL, 0, 0, 1800000), - TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, tps65218_ldo1_dcdc34_ops, 64, + TPS65218_ENABLE1_DC3_EN, 0, 0, ldo1_dcdc3_ranges, 2, + 0, 0), + TPS65218_REGULATOR("DCDC4", TPS65218_DCDC_4, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 53, + TPS65218_REG_CONTROL_DCDC4, + TPS65218_CONTROL_DCDC4_MASK, TPS65218_REG_ENABLE1, + TPS65218_ENABLE1_DC4_EN, 0, 0, dcdc4_ranges, 2, + 0, 0), + TPS65218_REGULATOR("DCDC5", TPS65218_DCDC_5, REGULATOR_VOLTAGE, + tps65218_dcdc56_pmic_ops, 1, -1, -1, + TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC5_EN, 0, 0, + NULL, 0, 0, 1000000), + TPS65218_REGULATOR("DCDC6", TPS65218_DCDC_6, REGULATOR_VOLTAGE, + tps65218_dcdc56_pmic_ops, 1, -1, -1, + TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC6_EN, 0, 0, + NULL, 0, 0, 1800000), + TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, REGULATOR_VOLTAGE, + tps65218_ldo1_dcdc34_ops, 64, TPS65218_REG_CONTROL_LDO1, TPS65218_CONTROL_LDO1_MASK, TPS65218_REG_ENABLE2, - TPS65218_ENABLE2_LDO1_EN, ldo1_dcdc3_ranges, + TPS65218_ENABLE2_LDO1_EN, 0, 0, ldo1_dcdc3_ranges, 2, 0, 0), + TPS65218_REGULATOR("LS3", TPS65218_LS_3, REGULATOR_CURRENT, + tps65218_ls3_ops, 0, 0, 0, TPS65218_REG_ENABLE2, + TPS65218_ENABLE2_LS3_EN, TPS65218_REG_CONFIG2, + TPS65218_CONFIG2_LS3ILIM_MASK, NULL, 0, 0, 0), }; static int tps65218_regulator_probe(struct platform_device *pdev) diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index 2f9b593246ee..d58f3b5f585a 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -200,6 +200,8 @@ enum tps65218_regulator_id { TPS65218_DCDC_4, TPS65218_DCDC_5, TPS65218_DCDC_6, + /* LS's */ + TPS65218_LS_3, /* LDOs */ TPS65218_LDO_1, }; @@ -210,8 +212,11 @@ enum tps65218_regulator_id { #define TPS65218_NUM_DCDC 6 /* Number of LDO voltage regulators available */ #define TPS65218_NUM_LDO 1 +/* Number of total LS current regulators available */ +#define TPS65218_NUM_LS 1 /* Number of total regulators available */ -#define TPS65218_NUM_REGULATOR (TPS65218_NUM_DCDC + TPS65218_NUM_LDO) +#define TPS65218_NUM_REGULATOR (TPS65218_NUM_DCDC + TPS65218_NUM_LDO \ + + TPS65218_NUM_LS) /* Define the TPS65218 IRQ numbers */ enum tps65218_irqs { diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 9c2903e58adb..16ac9e108806 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -302,6 +302,8 @@ struct regulator_desc { unsigned int vsel_reg; unsigned int vsel_mask; + unsigned int csel_reg; + unsigned int csel_mask; unsigned int apply_reg; unsigned int apply_bit; unsigned int enable_reg; -- cgit v1.2.3 From 749de3dac5e4d65cbed3b58f89c56883e31d1a5a Mon Sep 17 00:00:00 2001 From: Nicola Corna Date: Thu, 29 Oct 2015 12:34:23 +0100 Subject: i2c: add i2c quirk flag for unsupported clock stretching Add I2C_AQ_NO_CLK_STRETCH quirk flag, to be used when clock stretching is not supported. Signed-off-by: Nicola Corna Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 768063baafbf..96970024883f 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -493,6 +493,8 @@ struct i2c_adapter_quirks { /* convenience macro for typical write-then read case */ #define I2C_AQ_COMB_WRITE_THEN_READ (I2C_AQ_COMB | I2C_AQ_COMB_WRITE_FIRST | \ I2C_AQ_COMB_READ_SECOND | I2C_AQ_COMB_SAME_ADDR) +/* clock stretching is not supported */ +#define I2C_AQ_NO_CLK_STRETCH BIT(4) /* * i2c_adapter is the structure used to identify a physical i2c bus along -- cgit v1.2.3 From cfa576db834cacc1bb01bc41b2f61a8b578e67c5 Mon Sep 17 00:00:00 2001 From: Nicola Corna Date: Thu, 29 Oct 2015 12:34:26 +0100 Subject: i2c: add i2c_check_quirks helper function This patch adds a i2c_check_quirks helper function to check the quirk flags of an i2c adapter, in a similar way to i2c_check_functionality. Signed-off-by: Nicola Corna Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 96970024883f..51028f351d13 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -617,6 +617,20 @@ static inline int i2c_check_functionality(struct i2c_adapter *adap, u32 func) return (func & i2c_get_functionality(adap)) == func; } +/** + * i2c_check_quirks() - Function for checking the quirk flags in an i2c adapter + * @adap: i2c adapter + * @quirks: quirk flags + * + * Return: true if the adapter has all the specified quirk flags, false if not + */ +static inline bool i2c_check_quirks(struct i2c_adapter *adap, u64 quirks) +{ + if (!adap->quirks) + return false; + return (adap->quirks->flags & quirks) == quirks; +} + /* Return the adapter number for a specific adapter */ static inline int i2c_adapter_id(struct i2c_adapter *adap) { -- cgit v1.2.3 From 2c81de771f38e54324ede3f24118f4852570b384 Mon Sep 17 00:00:00 2001 From: RafaÅ‚ MiÅ‚ecki Date: Thu, 26 Nov 2015 09:05:04 +0100 Subject: mtd: spi-nor: include mtd.h header for struct mtd_info definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far struct spi_nor was using just a pointer to struct mtd_info so it wasn't needed to have it fully defined there. After recent change we embed whole struct so we need to include a proper header. Fixes: 1976367173a4 ("mtd: spi-nor: embed struct mtd_info within struct spi_nor") Signed-off-by: RafaÅ‚ MiÅ‚ecki Signed-off-by: Brian Norris --- include/linux/mtd/spi-nor.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 7bed97471e53..fac3f6f53981 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -12,6 +12,7 @@ #include #include +#include /* * Manufacturer IDs @@ -117,8 +118,6 @@ enum spi_nor_option_flags { SNOR_F_USE_FSR = BIT(0), }; -struct mtd_info; - /** * struct spi_nor - Structure for defining a the SPI NOR layer * @mtd: point to a mtd_info structure -- cgit v1.2.3 From fe7579d6122f2869d00b55842bca9e2a9be51607 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 24 Nov 2015 23:09:02 +0100 Subject: mtd: cfi: don't warn about broken geometry for !CONFIG_MTD The linux/mtd/map.h header file is included by a couple of platform specific files that are built even when CONFIG_MTD is disabled, and we always get warning "No CONFIG_MTD_MAP_BANK_WIDTH_xx selected. No NOR chip support can work" in that case. This adds an #ifdef around the pointless warning, as everything is really fine when we don't build the drivers anyway. Signed-off-by: Arnd Bergmann Signed-off-by: Brian Norris --- include/linux/mtd/map.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 366cf77953b5..58f3ba709ade 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -142,7 +142,9 @@ #endif #ifndef map_bankwidth +#ifdef CONFIG_MTD #warning "No CONFIG_MTD_MAP_BANK_WIDTH_xx selected. No NOR chip support can work" +#endif static inline int map_bankwidth(void *map) { BUG(); -- cgit v1.2.3 From 3b1884c24c98dada51fc4b05735773f0078711d2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 30 Nov 2015 15:28:06 +0100 Subject: spi: Uninline spi_unregister_device() Uninline spi_unregister_device() in preparation of adding more code to it. Add kerneldoc documentation while we're at it. Signed-off-by: Geert Uytterhoeven Signed-off-by: Mark Brown --- drivers/spi/spi.c | 14 ++++++++++++++ include/linux/spi/spi.h | 7 +------ 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index e2415be209d5..3f135cc9a70e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -604,6 +604,20 @@ struct spi_device *spi_new_device(struct spi_master *master, } EXPORT_SYMBOL_GPL(spi_new_device); +/** + * spi_unregister_device - unregister a single SPI device + * @spi: spi_device to unregister + * + * Start making the passed SPI device vanish. Normally this would be handled + * by spi_unregister_master(). + */ +void spi_unregister_device(struct spi_device *spi) +{ + if (spi) + device_unregister(&spi->dev); +} +EXPORT_SYMBOL_GPL(spi_unregister_device); + static void spi_match_master_to_boardinfo(struct spi_master *master, struct spi_board_info *bi) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cce80e6dc7d1..075bede66521 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1115,12 +1115,7 @@ spi_add_device(struct spi_device *spi); extern struct spi_device * spi_new_device(struct spi_master *, struct spi_board_info *); -static inline void -spi_unregister_device(struct spi_device *spi) -{ - if (spi) - device_unregister(&spi->dev); -} +extern void spi_unregister_device(struct spi_device *spi); extern const struct spi_device_id * spi_get_device_id(const struct spi_device *sdev); -- cgit v1.2.3 From de64aa9ec129ba627634088f662a4d09e356ddb6 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 23 Nov 2015 11:23:07 +0100 Subject: mtd: nand: fix ONFI parameter page layout src_ssync_features field is only 1 byte large, and the 4th reserved area is actually 8 bytes large. Fixes: d1e1f4e42b5 ("mtd: nand: add support for reading ONFI parameters from NAND device") Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 056d1650eb89..eaf48b5a95dd 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -276,7 +276,7 @@ struct nand_onfi_params { __le16 t_r; __le16 t_ccs; __le16 src_sync_timing_mode; - __le16 src_ssync_features; + u8 src_ssync_features; __le16 clk_pin_capacitance_typ; __le16 io_pin_capacitance_typ; __le16 input_pin_capacitance_typ; @@ -284,7 +284,7 @@ struct nand_onfi_params { u8 driver_strength_support; __le16 t_int_r; __le16 t_ald; - u8 reserved4[7]; + u8 reserved4[8]; /* vendor */ __le16 vendor_revision; -- cgit v1.2.3 From 74e98be45fe069fcdb00f35eccbb179309ab65cd Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 1 Dec 2015 11:08:32 -0800 Subject: mtd: nand: fix typo (t_ald -> t_adl) It's "ADL" ("ALE to data loading" time) not "ALD". Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- include/linux/mtd/nand.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index eaf48b5a95dd..fad634ea1685 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -283,7 +283,7 @@ struct nand_onfi_params { u8 input_pin_capacitance_max; u8 driver_strength_support; __le16 t_int_r; - __le16 t_ald; + __le16 t_adl; u8 reserved4[8]; /* vendor */ @@ -407,7 +407,7 @@ struct nand_jedec_params { __le16 input_pin_capacitance_typ; __le16 clk_pin_capacitance_typ; u8 driver_strength_support; - __le16 t_ald; + __le16 t_adl; u8 reserved4[36]; /* ECC and endurance block */ -- cgit v1.2.3 From 6fb8ac81cb3125aafc7136f2ef0145da792bab94 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 28 Nov 2015 16:07:10 +0100 Subject: USB: constify usb_mon_operations structure The usb_mon_operations structure is never modified, so declare it as const. Done with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 4 ++-- drivers/usb/mon/mon_main.c | 2 +- include/linux/usb/hcd.h | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 1c102d60cd9f..df0e3b92533a 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -3000,7 +3000,7 @@ EXPORT_SYMBOL_GPL(usb_hcd_platform_shutdown); #if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE) -struct usb_mon_operations *mon_ops; +const struct usb_mon_operations *mon_ops; /* * The registration is unlocked. @@ -3010,7 +3010,7 @@ struct usb_mon_operations *mon_ops; * symbols from usbcore, usbcore gets referenced and cannot be unloaded first. */ -int usb_mon_register (struct usb_mon_operations *ops) +int usb_mon_register(const struct usb_mon_operations *ops) { if (mon_ops) diff --git a/drivers/usb/mon/mon_main.c b/drivers/usb/mon/mon_main.c index f7c292f4891e..fec3f1128fdc 100644 --- a/drivers/usb/mon/mon_main.c +++ b/drivers/usb/mon/mon_main.c @@ -241,7 +241,7 @@ static struct notifier_block mon_nb = { /* * Ops */ -static struct usb_mon_operations mon_ops_0 = { +static const struct usb_mon_operations mon_ops_0 = { .urb_submit = mon_submit, .urb_submit_error = mon_submit_error, .urb_complete = mon_complete, diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index f89c24bd53a4..4dcf8446dbcd 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -660,7 +660,7 @@ struct usb_mon_operations { /* void (*urb_unlink)(struct usb_bus *bus, struct urb *urb); */ }; -extern struct usb_mon_operations *mon_ops; +extern const struct usb_mon_operations *mon_ops; static inline void usbmon_urb_submit(struct usb_bus *bus, struct urb *urb) { @@ -682,7 +682,7 @@ static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb, (*mon_ops->urb_complete)(bus, urb, status); } -int usb_mon_register(struct usb_mon_operations *ops); +int usb_mon_register(const struct usb_mon_operations *ops); void usb_mon_deregister(void); #else -- cgit v1.2.3 From bf5ce5bf3cc7136fd7fe5e8999a580bc93a9c8f6 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Nov 2015 16:26:32 +0800 Subject: usb: core: lpm: fix usb3_hardware_lpm sysfs node Commit 655fe4effe0f ("usbcore: add sysfs support to xHCI usb3 hardware LPM") introduced usb3_hardware_lpm sysfs node. This doesn't show the correct status of USB3 U1 and U2 LPM status. This patch fixes this by replacing usb3_hardware_lpm with two nodes, usb3_hardware_lpm_u1 (for U1) and usb3_hardware_lpm_u2 (for U2), and recording the U1/U2 LPM status in right places. This patch should be back-ported to kernels as old as 4.3, that contains Commit 655fe4effe0f ("usbcore: add sysfs support to xHCI usb3 hardware LPM"). Cc: stable@vger.kernel.org Signed-off-by: Lu Baolu Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-usb | 16 ++++++++------ Documentation/usb/power-management.txt | 11 +++++----- drivers/usb/core/hub.c | 39 +++++++++++++++++++++++++-------- drivers/usb/core/sysfs.c | 31 +++++++++++++++++++++----- include/linux/usb.h | 4 ++++ 5 files changed, 75 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index 3a4abfc44f5e..136ba17d2da0 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -134,19 +134,21 @@ Description: enabled for the device. Developer can write y/Y/1 or n/N/0 to the file to enable/disable the feature. -What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm -Date: June 2015 +What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1 + /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2 +Date: November 2015 Contact: Kevin Strasser + Lu Baolu Description: If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if - the check is is passed and the host supports USB3 hardware LPM, + the check is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be enabled for the device and the USB - device directory will contain a file named - power/usb3_hardware_lpm. The file holds a string value (enable - or disable) indicating whether or not USB3 hardware LPM is - enabled for the device. + device directory will contain two files named + power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These + files hold a string value (enable or disable) indicating whether + or not USB3 hardware LPM U1 or U2 is enabled for the device. What: /sys/bus/usb/devices/.../removable Date: February 2012 diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index 4a15c90bc11d..0a94ffe17ab6 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm. can write y/Y/1 or n/N/0 to the file to enable/disable USB2 hardware LPM manually. This is for test purpose mainly. - power/usb3_hardware_lpm + power/usb3_hardware_lpm_u1 + power/usb3_hardware_lpm_u2 When a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if the check is is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be - enabled for the device and this file will be created. - The file holds a string value (enable or disable) - indicating whether or not USB3 hardware LPM is - enabled for the device. + enabled for the device and these files will be created. + The files hold a string value (enable or disable) + indicating whether or not USB3 hardware LPM U1 or U2 + is enabled for the device. USB Port Power Control ---------------------- diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index bdeadc112d29..59f998e60030 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -3875,17 +3875,30 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, return; } - if (usb_set_lpm_timeout(udev, state, timeout)) + if (usb_set_lpm_timeout(udev, state, timeout)) { /* If we can't set the parent hub U1/U2 timeout, * device-initiated LPM won't be allowed either, so let the xHCI * host know that this link state won't be enabled. */ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state); + } else { + /* Only a configured device will accept the Set Feature + * U1/U2_ENABLE + */ + if (udev->actconfig) + usb_set_device_initiated_lpm(udev, state, true); - /* Only a configured device will accept the Set Feature U1/U2_ENABLE */ - else if (udev->actconfig) - usb_set_device_initiated_lpm(udev, state, true); - + /* As soon as usb_set_lpm_timeout(timeout) returns 0, the + * hub-initiated LPM is enabled. Thus, LPM is enabled no + * matter the result of usb_set_device_initiated_lpm(). + * The only difference is whether device is able to initiate + * LPM. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 1; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 1; + } } /* @@ -3925,6 +3938,18 @@ static int usb_disable_link_state(struct usb_hcd *hcd, struct usb_device *udev, dev_warn(&udev->dev, "Could not disable xHCI %s timeout, " "bus schedule bandwidth may be impacted.\n", usb3_lpm_names[state]); + + /* As soon as usb_set_lpm_timeout(0) return 0, hub initiated LPM + * is disabled. Hub will disallows link to enter U1/U2 as well, + * even device is initiating LPM. Hence LPM is disabled if hub LPM + * timeout set to 0, no matter device-initiated LPM is disabled or + * not. + */ + if (state == USB3_LPM_U1) + udev->usb3_lpm_u1_enabled = 0; + else if (state == USB3_LPM_U2) + udev->usb3_lpm_u2_enabled = 0; + return 0; } @@ -3959,8 +3984,6 @@ int usb_disable_lpm(struct usb_device *udev) if (usb_disable_link_state(hcd, udev, USB3_LPM_U2)) goto enable_lpm; - udev->usb3_lpm_enabled = 0; - return 0; enable_lpm: @@ -4018,8 +4041,6 @@ void usb_enable_lpm(struct usb_device *udev) usb_enable_link_state(hcd, udev, USB3_LPM_U1); usb_enable_link_state(hcd, udev, USB3_LPM_U2); - - udev->usb3_lpm_enabled = 1; } EXPORT_SYMBOL_GPL(usb_enable_lpm); diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index d9ec2de6c4cf..65b6e6b84043 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -531,7 +531,7 @@ static ssize_t usb2_lpm_besl_store(struct device *dev, } static DEVICE_ATTR_RW(usb2_lpm_besl); -static ssize_t usb3_hardware_lpm_show(struct device *dev, +static ssize_t usb3_hardware_lpm_u1_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_device *udev = to_usb_device(dev); @@ -539,7 +539,7 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, usb_lock_device(udev); - if (udev->usb3_lpm_enabled) + if (udev->usb3_lpm_u1_enabled) p = "enabled"; else p = "disabled"; @@ -548,7 +548,26 @@ static ssize_t usb3_hardware_lpm_show(struct device *dev, return sprintf(buf, "%s\n", p); } -static DEVICE_ATTR_RO(usb3_hardware_lpm); +static DEVICE_ATTR_RO(usb3_hardware_lpm_u1); + +static ssize_t usb3_hardware_lpm_u2_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct usb_device *udev = to_usb_device(dev); + const char *p; + + usb_lock_device(udev); + + if (udev->usb3_lpm_u2_enabled) + p = "enabled"; + else + p = "disabled"; + + usb_unlock_device(udev); + + return sprintf(buf, "%s\n", p); +} +static DEVICE_ATTR_RO(usb3_hardware_lpm_u2); static struct attribute *usb2_hardware_lpm_attr[] = { &dev_attr_usb2_hardware_lpm.attr, @@ -562,7 +581,8 @@ static struct attribute_group usb2_hardware_lpm_attr_group = { }; static struct attribute *usb3_hardware_lpm_attr[] = { - &dev_attr_usb3_hardware_lpm.attr, + &dev_attr_usb3_hardware_lpm_u1.attr, + &dev_attr_usb3_hardware_lpm_u2.attr, NULL, }; static struct attribute_group usb3_hardware_lpm_attr_group = { @@ -592,7 +612,8 @@ static int add_power_attributes(struct device *dev) if (udev->usb2_hw_lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb2_hardware_lpm_attr_group); - if (udev->lpm_capable == 1) + if (udev->speed == USB_SPEED_SUPER && + udev->lpm_capable == 1) rc = sysfs_merge_group(&dev->kobj, &usb3_hardware_lpm_attr_group); } diff --git a/include/linux/usb.h b/include/linux/usb.h index b9a28074210f..b79925dd2b41 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -511,6 +511,8 @@ struct usb3_lpm_parameters { * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled * @usb3_lpm_enabled: USB3 hardware LPM enabled + * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled + * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -584,6 +586,8 @@ struct usb_device { unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; unsigned usb3_lpm_enabled:1; + unsigned usb3_lpm_u1_enabled:1; + unsigned usb3_lpm_u2_enabled:1; int string_langid; /* static strings from the device */ -- cgit v1.2.3 From 498378d9d2c12d97318028f1a648d98ee7568430 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 14 Nov 2015 16:26:34 +0800 Subject: usb: core: lpm: remove usb3_lpm_enabled in usb_device Commit 8306095fd2c1 ("USB: Disable USB 3.0 LPM in critical sections.") adds usb3_lpm_enabled member to struct usb_device. There is no reference to this member now. Hence, it could be removed. Signed-off-by: Lu Baolu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index b79925dd2b41..89533ba38691 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -510,7 +510,6 @@ struct usb3_lpm_parameters { * @usb2_hw_lpm_besl_capable: device can perform USB2 hardware BESL LPM * @usb2_hw_lpm_enabled: USB2 hardware LPM is enabled * @usb2_hw_lpm_allowed: Userspace allows USB 2.0 LPM to be enabled - * @usb3_lpm_enabled: USB3 hardware LPM enabled * @usb3_lpm_u1_enabled: USB3 hardware U1 LPM enabled * @usb3_lpm_u2_enabled: USB3 hardware U2 LPM enabled * @string_langid: language ID for strings @@ -585,7 +584,6 @@ struct usb_device { unsigned usb2_hw_lpm_besl_capable:1; unsigned usb2_hw_lpm_enabled:1; unsigned usb2_hw_lpm_allowed:1; - unsigned usb3_lpm_enabled:1; unsigned usb3_lpm_u1_enabled:1; unsigned usb3_lpm_u2_enabled:1; int string_langid; -- cgit v1.2.3 From b662f809d41009749a9ee6f9a4db3d9af579e171 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 9 Nov 2015 09:14:00 +0200 Subject: iio: core: Introduce IIO software triggers A software trigger associates an IIO device trigger with a software interrupt source (e.g: timer, sysfs). This patch adds the generic infrastructure for handling software triggers. Software interrupts sources are kept in a iio_trigger_types_list and registered separately when the associated kernel module is loaded. Software triggers can be created directly from drivers or from user space via configfs interface. To sum up, this dynamically creates "triggers" group to be found under /config/iio/triggers and offers the possibility of dynamically creating trigger types groups. The first supported trigger type is "hrtimer" found under /config/iio/triggers/hrtimer. Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- drivers/iio/Kconfig | 8 ++ drivers/iio/Makefile | 1 + drivers/iio/industrialio-sw-trigger.c | 183 ++++++++++++++++++++++++++++++++++ include/linux/iio/sw_trigger.h | 71 +++++++++++++ 4 files changed, 263 insertions(+) create mode 100644 drivers/iio/industrialio-sw-trigger.c create mode 100644 include/linux/iio/sw_trigger.h (limited to 'include/linux') diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index 9509b8a4c551..ac8715e56ba1 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -46,6 +46,14 @@ config IIO_CONSUMERS_PER_TRIGGER This value controls the maximum number of consumers that a given trigger may handle. Default is 2. +config IIO_SW_TRIGGER + tristate "Enable software triggers support" + select IIO_CONFIGFS + help + Provides IIO core support for software triggers. A software + trigger can be created via configfs or directly by a driver + using the API provided. + config IIO_TRIGGERED_EVENT tristate select IIO_TRIGGER diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile index 39d119f18f2e..f670b82298aa 100644 --- a/drivers/iio/Makefile +++ b/drivers/iio/Makefile @@ -8,6 +8,7 @@ industrialio-$(CONFIG_IIO_BUFFER) += industrialio-buffer.o industrialio-$(CONFIG_IIO_TRIGGER) += industrialio-trigger.o obj-$(CONFIG_IIO_CONFIGFS) += industrialio-configfs.o +obj-$(CONFIG_IIO_SW_TRIGGER) += industrialio-sw-trigger.o obj-$(CONFIG_IIO_TRIGGERED_EVENT) += industrialio-triggered-event.o obj-y += accel/ diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c new file mode 100644 index 000000000000..4825cfd9c4ea --- /dev/null +++ b/drivers/iio/industrialio-sw-trigger.c @@ -0,0 +1,183 @@ +/* + * The Industrial I/O core, software trigger functions + * + * Copyright (c) 2015 Intel Corporation + * + * 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. + */ + +#include +#include +#include +#include +#include + +#include +#include + +static struct config_group *iio_triggers_group; +static struct config_item_type iio_trigger_type_group_type; + +static struct config_item_type iio_triggers_group_type = { + .ct_owner = THIS_MODULE, +}; + +static LIST_HEAD(iio_trigger_types_list); +static DEFINE_MUTEX(iio_trigger_types_lock); + +static +struct iio_sw_trigger_type *__iio_find_sw_trigger_type(const char *name, + unsigned len) +{ + struct iio_sw_trigger_type *t = NULL, *iter; + + list_for_each_entry(iter, &iio_trigger_types_list, list) + if (!strcmp(iter->name, name)) { + t = iter; + break; + } + + return t; +} + +int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t) +{ + struct iio_sw_trigger_type *iter; + int ret = 0; + + mutex_lock(&iio_trigger_types_lock); + iter = __iio_find_sw_trigger_type(t->name, strlen(t->name)); + if (iter) + ret = -EBUSY; + else + list_add_tail(&t->list, &iio_trigger_types_list); + mutex_unlock(&iio_trigger_types_lock); + + if (ret) + return ret; + + t->group = configfs_register_default_group(iio_triggers_group, t->name, + &iio_trigger_type_group_type); + if (IS_ERR(t->group)) + ret = PTR_ERR(t->group); + + return ret; +} +EXPORT_SYMBOL(iio_register_sw_trigger_type); + +void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *t) +{ + struct iio_sw_trigger_type *iter; + + mutex_lock(&iio_trigger_types_lock); + iter = __iio_find_sw_trigger_type(t->name, strlen(t->name)); + if (iter) + list_del(&t->list); + mutex_unlock(&iio_trigger_types_lock); + + configfs_unregister_default_group(t->group); +} +EXPORT_SYMBOL(iio_unregister_sw_trigger_type); + +static +struct iio_sw_trigger_type *iio_get_sw_trigger_type(const char *name) +{ + struct iio_sw_trigger_type *t; + + mutex_lock(&iio_trigger_types_lock); + t = __iio_find_sw_trigger_type(name, strlen(name)); + if (t && !try_module_get(t->owner)) + t = NULL; + mutex_unlock(&iio_trigger_types_lock); + + return t; +} + +struct iio_sw_trigger *iio_sw_trigger_create(const char *type, const char *name) +{ + struct iio_sw_trigger *t; + struct iio_sw_trigger_type *tt; + + tt = iio_get_sw_trigger_type(type); + if (!tt) { + pr_err("Invalid trigger type: %s\n", type); + return ERR_PTR(-EINVAL); + } + t = tt->ops->probe(name); + if (IS_ERR(t)) + goto out_module_put; + + t->trigger_type = tt; + + return t; +out_module_put: + module_put(tt->owner); + return t; +} +EXPORT_SYMBOL(iio_sw_trigger_create); + +void iio_sw_trigger_destroy(struct iio_sw_trigger *t) +{ + struct iio_sw_trigger_type *tt = t->trigger_type; + + tt->ops->remove(t); + module_put(tt->owner); +} +EXPORT_SYMBOL(iio_sw_trigger_destroy); + +static struct config_group *trigger_make_group(struct config_group *group, + const char *name) +{ + struct iio_sw_trigger *t; + + t = iio_sw_trigger_create(group->cg_item.ci_name, name); + if (IS_ERR(t)) + return ERR_CAST(t); + + config_item_set_name(&t->group.cg_item, "%s", name); + + return &t->group; +} + +static void trigger_drop_group(struct config_group *group, + struct config_item *item) +{ + struct iio_sw_trigger *t = to_iio_sw_trigger(item); + + iio_sw_trigger_destroy(t); + config_item_put(item); +} + +static struct configfs_group_operations trigger_ops = { + .make_group = &trigger_make_group, + .drop_item = &trigger_drop_group, +}; + +static struct config_item_type iio_trigger_type_group_type = { + .ct_group_ops = &trigger_ops, + .ct_owner = THIS_MODULE, +}; + +static int __init iio_sw_trigger_init(void) +{ + iio_triggers_group = + configfs_register_default_group(&iio_configfs_subsys.su_group, + "triggers", + &iio_triggers_group_type); + if (IS_ERR(iio_triggers_group)) + return PTR_ERR(iio_triggers_group); + return 0; +} +module_init(iio_sw_trigger_init); + +static void __exit iio_sw_trigger_exit(void) +{ + configfs_unregister_default_group(iio_triggers_group); +} +module_exit(iio_sw_trigger_exit); + +MODULE_AUTHOR("Daniel Baluta "); +MODULE_DESCRIPTION("Industrial I/O software triggers support"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h new file mode 100644 index 000000000000..c2f33b2b35a5 --- /dev/null +++ b/include/linux/iio/sw_trigger.h @@ -0,0 +1,71 @@ +/* + * Industrial I/O software trigger interface + * + * Copyright (c) 2015 Intel Corporation + * + * 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 __IIO_SW_TRIGGER +#define __IIO_SW_TRIGGER + +#include +#include +#include +#include + +#define module_iio_sw_trigger_driver(__iio_sw_trigger_type) \ + module_driver(__iio_sw_trigger_type, iio_register_sw_trigger_type, \ + iio_unregister_sw_trigger_type) + +extern struct configfs_subsystem iio_configfs_subsys; +struct iio_sw_trigger_ops; + +struct iio_sw_trigger_type { + const char *name; + struct module *owner; + const struct iio_sw_trigger_ops *ops; + struct list_head list; + struct config_group *group; +}; + +struct iio_sw_trigger { + struct iio_trigger *trigger; + struct iio_sw_trigger_type *trigger_type; + struct config_group group; +}; + +struct iio_sw_trigger_ops { + struct iio_sw_trigger* (*probe)(const char *); + int (*remove)(struct iio_sw_trigger *); +}; + +static inline +struct iio_sw_trigger *to_iio_sw_trigger(struct config_item *item) +{ + return container_of(to_config_group(item), struct iio_sw_trigger, + group); +} + +int iio_register_sw_trigger_type(struct iio_sw_trigger_type *tt); +void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *tt); + +struct iio_sw_trigger *iio_sw_trigger_create(const char *, const char *); +void iio_sw_trigger_destroy(struct iio_sw_trigger *); + +int iio_sw_trigger_type_configfs_register(struct iio_sw_trigger_type *tt); +void iio_sw_trigger_type_configfs_unregister(struct iio_sw_trigger_type *tt); + +static inline +void iio_swt_group_init_type_name(struct iio_sw_trigger *t, + const char *name, + struct config_item_type *type) +{ +#ifdef CONFIG_CONFIGFS_FS + config_group_init_type_name(&t->group, name, type); +#endif +} + +#endif /* __IIO_SW_TRIGGER */ -- cgit v1.2.3 From b2b018ef48675a9a524fa9791ea7d67fdac405f7 Mon Sep 17 00:00:00 2001 From: Chris J Arges Date: Tue, 1 Dec 2015 20:40:54 -0600 Subject: livepatch: add old_sympos as disambiguator field to klp_func Currently, patching objects with duplicate symbol names fail because the creation of the sysfs function directory collides with the previous attempt. Appending old_addr to the function name is problematic as it reveals the address of the function being patch to a normal user. Using the symbol's occurrence in kallsyms to postfix the function name in the sysfs directory solves the issue of having consistent unique names and ensuring that the address is not exposed to a normal user. In addition, using the symbol position as the user's method to disambiguate symbols instead of addr allows for disambiguating symbols in modules as well for both function addresses and for relocs. This also simplifies much of the code. Special handling for kASLR is no longer needed and can be removed. The klp_find_verify_func_addr function can be replaced by klp_find_object_symbol, and klp_verify_vmlinux_symbol and its callback can be removed completely. In cases of duplicate symbols, old_sympos will be used to disambiguate instead of old_addr. By default old_sympos will be 0, and patching will only succeed if the symbol is unique. Specifying a positive value will ensure that occurrence of the symbol in kallsyms for the patched object will be used for patching if it is valid. In addition, make old_addr an internal structure field not to be specified by the user. Finally, remove klp_find_verify_func_addr as it can be replaced by klp_find_object_symbol directly. Support for symbol position disambiguation for relocations is added in the next patch in this series. Signed-off-by: Chris J Arges Reviewed-by: Petr Mladek Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 19 +++++++------ kernel/livepatch/core.c | 72 ++++++++++++++++++++--------------------------- 2 files changed, 41 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 31db7a05dd36..b60e8abab0ab 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -37,8 +37,9 @@ enum klp_state { * 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) + * @old_sympos: a hint indicating which symbol position the old function + * can be found (optional) + * @old_addr: the address of the function being patched * @kobj: kobject for sysfs resources * @state: tracks function-level patch application state * @stack_node: list node for klp_ops func_stack list @@ -48,16 +49,16 @@ struct klp_func { 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. + * The old_sympos field is optional and can be used to resolve + * duplicate symbol names in livepatch objects. If this field is zero, + * it is expected the symbol is unique, otherwise patching fails. If + * this value is greater than zero then that occurrence of the symbol + * in kallsyms for the given object is used. */ - unsigned long old_addr; + unsigned long old_sympos; /* internal */ + unsigned long old_addr; struct kobject kobj; enum klp_state state; struct list_head stack_node; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index db545cbcdb89..e416f96e938d 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -135,13 +135,8 @@ struct klp_find_arg { const char *objname; const char *name; unsigned long addr; - /* - * If count == 0, the symbol was not found. If count == 1, a unique - * match was found and addr is set. If count > 1, there is - * unresolvable ambiguity among "count" number of symbols with the same - * name in the same object. - */ unsigned long count; + unsigned long pos; }; static int klp_find_callback(void *data, const char *name, @@ -158,37 +153,48 @@ static int klp_find_callback(void *data, const char *name, if (args->objname && strcmp(args->objname, mod->name)) return 0; - /* - * args->addr might be overwritten if another match is found - * but klp_find_object_symbol() handles this and only returns the - * addr if count == 1. - */ args->addr = addr; args->count++; + /* + * Finish the search when the symbol is found for the desired position + * or the position is not defined for a non-unique symbol. + */ + if ((args->pos && (args->count == args->pos)) || + (!args->pos && (args->count > 1))) + return 1; + return 0; } static int klp_find_object_symbol(const char *objname, const char *name, - unsigned long *addr) + unsigned long sympos, unsigned long *addr) { struct klp_find_arg args = { .objname = objname, .name = name, .addr = 0, - .count = 0 + .count = 0, + .pos = sympos, }; mutex_lock(&module_mutex); kallsyms_on_each_symbol(klp_find_callback, &args); mutex_unlock(&module_mutex); - if (args.count == 0) + /* + * Ensure an address was found. If sympos is 0, ensure symbol is unique; + * otherwise ensure the symbol position count matches sympos. + */ + if (args.addr == 0) pr_err("symbol '%s' not found in symbol table\n", name); - else if (args.count > 1) + else if (args.count > 1 && sympos == 0) { pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", args.count, name, objname); - else { + } else if (sympos != args.count && sympos > 0) { + pr_err("symbol position %lu for symbol '%s' in object '%s' not found\n", + sympos, name, objname ? objname : "vmlinux"); + } else { *addr = args.addr; return 0; } @@ -236,27 +242,6 @@ static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) return 0; } -static int klp_find_verify_func_addr(struct klp_object *obj, - struct klp_func *func) -{ - int ret; - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old_addr accordingly */ - if (kaslr_enabled() && func->old_addr) - func->old_addr += kaslr_offset(); -#endif - - if (!func->old_addr || klp_is_module(obj)) - ret = klp_find_object_symbol(obj->name, func->old_name, - &func->old_addr); - else - ret = klp_verify_vmlinux_symbol(func->old_name, - func->old_addr); - - return ret; -} - /* * external symbols are located outside the parent object (where the parent * object is either vmlinux or the kmod being patched). @@ -276,8 +261,11 @@ static int klp_find_external_symbol(struct module *pmod, const char *name, } preempt_enable(); - /* otherwise check if it's in another .o within the patch module */ - return klp_find_object_symbol(pmod->name, name, addr); + /* + * Check if it's in another .o within the patch module. This also + * checks that the external symbol is unique. + */ + return klp_find_object_symbol(pmod->name, name, 0, addr); } static int klp_write_object_relocations(struct module *pmod, @@ -313,7 +301,7 @@ static int klp_write_object_relocations(struct module *pmod, else ret = klp_find_object_symbol(obj->mod->name, reloc->name, - &reloc->val); + 0, &reloc->val); if (ret) return ret; } @@ -756,7 +744,9 @@ static int klp_init_object_loaded(struct klp_patch *patch, } klp_for_each_func(obj, func) { - ret = klp_find_verify_func_addr(obj, func); + ret = klp_find_object_symbol(obj->name, func->old_name, + func->old_sympos, + &func->old_addr); if (ret) return ret; } -- cgit v1.2.3 From 064c89df6247cd829a7880cc8a87b7ed2cdfccd8 Mon Sep 17 00:00:00 2001 From: Chris J Arges Date: Tue, 1 Dec 2015 20:40:55 -0600 Subject: livepatch: add sympos as disambiguator field to klp_reloc In cases of duplicate symbols, sympos will be used to disambiguate instead of val. By default sympos will be 0, and patching will only succeed if the symbol is unique. Specifying a positive value will ensure that occurrence of the symbol in kallsyms for the patched object will be used for patching if it is valid. For external relocations sympos is not supported. Remove klp_verify_callback, klp_verify_args and klp_verify_vmlinux_symbol as they are no longer used. From the klp_reloc structure remove val, as it can be refactored as a local variable in klp_write_object_relocations. Signed-off-by: Chris J Arges Reviewed-by: Petr Mladek Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- include/linux/livepatch.h | 5 ++- kernel/livepatch/core.c | 84 +++++++++++------------------------------------ 2 files changed, 21 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index b60e8abab0ab..a8828652f794 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -67,8 +67,7 @@ struct klp_func { /** * 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) + * @sympos: position in kallsyms to disambiguate symbols (optional) * @type: ELF relocation type * @name: name of the referenced symbol (for lookup/verification) * @addend: offset from the referenced symbol @@ -76,7 +75,7 @@ struct klp_func { */ struct klp_reloc { unsigned long loc; - unsigned long val; + unsigned long sympos; unsigned long type; const char *name; int addend; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index e416f96e938d..e842534d3493 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -203,45 +203,6 @@ static int klp_find_object_symbol(const char *objname, const char *name, return -EINVAL; } -struct klp_verify_args { - const char *name; - const unsigned long addr; -}; - -static int klp_verify_callback(void *data, const char *name, - struct module *mod, unsigned long addr) -{ - struct klp_verify_args *args = data; - - if (!mod && - !strcmp(args->name, name) && - args->addr == addr) - return 1; - - return 0; -} - -static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) -{ - struct klp_verify_args args = { - .name = name, - .addr = addr, - }; - int ret; - - mutex_lock(&module_mutex); - ret = kallsyms_on_each_symbol(klp_verify_callback, &args); - mutex_unlock(&module_mutex); - - if (!ret) { - pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n", - name, addr); - return -EINVAL; - } - - return 0; -} - /* * external symbols are located outside the parent object (where the parent * object is either vmlinux or the kmod being patched). @@ -272,6 +233,7 @@ static int klp_write_object_relocations(struct module *pmod, struct klp_object *obj) { int ret; + unsigned long val; struct klp_reloc *reloc; if (WARN_ON(!klp_is_object_loaded(obj))) @@ -281,35 +243,27 @@ static int klp_write_object_relocations(struct module *pmod, return -EINVAL; for (reloc = obj->relocs; reloc->name; reloc++) { - if (!klp_is_module(obj)) { - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old value accordingly */ - if (kaslr_enabled()) - reloc->val += kaslr_offset(); -#endif - ret = klp_verify_vmlinux_symbol(reloc->name, - reloc->val); - if (ret) - return ret; - } else { - /* module, reloc->val needs to be discovered */ - if (reloc->external) - ret = klp_find_external_symbol(pmod, - reloc->name, - &reloc->val); - else - ret = klp_find_object_symbol(obj->mod->name, - reloc->name, - 0, &reloc->val); - if (ret) - return ret; - } + /* discover the address of the referenced symbol */ + if (reloc->external) { + if (reloc->sympos > 0) { + pr_err("non-zero sympos for external reloc symbol '%s' is not supported\n", + reloc->name); + return -EINVAL; + } + ret = klp_find_external_symbol(pmod, reloc->name, &val); + } else + ret = klp_find_object_symbol(obj->name, + reloc->name, + reloc->sympos, + &val); + if (ret) + return ret; + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, - reloc->val + reloc->addend); + val + reloc->addend); if (ret) { pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", - reloc->name, reloc->val, ret); + reloc->name, val, ret); return ret; } } -- cgit v1.2.3 From ea1f3339909d8973b41f09ef7275d7e49974b910 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 3 Nov 2015 15:08:32 +0000 Subject: mfd: arizona: Support Cirrus Logic CS47L24 and WM1831 This patch adds the regmap configuration tables and core MFD handling for the CS47L24 and WM1831 codecs. Note that compared to the other Arizona codecs, these devices do not have an LDO1 or micsupp regulators, extcon driver, or the DCVDD isolation control. Signed-off-by: Richard Fitzgerald Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 18 +- drivers/mfd/Makefile | 3 + drivers/mfd/arizona-core.c | 74 +- drivers/mfd/arizona-irq.c | 40 +- drivers/mfd/arizona-spi.c | 7 + drivers/mfd/arizona.h | 4 + drivers/mfd/cs47l24-tables.c | 1629 ++++++++++++++++++++++++++++++++++++++ include/linux/mfd/arizona/core.h | 3 + 8 files changed, 1753 insertions(+), 25 deletions(-) create mode 100644 drivers/mfd/cs47l24-tables.c (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 4d92df6ef9fe..9581ebbfb4a0 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1370,24 +1370,30 @@ config MFD_ARIZONA bool config MFD_ARIZONA_I2C - tristate "Wolfson Microelectronics Arizona platform with I2C" + tristate "Cirrus Logic/Wolfson Microelectronics Arizona platform with I2C" select MFD_ARIZONA select MFD_CORE select REGMAP_I2C depends on I2C help - Support for the Wolfson Microelectronics Arizona platform audio SoC - core functionality controlled via I2C. + Support for the Cirrus Logic/Wolfson Microelectronics Arizona platform + audio SoC core functionality controlled via I2C. config MFD_ARIZONA_SPI - tristate "Wolfson Microelectronics Arizona platform with SPI" + tristate "Cirrus Logic/Wolfson Microelectronics Arizona platform with SPI" select MFD_ARIZONA select MFD_CORE select REGMAP_SPI depends on SPI_MASTER help - Support for the Wolfson Microelectronics Arizona platform audio SoC - core functionality controlled via I2C. + Support for the Cirrus Logic/Wolfson Microelectronics Arizona platform + audio SoC core functionality controlled via I2C. + +config MFD_CS47L24 + bool "Cirrus Logic CS47L24 and WM1831" + depends on MFD_ARIZONA + help + Support for Cirrus Logic CS47L24 and WM1831 low power audio SoC config MFD_WM5102 bool "Wolfson Microelectronics WM5102" diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 99f93ab26348..0f230a6103f8 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -51,6 +51,9 @@ endif ifeq ($(CONFIG_MFD_WM8998),y) obj-$(CONFIG_MFD_ARIZONA) += wm8998-tables.o endif +ifeq ($(CONFIG_MFD_CS47L24),y) +obj-$(CONFIG_MFD_ARIZONA) += cs47l24-tables.o +endif obj-$(CONFIG_MFD_WM8400) += wm8400-core.o wm831x-objs := wm831x-core.o wm831x-irq.o wm831x-otp.o wm831x-objs += wm831x-auxadc.o diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index d474732cc65c..b9489a0d7fab 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -598,6 +598,12 @@ static int arizona_runtime_resume(struct device *dev) goto err; } break; + case WM1831: + case CS47L24: + ret = arizona_wait_for_boot(arizona); + if (ret != 0) + goto err; + break; default: ret = arizona_wait_for_boot(arizona); if (ret != 0) @@ -682,6 +688,9 @@ static int arizona_runtime_suspend(struct device *dev) } } break; + case WM1831: + case CS47L24: + break; default: jd_active = arizona_is_jack_det_active(arizona); if (jd_active < 0) @@ -862,6 +871,8 @@ const struct of_device_id arizona_of_match[] = { { .compatible = "wlf,wm8997", .data = (void *)WM8997 }, { .compatible = "wlf,wm8998", .data = (void *)WM8998 }, { .compatible = "wlf,wm1814", .data = (void *)WM1814 }, + { .compatible = "wlf,wm1831", .data = (void *)WM1831 }, + { .compatible = "cirrus,cs47l24", .data = (void *)CS47L24 }, {}, }; EXPORT_SYMBOL_GPL(arizona_of_match); @@ -919,6 +930,23 @@ static const struct mfd_cell wm5110_devs[] = { }, }; +static const char * const cs47l24_supplies[] = { + "MICVDD", + "CPVDD", + "SPKVDD", +}; + +static const struct mfd_cell cs47l24_devs[] = { + { .name = "arizona-gpio" }, + { .name = "arizona-haptics" }, + { .name = "arizona-pwm" }, + { + .name = "cs47l24-codec", + .parent_supplies = cs47l24_supplies, + .num_parent_supplies = ARRAY_SIZE(cs47l24_supplies), + }, +}; + static const char * const wm8997_supplies[] = { "MICVDD", "DBVDD2", @@ -963,7 +991,7 @@ static const struct mfd_cell wm8998_devs[] = { int arizona_dev_init(struct arizona *arizona) { struct device *dev = arizona->dev; - const char *type_name; + const char *type_name = NULL; unsigned int reg, val, mask; int (*apply_patch)(struct arizona *) = NULL; const struct mfd_cell *subdevs = NULL; @@ -987,6 +1015,8 @@ int arizona_dev_init(struct arizona *arizona) case WM8997: case WM8998: case WM1814: + case WM1831: + case CS47L24: for (i = 0; i < ARRAY_SIZE(wm5102_core_supplies); i++) arizona->core_supplies[i].supply = wm5102_core_supplies[i]; @@ -1001,11 +1031,18 @@ int arizona_dev_init(struct arizona *arizona) /* Mark DCVDD as external, LDO1 driver will clear if internal */ arizona->external_dcvdd = true; - ret = mfd_add_devices(arizona->dev, -1, early_devs, - ARRAY_SIZE(early_devs), NULL, 0, NULL); - if (ret != 0) { - dev_err(dev, "Failed to add early children: %d\n", ret); - return ret; + switch (arizona->type) { + case WM1831: + case CS47L24: + break; /* No LDO1 regulator */ + default: + ret = mfd_add_devices(arizona->dev, -1, early_devs, + ARRAY_SIZE(early_devs), NULL, 0, NULL); + if (ret != 0) { + dev_err(dev, "Failed to add early children: %d\n", ret); + return ret; + } + break; } ret = devm_regulator_bulk_get(dev, arizona->num_core_supplies, @@ -1069,6 +1106,7 @@ int arizona_dev_init(struct arizona *arizona) case 0x5102: case 0x5110: case 0x6349: + case 0x6363: case 0x8997: break; default: @@ -1167,6 +1205,30 @@ int arizona_dev_init(struct arizona *arizona) n_subdevs = ARRAY_SIZE(wm5110_devs); } break; + case 0x6363: + if (IS_ENABLED(CONFIG_MFD_CS47L24)) { + switch (arizona->type) { + case CS47L24: + type_name = "CS47L24"; + break; + + case WM1831: + type_name = "WM1831"; + break; + + default: + dev_warn(arizona->dev, + "CS47L24 registered as %d\n", + arizona->type); + arizona->type = CS47L24; + break; + } + + apply_patch = cs47l24_patch; + subdevs = cs47l24_devs; + n_subdevs = ARRAY_SIZE(cs47l24_devs); + } + break; case 0x8997: if (IS_ENABLED(CONFIG_MFD_WM8997)) { type_name = "WM8997"; diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c index 3d425e93ce84..682bc865fa8b 100644 --- a/drivers/mfd/arizona-irq.c +++ b/drivers/mfd/arizona-irq.c @@ -30,11 +30,13 @@ static int arizona_map_irq(struct arizona *arizona, int irq) { int ret; - ret = regmap_irq_get_virq(arizona->aod_irq_chip, irq); - if (ret < 0) - ret = regmap_irq_get_virq(arizona->irq_chip, irq); + if (arizona->aod_irq_chip) { + ret = regmap_irq_get_virq(arizona->aod_irq_chip, irq); + if (ret >= 0) + return ret; + } - return ret; + return regmap_irq_get_virq(arizona->irq_chip, irq); } int arizona_request_irq(struct arizona *arizona, int irq, char *name, @@ -107,8 +109,8 @@ static irqreturn_t arizona_irq_thread(int irq, void *data) do { poll = false; - /* Always handle the AoD domain */ - handle_nested_irq(irq_find_mapping(arizona->virq, 0)); + if (arizona->aod_irq_chip) + handle_nested_irq(irq_find_mapping(arizona->virq, 0)); /* * Check if one of the main interrupts is asserted and only @@ -219,6 +221,15 @@ int arizona_irq_init(struct arizona *arizona) arizona->ctrlif_error = false; break; #endif +#ifdef CONFIG_MFD_CS47L24 + case WM1831: + case CS47L24: + aod = NULL; + irq = &cs47l24_irq; + + arizona->ctrlif_error = false; + break; +#endif #ifdef CONFIG_MFD_WM8997 case WM8997: aod = &wm8997_aod; @@ -291,13 +302,16 @@ int arizona_irq_init(struct arizona *arizona) goto err; } - ret = regmap_add_irq_chip(arizona->regmap, - irq_create_mapping(arizona->virq, 0), - IRQF_ONESHOT, 0, aod, - &arizona->aod_irq_chip); - if (ret != 0) { - dev_err(arizona->dev, "Failed to add AOD IRQs: %d\n", ret); - goto err_domain; + if (aod) { + ret = regmap_add_irq_chip(arizona->regmap, + irq_create_mapping(arizona->virq, 0), + IRQF_ONESHOT, 0, aod, + &arizona->aod_irq_chip); + if (ret != 0) { + dev_err(arizona->dev, + "Failed to add AOD IRQs: %d\n", ret); + goto err_domain; + } } ret = regmap_add_irq_chip(arizona->regmap, diff --git a/drivers/mfd/arizona-spi.c b/drivers/mfd/arizona-spi.c index befbc89bfd34..5c1ccdeb9b70 100644 --- a/drivers/mfd/arizona-spi.c +++ b/drivers/mfd/arizona-spi.c @@ -46,6 +46,11 @@ static int arizona_spi_probe(struct spi_device *spi) if (IS_ENABLED(CONFIG_MFD_WM5110)) regmap_config = &wm5110_spi_regmap; break; + case WM1831: + case CS47L24: + if (IS_ENABLED(CONFIG_MFD_CS47L24)) + regmap_config = &cs47l24_spi_regmap; + break; default: dev_err(&spi->dev, "Unknown device type %ld\n", type); return -EINVAL; @@ -89,6 +94,8 @@ static const struct spi_device_id arizona_spi_ids[] = { { "wm5102", WM5102 }, { "wm5110", WM5110 }, { "wm8280", WM8280 }, + { "wm1831", WM1831 }, + { "cs47l24", CS47L24 }, { }, }; MODULE_DEVICE_TABLE(spi, arizona_spi_ids); diff --git a/drivers/mfd/arizona.h b/drivers/mfd/arizona.h index 3af12e938f57..198e9cea77f9 100644 --- a/drivers/mfd/arizona.h +++ b/drivers/mfd/arizona.h @@ -25,6 +25,8 @@ extern const struct regmap_config wm5102_spi_regmap; extern const struct regmap_config wm5110_i2c_regmap; extern const struct regmap_config wm5110_spi_regmap; +extern const struct regmap_config cs47l24_spi_regmap; + extern const struct regmap_config wm8997_i2c_regmap; extern const struct regmap_config wm8998_i2c_regmap; @@ -40,6 +42,8 @@ extern const struct regmap_irq_chip wm5110_aod; extern const struct regmap_irq_chip wm5110_irq; extern const struct regmap_irq_chip wm5110_revd_irq; +extern const struct regmap_irq_chip cs47l24_irq; + extern const struct regmap_irq_chip wm8997_aod; extern const struct regmap_irq_chip wm8997_irq; diff --git a/drivers/mfd/cs47l24-tables.c b/drivers/mfd/cs47l24-tables.c new file mode 100644 index 000000000000..870800657594 --- /dev/null +++ b/drivers/mfd/cs47l24-tables.c @@ -0,0 +1,1629 @@ +/* + * Data tables for CS47L24 codec + * + * Copyright 2015 Cirrus Logic, Inc. + * + * Author: Richard Fitzgerald + * + * 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. + */ + +#include + +#include +#include +#include + +#include "arizona.h" + +#define CS47L24_NUM_ISR 5 + +static const struct reg_sequence cs47l24_reva_patch[] = { + { 0x80, 0x3 }, + { 0x27C, 0x0010 }, + { 0x221, 0x0070 }, + { 0x80, 0x0 }, +}; + +int cs47l24_patch(struct arizona *arizona) +{ + return regmap_register_patch(arizona->regmap, + cs47l24_reva_patch, + ARRAY_SIZE(cs47l24_reva_patch)); +} +EXPORT_SYMBOL_GPL(cs47l24_patch); + +static const struct regmap_irq cs47l24_irqs[ARIZONA_NUM_IRQ] = { + [ARIZONA_IRQ_GP2] = { .reg_offset = 0, .mask = ARIZONA_GP2_EINT1 }, + [ARIZONA_IRQ_GP1] = { .reg_offset = 0, .mask = ARIZONA_GP1_EINT1 }, + + [ARIZONA_IRQ_DSP3_RAM_RDY] = { + .reg_offset = 1, .mask = ARIZONA_DSP3_RAM_RDY_EINT1 + }, + [ARIZONA_IRQ_DSP2_RAM_RDY] = { + .reg_offset = 1, .mask = ARIZONA_DSP2_RAM_RDY_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ8] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ8_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ7] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ7_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ6] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ6_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ5] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ5_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ4] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ4_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ3] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ3_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ2] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ2_EINT1 + }, + [ARIZONA_IRQ_DSP_IRQ1] = { + .reg_offset = 1, .mask = ARIZONA_DSP_IRQ1_EINT1 + }, + + [ARIZONA_IRQ_SPK_OVERHEAT_WARN] = { + .reg_offset = 2, .mask = ARIZONA_SPK_OVERHEAT_WARN_EINT1 + }, + [ARIZONA_IRQ_SPK_OVERHEAT] = { + .reg_offset = 2, .mask = ARIZONA_SPK_OVERHEAT_EINT1 + }, + [ARIZONA_IRQ_WSEQ_DONE] = { + .reg_offset = 2, .mask = ARIZONA_WSEQ_DONE_EINT1 + }, + [ARIZONA_IRQ_DRC2_SIG_DET] = { + .reg_offset = 2, .mask = ARIZONA_DRC2_SIG_DET_EINT1 + }, + [ARIZONA_IRQ_DRC1_SIG_DET] = { + .reg_offset = 2, .mask = ARIZONA_DRC1_SIG_DET_EINT1 + }, + [ARIZONA_IRQ_ASRC2_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_ASRC2_LOCK_EINT1 + }, + [ARIZONA_IRQ_ASRC1_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_ASRC1_LOCK_EINT1 + }, + [ARIZONA_IRQ_UNDERCLOCKED] = { + .reg_offset = 2, .mask = ARIZONA_UNDERCLOCKED_EINT1 + }, + [ARIZONA_IRQ_OVERCLOCKED] = { + .reg_offset = 2, .mask = ARIZONA_OVERCLOCKED_EINT1 + }, + [ARIZONA_IRQ_FLL2_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_FLL2_LOCK_EINT1 + }, + [ARIZONA_IRQ_FLL1_LOCK] = { + .reg_offset = 2, .mask = ARIZONA_FLL1_LOCK_EINT1 + }, + [ARIZONA_IRQ_CLKGEN_ERR] = { + .reg_offset = 2, .mask = ARIZONA_CLKGEN_ERR_EINT1 + }, + [ARIZONA_IRQ_CLKGEN_ERR_ASYNC] = { + .reg_offset = 2, .mask = ARIZONA_CLKGEN_ERR_ASYNC_EINT1 + }, + + [ARIZONA_IRQ_CTRLIF_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_CTRLIF_ERR_EINT1 + }, + [ARIZONA_IRQ_MIXER_DROPPED_SAMPLES] = { + .reg_offset = 3, .mask = ARIZONA_V2_MIXER_DROPPED_SAMPLE_EINT1 + }, + [ARIZONA_IRQ_ASYNC_CLK_ENA_LOW] = { + .reg_offset = 3, .mask = ARIZONA_V2_ASYNC_CLK_ENA_LOW_EINT1 + }, + [ARIZONA_IRQ_SYSCLK_ENA_LOW] = { + .reg_offset = 3, .mask = ARIZONA_V2_SYSCLK_ENA_LOW_EINT1 + }, + [ARIZONA_IRQ_ISRC1_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC1_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_ISRC2_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC2_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_ISRC3_CFG_ERR] = { + .reg_offset = 3, .mask = ARIZONA_V2_ISRC3_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_HP1R_DONE] = { + .reg_offset = 3, .mask = ARIZONA_HP1R_DONE_EINT1 + }, + [ARIZONA_IRQ_HP1L_DONE] = { + .reg_offset = 3, .mask = ARIZONA_HP1L_DONE_EINT1 + }, + + [ARIZONA_IRQ_BOOT_DONE] = { + .reg_offset = 4, .mask = ARIZONA_BOOT_DONE_EINT1 + }, + [ARIZONA_IRQ_ASRC_CFG_ERR] = { + .reg_offset = 4, .mask = ARIZONA_V2_ASRC_CFG_ERR_EINT1 + }, + [ARIZONA_IRQ_FLL2_CLOCK_OK] = { + .reg_offset = 4, .mask = ARIZONA_FLL2_CLOCK_OK_EINT1 + }, + [ARIZONA_IRQ_FLL1_CLOCK_OK] = { + .reg_offset = 4, .mask = ARIZONA_FLL1_CLOCK_OK_EINT1 + }, + + [ARIZONA_IRQ_DSP_SHARED_WR_COLL] = { + .reg_offset = 5, .mask = ARIZONA_DSP_SHARED_WR_COLL_EINT1 + }, + [ARIZONA_IRQ_SPK_SHUTDOWN] = { + .reg_offset = 5, .mask = ARIZONA_SPK_SHUTDOWN_EINT1 + }, + [ARIZONA_IRQ_SPK1R_SHORT] = { + .reg_offset = 5, .mask = ARIZONA_SPK1R_SHORT_EINT1 + }, + [ARIZONA_IRQ_SPK1L_SHORT] = { + .reg_offset = 5, .mask = ARIZONA_SPK1L_SHORT_EINT1 + }, + [ARIZONA_IRQ_HP1R_SC_POS] = { + .reg_offset = 5, .mask = ARIZONA_HP1R_SC_POS_EINT1 + }, + [ARIZONA_IRQ_HP1L_SC_POS] = { + .reg_offset = 5, .mask = ARIZONA_HP1L_SC_POS_EINT1 + }, +}; + +const struct regmap_irq_chip cs47l24_irq = { + .name = "cs47l24 IRQ", + .status_base = ARIZONA_INTERRUPT_STATUS_1, + .mask_base = ARIZONA_INTERRUPT_STATUS_1_MASK, + .ack_base = ARIZONA_INTERRUPT_STATUS_1, + .num_regs = 6, + .irqs = cs47l24_irqs, + .num_irqs = ARRAY_SIZE(cs47l24_irqs), +}; +EXPORT_SYMBOL_GPL(cs47l24_irq); + +static const struct reg_default cs47l24_reg_default[] = { + { 0x00000008, 0x0019 }, /* R8 - Ctrl IF SPI CFG 1 */ + { 0x00000020, 0x0000 }, /* R32 - Tone Generator 1 */ + { 0x00000021, 0x1000 }, /* R33 - Tone Generator 2 */ + { 0x00000022, 0x0000 }, /* R34 - Tone Generator 3 */ + { 0x00000023, 0x1000 }, /* R35 - Tone Generator 4 */ + { 0x00000024, 0x0000 }, /* R36 - Tone Generator 5 */ + { 0x00000030, 0x0000 }, /* R48 - PWM Drive 1 */ + { 0x00000031, 0x0100 }, /* R49 - PWM Drive 2 */ + { 0x00000032, 0x0100 }, /* R50 - PWM Drive 3 */ + { 0x00000041, 0x0000 }, /* R65 - Sequence control */ + { 0x00000061, 0x01FF }, /* R97 - Sample Rate Sequence Select 1 */ + { 0x00000062, 0x01FF }, /* R98 - Sample Rate Sequence Select 2 */ + { 0x00000063, 0x01FF }, /* R99 - Sample Rate Sequence Select 3 */ + { 0x00000064, 0x01FF }, /* R100 - Sample Rate Sequence Select 4 */ + { 0x00000070, 0x0000 }, /* R112 - Comfort Noise Generator */ + { 0x00000090, 0x0000 }, /* R144 - Haptics Control 1 */ + { 0x00000091, 0x7FFF }, /* R145 - Haptics Control 2 */ + { 0x00000092, 0x0000 }, /* R146 - Haptics phase 1 intensity */ + { 0x00000093, 0x0000 }, /* R147 - Haptics phase 1 duration */ + { 0x00000094, 0x0000 }, /* R148 - Haptics phase 2 intensity */ + { 0x00000095, 0x0000 }, /* R149 - Haptics phase 2 duration */ + { 0x00000096, 0x0000 }, /* R150 - Haptics phase 3 intensity */ + { 0x00000097, 0x0000 }, /* R151 - Haptics phase 3 duration */ + { 0x00000100, 0x0002 }, /* R256 - Clock 32k 1 */ + { 0x00000101, 0x0504 }, /* R257 - System Clock 1 */ + { 0x00000102, 0x0011 }, /* R258 - Sample rate 1 */ + { 0x00000103, 0x0011 }, /* R259 - Sample rate 2 */ + { 0x00000104, 0x0011 }, /* R260 - Sample rate 3 */ + { 0x00000112, 0x0305 }, /* R274 - Async clock 1 */ + { 0x00000113, 0x0011 }, /* R275 - Async sample rate 1 */ + { 0x00000114, 0x0011 }, /* R276 - Async sample rate 2 */ + { 0x00000149, 0x0000 }, /* R329 - Output system clock */ + { 0x0000014A, 0x0000 }, /* R330 - Output async clock */ + { 0x00000152, 0x0000 }, /* R338 - Rate Estimator 1 */ + { 0x00000153, 0x0000 }, /* R339 - Rate Estimator 2 */ + { 0x00000154, 0x0000 }, /* R340 - Rate Estimator 3 */ + { 0x00000155, 0x0000 }, /* R341 - Rate Estimator 4 */ + { 0x00000156, 0x0000 }, /* R342 - Rate Estimator 5 */ + { 0x00000171, 0x0002 }, /* R369 - FLL1 Control 1 */ + { 0x00000172, 0x0008 }, /* R370 - FLL1 Control 2 */ + { 0x00000173, 0x0018 }, /* R371 - FLL1 Control 3 */ + { 0x00000174, 0x007D }, /* R372 - FLL1 Control 4 */ + { 0x00000175, 0x0006 }, /* R373 - FLL1 Control 5 */ + { 0x00000176, 0x0000 }, /* R374 - FLL1 Control 6 */ + { 0x00000177, 0x0281 }, /* R375 - FLL1 Loop Filter Test 1 */ + { 0x00000178, 0x0000 }, /* R376 - FLL1 NCO Test 0 */ + { 0x00000179, 0x0000 }, /* R376 - FLL1 Control 7 */ + { 0x00000181, 0x0000 }, /* R385 - FLL1 Synchroniser 1 */ + { 0x00000182, 0x0000 }, /* R386 - FLL1 Synchroniser 2 */ + { 0x00000183, 0x0000 }, /* R387 - FLL1 Synchroniser 3 */ + { 0x00000184, 0x0000 }, /* R388 - FLL1 Synchroniser 4 */ + { 0x00000185, 0x0000 }, /* R389 - FLL1 Synchroniser 5 */ + { 0x00000186, 0x0000 }, /* R390 - FLL1 Synchroniser 6 */ + { 0x00000187, 0x0001 }, /* R390 - FLL1 Synchroniser 7 */ + { 0x00000189, 0x0000 }, /* R393 - FLL1 Spread Spectrum */ + { 0x0000018A, 0x000C }, /* R394 - FLL1 GPIO Clock */ + { 0x00000191, 0x0002 }, /* R401 - FLL2 Control 1 */ + { 0x00000192, 0x0008 }, /* R402 - FLL2 Control 2 */ + { 0x00000193, 0x0018 }, /* R403 - FLL2 Control 3 */ + { 0x00000194, 0x007D }, /* R404 - FLL2 Control 4 */ + { 0x00000195, 0x000C }, /* R405 - FLL2 Control 5 */ + { 0x00000196, 0x0000 }, /* R406 - FLL2 Control 6 */ + { 0x00000197, 0x0000 }, /* R407 - FLL2 Loop Filter Test 1 */ + { 0x00000198, 0x0000 }, /* R408 - FLL2 NCO Test 0 */ + { 0x00000199, 0x0000 }, /* R408 - FLL2 Control 7 */ + { 0x000001A1, 0x0000 }, /* R417 - FLL2 Synchroniser 1 */ + { 0x000001A2, 0x0000 }, /* R418 - FLL2 Synchroniser 2 */ + { 0x000001A3, 0x0000 }, /* R419 - FLL2 Synchroniser 3 */ + { 0x000001A4, 0x0000 }, /* R420 - FLL2 Synchroniser 4 */ + { 0x000001A5, 0x0000 }, /* R421 - FLL2 Synchroniser 5 */ + { 0x000001A6, 0x0000 }, /* R422 - FLL2 Synchroniser 6 */ + { 0x000001A7, 0x0001 }, /* R422 - FLL2 Synchroniser 7 */ + { 0x000001A9, 0x0000 }, /* R425 - FLL2 Spread Spectrum */ + { 0x000001AA, 0x000C }, /* R426 - FLL2 GPIO Clock */ + { 0x00000218, 0x00E6 }, /* R536 - Mic Bias Ctrl 1 */ + { 0x00000219, 0x00E6 }, /* R537 - Mic Bias Ctrl 2 */ + { 0x00000300, 0x0000 }, /* R768 - Input Enables */ + { 0x00000308, 0x0000 }, /* R776 - Input Rate */ + { 0x00000309, 0x0022 }, /* R777 - Input Volume Ramp */ + { 0x0000030C, 0x0002 }, /* R780 - HPF Control */ + { 0x00000310, 0x2000 }, /* R784 - IN1L Control */ + { 0x00000311, 0x0180 }, /* R785 - ADC Digital Volume 1L */ + { 0x00000312, 0x0000 }, /* R786 - DMIC1L Control */ + { 0x00000314, 0x0000 }, /* R788 - IN1R Control */ + { 0x00000315, 0x0180 }, /* R789 - ADC Digital Volume 1R */ + { 0x00000316, 0x0000 }, /* R790 - DMIC1R Control */ + { 0x00000318, 0x2000 }, /* R792 - IN2L Control */ + { 0x00000319, 0x0180 }, /* R793 - ADC Digital Volume 2L */ + { 0x0000031A, 0x0000 }, /* R794 - DMIC2L Control */ + { 0x0000031C, 0x0000 }, /* R796 - IN2R Control */ + { 0x0000031D, 0x0180 }, /* R797 - ADC Digital Volume 2R */ + { 0x0000031E, 0x0000 }, /* R798 - DMIC2R Control */ + { 0x00000400, 0x0000 }, /* R1024 - Output Enables 1 */ + { 0x00000408, 0x0000 }, /* R1032 - Output Rate 1 */ + { 0x00000409, 0x0022 }, /* R1033 - Output Volume Ramp */ + { 0x00000410, 0x0080 }, /* R1040 - Output Path Config 1L */ + { 0x00000411, 0x0180 }, /* R1041 - DAC Digital Volume 1L */ + { 0x00000412, 0x0081 }, /* R1042 - DAC Volume Limit 1L */ + { 0x00000413, 0x0001 }, /* R1043 - Noise Gate Select 1L */ + { 0x00000415, 0x0180 }, /* R1045 - DAC Digital Volume 1R */ + { 0x00000416, 0x0081 }, /* R1046 - DAC Volume Limit 1R */ + { 0x00000417, 0x0002 }, /* R1047 - Noise Gate Select 1R */ + { 0x00000429, 0x0180 }, /* R1065 - DAC Digital Volume 4L */ + { 0x0000042A, 0x0081 }, /* R1066 - Out Volume 4L */ + { 0x0000042B, 0x0040 }, /* R1067 - Noise Gate Select 4L */ + { 0x00000450, 0x0000 }, /* R1104 - DAC AEC Control 1 */ + { 0x00000458, 0x0000 }, /* R1112 - Noise Gate Control */ + { 0x000004A0, 0x3480 }, /* R1184 - HP1 Short Circuit Ctrl */ + { 0x00000500, 0x000C }, /* R1280 - AIF1 BCLK Ctrl */ + { 0x00000501, 0x0008 }, /* R1281 - AIF1 Tx Pin Ctrl */ + { 0x00000502, 0x0000 }, /* R1282 - AIF1 Rx Pin Ctrl */ + { 0x00000503, 0x0000 }, /* R1283 - AIF1 Rate Ctrl */ + { 0x00000504, 0x0000 }, /* R1284 - AIF1 Format */ + { 0x00000506, 0x0040 }, /* R1286 - AIF1 Rx BCLK Rate */ + { 0x00000507, 0x1818 }, /* R1287 - AIF1 Frame Ctrl 1 */ + { 0x00000508, 0x1818 }, /* R1288 - AIF1 Frame Ctrl 2 */ + { 0x00000509, 0x0000 }, /* R1289 - AIF1 Frame Ctrl 3 */ + { 0x0000050A, 0x0001 }, /* R1290 - AIF1 Frame Ctrl 4 */ + { 0x0000050B, 0x0002 }, /* R1291 - AIF1 Frame Ctrl 5 */ + { 0x0000050C, 0x0003 }, /* R1292 - AIF1 Frame Ctrl 6 */ + { 0x0000050D, 0x0004 }, /* R1293 - AIF1 Frame Ctrl 7 */ + { 0x0000050E, 0x0005 }, /* R1294 - AIF1 Frame Ctrl 8 */ + { 0x0000050F, 0x0006 }, /* R1295 - AIF1 Frame Ctrl 9 */ + { 0x00000510, 0x0007 }, /* R1296 - AIF1 Frame Ctrl 10 */ + { 0x00000511, 0x0000 }, /* R1297 - AIF1 Frame Ctrl 11 */ + { 0x00000512, 0x0001 }, /* R1298 - AIF1 Frame Ctrl 12 */ + { 0x00000513, 0x0002 }, /* R1299 - AIF1 Frame Ctrl 13 */ + { 0x00000514, 0x0003 }, /* R1300 - AIF1 Frame Ctrl 14 */ + { 0x00000515, 0x0004 }, /* R1301 - AIF1 Frame Ctrl 15 */ + { 0x00000516, 0x0005 }, /* R1302 - AIF1 Frame Ctrl 16 */ + { 0x00000517, 0x0006 }, /* R1303 - AIF1 Frame Ctrl 17 */ + { 0x00000518, 0x0007 }, /* R1304 - AIF1 Frame Ctrl 18 */ + { 0x00000519, 0x0000 }, /* R1305 - AIF1 Tx Enables */ + { 0x0000051A, 0x0000 }, /* R1306 - AIF1 Rx Enables */ + { 0x00000540, 0x000C }, /* R1344 - AIF2 BCLK Ctrl */ + { 0x00000541, 0x0008 }, /* R1345 - AIF2 Tx Pin Ctrl */ + { 0x00000542, 0x0000 }, /* R1346 - AIF2 Rx Pin Ctrl */ + { 0x00000543, 0x0000 }, /* R1347 - AIF2 Rate Ctrl */ + { 0x00000544, 0x0000 }, /* R1348 - AIF2 Format */ + { 0x00000546, 0x0040 }, /* R1350 - AIF2 Rx BCLK Rate */ + { 0x00000547, 0x1818 }, /* R1351 - AIF2 Frame Ctrl 1 */ + { 0x00000548, 0x1818 }, /* R1352 - AIF2 Frame Ctrl 2 */ + { 0x00000549, 0x0000 }, /* R1353 - AIF2 Frame Ctrl 3 */ + { 0x0000054A, 0x0001 }, /* R1354 - AIF2 Frame Ctrl 4 */ + { 0x0000054B, 0x0002 }, /* R1355 - AIF2 Frame Ctrl 5 */ + { 0x0000054C, 0x0003 }, /* R1356 - AIF2 Frame Ctrl 6 */ + { 0x0000054D, 0x0004 }, /* R1357 - AIF2 Frame Ctrl 7 */ + { 0x0000054E, 0x0005 }, /* R1358 - AIF2 Frame Ctrl 8 */ + { 0x00000551, 0x0000 }, /* R1361 - AIF2 Frame Ctrl 11 */ + { 0x00000552, 0x0001 }, /* R1362 - AIF2 Frame Ctrl 12 */ + { 0x00000553, 0x0002 }, /* R1363 - AIF2 Frame Ctrl 13 */ + { 0x00000554, 0x0003 }, /* R1364 - AIF2 Frame Ctrl 14 */ + { 0x00000555, 0x0004 }, /* R1365 - AIF2 Frame Ctrl 15 */ + { 0x00000556, 0x0005 }, /* R1366 - AIF2 Frame Ctrl 16 */ + { 0x00000559, 0x0000 }, /* R1369 - AIF2 Tx Enables */ + { 0x0000055A, 0x0000 }, /* R1370 - AIF2 Rx Enables */ + { 0x00000580, 0x000C }, /* R1408 - AIF3 BCLK Ctrl */ + { 0x00000581, 0x0008 }, /* R1409 - AIF3 Tx Pin Ctrl */ + { 0x00000582, 0x0000 }, /* R1410 - AIF3 Rx Pin Ctrl */ + { 0x00000583, 0x0000 }, /* R1411 - AIF3 Rate Ctrl */ + { 0x00000584, 0x0000 }, /* R1412 - AIF3 Format */ + { 0x00000586, 0x0040 }, /* R1414 - AIF3 Rx BCLK Rate */ + { 0x00000587, 0x1818 }, /* R1415 - AIF3 Frame Ctrl 1 */ + { 0x00000588, 0x1818 }, /* R1416 - AIF3 Frame Ctrl 2 */ + { 0x00000589, 0x0000 }, /* R1417 - AIF3 Frame Ctrl 3 */ + { 0x0000058A, 0x0001 }, /* R1418 - AIF3 Frame Ctrl 4 */ + { 0x00000591, 0x0000 }, /* R1425 - AIF3 Frame Ctrl 11 */ + { 0x00000592, 0x0001 }, /* R1426 - AIF3 Frame Ctrl 12 */ + { 0x00000599, 0x0000 }, /* R1433 - AIF3 Tx Enables */ + { 0x0000059A, 0x0000 }, /* R1434 - AIF3 Rx Enables */ + { 0x00000640, 0x0000 }, /* R1600 - PWM1MIX Input 1 Source */ + { 0x00000641, 0x0080 }, /* R1601 - PWM1MIX Input 1 Volume */ + { 0x00000642, 0x0000 }, /* R1602 - PWM1MIX Input 2 Source */ + { 0x00000643, 0x0080 }, /* R1603 - PWM1MIX Input 2 Volume */ + { 0x00000644, 0x0000 }, /* R1604 - PWM1MIX Input 3 Source */ + { 0x00000645, 0x0080 }, /* R1605 - PWM1MIX Input 3 Volume */ + { 0x00000646, 0x0000 }, /* R1606 - PWM1MIX Input 4 Source */ + { 0x00000647, 0x0080 }, /* R1607 - PWM1MIX Input 4 Volume */ + { 0x00000648, 0x0000 }, /* R1608 - PWM2MIX Input 1 Source */ + { 0x00000649, 0x0080 }, /* R1609 - PWM2MIX Input 1 Volume */ + { 0x0000064A, 0x0000 }, /* R1610 - PWM2MIX Input 2 Source */ + { 0x0000064B, 0x0080 }, /* R1611 - PWM2MIX Input 2 Volume */ + { 0x0000064C, 0x0000 }, /* R1612 - PWM2MIX Input 3 Source */ + { 0x0000064D, 0x0080 }, /* R1613 - PWM2MIX Input 3 Volume */ + { 0x0000064E, 0x0000 }, /* R1614 - PWM2MIX Input 4 Source */ + { 0x0000064F, 0x0080 }, /* R1615 - PWM2MIX Input 4 Volume */ + { 0x00000680, 0x0000 }, /* R1664 - OUT1LMIX Input 1 Source */ + { 0x00000681, 0x0080 }, /* R1665 - OUT1LMIX Input 1 Volume */ + { 0x00000682, 0x0000 }, /* R1666 - OUT1LMIX Input 2 Source */ + { 0x00000683, 0x0080 }, /* R1667 - OUT1LMIX Input 2 Volume */ + { 0x00000684, 0x0000 }, /* R1668 - OUT1LMIX Input 3 Source */ + { 0x00000685, 0x0080 }, /* R1669 - OUT1LMIX Input 3 Volume */ + { 0x00000686, 0x0000 }, /* R1670 - OUT1LMIX Input 4 Source */ + { 0x00000687, 0x0080 }, /* R1671 - OUT1LMIX Input 4 Volume */ + { 0x00000688, 0x0000 }, /* R1672 - OUT1RMIX Input 1 Source */ + { 0x00000689, 0x0080 }, /* R1673 - OUT1RMIX Input 1 Volume */ + { 0x0000068A, 0x0000 }, /* R1674 - OUT1RMIX Input 2 Source */ + { 0x0000068B, 0x0080 }, /* R1675 - OUT1RMIX Input 2 Volume */ + { 0x0000068C, 0x0000 }, /* R1676 - OUT1RMIX Input 3 Source */ + { 0x0000068D, 0x0080 }, /* R1677 - OUT1RMIX Input 3 Volume */ + { 0x0000068E, 0x0000 }, /* R1678 - OUT1RMIX Input 4 Source */ + { 0x0000068F, 0x0080 }, /* R1679 - OUT1RMIX Input 4 Volume */ + { 0x000006B0, 0x0000 }, /* R1712 - OUT4LMIX Input 1 Source */ + { 0x000006B1, 0x0080 }, /* R1713 - OUT4LMIX Input 1 Volume */ + { 0x000006B2, 0x0000 }, /* R1714 - OUT4LMIX Input 2 Source */ + { 0x000006B3, 0x0080 }, /* R1715 - OUT4LMIX Input 2 Volume */ + { 0x000006B4, 0x0000 }, /* R1716 - OUT4LMIX Input 3 Source */ + { 0x000006B5, 0x0080 }, /* R1717 - OUT4LMIX Input 3 Volume */ + { 0x000006B6, 0x0000 }, /* R1718 - OUT4LMIX Input 4 Source */ + { 0x000006B7, 0x0080 }, /* R1719 - OUT4LMIX Input 4 Volume */ + { 0x00000700, 0x0000 }, /* R1792 - AIF1TX1MIX Input 1 Source */ + { 0x00000701, 0x0080 }, /* R1793 - AIF1TX1MIX Input 1 Volume */ + { 0x00000702, 0x0000 }, /* R1794 - AIF1TX1MIX Input 2 Source */ + { 0x00000703, 0x0080 }, /* R1795 - AIF1TX1MIX Input 2 Volume */ + { 0x00000704, 0x0000 }, /* R1796 - AIF1TX1MIX Input 3 Source */ + { 0x00000705, 0x0080 }, /* R1797 - AIF1TX1MIX Input 3 Volume */ + { 0x00000706, 0x0000 }, /* R1798 - AIF1TX1MIX Input 4 Source */ + { 0x00000707, 0x0080 }, /* R1799 - AIF1TX1MIX Input 4 Volume */ + { 0x00000708, 0x0000 }, /* R1800 - AIF1TX2MIX Input 1 Source */ + { 0x00000709, 0x0080 }, /* R1801 - AIF1TX2MIX Input 1 Volume */ + { 0x0000070A, 0x0000 }, /* R1802 - AIF1TX2MIX Input 2 Source */ + { 0x0000070B, 0x0080 }, /* R1803 - AIF1TX2MIX Input 2 Volume */ + { 0x0000070C, 0x0000 }, /* R1804 - AIF1TX2MIX Input 3 Source */ + { 0x0000070D, 0x0080 }, /* R1805 - AIF1TX2MIX Input 3 Volume */ + { 0x0000070E, 0x0000 }, /* R1806 - AIF1TX2MIX Input 4 Source */ + { 0x0000070F, 0x0080 }, /* R1807 - AIF1TX2MIX Input 4 Volume */ + { 0x00000710, 0x0000 }, /* R1808 - AIF1TX3MIX Input 1 Source */ + { 0x00000711, 0x0080 }, /* R1809 - AIF1TX3MIX Input 1 Volume */ + { 0x00000712, 0x0000 }, /* R1810 - AIF1TX3MIX Input 2 Source */ + { 0x00000713, 0x0080 }, /* R1811 - AIF1TX3MIX Input 2 Volume */ + { 0x00000714, 0x0000 }, /* R1812 - AIF1TX3MIX Input 3 Source */ + { 0x00000715, 0x0080 }, /* R1813 - AIF1TX3MIX Input 3 Volume */ + { 0x00000716, 0x0000 }, /* R1814 - AIF1TX3MIX Input 4 Source */ + { 0x00000717, 0x0080 }, /* R1815 - AIF1TX3MIX Input 4 Volume */ + { 0x00000718, 0x0000 }, /* R1816 - AIF1TX4MIX Input 1 Source */ + { 0x00000719, 0x0080 }, /* R1817 - AIF1TX4MIX Input 1 Volume */ + { 0x0000071A, 0x0000 }, /* R1818 - AIF1TX4MIX Input 2 Source */ + { 0x0000071B, 0x0080 }, /* R1819 - AIF1TX4MIX Input 2 Volume */ + { 0x0000071C, 0x0000 }, /* R1820 - AIF1TX4MIX Input 3 Source */ + { 0x0000071D, 0x0080 }, /* R1821 - AIF1TX4MIX Input 3 Volume */ + { 0x0000071E, 0x0000 }, /* R1822 - AIF1TX4MIX Input 4 Source */ + { 0x0000071F, 0x0080 }, /* R1823 - AIF1TX4MIX Input 4 Volume */ + { 0x00000720, 0x0000 }, /* R1824 - AIF1TX5MIX Input 1 Source */ + { 0x00000721, 0x0080 }, /* R1825 - AIF1TX5MIX Input 1 Volume */ + { 0x00000722, 0x0000 }, /* R1826 - AIF1TX5MIX Input 2 Source */ + { 0x00000723, 0x0080 }, /* R1827 - AIF1TX5MIX Input 2 Volume */ + { 0x00000724, 0x0000 }, /* R1828 - AIF1TX5MIX Input 3 Source */ + { 0x00000725, 0x0080 }, /* R1829 - AIF1TX5MIX Input 3 Volume */ + { 0x00000726, 0x0000 }, /* R1830 - AIF1TX5MIX Input 4 Source */ + { 0x00000727, 0x0080 }, /* R1831 - AIF1TX5MIX Input 4 Volume */ + { 0x00000728, 0x0000 }, /* R1832 - AIF1TX6MIX Input 1 Source */ + { 0x00000729, 0x0080 }, /* R1833 - AIF1TX6MIX Input 1 Volume */ + { 0x0000072A, 0x0000 }, /* R1834 - AIF1TX6MIX Input 2 Source */ + { 0x0000072B, 0x0080 }, /* R1835 - AIF1TX6MIX Input 2 Volume */ + { 0x0000072C, 0x0000 }, /* R1836 - AIF1TX6MIX Input 3 Source */ + { 0x0000072D, 0x0080 }, /* R1837 - AIF1TX6MIX Input 3 Volume */ + { 0x0000072E, 0x0000 }, /* R1838 - AIF1TX6MIX Input 4 Source */ + { 0x0000072F, 0x0080 }, /* R1839 - AIF1TX6MIX Input 4 Volume */ + { 0x00000730, 0x0000 }, /* R1840 - AIF1TX7MIX Input 1 Source */ + { 0x00000731, 0x0080 }, /* R1841 - AIF1TX7MIX Input 1 Volume */ + { 0x00000732, 0x0000 }, /* R1842 - AIF1TX7MIX Input 2 Source */ + { 0x00000733, 0x0080 }, /* R1843 - AIF1TX7MIX Input 2 Volume */ + { 0x00000734, 0x0000 }, /* R1844 - AIF1TX7MIX Input 3 Source */ + { 0x00000735, 0x0080 }, /* R1845 - AIF1TX7MIX Input 3 Volume */ + { 0x00000736, 0x0000 }, /* R1846 - AIF1TX7MIX Input 4 Source */ + { 0x00000737, 0x0080 }, /* R1847 - AIF1TX7MIX Input 4 Volume */ + { 0x00000738, 0x0000 }, /* R1848 - AIF1TX8MIX Input 1 Source */ + { 0x00000739, 0x0080 }, /* R1849 - AIF1TX8MIX Input 1 Volume */ + { 0x0000073A, 0x0000 }, /* R1850 - AIF1TX8MIX Input 2 Source */ + { 0x0000073B, 0x0080 }, /* R1851 - AIF1TX8MIX Input 2 Volume */ + { 0x0000073C, 0x0000 }, /* R1852 - AIF1TX8MIX Input 3 Source */ + { 0x0000073D, 0x0080 }, /* R1853 - AIF1TX8MIX Input 3 Volume */ + { 0x0000073E, 0x0000 }, /* R1854 - AIF1TX8MIX Input 4 Source */ + { 0x0000073F, 0x0080 }, /* R1855 - AIF1TX8MIX Input 4 Volume */ + { 0x00000740, 0x0000 }, /* R1856 - AIF2TX1MIX Input 1 Source */ + { 0x00000741, 0x0080 }, /* R1857 - AIF2TX1MIX Input 1 Volume */ + { 0x00000742, 0x0000 }, /* R1858 - AIF2TX1MIX Input 2 Source */ + { 0x00000743, 0x0080 }, /* R1859 - AIF2TX1MIX Input 2 Volume */ + { 0x00000744, 0x0000 }, /* R1860 - AIF2TX1MIX Input 3 Source */ + { 0x00000745, 0x0080 }, /* R1861 - AIF2TX1MIX Input 3 Volume */ + { 0x00000746, 0x0000 }, /* R1862 - AIF2TX1MIX Input 4 Source */ + { 0x00000747, 0x0080 }, /* R1863 - AIF2TX1MIX Input 4 Volume */ + { 0x00000748, 0x0000 }, /* R1864 - AIF2TX2MIX Input 1 Source */ + { 0x00000749, 0x0080 }, /* R1865 - AIF2TX2MIX Input 1 Volume */ + { 0x0000074A, 0x0000 }, /* R1866 - AIF2TX2MIX Input 2 Source */ + { 0x0000074B, 0x0080 }, /* R1867 - AIF2TX2MIX Input 2 Volume */ + { 0x0000074C, 0x0000 }, /* R1868 - AIF2TX2MIX Input 3 Source */ + { 0x0000074D, 0x0080 }, /* R1869 - AIF2TX2MIX Input 3 Volume */ + { 0x0000074E, 0x0000 }, /* R1870 - AIF2TX2MIX Input 4 Source */ + { 0x0000074F, 0x0080 }, /* R1871 - AIF2TX2MIX Input 4 Volume */ + { 0x00000750, 0x0000 }, /* R1872 - AIF2TX3MIX Input 1 Source */ + { 0x00000751, 0x0080 }, /* R1873 - AIF2TX3MIX Input 1 Volume */ + { 0x00000752, 0x0000 }, /* R1874 - AIF2TX3MIX Input 2 Source */ + { 0x00000753, 0x0080 }, /* R1875 - AIF2TX3MIX Input 2 Volume */ + { 0x00000754, 0x0000 }, /* R1876 - AIF2TX3MIX Input 3 Source */ + { 0x00000755, 0x0080 }, /* R1877 - AIF2TX3MIX Input 3 Volume */ + { 0x00000756, 0x0000 }, /* R1878 - AIF2TX3MIX Input 4 Source */ + { 0x00000757, 0x0080 }, /* R1879 - AIF2TX3MIX Input 4 Volume */ + { 0x00000758, 0x0000 }, /* R1880 - AIF2TX4MIX Input 1 Source */ + { 0x00000759, 0x0080 }, /* R1881 - AIF2TX4MIX Input 1 Volume */ + { 0x0000075A, 0x0000 }, /* R1882 - AIF2TX4MIX Input 2 Source */ + { 0x0000075B, 0x0080 }, /* R1883 - AIF2TX4MIX Input 2 Volume */ + { 0x0000075C, 0x0000 }, /* R1884 - AIF2TX4MIX Input 3 Source */ + { 0x0000075D, 0x0080 }, /* R1885 - AIF2TX4MIX Input 3 Volume */ + { 0x0000075E, 0x0000 }, /* R1886 - AIF2TX4MIX Input 4 Source */ + { 0x0000075F, 0x0080 }, /* R1887 - AIF2TX4MIX Input 4 Volume */ + { 0x00000760, 0x0000 }, /* R1888 - AIF2TX5MIX Input 1 Source */ + { 0x00000761, 0x0080 }, /* R1889 - AIF2TX5MIX Input 1 Volume */ + { 0x00000762, 0x0000 }, /* R1890 - AIF2TX5MIX Input 2 Source */ + { 0x00000763, 0x0080 }, /* R1891 - AIF2TX5MIX Input 2 Volume */ + { 0x00000764, 0x0000 }, /* R1892 - AIF2TX5MIX Input 3 Source */ + { 0x00000765, 0x0080 }, /* R1893 - AIF2TX5MIX Input 3 Volume */ + { 0x00000766, 0x0000 }, /* R1894 - AIF2TX5MIX Input 4 Source */ + { 0x00000767, 0x0080 }, /* R1895 - AIF2TX5MIX Input 4 Volume */ + { 0x00000768, 0x0000 }, /* R1896 - AIF2TX6MIX Input 1 Source */ + { 0x00000769, 0x0080 }, /* R1897 - AIF2TX6MIX Input 1 Volume */ + { 0x0000076A, 0x0000 }, /* R1898 - AIF2TX6MIX Input 2 Source */ + { 0x0000076B, 0x0080 }, /* R1899 - AIF2TX6MIX Input 2 Volume */ + { 0x0000076C, 0x0000 }, /* R1900 - AIF2TX6MIX Input 3 Source */ + { 0x0000076D, 0x0080 }, /* R1901 - AIF2TX6MIX Input 3 Volume */ + { 0x0000076E, 0x0000 }, /* R1902 - AIF2TX6MIX Input 4 Source */ + { 0x0000076F, 0x0080 }, /* R1903 - AIF2TX6MIX Input 4 Volume */ + { 0x00000780, 0x0000 }, /* R1920 - AIF3TX1MIX Input 1 Source */ + { 0x00000781, 0x0080 }, /* R1921 - AIF3TX1MIX Input 1 Volume */ + { 0x00000782, 0x0000 }, /* R1922 - AIF3TX1MIX Input 2 Source */ + { 0x00000783, 0x0080 }, /* R1923 - AIF3TX1MIX Input 2 Volume */ + { 0x00000784, 0x0000 }, /* R1924 - AIF3TX1MIX Input 3 Source */ + { 0x00000785, 0x0080 }, /* R1925 - AIF3TX1MIX Input 3 Volume */ + { 0x00000786, 0x0000 }, /* R1926 - AIF3TX1MIX Input 4 Source */ + { 0x00000787, 0x0080 }, /* R1927 - AIF3TX1MIX Input 4 Volume */ + { 0x00000788, 0x0000 }, /* R1928 - AIF3TX2MIX Input 1 Source */ + { 0x00000789, 0x0080 }, /* R1929 - AIF3TX2MIX Input 1 Volume */ + { 0x0000078A, 0x0000 }, /* R1930 - AIF3TX2MIX Input 2 Source */ + { 0x0000078B, 0x0080 }, /* R1931 - AIF3TX2MIX Input 2 Volume */ + { 0x0000078C, 0x0000 }, /* R1932 - AIF3TX2MIX Input 3 Source */ + { 0x0000078D, 0x0080 }, /* R1933 - AIF3TX2MIX Input 3 Volume */ + { 0x0000078E, 0x0000 }, /* R1934 - AIF3TX2MIX Input 4 Source */ + { 0x0000078F, 0x0080 }, /* R1935 - AIF3TX2MIX Input 4 Volume */ + { 0x00000880, 0x0000 }, /* R2176 - EQ1MIX Input 1 Source */ + { 0x00000881, 0x0080 }, /* R2177 - EQ1MIX Input 1 Volume */ + { 0x00000882, 0x0000 }, /* R2178 - EQ1MIX Input 2 Source */ + { 0x00000883, 0x0080 }, /* R2179 - EQ1MIX Input 2 Volume */ + { 0x00000884, 0x0000 }, /* R2180 - EQ1MIX Input 3 Source */ + { 0x00000885, 0x0080 }, /* R2181 - EQ1MIX Input 3 Volume */ + { 0x00000886, 0x0000 }, /* R2182 - EQ1MIX Input 4 Source */ + { 0x00000887, 0x0080 }, /* R2183 - EQ1MIX Input 4 Volume */ + { 0x00000888, 0x0000 }, /* R2184 - EQ2MIX Input 1 Source */ + { 0x00000889, 0x0080 }, /* R2185 - EQ2MIX Input 1 Volume */ + { 0x0000088A, 0x0000 }, /* R2186 - EQ2MIX Input 2 Source */ + { 0x0000088B, 0x0080 }, /* R2187 - EQ2MIX Input 2 Volume */ + { 0x0000088C, 0x0000 }, /* R2188 - EQ2MIX Input 3 Source */ + { 0x0000088D, 0x0080 }, /* R2189 - EQ2MIX Input 3 Volume */ + { 0x0000088E, 0x0000 }, /* R2190 - EQ2MIX Input 4 Source */ + { 0x0000088F, 0x0080 }, /* R2191 - EQ2MIX Input 4 Volume */ + { 0x000008C0, 0x0000 }, /* R2240 - DRC1LMIX Input 1 Source */ + { 0x000008C1, 0x0080 }, /* R2241 - DRC1LMIX Input 1 Volume */ + { 0x000008C2, 0x0000 }, /* R2242 - DRC1LMIX Input 2 Source */ + { 0x000008C3, 0x0080 }, /* R2243 - DRC1LMIX Input 2 Volume */ + { 0x000008C4, 0x0000 }, /* R2244 - DRC1LMIX Input 3 Source */ + { 0x000008C5, 0x0080 }, /* R2245 - DRC1LMIX Input 3 Volume */ + { 0x000008C6, 0x0000 }, /* R2246 - DRC1LMIX Input 4 Source */ + { 0x000008C7, 0x0080 }, /* R2247 - DRC1LMIX Input 4 Volume */ + { 0x000008C8, 0x0000 }, /* R2248 - DRC1RMIX Input 1 Source */ + { 0x000008C9, 0x0080 }, /* R2249 - DRC1RMIX Input 1 Volume */ + { 0x000008CA, 0x0000 }, /* R2250 - DRC1RMIX Input 2 Source */ + { 0x000008CB, 0x0080 }, /* R2251 - DRC1RMIX Input 2 Volume */ + { 0x000008CC, 0x0000 }, /* R2252 - DRC1RMIX Input 3 Source */ + { 0x000008CD, 0x0080 }, /* R2253 - DRC1RMIX Input 3 Volume */ + { 0x000008CE, 0x0000 }, /* R2254 - DRC1RMIX Input 4 Source */ + { 0x000008CF, 0x0080 }, /* R2255 - DRC1RMIX Input 4 Volume */ + { 0x000008D0, 0x0000 }, /* R2256 - DRC2LMIX Input 1 Source */ + { 0x000008D1, 0x0080 }, /* R2257 - DRC2LMIX Input 1 Volume */ + { 0x000008D2, 0x0000 }, /* R2258 - DRC2LMIX Input 2 Source */ + { 0x000008D3, 0x0080 }, /* R2259 - DRC2LMIX Input 2 Volume */ + { 0x000008D4, 0x0000 }, /* R2260 - DRC2LMIX Input 3 Source */ + { 0x000008D5, 0x0080 }, /* R2261 - DRC2LMIX Input 3 Volume */ + { 0x000008D6, 0x0000 }, /* R2262 - DRC2LMIX Input 4 Source */ + { 0x000008D7, 0x0080 }, /* R2263 - DRC2LMIX Input 4 Volume */ + { 0x000008D8, 0x0000 }, /* R2264 - DRC2RMIX Input 1 Source */ + { 0x000008D9, 0x0080 }, /* R2265 - DRC2RMIX Input 1 Volume */ + { 0x000008DA, 0x0000 }, /* R2266 - DRC2RMIX Input 2 Source */ + { 0x000008DB, 0x0080 }, /* R2267 - DRC2RMIX Input 2 Volume */ + { 0x000008DC, 0x0000 }, /* R2268 - DRC2RMIX Input 3 Source */ + { 0x000008DD, 0x0080 }, /* R2269 - DRC2RMIX Input 3 Volume */ + { 0x000008DE, 0x0000 }, /* R2270 - DRC2RMIX Input 4 Source */ + { 0x000008DF, 0x0080 }, /* R2271 - DRC2RMIX Input 4 Volume */ + { 0x00000900, 0x0000 }, /* R2304 - HPLP1MIX Input 1 Source */ + { 0x00000901, 0x0080 }, /* R2305 - HPLP1MIX Input 1 Volume */ + { 0x00000902, 0x0000 }, /* R2306 - HPLP1MIX Input 2 Source */ + { 0x00000903, 0x0080 }, /* R2307 - HPLP1MIX Input 2 Volume */ + { 0x00000904, 0x0000 }, /* R2308 - HPLP1MIX Input 3 Source */ + { 0x00000905, 0x0080 }, /* R2309 - HPLP1MIX Input 3 Volume */ + { 0x00000906, 0x0000 }, /* R2310 - HPLP1MIX Input 4 Source */ + { 0x00000907, 0x0080 }, /* R2311 - HPLP1MIX Input 4 Volume */ + { 0x00000908, 0x0000 }, /* R2312 - HPLP2MIX Input 1 Source */ + { 0x00000909, 0x0080 }, /* R2313 - HPLP2MIX Input 1 Volume */ + { 0x0000090A, 0x0000 }, /* R2314 - HPLP2MIX Input 2 Source */ + { 0x0000090B, 0x0080 }, /* R2315 - HPLP2MIX Input 2 Volume */ + { 0x0000090C, 0x0000 }, /* R2316 - HPLP2MIX Input 3 Source */ + { 0x0000090D, 0x0080 }, /* R2317 - HPLP2MIX Input 3 Volume */ + { 0x0000090E, 0x0000 }, /* R2318 - HPLP2MIX Input 4 Source */ + { 0x0000090F, 0x0080 }, /* R2319 - HPLP2MIX Input 4 Volume */ + { 0x00000910, 0x0000 }, /* R2320 - HPLP3MIX Input 1 Source */ + { 0x00000911, 0x0080 }, /* R2321 - HPLP3MIX Input 1 Volume */ + { 0x00000912, 0x0000 }, /* R2322 - HPLP3MIX Input 2 Source */ + { 0x00000913, 0x0080 }, /* R2323 - HPLP3MIX Input 2 Volume */ + { 0x00000914, 0x0000 }, /* R2324 - HPLP3MIX Input 3 Source */ + { 0x00000915, 0x0080 }, /* R2325 - HPLP3MIX Input 3 Volume */ + { 0x00000916, 0x0000 }, /* R2326 - HPLP3MIX Input 4 Source */ + { 0x00000917, 0x0080 }, /* R2327 - HPLP3MIX Input 4 Volume */ + { 0x00000918, 0x0000 }, /* R2328 - HPLP4MIX Input 1 Source */ + { 0x00000919, 0x0080 }, /* R2329 - HPLP4MIX Input 1 Volume */ + { 0x0000091A, 0x0000 }, /* R2330 - HPLP4MIX Input 2 Source */ + { 0x0000091B, 0x0080 }, /* R2331 - HPLP4MIX Input 2 Volume */ + { 0x0000091C, 0x0000 }, /* R2332 - HPLP4MIX Input 3 Source */ + { 0x0000091D, 0x0080 }, /* R2333 - HPLP4MIX Input 3 Volume */ + { 0x0000091E, 0x0000 }, /* R2334 - HPLP4MIX Input 4 Source */ + { 0x0000091F, 0x0080 }, /* R2335 - HPLP4MIX Input 4 Volume */ + { 0x00000980, 0x0000 }, /* R2432 - DSP2LMIX Input 1 Source */ + { 0x00000981, 0x0080 }, /* R2433 - DSP2LMIX Input 1 Volume */ + { 0x00000982, 0x0000 }, /* R2434 - DSP2LMIX Input 2 Source */ + { 0x00000983, 0x0080 }, /* R2435 - DSP2LMIX Input 2 Volume */ + { 0x00000984, 0x0000 }, /* R2436 - DSP2LMIX Input 3 Source */ + { 0x00000985, 0x0080 }, /* R2437 - DSP2LMIX Input 3 Volume */ + { 0x00000986, 0x0000 }, /* R2438 - DSP2LMIX Input 4 Source */ + { 0x00000987, 0x0080 }, /* R2439 - DSP2LMIX Input 4 Volume */ + { 0x00000988, 0x0000 }, /* R2440 - DSP2RMIX Input 1 Source */ + { 0x00000989, 0x0080 }, /* R2441 - DSP2RMIX Input 1 Volume */ + { 0x0000098A, 0x0000 }, /* R2442 - DSP2RMIX Input 2 Source */ + { 0x0000098B, 0x0080 }, /* R2443 - DSP2RMIX Input 2 Volume */ + { 0x0000098C, 0x0000 }, /* R2444 - DSP2RMIX Input 3 Source */ + { 0x0000098D, 0x0080 }, /* R2445 - DSP2RMIX Input 3 Volume */ + { 0x0000098E, 0x0000 }, /* R2446 - DSP2RMIX Input 4 Source */ + { 0x0000098F, 0x0080 }, /* R2447 - DSP2RMIX Input 4 Volume */ + { 0x00000990, 0x0000 }, /* R2448 - DSP2AUX1MIX Input 1 Source */ + { 0x00000998, 0x0000 }, /* R2456 - DSP2AUX2MIX Input 1 Source */ + { 0x000009A0, 0x0000 }, /* R2464 - DSP2AUX3MIX Input 1 Source */ + { 0x000009A8, 0x0000 }, /* R2472 - DSP2AUX4MIX Input 1 Source */ + { 0x000009B0, 0x0000 }, /* R2480 - DSP2AUX5MIX Input 1 Source */ + { 0x000009B8, 0x0000 }, /* R2488 - DSP2AUX6MIX Input 1 Source */ + { 0x000009C0, 0x0000 }, /* R2496 - DSP3LMIX Input 1 Source */ + { 0x000009C1, 0x0080 }, /* R2497 - DSP3LMIX Input 1 Volume */ + { 0x000009C2, 0x0000 }, /* R2498 - DSP3LMIX Input 2 Source */ + { 0x000009C3, 0x0080 }, /* R2499 - DSP3LMIX Input 2 Volume */ + { 0x000009C4, 0x0000 }, /* R2500 - DSP3LMIX Input 3 Source */ + { 0x000009C5, 0x0080 }, /* R2501 - DSP3LMIX Input 3 Volume */ + { 0x000009C6, 0x0000 }, /* R2502 - DSP3LMIX Input 4 Source */ + { 0x000009C7, 0x0080 }, /* R2503 - DSP3LMIX Input 4 Volume */ + { 0x000009C8, 0x0000 }, /* R2504 - DSP3RMIX Input 1 Source */ + { 0x000009C9, 0x0080 }, /* R2505 - DSP3RMIX Input 1 Volume */ + { 0x000009CA, 0x0000 }, /* R2506 - DSP3RMIX Input 2 Source */ + { 0x000009CB, 0x0080 }, /* R2507 - DSP3RMIX Input 2 Volume */ + { 0x000009CC, 0x0000 }, /* R2508 - DSP3RMIX Input 3 Source */ + { 0x000009CD, 0x0080 }, /* R2509 - DSP3RMIX Input 3 Volume */ + { 0x000009CE, 0x0000 }, /* R2510 - DSP3RMIX Input 4 Source */ + { 0x000009CF, 0x0080 }, /* R2511 - DSP3RMIX Input 4 Volume */ + { 0x000009D0, 0x0000 }, /* R2512 - DSP3AUX1MIX Input 1 Source */ + { 0x000009D8, 0x0000 }, /* R2520 - DSP3AUX2MIX Input 1 Source */ + { 0x000009E0, 0x0000 }, /* R2528 - DSP3AUX3MIX Input 1 Source */ + { 0x000009E8, 0x0000 }, /* R2536 - DSP3AUX4MIX Input 1 Source */ + { 0x000009F0, 0x0000 }, /* R2544 - DSP3AUX5MIX Input 1 Source */ + { 0x000009F8, 0x0000 }, /* R2552 - DSP3AUX6MIX Input 1 Source */ + { 0x00000A80, 0x0000 }, /* R2688 - ASRC1LMIX Input 1 Source */ + { 0x00000A88, 0x0000 }, /* R2696 - ASRC1RMIX Input 1 Source */ + { 0x00000A90, 0x0000 }, /* R2704 - ASRC2LMIX Input 1 Source */ + { 0x00000A98, 0x0000 }, /* R2712 - ASRC2RMIX Input 1 Source */ + { 0x00000B00, 0x0000 }, /* R2816 - ISRC1DEC1MIX Input 1 Source */ + { 0x00000B08, 0x0000 }, /* R2824 - ISRC1DEC2MIX Input 1 Source */ + { 0x00000B10, 0x0000 }, /* R2832 - ISRC1DEC3MIX Input 1 Source */ + { 0x00000B18, 0x0000 }, /* R2840 - ISRC1DEC4MIX Input 1 Source */ + { 0x00000B20, 0x0000 }, /* R2848 - ISRC1INT1MIX Input 1 Source */ + { 0x00000B28, 0x0000 }, /* R2856 - ISRC1INT2MIX Input 1 Source */ + { 0x00000B30, 0x0000 }, /* R2864 - ISRC1INT3MIX Input 1 Source */ + { 0x00000B38, 0x0000 }, /* R2872 - ISRC1INT4MIX Input 1 Source */ + { 0x00000B40, 0x0000 }, /* R2880 - ISRC2DEC1MIX Input 1 Source */ + { 0x00000B48, 0x0000 }, /* R2888 - ISRC2DEC2MIX Input 1 Source */ + { 0x00000B50, 0x0000 }, /* R2896 - ISRC2DEC3MIX Input 1 Source */ + { 0x00000B58, 0x0000 }, /* R2904 - ISRC2DEC4MIX Input 1 Source */ + { 0x00000B60, 0x0000 }, /* R2912 - ISRC2INT1MIX Input 1 Source */ + { 0x00000B68, 0x0000 }, /* R2920 - ISRC2INT2MIX Input 1 Source */ + { 0x00000B70, 0x0000 }, /* R2928 - ISRC2INT3MIX Input 1 Source */ + { 0x00000B78, 0x0000 }, /* R2936 - ISRC2INT4MIX Input 1 Source */ + { 0x00000B80, 0x0000 }, /* R2944 - ISRC3DEC1MIX Input 1 Source */ + { 0x00000B88, 0x0000 }, /* R2952 - ISRC3DEC2MIX Input 1 Source */ + { 0x00000B90, 0x0000 }, /* R2960 - ISRC3DEC3MIX Input 1 Source */ + { 0x00000B98, 0x0000 }, /* R2968 - ISRC3DEC4MIX Input 1 Source */ + { 0x00000BA0, 0x0000 }, /* R2976 - ISRC3INT1MIX Input 1 Source */ + { 0x00000BA8, 0x0000 }, /* R2984 - ISRC3INT2MIX Input 1 Source */ + { 0x00000BB0, 0x0000 }, /* R2992 - ISRC3INT3MIX Input 1 Source */ + { 0x00000BB8, 0x0000 }, /* R3000 - ISRC3INT4MIX Input 1 Source */ + { 0x00000C00, 0xA101 }, /* R3072 - GPIO1 CTRL */ + { 0x00000C01, 0xA101 }, /* R3073 - GPIO2 CTRL */ + { 0x00000C0F, 0x0400 }, /* R3087 - IRQ CTRL 1 */ + { 0x00000C10, 0x1000 }, /* R3088 - GPIO Debounce Config */ + { 0x00000C20, 0x0002 }, /* R3104 - Misc Pad Ctrl 1 */ + { 0x00000C21, 0x8001 }, /* R3105 - Misc Pad Ctrl 2 */ + { 0x00000C22, 0x0000 }, /* R3106 - Misc Pad Ctrl 3 */ + { 0x00000C23, 0x0000 }, /* R3107 - Misc Pad Ctrl 4 */ + { 0x00000C24, 0x0000 }, /* R3108 - Misc Pad Ctrl 5 */ + { 0x00000C25, 0x0000 }, /* R3109 - Misc Pad Ctrl 6 */ + { 0x00000C30, 0x0404 }, /* R3120 - Misc Pad Ctrl 7 */ + { 0x00000C32, 0x0404 }, /* R3122 - Misc Pad Ctrl 9 */ + { 0x00000C33, 0x0404 }, /* R3123 - Misc Pad Ctrl 10 */ + { 0x00000C34, 0x0404 }, /* R3124 - Misc Pad Ctrl 11 */ + { 0x00000C35, 0x0404 }, /* R3125 - Misc Pad Ctrl 12 */ + { 0x00000C36, 0x0400 }, /* R3126 - Misc Pad Ctrl 13 */ + { 0x00000C37, 0x0404 }, /* R3127 - Misc Pad Ctrl 14 */ + { 0x00000C39, 0x0400 }, /* R3129 - Misc Pad Ctrl 16 */ + { 0x00000D08, 0x0007 }, /* R3336 - Interrupt Status 1 Mask */ + { 0x00000D09, 0x06FF }, /* R3337 - Interrupt Status 2 Mask */ + { 0x00000D0A, 0xCFEF }, /* R3338 - Interrupt Status 3 Mask */ + { 0x00000D0B, 0xFFC3 }, /* R3339 - Interrupt Status 4 Mask */ + { 0x00000D0C, 0x000B }, /* R3340 - Interrupt Status 5 Mask */ + { 0x00000D0D, 0xD005 }, /* R3341 - Interrupt Status 6 Mask */ + { 0x00000D0F, 0x0000 }, /* R3343 - Interrupt Control */ + { 0x00000D18, 0x0007 }, /* R3352 - IRQ2 Status 1 Mask */ + { 0x00000D19, 0x06FF }, /* R3353 - IRQ2 Status 2 Mask */ + { 0x00000D1A, 0xCFEF }, /* R3354 - IRQ2 Status 3 Mask */ + { 0x00000D1B, 0xFFC3 }, /* R3355 - IRQ2 Status 4 Mask */ + { 0x00000D1C, 0x000B }, /* R3356 - IRQ2 Status 5 Mask */ + { 0x00000D1D, 0xD005 }, /* R3357 - IRQ2 Status 6 Mask */ + { 0x00000D1F, 0x0000 }, /* R3359 - IRQ2 Control */ + { 0x00000E00, 0x0000 }, /* R3584 - FX_Ctrl1 */ + { 0x00000E10, 0x6318 }, /* R3600 - EQ1_1 */ + { 0x00000E11, 0x6300 }, /* R3601 - EQ1_2 */ + { 0x00000E12, 0x0FC8 }, /* R3602 - EQ1_3 */ + { 0x00000E13, 0x03FE }, /* R3603 - EQ1_4 */ + { 0x00000E14, 0x00E0 }, /* R3604 - EQ1_5 */ + { 0x00000E15, 0x1EC4 }, /* R3605 - EQ1_6 */ + { 0x00000E16, 0xF136 }, /* R3606 - EQ1_7 */ + { 0x00000E17, 0x0409 }, /* R3607 - EQ1_8 */ + { 0x00000E18, 0x04CC }, /* R3608 - EQ1_9 */ + { 0x00000E19, 0x1C9B }, /* R3609 - EQ1_10 */ + { 0x00000E1A, 0xF337 }, /* R3610 - EQ1_11 */ + { 0x00000E1B, 0x040B }, /* R3611 - EQ1_12 */ + { 0x00000E1C, 0x0CBB }, /* R3612 - EQ1_13 */ + { 0x00000E1D, 0x16F8 }, /* R3613 - EQ1_14 */ + { 0x00000E1E, 0xF7D9 }, /* R3614 - EQ1_15 */ + { 0x00000E1F, 0x040A }, /* R3615 - EQ1_16 */ + { 0x00000E20, 0x1F14 }, /* R3616 - EQ1_17 */ + { 0x00000E21, 0x058C }, /* R3617 - EQ1_18 */ + { 0x00000E22, 0x0563 }, /* R3618 - EQ1_19 */ + { 0x00000E23, 0x4000 }, /* R3619 - EQ1_20 */ + { 0x00000E24, 0x0B75 }, /* R3620 - EQ1_21 */ + { 0x00000E26, 0x6318 }, /* R3622 - EQ2_1 */ + { 0x00000E27, 0x6300 }, /* R3623 - EQ2_2 */ + { 0x00000E28, 0x0FC8 }, /* R3624 - EQ2_3 */ + { 0x00000E29, 0x03FE }, /* R3625 - EQ2_4 */ + { 0x00000E2A, 0x00E0 }, /* R3626 - EQ2_5 */ + { 0x00000E2B, 0x1EC4 }, /* R3627 - EQ2_6 */ + { 0x00000E2C, 0xF136 }, /* R3628 - EQ2_7 */ + { 0x00000E2D, 0x0409 }, /* R3629 - EQ2_8 */ + { 0x00000E2E, 0x04CC }, /* R3630 - EQ2_9 */ + { 0x00000E2F, 0x1C9B }, /* R3631 - EQ2_10 */ + { 0x00000E30, 0xF337 }, /* R3632 - EQ2_11 */ + { 0x00000E31, 0x040B }, /* R3633 - EQ2_12 */ + { 0x00000E32, 0x0CBB }, /* R3634 - EQ2_13 */ + { 0x00000E33, 0x16F8 }, /* R3635 - EQ2_14 */ + { 0x00000E34, 0xF7D9 }, /* R3636 - EQ2_15 */ + { 0x00000E35, 0x040A }, /* R3637 - EQ2_16 */ + { 0x00000E36, 0x1F14 }, /* R3638 - EQ2_17 */ + { 0x00000E37, 0x058C }, /* R3639 - EQ2_18 */ + { 0x00000E38, 0x0563 }, /* R3640 - EQ2_19 */ + { 0x00000E39, 0x4000 }, /* R3641 - EQ2_20 */ + { 0x00000E3A, 0x0B75 }, /* R3642 - EQ2_21 */ + { 0x00000E80, 0x0018 }, /* R3712 - DRC1 ctrl1 */ + { 0x00000E81, 0x0933 }, /* R3713 - DRC1 ctrl2 */ + { 0x00000E82, 0x0018 }, /* R3714 - DRC1 ctrl3 */ + { 0x00000E83, 0x0000 }, /* R3715 - DRC1 ctrl4 */ + { 0x00000E84, 0x0000 }, /* R3716 - DRC1 ctrl5 */ + { 0x00000E89, 0x0018 }, /* R3721 - DRC2 ctrl1 */ + { 0x00000E8A, 0x0933 }, /* R3722 - DRC2 ctrl2 */ + { 0x00000E8B, 0x0018 }, /* R3723 - DRC2 ctrl3 */ + { 0x00000E8C, 0x0000 }, /* R3724 - DRC2 ctrl4 */ + { 0x00000E8D, 0x0000 }, /* R3725 - DRC2 ctrl5 */ + { 0x00000EC0, 0x0000 }, /* R3776 - HPLPF1_1 */ + { 0x00000EC1, 0x0000 }, /* R3777 - HPLPF1_2 */ + { 0x00000EC4, 0x0000 }, /* R3780 - HPLPF2_1 */ + { 0x00000EC5, 0x0000 }, /* R3781 - HPLPF2_2 */ + { 0x00000EC8, 0x0000 }, /* R3784 - HPLPF3_1 */ + { 0x00000EC9, 0x0000 }, /* R3785 - HPLPF3_2 */ + { 0x00000ECC, 0x0000 }, /* R3788 - HPLPF4_1 */ + { 0x00000ECD, 0x0000 }, /* R3789 - HPLPF4_2 */ + { 0x00000EE0, 0x0000 }, /* R3808 - ASRC_ENABLE */ + { 0x00000EE2, 0x0000 }, /* R3810 - ASRC_RATE1 */ + { 0x00000EE3, 0x4000 }, /* R3811 - ASRC_RATE2 */ + { 0x00000EF0, 0x0000 }, /* R3824 - ISRC 1 CTRL 1 */ + { 0x00000EF1, 0x0000 }, /* R3825 - ISRC 1 CTRL 2 */ + { 0x00000EF2, 0x0000 }, /* R3826 - ISRC 1 CTRL 3 */ + { 0x00000EF3, 0x0000 }, /* R3827 - ISRC 2 CTRL 1 */ + { 0x00000EF4, 0x0000 }, /* R3828 - ISRC 2 CTRL 2 */ + { 0x00000EF5, 0x0000 }, /* R3829 - ISRC 2 CTRL 3 */ + { 0x00000EF6, 0x0000 }, /* R3830 - ISRC 3 CTRL 1 */ + { 0x00000EF7, 0x0000 }, /* R3831 - ISRC 3 CTRL 2 */ + { 0x00000EF8, 0x0000 }, /* R3832 - ISRC 3 CTRL 3 */ + { 0x00001200, 0x0010 }, /* R4608 - DSP2 Control 1 */ + { 0x00001300, 0x0010 }, /* R4864 - DSP3 Control 1 */ +}; + +static bool cs47l24_is_adsp_memory(unsigned int reg) +{ + switch (reg) { + case 0x200000 ... 0x205fff: /* DSP2 PM */ + case 0x280000 ... 0x281fff: /* DSP2 ZM */ + case 0x290000 ... 0x2a7fff: /* DSP2 XM */ + case 0x2a8000 ... 0x2b3fff: /* DSP2 YM */ + case 0x300000 ... 0x308fff: /* DSP3 PM */ + case 0x380000 ... 0x381fff: /* DSP3 ZM */ + case 0x390000 ... 0x3a7fff: /* DSP3 XM */ + case 0x3a8000 ... 0x3b3fff: /* DSP3 YM */ + return true; + default: + return false; + } +} + +static bool cs47l24_readable_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case ARIZONA_SOFTWARE_RESET: + case ARIZONA_DEVICE_REVISION: + case ARIZONA_CTRL_IF_SPI_CFG_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_0: + case ARIZONA_WRITE_SEQUENCER_CTRL_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_2: + case ARIZONA_TONE_GENERATOR_1: + case ARIZONA_TONE_GENERATOR_2: + case ARIZONA_TONE_GENERATOR_3: + case ARIZONA_TONE_GENERATOR_4: + case ARIZONA_TONE_GENERATOR_5: + case ARIZONA_PWM_DRIVE_1: + case ARIZONA_PWM_DRIVE_2: + case ARIZONA_PWM_DRIVE_3: + case ARIZONA_SEQUENCE_CONTROL: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_1: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_2: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_3: + case ARIZONA_SAMPLE_RATE_SEQUENCE_SELECT_4: + case ARIZONA_COMFORT_NOISE_GENERATOR: + case ARIZONA_HAPTICS_CONTROL_1: + case ARIZONA_HAPTICS_CONTROL_2: + case ARIZONA_HAPTICS_PHASE_1_INTENSITY: + case ARIZONA_HAPTICS_PHASE_1_DURATION: + case ARIZONA_HAPTICS_PHASE_2_INTENSITY: + case ARIZONA_HAPTICS_PHASE_2_DURATION: + case ARIZONA_HAPTICS_PHASE_3_INTENSITY: + case ARIZONA_HAPTICS_PHASE_3_DURATION: + case ARIZONA_HAPTICS_STATUS: + case ARIZONA_CLOCK_32K_1: + case ARIZONA_SYSTEM_CLOCK_1: + case ARIZONA_SAMPLE_RATE_1: + case ARIZONA_SAMPLE_RATE_2: + case ARIZONA_SAMPLE_RATE_3: + case ARIZONA_SAMPLE_RATE_1_STATUS: + case ARIZONA_SAMPLE_RATE_2_STATUS: + case ARIZONA_SAMPLE_RATE_3_STATUS: + case ARIZONA_ASYNC_CLOCK_1: + case ARIZONA_ASYNC_SAMPLE_RATE_1: + case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_2: + case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS: + case ARIZONA_OUTPUT_SYSTEM_CLOCK: + case ARIZONA_OUTPUT_ASYNC_CLOCK: + case ARIZONA_RATE_ESTIMATOR_1: + case ARIZONA_RATE_ESTIMATOR_2: + case ARIZONA_RATE_ESTIMATOR_3: + case ARIZONA_RATE_ESTIMATOR_4: + case ARIZONA_RATE_ESTIMATOR_5: + case ARIZONA_FLL1_CONTROL_1: + case ARIZONA_FLL1_CONTROL_2: + case ARIZONA_FLL1_CONTROL_3: + case ARIZONA_FLL1_CONTROL_4: + case ARIZONA_FLL1_CONTROL_5: + case ARIZONA_FLL1_CONTROL_6: + case ARIZONA_FLL1_CONTROL_7: + case ARIZONA_FLL1_LOOP_FILTER_TEST_1: + case ARIZONA_FLL1_NCO_TEST_0: + case ARIZONA_FLL1_SYNCHRONISER_1: + case ARIZONA_FLL1_SYNCHRONISER_2: + case ARIZONA_FLL1_SYNCHRONISER_3: + case ARIZONA_FLL1_SYNCHRONISER_4: + case ARIZONA_FLL1_SYNCHRONISER_5: + case ARIZONA_FLL1_SYNCHRONISER_6: + case ARIZONA_FLL1_SYNCHRONISER_7: + case ARIZONA_FLL1_SPREAD_SPECTRUM: + case ARIZONA_FLL1_GPIO_CLOCK: + case ARIZONA_FLL2_CONTROL_1: + case ARIZONA_FLL2_CONTROL_2: + case ARIZONA_FLL2_CONTROL_3: + case ARIZONA_FLL2_CONTROL_4: + case ARIZONA_FLL2_CONTROL_5: + case ARIZONA_FLL2_CONTROL_6: + case ARIZONA_FLL2_CONTROL_7: + case ARIZONA_FLL2_LOOP_FILTER_TEST_1: + case ARIZONA_FLL2_NCO_TEST_0: + case ARIZONA_FLL2_SYNCHRONISER_1: + case ARIZONA_FLL2_SYNCHRONISER_2: + case ARIZONA_FLL2_SYNCHRONISER_3: + case ARIZONA_FLL2_SYNCHRONISER_4: + case ARIZONA_FLL2_SYNCHRONISER_5: + case ARIZONA_FLL2_SYNCHRONISER_6: + case ARIZONA_FLL2_SYNCHRONISER_7: + case ARIZONA_FLL2_SPREAD_SPECTRUM: + case ARIZONA_FLL2_GPIO_CLOCK: + case ARIZONA_MIC_BIAS_CTRL_1: + case ARIZONA_MIC_BIAS_CTRL_2: + case ARIZONA_HP_CTRL_1L: + case ARIZONA_HP_CTRL_1R: + case ARIZONA_INPUT_ENABLES: + case ARIZONA_INPUT_ENABLES_STATUS: + case ARIZONA_INPUT_RATE: + case ARIZONA_INPUT_VOLUME_RAMP: + case ARIZONA_HPF_CONTROL: + case ARIZONA_IN1L_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_1L: + case ARIZONA_DMIC1L_CONTROL: + case ARIZONA_IN1R_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_1R: + case ARIZONA_DMIC1R_CONTROL: + case ARIZONA_IN2L_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_2L: + case ARIZONA_DMIC2L_CONTROL: + case ARIZONA_IN2R_CONTROL: + case ARIZONA_ADC_DIGITAL_VOLUME_2R: + case ARIZONA_DMIC2R_CONTROL: + case ARIZONA_OUTPUT_ENABLES_1: + case ARIZONA_OUTPUT_STATUS_1: + case ARIZONA_RAW_OUTPUT_STATUS_1: + case ARIZONA_OUTPUT_RATE_1: + case ARIZONA_OUTPUT_VOLUME_RAMP: + case ARIZONA_OUTPUT_PATH_CONFIG_1L: + case ARIZONA_DAC_DIGITAL_VOLUME_1L: + case ARIZONA_DAC_VOLUME_LIMIT_1L: + case ARIZONA_NOISE_GATE_SELECT_1L: + case ARIZONA_DAC_DIGITAL_VOLUME_1R: + case ARIZONA_DAC_VOLUME_LIMIT_1R: + case ARIZONA_NOISE_GATE_SELECT_1R: + case ARIZONA_DAC_DIGITAL_VOLUME_4L: + case ARIZONA_OUT_VOLUME_4L: + case ARIZONA_NOISE_GATE_SELECT_4L: + case ARIZONA_DAC_AEC_CONTROL_1: + case ARIZONA_NOISE_GATE_CONTROL: + case ARIZONA_HP1_SHORT_CIRCUIT_CTRL: + case ARIZONA_AIF1_BCLK_CTRL: + case ARIZONA_AIF1_TX_PIN_CTRL: + case ARIZONA_AIF1_RX_PIN_CTRL: + case ARIZONA_AIF1_RATE_CTRL: + case ARIZONA_AIF1_FORMAT: + case ARIZONA_AIF1_RX_BCLK_RATE: + case ARIZONA_AIF1_FRAME_CTRL_1: + case ARIZONA_AIF1_FRAME_CTRL_2: + case ARIZONA_AIF1_FRAME_CTRL_3: + case ARIZONA_AIF1_FRAME_CTRL_4: + case ARIZONA_AIF1_FRAME_CTRL_5: + case ARIZONA_AIF1_FRAME_CTRL_6: + case ARIZONA_AIF1_FRAME_CTRL_7: + case ARIZONA_AIF1_FRAME_CTRL_8: + case ARIZONA_AIF1_FRAME_CTRL_9: + case ARIZONA_AIF1_FRAME_CTRL_10: + case ARIZONA_AIF1_FRAME_CTRL_11: + case ARIZONA_AIF1_FRAME_CTRL_12: + case ARIZONA_AIF1_FRAME_CTRL_13: + case ARIZONA_AIF1_FRAME_CTRL_14: + case ARIZONA_AIF1_FRAME_CTRL_15: + case ARIZONA_AIF1_FRAME_CTRL_16: + case ARIZONA_AIF1_FRAME_CTRL_17: + case ARIZONA_AIF1_FRAME_CTRL_18: + case ARIZONA_AIF1_TX_ENABLES: + case ARIZONA_AIF1_RX_ENABLES: + case ARIZONA_AIF2_BCLK_CTRL: + case ARIZONA_AIF2_TX_PIN_CTRL: + case ARIZONA_AIF2_RX_PIN_CTRL: + case ARIZONA_AIF2_RATE_CTRL: + case ARIZONA_AIF2_FORMAT: + case ARIZONA_AIF2_RX_BCLK_RATE: + case ARIZONA_AIF2_FRAME_CTRL_1: + case ARIZONA_AIF2_FRAME_CTRL_2: + case ARIZONA_AIF2_FRAME_CTRL_3: + case ARIZONA_AIF2_FRAME_CTRL_4: + case ARIZONA_AIF2_FRAME_CTRL_5: + case ARIZONA_AIF2_FRAME_CTRL_6: + case ARIZONA_AIF2_FRAME_CTRL_7: + case ARIZONA_AIF2_FRAME_CTRL_8: + case ARIZONA_AIF2_FRAME_CTRL_11: + case ARIZONA_AIF2_FRAME_CTRL_12: + case ARIZONA_AIF2_FRAME_CTRL_13: + case ARIZONA_AIF2_FRAME_CTRL_14: + case ARIZONA_AIF2_FRAME_CTRL_15: + case ARIZONA_AIF2_FRAME_CTRL_16: + case ARIZONA_AIF2_TX_ENABLES: + case ARIZONA_AIF2_RX_ENABLES: + case ARIZONA_AIF3_BCLK_CTRL: + case ARIZONA_AIF3_TX_PIN_CTRL: + case ARIZONA_AIF3_RX_PIN_CTRL: + case ARIZONA_AIF3_RATE_CTRL: + case ARIZONA_AIF3_FORMAT: + case ARIZONA_AIF3_RX_BCLK_RATE: + case ARIZONA_AIF3_FRAME_CTRL_1: + case ARIZONA_AIF3_FRAME_CTRL_2: + case ARIZONA_AIF3_FRAME_CTRL_3: + case ARIZONA_AIF3_FRAME_CTRL_4: + case ARIZONA_AIF3_FRAME_CTRL_11: + case ARIZONA_AIF3_FRAME_CTRL_12: + case ARIZONA_AIF3_TX_ENABLES: + case ARIZONA_AIF3_RX_ENABLES: + case ARIZONA_PWM1MIX_INPUT_1_SOURCE: + case ARIZONA_PWM1MIX_INPUT_1_VOLUME: + case ARIZONA_PWM1MIX_INPUT_2_SOURCE: + case ARIZONA_PWM1MIX_INPUT_2_VOLUME: + case ARIZONA_PWM1MIX_INPUT_3_SOURCE: + case ARIZONA_PWM1MIX_INPUT_3_VOLUME: + case ARIZONA_PWM1MIX_INPUT_4_SOURCE: + case ARIZONA_PWM1MIX_INPUT_4_VOLUME: + case ARIZONA_PWM2MIX_INPUT_1_SOURCE: + case ARIZONA_PWM2MIX_INPUT_1_VOLUME: + case ARIZONA_PWM2MIX_INPUT_2_SOURCE: + case ARIZONA_PWM2MIX_INPUT_2_VOLUME: + case ARIZONA_PWM2MIX_INPUT_3_SOURCE: + case ARIZONA_PWM2MIX_INPUT_3_VOLUME: + case ARIZONA_PWM2MIX_INPUT_4_SOURCE: + case ARIZONA_PWM2MIX_INPUT_4_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_1_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_1_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_2_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_2_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_3_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_3_VOLUME: + case ARIZONA_OUT1LMIX_INPUT_4_SOURCE: + case ARIZONA_OUT1LMIX_INPUT_4_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_1_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_1_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_2_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_2_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_3_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_3_VOLUME: + case ARIZONA_OUT1RMIX_INPUT_4_SOURCE: + case ARIZONA_OUT1RMIX_INPUT_4_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_1_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_1_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_2_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_2_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_3_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_3_VOLUME: + case ARIZONA_OUT4LMIX_INPUT_4_SOURCE: + case ARIZONA_OUT4LMIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX2MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX3MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX3MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX4MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX4MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX5MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX5MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX6MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX6MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX7MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX7MIX_INPUT_4_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_1_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_1_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_2_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_2_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_3_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_3_VOLUME: + case ARIZONA_AIF1TX8MIX_INPUT_4_SOURCE: + case ARIZONA_AIF1TX8MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX2MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX3MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX3MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX4MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX4MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX5MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX5MIX_INPUT_4_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_1_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_1_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_2_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_2_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_3_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_3_VOLUME: + case ARIZONA_AIF2TX6MIX_INPUT_4_SOURCE: + case ARIZONA_AIF2TX6MIX_INPUT_4_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_1_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_1_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_2_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_2_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_3_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_3_VOLUME: + case ARIZONA_AIF3TX1MIX_INPUT_4_SOURCE: + case ARIZONA_AIF3TX1MIX_INPUT_4_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_1_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_1_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_2_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_2_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_3_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_3_VOLUME: + case ARIZONA_AIF3TX2MIX_INPUT_4_SOURCE: + case ARIZONA_AIF3TX2MIX_INPUT_4_VOLUME: + case ARIZONA_EQ1MIX_INPUT_1_SOURCE: + case ARIZONA_EQ1MIX_INPUT_1_VOLUME: + case ARIZONA_EQ1MIX_INPUT_2_SOURCE: + case ARIZONA_EQ1MIX_INPUT_2_VOLUME: + case ARIZONA_EQ1MIX_INPUT_3_SOURCE: + case ARIZONA_EQ1MIX_INPUT_3_VOLUME: + case ARIZONA_EQ1MIX_INPUT_4_SOURCE: + case ARIZONA_EQ1MIX_INPUT_4_VOLUME: + case ARIZONA_EQ2MIX_INPUT_1_SOURCE: + case ARIZONA_EQ2MIX_INPUT_1_VOLUME: + case ARIZONA_EQ2MIX_INPUT_2_SOURCE: + case ARIZONA_EQ2MIX_INPUT_2_VOLUME: + case ARIZONA_EQ2MIX_INPUT_3_SOURCE: + case ARIZONA_EQ2MIX_INPUT_3_VOLUME: + case ARIZONA_EQ2MIX_INPUT_4_SOURCE: + case ARIZONA_EQ2MIX_INPUT_4_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_1_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_1_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_2_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_2_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_3_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_3_VOLUME: + case ARIZONA_DRC1LMIX_INPUT_4_SOURCE: + case ARIZONA_DRC1LMIX_INPUT_4_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_1_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_1_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_2_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_2_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_3_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_3_VOLUME: + case ARIZONA_DRC1RMIX_INPUT_4_SOURCE: + case ARIZONA_DRC1RMIX_INPUT_4_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_1_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_1_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_2_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_2_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_3_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_3_VOLUME: + case ARIZONA_DRC2LMIX_INPUT_4_SOURCE: + case ARIZONA_DRC2LMIX_INPUT_4_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_1_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_1_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_2_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_2_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_3_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_3_VOLUME: + case ARIZONA_DRC2RMIX_INPUT_4_SOURCE: + case ARIZONA_DRC2RMIX_INPUT_4_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP1MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP1MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP2MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP2MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP3MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP3MIX_INPUT_4_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_1_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_1_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_2_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_2_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_3_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_3_VOLUME: + case ARIZONA_HPLP4MIX_INPUT_4_SOURCE: + case ARIZONA_HPLP4MIX_INPUT_4_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_1_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_1_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_2_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_2_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_3_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_3_VOLUME: + case ARIZONA_DSP2LMIX_INPUT_4_SOURCE: + case ARIZONA_DSP2LMIX_INPUT_4_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_1_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_1_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_2_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_2_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_3_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_3_VOLUME: + case ARIZONA_DSP2RMIX_INPUT_4_SOURCE: + case ARIZONA_DSP2RMIX_INPUT_4_VOLUME: + case ARIZONA_DSP2AUX1MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX2MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX3MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX4MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX5MIX_INPUT_1_SOURCE: + case ARIZONA_DSP2AUX6MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_1_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_1_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_2_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_2_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_3_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_3_VOLUME: + case ARIZONA_DSP3LMIX_INPUT_4_SOURCE: + case ARIZONA_DSP3LMIX_INPUT_4_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_1_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_1_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_2_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_2_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_3_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_3_VOLUME: + case ARIZONA_DSP3RMIX_INPUT_4_SOURCE: + case ARIZONA_DSP3RMIX_INPUT_4_VOLUME: + case ARIZONA_DSP3AUX1MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX2MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX3MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX4MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX5MIX_INPUT_1_SOURCE: + case ARIZONA_DSP3AUX6MIX_INPUT_1_SOURCE: + case ARIZONA_ASRC1LMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC1RMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC2LMIX_INPUT_1_SOURCE: + case ARIZONA_ASRC2RMIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC2INT4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3DEC4MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT1MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT2MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT3MIX_INPUT_1_SOURCE: + case ARIZONA_ISRC3INT4MIX_INPUT_1_SOURCE: + case ARIZONA_GPIO1_CTRL: + case ARIZONA_GPIO2_CTRL: + case ARIZONA_IRQ_CTRL_1: + case ARIZONA_GPIO_DEBOUNCE_CONFIG: + case ARIZONA_MISC_PAD_CTRL_1: + case ARIZONA_MISC_PAD_CTRL_2: + case ARIZONA_MISC_PAD_CTRL_3: + case ARIZONA_MISC_PAD_CTRL_4: + case ARIZONA_MISC_PAD_CTRL_5: + case ARIZONA_MISC_PAD_CTRL_6: + case ARIZONA_MISC_PAD_CTRL_7: + case ARIZONA_MISC_PAD_CTRL_9: + case ARIZONA_MISC_PAD_CTRL_10: + case ARIZONA_MISC_PAD_CTRL_11: + case ARIZONA_MISC_PAD_CTRL_12: + case ARIZONA_MISC_PAD_CTRL_13: + case ARIZONA_MISC_PAD_CTRL_14: + case ARIZONA_MISC_PAD_CTRL_16: + case ARIZONA_INTERRUPT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_2: + case ARIZONA_INTERRUPT_STATUS_3: + case ARIZONA_INTERRUPT_STATUS_4: + case ARIZONA_INTERRUPT_STATUS_5: + case ARIZONA_INTERRUPT_STATUS_6: + case ARIZONA_INTERRUPT_STATUS_1_MASK: + case ARIZONA_INTERRUPT_STATUS_2_MASK: + case ARIZONA_INTERRUPT_STATUS_3_MASK: + case ARIZONA_INTERRUPT_STATUS_4_MASK: + case ARIZONA_INTERRUPT_STATUS_5_MASK: + case ARIZONA_INTERRUPT_STATUS_6_MASK: + case ARIZONA_INTERRUPT_CONTROL: + case ARIZONA_IRQ2_STATUS_1: + case ARIZONA_IRQ2_STATUS_2: + case ARIZONA_IRQ2_STATUS_3: + case ARIZONA_IRQ2_STATUS_4: + case ARIZONA_IRQ2_STATUS_5: + case ARIZONA_IRQ2_STATUS_6: + case ARIZONA_IRQ2_STATUS_1_MASK: + case ARIZONA_IRQ2_STATUS_2_MASK: + case ARIZONA_IRQ2_STATUS_3_MASK: + case ARIZONA_IRQ2_STATUS_4_MASK: + case ARIZONA_IRQ2_STATUS_5_MASK: + case ARIZONA_IRQ2_STATUS_6_MASK: + case ARIZONA_IRQ2_CONTROL: + case ARIZONA_INTERRUPT_RAW_STATUS_2: + case ARIZONA_INTERRUPT_RAW_STATUS_3: + case ARIZONA_INTERRUPT_RAW_STATUS_4: + case ARIZONA_INTERRUPT_RAW_STATUS_5: + case ARIZONA_INTERRUPT_RAW_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_7: + case ARIZONA_INTERRUPT_RAW_STATUS_8: + case ARIZONA_INTERRUPT_RAW_STATUS_9: + case ARIZONA_IRQ_PIN_STATUS: + case ARIZONA_FX_CTRL1: + case ARIZONA_FX_CTRL2: + case ARIZONA_EQ1_1: + case ARIZONA_EQ1_2: + case ARIZONA_EQ1_3: + case ARIZONA_EQ1_4: + case ARIZONA_EQ1_5: + case ARIZONA_EQ1_6: + case ARIZONA_EQ1_7: + case ARIZONA_EQ1_8: + case ARIZONA_EQ1_9: + case ARIZONA_EQ1_10: + case ARIZONA_EQ1_11: + case ARIZONA_EQ1_12: + case ARIZONA_EQ1_13: + case ARIZONA_EQ1_14: + case ARIZONA_EQ1_15: + case ARIZONA_EQ1_16: + case ARIZONA_EQ1_17: + case ARIZONA_EQ1_18: + case ARIZONA_EQ1_19: + case ARIZONA_EQ1_20: + case ARIZONA_EQ1_21: + case ARIZONA_EQ2_1: + case ARIZONA_EQ2_2: + case ARIZONA_EQ2_3: + case ARIZONA_EQ2_4: + case ARIZONA_EQ2_5: + case ARIZONA_EQ2_6: + case ARIZONA_EQ2_7: + case ARIZONA_EQ2_8: + case ARIZONA_EQ2_9: + case ARIZONA_EQ2_10: + case ARIZONA_EQ2_11: + case ARIZONA_EQ2_12: + case ARIZONA_EQ2_13: + case ARIZONA_EQ2_14: + case ARIZONA_EQ2_15: + case ARIZONA_EQ2_16: + case ARIZONA_EQ2_17: + case ARIZONA_EQ2_18: + case ARIZONA_EQ2_19: + case ARIZONA_EQ2_20: + case ARIZONA_EQ2_21: + case ARIZONA_DRC1_CTRL1: + case ARIZONA_DRC1_CTRL2: + case ARIZONA_DRC1_CTRL3: + case ARIZONA_DRC1_CTRL4: + case ARIZONA_DRC1_CTRL5: + case ARIZONA_DRC2_CTRL1: + case ARIZONA_DRC2_CTRL2: + case ARIZONA_DRC2_CTRL3: + case ARIZONA_DRC2_CTRL4: + case ARIZONA_DRC2_CTRL5: + case ARIZONA_HPLPF1_1: + case ARIZONA_HPLPF1_2: + case ARIZONA_HPLPF2_1: + case ARIZONA_HPLPF2_2: + case ARIZONA_HPLPF3_1: + case ARIZONA_HPLPF3_2: + case ARIZONA_HPLPF4_1: + case ARIZONA_HPLPF4_2: + case ARIZONA_ASRC_ENABLE: + case ARIZONA_ASRC_STATUS: + case ARIZONA_ASRC_RATE1: + case ARIZONA_ASRC_RATE2: + case ARIZONA_ISRC_1_CTRL_1: + case ARIZONA_ISRC_1_CTRL_2: + case ARIZONA_ISRC_1_CTRL_3: + case ARIZONA_ISRC_2_CTRL_1: + case ARIZONA_ISRC_2_CTRL_2: + case ARIZONA_ISRC_2_CTRL_3: + case ARIZONA_ISRC_3_CTRL_1: + case ARIZONA_ISRC_3_CTRL_2: + case ARIZONA_ISRC_3_CTRL_3: + case ARIZONA_DSP2_CONTROL_1: + case ARIZONA_DSP2_CLOCKING_1: + case ARIZONA_DSP2_STATUS_1: + case ARIZONA_DSP2_STATUS_2: + case ARIZONA_DSP2_STATUS_3: + case ARIZONA_DSP2_STATUS_4: + case ARIZONA_DSP2_WDMA_BUFFER_1: + case ARIZONA_DSP2_WDMA_BUFFER_2: + case ARIZONA_DSP2_WDMA_BUFFER_3: + case ARIZONA_DSP2_WDMA_BUFFER_4: + case ARIZONA_DSP2_WDMA_BUFFER_5: + case ARIZONA_DSP2_WDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_BUFFER_7: + case ARIZONA_DSP2_WDMA_BUFFER_8: + case ARIZONA_DSP2_RDMA_BUFFER_1: + case ARIZONA_DSP2_RDMA_BUFFER_2: + case ARIZONA_DSP2_RDMA_BUFFER_3: + case ARIZONA_DSP2_RDMA_BUFFER_4: + case ARIZONA_DSP2_RDMA_BUFFER_5: + case ARIZONA_DSP2_RDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_CONFIG_1: + case ARIZONA_DSP2_WDMA_CONFIG_2: + case ARIZONA_DSP2_WDMA_OFFSET_1: + case ARIZONA_DSP2_RDMA_CONFIG_1: + case ARIZONA_DSP2_RDMA_OFFSET_1: + case ARIZONA_DSP2_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP2_SCRATCH_0: + case ARIZONA_DSP2_SCRATCH_1: + case ARIZONA_DSP2_SCRATCH_2: + case ARIZONA_DSP2_SCRATCH_3: + case ARIZONA_DSP3_CONTROL_1: + case ARIZONA_DSP3_CLOCKING_1: + case ARIZONA_DSP3_STATUS_1: + case ARIZONA_DSP3_STATUS_2: + case ARIZONA_DSP3_STATUS_3: + case ARIZONA_DSP3_STATUS_4: + case ARIZONA_DSP3_WDMA_BUFFER_1: + case ARIZONA_DSP3_WDMA_BUFFER_2: + case ARIZONA_DSP3_WDMA_BUFFER_3: + case ARIZONA_DSP3_WDMA_BUFFER_4: + case ARIZONA_DSP3_WDMA_BUFFER_5: + case ARIZONA_DSP3_WDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_BUFFER_7: + case ARIZONA_DSP3_WDMA_BUFFER_8: + case ARIZONA_DSP3_RDMA_BUFFER_1: + case ARIZONA_DSP3_RDMA_BUFFER_2: + case ARIZONA_DSP3_RDMA_BUFFER_3: + case ARIZONA_DSP3_RDMA_BUFFER_4: + case ARIZONA_DSP3_RDMA_BUFFER_5: + case ARIZONA_DSP3_RDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_CONFIG_1: + case ARIZONA_DSP3_WDMA_CONFIG_2: + case ARIZONA_DSP3_WDMA_OFFSET_1: + case ARIZONA_DSP3_RDMA_CONFIG_1: + case ARIZONA_DSP3_RDMA_OFFSET_1: + case ARIZONA_DSP3_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP3_SCRATCH_0: + case ARIZONA_DSP3_SCRATCH_1: + case ARIZONA_DSP3_SCRATCH_2: + case ARIZONA_DSP3_SCRATCH_3: + return true; + default: + return cs47l24_is_adsp_memory(reg); + } +} + +static bool cs47l24_volatile_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case ARIZONA_SOFTWARE_RESET: + case ARIZONA_DEVICE_REVISION: + case ARIZONA_WRITE_SEQUENCER_CTRL_0: + case ARIZONA_WRITE_SEQUENCER_CTRL_1: + case ARIZONA_WRITE_SEQUENCER_CTRL_2: + case ARIZONA_HAPTICS_STATUS: + case ARIZONA_SAMPLE_RATE_1_STATUS: + case ARIZONA_SAMPLE_RATE_2_STATUS: + case ARIZONA_SAMPLE_RATE_3_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_1_STATUS: + case ARIZONA_ASYNC_SAMPLE_RATE_2_STATUS: + case ARIZONA_HP_CTRL_1L: + case ARIZONA_HP_CTRL_1R: + case ARIZONA_INPUT_ENABLES_STATUS: + case ARIZONA_OUTPUT_STATUS_1: + case ARIZONA_RAW_OUTPUT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_1: + case ARIZONA_INTERRUPT_STATUS_2: + case ARIZONA_INTERRUPT_STATUS_3: + case ARIZONA_INTERRUPT_STATUS_4: + case ARIZONA_INTERRUPT_STATUS_5: + case ARIZONA_INTERRUPT_STATUS_6: + case ARIZONA_IRQ2_STATUS_1: + case ARIZONA_IRQ2_STATUS_2: + case ARIZONA_IRQ2_STATUS_3: + case ARIZONA_IRQ2_STATUS_4: + case ARIZONA_IRQ2_STATUS_5: + case ARIZONA_IRQ2_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_2: + case ARIZONA_INTERRUPT_RAW_STATUS_3: + case ARIZONA_INTERRUPT_RAW_STATUS_4: + case ARIZONA_INTERRUPT_RAW_STATUS_5: + case ARIZONA_INTERRUPT_RAW_STATUS_6: + case ARIZONA_INTERRUPT_RAW_STATUS_7: + case ARIZONA_INTERRUPT_RAW_STATUS_8: + case ARIZONA_INTERRUPT_RAW_STATUS_9: + case ARIZONA_IRQ_PIN_STATUS: + case ARIZONA_FX_CTRL2: + case ARIZONA_ASRC_STATUS: + case ARIZONA_DSP2_STATUS_1: + case ARIZONA_DSP2_STATUS_2: + case ARIZONA_DSP2_STATUS_3: + case ARIZONA_DSP2_STATUS_4: + case ARIZONA_DSP2_WDMA_BUFFER_1: + case ARIZONA_DSP2_WDMA_BUFFER_2: + case ARIZONA_DSP2_WDMA_BUFFER_3: + case ARIZONA_DSP2_WDMA_BUFFER_4: + case ARIZONA_DSP2_WDMA_BUFFER_5: + case ARIZONA_DSP2_WDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_BUFFER_7: + case ARIZONA_DSP2_WDMA_BUFFER_8: + case ARIZONA_DSP2_RDMA_BUFFER_1: + case ARIZONA_DSP2_RDMA_BUFFER_2: + case ARIZONA_DSP2_RDMA_BUFFER_3: + case ARIZONA_DSP2_RDMA_BUFFER_4: + case ARIZONA_DSP2_RDMA_BUFFER_5: + case ARIZONA_DSP2_RDMA_BUFFER_6: + case ARIZONA_DSP2_WDMA_CONFIG_1: + case ARIZONA_DSP2_WDMA_CONFIG_2: + case ARIZONA_DSP2_WDMA_OFFSET_1: + case ARIZONA_DSP2_RDMA_CONFIG_1: + case ARIZONA_DSP2_RDMA_OFFSET_1: + case ARIZONA_DSP2_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP2_SCRATCH_0: + case ARIZONA_DSP2_SCRATCH_1: + case ARIZONA_DSP2_SCRATCH_2: + case ARIZONA_DSP2_SCRATCH_3: + case ARIZONA_DSP2_CLOCKING_1: + case ARIZONA_DSP3_STATUS_1: + case ARIZONA_DSP3_STATUS_2: + case ARIZONA_DSP3_STATUS_3: + case ARIZONA_DSP3_STATUS_4: + case ARIZONA_DSP3_WDMA_BUFFER_1: + case ARIZONA_DSP3_WDMA_BUFFER_2: + case ARIZONA_DSP3_WDMA_BUFFER_3: + case ARIZONA_DSP3_WDMA_BUFFER_4: + case ARIZONA_DSP3_WDMA_BUFFER_5: + case ARIZONA_DSP3_WDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_BUFFER_7: + case ARIZONA_DSP3_WDMA_BUFFER_8: + case ARIZONA_DSP3_RDMA_BUFFER_1: + case ARIZONA_DSP3_RDMA_BUFFER_2: + case ARIZONA_DSP3_RDMA_BUFFER_3: + case ARIZONA_DSP3_RDMA_BUFFER_4: + case ARIZONA_DSP3_RDMA_BUFFER_5: + case ARIZONA_DSP3_RDMA_BUFFER_6: + case ARIZONA_DSP3_WDMA_CONFIG_1: + case ARIZONA_DSP3_WDMA_CONFIG_2: + case ARIZONA_DSP3_WDMA_OFFSET_1: + case ARIZONA_DSP3_RDMA_CONFIG_1: + case ARIZONA_DSP3_RDMA_OFFSET_1: + case ARIZONA_DSP3_EXTERNAL_START_SELECT_1: + case ARIZONA_DSP3_SCRATCH_0: + case ARIZONA_DSP3_SCRATCH_1: + case ARIZONA_DSP3_SCRATCH_2: + case ARIZONA_DSP3_SCRATCH_3: + case ARIZONA_DSP3_CLOCKING_1: + return true; + default: + return cs47l24_is_adsp_memory(reg); + } +} + +#define CS47L24_MAX_REGISTER 0x3b3fff + +const struct regmap_config cs47l24_spi_regmap = { + .reg_bits = 32, + .pad_bits = 16, + .val_bits = 16, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .val_format_endian = REGMAP_ENDIAN_BIG, + + .max_register = CS47L24_MAX_REGISTER, + .readable_reg = cs47l24_readable_register, + .volatile_reg = cs47l24_volatile_register, + + .cache_type = REGCACHE_RBTREE, + .reg_defaults = cs47l24_reg_default, + .num_reg_defaults = ARRAY_SIZE(cs47l24_reg_default), +}; +EXPORT_SYMBOL_GPL(cs47l24_spi_regmap); + diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h index 79e607e2f081..d55a42297d49 100644 --- a/include/linux/mfd/arizona/core.h +++ b/include/linux/mfd/arizona/core.h @@ -27,6 +27,8 @@ enum arizona_type { WM8280 = 4, WM8998 = 5, WM1814 = 6, + WM1831 = 7, + CS47L24 = 8, }; #define ARIZONA_IRQ_GP1 0 @@ -166,6 +168,7 @@ static inline int wm5102_patch(struct arizona *arizona) #endif int wm5110_patch(struct arizona *arizona); +int cs47l24_patch(struct arizona *arizona); int wm8997_patch(struct arizona *arizona); int wm8998_patch(struct arizona *arizona); -- cgit v1.2.3 From 7523e4dc5057e157212b4741abd6256e03404cf1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 26 Nov 2015 09:44:08 +1030 Subject: module: use a structure to encapsulate layout. Makes it easier to handle init vs core cleanly, though the change is fairly invasive across random architectures. It simplifies the rbtree code immediately, however, while keeping the core data together in the same cachline (now iff the rbtree code is enabled). Acked-by: Peter Zijlstra Reviewed-by: Josh Poimboeuf Signed-off-by: Rusty Russell Signed-off-by: Jiri Kosina --- arch/alpha/kernel/module.c | 2 +- arch/arc/kernel/unwind.c | 4 +- arch/arm/kernel/module-plts.c | 2 +- arch/avr32/kernel/module.c | 12 +-- arch/ia64/kernel/module.c | 14 +-- arch/metag/kernel/module.c | 4 +- arch/mips/kernel/vpe.c | 6 +- arch/parisc/kernel/module.c | 32 +++---- arch/powerpc/kernel/module_32.c | 6 +- arch/s390/kernel/module.c | 22 ++--- arch/x86/kernel/livepatch.c | 6 +- include/linux/module.h | 64 ++++++------- kernel/debug/kdb/kdb_main.c | 4 +- kernel/module.c | 199 +++++++++++++++++++--------------------- 14 files changed, 178 insertions(+), 199 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 2fd00b7077e4..936bc8f89a67 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -160,7 +160,7 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, /* The small sections were sorted to the end of the segment. The following should definitely cover them. */ - gp = (u64)me->module_core + me->core_size - 0x8000; + gp = (u64)me->core_layout.base + me->core_layout.size - 0x8000; got = sechdrs[me->arch.gotsecindex].sh_addr; for (i = 0; i < n; i++) { diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 93c6ea52b671..e0034a6656ef 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -372,8 +372,8 @@ void *unwind_add_table(struct module *module, const void *table_start, return NULL; init_unwind_table(table, module->name, - module->module_core, module->core_size, - module->module_init, module->init_size, + module->core_layout.base, module->core_layout.size, + module->init_layout.base, module->init_layout.size, table_start, table_size, NULL, 0); diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index 097e2e201b9f..0c7efc3446c0 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -32,7 +32,7 @@ struct plt_entries { static bool in_init(const struct module *mod, u32 addr) { - return addr - (u32)mod->module_init < mod->init_size; + return addr - (u32)mod->init_layout.base < mod->init_layout.size; } u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 164efa009e5b..2b4c54c04cb6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -118,9 +118,9 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, * Increase core size to make room for GOT and set start * offset for GOT. */ - module->core_size = ALIGN(module->core_size, 4); - module->arch.got_offset = module->core_size; - module->core_size += module->arch.got_size; + module->core_layout.size = ALIGN(module->core_layout.size, 4); + module->arch.got_offset = module->core_layout.size; + module->core_layout.size += module->arch.got_size; return 0; @@ -177,7 +177,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, if (!info->got_initialized) { Elf32_Addr *gotent; - gotent = (module->module_core + gotent = (module->core_layout.base + module->arch.got_offset + info->got_offset); *gotent = relocation; @@ -255,8 +255,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, */ pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n", relocation, module->arch.got_offset, - module->module_core); - relocation -= ((unsigned long)module->module_core + module->core_layout.base); + relocation -= ((unsigned long)module->core_layout.base + module->arch.got_offset); *location = relocation; break; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index b15933c31b2f..6ab0ae7d6535 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -486,13 +486,13 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, static inline int in_init (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_init < mod->init_size; + return addr - (uint64_t) mod->init_layout.base < mod->init_layout.size; } static inline int in_core (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->module_core < mod->core_size; + return addr - (uint64_t) mod->core_layout.base < mod->core_layout.size; } static inline int @@ -675,7 +675,7 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, break; case RV_BDREL: - val -= (uint64_t) (in_init(mod, val) ? mod->module_init : mod->module_core); + val -= (uint64_t) (in_init(mod, val) ? mod->init_layout.base : mod->core_layout.base); break; case RV_LTV: @@ -810,15 +810,15 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind * addresses have been selected... */ uint64_t gp; - if (mod->core_size > MAX_LTOFF) + if (mod->core_layout.size > MAX_LTOFF) /* * This takes advantage of fact that SHF_ARCH_SMALL gets allocated * at the end of the module. */ - gp = mod->core_size - MAX_LTOFF / 2; + gp = mod->core_layout.size - MAX_LTOFF / 2; else - gp = mod->core_size / 2; - gp = (uint64_t) mod->module_core + ((gp + 7) & -8); + gp = mod->core_layout.size / 2; + gp = (uint64_t) mod->core_layout.base + ((gp + 7) & -8); mod->arch.gp = gp; DEBUGP("%s: placing gp at 0x%lx\n", __func__, gp); } diff --git a/arch/metag/kernel/module.c b/arch/metag/kernel/module.c index 986331cd0a52..bb8dfba9a763 100644 --- a/arch/metag/kernel/module.c +++ b/arch/metag/kernel/module.c @@ -176,8 +176,8 @@ static uint32_t do_plt_call(void *location, Elf32_Addr val, tramp[1] = 0xac000001 | ((val & 0x0000ffff) << 3); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 9067b651c7a2..544ea21bfef9 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -205,11 +205,11 @@ static void layout_sections(struct module *mod, const Elf_Ehdr *hdr, || s->sh_entsize != ~0UL) continue; s->sh_entsize = - get_offset((unsigned long *)&mod->core_size, s); + get_offset((unsigned long *)&mod->core_layout.size, s); } if (m == 0) - mod->core_text_size = mod->core_size; + mod->core_layout.text_size = mod->core_layout.size; } } @@ -641,7 +641,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.core_size); + v->load_addr = alloc_progmem(mod.core_layout.size); if (!v->load_addr) return -ENOMEM; diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 3c63a820fcda..b9d75d9fa9ac 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -42,9 +42,9 @@ * We are not doing SEGREL32 handling correctly. According to the ABI, we * should do a value offset, like this: * if (in_init(me, (void *)val)) - * val -= (uint32_t)me->module_init; + * val -= (uint32_t)me->init_layout.base; * else - * val -= (uint32_t)me->module_core; + * val -= (uint32_t)me->core_layout.base; * However, SEGREL32 is used only for PARISC unwind entries, and we want * those entries to have an absolute address, and not just an offset. * @@ -100,14 +100,14 @@ * or init pieces the location is */ static inline int in_init(struct module *me, void *loc) { - return (loc >= me->module_init && - loc <= (me->module_init + me->init_size)); + return (loc >= me->init_layout.base && + loc <= (me->init_layout.base + me->init_layout.size)); } static inline int in_core(struct module *me, void *loc) { - return (loc >= me->module_core && - loc <= (me->module_core + me->core_size)); + return (loc >= me->core_layout.base && + loc <= (me->core_layout.base + me->core_layout.size)); } static inline int in_local(struct module *me, void *loc) @@ -367,13 +367,13 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, } /* align things a bit */ - me->core_size = ALIGN(me->core_size, 16); - me->arch.got_offset = me->core_size; - me->core_size += gots * sizeof(struct got_entry); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += gots * sizeof(struct got_entry); - me->core_size = ALIGN(me->core_size, 16); - me->arch.fdesc_offset = me->core_size; - me->core_size += fdescs * sizeof(Elf_Fdesc); + me->core_layout.size = ALIGN(me->core_layout.size, 16); + me->arch.fdesc_offset = me->core_layout.size; + me->core_layout.size += fdescs * sizeof(Elf_Fdesc); me->arch.got_max = gots; me->arch.fdesc_max = fdescs; @@ -391,7 +391,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) BUG_ON(value == 0); - got = me->module_core + me->arch.got_offset; + got = me->core_layout.base + me->arch.got_offset; for (i = 0; got[i].addr; i++) if (got[i].addr == value) goto out; @@ -409,7 +409,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) #ifdef CONFIG_64BIT static Elf_Addr get_fdesc(struct module *me, unsigned long value) { - Elf_Fdesc *fdesc = me->module_core + me->arch.fdesc_offset; + Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset; if (!value) { printk(KERN_ERR "%s: zero OPD requested!\n", me->name); @@ -427,7 +427,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value) /* Create new one */ fdesc->addr = value; - fdesc->gp = (Elf_Addr)me->module_core + me->arch.got_offset; + fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; return (Elf_Addr)fdesc; } #endif /* CONFIG_64BIT */ @@ -839,7 +839,7 @@ register_unwind_table(struct module *me, table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr; end = table + sechdrs[me->arch.unwind_section].sh_size; - gp = (Elf_Addr)me->module_core + me->arch.got_offset; + gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; DEBUGP("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n", me->arch.unwind_section, table, end, gp); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index c94d2e018d84..2c01665eb410 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -188,8 +188,8 @@ static uint32_t do_plt_call(void *location, pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location); /* Init, or core PLT? */ - if (location >= mod->module_core - && location < mod->module_core + mod->core_size) + if (location >= mod->core_layout.base + && location < mod->core_layout.base + mod->core_layout.size) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; @@ -296,7 +296,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, } #ifdef CONFIG_DYNAMIC_FTRACE module->arch.tramp = - do_plt_call(module->module_core, + do_plt_call(module->core_layout.base, (unsigned long)ftrace_caller, sechdrs, module); #endif diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 0c1a679314dd..7873e171457c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -159,11 +159,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, /* Increase core size by size of got & plt and set start offsets for got and plt. */ - me->core_size = ALIGN(me->core_size, 4); - me->arch.got_offset = me->core_size; - me->core_size += me->arch.got_size; - me->arch.plt_offset = me->core_size; - me->core_size += me->arch.plt_size; + me->core_layout.size = ALIGN(me->core_layout.size, 4); + me->arch.got_offset = me->core_layout.size; + me->core_layout.size += me->arch.got_size; + me->arch.plt_offset = me->core_layout.size; + me->core_layout.size += me->arch.plt_size; return 0; } @@ -279,7 +279,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, if (info->got_initialized == 0) { Elf_Addr *gotent; - gotent = me->module_core + me->arch.got_offset + + gotent = me->core_layout.base + me->arch.got_offset + info->got_offset; *gotent = val; info->got_initialized = 1; @@ -302,7 +302,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, rc = apply_rela_bits(loc, val, 0, 64, 0); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { - val += (Elf_Addr) me->module_core - loc; + val += (Elf_Addr) me->core_layout.base - loc; rc = apply_rela_bits(loc, val, 1, 32, 1); } break; @@ -315,7 +315,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { unsigned int *ip; - ip = me->module_core + me->arch.plt_offset + + ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ ip[1] = 0x100a0004; @@ -334,7 +334,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val - loc + 0xffffUL < 0x1ffffeUL) || (r_type == R_390_PLT32DBL && val - loc + 0xffffffffULL < 0x1fffffffeULL))) - val = (Elf_Addr) me->module_core + + val = (Elf_Addr) me->core_layout.base + me->arch.plt_offset + info->plt_offset; val += rela->r_addend - loc; @@ -356,7 +356,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTOFF32: /* 32 bit offset to GOT. */ case R_390_GOTOFF64: /* 64 bit offset to GOT. */ val = val + rela->r_addend - - ((Elf_Addr) me->module_core + me->arch.got_offset); + ((Elf_Addr) me->core_layout.base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) rc = apply_rela_bits(loc, val, 0, 16, 0); else if (r_type == R_390_GOTOFF32) @@ -366,7 +366,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ - val = (Elf_Addr) me->module_core + me->arch.got_offset + + val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) rc = apply_rela_bits(loc, val, 1, 32, 0); diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c index d1d35ccffed3..bcc06e82a593 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -41,8 +41,8 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, int ret, numpages, size = 4; bool readonly; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -72,7 +72,7 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, readonly = false; #ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_ro_size) + if (loc < core + mod->core_layout.ro_size) readonly = true; #endif diff --git a/include/linux/module.h b/include/linux/module.h index 3a19c79918e0..6e68e8cf4d0d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -302,6 +302,28 @@ struct mod_tree_node { struct latch_tree_node node; }; +struct module_layout { + /* The actual code + data. */ + void *base; + /* Total size. */ + unsigned int size; + /* The size of the executable code. */ + unsigned int text_size; + /* Size of RO section of the module (text+rodata) */ + unsigned int ro_size; + +#ifdef CONFIG_MODULES_TREE_LOOKUP + struct mod_tree_node mtn; +#endif +}; + +#ifdef CONFIG_MODULES_TREE_LOOKUP +/* Only touch one cacheline for common rbtree-for-core-layout case. */ +#define __module_layout_align ____cacheline_aligned +#else +#define __module_layout_align +#endif + struct module { enum module_state state; @@ -366,37 +388,9 @@ struct module { /* Startup function. */ int (*init)(void); - /* - * If this is non-NULL, vfree() after init() returns. - * - * Cacheline align here, such that: - * module_init, module_core, init_size, core_size, - * init_text_size, core_text_size and mtn_core::{mod,node[0]} - * are on the same cacheline. - */ - void *module_init ____cacheline_aligned; - - /* Here is the actual code + data, vfree'd on unload. */ - void *module_core; - - /* Here are the sizes of the init and core sections */ - unsigned int init_size, core_size; - - /* The size of the executable code in each section. */ - unsigned int init_text_size, core_text_size; - -#ifdef CONFIG_MODULES_TREE_LOOKUP - /* - * We want mtn_core::{mod,node[0]} to be in the same cacheline as the - * above entries such that a regular lookup will only touch one - * cacheline. - */ - struct mod_tree_node mtn_core; - struct mod_tree_node mtn_init; -#endif - - /* Size of RO sections of the module (text+rodata) */ - unsigned int init_ro_size, core_ro_size; + /* Core layout: rbtree is accessed frequently, so keep together. */ + struct module_layout core_layout __module_layout_align; + struct module_layout init_layout; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -505,15 +499,15 @@ bool is_module_text_address(unsigned long addr); static inline bool within_module_core(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_core <= addr && - addr < (unsigned long)mod->module_core + mod->core_size; + return (unsigned long)mod->core_layout.base <= addr && + addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->module_init <= addr && - addr < (unsigned long)mod->module_init + mod->init_size; + return (unsigned long)mod->init_layout.base <= addr && + addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; } static inline bool within_module(unsigned long addr, const struct module *mod) diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4121345498e0..2a20c0dfdafc 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2021,7 +2021,7 @@ static int kdb_lsmod(int argc, const char **argv) continue; kdb_printf("%-20s%8u 0x%p ", mod->name, - mod->core_size, (void *)mod); + mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); #endif @@ -2031,7 +2031,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->module_core); + kdb_printf(" 0x%p", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { diff --git a/kernel/module.c b/kernel/module.c index 14b224967e7b..a0a3d6d9d5e8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -108,13 +108,6 @@ static LIST_HEAD(modules); * Use a latched RB-tree for __module_address(); this allows us to use * RCU-sched lookups of the address from any context. * - * Because modules have two address ranges: init and core, we need two - * latch_tree_nodes entries. Therefore we need the back-pointer from - * mod_tree_node. - * - * Because init ranges are short lived we mark them unlikely and have placed - * them outside the critical cacheline in struct module. - * * This is conditional on PERF_EVENTS || TRACING because those can really hit * __module_address() hard by doing a lot of stack unwinding; potentially from * NMI context. @@ -122,24 +115,16 @@ static LIST_HEAD(modules); static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->module_init; - - return (unsigned long)mod->module_core; + return (unsigned long)layout->base; } static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; - - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->init_size; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - return (unsigned long)mod->core_size; + return (unsigned long)layout->size; } static __always_inline bool @@ -197,23 +182,23 @@ static void __mod_tree_remove(struct mod_tree_node *node) */ static void mod_tree_insert(struct module *mod) { - mod->mtn_core.mod = mod; - mod->mtn_init.mod = mod; + mod->core_layout.mtn.mod = mod; + mod->init_layout.mtn.mod = mod; - __mod_tree_insert(&mod->mtn_core); - if (mod->init_size) - __mod_tree_insert(&mod->mtn_init); + __mod_tree_insert(&mod->core_layout.mtn); + if (mod->init_layout.size) + __mod_tree_insert(&mod->init_layout.mtn); } static void mod_tree_remove_init(struct module *mod) { - if (mod->init_size) - __mod_tree_remove(&mod->mtn_init); + if (mod->init_layout.size) + __mod_tree_remove(&mod->init_layout.mtn); } static void mod_tree_remove(struct module *mod) { - __mod_tree_remove(&mod->mtn_core); + __mod_tree_remove(&mod->core_layout.mtn); mod_tree_remove_init(mod); } @@ -267,9 +252,9 @@ static void __mod_update_bounds(void *base, unsigned int size) static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->module_core, mod->core_size); - if (mod->init_size) - __mod_update_bounds(mod->module_init, mod->init_size); + __mod_update_bounds(mod->core_layout.base, mod->core_layout.size); + if (mod->init_layout.size) + __mod_update_bounds(mod->init_layout.base, mod->init_layout.size); } #ifdef CONFIG_KGDB_KDB @@ -1214,7 +1199,7 @@ struct module_attribute module_uevent = static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->core_size); + return sprintf(buffer, "%u\n", mk->mod->core_layout.size); } static struct module_attribute modinfo_coresize = @@ -1223,7 +1208,7 @@ static struct module_attribute modinfo_coresize = static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->init_size); + return sprintf(buffer, "%u\n", mk->mod->init_layout.size); } static struct module_attribute modinfo_initsize = @@ -1917,29 +1902,29 @@ static void set_section_ro_nx(void *base, static void set_module_core_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_core, mod->core_text_size, - mod->core_ro_size, mod->core_size, + set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, + mod->core_layout.ro_size, mod->core_layout.size, set_memory_ro, set_memory_nx); } static void unset_module_core_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_core, mod->core_text_size, - mod->core_ro_size, mod->core_size, + set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, + mod->core_layout.ro_size, mod->core_layout.size, set_memory_rw, set_memory_x); } static void set_module_init_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_init, mod->init_text_size, - mod->init_ro_size, mod->init_size, + set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, + mod->init_layout.ro_size, mod->init_layout.size, set_memory_ro, set_memory_nx); } static void unset_module_init_ro_nx(struct module *mod) { - set_section_ro_nx(mod->module_init, mod->init_text_size, - mod->init_ro_size, mod->init_size, + set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, + mod->init_layout.ro_size, mod->init_layout.size, set_memory_rw, set_memory_x); } @@ -1952,14 +1937,14 @@ void set_all_modules_text_rw(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, + if ((mod->core_layout.base) && (mod->core_layout.text_size)) { + set_page_attributes(mod->core_layout.base, + mod->core_layout.base + mod->core_layout.text_size, set_memory_rw); } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, + if ((mod->init_layout.base) && (mod->init_layout.text_size)) { + set_page_attributes(mod->init_layout.base, + mod->init_layout.base + mod->init_layout.text_size, set_memory_rw); } } @@ -1975,14 +1960,14 @@ void set_all_modules_text_ro(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, + if ((mod->core_layout.base) && (mod->core_layout.text_size)) { + set_page_attributes(mod->core_layout.base, + mod->core_layout.base + mod->core_layout.text_size, set_memory_ro); } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, + if ((mod->init_layout.base) && (mod->init_layout.text_size)) { + set_page_attributes(mod->init_layout.base, + mod->init_layout.base + mod->init_layout.text_size, set_memory_ro); } } @@ -2047,16 +2032,16 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); + module_memfree(mod->init_layout.base); kfree(mod->args); percpu_modfree(mod); /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ unset_module_core_ro_nx(mod); - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2259,20 +2244,20 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || strstarts(sname, ".init")) continue; - s->sh_entsize = get_offset(mod, &mod->core_size, s, i); + s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->core_size = debug_align(mod->core_size); - mod->core_text_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.text_size = mod->core_layout.size; break; case 1: /* RO: text and ro-data */ - mod->core_size = debug_align(mod->core_size); - mod->core_ro_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.ro_size = mod->core_layout.size; break; case 3: /* whole core */ - mod->core_size = debug_align(mod->core_size); + mod->core_layout.size = debug_align(mod->core_layout.size); break; } } @@ -2288,21 +2273,21 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || !strstarts(sname, ".init")) continue; - s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) + s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->init_size = debug_align(mod->init_size); - mod->init_text_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.text_size = mod->init_layout.size; break; case 1: /* RO: text and ro-data */ - mod->init_size = debug_align(mod->init_size); - mod->init_ro_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.ro_size = mod->init_layout.size; break; case 3: /* whole init */ - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); break; } } @@ -2477,7 +2462,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + symsect->sh_entsize = get_offset(mod, &mod->init_layout.size, symsect, info->index.sym) | INIT_OFFSET_MASK; pr_debug("\t%s\n", info->secstrings + symsect->sh_name); @@ -2494,16 +2479,16 @@ static void layout_symtab(struct module *mod, struct load_info *info) } /* Append room for core symbols at end of core part. */ - info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->core_size += strtab_size; - mod->core_size = debug_align(mod->core_size); + info->symoffs = ALIGN(mod->core_layout.size, symsect->sh_addralign ?: 1); + info->stroffs = mod->core_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->core_layout.size += strtab_size; + mod->core_layout.size = debug_align(mod->core_layout.size); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; - strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, + strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); } @@ -2524,8 +2509,8 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + info->symoffs; - mod->core_strtab = s = mod->module_core + info->stroffs; + mod->core_symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_strtab = s = mod->core_layout.base + info->stroffs; src = mod->symtab; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || @@ -2975,7 +2960,7 @@ static int move_module(struct module *mod, struct load_info *info) void *ptr; /* Do the allocs. */ - ptr = module_alloc(mod->core_size); + ptr = module_alloc(mod->core_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. Just mark it as not being a @@ -2985,11 +2970,11 @@ static int move_module(struct module *mod, struct load_info *info) if (!ptr) return -ENOMEM; - memset(ptr, 0, mod->core_size); - mod->module_core = ptr; + memset(ptr, 0, mod->core_layout.size); + mod->core_layout.base = ptr; - if (mod->init_size) { - ptr = module_alloc(mod->init_size); + if (mod->init_layout.size) { + ptr = module_alloc(mod->init_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. This block doesn't need to be @@ -2998,13 +2983,13 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); return -ENOMEM; } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + memset(ptr, 0, mod->init_layout.size); + mod->init_layout.base = ptr; } else - mod->module_init = NULL; + mod->init_layout.base = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -3016,10 +3001,10 @@ static int move_module(struct module *mod, struct load_info *info) continue; if (shdr->sh_entsize & INIT_OFFSET_MASK) - dest = mod->module_init + dest = mod->init_layout.base + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + shdr->sh_entsize; + dest = mod->core_layout.base + shdr->sh_entsize; if (shdr->sh_type != SHT_NOBITS) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); @@ -3081,12 +3066,12 @@ static void flush_module_icache(const struct module *mod) * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ - if (mod->module_init) - flush_icache_range((unsigned long)mod->module_init, - (unsigned long)mod->module_init - + mod->init_size); - flush_icache_range((unsigned long)mod->module_core, - (unsigned long)mod->module_core + mod->core_size); + if (mod->init_layout.base) + flush_icache_range((unsigned long)mod->init_layout.base, + (unsigned long)mod->init_layout.base + + mod->init_layout.size); + flush_icache_range((unsigned long)mod->core_layout.base, + (unsigned long)mod->core_layout.base + mod->core_layout.size); set_fs(old_fs); } @@ -3144,8 +3129,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); - module_memfree(mod->module_core); + module_memfree(mod->init_layout.base); + module_memfree(mod->core_layout.base); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3232,7 +3217,7 @@ static noinline int do_init_module(struct module *mod) ret = -ENOMEM; goto fail; } - freeinit->module_init = mod->module_init; + freeinit->module_init = mod->init_layout.base; /* * We want to find out whether @mod uses async during init. Clear @@ -3292,10 +3277,10 @@ static noinline int do_init_module(struct module *mod) mod_tree_remove_init(mod); unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; + mod->init_layout.base = NULL; + mod->init_layout.size = 0; + mod->init_layout.ro_size = 0; + mod->init_layout.text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we @@ -3575,7 +3560,7 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); module_deallocate(mod, info); free_copy: @@ -3653,9 +3638,9 @@ static const char *get_ksymbol(struct module *mod, /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->module_init+mod->init_text_size; + nextval = (unsigned long)mod->init_layout.base+mod->init_layout.text_size; else - nextval = (unsigned long)mod->module_core+mod->core_text_size; + nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size; /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ @@ -3902,7 +3887,7 @@ static int m_show(struct seq_file *m, void *p) return 0; seq_printf(m, "%s %u", - mod->name, mod->init_size + mod->core_size); + mod->name, mod->init_layout.size + mod->core_layout.size); print_unload_info(m, mod); /* Informative for users. */ @@ -3911,7 +3896,7 @@ static int m_show(struct seq_file *m, void *p) mod->state == MODULE_STATE_COMING ? "Loading" : "Live"); /* Used by oprofile and other similar tools. */ - seq_printf(m, " 0x%pK", mod->module_core); + seq_printf(m, " 0x%pK", mod->core_layout.base); /* Taints info */ if (mod->taints) @@ -4054,8 +4039,8 @@ struct module *__module_text_address(unsigned long addr) struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ - if (!within(addr, mod->module_init, mod->init_text_size) - && !within(addr, mod->module_core, mod->core_text_size)) + if (!within(addr, mod->init_layout.base, mod->init_layout.text_size) + && !within(addr, mod->core_layout.base, mod->core_layout.text_size)) mod = NULL; } return mod; -- cgit v1.2.3 From 85c898db6327353d38f3dd428457384cf81f83f8 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 26 Nov 2015 09:45:08 +1030 Subject: module: clean up RO/NX handling. Modules have three sections: text, rodata and writable data. The code handled the case where these overlapped, however they never can: debug_align() ensures they are always page-aligned. This is why we got away with manually traversing the pages in set_all_modules_text_rw() without rounding. We create three helper functions: frob_text(), frob_rodata() and frob_writable_data(). We then call these explicitly at every point, so it's clear what we're doing. We also expose module_enable_ro() and module_disable_ro() for livepatch to use. Reviewed-by: Josh Poimboeuf Signed-off-by: Rusty Russell Signed-off-by: Jiri Kosina --- include/linux/module.h | 4 ++ kernel/module.c | 168 +++++++++++++++++++++++-------------------------- 2 files changed, 81 insertions(+), 91 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 6e68e8cf4d0d..4560d8f1545d 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -762,9 +762,13 @@ extern int module_sysfs_initialized; #ifdef CONFIG_DEBUG_SET_MODULE_RONX extern void set_all_modules_text_rw(void); extern void set_all_modules_text_ro(void); +extern void module_enable_ro(const struct module *mod); +extern void module_disable_ro(const struct module *mod); #else static inline void set_all_modules_text_rw(void) { } static inline void set_all_modules_text_ro(void) { } +static inline void module_enable_ro(const struct module *mod) { } +static inline void module_disable_ro(const struct module *mod) { } #endif #ifdef CONFIG_GENERIC_BUG diff --git a/kernel/module.c b/kernel/module.c index a0a3d6d9d5e8..77212128f34a 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -80,15 +80,6 @@ # define debug_align(X) (X) #endif -/* - * Given BASE and SIZE this macro calculates the number of pages the - * memory regions occupies - */ -#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \ - (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \ - PFN_DOWN((unsigned long)BASE) + 1) \ - : (0UL)) - /* If this is set, the section belongs in the init part of the module */ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) @@ -1858,74 +1849,75 @@ static void mod_sysfs_teardown(struct module *mod) /* * LKM RO/NX protection: protect module's text/ro-data * from modification and any data from execution. + * + * General layout of module is: + * [text] [read-only-data] [writable data] + * text_size -----^ ^ ^ + * ro_size ------------------------| | + * size -------------------------------------------| + * + * These values are always page-aligned (as is base) */ -void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages)) +static void frob_text(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - unsigned long begin_pfn = PFN_DOWN((unsigned long)start); - unsigned long end_pfn = PFN_DOWN((unsigned long)end); - - if (end_pfn > begin_pfn) - set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base, + layout->text_size >> PAGE_SHIFT); } -static void set_section_ro_nx(void *base, - unsigned long text_size, - unsigned long ro_size, - unsigned long total_size, - int (*set_ro)(unsigned long start, int num_pages), - int (*set_nx)(unsigned long start, int num_pages)) +static void frob_rodata(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - /* begin and end PFNs of the current subsection */ - unsigned long begin_pfn; - unsigned long end_pfn; - - /* - * Set RO for module text and RO-data: - * - Always protect first page. - * - Do not protect last partial page. - */ - if (ro_size > 0) - set_page_attributes(base, base + ro_size, set_ro); + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->text_size, + (layout->ro_size - layout->text_size) >> PAGE_SHIFT); +} - /* - * Set NX permissions for module data: - * - Do not protect first partial page. - * - Always protect last page. - */ - if (total_size > text_size) { - begin_pfn = PFN_UP((unsigned long)base + text_size); - end_pfn = PFN_UP((unsigned long)base + total_size); - if (end_pfn > begin_pfn) - set_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); - } +static void frob_writable_data(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->ro_size, + (layout->size - layout->ro_size) >> PAGE_SHIFT); } -static void set_module_core_ro_nx(struct module *mod) +/* livepatching wants to disable read-only so it can frob module. */ +void module_disable_ro(const struct module *mod) { - set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, - mod->core_layout.ro_size, mod->core_layout.size, - set_memory_ro, set_memory_nx); + frob_text(&mod->core_layout, set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); + frob_rodata(&mod->init_layout, set_memory_rw); } -static void unset_module_core_ro_nx(struct module *mod) +void module_enable_ro(const struct module *mod) { - set_section_ro_nx(mod->core_layout.base, mod->core_layout.text_size, - mod->core_layout.ro_size, mod->core_layout.size, - set_memory_rw, set_memory_x); + frob_text(&mod->core_layout, set_memory_ro); + frob_rodata(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_rodata(&mod->init_layout, set_memory_ro); } -static void set_module_init_ro_nx(struct module *mod) +static void module_enable_nx(const struct module *mod) { - set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, - mod->init_layout.ro_size, mod->init_layout.size, - set_memory_ro, set_memory_nx); + frob_rodata(&mod->core_layout, set_memory_nx); + frob_writable_data(&mod->core_layout, set_memory_nx); + frob_rodata(&mod->init_layout, set_memory_nx); + frob_writable_data(&mod->init_layout, set_memory_nx); } -static void unset_module_init_ro_nx(struct module *mod) +static void module_disable_nx(const struct module *mod) { - set_section_ro_nx(mod->init_layout.base, mod->init_layout.text_size, - mod->init_layout.ro_size, mod->init_layout.size, - set_memory_rw, set_memory_x); + frob_rodata(&mod->core_layout, set_memory_x); + frob_writable_data(&mod->core_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_x); + frob_writable_data(&mod->init_layout, set_memory_x); } /* Iterate through all modules and set each module's text as RW */ @@ -1937,16 +1929,9 @@ void set_all_modules_text_rw(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->core_layout.base) && (mod->core_layout.text_size)) { - set_page_attributes(mod->core_layout.base, - mod->core_layout.base + mod->core_layout.text_size, - set_memory_rw); - } - if ((mod->init_layout.base) && (mod->init_layout.text_size)) { - set_page_attributes(mod->init_layout.base, - mod->init_layout.base + mod->init_layout.text_size, - set_memory_rw); - } + + frob_text(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); } mutex_unlock(&module_mutex); } @@ -1960,24 +1945,25 @@ void set_all_modules_text_ro(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->core_layout.base) && (mod->core_layout.text_size)) { - set_page_attributes(mod->core_layout.base, - mod->core_layout.base + mod->core_layout.text_size, - set_memory_ro); - } - if ((mod->init_layout.base) && (mod->init_layout.text_size)) { - set_page_attributes(mod->init_layout.base, - mod->init_layout.base + mod->init_layout.text_size, - set_memory_ro); - } + + frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); } mutex_unlock(&module_mutex); } + +static void disable_ro_nx(const struct module_layout *layout) +{ + frob_text(layout, set_memory_rw); + frob_rodata(layout, set_memory_rw); + frob_rodata(layout, set_memory_x); + frob_writable_data(layout, set_memory_x); +} + #else -static void set_module_core_ro_nx(struct module *mod) { } -static void set_module_init_ro_nx(struct module *mod) { } -static void unset_module_core_ro_nx(struct module *mod) { } -static void unset_module_init_ro_nx(struct module *mod) { } +static void disable_ro_nx(const struct module_layout *layout) { } +static void module_enable_nx(const struct module *mod) { } +static void module_disable_nx(const struct module *mod) { } #endif void __weak module_memfree(void *module_region) @@ -2029,8 +2015,8 @@ static void free_module(struct module *mod) synchronize_sched(); mutex_unlock(&module_mutex); - /* This may be NULL, but that's OK */ - unset_module_init_ro_nx(mod); + /* This may be empty, but that's OK */ + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); module_memfree(mod->init_layout.base); kfree(mod->args); @@ -2040,7 +2026,7 @@ static void free_module(struct module *mod) lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ - unset_module_core_ro_nx(mod); + disable_ro_nx(&mod->core_layout); module_memfree(mod->core_layout.base); #ifdef CONFIG_MPU @@ -3275,7 +3261,7 @@ static noinline int do_init_module(struct module *mod) mod->strtab = mod->core_strtab; #endif mod_tree_remove_init(mod); - unset_module_init_ro_nx(mod); + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); mod->init_layout.base = NULL; mod->init_layout.size = 0; @@ -3370,8 +3356,8 @@ static int complete_formation(struct module *mod, struct load_info *info) module_bug_finalize(info->hdr, info->sechdrs, mod); /* Set RO and NX regions */ - set_module_init_ro_nx(mod); - set_module_core_ro_nx(mod); + module_enable_ro(mod); + module_enable_nx(mod); /* Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ @@ -3536,8 +3522,8 @@ static int load_module(struct load_info *info, const char __user *uargs, MODULE_STATE_GOING, mod); /* we can't deallocate the module until we clear memory protection */ - unset_module_init_ro_nx(mod); - unset_module_core_ro_nx(mod); + module_disable_ro(mod); + module_disable_nx(mod); ddebug_cleanup: dynamic_debug_remove(info->debug); -- cgit v1.2.3 From 703df6c097956d17a818e63961c82e8e9eef9fef Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 23 Nov 2015 10:53:51 -0600 Subject: power: bq27xxx_battery: Reorganize I2C into a module Separate out I2C functionality into a module. This fixes several small issues and simplifies the driver initialization. Signed-off-by: Andrew F. Davis Signed-off-by: Sebastian Reichel --- drivers/power/Kconfig | 14 +- drivers/power/Makefile | 1 + drivers/power/bq27xxx_battery.c | 326 +++------------------------------- drivers/power/bq27xxx_battery_i2c.c | 150 ++++++++++++++++ include/linux/power/bq27xxx_battery.h | 57 ++++-- 5 files changed, 227 insertions(+), 321 deletions(-) create mode 100644 drivers/power/bq27xxx_battery_i2c.c (limited to 'include/linux') diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 237d7aa73e8c..42a5b51c3d2e 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -160,22 +160,16 @@ config BATTERY_SBS config BATTERY_BQ27XXX tristate "BQ27xxx battery driver" help - Say Y here to enable support for batteries with BQ27xxx (I2C/HDQ) chips. + Say Y here to enable support for batteries with BQ27xxx chips. config BATTERY_BQ27XXX_I2C - bool "BQ27xxx I2C support" + tristate "BQ27xxx I2C support" depends on BATTERY_BQ27XXX depends on I2C default y help - Say Y here to enable support for batteries with BQ27xxx (I2C) chips. - -config BATTERY_BQ27XXX_PLATFORM - bool "BQ27xxx HDQ support" - depends on BATTERY_BQ27XXX - default y - help - Say Y here to enable support for batteries with BQ27xxx (HDQ) chips. + Say Y here to enable support for batteries with BQ27xxx chips + connected over an I2C bus. config BATTERY_DA9030 tristate "DA9030 battery driver" diff --git a/drivers/power/Makefile b/drivers/power/Makefile index b656638f8b39..0e4eab55f8d7 100644 --- a/drivers/power/Makefile +++ b/drivers/power/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_BATTERY_IPAQ_MICRO) += ipaq_micro_battery.o obj-$(CONFIG_BATTERY_WM97XX) += wm97xx_battery.o obj-$(CONFIG_BATTERY_SBS) += sbs-battery.o obj-$(CONFIG_BATTERY_BQ27XXX) += bq27xxx_battery.o +obj-$(CONFIG_BATTERY_BQ27XXX_I2C) += bq27xxx_battery_i2c.o obj-$(CONFIG_BATTERY_DA9030) += da9030_battery.o obj-$(CONFIG_BATTERY_DA9052) += da9052-battery.o obj-$(CONFIG_CHARGER_DA9150) += da9150-charger.o diff --git a/drivers/power/bq27xxx_battery.c b/drivers/power/bq27xxx_battery.c index 1cad7accf339..8d4ef9fd9b6e 100644 --- a/drivers/power/bq27xxx_battery.c +++ b/drivers/power/bq27xxx_battery.c @@ -45,11 +45,7 @@ #include #include #include -#include -#include #include -#include -#include #include @@ -78,11 +74,6 @@ #define BQ27XXX_POWER_CONSTANT (29200) /* 29.2 µV^2 * 1000 */ #define BQ27XXX_CURRENT_CONSTANT (3570) /* 3.57 µV * 1000 */ -struct bq27xxx_device_info; -struct bq27xxx_access_methods { - int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); -}; - #define INVALID_REG_ADDR 0xff /* @@ -110,40 +101,6 @@ enum bq27xxx_reg_index { BQ27XXX_REG_AP, /* Average Power */ }; -struct bq27xxx_reg_cache { - int temperature; - int time_to_empty; - int time_to_empty_avg; - int time_to_full; - int charge_full; - int cycle_count; - int capacity; - int energy; - int flags; - int power_avg; - int health; -}; - -struct bq27xxx_device_info { - struct device *dev; - int id; - enum bq27xxx_chip chip; - - struct bq27xxx_reg_cache cache; - int charge_design_full; - - unsigned long last_update; - struct delayed_work work; - - struct power_supply *bat; - - struct bq27xxx_access_methods bus; - - struct mutex lock; - - u8 *regs; -}; - /* Register mappings */ static u8 bq27000_regs[] = { 0x00, /* CONTROL */ @@ -710,7 +667,7 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -static void bq27xxx_battery_update(struct bq27xxx_device_info *di) +void bq27xxx_battery_update(struct bq27xxx_device_info *di) { struct bq27xxx_reg_cache cache = {0, }; bool has_ci_flag = di->chip == BQ27000 || di->chip == BQ27010; @@ -761,6 +718,7 @@ static void bq27xxx_battery_update(struct bq27xxx_device_info *di) di->last_update = jiffies; } +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); static void bq27xxx_battery_poll(struct work_struct *work) { @@ -991,32 +949,30 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) schedule_delayed_work(&di->work, 0); } -static int bq27xxx_powersupply_init(struct bq27xxx_device_info *di, - const char *name) +int bq27xxx_battery_setup(struct bq27xxx_device_info *di) { - int ret; struct power_supply_desc *psy_desc; struct power_supply_config psy_cfg = { .drv_data = di, }; + INIT_DELAYED_WORK(&di->work, bq27xxx_battery_poll); + mutex_init(&di->lock); + di->regs = bq27xxx_regs[di->chip]; + psy_desc = devm_kzalloc(di->dev, sizeof(*psy_desc), GFP_KERNEL); if (!psy_desc) return -ENOMEM; - psy_desc->name = name; + psy_desc->name = di->name; psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; psy_desc->properties = bq27xxx_battery_props[di->chip].props; psy_desc->num_properties = bq27xxx_battery_props[di->chip].size; psy_desc->get_property = bq27xxx_battery_get_property; psy_desc->external_power_changed = bq27xxx_external_power_changed; - INIT_DELAYED_WORK(&di->work, bq27xxx_battery_poll); - mutex_init(&di->lock); - di->bat = power_supply_register_no_ws(di->dev, psy_desc, &psy_cfg); if (IS_ERR(di->bat)) { - ret = PTR_ERR(di->bat); - dev_err(di->dev, "failed to register battery: %d\n", ret); - return ret; + dev_err(di->dev, "failed to register battery\n"); + return PTR_ERR(di->bat); } dev_info(di->dev, "support ver. %s enabled\n", DRIVER_VERSION); @@ -1025,8 +981,9 @@ static int bq27xxx_powersupply_init(struct bq27xxx_device_info *di, return 0; } +EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); -static void bq27xxx_powersupply_unregister(struct bq27xxx_device_info *di) +void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { /* * power_supply_unregister call bq27xxx_battery_get_property which @@ -1042,192 +999,7 @@ static void bq27xxx_powersupply_unregister(struct bq27xxx_device_info *di) mutex_destroy(&di->lock); } - -/* i2c specific code */ -#ifdef CONFIG_BATTERY_BQ27XXX_I2C - -/* If the system has several batteries we need a different name for each - * of them... - */ -static DEFINE_IDR(battery_id); -static DEFINE_MUTEX(battery_mutex); - -static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) -{ - struct bq27xxx_device_info *di = data; - - bq27xxx_battery_update(di); - - return IRQ_HANDLED; -} - -static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg, - bool single) -{ - struct i2c_client *client = to_i2c_client(di->dev); - struct i2c_msg msg[2]; - unsigned char data[2]; - int ret; - - if (!client->adapter) - return -ENODEV; - - msg[0].addr = client->addr; - msg[0].flags = 0; - msg[0].buf = ® - msg[0].len = sizeof(reg); - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].buf = data; - if (single) - msg[1].len = 1; - else - msg[1].len = 2; - - ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg)); - if (ret < 0) - return ret; - - if (!single) - ret = get_unaligned_le16(data); - else - ret = data[0]; - - return ret; -} - -static int bq27xxx_battery_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) -{ - char *name; - struct bq27xxx_device_info *di; - int num; - int retval = 0; - - /* Get new ID for the new battery device */ - mutex_lock(&battery_mutex); - num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); - mutex_unlock(&battery_mutex); - if (num < 0) - return num; - - name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num); - if (!name) { - retval = -ENOMEM; - goto batt_failed; - } - - di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); - if (!di) { - retval = -ENOMEM; - goto batt_failed; - } - - di->id = num; - di->dev = &client->dev; - di->chip = id->driver_data; - di->bus.read = &bq27xxx_battery_i2c_read; - di->regs = bq27xxx_regs[di->chip]; - - retval = bq27xxx_powersupply_init(di, name); - if (retval) - goto batt_failed; - - /* Schedule a polling after about 1 min */ - schedule_delayed_work(&di->work, 60 * HZ); - - i2c_set_clientdata(client, di); - - if (client->irq) { - retval = devm_request_threaded_irq(&client->dev, client->irq, - NULL, bq27xxx_battery_irq_handler_thread, - IRQF_ONESHOT, - name, di); - if (retval) { - dev_err(&client->dev, - "Unable to register IRQ %d error %d\n", - client->irq, retval); - return retval; - } - } - - return 0; - -batt_failed: - mutex_lock(&battery_mutex); - idr_remove(&battery_id, num); - mutex_unlock(&battery_mutex); - - return retval; -} - -static int bq27xxx_battery_i2c_remove(struct i2c_client *client) -{ - struct bq27xxx_device_info *di = i2c_get_clientdata(client); - - bq27xxx_powersupply_unregister(di); - - mutex_lock(&battery_mutex); - idr_remove(&battery_id, di->id); - mutex_unlock(&battery_mutex); - - return 0; -} - -static const struct i2c_device_id bq27xxx_id[] = { - { "bq27200", BQ27000 }, - { "bq27210", BQ27010 }, - { "bq27500", BQ27500 }, - { "bq27510", BQ27500 }, - { "bq27520", BQ27500 }, - { "bq27530", BQ27530 }, - { "bq27531", BQ27530 }, - { "bq27541", BQ27541 }, - { "bq27542", BQ27541 }, - { "bq27546", BQ27541 }, - { "bq27742", BQ27541 }, - { "bq27545", BQ27545 }, - { "bq27421", BQ27421 }, - { "bq27425", BQ27421 }, - { "bq27441", BQ27421 }, - { "bq27621", BQ27421 }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, bq27xxx_id); - -static struct i2c_driver bq27xxx_battery_i2c_driver = { - .driver = { - .name = "bq27xxx-battery", - }, - .probe = bq27xxx_battery_i2c_probe, - .remove = bq27xxx_battery_i2c_remove, - .id_table = bq27xxx_id, -}; - -static inline int bq27xxx_battery_i2c_init(void) -{ - int ret = i2c_add_driver(&bq27xxx_battery_i2c_driver); - - if (ret) - pr_err("Unable to register BQ27xxx i2c driver\n"); - - return ret; -} - -static inline void bq27xxx_battery_i2c_exit(void) -{ - i2c_del_driver(&bq27xxx_battery_i2c_driver); -} - -#else - -static inline int bq27xxx_battery_i2c_init(void) { return 0; } -static inline void bq27xxx_battery_i2c_exit(void) {}; - -#endif - -/* platform specific code */ -#ifdef CONFIG_BATTERY_BQ27XXX_PLATFORM +EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); static int bq27xxx_battery_platform_read(struct bq27xxx_device_info *di, u8 reg, bool single) @@ -1267,7 +1039,6 @@ static int bq27xxx_battery_platform_probe(struct platform_device *pdev) { struct bq27xxx_device_info *di; struct bq27xxx_platform_data *pdata = pdev->dev.platform_data; - const char *name; if (!pdata) { dev_err(&pdev->dev, "no platform_data supplied\n"); @@ -1292,83 +1063,36 @@ static int bq27xxx_battery_platform_probe(struct platform_device *pdev) di->dev = &pdev->dev; di->chip = pdata->chip; - di->regs = bq27xxx_regs[di->chip]; - - name = pdata->name ?: dev_name(&pdev->dev); - di->bus.read = &bq27xxx_battery_platform_read; + di->name = pdata->name ?: dev_name(&pdev->dev); + di->bus.read = bq27xxx_battery_platform_read; - return bq27xxx_powersupply_init(di, name); + return bq27xxx_battery_setup(di); } static int bq27xxx_battery_platform_remove(struct platform_device *pdev) { struct bq27xxx_device_info *di = platform_get_drvdata(pdev); - bq27xxx_powersupply_unregister(di); + bq27xxx_battery_teardown(di); return 0; } +static const struct platform_device_id bq27xxx_battery_platform_id_table[] = { + { "bq27000-battery", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, bq27xxx_battery_platform_id_table); + static struct platform_driver bq27xxx_battery_platform_driver = { .probe = bq27xxx_battery_platform_probe, .remove = bq27xxx_battery_platform_remove, .driver = { .name = "bq27000-battery", }, + .id_table = bq27xxx_battery_platform_id_table, }; - -static inline int bq27xxx_battery_platform_init(void) -{ - int ret = platform_driver_register(&bq27xxx_battery_platform_driver); - - if (ret) - pr_err("Unable to register BQ27xxx platform driver\n"); - - return ret; -} - -static inline void bq27xxx_battery_platform_exit(void) -{ - platform_driver_unregister(&bq27xxx_battery_platform_driver); -} - -#else - -static inline int bq27xxx_battery_platform_init(void) { return 0; } -static inline void bq27xxx_battery_platform_exit(void) {}; - -#endif - -/* - * Module stuff - */ - -static int __init bq27xxx_battery_init(void) -{ - int ret; - - ret = bq27xxx_battery_i2c_init(); - if (ret) - return ret; - - ret = bq27xxx_battery_platform_init(); - if (ret) - bq27xxx_battery_i2c_exit(); - - return ret; -} -module_init(bq27xxx_battery_init); - -static void __exit bq27xxx_battery_exit(void) -{ - bq27xxx_battery_platform_exit(); - bq27xxx_battery_i2c_exit(); -} -module_exit(bq27xxx_battery_exit); - -#ifdef CONFIG_BATTERY_BQ27XXX_PLATFORM -MODULE_ALIAS("platform:bq27000-battery"); -#endif +module_platform_driver(bq27xxx_battery_platform_driver); MODULE_AUTHOR("Rodolfo Giometti "); MODULE_DESCRIPTION("BQ27xxx battery monitor driver"); diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c new file mode 100644 index 000000000000..9429e66be096 --- /dev/null +++ b/drivers/power/bq27xxx_battery_i2c.c @@ -0,0 +1,150 @@ +/* + * SCI Reset driver for Keystone based devices + * + * Copyright (C) 2015 Texas Instruments Incorporated - http://www.ti.com/ + * Andrew F. Davis + * + * 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 "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include + +#include + +static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) +{ + struct bq27xxx_device_info *di = data; + + bq27xxx_battery_update(di); + + return IRQ_HANDLED; +} + +static int bq27xxx_battery_i2c_read(struct bq27xxx_device_info *di, u8 reg, + bool single) +{ + struct i2c_client *client = to_i2c_client(di->dev); + struct i2c_msg msg[2]; + unsigned char data[2]; + int ret; + + if (!client->adapter) + return -ENODEV; + + msg[0].addr = client->addr; + msg[0].flags = 0; + msg[0].buf = ® + msg[0].len = sizeof(reg); + msg[1].addr = client->addr; + msg[1].flags = I2C_M_RD; + msg[1].buf = data; + if (single) + msg[1].len = 1; + else + msg[1].len = 2; + + ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg)); + if (ret < 0) + return ret; + + if (!single) + ret = get_unaligned_le16(data); + else + ret = data[0]; + + return ret; +} + +static int bq27xxx_battery_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct bq27xxx_device_info *di; + int ret; + + di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); + if (!di) + return -ENOMEM; + + di->dev = &client->dev; + di->chip = id->driver_data; + di->name = id->name; + di->bus.read = bq27xxx_battery_i2c_read; + + ret = bq27xxx_battery_setup(di); + if (ret) + return ret; + + /* Schedule a polling after about 1 min */ + schedule_delayed_work(&di->work, 60 * HZ); + + i2c_set_clientdata(client, di); + + if (client->irq) { + ret = devm_request_threaded_irq(&client->dev, client->irq, + NULL, bq27xxx_battery_irq_handler_thread, + IRQF_ONESHOT, + di->name, di); + if (ret) { + dev_err(&client->dev, + "Unable to register IRQ %d error %d\n", + client->irq, ret); + return ret; + } + } + + return 0; +} + +static int bq27xxx_battery_i2c_remove(struct i2c_client *client) +{ + struct bq27xxx_device_info *di = i2c_get_clientdata(client); + + bq27xxx_battery_teardown(di); + + return 0; +} + +static const struct i2c_device_id bq27xxx_i2c_id_table[] = { + { "bq27200", BQ27000 }, + { "bq27210", BQ27010 }, + { "bq27500", BQ27500 }, + { "bq27510", BQ27500 }, + { "bq27520", BQ27500 }, + { "bq27530", BQ27530 }, + { "bq27531", BQ27530 }, + { "bq27541", BQ27541 }, + { "bq27542", BQ27541 }, + { "bq27546", BQ27541 }, + { "bq27742", BQ27541 }, + { "bq27545", BQ27545 }, + { "bq27421", BQ27421 }, + { "bq27425", BQ27421 }, + { "bq27441", BQ27421 }, + { "bq27621", BQ27421 }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, bq27xxx_i2c_id_table); + +static struct i2c_driver bq27xxx_battery_i2c_driver = { + .driver = { + .name = "bq27xxx-battery", + }, + .probe = bq27xxx_battery_i2c_probe, + .remove = bq27xxx_battery_i2c_remove, + .id_table = bq27xxx_i2c_id_table, +}; +module_i2c_driver(bq27xxx_battery_i2c_driver); + +MODULE_AUTHOR("Andrew F. Davis "); +MODULE_DESCRIPTION("BQ27xxx battery monitor i2c driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 45f6a7b5b3cb..998d8f1c3c91 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -1,6 +1,16 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +enum bq27xxx_chip { + BQ27000 = 1, /* bq27000, bq27200 */ + BQ27010, /* bq27010, bq27210 */ + BQ27500, /* bq27500, bq27510, bq27520 */ + BQ27530, /* bq27530, bq27531 */ + BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ + BQ27545, /* bq27545 */ + BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ +}; + /** * struct bq27xxx_plaform_data - Platform data for bq27xxx devices * @name: Name of the battery. @@ -12,20 +22,47 @@ * register to be read. The return value should either be the content of * the passed register or an error value. */ -enum bq27xxx_chip { - BQ27000 = 1, /* bq27000, bq27200 */ - BQ27010, /* bq27010, bq27210 */ - BQ27500, /* bq27500, bq27510, bq27520 */ - BQ27530, /* bq27530, bq27531 */ - BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ - BQ27545, /* bq27545 */ - BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ -}; - struct bq27xxx_platform_data { const char *name; enum bq27xxx_chip chip; int (*read)(struct device *dev, unsigned int); }; +struct bq27xxx_device_info; +struct bq27xxx_access_methods { + int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); +}; + +struct bq27xxx_reg_cache { + int temperature; + int time_to_empty; + int time_to_empty_avg; + int time_to_full; + int charge_full; + int cycle_count; + int capacity; + int energy; + int flags; + int power_avg; + int health; +}; + +struct bq27xxx_device_info { + struct device *dev; + enum bq27xxx_chip chip; + const char *name; + struct bq27xxx_access_methods bus; + struct bq27xxx_reg_cache cache; + int charge_design_full; + unsigned long last_update; + struct delayed_work work; + struct power_supply *bat; + struct mutex lock; + u8 *regs; +}; + +void bq27xxx_battery_update(struct bq27xxx_device_info *di); +int bq27xxx_battery_setup(struct bq27xxx_device_info *di); +void bq27xxx_battery_teardown(struct bq27xxx_device_info *di); + #endif -- cgit v1.2.3 From b1d6ab1aa8cdc23b89bcd578ea8d5e3c501a13d9 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 23 Nov 2015 11:06:43 +0100 Subject: dmaengine: Add might_sleep() to dmaengine_synchronize() Implementations of dmaengine_synchronize() are allowed to sleep, hence the function must not be called to from atomic context. Add might_sleep() to dmaengine_synchronize() to make it easier to detect non-compliant callers. Suggested-by: Andy Shevchenko Signed-off-by: Lars-Peter Clausen Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 4662d9aa6d5a..2f69e1d93f92 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -895,6 +895,8 @@ static inline int dmaengine_terminate_async(struct dma_chan *chan) */ static inline void dmaengine_synchronize(struct dma_chan *chan) { + might_sleep(); + if (chan->device->device_synchronize) chan->device->device_synchronize(chan); } -- cgit v1.2.3 From 8d6c16dd7213fa43702416e3dd1059e9e36bc758 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 5 Dec 2015 16:23:26 +0000 Subject: iio:configfs: Introduce iio/configfs.h to provide a location for the configfs_subsystem This exported element needs to be accesible to all drivers using configfs within IIO. Previously it was in the sw_trig.h file which only convered one such usecase. This also fixes a sparse warning as it is now in a header that makes sense to include from industrialio-configfs.c Signed-off-by: Jonathan Cameron < jic23@kernel.org> --- drivers/iio/industrialio-configfs.c | 1 + drivers/iio/industrialio-sw-trigger.c | 1 + include/linux/iio/configfs.h | 15 +++++++++++++++ include/linux/iio/sw_trigger.h | 1 - 4 files changed, 17 insertions(+), 1 deletion(-) create mode 100644 include/linux/iio/configfs.h (limited to 'include/linux') diff --git a/drivers/iio/industrialio-configfs.c b/drivers/iio/industrialio-configfs.c index 83563dd7fcf4..45ce2bc47180 100644 --- a/drivers/iio/industrialio-configfs.c +++ b/drivers/iio/industrialio-configfs.c @@ -15,6 +15,7 @@ #include #include +#include static struct config_item_type iio_root_group_type = { .ct_owner = THIS_MODULE, diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c index 4825cfd9c4ea..311f9fe5aa34 100644 --- a/drivers/iio/industrialio-sw-trigger.c +++ b/drivers/iio/industrialio-sw-trigger.c @@ -15,6 +15,7 @@ #include #include +#include #include static struct config_group *iio_triggers_group; diff --git a/include/linux/iio/configfs.h b/include/linux/iio/configfs.h new file mode 100644 index 000000000000..93befd67c15c --- /dev/null +++ b/include/linux/iio/configfs.h @@ -0,0 +1,15 @@ +/* + * Industrial I/O configfs support + * + * Copyright (c) 2015 Intel Corporation + * + * 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 __IIO_CONFIGFS +#define __IIO_CONFIGFS + +extern struct configfs_subsystem iio_configfs_subsys; + +#endif /* __IIO_CONFIGFS */ diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h index c2f33b2b35a5..5198f8ed08a4 100644 --- a/include/linux/iio/sw_trigger.h +++ b/include/linux/iio/sw_trigger.h @@ -20,7 +20,6 @@ module_driver(__iio_sw_trigger_type, iio_register_sw_trigger_type, \ iio_unregister_sw_trigger_type) -extern struct configfs_subsystem iio_configfs_subsys; struct iio_sw_trigger_ops; struct iio_sw_trigger_type { -- cgit v1.2.3 From ed4f85c03cc7460a2f76afb73c22b8894b44ee20 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Tue, 1 Dec 2015 12:03:06 +0100 Subject: mtd: nand: embed an mtd_info structure into nand_chip Currently all NAND controller drivers are providing both the mtd_info and nand_chip struct and then let the NAND subsystem to initialize a few things before registering the mtd instance to the MTD layer. Embed an mtd_info field into nand_chip to add some consistency to all NAND controller drivers. This change will also help factorizing boilerplate code copied in all NAND drivers. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index fad634ea1685..d6710575ddb6 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -540,6 +540,7 @@ struct nand_buffers { /** * struct nand_chip - NAND Private Flash Chip Data + * @mtd: MTD device registered to the MTD framework * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the * flash device * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the @@ -640,6 +641,7 @@ struct nand_buffers { */ struct nand_chip { + struct mtd_info mtd; void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; -- cgit v1.2.3 From ffd014f43fdcb6edb5a7f302de1e717e8c0673d5 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Tue, 1 Dec 2015 12:03:07 +0100 Subject: mtd: nand: add nand_to_mtd() helper Add a new helper to retrieve the MTD device attached to a NAND chip. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index d6710575ddb6..b614ed2105ac 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -737,6 +737,11 @@ static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) return mtd->priv; } +static inline struct mtd_info *nand_to_mtd(struct nand_chip *chip) +{ + return &chip->mtd; +} + /* * NAND Flash Manufacturer ID Codes */ -- cgit v1.2.3 From b9adf469f8abb8a66f5795bbd8fe50fe201a14a1 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 4 Dec 2015 15:25:14 -0800 Subject: mtd: partitions: make parsers return 'const' partition arrays We only want to modify these arrays inside the parser "drivers", so the drivers should construct them however they like, then return them as immutable arrays. This will make other refactorings easier. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- drivers/mtd/afs.c | 2 +- drivers/mtd/ar7part.c | 2 +- drivers/mtd/bcm47xxpart.c | 2 +- drivers/mtd/bcm63xxpart.c | 2 +- drivers/mtd/cmdlinepart.c | 2 +- drivers/mtd/ofpart.c | 4 ++-- drivers/mtd/redboot.c | 2 +- include/linux/mtd/partitions.h | 2 +- 8 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/afs.c b/drivers/mtd/afs.c index e02dae3b739b..d61b7edfc938 100644 --- a/drivers/mtd/afs.c +++ b/drivers/mtd/afs.c @@ -162,7 +162,7 @@ afs_read_iis_v1(struct mtd_info *mtd, struct image_info_v1 *iis, u_int ptr) } static int parse_afs_partitions(struct mtd_info *mtd, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { struct mtd_partition *parts; diff --git a/drivers/mtd/ar7part.c b/drivers/mtd/ar7part.c index 9203b96fd789..90575deff0ae 100644 --- a/drivers/mtd/ar7part.c +++ b/drivers/mtd/ar7part.c @@ -43,7 +43,7 @@ struct ar7_bin_rec { }; static int create_mtd_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { struct ar7_bin_rec header; diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c index 92a6dd18198b..8282f47bcf5d 100644 --- a/drivers/mtd/bcm47xxpart.c +++ b/drivers/mtd/bcm47xxpart.c @@ -82,7 +82,7 @@ out_default: } static int bcm47xxpart_parse(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { struct mtd_partition *parts; diff --git a/drivers/mtd/bcm63xxpart.c b/drivers/mtd/bcm63xxpart.c index cf02135320bc..440936998593 100644 --- a/drivers/mtd/bcm63xxpart.c +++ b/drivers/mtd/bcm63xxpart.c @@ -68,7 +68,7 @@ static int bcm63xx_detect_cfe(struct mtd_info *master) } static int bcm63xx_parse_cfe_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { /* CFE, NVRAM and global Linux are always present */ diff --git a/drivers/mtd/cmdlinepart.c b/drivers/mtd/cmdlinepart.c index 420489864bc2..fbd5affc0acf 100644 --- a/drivers/mtd/cmdlinepart.c +++ b/drivers/mtd/cmdlinepart.c @@ -304,7 +304,7 @@ static int mtdpart_setup_real(char *s) * the first one in the chain if a NULL mtd_id is passed in. */ static int parse_cmdline_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { unsigned long long offset; diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c index c7df2f1dd6b8..ede407d6e106 100644 --- a/drivers/mtd/ofpart.c +++ b/drivers/mtd/ofpart.c @@ -26,7 +26,7 @@ static bool node_has_compatible(struct device_node *pp) } static int parse_ofpart_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { struct mtd_partition *parts; @@ -145,7 +145,7 @@ static struct mtd_part_parser ofpart_parser = { }; static int parse_ofoldpart_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { struct mtd_partition *parts; diff --git a/drivers/mtd/redboot.c b/drivers/mtd/redboot.c index 11c3447eb8ff..7623ac5fc586 100644 --- a/drivers/mtd/redboot.c +++ b/drivers/mtd/redboot.c @@ -57,7 +57,7 @@ static inline int redboot_checksum(struct fis_image_desc *img) } static int parse_redboot_partitions(struct mtd_info *master, - struct mtd_partition **pparts, + const struct mtd_partition **pparts, struct mtd_part_parser_data *data) { int nrparts = 0; diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index d002d9b5d797..6185536daacc 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -69,7 +69,7 @@ struct mtd_part_parser { struct list_head list; struct module *owner; const char *name; - int (*parse_fn)(struct mtd_info *, struct mtd_partition **, + int (*parse_fn)(struct mtd_info *, const struct mtd_partition **, struct mtd_part_parser_data *); }; -- cgit v1.2.3 From 07fd2f871c5e3dfb8ff5eb9c4b44fdb4cf1aeff5 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 4 Dec 2015 15:25:17 -0800 Subject: mtd: partitions: pass around 'mtd_partitions' wrapper struct For some of the core partitioning code, it helps to keep info about the parsed partition (and who parsed them) together in one place. Signed-off-by: Brian Norris --- drivers/mtd/mtdcore.c | 33 +++++++++++++++++++-------------- drivers/mtd/mtdcore.h | 5 ++++- drivers/mtd/mtdpart.c | 15 ++++++++------- include/linux/mtd/partitions.h | 7 +++++++ 4 files changed, 38 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 868ee52d5063..20b2b38247b6 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -532,9 +532,10 @@ out_error: } static int mtd_add_device_partitions(struct mtd_info *mtd, - const struct mtd_partition *real_parts, - int nbparts) + struct mtd_partitions *parts) { + const struct mtd_partition *real_parts = parts->parts; + int nbparts = parts->nr_parts; int ret; if (nbparts == 0 || IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) { @@ -588,23 +589,27 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, const struct mtd_partition *parts, int nr_parts) { + struct mtd_partitions parsed; int ret; - const struct mtd_partition *real_parts = NULL; - ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data); - if (ret <= 0 && nr_parts && parts) { - real_parts = parts; - ret = nr_parts; - } - /* Didn't come up with either parsed OR fallback partitions */ - if (ret < 0) { + memset(&parsed, 0, sizeof(parsed)); + + ret = parse_mtd_partitions(mtd, types, &parsed, parser_data); + if ((ret < 0 || parsed.nr_parts == 0) && parts && nr_parts) { + /* Fall back to driver-provided partitions */ + parsed = (struct mtd_partitions){ + .parts = parts, + .nr_parts = nr_parts, + }; + } else if (ret < 0) { + /* Didn't come up with parsed OR fallback partitions */ pr_info("mtd: failed to find partitions; one or more parsers reports errors (%d)\n", ret); /* Don't abort on errors; we can still use unpartitioned MTD */ - ret = 0; + memset(&parsed, 0, sizeof(parsed)); } - ret = mtd_add_device_partitions(mtd, real_parts, ret); + ret = mtd_add_device_partitions(mtd, &parsed); if (ret) goto out; @@ -625,8 +630,8 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, out: /* Cleanup any parsed partitions */ - if (real_parts != parts) - kfree(real_parts); + if (parsed.parser) + kfree(parsed.parts); return ret; } EXPORT_SYMBOL_GPL(mtd_device_parse_register); diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h index 537ec66f9cfd..ce81cc2002f4 100644 --- a/drivers/mtd/mtdcore.h +++ b/drivers/mtd/mtdcore.h @@ -10,8 +10,11 @@ int add_mtd_device(struct mtd_info *mtd); int del_mtd_device(struct mtd_info *mtd); int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int); int del_mtd_partitions(struct mtd_info *); + +struct mtd_partitions; + int parse_mtd_partitions(struct mtd_info *master, const char * const *types, - const struct mtd_partition **pparts, + struct mtd_partitions *pparts, struct mtd_part_parser_data *data); int __init init_mtdchar(void); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 898999c5aea1..53517d7653cb 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -743,7 +743,7 @@ static const char * const default_mtd_part_types[] = { * parse_mtd_partitions - parse MTD partitions * @master: the master partition (describes whole MTD device) * @types: names of partition parsers to try or %NULL - * @pparts: array of partitions found is returned here + * @pparts: info about partitions found is returned here * @data: MTD partition parser-specific data * * This function tries to find partition on MTD device @master. It uses MTD @@ -755,12 +755,11 @@ static const char * const default_mtd_part_types[] = { * * This function may return: * o a negative error code in case of failure - * o zero if no partitions were found - * o a positive number of found partitions, in which case on exit @pparts will - * point to an array containing this number of &struct mtd_info objects. + * o zero otherwise, and @pparts will describe the partitions, number of + * partitions, and the parser which parsed them */ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, - const struct mtd_partition **pparts, + struct mtd_partitions *pparts, struct mtd_part_parser_data *data) { struct mtd_part_parser *parser; @@ -778,14 +777,16 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, parser ? parser->name : NULL); if (!parser) continue; - ret = (*parser->parse_fn)(master, pparts, data); + ret = (*parser->parse_fn)(master, &pparts->parts, data); pr_debug("%s: parser %s: %i\n", master->name, parser->name, ret); mtd_part_parser_put(parser); if (ret > 0) { printk(KERN_NOTICE "%d %s partitions found on MTD device %s\n", ret, parser->name, master->name); - return ret; + pparts->nr_parts = ret; + pparts->parser = parser; + return 0; } /* * Stash the first error we see; only report it if no parser diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 6185536daacc..cceaf7bd1537 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -73,6 +73,13 @@ struct mtd_part_parser { struct mtd_part_parser_data *); }; +/* Container for passing around a set of parsed partitions */ +struct mtd_partitions { + const struct mtd_partition *parts; + int nr_parts; + const struct mtd_part_parser *parser; +}; + extern int __register_mtd_parser(struct mtd_part_parser *parser, struct module *owner); #define register_mtd_parser(parser) __register_mtd_parser(parser, THIS_MODULE) -- cgit v1.2.3 From adc83bf8896353603213754353dd66dae69e3d7f Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Wed, 9 Dec 2015 10:24:03 -0800 Subject: mtd: partitions: support a cleanup callback for parsers If partition parsers need to clean up their resources, we shouldn't assume that all memory will fit in a single kmalloc() that the caller can kfree(). We should allow the parser to provide a proper cleanup routine. Note that this means we need to keep a hold on the parser's module for a bit longer, and release it later with mtd_part_parser_put(). Alongside this, define a default callback that we'll automatically use if the parser doesn't provide one, so we can still retain the old behavior. Signed-off-by: Brian Norris Reviewed-by: Boris Brezillon --- drivers/mtd/mtdcore.c | 3 +-- drivers/mtd/mtdcore.h | 2 ++ drivers/mtd/mtdpart.c | 35 +++++++++++++++++++++++++++++++++-- include/linux/mtd/partitions.h | 1 + 4 files changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 20b2b38247b6..89d811e7b04a 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -630,8 +630,7 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, out: /* Cleanup any parsed partitions */ - if (parsed.parser) - kfree(parsed.parts); + mtd_part_parser_cleanup(&parsed); return ret; } EXPORT_SYMBOL_GPL(mtd_device_parse_register); diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h index ce81cc2002f4..55fdb8e1fd2a 100644 --- a/drivers/mtd/mtdcore.h +++ b/drivers/mtd/mtdcore.h @@ -17,6 +17,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char * const *types, struct mtd_partitions *pparts, struct mtd_part_parser_data *data); +void mtd_part_parser_cleanup(struct mtd_partitions *parts); + int __init init_mtdchar(void); void __exit cleanup_mtdchar(void); diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 53517d7653cb..10bf304027dd 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -709,10 +709,23 @@ static inline void mtd_part_parser_put(const struct mtd_part_parser *p) module_put(p->owner); } +/* + * Many partition parsers just expected the core to kfree() all their data in + * one chunk. Do that by default. + */ +static void mtd_part_parser_cleanup_default(const struct mtd_partition *pparts, + int nr_parts) +{ + kfree(pparts); +} + int __register_mtd_parser(struct mtd_part_parser *p, struct module *owner) { p->owner = owner; + if (!p->cleanup) + p->cleanup = &mtd_part_parser_cleanup_default; + spin_lock(&part_parser_lock); list_add(&p->list, &part_parsers); spin_unlock(&part_parser_lock); @@ -756,7 +769,9 @@ static const char * const default_mtd_part_types[] = { * This function may return: * o a negative error code in case of failure * o zero otherwise, and @pparts will describe the partitions, number of - * partitions, and the parser which parsed them + * partitions, and the parser which parsed them. Caller must release + * resources with mtd_part_parser_cleanup() when finished with the returned + * data. */ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, struct mtd_partitions *pparts, @@ -780,7 +795,6 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, ret = (*parser->parse_fn)(master, &pparts->parts, data); pr_debug("%s: parser %s: %i\n", master->name, parser->name, ret); - mtd_part_parser_put(parser); if (ret > 0) { printk(KERN_NOTICE "%d %s partitions found on MTD device %s\n", ret, parser->name, master->name); @@ -788,6 +802,7 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, pparts->parser = parser; return 0; } + mtd_part_parser_put(parser); /* * Stash the first error we see; only report it if no parser * succeeds @@ -798,6 +813,22 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types, return err; } +void mtd_part_parser_cleanup(struct mtd_partitions *parts) +{ + const struct mtd_part_parser *parser; + + if (!parts) + return; + + parser = parts->parser; + if (parser) { + if (parser->cleanup) + parser->cleanup(parts->parts, parts->nr_parts); + + mtd_part_parser_put(parser); + } +} + int mtd_is_partition(const struct mtd_info *mtd) { struct mtd_part *part; diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index cceaf7bd1537..70736e1e6c8f 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -71,6 +71,7 @@ struct mtd_part_parser { const char *name; int (*parse_fn)(struct mtd_info *, const struct mtd_partition **, struct mtd_part_parser_data *); + void (*cleanup)(const struct mtd_partition *pparts, int nr_parts); }; /* Container for passing around a set of parsed partitions */ -- cgit v1.2.3 From 4d42e95fc789393d267bbab8b4684936c1529378 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 4 Dec 2015 16:56:29 +0100 Subject: dmaengine: sh: Remove unused R-Car HPB-DMAC driver As of commit 4baadb9e05c68962 ("ARM: shmobile: r8a7778: remove obsolete setup code"), the Renesas R-Car HPB-DMAC driver is no longer used. In theory it could still be used on R-Car Gen1 SoCs, but that requires adding DT support to the driver, which is not planned. Remove the driver, it can be resurrected from git history when needed. Signed-off-by: Geert Uytterhoeven Acked-by: Simon Horman Signed-off-by: Vinod Koul --- drivers/dma/sh/Kconfig | 6 - drivers/dma/sh/Makefile | 1 - drivers/dma/sh/rcar-hpbdma.c | 669 -------------------------- include/linux/platform_data/dma-rcar-hpbdma.h | 103 ---- 4 files changed, 779 deletions(-) delete mode 100644 drivers/dma/sh/rcar-hpbdma.c delete mode 100644 include/linux/platform_data/dma-rcar-hpbdma.h (limited to 'include/linux') diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig index 9fda65af841e..f32c430eb16c 100644 --- a/drivers/dma/sh/Kconfig +++ b/drivers/dma/sh/Kconfig @@ -47,12 +47,6 @@ config RCAR_DMAC This driver supports the general purpose DMA controller found in the Renesas R-Car second generation SoCs. -config RCAR_HPB_DMAE - tristate "Renesas R-Car HPB DMAC support" - depends on SH_DMAE_BASE - help - Enable support for the Renesas R-Car series DMA controllers. - config RENESAS_USB_DMAC tristate "Renesas USB-DMA Controller" depends on ARCH_SHMOBILE || COMPILE_TEST diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile index 0133e4658196..f1e2fd64f279 100644 --- a/drivers/dma/sh/Makefile +++ b/drivers/dma/sh/Makefile @@ -14,6 +14,5 @@ shdma-objs := $(shdma-y) obj-$(CONFIG_SH_DMAE) += shdma.o obj-$(CONFIG_RCAR_DMAC) += rcar-dmac.o -obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o obj-$(CONFIG_RENESAS_USB_DMAC) += usb-dmac.o obj-$(CONFIG_SUDMAC) += sudmac.o diff --git a/drivers/dma/sh/rcar-hpbdma.c b/drivers/dma/sh/rcar-hpbdma.c deleted file mode 100644 index 749f26ecd3b3..000000000000 --- a/drivers/dma/sh/rcar-hpbdma.c +++ /dev/null @@ -1,669 +0,0 @@ -/* - * Copyright (C) 2011-2013 Renesas Electronics Corporation - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * This file is based on the drivers/dma/sh/shdma.c - * - * Renesas SuperH DMA Engine support - * - * This 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. - * - * - DMA of SuperH does not have Hardware DMA chain mode. - * - max DMA size is 16MB. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* DMA channel registers */ -#define HPB_DMAE_DSAR0 0x00 -#define HPB_DMAE_DDAR0 0x04 -#define HPB_DMAE_DTCR0 0x08 -#define HPB_DMAE_DSAR1 0x0C -#define HPB_DMAE_DDAR1 0x10 -#define HPB_DMAE_DTCR1 0x14 -#define HPB_DMAE_DSASR 0x18 -#define HPB_DMAE_DDASR 0x1C -#define HPB_DMAE_DTCSR 0x20 -#define HPB_DMAE_DPTR 0x24 -#define HPB_DMAE_DCR 0x28 -#define HPB_DMAE_DCMDR 0x2C -#define HPB_DMAE_DSTPR 0x30 -#define HPB_DMAE_DSTSR 0x34 -#define HPB_DMAE_DDBGR 0x38 -#define HPB_DMAE_DDBGR2 0x3C -#define HPB_DMAE_CHAN(n) (0x40 * (n)) - -/* DMA command register (DCMDR) bits */ -#define HPB_DMAE_DCMDR_BDOUT BIT(7) -#define HPB_DMAE_DCMDR_DQSPD BIT(6) -#define HPB_DMAE_DCMDR_DQSPC BIT(5) -#define HPB_DMAE_DCMDR_DMSPD BIT(4) -#define HPB_DMAE_DCMDR_DMSPC BIT(3) -#define HPB_DMAE_DCMDR_DQEND BIT(2) -#define HPB_DMAE_DCMDR_DNXT BIT(1) -#define HPB_DMAE_DCMDR_DMEN BIT(0) - -/* DMA forced stop register (DSTPR) bits */ -#define HPB_DMAE_DSTPR_DMSTP BIT(0) - -/* DMA status register (DSTSR) bits */ -#define HPB_DMAE_DSTSR_DQSTS BIT(2) -#define HPB_DMAE_DSTSR_DMSTS BIT(0) - -/* DMA common registers */ -#define HPB_DMAE_DTIMR 0x00 -#define HPB_DMAE_DINTSR0 0x0C -#define HPB_DMAE_DINTSR1 0x10 -#define HPB_DMAE_DINTCR0 0x14 -#define HPB_DMAE_DINTCR1 0x18 -#define HPB_DMAE_DINTMR0 0x1C -#define HPB_DMAE_DINTMR1 0x20 -#define HPB_DMAE_DACTSR0 0x24 -#define HPB_DMAE_DACTSR1 0x28 -#define HPB_DMAE_HSRSTR(n) (0x40 + (n) * 4) -#define HPB_DMAE_HPB_DMASPR(n) (0x140 + (n) * 4) -#define HPB_DMAE_HPB_DMLVLR0 0x160 -#define HPB_DMAE_HPB_DMLVLR1 0x164 -#define HPB_DMAE_HPB_DMSHPT0 0x168 -#define HPB_DMAE_HPB_DMSHPT1 0x16C - -#define HPB_DMA_SLAVE_NUMBER 256 -#define HPB_DMA_TCR_MAX 0x01000000 /* 16 MiB */ - -struct hpb_dmae_chan { - struct shdma_chan shdma_chan; - int xfer_mode; /* DMA transfer mode */ -#define XFER_SINGLE 1 -#define XFER_DOUBLE 2 - unsigned plane_idx; /* current DMA information set */ - bool first_desc; /* first/next transfer */ - int xmit_shift; /* log_2(bytes_per_xfer) */ - void __iomem *base; - const struct hpb_dmae_slave_config *cfg; - char dev_id[16]; /* unique name per DMAC of channel */ - dma_addr_t slave_addr; -}; - -struct hpb_dmae_device { - struct shdma_dev shdma_dev; - spinlock_t reg_lock; /* comm_reg operation lock */ - struct hpb_dmae_pdata *pdata; - void __iomem *chan_reg; - void __iomem *comm_reg; - void __iomem *reset_reg; - void __iomem *mode_reg; -}; - -struct hpb_dmae_regs { - u32 sar; /* SAR / source address */ - u32 dar; /* DAR / destination address */ - u32 tcr; /* TCR / transfer count */ -}; - -struct hpb_desc { - struct shdma_desc shdma_desc; - struct hpb_dmae_regs hw; - unsigned plane_idx; -}; - -#define to_chan(schan) container_of(schan, struct hpb_dmae_chan, shdma_chan) -#define to_desc(sdesc) container_of(sdesc, struct hpb_desc, shdma_desc) -#define to_dev(sc) container_of(sc->shdma_chan.dma_chan.device, \ - struct hpb_dmae_device, shdma_dev.dma_dev) - -static void ch_reg_write(struct hpb_dmae_chan *hpb_dc, u32 data, u32 reg) -{ - iowrite32(data, hpb_dc->base + reg); -} - -static u32 ch_reg_read(struct hpb_dmae_chan *hpb_dc, u32 reg) -{ - return ioread32(hpb_dc->base + reg); -} - -static void dcmdr_write(struct hpb_dmae_device *hpbdev, u32 data) -{ - iowrite32(data, hpbdev->chan_reg + HPB_DMAE_DCMDR); -} - -static void hsrstr_write(struct hpb_dmae_device *hpbdev, u32 ch) -{ - iowrite32(0x1, hpbdev->comm_reg + HPB_DMAE_HSRSTR(ch)); -} - -static u32 dintsr_read(struct hpb_dmae_device *hpbdev, u32 ch) -{ - u32 v; - - if (ch < 32) - v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR0) >> ch; - else - v = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTSR1) >> (ch - 32); - return v & 0x1; -} - -static void dintcr_write(struct hpb_dmae_device *hpbdev, u32 ch) -{ - if (ch < 32) - iowrite32((0x1 << ch), hpbdev->comm_reg + HPB_DMAE_DINTCR0); - else - iowrite32((0x1 << (ch - 32)), - hpbdev->comm_reg + HPB_DMAE_DINTCR1); -} - -static void asyncmdr_write(struct hpb_dmae_device *hpbdev, u32 data) -{ - iowrite32(data, hpbdev->mode_reg); -} - -static u32 asyncmdr_read(struct hpb_dmae_device *hpbdev) -{ - return ioread32(hpbdev->mode_reg); -} - -static void hpb_dmae_enable_int(struct hpb_dmae_device *hpbdev, u32 ch) -{ - u32 intreg; - - spin_lock_irq(&hpbdev->reg_lock); - if (ch < 32) { - intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR0); - iowrite32(BIT(ch) | intreg, - hpbdev->comm_reg + HPB_DMAE_DINTMR0); - } else { - intreg = ioread32(hpbdev->comm_reg + HPB_DMAE_DINTMR1); - iowrite32(BIT(ch - 32) | intreg, - hpbdev->comm_reg + HPB_DMAE_DINTMR1); - } - spin_unlock_irq(&hpbdev->reg_lock); -} - -static void hpb_dmae_async_reset(struct hpb_dmae_device *hpbdev, u32 data) -{ - u32 rstr; - int timeout = 10000; /* 100 ms */ - - spin_lock(&hpbdev->reg_lock); - rstr = ioread32(hpbdev->reset_reg); - rstr |= data; - iowrite32(rstr, hpbdev->reset_reg); - do { - rstr = ioread32(hpbdev->reset_reg); - if ((rstr & data) == data) - break; - udelay(10); - } while (timeout--); - - if (timeout < 0) - dev_err(hpbdev->shdma_dev.dma_dev.dev, - "%s timeout\n", __func__); - - rstr &= ~data; - iowrite32(rstr, hpbdev->reset_reg); - spin_unlock(&hpbdev->reg_lock); -} - -static void hpb_dmae_set_async_mode(struct hpb_dmae_device *hpbdev, - u32 mask, u32 data) -{ - u32 mode; - - spin_lock_irq(&hpbdev->reg_lock); - mode = asyncmdr_read(hpbdev); - mode &= ~mask; - mode |= data; - asyncmdr_write(hpbdev, mode); - spin_unlock_irq(&hpbdev->reg_lock); -} - -static void hpb_dmae_ctl_stop(struct hpb_dmae_device *hpbdev) -{ - dcmdr_write(hpbdev, HPB_DMAE_DCMDR_DQSPD); -} - -static void hpb_dmae_reset(struct hpb_dmae_device *hpbdev) -{ - u32 ch; - - for (ch = 0; ch < hpbdev->pdata->num_hw_channels; ch++) - hsrstr_write(hpbdev, ch); -} - -static unsigned int calc_xmit_shift(struct hpb_dmae_chan *hpb_chan) -{ - struct hpb_dmae_device *hpbdev = to_dev(hpb_chan); - struct hpb_dmae_pdata *pdata = hpbdev->pdata; - int width = ch_reg_read(hpb_chan, HPB_DMAE_DCR); - int i; - - switch (width & (HPB_DMAE_DCR_SPDS_MASK | HPB_DMAE_DCR_DPDS_MASK)) { - case HPB_DMAE_DCR_SPDS_8BIT | HPB_DMAE_DCR_DPDS_8BIT: - default: - i = XMIT_SZ_8BIT; - break; - case HPB_DMAE_DCR_SPDS_16BIT | HPB_DMAE_DCR_DPDS_16BIT: - i = XMIT_SZ_16BIT; - break; - case HPB_DMAE_DCR_SPDS_32BIT | HPB_DMAE_DCR_DPDS_32BIT: - i = XMIT_SZ_32BIT; - break; - } - return pdata->ts_shift[i]; -} - -static void hpb_dmae_set_reg(struct hpb_dmae_chan *hpb_chan, - struct hpb_dmae_regs *hw, unsigned plane) -{ - ch_reg_write(hpb_chan, hw->sar, - plane ? HPB_DMAE_DSAR1 : HPB_DMAE_DSAR0); - ch_reg_write(hpb_chan, hw->dar, - plane ? HPB_DMAE_DDAR1 : HPB_DMAE_DDAR0); - ch_reg_write(hpb_chan, hw->tcr >> hpb_chan->xmit_shift, - plane ? HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0); -} - -static void hpb_dmae_start(struct hpb_dmae_chan *hpb_chan, bool next) -{ - ch_reg_write(hpb_chan, (next ? HPB_DMAE_DCMDR_DNXT : 0) | - HPB_DMAE_DCMDR_DMEN, HPB_DMAE_DCMDR); -} - -static void hpb_dmae_halt(struct shdma_chan *schan) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - - ch_reg_write(chan, HPB_DMAE_DCMDR_DQEND, HPB_DMAE_DCMDR); - ch_reg_write(chan, HPB_DMAE_DSTPR_DMSTP, HPB_DMAE_DSTPR); - - chan->plane_idx = 0; - chan->first_desc = true; -} - -static const struct hpb_dmae_slave_config * -hpb_dmae_find_slave(struct hpb_dmae_chan *hpb_chan, int slave_id) -{ - struct hpb_dmae_device *hpbdev = to_dev(hpb_chan); - struct hpb_dmae_pdata *pdata = hpbdev->pdata; - int i; - - if (slave_id >= HPB_DMA_SLAVE_NUMBER) - return NULL; - - for (i = 0; i < pdata->num_slaves; i++) - if (pdata->slaves[i].id == slave_id) - return pdata->slaves + i; - - return NULL; -} - -static void hpb_dmae_start_xfer(struct shdma_chan *schan, - struct shdma_desc *sdesc) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - struct hpb_dmae_device *hpbdev = to_dev(chan); - struct hpb_desc *desc = to_desc(sdesc); - - if (chan->cfg->flags & HPB_DMAE_SET_ASYNC_RESET) - hpb_dmae_async_reset(hpbdev, chan->cfg->rstr); - - desc->plane_idx = chan->plane_idx; - hpb_dmae_set_reg(chan, &desc->hw, chan->plane_idx); - hpb_dmae_start(chan, !chan->first_desc); - - if (chan->xfer_mode == XFER_DOUBLE) { - chan->plane_idx ^= 1; - chan->first_desc = false; - } -} - -static bool hpb_dmae_desc_completed(struct shdma_chan *schan, - struct shdma_desc *sdesc) -{ - /* - * This is correct since we always have at most single - * outstanding DMA transfer per channel, and by the time - * we get completion interrupt the transfer is completed. - * This will change if we ever use alternating DMA - * information sets and submit two descriptors at once. - */ - return true; -} - -static bool hpb_dmae_chan_irq(struct shdma_chan *schan, int irq) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - struct hpb_dmae_device *hpbdev = to_dev(chan); - int ch = chan->cfg->dma_ch; - - /* Check Complete DMA Transfer */ - if (dintsr_read(hpbdev, ch)) { - /* Clear Interrupt status */ - dintcr_write(hpbdev, ch); - return true; - } - return false; -} - -static int hpb_dmae_desc_setup(struct shdma_chan *schan, - struct shdma_desc *sdesc, - dma_addr_t src, dma_addr_t dst, size_t *len) -{ - struct hpb_desc *desc = to_desc(sdesc); - - if (*len > (size_t)HPB_DMA_TCR_MAX) - *len = (size_t)HPB_DMA_TCR_MAX; - - desc->hw.sar = src; - desc->hw.dar = dst; - desc->hw.tcr = *len; - - return 0; -} - -static size_t hpb_dmae_get_partial(struct shdma_chan *schan, - struct shdma_desc *sdesc) -{ - struct hpb_desc *desc = to_desc(sdesc); - struct hpb_dmae_chan *chan = to_chan(schan); - u32 tcr = ch_reg_read(chan, desc->plane_idx ? - HPB_DMAE_DTCR1 : HPB_DMAE_DTCR0); - - return (desc->hw.tcr - tcr) << chan->xmit_shift; -} - -static bool hpb_dmae_channel_busy(struct shdma_chan *schan) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - u32 dstsr = ch_reg_read(chan, HPB_DMAE_DSTSR); - - if (chan->xfer_mode == XFER_DOUBLE) - return dstsr & HPB_DMAE_DSTSR_DQSTS; - else - return dstsr & HPB_DMAE_DSTSR_DMSTS; -} - -static int -hpb_dmae_alloc_chan_resources(struct hpb_dmae_chan *hpb_chan, - const struct hpb_dmae_slave_config *cfg) -{ - struct hpb_dmae_device *hpbdev = to_dev(hpb_chan); - struct hpb_dmae_pdata *pdata = hpbdev->pdata; - const struct hpb_dmae_channel *channel = pdata->channels; - int slave_id = cfg->id; - int i, err; - - for (i = 0; i < pdata->num_channels; i++, channel++) { - if (channel->s_id == slave_id) { - struct device *dev = hpb_chan->shdma_chan.dev; - - hpb_chan->base = hpbdev->chan_reg + - HPB_DMAE_CHAN(cfg->dma_ch); - - dev_dbg(dev, "Detected Slave device\n"); - dev_dbg(dev, " -- slave_id : 0x%x\n", slave_id); - dev_dbg(dev, " -- cfg->dma_ch : %d\n", cfg->dma_ch); - dev_dbg(dev, " -- channel->ch_irq: %d\n", - channel->ch_irq); - break; - } - } - - err = shdma_request_irq(&hpb_chan->shdma_chan, channel->ch_irq, - IRQF_SHARED, hpb_chan->dev_id); - if (err) { - dev_err(hpb_chan->shdma_chan.dev, - "DMA channel request_irq %d failed with error %d\n", - channel->ch_irq, err); - return err; - } - - hpb_chan->plane_idx = 0; - hpb_chan->first_desc = true; - - if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) == 0) { - hpb_chan->xfer_mode = XFER_SINGLE; - } else if ((cfg->dcr & (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) == - (HPB_DMAE_DCR_CT | HPB_DMAE_DCR_DIP)) { - hpb_chan->xfer_mode = XFER_DOUBLE; - } else { - dev_err(hpb_chan->shdma_chan.dev, "DCR setting error"); - return -EINVAL; - } - - if (cfg->flags & HPB_DMAE_SET_ASYNC_MODE) - hpb_dmae_set_async_mode(hpbdev, cfg->mdm, cfg->mdr); - ch_reg_write(hpb_chan, cfg->dcr, HPB_DMAE_DCR); - ch_reg_write(hpb_chan, cfg->port, HPB_DMAE_DPTR); - hpb_chan->xmit_shift = calc_xmit_shift(hpb_chan); - hpb_dmae_enable_int(hpbdev, cfg->dma_ch); - - return 0; -} - -static int hpb_dmae_set_slave(struct shdma_chan *schan, int slave_id, - dma_addr_t slave_addr, bool try) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - const struct hpb_dmae_slave_config *sc = - hpb_dmae_find_slave(chan, slave_id); - - if (!sc) - return -ENODEV; - if (try) - return 0; - chan->cfg = sc; - chan->slave_addr = slave_addr ? : sc->addr; - return hpb_dmae_alloc_chan_resources(chan, sc); -} - -static void hpb_dmae_setup_xfer(struct shdma_chan *schan, int slave_id) -{ -} - -static dma_addr_t hpb_dmae_slave_addr(struct shdma_chan *schan) -{ - struct hpb_dmae_chan *chan = to_chan(schan); - - return chan->slave_addr; -} - -static struct shdma_desc *hpb_dmae_embedded_desc(void *buf, int i) -{ - return &((struct hpb_desc *)buf)[i].shdma_desc; -} - -static const struct shdma_ops hpb_dmae_ops = { - .desc_completed = hpb_dmae_desc_completed, - .halt_channel = hpb_dmae_halt, - .channel_busy = hpb_dmae_channel_busy, - .slave_addr = hpb_dmae_slave_addr, - .desc_setup = hpb_dmae_desc_setup, - .set_slave = hpb_dmae_set_slave, - .setup_xfer = hpb_dmae_setup_xfer, - .start_xfer = hpb_dmae_start_xfer, - .embedded_desc = hpb_dmae_embedded_desc, - .chan_irq = hpb_dmae_chan_irq, - .get_partial = hpb_dmae_get_partial, -}; - -static int hpb_dmae_chan_probe(struct hpb_dmae_device *hpbdev, int id) -{ - struct shdma_dev *sdev = &hpbdev->shdma_dev; - struct platform_device *pdev = - to_platform_device(hpbdev->shdma_dev.dma_dev.dev); - struct hpb_dmae_chan *new_hpb_chan; - struct shdma_chan *schan; - - /* Alloc channel */ - new_hpb_chan = devm_kzalloc(&pdev->dev, - sizeof(struct hpb_dmae_chan), GFP_KERNEL); - if (!new_hpb_chan) { - dev_err(hpbdev->shdma_dev.dma_dev.dev, - "No free memory for allocating DMA channels!\n"); - return -ENOMEM; - } - - schan = &new_hpb_chan->shdma_chan; - schan->max_xfer_len = HPB_DMA_TCR_MAX; - - shdma_chan_probe(sdev, schan, id); - - if (pdev->id >= 0) - snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id), - "hpb-dmae%d.%d", pdev->id, id); - else - snprintf(new_hpb_chan->dev_id, sizeof(new_hpb_chan->dev_id), - "hpb-dma.%d", id); - - return 0; -} - -static int hpb_dmae_probe(struct platform_device *pdev) -{ - const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE | - DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES; - struct hpb_dmae_pdata *pdata = pdev->dev.platform_data; - struct hpb_dmae_device *hpbdev; - struct dma_device *dma_dev; - struct resource *chan, *comm, *rest, *mode, *irq_res; - int err, i; - - /* Get platform data */ - if (!pdata || !pdata->num_channels) - return -ENODEV; - - chan = platform_get_resource(pdev, IORESOURCE_MEM, 0); - comm = platform_get_resource(pdev, IORESOURCE_MEM, 1); - rest = platform_get_resource(pdev, IORESOURCE_MEM, 2); - mode = platform_get_resource(pdev, IORESOURCE_MEM, 3); - - irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!irq_res) - return -ENODEV; - - hpbdev = devm_kzalloc(&pdev->dev, sizeof(struct hpb_dmae_device), - GFP_KERNEL); - if (!hpbdev) { - dev_err(&pdev->dev, "Not enough memory\n"); - return -ENOMEM; - } - - hpbdev->chan_reg = devm_ioremap_resource(&pdev->dev, chan); - if (IS_ERR(hpbdev->chan_reg)) - return PTR_ERR(hpbdev->chan_reg); - - hpbdev->comm_reg = devm_ioremap_resource(&pdev->dev, comm); - if (IS_ERR(hpbdev->comm_reg)) - return PTR_ERR(hpbdev->comm_reg); - - hpbdev->reset_reg = devm_ioremap_resource(&pdev->dev, rest); - if (IS_ERR(hpbdev->reset_reg)) - return PTR_ERR(hpbdev->reset_reg); - - hpbdev->mode_reg = devm_ioremap_resource(&pdev->dev, mode); - if (IS_ERR(hpbdev->mode_reg)) - return PTR_ERR(hpbdev->mode_reg); - - dma_dev = &hpbdev->shdma_dev.dma_dev; - - spin_lock_init(&hpbdev->reg_lock); - - /* Platform data */ - hpbdev->pdata = pdata; - - pm_runtime_enable(&pdev->dev); - err = pm_runtime_get_sync(&pdev->dev); - if (err < 0) - dev_err(&pdev->dev, "%s(): GET = %d\n", __func__, err); - - /* Reset DMA controller */ - hpb_dmae_reset(hpbdev); - - pm_runtime_put(&pdev->dev); - - dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); - dma_cap_set(DMA_SLAVE, dma_dev->cap_mask); - dma_dev->src_addr_widths = widths; - dma_dev->dst_addr_widths = widths; - dma_dev->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); - dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; - - hpbdev->shdma_dev.ops = &hpb_dmae_ops; - hpbdev->shdma_dev.desc_size = sizeof(struct hpb_desc); - err = shdma_init(&pdev->dev, &hpbdev->shdma_dev, pdata->num_channels); - if (err < 0) - goto error; - - /* Create DMA channels */ - for (i = 0; i < pdata->num_channels; i++) - hpb_dmae_chan_probe(hpbdev, i); - - platform_set_drvdata(pdev, hpbdev); - err = dma_async_device_register(dma_dev); - if (!err) - return 0; - - shdma_cleanup(&hpbdev->shdma_dev); -error: - pm_runtime_disable(&pdev->dev); - return err; -} - -static void hpb_dmae_chan_remove(struct hpb_dmae_device *hpbdev) -{ - struct shdma_chan *schan; - int i; - - shdma_for_each_chan(schan, &hpbdev->shdma_dev, i) { - BUG_ON(!schan); - - shdma_chan_remove(schan); - } -} - -static int hpb_dmae_remove(struct platform_device *pdev) -{ - struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev); - - dma_async_device_unregister(&hpbdev->shdma_dev.dma_dev); - - pm_runtime_disable(&pdev->dev); - - hpb_dmae_chan_remove(hpbdev); - - return 0; -} - -static void hpb_dmae_shutdown(struct platform_device *pdev) -{ - struct hpb_dmae_device *hpbdev = platform_get_drvdata(pdev); - hpb_dmae_ctl_stop(hpbdev); -} - -static struct platform_driver hpb_dmae_driver = { - .probe = hpb_dmae_probe, - .remove = hpb_dmae_remove, - .shutdown = hpb_dmae_shutdown, - .driver = { - .name = "hpb-dma-engine", - }, -}; -module_platform_driver(hpb_dmae_driver); - -MODULE_AUTHOR("Max Filippov "); -MODULE_DESCRIPTION("Renesas HPB DMA Engine driver"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/dma-rcar-hpbdma.h b/include/linux/platform_data/dma-rcar-hpbdma.h deleted file mode 100644 index 648b8ea61a22..000000000000 --- a/include/linux/platform_data/dma-rcar-hpbdma.h +++ /dev/null @@ -1,103 +0,0 @@ -/* - * Copyright (C) 2011-2013 Renesas Electronics Corporation - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * 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 __DMA_RCAR_HPBDMA_H -#define __DMA_RCAR_HPBDMA_H - -#include -#include - -/* Transmit sizes and respective register values */ -enum { - XMIT_SZ_8BIT = 0, - XMIT_SZ_16BIT = 1, - XMIT_SZ_32BIT = 2, - XMIT_SZ_MAX -}; - -/* DMA control register (DCR) bits */ -#define HPB_DMAE_DCR_DTAMD (1u << 26) -#define HPB_DMAE_DCR_DTAC (1u << 25) -#define HPB_DMAE_DCR_DTAU (1u << 24) -#define HPB_DMAE_DCR_DTAU1 (1u << 23) -#define HPB_DMAE_DCR_SWMD (1u << 22) -#define HPB_DMAE_DCR_BTMD (1u << 21) -#define HPB_DMAE_DCR_PKMD (1u << 20) -#define HPB_DMAE_DCR_CT (1u << 18) -#define HPB_DMAE_DCR_ACMD (1u << 17) -#define HPB_DMAE_DCR_DIP (1u << 16) -#define HPB_DMAE_DCR_SMDL (1u << 13) -#define HPB_DMAE_DCR_SPDAM (1u << 12) -#define HPB_DMAE_DCR_SDRMD_MASK (3u << 10) -#define HPB_DMAE_DCR_SDRMD_MOD (0u << 10) -#define HPB_DMAE_DCR_SDRMD_AUTO (1u << 10) -#define HPB_DMAE_DCR_SDRMD_TIMER (2u << 10) -#define HPB_DMAE_DCR_SPDS_MASK (3u << 8) -#define HPB_DMAE_DCR_SPDS_8BIT (0u << 8) -#define HPB_DMAE_DCR_SPDS_16BIT (1u << 8) -#define HPB_DMAE_DCR_SPDS_32BIT (2u << 8) -#define HPB_DMAE_DCR_DMDL (1u << 5) -#define HPB_DMAE_DCR_DPDAM (1u << 4) -#define HPB_DMAE_DCR_DDRMD_MASK (3u << 2) -#define HPB_DMAE_DCR_DDRMD_MOD (0u << 2) -#define HPB_DMAE_DCR_DDRMD_AUTO (1u << 2) -#define HPB_DMAE_DCR_DDRMD_TIMER (2u << 2) -#define HPB_DMAE_DCR_DPDS_MASK (3u << 0) -#define HPB_DMAE_DCR_DPDS_8BIT (0u << 0) -#define HPB_DMAE_DCR_DPDS_16BIT (1u << 0) -#define HPB_DMAE_DCR_DPDS_32BIT (2u << 0) - -/* Asynchronous reset register (ASYNCRSTR) bits */ -#define HPB_DMAE_ASYNCRSTR_ASRST41 BIT(10) -#define HPB_DMAE_ASYNCRSTR_ASRST40 BIT(9) -#define HPB_DMAE_ASYNCRSTR_ASRST39 BIT(8) -#define HPB_DMAE_ASYNCRSTR_ASRST27 BIT(7) -#define HPB_DMAE_ASYNCRSTR_ASRST26 BIT(6) -#define HPB_DMAE_ASYNCRSTR_ASRST25 BIT(5) -#define HPB_DMAE_ASYNCRSTR_ASRST24 BIT(4) -#define HPB_DMAE_ASYNCRSTR_ASRST23 BIT(3) -#define HPB_DMAE_ASYNCRSTR_ASRST22 BIT(2) -#define HPB_DMAE_ASYNCRSTR_ASRST21 BIT(1) -#define HPB_DMAE_ASYNCRSTR_ASRST20 BIT(0) - -struct hpb_dmae_slave_config { - unsigned int id; - dma_addr_t addr; - u32 dcr; - u32 port; - u32 rstr; - u32 mdr; - u32 mdm; - u32 flags; -#define HPB_DMAE_SET_ASYNC_RESET BIT(0) -#define HPB_DMAE_SET_ASYNC_MODE BIT(1) - u32 dma_ch; -}; - -#define HPB_DMAE_CHANNEL(_irq, _s_id) \ -{ \ - .ch_irq = _irq, \ - .s_id = _s_id, \ -} - -struct hpb_dmae_channel { - unsigned int ch_irq; - unsigned int s_id; -}; - -struct hpb_dmae_pdata { - const struct hpb_dmae_slave_config *slaves; - int num_slaves; - const struct hpb_dmae_channel *channels; - int num_channels; - const unsigned int ts_shift[XMIT_SZ_MAX]; - int num_hw_channels; -}; - -#endif -- cgit v1.2.3 From 49ddedf3bfcb59a562c7db0e50aecd1422e9cdc9 Mon Sep 17 00:00:00 2001 From: Martin Sperl Date: Fri, 27 Nov 2015 13:56:03 +0000 Subject: spi: add spi_message_init_no_memset to avoid zeroing the spi_message In the spi_loopback_test driver there is the need to initialize a spi_message that is filled with values from a static structure. Applying spi_message_init to such a prefilled structure results in all the settings getting reset to zero, which is not what we want. Copying each field of spi_message separately instead always includes the risk that some new fields have not been implemented in the copying code. So here we introduce a version of spi_message_init called spi_message_init_no_memset that does not fill the structure with zero first, but only initializes the relevant list_heads. Signed-off-by: Martin Sperl Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cce80e6dc7d1..4c54d4744107 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -762,10 +762,15 @@ struct spi_message { void *state; }; +static inline void spi_message_init_no_memset(struct spi_message *m) +{ + INIT_LIST_HEAD(&m->transfers); +} + static inline void spi_message_init(struct spi_message *m) { memset(m, 0, sizeof *m); - INIT_LIST_HEAD(&m->transfers); + spi_message_init_no_memset(m); } static inline void -- cgit v1.2.3 From bd94c4077a0b2ecc35562c294f80f3659ecd8499 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 28 Oct 2015 12:46:05 +0900 Subject: serial: support 16-bit register interface for console Currently, 8-bit (MMIO) and 32-bit (MMIO32) register interfaces are supported for the 8250 console, but the 16-bit (MMIO16) is not. The 8250 UART device on my board is connected to a 16-bit bus and my main motivation is to use earlycon with it. (Refer to arch/arm/boot/dts/uniphier-support-card.dtsi) Signed-off-by: Masahiro Yamada Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 9 +++++---- drivers/tty/serial/8250/8250_core.c | 7 ++++--- drivers/tty/serial/8250/8250_early.c | 5 +++++ drivers/tty/serial/8250/8250_port.c | 20 ++++++++++++++++++++ drivers/tty/serial/earlycon.c | 15 +++++++++++---- drivers/tty/serial/of_serial.c | 3 +++ drivers/tty/serial/serial_core.c | 9 +++++++-- include/linux/serial_core.h | 1 + include/uapi/linux/serial.h | 1 + 9 files changed, 57 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 742f69d18fc8..054e11d33b6b 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -721,16 +721,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted. uart[8250],io,[,options] uart[8250],mmio,[,options] + uart[8250],mmio16,[,options] uart[8250],mmio32,[,options] uart[8250],0x[,options] Start an early, polled-mode console on the 8250/16550 UART at the specified I/O port or MMIO address, switching to the matching ttyS device later. MMIO inter-register address stride is either 8-bit - (mmio) or 32-bit (mmio32). - If none of [io|mmio|mmio32], is assumed to be - equivalent to 'mmio'. 'options' are specified in the - same format described for ttyS above; if unspecified, + (mmio), 16-bit (mmio16), or 32-bit (mmio32). + If none of [io|mmio|mmio16|mmio32], is assumed + to be equivalent to 'mmio'. 'options' are specified in + the same format described for ttyS above; if unspecified, the h/w is not re-initialized. hvc Use the hypervisor console device . This is for diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 39126460c1f5..c9720a97a977 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -620,7 +620,7 @@ static int univ8250_console_setup(struct console *co, char *options) * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: - * console=uart[8250],io|mmio|mmio32,[,] + * console=uart[8250],io|mmio|mmio16|mmio32,[,] * console=uart[8250],0x[,] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. @@ -650,8 +650,9 @@ static int univ8250_console_match(struct console *co, char *name, int idx, if (port->iotype != iotype) continue; - if ((iotype == UPIO_MEM || iotype == UPIO_MEM32) && - (port->mapbase != addr)) + if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || + iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) + && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c index ca16195fb069..af62131af21e 100644 --- a/drivers/tty/serial/8250/8250_early.c +++ b/drivers/tty/serial/8250/8250_early.c @@ -42,6 +42,8 @@ static unsigned int __init serial8250_early_in(struct uart_port *port, int offse switch (port->iotype) { case UPIO_MEM: return readb(port->membase + offset); + case UPIO_MEM16: + return readw(port->membase + (offset << 1)); case UPIO_MEM32: return readl(port->membase + (offset << 2)); case UPIO_MEM32BE: @@ -59,6 +61,9 @@ static void __init serial8250_early_out(struct uart_port *port, int offset, int case UPIO_MEM: writeb(value, port->membase + offset); break; + case UPIO_MEM16: + writew(value, port->membase + (offset << 1)); + break; case UPIO_MEM32: writel(value, port->membase + (offset << 2)); break; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 52d82d2ac726..8d262bce97e4 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -368,6 +368,18 @@ static void mem_serial_out(struct uart_port *p, int offset, int value) writeb(value, p->membase + offset); } +static void mem16_serial_out(struct uart_port *p, int offset, int value) +{ + offset = offset << p->regshift; + writew(value, p->membase + offset); +} + +static unsigned int mem16_serial_in(struct uart_port *p, int offset) +{ + offset = offset << p->regshift; + return readw(p->membase + offset); +} + static void mem32_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; @@ -425,6 +437,11 @@ static void set_io_from_upio(struct uart_port *p) p->serial_out = mem_serial_out; break; + case UPIO_MEM16: + p->serial_in = mem16_serial_in; + p->serial_out = mem16_serial_out; + break; + case UPIO_MEM32: p->serial_in = mem32_serial_in; p->serial_out = mem32_serial_out; @@ -459,6 +476,7 @@ serial_port_out_sync(struct uart_port *p, int offset, int value) { switch (p->iotype) { case UPIO_MEM: + case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: @@ -2462,6 +2480,7 @@ static int serial8250_request_std_resource(struct uart_8250_port *up) case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: + case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) break; @@ -2499,6 +2518,7 @@ static void serial8250_release_std_resource(struct uart_8250_port *up) case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: + case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) break; diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index f09636083426..07f7393210db 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -71,10 +71,16 @@ static int __init parse_options(struct earlycon_device *device, char *options) return -EINVAL; switch (port->iotype) { + case UPIO_MEM: + port->mapbase = addr; + break; + case UPIO_MEM16: + port->regshift = 1; + port->mapbase = addr; + break; case UPIO_MEM32: case UPIO_MEM32BE: - port->regshift = 2; /* fall-through */ - case UPIO_MEM: + port->regshift = 2; port->mapbase = addr; break; case UPIO_PORT: @@ -91,10 +97,11 @@ static int __init parse_options(struct earlycon_device *device, char *options) strlcpy(device->options, options, length); } - if (port->iotype == UPIO_MEM || port->iotype == UPIO_MEM32 || - port->iotype == UPIO_MEM32BE) + if (port->iotype == UPIO_MEM || port->iotype == UPIO_MEM16 || + port->iotype == UPIO_MEM32 || port->iotype == UPIO_MEM32BE) pr_info("Early serial console at MMIO%s 0x%llx (options '%s')\n", (port->iotype == UPIO_MEM) ? "" : + (port->iotype == UPIO_MEM16) ? "16" : (port->iotype == UPIO_MEM32) ? "32" : "32be", (unsigned long long)port->mapbase, device->options); diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index de5029649795..6d002eeb2516 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -122,6 +122,9 @@ static int of_platform_serial_setup(struct platform_device *ofdev, case 1: port->iotype = UPIO_MEM; break; + case 2: + port->iotype = UPIO_MEM16; + break; case 4: port->iotype = of_device_is_big_endian(np) ? UPIO_MEM32BE : UPIO_MEM32; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 22cfc3271744..b1f54ab1818c 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1818,8 +1818,8 @@ uart_get_console(struct uart_port *ports, int nr, struct console *co) * @options: ptr for field; NULL if not present (out) * * Decodes earlycon kernel command line parameters of the form - * earlycon=,io|mmio|mmio32|mmio32be|mmio32native,, - * console=,io|mmio|mmio32|mmio32be|mmio32native,, + * earlycon=,io|mmio|mmio16|mmio32|mmio32be|mmio32native,, + * console=,io|mmio|mmio16|mmio32|mmio32be|mmio32native,, * * The optional form * earlycon=,0x, @@ -1834,6 +1834,9 @@ int uart_parse_earlycon(char *p, unsigned char *iotype, unsigned long *addr, if (strncmp(p, "mmio,", 5) == 0) { *iotype = UPIO_MEM; p += 5; + } else if (strncmp(p, "mmio16,", 7) == 0) { + *iotype = UPIO_MEM16; + p += 7; } else if (strncmp(p, "mmio32,", 7) == 0) { *iotype = UPIO_MEM32; p += 7; @@ -2186,6 +2189,7 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port) "I/O 0x%lx offset 0x%x", port->iobase, port->hub6); break; case UPIO_MEM: + case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: @@ -2831,6 +2835,7 @@ int uart_match_port(struct uart_port *port1, struct uart_port *port2) return (port1->iobase == port2->iobase) && (port1->hub6 == port2->hub6); case UPIO_MEM: + case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 297d4fa1cfe5..35aa87b96b71 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -150,6 +150,7 @@ struct uart_port { #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 */ +#define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index 25331f9faa76..5d59c3ebf459 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -69,6 +69,7 @@ struct serial_struct { #define SERIAL_IO_AU 4 #define SERIAL_IO_TSI 5 #define SERIAL_IO_MEM32BE 6 +#define SERIAL_IO_MEM16 7 #define UART_CLEAR_FIFO 0x01 #define UART_USE_FIFO 0x02 -- cgit v1.2.3 From 998b4a4571b87eb6795863e07683fa5d4e0398ba Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 13:01:08 -0500 Subject: tty: Improve tty_debug() macro Incorporate suggestions for tty core debug macro improvements - printk(KERN_DEBUG) => pr_debug() - ##args => ##__VA_ARGS__ - remove do {} while() - output tty_name() first cc: Joe Perches Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5e31f1b99037..3695c884258a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -667,10 +667,7 @@ static inline void proc_tty_register_driver(struct tty_driver *d) {} static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #endif -#define tty_debug(tty, f, args...) \ - do { \ - printk(KERN_DEBUG "%s: %s: " f, __func__, \ - tty_name(tty), ##args); \ - } while (0) +#define tty_debug(tty, f, ...) \ + pr_debug("%s: %s: " f, tty_name(tty), __func__, ##__VA_ARGS__) #endif -- cgit v1.2.3 From 82b8f888e99c81c609710901d8defbc8eff13f79 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 13:01:09 -0500 Subject: tty: Make tty_paranoia_check() file scope tty_paranoia_check() is only used within drivers/tty/tty_io.c; remove extern declaration in header and limit symbol to file scope. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 2 +- include/linux/tty.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index bcc8e1e8bb72..adc0229f6b5d 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -256,7 +256,7 @@ const char *tty_name(const struct tty_struct *tty) EXPORT_SYMBOL(tty_name); -int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, +static int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, const char *routine) { #ifdef TTY_PARANOIA_CHECK diff --git a/include/linux/tty.h b/include/linux/tty.h index 3695c884258a..0532465ea142 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -419,8 +419,6 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) return tty; } -extern int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, - const char *routine); extern const char *tty_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); extern int __tty_check_change(struct tty_struct *tty, int sig); -- cgit v1.2.3 From 0a083eddae33b6e20234d05a9cf54f87b0095511 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 13:01:12 -0500 Subject: tty: core: Add helper fn to deref tty driver name Similar to tty_name(), add tty_driver_name() helper to safely dereference tty->driver->name (otherwise return empty string). Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 7 +++++++ include/linux/tty.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 336714cf370a..ef8ee34670c3 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -256,6 +256,13 @@ const char *tty_name(const struct tty_struct *tty) EXPORT_SYMBOL(tty_name); +const char *tty_driver_name(const struct tty_struct *tty) +{ + if (!tty || !tty->driver) + return ""; + return tty->driver->name; +} + static int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, const char *routine) { diff --git a/include/linux/tty.h b/include/linux/tty.h index 0532465ea142..a9c1af990da9 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -420,6 +420,7 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) } extern const char *tty_name(const struct tty_struct *tty); +extern const char *tty_driver_name(const struct tty_struct *tty); extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); extern int __tty_check_change(struct tty_struct *tty, int sig); extern int tty_check_change(struct tty_struct *tty); -- cgit v1.2.3 From 339f36ba14cf9f8fcf6e6b78385bd6811ec59fbe Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 13:01:13 -0500 Subject: tty: Define tty_*() printk macros Since not all ttys are devices (eg., SysV ptys), dev_*() printk macros cannot be used. Define tty_*() printk macros that output in similar format to dev_*() macros (ie., : .....). Transform the most-trivial printk( LEVEL ...) usage to tty_*() usage. NB: The function name has been eliminated from messages with unique context, or prefixed to the format when given. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 7 ++----- drivers/tty/tty_io.c | 27 ++++++++++----------------- drivers/tty/tty_port.c | 9 ++++----- include/linux/tty.h | 12 +++++++++++- 4 files changed, 27 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index ed776149261e..c37c15d2f782 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1201,9 +1201,7 @@ static void n_tty_receive_overrun(struct tty_struct *tty) ldata->num_overrun++; if (time_after(jiffies, ldata->overrun_time + HZ) || time_after(ldata->overrun_time, jiffies)) { - printk(KERN_WARNING "%s: %d input overrun(s)\n", - tty_name(tty), - ldata->num_overrun); + tty_warn(tty, "%d input overrun(s)\n", ldata->num_overrun); ldata->overrun_time = jiffies; ldata->num_overrun = 0; } @@ -1486,8 +1484,7 @@ n_tty_receive_char_flagged(struct tty_struct *tty, unsigned char c, char flag) n_tty_receive_overrun(tty); break; default: - printk(KERN_ERR "%s: unknown flag %d\n", - tty_name(tty), flag); + tty_err(tty, "unknown flag %d\n", flag); break; } } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index ef8ee34670c3..c9d3989b1f14 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -300,9 +300,8 @@ static int check_tty_count(struct tty_struct *tty, const char *routine) tty->link && tty->link->count) count++; if (tty->count != count) { - printk(KERN_WARNING "Warning: dev (%s) tty->count(%d) " - "!= #fd's(%d) in %s\n", - tty->name, tty->count, count, routine); + tty_warn(tty, "%s: tty->count(%d) != #fd's(%d)\n", + routine, tty->count, count); return count; } #endif @@ -427,10 +426,8 @@ int __tty_check_change(struct tty_struct *tty, int sig) } rcu_read_unlock(); - if (!tty_pgrp) { - pr_warn("%s: tty_check_change: sig=%d, tty->pgrp == NULL!\n", - tty_name(tty), sig); - } + if (!tty_pgrp) + tty_warn(tty, "sig=%d, tty->pgrp == NULL!\n", sig); return ret; } @@ -1246,8 +1243,7 @@ static ssize_t tty_write(struct file *file, const char __user *buf, return -EIO; /* Short term debug to catch buggy drivers */ if (tty->ops->write_room == NULL) - printk(KERN_ERR "tty driver %s lacks a write_room method.\n", - tty->driver->name); + tty_err(tty, "missing write_room method\n"); ld = tty_ldisc_ref_wait(tty); if (!ld->ops->write) ret = -EIO; @@ -1568,8 +1564,8 @@ err_module_put: /* call the tty release_tty routine to clean out this slot */ err_release_tty: tty_unlock(tty); - printk_ratelimited(KERN_INFO "tty_init_dev: ldisc open failed, " - "clearing slot %d\n", idx); + tty_info_ratelimited(tty, "ldisc open failed (%d), clearing slot %d\n", + retval, idx); release_tty(tty, idx); return ERR_PTR(retval); } @@ -1842,8 +1838,7 @@ int tty_release(struct inode *inode, struct file *filp) if (once) { once = 0; - printk(KERN_WARNING "%s: %s: read/write wait queue active!\n", - __func__, tty_name(tty)); + tty_warn(tty, "read/write wait queue active!\n"); } schedule_timeout_killable(timeout); if (timeout < 120 * HZ) @@ -1854,14 +1849,12 @@ int tty_release(struct inode *inode, struct file *filp) if (o_tty) { if (--o_tty->count < 0) { - printk(KERN_WARNING "%s: bad pty slave count (%d) for %s\n", - __func__, o_tty->count, tty_name(o_tty)); + tty_warn(tty, "bad slave count (%d)\n", o_tty->count); o_tty->count = 0; } } if (--tty->count < 0) { - printk(KERN_WARNING "%s: bad tty->count (%d) for %s\n", - __func__, tty->count, tty_name(tty)); + tty_warn(tty, "bad tty->count (%d)\n", tty->count); tty->count = 0; } diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 482f33f20043..846ed481c24f 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -462,14 +462,13 @@ int tty_port_close_start(struct tty_port *port, spin_lock_irqsave(&port->lock, flags); if (tty->count == 1 && port->count != 1) { - printk(KERN_WARNING - "tty_port_close_start: tty->count = 1 port count = %d.\n", - port->count); + tty_warn(tty, "%s: tty->count = 1 port count = %d\n", __func__, + port->count); port->count = 1; } if (--port->count < 0) { - printk(KERN_WARNING "tty_port_close_start: count = %d\n", - port->count); + tty_warn(tty, "%s: bad port count (%d)\n", __func__, + port->count); port->count = 0; } diff --git a/include/linux/tty.h b/include/linux/tty.h index a9c1af990da9..f578e8405ff0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -666,7 +666,17 @@ static inline void proc_tty_register_driver(struct tty_driver *d) {} static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #endif +#define tty_msg(fn, tty, f, ...) \ + fn("%s %s: " f, tty_driver_name(tty), tty_name(tty), ##__VA_ARGS__) + #define tty_debug(tty, f, ...) \ - pr_debug("%s: %s: " f, tty_name(tty), __func__, ##__VA_ARGS__) + tty_msg(pr_debug, tty, "%s:" f, __func__, ##__VA_ARGS__) +#define tty_info(tty, f, ...) tty_msg(pr_info, tty, f, ##__VA_ARGS__) +#define tty_notice(tty, f, ...) tty_msg(pr_notice, tty, f, ##__VA_ARGS__) +#define tty_warn(tty, f, ...) tty_msg(pr_warn, tty, f, ##__VA_ARGS__) +#define tty_err(tty, f, ...) tty_msg(pr_err, tty, f, ##__VA_ARGS__) + +#define tty_info_ratelimited(tty, f, ...) \ + tty_msg(pr_info_ratelimited, tty, f, ##__VA_ARGS__) #endif -- cgit v1.2.3 From d435cefe9cbc9308cac8d4b19069a572e2bd1558 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 13:01:19 -0500 Subject: tty: Remove __func__ from tty_debug() macro Now that tty_debug() macro uses pr_debug(), the function name can be printed when using dynamic debug; printing the function name within the format string is redundant. Remove the __func__ parameter and print specifier from the format string. Add context to messages for when the function name is not printed by dynamic debug, or when dynamic debug is not enabled. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 2 +- drivers/tty/tty_io.c | 14 +++++++------- drivers/tty/tty_ioctl.c | 2 +- include/linux/tty.h | 3 +-- 4 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index a45660f62db5..b3110040164a 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -788,7 +788,7 @@ static int ptmx_open(struct inode *inode, struct file *filp) if (retval) goto err_release; - tty_debug_hangup(tty, "(tty count=%d)\n", tty->count); + tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); tty_unlock(tty); return 0; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index d9df15f1086b..f8e1fce9bdfd 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -783,7 +783,7 @@ static void do_tty_hangup(struct work_struct *work) void tty_hangup(struct tty_struct *tty) { - tty_debug_hangup(tty, "\n"); + tty_debug_hangup(tty, "hangup\n"); schedule_work(&tty->hangup_work); } @@ -800,7 +800,7 @@ EXPORT_SYMBOL(tty_hangup); void tty_vhangup(struct tty_struct *tty) { - tty_debug_hangup(tty, "\n"); + tty_debug_hangup(tty, "vhangup\n"); __tty_hangup(tty, 0); } @@ -837,7 +837,7 @@ void tty_vhangup_self(void) static void tty_vhangup_session(struct tty_struct *tty) { - tty_debug_hangup(tty, "\n"); + tty_debug_hangup(tty, "session hangup\n"); __tty_hangup(tty, 1); } @@ -1787,7 +1787,7 @@ int tty_release(struct inode *inode, struct file *filp) return 0; } - tty_debug_hangup(tty, "(tty count=%d)...\n", tty->count); + tty_debug_hangup(tty, "releasing (count=%d)\n", tty->count); if (tty->ops->close) tty->ops->close(tty, filp); @@ -1903,7 +1903,7 @@ int tty_release(struct inode *inode, struct file *filp) /* Wait for pending work before tty destruction commmences */ tty_flush_works(tty); - tty_debug_hangup(tty, "freeing structure...\n"); + tty_debug_hangup(tty, "freeing structure\n"); /* * The release_tty function takes care of the details of clearing * the slots and preserving the termios structure. The tty_unlock_pair @@ -2093,7 +2093,7 @@ retry_open: tty->driver->subtype == PTY_TYPE_MASTER) noctty = 1; - tty_debug_hangup(tty, "(tty count=%d)\n", tty->count); + tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); if (tty->ops->open) retval = tty->ops->open(tty, filp); @@ -2102,7 +2102,7 @@ retry_open: filp->f_flags = saved_flags; if (retval) { - tty_debug_hangup(tty, "error %d, releasing...\n", retval); + tty_debug_hangup(tty, "open error %d, releasing\n", retval); tty_unlock(tty); /* need to call tty_release without BTM */ tty_release(inode, filp); diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 40964eaf115f..0ea351388724 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -216,7 +216,7 @@ int tty_unthrottle_safe(struct tty_struct *tty) void tty_wait_until_sent(struct tty_struct *tty, long timeout) { - tty_debug_wait_until_sent(tty, "\n"); + tty_debug_wait_until_sent(tty, "wait until sent, timeout=%ld\n", timeout); if (!timeout) timeout = MAX_SCHEDULE_TIMEOUT; diff --git a/include/linux/tty.h b/include/linux/tty.h index f578e8405ff0..f06dd7a41a03 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -669,8 +669,7 @@ static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #define tty_msg(fn, tty, f, ...) \ fn("%s %s: " f, tty_driver_name(tty), tty_name(tty), ##__VA_ARGS__) -#define tty_debug(tty, f, ...) \ - tty_msg(pr_debug, tty, "%s:" f, __func__, ##__VA_ARGS__) +#define tty_debug(tty, f, ...) tty_msg(pr_debug, tty, f, ##__VA_ARGS__) #define tty_info(tty, f, ...) tty_msg(pr_info, tty, f, ##__VA_ARGS__) #define tty_notice(tty, f, ...) tty_msg(pr_notice, tty, f, ##__VA_ARGS__) #define tty_warn(tty, f, ...) tty_msg(pr_warn, tty, f, ##__VA_ARGS__) -- cgit v1.2.3 From 4de91ebcc788f81d2a974d91208f5560ddf36378 Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Sun, 8 Nov 2015 09:18:31 -0500 Subject: tty: Remove dead tty_write_flush() declaration and macro tty_write_flush() has no definition and the TTY_WRITE_FLUSH() macro is never invoked; remove. Signed-off-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index f06dd7a41a03..2fd8708ea888 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -345,8 +345,6 @@ struct tty_file_private { #define TTY_HUPPED 18 /* Post driver->hangup() */ #define TTY_LDISC_HALTED 22 /* Line discipline is halted */ -#define TTY_WRITE_FLUSH(tty) tty_write_flush((tty)) - /* Values for tty->flow_change */ #define TTY_THROTTLE_SAFE 1 #define TTY_UNTHROTTLE_SAFE 2 @@ -395,8 +393,6 @@ static inline int __init tty_init(void) { return 0; } #endif -extern void tty_write_flush(struct tty_struct *); - extern struct ktermios tty_std_termios; extern int vcs_init(void); -- cgit v1.2.3 From d1b5c87fa8058a3f477ae05555916dd1cea934ad Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Nov 2015 16:48:12 +0100 Subject: serial: remove NWP serial support The NWP serial driver is no longer needed, as the two users of this hardware have migrated to a much faster generation hardware, see https://en.wikipedia.org/wiki/QPACE2 for the replacement. Signed-off-by: Arnd Bergmann Cc: Benjamin Krill Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 19 +- drivers/tty/serial/Makefile | 1 - drivers/tty/serial/nwpserial.c | 477 --------------------------------------- drivers/tty/serial/of_serial.c | 14 -- include/linux/nwpserial.h | 18 -- include/uapi/linux/serial_core.h | 2 +- 6 files changed, 2 insertions(+), 529 deletions(-) delete mode 100644 drivers/tty/serial/nwpserial.c delete mode 100644 include/linux/nwpserial.h (limited to 'include/linux') diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index f0bbedf61cae..643fc50bb741 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1099,7 +1099,7 @@ config SERIAL_NETX_CONSOLE config SERIAL_OF_PLATFORM tristate "Serial port on Open Firmware platform bus" depends on OF - depends on SERIAL_8250 || SERIAL_OF_PLATFORM_NWPSERIAL + depends on SERIAL_8250 help If you have a PowerPC based system that has serial ports on a platform specific bus, you should enable this option. @@ -1133,23 +1133,6 @@ config SERIAL_OMAP_CONSOLE your boot loader about how to pass options to the kernel at boot time.) -config SERIAL_OF_PLATFORM_NWPSERIAL - tristate "NWP serial port driver" - depends on PPC_DCR - select SERIAL_OF_PLATFORM - select SERIAL_CORE_CONSOLE - select SERIAL_CORE - help - This driver supports the cell network processor nwp serial - device. - -config SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE - bool "Console on NWP serial port" - depends on SERIAL_OF_PLATFORM_NWPSERIAL=y - select SERIAL_CORE_CONSOLE - help - Support for Console on the NWP serial ports. - config SERIAL_LANTIQ bool "Lantiq serial driver" depends on LANTIQ diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index 5ab41119b3dc..ee8893317433 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -64,7 +64,6 @@ obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o obj-$(CONFIG_SERIAL_MSM) += msm_serial.o obj-$(CONFIG_SERIAL_NETX) += netx-serial.o obj-$(CONFIG_SERIAL_OF_PLATFORM) += of_serial.o -obj-$(CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL) += nwpserial.o obj-$(CONFIG_SERIAL_KGDB_NMI) += kgdb_nmi.o obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o obj-$(CONFIG_SERIAL_OMAP) += omap-serial.o diff --git a/drivers/tty/serial/nwpserial.c b/drivers/tty/serial/nwpserial.c deleted file mode 100644 index 5da7622e88c3..000000000000 --- a/drivers/tty/serial/nwpserial.c +++ /dev/null @@ -1,477 +0,0 @@ -/* - * Serial Port driver for a NWP uart device - * - * Copyright (C) 2008 IBM Corp., Benjamin Krill - * - * 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. - * - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define NWPSERIAL_NR 2 - -#define NWPSERIAL_STATUS_RXVALID 0x1 -#define NWPSERIAL_STATUS_TXFULL 0x2 - -struct nwpserial_port { - struct uart_port port; - dcr_host_t dcr_host; - unsigned int ier; - unsigned int mcr; -}; - -static DEFINE_MUTEX(nwpserial_mutex); -static struct nwpserial_port nwpserial_ports[NWPSERIAL_NR]; - -static void wait_for_bits(struct nwpserial_port *up, int bits) -{ - unsigned int status, tmout = 10000; - - /* Wait up to 10ms for the character(s) to be sent. */ - do { - status = dcr_read(up->dcr_host, UART_LSR); - - if (--tmout == 0) - break; - udelay(1); - } while ((status & bits) != bits); -} - -#ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE -static void nwpserial_console_putchar(struct uart_port *port, int c) -{ - struct nwpserial_port *up; - up = container_of(port, struct nwpserial_port, port); - /* check if tx buffer is full */ - wait_for_bits(up, UART_LSR_THRE); - dcr_write(up->dcr_host, UART_TX, c); - up->port.icount.tx++; -} - -static void -nwpserial_console_write(struct console *co, const char *s, unsigned int count) -{ - struct nwpserial_port *up = &nwpserial_ports[co->index]; - unsigned long flags; - int locked = 1; - - if (oops_in_progress) - locked = spin_trylock_irqsave(&up->port.lock, flags); - else - spin_lock_irqsave(&up->port.lock, flags); - - /* save and disable interrupt */ - up->ier = dcr_read(up->dcr_host, UART_IER); - dcr_write(up->dcr_host, UART_IER, up->ier & ~UART_IER_RDI); - - uart_console_write(&up->port, s, count, nwpserial_console_putchar); - - /* wait for transmitter to become empty */ - while ((dcr_read(up->dcr_host, UART_LSR) & UART_LSR_THRE) == 0) - cpu_relax(); - - /* restore interrupt state */ - dcr_write(up->dcr_host, UART_IER, up->ier); - - if (locked) - spin_unlock_irqrestore(&up->port.lock, flags); -} - -static struct uart_driver nwpserial_reg; -static struct console nwpserial_console = { - .name = "ttySQ", - .write = nwpserial_console_write, - .device = uart_console_device, - .flags = CON_PRINTBUFFER, - .index = -1, - .data = &nwpserial_reg, -}; -#define NWPSERIAL_CONSOLE (&nwpserial_console) -#else -#define NWPSERIAL_CONSOLE NULL -#endif /* CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE */ - -/**************************************************************************/ - -static int nwpserial_request_port(struct uart_port *port) -{ - return 0; -} - -static void nwpserial_release_port(struct uart_port *port) -{ - /* N/A */ -} - -static void nwpserial_config_port(struct uart_port *port, int flags) -{ - port->type = PORT_NWPSERIAL; -} - -static irqreturn_t nwpserial_interrupt(int irq, void *dev_id) -{ - struct nwpserial_port *up = dev_id; - struct tty_port *port = &up->port.state->port; - irqreturn_t ret; - unsigned int iir; - unsigned char ch; - - spin_lock(&up->port.lock); - - /* check if the uart was the interrupt source. */ - iir = dcr_read(up->dcr_host, UART_IIR); - if (!iir) { - ret = IRQ_NONE; - goto out; - } - - do { - up->port.icount.rx++; - ch = dcr_read(up->dcr_host, UART_RX); - if (up->port.ignore_status_mask != NWPSERIAL_STATUS_RXVALID) - tty_insert_flip_char(port, ch, TTY_NORMAL); - } while (dcr_read(up->dcr_host, UART_LSR) & UART_LSR_DR); - - spin_unlock(&up->port.lock); - tty_flip_buffer_push(port); - spin_lock(&up->port.lock); - - ret = IRQ_HANDLED; - - /* clear interrupt */ - dcr_write(up->dcr_host, UART_IIR, 1); -out: - spin_unlock(&up->port.lock); - return ret; -} - -static int nwpserial_startup(struct uart_port *port) -{ - struct nwpserial_port *up; - int err; - - up = container_of(port, struct nwpserial_port, port); - - /* disable flow control by default */ - up->mcr = dcr_read(up->dcr_host, UART_MCR) & ~UART_MCR_AFE; - dcr_write(up->dcr_host, UART_MCR, up->mcr); - - /* register interrupt handler */ - err = request_irq(up->port.irq, nwpserial_interrupt, - IRQF_SHARED, "nwpserial", up); - if (err) - return err; - - /* enable interrupts */ - up->ier = UART_IER_RDI; - dcr_write(up->dcr_host, UART_IER, up->ier); - - /* enable receiving */ - up->port.ignore_status_mask &= ~NWPSERIAL_STATUS_RXVALID; - - return 0; -} - -static void nwpserial_shutdown(struct uart_port *port) -{ - struct nwpserial_port *up; - up = container_of(port, struct nwpserial_port, port); - - /* disable receiving */ - up->port.ignore_status_mask |= NWPSERIAL_STATUS_RXVALID; - - /* disable interrupts from this port */ - up->ier = 0; - dcr_write(up->dcr_host, UART_IER, up->ier); - - /* free irq */ - free_irq(up->port.irq, up); -} - -static int nwpserial_verify_port(struct uart_port *port, - struct serial_struct *ser) -{ - return -EINVAL; -} - -static const char *nwpserial_type(struct uart_port *port) -{ - return port->type == PORT_NWPSERIAL ? "nwpserial" : NULL; -} - -static void nwpserial_set_termios(struct uart_port *port, - struct ktermios *termios, struct ktermios *old) -{ - struct nwpserial_port *up; - up = container_of(port, struct nwpserial_port, port); - - up->port.read_status_mask = NWPSERIAL_STATUS_RXVALID - | NWPSERIAL_STATUS_TXFULL; - - up->port.ignore_status_mask = 0; - /* ignore all characters if CREAD is not set */ - if ((termios->c_cflag & CREAD) == 0) - up->port.ignore_status_mask |= NWPSERIAL_STATUS_RXVALID; - - /* Copy back the old hardware settings */ - if (old) - tty_termios_copy_hw(termios, old); -} - -static void nwpserial_break_ctl(struct uart_port *port, int ctl) -{ - /* N/A */ -} - -static void nwpserial_stop_rx(struct uart_port *port) -{ - struct nwpserial_port *up; - up = container_of(port, struct nwpserial_port, port); - /* don't forward any more data (like !CREAD) */ - up->port.ignore_status_mask = NWPSERIAL_STATUS_RXVALID; -} - -static void nwpserial_putchar(struct nwpserial_port *up, unsigned char c) -{ - /* check if tx buffer is full */ - wait_for_bits(up, UART_LSR_THRE); - dcr_write(up->dcr_host, UART_TX, c); - up->port.icount.tx++; -} - -static void nwpserial_start_tx(struct uart_port *port) -{ - struct nwpserial_port *up; - struct circ_buf *xmit; - up = container_of(port, struct nwpserial_port, port); - xmit = &up->port.state->xmit; - - if (port->x_char) { - nwpserial_putchar(up, up->port.x_char); - port->x_char = 0; - } - - while (!(uart_circ_empty(xmit) || uart_tx_stopped(&up->port))) { - nwpserial_putchar(up, xmit->buf[xmit->tail]); - xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE-1); - } -} - -static unsigned int nwpserial_get_mctrl(struct uart_port *port) -{ - return 0; -} - -static void nwpserial_set_mctrl(struct uart_port *port, unsigned int mctrl) -{ - /* N/A */ -} - -static void nwpserial_stop_tx(struct uart_port *port) -{ - /* N/A */ -} - -static unsigned int nwpserial_tx_empty(struct uart_port *port) -{ - struct nwpserial_port *up; - unsigned long flags; - int ret; - up = container_of(port, struct nwpserial_port, port); - - spin_lock_irqsave(&up->port.lock, flags); - ret = dcr_read(up->dcr_host, UART_LSR); - spin_unlock_irqrestore(&up->port.lock, flags); - - return ret & UART_LSR_TEMT ? TIOCSER_TEMT : 0; -} - -static struct uart_ops nwpserial_pops = { - .tx_empty = nwpserial_tx_empty, - .set_mctrl = nwpserial_set_mctrl, - .get_mctrl = nwpserial_get_mctrl, - .stop_tx = nwpserial_stop_tx, - .start_tx = nwpserial_start_tx, - .stop_rx = nwpserial_stop_rx, - .break_ctl = nwpserial_break_ctl, - .startup = nwpserial_startup, - .shutdown = nwpserial_shutdown, - .set_termios = nwpserial_set_termios, - .type = nwpserial_type, - .release_port = nwpserial_release_port, - .request_port = nwpserial_request_port, - .config_port = nwpserial_config_port, - .verify_port = nwpserial_verify_port, -}; - -static struct uart_driver nwpserial_reg = { - .owner = THIS_MODULE, - .driver_name = "nwpserial", - .dev_name = "ttySQ", - .major = TTY_MAJOR, - .minor = 68, - .nr = NWPSERIAL_NR, - .cons = NWPSERIAL_CONSOLE, -}; - -int nwpserial_register_port(struct uart_port *port) -{ - struct nwpserial_port *up = NULL; - int ret = -1; - int i; - static int first = 1; - int dcr_len; - int dcr_base; - struct device_node *dn; - - mutex_lock(&nwpserial_mutex); - - dn = port->dev->of_node; - if (dn == NULL) - goto out; - - /* get dcr base. */ - dcr_base = dcr_resource_start(dn, 0); - - /* find matching entry */ - for (i = 0; i < NWPSERIAL_NR; i++) - if (nwpserial_ports[i].port.iobase == dcr_base) { - up = &nwpserial_ports[i]; - break; - } - - /* we didn't find a mtching entry, search for a free port */ - if (up == NULL) - for (i = 0; i < NWPSERIAL_NR; i++) - if (nwpserial_ports[i].port.type == PORT_UNKNOWN && - nwpserial_ports[i].port.iobase == 0) { - up = &nwpserial_ports[i]; - break; - } - - if (up == NULL) { - ret = -EBUSY; - goto out; - } - - if (first) - uart_register_driver(&nwpserial_reg); - first = 0; - - up->port.membase = port->membase; - up->port.irq = port->irq; - up->port.uartclk = port->uartclk; - up->port.fifosize = port->fifosize; - up->port.regshift = port->regshift; - up->port.iotype = port->iotype; - up->port.flags = port->flags; - up->port.mapbase = port->mapbase; - up->port.private_data = port->private_data; - - if (port->dev) - up->port.dev = port->dev; - - if (up->port.iobase != dcr_base) { - up->port.ops = &nwpserial_pops; - up->port.fifosize = 16; - - spin_lock_init(&up->port.lock); - - up->port.iobase = dcr_base; - dcr_len = dcr_resource_len(dn, 0); - - up->dcr_host = dcr_map(dn, dcr_base, dcr_len); - if (!DCR_MAP_OK(up->dcr_host)) { - printk(KERN_ERR "Cannot map DCR resources for NWPSERIAL"); - goto out; - } - } - - ret = uart_add_one_port(&nwpserial_reg, &up->port); - if (ret == 0) - ret = up->port.line; - -out: - mutex_unlock(&nwpserial_mutex); - - return ret; -} -EXPORT_SYMBOL(nwpserial_register_port); - -void nwpserial_unregister_port(int line) -{ - struct nwpserial_port *up = &nwpserial_ports[line]; - mutex_lock(&nwpserial_mutex); - uart_remove_one_port(&nwpserial_reg, &up->port); - - up->port.type = PORT_UNKNOWN; - - mutex_unlock(&nwpserial_mutex); -} -EXPORT_SYMBOL(nwpserial_unregister_port); - -#ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE -static int __init nwpserial_console_init(void) -{ - struct nwpserial_port *up = NULL; - struct device_node *dn; - const char *name; - int dcr_base; - int dcr_len; - int i; - - /* search for a free port */ - for (i = 0; i < NWPSERIAL_NR; i++) - if (nwpserial_ports[i].port.type == PORT_UNKNOWN) { - up = &nwpserial_ports[i]; - break; - } - - if (up == NULL) - return -1; - - name = of_get_property(of_chosen, "linux,stdout-path", NULL); - if (name == NULL) - return -1; - - dn = of_find_node_by_path(name); - if (!dn) - return -1; - - spin_lock_init(&up->port.lock); - up->port.ops = &nwpserial_pops; - up->port.type = PORT_NWPSERIAL; - up->port.fifosize = 16; - - dcr_base = dcr_resource_start(dn, 0); - dcr_len = dcr_resource_len(dn, 0); - up->port.iobase = dcr_base; - - up->dcr_host = dcr_map(dn, dcr_base, dcr_len); - if (!DCR_MAP_OK(up->dcr_host)) { - printk("Cannot map DCR resources for SERIAL"); - return -1; - } - register_console(&nwpserial_console); - return 0; -} -console_initcall(nwpserial_console_init); -#endif /* CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL_CONSOLE */ diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c index 6d002eeb2516..920468bf4e83 100644 --- a/drivers/tty/serial/of_serial.c +++ b/drivers/tty/serial/of_serial.c @@ -215,11 +215,6 @@ static int of_platform_serial_probe(struct platform_device *ofdev) ret = serial8250_register_8250_port(&port8250); break; } -#endif -#ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL - case PORT_NWPSERIAL: - ret = nwpserial_register_port(&port); - break; #endif default: /* need to add code for these */ @@ -252,11 +247,6 @@ static int of_platform_serial_remove(struct platform_device *ofdev) case PORT_8250 ... PORT_MAX_8250: serial8250_unregister_port(info->line); break; -#endif -#ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL - case PORT_NWPSERIAL: - nwpserial_unregister_port(info->line); - break; #endif default: /* need to add code for these */ @@ -356,10 +346,6 @@ static const struct of_device_id of_platform_serial_table[] = { .data = (void *)PORT_XSCALE, }, { .compatible = "mrvl,pxa-uart", .data = (void *)PORT_XSCALE, }, -#ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL - { .compatible = "ibm,qpace-nwp-serial", - .data = (void *)PORT_NWPSERIAL, }, -#endif { /* end of list */ }, }; MODULE_DEVICE_TABLE(of, of_platform_serial_table); diff --git a/include/linux/nwpserial.h b/include/linux/nwpserial.h deleted file mode 100644 index 9acb21572eaf..000000000000 --- a/include/linux/nwpserial.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Serial Port driver for a NWP uart device - * - * Copyright (C) 2008 IBM Corp., Benjamin Krill - * - * 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 _NWPSERIAL_H -#define _NWPSERIAL_H - -int nwpserial_register_port(struct uart_port *port); -void nwpserial_unregister_port(int line); - -#endif /* _NWPSERIAL_H */ diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 93ba148f923e..3e5d757407fb 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -176,7 +176,7 @@ #define PORT_S3C6400 84 -/* NWPSERIAL */ +/* NWPSERIAL, now removed */ #define PORT_NWPSERIAL 85 /* MAX3100 */ -- cgit v1.2.3 From 7ec758718920e5e5876d0d02ece6855128c8eb1e Mon Sep 17 00:00:00 2001 From: Russell King Date: Mon, 16 Nov 2015 17:40:57 +0000 Subject: tty: amba-pl011: add support for ZTE UART (EXPERIMENTAL) Add (incomplete) support for the ZTE UART to the AMBA PL011 driver. This is similar to the ARM and ST variants, except it has a different register address layout, and requires 32-bit accesses to the registers. Use the newly introduced register tables and access size support to cope with these differences. Signed-off-by: Russell King Reviewed-by: Peter Hurley Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/amba-pl011.c | 23 +++++++++++++++++++++++ include/linux/amba/serial.h | 18 ++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index c8165b61dbf8..295f0be128f9 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -171,6 +171,29 @@ static struct vendor_data vendor_st = { .get_fifosize = get_fifosize_st, }; +static const u16 pl011_zte_offsets[REG_ARRAY_SIZE] = { + [REG_DR] = ZX_UART011_DR, + [REG_FR] = ZX_UART011_FR, + [REG_LCRH_RX] = ZX_UART011_LCRH, + [REG_LCRH_TX] = ZX_UART011_LCRH, + [REG_IBRD] = ZX_UART011_IBRD, + [REG_FBRD] = ZX_UART011_FBRD, + [REG_CR] = ZX_UART011_CR, + [REG_IFLS] = ZX_UART011_IFLS, + [REG_IMSC] = ZX_UART011_IMSC, + [REG_RIS] = ZX_UART011_RIS, + [REG_MIS] = ZX_UART011_MIS, + [REG_ICR] = ZX_UART011_ICR, + [REG_DMACR] = ZX_UART011_DMACR, +}; + +static struct vendor_data vendor_zte = { + .reg_offset = pl011_zte_offsets, + .access_32b = true, + .ifls = UART011_IFLS_RX4_8|UART011_IFLS_TX4_8, + .get_fifosize = get_fifosize_arm, +}; + /* Deals with DMA transactions */ struct pl011_sgbuf { diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 0ddb5c02ad8b..d76a19ba2cff 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -65,6 +65,24 @@ #define ST_UART011_ABCR 0x100 /* Autobaud control register. */ #define ST_UART011_ABIMSC 0x15C /* Autobaud interrupt mask/clear register. */ +/* + * ZTE UART register offsets. This UART has a radically different address + * allocation from the ARM and ST variants, so we list all registers here. + * We assume unlisted registers do not exist. + */ +#define ZX_UART011_DR 0x04 +#define ZX_UART011_FR 0x14 +#define ZX_UART011_IBRD 0x24 +#define ZX_UART011_FBRD 0x28 +#define ZX_UART011_LCRH 0x30 +#define ZX_UART011_CR 0x34 +#define ZX_UART011_IFLS 0x38 +#define ZX_UART011_IMSC 0x40 +#define ZX_UART011_RIS 0x44 +#define ZX_UART011_MIS 0x48 +#define ZX_UART011_ICR 0x4c +#define ZX_UART011_DMACR 0x50 + #define UART011_DR_OE (1 << 11) #define UART011_DR_BE (1 << 10) #define UART011_DR_PE (1 << 9) -- cgit v1.2.3 From 858965d909db32fb567a06916bbebdb8951cd39e Mon Sep 17 00:00:00 2001 From: Peter Hurley Date: Fri, 27 Nov 2015 21:29:24 -0500 Subject: serial: Fix UPIO_MEM comment The original semantics of UPIO_MEM did not include the notion of bitness and endianness; different drivers used UPIO_MEM to refer to their original mmio bitness/endianness. For example, for the 8250 driver this is 8-bit LE but for the amba-pl011 driver this is 16-bit LE. Since UPIO_* values are userspace ABI via TIOCGSERIAL/TIOCSSERIAL ioctls, the original meaning of UPIIO_MEM must remain as it was: the original mmio stride/width/endianness of the driver. Signed-off-by: Peter Hurley Acked-by: Timur Tabi Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 35aa87b96b71..e03d6ba5e5b4 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -145,7 +145,7 @@ struct uart_port { #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_MEM (SERIAL_IO_MEM) /* driver-specific */ #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 */ -- cgit v1.2.3 From e1dba01ca620bb0b3864d5237c1c597d9e012ebf Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 8 Dec 2015 10:37:46 +0100 Subject: i2c: add generic routine to parse DT for timing information Inspired from the i2c-rk3x driver (thanks guys!) but refactored and extended. See built-in docs for further information. Signed-off-by: Wolfram Sang Reviewed-by: Mika Westerberg Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/i2c.h | 18 +++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index ba8eb087f224..b34c412bd2c2 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -53,6 +53,7 @@ #include #include #include +#include #include "i2c-core.h" @@ -1438,6 +1439,58 @@ static void of_i2c_register_devices(struct i2c_adapter *adap) } } +/** + * i2c_parse_fw_timings - get I2C related timing parameters from firmware + * @dev: The device to scan for I2C timing properties + * @t: the i2c_timings struct to be filled with values + * @use_defaults: bool to use sane defaults derived from the I2C specification + * when properties are not found, otherwise use 0 + * + * Scan the device for the generic I2C properties describing timing parameters + * for the signal and fill the given struct with the results. If a property was + * not found and use_defaults was true, then maximum timings are assumed which + * are derived from the I2C specification. If use_defaults is not used, the + * results will be 0, so drivers can apply their own defaults later. The latter + * is mainly intended for avoiding regressions of existing drivers which want + * to switch to this function. New drivers almost always should use the defaults. + */ + +void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults) +{ + int ret; + + memset(t, 0, sizeof(*t)); + + ret = device_property_read_u32(dev, "clock-frequency", &t->bus_freq_hz); + if (ret && use_defaults) + t->bus_freq_hz = 100000; + + ret = device_property_read_u32(dev, "i2c-scl-rising-time-ns", &t->scl_rise_ns); + if (ret && use_defaults) { + if (t->bus_freq_hz <= 100000) + t->scl_rise_ns = 1000; + else if (t->bus_freq_hz <= 400000) + t->scl_rise_ns = 300; + else + t->scl_rise_ns = 120; + } + + ret = device_property_read_u32(dev, "i2c-scl-falling-time-ns", &t->scl_fall_ns); + if (ret && use_defaults) { + if (t->bus_freq_hz <= 400000) + t->scl_fall_ns = 300; + else + t->scl_fall_ns = 120; + } + + device_property_read_u32(dev, "i2c-scl-internal-delay-ns", &t->scl_int_delay_ns); + + ret = device_property_read_u32(dev, "i2c-sda-falling-time-ns", &t->sda_fall_ns); + if (ret && use_defaults) + t->sda_fall_ns = t->scl_fall_ns; +} +EXPORT_SYMBOL_GPL(i2c_parse_fw_timings); + static int of_dev_node_match(struct device *dev, void *data) { return dev->of_node == data; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 51028f351d13..bc2b19ad9357 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -413,6 +413,22 @@ struct i2c_algorithm { #endif }; +/** + * struct i2c_timings - I2C timing information + * @bus_freq_hz: the bus frequency in Hz + * @scl_rise_ns: time SCL signal takes to rise in ns; t(r) in the I2C specification + * @scl_fall_ns: time SCL signal takes to fall in ns; t(f) in the I2C specification + * @scl_int_delay_ns: time IP core additionally needs to setup SCL in ns + * @sda_fall_ns: time SDA signal takes to fall in ns; t(f) in the I2C specification + */ +struct i2c_timings { + u32 bus_freq_hz; + u32 scl_rise_ns; + u32 scl_fall_ns; + u32 scl_int_delay_ns; + u32 sda_fall_ns; +}; + /** * struct i2c_bus_recovery_info - I2C bus recovery information * @recover_bus: Recover routine. Either pass driver's recover_bus() routine, or @@ -604,6 +620,7 @@ extern void i2c_clients_command(struct i2c_adapter *adap, extern struct i2c_adapter *i2c_get_adapter(int nr); extern void i2c_put_adapter(struct i2c_adapter *adap); +void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults); /* Return the functionality mask */ static inline u32 i2c_get_functionality(struct i2c_adapter *adap) @@ -660,6 +677,7 @@ extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); + #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) -- cgit v1.2.3 From 665d2c2848f14c0c2a2e89192bde9073c4d352f7 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 8 Dec 2015 17:04:59 -0800 Subject: mtd: bcm47xxnflash: really unregister NAND on device removal MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The field bcma_nflash::mtd is never set to be non-zero anywhere, but we test for it in the removal path. So the MTD is never unregistered. Also, we should use nand_release(), not mtd_device_unregister(). Finally, we don't need to use the 'platdata' for stashing/retrieving our *driver* data -- that's what *_{get,set}_drvdata() are for. So, kill off bcm_nflash::mtd, and stash the struct bcm47xxnflash in drvdata instead. Also move the forward declaration of mtd_info up a bit, since struct bcma_sflash should be using it. Caught while inspecting other changes being made to this driver. Compile tested only. Signed-off-by: Brian Norris Cc: "RafaÅ‚ MiÅ‚ecki" Cc: linux-wireless@vger.kernel.org Acked-by: Boris Brezillon --- drivers/mtd/nand/bcm47xxnflash/main.c | 7 ++++--- include/linux/bcma/bcma_driver_chipcommon.h | 6 ++---- 2 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/bcm47xxnflash/main.c b/drivers/mtd/nand/bcm47xxnflash/main.c index 9ba0c0f2cd9b..0b3acc439181 100644 --- a/drivers/mtd/nand/bcm47xxnflash/main.c +++ b/drivers/mtd/nand/bcm47xxnflash/main.c @@ -49,6 +49,8 @@ static int bcm47xxnflash_probe(struct platform_device *pdev) return err; } + platform_set_drvdata(pdev, b47n); + err = mtd_device_parse_register(&b47n->mtd, probes, NULL, NULL, 0); if (err) { pr_err("Failed to register MTD device: %d\n", err); @@ -60,10 +62,9 @@ static int bcm47xxnflash_probe(struct platform_device *pdev) static int bcm47xxnflash_remove(struct platform_device *pdev) { - struct bcma_nflash *nflash = dev_get_platdata(&pdev->dev); + struct bcm47xxnflash *nflash = platform_get_drvdata(pdev); - if (nflash->mtd) - mtd_device_unregister(nflash->mtd); + nand_release(&nflash->mtd); return 0; } diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index cf038431a5cc..db51a6ffb7d6 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -579,6 +579,8 @@ struct bcma_pflash { }; #ifdef CONFIG_BCMA_SFLASH +struct mtd_info; + struct bcma_sflash { bool present; u32 window; @@ -592,13 +594,9 @@ struct bcma_sflash { #endif #ifdef CONFIG_BCMA_NFLASH -struct mtd_info; - struct bcma_nflash { bool present; bool boot; /* This is the flash the SoC boots from */ - - struct mtd_info *mtd; }; #endif -- cgit v1.2.3 From a11fac3776fc4db6a9fa1104b1d0477809c677e0 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Mon, 14 Dec 2015 18:58:42 -0800 Subject: f2fs: add symbol to avoid any confusion with tools This patch adds MAX_VOLUME_NAME to sync with f2fs-tools. Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 25c6324a0dd0..e59c3be92106 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -51,6 +51,7 @@ #define MAX_ACTIVE_DATA_LOGS 8 #define VERSION_LEN 256 +#define MAX_VOLUME_NAME 512 /* * For superblock @@ -84,7 +85,7 @@ struct f2fs_super_block { __le32 node_ino; /* node inode number */ __le32 meta_ino; /* meta inode number */ __u8 uuid[16]; /* 128-bit uuid for volume */ - __le16 volume_name[512]; /* volume name */ + __le16 volume_name[MAX_VOLUME_NAME]; /* volume name */ __le32 extension_count; /* # of extensions below */ __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ __le32 cp_payload; -- cgit v1.2.3 From 619848bd074343ff2bdeeafca0be39748f6da372 Mon Sep 17 00:00:00 2001 From: Jake Oshins Date: Mon, 14 Dec 2015 16:01:39 -0800 Subject: drivers:hv: Export a function that maps Linux CPU num onto Hyper-V proc num This patch exposes the mapping between Linux CPU number and Hyper-V virtual processor number. This is necessary because the hypervisor needs to know which virtual processors to target when making a mapping in the Interrupt Redirection Table in the I/O MMU. Signed-off-by: Jake Oshins Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/vmbus_drv.c | 17 +++++++++++++++++ include/linux/hyperv.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 3297731017e4..c01b689e39b1 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1193,6 +1193,23 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, } EXPORT_SYMBOL_GPL(vmbus_allocate_mmio); +/** + * vmbus_cpu_number_to_vp_number() - Map CPU to VP. + * @cpu_number: CPU number in Linux terms + * + * This function returns the mapping between the Linux processor + * number and the hypervisor's virtual processor number, useful + * in making hypercalls and such that talk about specific + * processors. + * + * Return: Virtual processor number in Hyper-V terms + */ +int vmbus_cpu_number_to_vp_number(int cpu_number) +{ + return hv_context.vp_index[cpu_number]; +} +EXPORT_SYMBOL_GPL(vmbus_cpu_number_to_vp_number); + static int vmbus_acpi_add(struct acpi_device *device) { acpi_status result; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 8fdc17b84739..fddb3e0e8feb 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -983,6 +983,8 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t size, resource_size_t align, bool fb_overlap_ok); +int vmbus_cpu_number_to_vp_number(int cpu_number); + /** * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device * -- cgit v1.2.3 From a108393dbf764efb2405f21ca759806c65b8bc16 Mon Sep 17 00:00:00 2001 From: Jake Oshins Date: Mon, 14 Dec 2015 16:01:40 -0800 Subject: drivers:hv: Export the API to invoke a hypercall on Hyper-V This patch exposes the function that hv_vmbus.ko uses to make hypercalls. This is necessary for retargeting an interrupt when it is given a new affinity. Since we are exporting this API, rename the API as it will be visible outside the hv.c file. Signed-off-by: Jake Oshins Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/hv.c | 20 ++++++++++---------- drivers/hv/hyperv_vmbus.h | 2 +- include/linux/hyperv.h | 1 + 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index ad7fc6d92c35..eb4e383dbc58 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -89,9 +89,9 @@ static int query_hypervisor_info(void) } /* - * do_hypercall- Invoke the specified hypercall + * hv_do_hypercall- Invoke the specified hypercall */ -static u64 do_hypercall(u64 control, void *input, void *output) +u64 hv_do_hypercall(u64 control, void *input, void *output) { u64 input_address = (input) ? virt_to_phys(input) : 0; u64 output_address = (output) ? virt_to_phys(output) : 0; @@ -132,6 +132,7 @@ static u64 do_hypercall(u64 control, void *input, void *output) return hv_status_lo | ((u64)hv_status_hi << 32); #endif /* !x86_64 */ } +EXPORT_SYMBOL_GPL(hv_do_hypercall); #ifdef CONFIG_X86_64 static cycle_t read_hv_clock_tsc(struct clocksource *arg) @@ -316,7 +317,7 @@ int hv_post_message(union hv_connection_id connection_id, { struct hv_input_post_message *aligned_msg; - u16 status; + u64 status; if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) return -EMSGSIZE; @@ -330,11 +331,10 @@ int hv_post_message(union hv_connection_id connection_id, aligned_msg->payload_size = payload_size; memcpy((void *)aligned_msg->payload, payload, payload_size); - status = do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL) - & 0xFFFF; + status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL); put_cpu(); - return status; + return status & 0xFFFF; } @@ -344,13 +344,13 @@ int hv_post_message(union hv_connection_id connection_id, * * This involves a hypercall. */ -u16 hv_signal_event(void *con_id) +int hv_signal_event(void *con_id) { - u16 status; + u64 status; - status = (do_hypercall(HVCALL_SIGNAL_EVENT, con_id, NULL) & 0xFFFF); + status = hv_do_hypercall(HVCALL_SIGNAL_EVENT, con_id, NULL); - return status; + return status & 0xFFFF; } static int hv_ce_set_next_event(unsigned long delta, diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 12156db2e88e..9beeb148797f 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -587,7 +587,7 @@ extern int hv_post_message(union hv_connection_id connection_id, enum hv_message_type message_type, void *payload, size_t payload_size); -extern u16 hv_signal_event(void *con_id); +extern int hv_signal_event(void *con_id); extern int hv_synic_alloc(void); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index fddb3e0e8feb..24d0b656e6e7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -984,6 +984,7 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, bool fb_overlap_ok); int vmbus_cpu_number_to_vp_number(int cpu_number); +u64 hv_do_hypercall(u64 control, void *input, void *output); /** * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device -- cgit v1.2.3 From 3053c762444a83ec6a8777f9476668b23b8ab180 Mon Sep 17 00:00:00 2001 From: Jake Oshins Date: Mon, 14 Dec 2015 16:01:41 -0800 Subject: drivers:hv: Define the channel type for Hyper-V PCI Express pass-through This defines the channel type for PCI front-ends in Hyper-V VMs. Signed-off-by: Jake Oshins Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 3 +++ include/linux/hyperv.h | 11 +++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 652afd11a9ef..a77646b4fcc8 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -358,6 +358,7 @@ enum { SCSI, NIC, ND_NIC, + PCIE, MAX_PERF_CHN, }; @@ -375,6 +376,8 @@ static const struct hv_vmbus_device_id hp_devs[] = { { HV_NIC_GUID, }, /* NetworkDirect Guest RDMA */ { HV_ND_GUID, }, + /* PCI Express Pass Through */ + { HV_PCIE_GUID, }, }; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 24d0b656e6e7..c9a9eed89af2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1140,6 +1140,17 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); 0xab, 0x99, 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01 \ } +/* + * PCI Express Pass Through + * {44C4F61D-4444-4400-9D52-802E27EDE19F} + */ + +#define HV_PCIE_GUID \ + .guid = { \ + 0x1D, 0xF6, 0xC4, 0x44, 0x44, 0x44, 0x00, 0x44, \ + 0x9D, 0x52, 0x80, 0x2E, 0x27, 0xED, 0xE1, 0x9F \ + } + /* * Common header for Hyper-V ICs */ -- cgit v1.2.3 From af3ff643ea91ba64dd8d0b1cbed54d44512f96cd Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Mon, 14 Dec 2015 16:01:43 -0800 Subject: Drivers: hv: vmbus: Use uuid_le type consistently Consistently use uuid_le type in the Hyper-V driver code. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel_mgmt.c | 2 +- drivers/hv/vmbus_drv.c | 10 ++--- include/linux/hyperv.h | 92 ++++++++++++++--------------------------- include/linux/mod_devicetable.h | 2 +- scripts/mod/file2alias.c | 2 +- 5 files changed, 40 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index a77646b4fcc8..38470aa4387f 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -408,7 +408,7 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui struct cpumask *alloced_mask; for (i = IDE; i < MAX_PERF_CHN; i++) { - if (!memcmp(type_guid->b, hp_devs[i].guid, + if (!memcmp(type_guid->b, &hp_devs[i].guid, sizeof(uuid_le))) { perf_chn = true; break; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index c01b689e39b1..7078b5f143a2 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -531,7 +531,7 @@ static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env) static const uuid_le null_guid; -static inline bool is_null_guid(const __u8 *guid) +static inline bool is_null_guid(const uuid_le *guid) { if (memcmp(guid, &null_guid, sizeof(uuid_le))) return false; @@ -544,9 +544,9 @@ static inline bool is_null_guid(const __u8 *guid) */ static const struct hv_vmbus_device_id *hv_vmbus_get_id( const struct hv_vmbus_device_id *id, - const __u8 *guid) + const uuid_le *guid) { - for (; !is_null_guid(id->guid); id++) + for (; !is_null_guid(&id->guid); id++) if (!memcmp(&id->guid, guid, sizeof(uuid_le))) return id; @@ -563,7 +563,7 @@ static int vmbus_match(struct device *device, struct device_driver *driver) struct hv_driver *drv = drv_to_hv_drv(driver); struct hv_device *hv_dev = device_to_hv_device(device); - if (hv_vmbus_get_id(drv->id_table, hv_dev->dev_type.b)) + if (hv_vmbus_get_id(drv->id_table, &hv_dev->dev_type)) return 1; return 0; @@ -580,7 +580,7 @@ static int vmbus_probe(struct device *child_device) struct hv_device *dev = device_to_hv_device(child_device); const struct hv_vmbus_device_id *dev_id; - dev_id = hv_vmbus_get_id(drv->id_table, dev->dev_type.b); + dev_id = hv_vmbus_get_id(drv->id_table, &dev->dev_type); if (drv->probe) { ret = drv->probe(dev, dev_id); if (ret != 0) diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c9a9eed89af2..b9f3bb25d8b4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -997,6 +997,8 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); .guid = { g0, g1, g2, g3, g4, g5, g6, g7, \ g8, g9, ga, gb, gc, gd, ge, gf }, + + /* * GUID definitions of various offer types - services offered to the guest. */ @@ -1006,118 +1008,94 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); * {f8615163-df3e-46c5-913f-f2d2f965ed0e} */ #define HV_NIC_GUID \ - .guid = { \ - 0x63, 0x51, 0x61, 0xf8, 0x3e, 0xdf, 0xc5, 0x46, \ - 0x91, 0x3f, 0xf2, 0xd2, 0xf9, 0x65, 0xed, 0x0e \ - } + .guid = UUID_LE(0xf8615163, 0xdf3e, 0x46c5, 0x91, 0x3f, \ + 0xf2, 0xd2, 0xf9, 0x65, 0xed, 0x0e) /* * IDE GUID * {32412632-86cb-44a2-9b5c-50d1417354f5} */ #define HV_IDE_GUID \ - .guid = { \ - 0x32, 0x26, 0x41, 0x32, 0xcb, 0x86, 0xa2, 0x44, \ - 0x9b, 0x5c, 0x50, 0xd1, 0x41, 0x73, 0x54, 0xf5 \ - } + .guid = UUID_LE(0x32412632, 0x86cb, 0x44a2, 0x9b, 0x5c, \ + 0x50, 0xd1, 0x41, 0x73, 0x54, 0xf5) /* * SCSI GUID * {ba6163d9-04a1-4d29-b605-72e2ffb1dc7f} */ #define HV_SCSI_GUID \ - .guid = { \ - 0xd9, 0x63, 0x61, 0xba, 0xa1, 0x04, 0x29, 0x4d, \ - 0xb6, 0x05, 0x72, 0xe2, 0xff, 0xb1, 0xdc, 0x7f \ - } + .guid = UUID_LE(0xba6163d9, 0x04a1, 0x4d29, 0xb6, 0x05, \ + 0x72, 0xe2, 0xff, 0xb1, 0xdc, 0x7f) /* * Shutdown GUID * {0e0b6031-5213-4934-818b-38d90ced39db} */ #define HV_SHUTDOWN_GUID \ - .guid = { \ - 0x31, 0x60, 0x0b, 0x0e, 0x13, 0x52, 0x34, 0x49, \ - 0x81, 0x8b, 0x38, 0xd9, 0x0c, 0xed, 0x39, 0xdb \ - } + .guid = UUID_LE(0x0e0b6031, 0x5213, 0x4934, 0x81, 0x8b, \ + 0x38, 0xd9, 0x0c, 0xed, 0x39, 0xdb) /* * Time Synch GUID * {9527E630-D0AE-497b-ADCE-E80AB0175CAF} */ #define HV_TS_GUID \ - .guid = { \ - 0x30, 0xe6, 0x27, 0x95, 0xae, 0xd0, 0x7b, 0x49, \ - 0xad, 0xce, 0xe8, 0x0a, 0xb0, 0x17, 0x5c, 0xaf \ - } + .guid = UUID_LE(0x9527e630, 0xd0ae, 0x497b, 0xad, 0xce, \ + 0xe8, 0x0a, 0xb0, 0x17, 0x5c, 0xaf) /* * Heartbeat GUID * {57164f39-9115-4e78-ab55-382f3bd5422d} */ #define HV_HEART_BEAT_GUID \ - .guid = { \ - 0x39, 0x4f, 0x16, 0x57, 0x15, 0x91, 0x78, 0x4e, \ - 0xab, 0x55, 0x38, 0x2f, 0x3b, 0xd5, 0x42, 0x2d \ - } + .guid = UUID_LE(0x57164f39, 0x9115, 0x4e78, 0xab, 0x55, \ + 0x38, 0x2f, 0x3b, 0xd5, 0x42, 0x2d) /* * KVP GUID * {a9a0f4e7-5a45-4d96-b827-8a841e8c03e6} */ #define HV_KVP_GUID \ - .guid = { \ - 0xe7, 0xf4, 0xa0, 0xa9, 0x45, 0x5a, 0x96, 0x4d, \ - 0xb8, 0x27, 0x8a, 0x84, 0x1e, 0x8c, 0x3, 0xe6 \ - } + .guid = UUID_LE(0xa9a0f4e7, 0x5a45, 0x4d96, 0xb8, 0x27, \ + 0x8a, 0x84, 0x1e, 0x8c, 0x03, 0xe6) /* * Dynamic memory GUID * {525074dc-8985-46e2-8057-a307dc18a502} */ #define HV_DM_GUID \ - .guid = { \ - 0xdc, 0x74, 0x50, 0X52, 0x85, 0x89, 0xe2, 0x46, \ - 0x80, 0x57, 0xa3, 0x07, 0xdc, 0x18, 0xa5, 0x02 \ - } + .guid = UUID_LE(0x525074dc, 0x8985, 0x46e2, 0x80, 0x57, \ + 0xa3, 0x07, 0xdc, 0x18, 0xa5, 0x02) /* * Mouse GUID * {cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a} */ #define HV_MOUSE_GUID \ - .guid = { \ - 0x9e, 0xb6, 0xa8, 0xcf, 0x4a, 0x5b, 0xc0, 0x4c, \ - 0xb9, 0x8b, 0x8b, 0xa1, 0xa1, 0xf3, 0xf9, 0x5a \ - } + .guid = UUID_LE(0xcfa8b69e, 0x5b4a, 0x4cc0, 0xb9, 0x8b, \ + 0x8b, 0xa1, 0xa1, 0xf3, 0xf9, 0x5a) /* * VSS (Backup/Restore) GUID */ #define HV_VSS_GUID \ - .guid = { \ - 0x29, 0x2e, 0xfa, 0x35, 0x23, 0xea, 0x36, 0x42, \ - 0x96, 0xae, 0x3a, 0x6e, 0xba, 0xcb, 0xa4, 0x40 \ - } + .guid = UUID_LE(0x35fa2e29, 0xea23, 0x4236, 0x96, 0xae, \ + 0x3a, 0x6e, 0xba, 0xcb, 0xa4, 0x40) /* * Synthetic Video GUID * {DA0A7802-E377-4aac-8E77-0558EB1073F8} */ #define HV_SYNTHVID_GUID \ - .guid = { \ - 0x02, 0x78, 0x0a, 0xda, 0x77, 0xe3, 0xac, 0x4a, \ - 0x8e, 0x77, 0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8 \ - } + .guid = UUID_LE(0xda0a7802, 0xe377, 0x4aac, 0x8e, 0x77, \ + 0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8) /* * Synthetic FC GUID * {2f9bcc4a-0069-4af3-b76b-6fd0be528cda} */ #define HV_SYNTHFC_GUID \ - .guid = { \ - 0x4A, 0xCC, 0x9B, 0x2F, 0x69, 0x00, 0xF3, 0x4A, \ - 0xB7, 0x6B, 0x6F, 0xD0, 0xBE, 0x52, 0x8C, 0xDA \ - } + .guid = UUID_LE(0x2f9bcc4a, 0x0069, 0x4af3, 0xb7, 0x6b, \ + 0x6f, 0xd0, 0xbe, 0x52, 0x8c, 0xda) /* * Guest File Copy Service @@ -1125,20 +1103,16 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); */ #define HV_FCOPY_GUID \ - .guid = { \ - 0xE3, 0x4B, 0xD1, 0x34, 0xE4, 0xDE, 0xC8, 0x41, \ - 0x9A, 0xE7, 0x6B, 0x17, 0x49, 0x77, 0xC1, 0x92 \ - } + .guid = UUID_LE(0x34d14be3, 0xdee4, 0x41c8, 0x9a, 0xe7, \ + 0x6b, 0x17, 0x49, 0x77, 0xc1, 0x92) /* * NetworkDirect. This is the guest RDMA service. * {8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501} */ #define HV_ND_GUID \ - .guid = { \ - 0x3d, 0xaf, 0x2e, 0x8c, 0xa7, 0x32, 0x09, 0x4b, \ - 0xab, 0x99, 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01 \ - } + .guid = UUID_LE(0x8c2eaf3d, 0x32a7, 0x4b09, 0xab, 0x99, \ + 0xbd, 0x1f, 0x1c, 0x86, 0xb5, 0x01) /* * PCI Express Pass Through @@ -1146,10 +1120,8 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); */ #define HV_PCIE_GUID \ - .guid = { \ - 0x1D, 0xF6, 0xC4, 0x44, 0x44, 0x44, 0x00, 0x44, \ - 0x9D, 0x52, 0x80, 0x2E, 0x27, 0xED, 0xE1, 0x9F \ - } + .guid = UUID_LE(0x44c4f61d, 0x4444, 0x4400, 0x9d, 0x52, \ + 0x80, 0x2e, 0x27, 0xed, 0xe1, 0x9f) /* * Common header for Hyper-V ICs diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 64f36e09a790..6e4c645e1c0d 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -404,7 +404,7 @@ struct virtio_device_id { * For Hyper-V devices we use the device guid as the id. */ struct hv_vmbus_device_id { - __u8 guid[16]; + uuid_le guid; kernel_ulong_t driver_data; /* Data private to the driver */ }; diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5b96206e9aab..8adca4406198 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -917,7 +917,7 @@ static int do_vmbus_entry(const char *filename, void *symval, char guid_name[(sizeof(*guid) + 1) * 2]; for (i = 0; i < (sizeof(*guid) * 2); i += 2) - sprintf(&guid_name[i], "%02x", TO_NATIVE((*guid)[i/2])); + sprintf(&guid_name[i], "%02x", TO_NATIVE((guid->b)[i/2])); strcpy(alias, "vmbus:"); strcat(alias, guid_name); -- cgit v1.2.3 From 90e031fa06ad6b660a8e9bebbb80bd30e555a2a5 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Mon, 14 Dec 2015 16:01:45 -0800 Subject: Drivers: hv: vmbus: Get rid of the unused macro The macro VMBUS_DEVICE() is unused; get rid of it. Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b9f3bb25d8b4..f773a6871f4c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -986,19 +986,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, int vmbus_cpu_number_to_vp_number(int cpu_number); u64 hv_do_hypercall(u64 control, void *input, void *output); -/** - * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device - * - * This macro is used to create a struct hv_vmbus_device_id that matches a - * specific device. - */ -#define VMBUS_DEVICE(g0, g1, g2, g3, g4, g5, g6, g7, \ - g8, g9, ga, gb, gc, gd, ge, gf) \ - .guid = { g0, g1, g2, g3, g4, g5, g6, g7, \ - g8, g9, ga, gb, gc, gd, ge, gf }, - - - /* * GUID definitions of various offer types - services offered to the guest. */ -- cgit v1.2.3 From 8599846d73997cdbccf63f23394d871cfad1e5e6 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Mon, 14 Dec 2015 16:01:54 -0800 Subject: Drivers: hv: vmbus: Fix a Host signaling bug Currently we have two policies for deciding when to signal the host: One based on the ring buffer state and the other based on what the VMBUS client driver wants to do. Consider the case when the client wants to explicitly control when to signal the host. In this case, if the client were to defer signaling, we will not be able to signal the host subsequently when the client does want to signal since the ring buffer state will prevent the signaling. Implement logic to have only one signaling policy in force for a given channel. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Tested-by: Haiyang Zhang Cc: # v4.2+ Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 18 ++++++++++++++++++ include/linux/hyperv.h | 18 ++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 77d2579d6124..2889d97c03b1 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -653,10 +653,19 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer, * on the ring. We will not signal if more data is * to be placed. * + * Based on the channel signal state, we will decide + * which signaling policy will be applied. + * * If we cannot write to the ring-buffer; signal the host * even if we may not have written anything. This is a rare * enough condition that it should not matter. */ + + if (channel->signal_policy) + signal = true; + else + kick_q = true; + if (((ret == 0) && kick_q && signal) || (ret)) vmbus_setevent(channel); @@ -756,10 +765,19 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, * on the ring. We will not signal if more data is * to be placed. * + * Based on the channel signal state, we will decide + * which signaling policy will be applied. + * * If we cannot write to the ring-buffer; signal the host * even if we may not have written anything. This is a rare * enough condition that it should not matter. */ + + if (channel->signal_policy) + signal = true; + else + kick_q = true; + if (((ret == 0) && kick_q && signal) || (ret)) vmbus_setevent(channel); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f773a6871f4c..acd995b81c6b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -630,6 +630,11 @@ struct hv_input_signal_event_buffer { struct hv_input_signal_event event; }; +enum hv_signal_policy { + HV_SIGNAL_POLICY_DEFAULT = 0, + HV_SIGNAL_POLICY_EXPLICIT, +}; + struct vmbus_channel { /* Unique channel id */ int id; @@ -757,8 +762,21 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; + /* + * Host signaling policy: The default policy will be + * based on the ring buffer state. We will also support + * a policy where the client driver can have explicit + * signaling control. + */ + enum hv_signal_policy signal_policy; }; +static inline void set_channel_signal_state(struct vmbus_channel *c, + enum hv_signal_policy policy) +{ + c->signal_policy = policy; +} + static inline void set_channel_read_state(struct vmbus_channel *c, bool state) { c->batched_reading = state; -- cgit v1.2.3 From 45870a441361d1c05a5f767c4ece2f6e30e0da9c Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 14 Dec 2015 19:01:58 -0800 Subject: Drivers: hv: ring_buffer: remove stray smp_read_barrier_depends() smp_read_barrier_depends() does nothing on almost all arcitectures including x86 and having it in the beginning of hv_get_ringbuffer_availbytes() does not provide any guarantees anyway. Signed-off-by: Vitaly Kuznetsov Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index acd995b81c6b..179ff330af59 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -141,8 +141,6 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, { u32 read_loc, write_loc, dsize; - smp_read_barrier_depends(); - /* Capture the read/write indices before they changed */ read_loc = rbi->ring_buffer->read_index; write_loc = rbi->ring_buffer->write_index; -- cgit v1.2.3 From 51f141a97a1406bb0b59d490e837a39ccb7c3999 Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 18 Nov 2015 14:34:09 +0900 Subject: usb: renesas_usbhs: Modify pipe configuration The current code has info->bufnmb_last to calculate the BUFNMB bits of PIPEBUF register. However, since the bufnmb_last is initialized in the usbhs_pipe_init() only, this driver is possible to set unexpected value to the register if usb_ep_{enable,disable}() are called many times. So, this patch modifies the pipe configuration via struct renesas_usbhs_driver_param to simplify the code. Also this patch changes: - a double buffer configuration - isochronous buffer size from 512 to 1024 Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- drivers/usb/renesas_usbhs/common.c | 69 +++++++++++---------- drivers/usb/renesas_usbhs/mod_host.c | 11 ++-- drivers/usb/renesas_usbhs/pipe.c | 112 ++++++++--------------------------- drivers/usb/renesas_usbhs/pipe.h | 1 - include/linux/usb/renesas_usbhs.h | 18 +++++- 5 files changed, 82 insertions(+), 129 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index d82fa36c3465..7ccc2fe4f6ec 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -302,37 +302,37 @@ static void usbhsc_set_buswait(struct usbhs_priv *priv) */ /* commonly used on old SH-Mobile SoCs */ -static u32 usbhsc_default_pipe_type[] = { - USB_ENDPOINT_XFER_CONTROL, - USB_ENDPOINT_XFER_ISOC, - USB_ENDPOINT_XFER_ISOC, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_INT, +static struct renesas_usbhs_driver_pipe_config usbhsc_default_pipe[] = { + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_CONTROL, 64, 0x00, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_ISOC, 1024, 0x08, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_ISOC, 1024, 0x18, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x28, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x38, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x48, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x04, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x05, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x06, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x07, false), }; /* commonly used on newer SH-Mobile and R-Car SoCs */ -static u32 usbhsc_new_pipe_type[] = { - USB_ENDPOINT_XFER_CONTROL, - USB_ENDPOINT_XFER_ISOC, - USB_ENDPOINT_XFER_ISOC, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_INT, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, - USB_ENDPOINT_XFER_BULK, +static struct renesas_usbhs_driver_pipe_config usbhsc_new_pipe[] = { + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_CONTROL, 64, 0x00, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_ISOC, 1024, 0x08, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_ISOC, 1024, 0x28, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x48, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x58, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x68, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x04, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x05, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_INT, 64, 0x06, false), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x78, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x88, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0x98, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0xa8, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0xb8, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0xc8, true), + RENESAS_USBHS_PIPE(USB_ENDPOINT_XFER_BULK, 512, 0xd8, true), }; /* @@ -564,10 +564,9 @@ static int usbhs_probe(struct platform_device *pdev) switch (priv->dparam.type) { case USBHS_TYPE_RCAR_GEN2: priv->pfunc = usbhs_rcar2_ops; - if (!priv->dparam.pipe_type) { - priv->dparam.pipe_type = usbhsc_new_pipe_type; - priv->dparam.pipe_size = - ARRAY_SIZE(usbhsc_new_pipe_type); + if (!priv->dparam.pipe_configs) { + priv->dparam.pipe_configs = usbhsc_new_pipe; + priv->dparam.pipe_size = ARRAY_SIZE(usbhsc_new_pipe); } break; default: @@ -586,9 +585,9 @@ static int usbhs_probe(struct platform_device *pdev) dfunc->notify_hotplug = usbhsc_drvcllbck_notify_hotplug; /* set default param if platform doesn't have */ - if (!priv->dparam.pipe_type) { - priv->dparam.pipe_type = usbhsc_default_pipe_type; - priv->dparam.pipe_size = ARRAY_SIZE(usbhsc_default_pipe_type); + if (!priv->dparam.pipe_configs) { + priv->dparam.pipe_configs = usbhsc_default_pipe; + priv->dparam.pipe_size = ARRAY_SIZE(usbhsc_default_pipe); } if (!priv->dparam.pio_dma_border) priv->dparam.pio_dma_border = 64; /* 64byte */ diff --git a/drivers/usb/renesas_usbhs/mod_host.c b/drivers/usb/renesas_usbhs/mod_host.c index bd050359926c..1a8e4c45c4c5 100644 --- a/drivers/usb/renesas_usbhs/mod_host.c +++ b/drivers/usb/renesas_usbhs/mod_host.c @@ -1414,7 +1414,8 @@ static void usbhsh_pipe_init_for_host(struct usbhs_priv *priv) { struct usbhsh_hpriv *hpriv = usbhsh_priv_to_hpriv(priv); struct usbhs_pipe *pipe; - u32 *pipe_type = usbhs_get_dparam(priv, pipe_type); + struct renesas_usbhs_driver_pipe_config *pipe_configs = + usbhs_get_dparam(priv, pipe_configs); int pipe_size = usbhs_get_dparam(priv, pipe_size); int old_type, dir_in, i; @@ -1442,15 +1443,15 @@ static void usbhsh_pipe_init_for_host(struct usbhs_priv *priv) * USB_ENDPOINT_XFER_BULK -> dir in * ... */ - dir_in = (pipe_type[i] == old_type); - old_type = pipe_type[i]; + dir_in = (pipe_configs[i].type == old_type); + old_type = pipe_configs[i].type; - if (USB_ENDPOINT_XFER_CONTROL == pipe_type[i]) { + if (USB_ENDPOINT_XFER_CONTROL == pipe_configs[i].type) { pipe = usbhs_dcp_malloc(priv); usbhsh_hpriv_to_dcp(hpriv) = pipe; } else { pipe = usbhs_pipe_malloc(priv, - pipe_type[i], + pipe_configs[i].type, dir_in); } diff --git a/drivers/usb/renesas_usbhs/pipe.c b/drivers/usb/renesas_usbhs/pipe.c index 4f9c3356127a..0e95d2925dc5 100644 --- a/drivers/usb/renesas_usbhs/pipe.c +++ b/drivers/usb/renesas_usbhs/pipe.c @@ -44,6 +44,15 @@ char *usbhs_pipe_name(struct usbhs_pipe *pipe) return usbhsp_pipe_name[usbhs_pipe_type(pipe)]; } +static struct renesas_usbhs_driver_pipe_config +*usbhsp_get_pipe_config(struct usbhs_priv *priv, int pipe_num) +{ + struct renesas_usbhs_driver_pipe_config *pipe_configs = + usbhs_get_dparam(priv, pipe_configs); + + return &pipe_configs[pipe_num]; +} + /* * DCPCTR/PIPEnCTR functions */ @@ -384,18 +393,6 @@ void usbhs_pipe_set_trans_count_if_bulk(struct usbhs_pipe *pipe, int len) /* * pipe setup */ -static int usbhsp_possible_double_buffer(struct usbhs_pipe *pipe) -{ - /* - * only ISO / BULK pipe can use double buffer - */ - if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_BULK) || - usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC)) - return 1; - - return 0; -} - static u16 usbhsp_setup_pipecfg(struct usbhs_pipe *pipe, int is_host, int dir_in) @@ -412,7 +409,6 @@ static u16 usbhsp_setup_pipecfg(struct usbhs_pipe *pipe, [USB_ENDPOINT_XFER_INT] = TYPE_INT, [USB_ENDPOINT_XFER_ISOC] = TYPE_ISO, }; - int is_double = usbhsp_possible_double_buffer(pipe); if (usbhs_pipe_is_dcp(pipe)) return -EINVAL; @@ -434,10 +430,7 @@ static u16 usbhsp_setup_pipecfg(struct usbhs_pipe *pipe, usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_BULK)) bfre = 0; /* FIXME */ - /* DBLB */ - if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC) || - usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_BULK)) - dblb = (is_double) ? DBLB : 0; + /* DBLB: see usbhs_pipe_config_update() */ /* CNTMD */ if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_BULK)) @@ -473,13 +466,13 @@ static u16 usbhsp_setup_pipecfg(struct usbhs_pipe *pipe, static u16 usbhsp_setup_pipebuff(struct usbhs_pipe *pipe) { struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); - struct usbhs_pipe_info *info = usbhs_priv_to_pipeinfo(priv); struct device *dev = usbhs_priv_to_dev(priv); int pipe_num = usbhs_pipe_number(pipe); - int is_double = usbhsp_possible_double_buffer(pipe); u16 buff_size; u16 bufnmb; u16 bufnmb_cnt; + struct renesas_usbhs_driver_pipe_config *pipe_config = + usbhsp_get_pipe_config(priv, pipe_num); /* * PIPEBUF @@ -489,56 +482,13 @@ static u16 usbhsp_setup_pipebuff(struct usbhs_pipe *pipe) * - "Features" - "Pipe configuration" * - "Operation" - "FIFO Buffer Memory" * - "Operation" - "Pipe Control" - * - * ex) if pipe6 - pipe9 are USB_ENDPOINT_XFER_INT (SH7724) - * - * BUFNMB: PIPE - * 0: pipe0 (DCP 256byte) - * 1: - - * 2: - - * 3: - - * 4: pipe6 (INT 64byte) - * 5: pipe7 (INT 64byte) - * 6: pipe8 (INT 64byte) - * 7: pipe9 (INT 64byte) - * 8 - xx: free (for BULK, ISOC) */ - - /* - * FIXME - * - * it doesn't have good buffer allocator - * - * DCP : 256 byte - * BULK: 512 byte - * INT : 64 byte - * ISOC: 512 byte - */ - if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_CONTROL)) - buff_size = 256; - else if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_INT)) - buff_size = 64; - else - buff_size = 512; + buff_size = pipe_config->bufsize; + bufnmb = pipe_config->bufnum; /* change buff_size to register value */ bufnmb_cnt = (buff_size / 64) - 1; - /* BUFNMB has been reserved for INT pipe - * see above */ - if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_INT)) { - bufnmb = pipe_num - 2; - } else { - bufnmb = info->bufnmb_last; - info->bufnmb_last += bufnmb_cnt + 1; - - /* - * double buffer - */ - if (is_double) - info->bufnmb_last += bufnmb_cnt + 1; - } - dev_dbg(dev, "pipe : %d : buff_size 0x%x: bufnmb 0x%x\n", pipe_num, buff_size, bufnmb); @@ -549,8 +499,13 @@ static u16 usbhsp_setup_pipebuff(struct usbhs_pipe *pipe) void usbhs_pipe_config_update(struct usbhs_pipe *pipe, u16 devsel, u16 epnum, u16 maxp) { + struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); + int pipe_num = usbhs_pipe_number(pipe); + struct renesas_usbhs_driver_pipe_config *pipe_config = + usbhsp_get_pipe_config(priv, pipe_num); + u16 dblb = pipe_config->double_buf ? DBLB : 0; + if (devsel > 0xA) { - struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe); struct device *dev = usbhs_priv_to_dev(priv); dev_err(dev, "devsel error %d\n", devsel); @@ -568,7 +523,7 @@ void usbhs_pipe_config_update(struct usbhs_pipe *pipe, u16 devsel, maxp); if (!usbhs_pipe_is_dcp(pipe)) - usbhsp_pipe_cfg_set(pipe, 0x000F, epnum); + usbhsp_pipe_cfg_set(pipe, 0x000F | DBLB, epnum | dblb); } /* @@ -708,23 +663,7 @@ void usbhs_pipe_init(struct usbhs_priv *priv, struct usbhs_pipe *pipe; int i; - /* - * FIXME - * - * driver needs good allocator. - * - * find first free buffer area (BULK, ISOC) - * (DCP, INT area is fixed) - * - * buffer number 0 - 3 have been reserved for DCP - * see - * usbhsp_to_bufnmb - */ - info->bufnmb_last = 4; usbhs_for_each_pipe_with_dcp(pipe, priv, i) { - if (usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_INT)) - info->bufnmb_last++; - usbhsp_flags_init(pipe); pipe->fifo = NULL; pipe->mod_private = NULL; @@ -851,12 +790,13 @@ int usbhs_pipe_probe(struct usbhs_priv *priv) struct usbhs_pipe_info *info = usbhs_priv_to_pipeinfo(priv); struct usbhs_pipe *pipe; struct device *dev = usbhs_priv_to_dev(priv); - u32 *pipe_type = usbhs_get_dparam(priv, pipe_type); + struct renesas_usbhs_driver_pipe_config *pipe_configs = + usbhs_get_dparam(priv, pipe_configs); int pipe_size = usbhs_get_dparam(priv, pipe_size); int i; /* This driver expects 1st pipe is DCP */ - if (pipe_type[0] != USB_ENDPOINT_XFER_CONTROL) { + if (pipe_configs[0].type != USB_ENDPOINT_XFER_CONTROL) { dev_err(dev, "1st PIPE is not DCP\n"); return -EINVAL; } @@ -876,10 +816,10 @@ int usbhs_pipe_probe(struct usbhs_priv *priv) pipe->priv = priv; usbhs_pipe_type(pipe) = - pipe_type[i] & USB_ENDPOINT_XFERTYPE_MASK; + pipe_configs[i].type & USB_ENDPOINT_XFERTYPE_MASK; dev_dbg(dev, "pipe %x\t: %s\n", - i, usbhsp_pipe_name[pipe_type[i]]); + i, usbhsp_pipe_name[pipe_configs[i].type]); } return 0; diff --git a/drivers/usb/renesas_usbhs/pipe.h b/drivers/usb/renesas_usbhs/pipe.h index b0bc7b603016..3212ab51e844 100644 --- a/drivers/usb/renesas_usbhs/pipe.h +++ b/drivers/usb/renesas_usbhs/pipe.h @@ -46,7 +46,6 @@ struct usbhs_pipe { struct usbhs_pipe_info { struct usbhs_pipe *pipe; int size; /* array size of "pipe" */ - int bufnmb_last; /* FIXME : driver needs good allocator */ int (*dma_map_ctrl)(struct usbhs_pkt *pkt, int map); }; diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index bfb74723f151..4db191fe8c2c 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -105,12 +105,26 @@ struct renesas_usbhs_platform_callback { * some register needs USB chip specific parameters. * This struct show it to driver */ + +struct renesas_usbhs_driver_pipe_config { + u8 type; /* USB_ENDPOINT_XFER_xxx */ + u16 bufsize; + u8 bufnum; + bool double_buf; +}; +#define RENESAS_USBHS_PIPE(_type, _size, _num, _double_buf) { \ + .type = (_type), \ + .bufsize = (_size), \ + .bufnum = (_num), \ + .double_buf = (_double_buf), \ + } + struct renesas_usbhs_driver_param { /* * pipe settings */ - u32 *pipe_type; /* array of USB_ENDPOINT_XFER_xxx (from ep0) */ - int pipe_size; /* pipe_type array size */ + struct renesas_usbhs_driver_pipe_config *pipe_configs; + int pipe_size; /* pipe_configs array size */ /* * option: -- cgit v1.2.3 From 98bfb39466954c69d2a448e6ddcab6d91cd48e25 Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Tue, 3 Nov 2015 11:51:15 -0600 Subject: usb: of: add an api to get dr_mode by the phy node Some USB phy drivers have different handling for the controller in each dr_mode. But the phy driver does not have visibility to the dr_mode of the controller. This adds an api to return the dr_mode of the controller which associates the given phy node. Signed-off-by: Bin Liu Signed-off-by: Felipe Balbi --- drivers/usb/common/common.c | 60 ++++++++++++++++++++++++++++++++++++++++----- include/linux/usb/of.h | 5 ++++ 2 files changed, 59 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 673d53038ed2..e6ec125e4485 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -17,6 +17,7 @@ #include #include #include +#include const char *usb_otg_state_string(enum usb_otg_state state) { @@ -106,24 +107,71 @@ static const char *const usb_dr_modes[] = { [USB_DR_MODE_OTG] = "otg", }; +static enum usb_dr_mode usb_get_dr_mode_from_string(const char *str) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(usb_dr_modes); i++) + if (!strcmp(usb_dr_modes[i], str)) + return i; + + return USB_DR_MODE_UNKNOWN; +} + enum usb_dr_mode usb_get_dr_mode(struct device *dev) { const char *dr_mode; - int err, i; + int err; err = device_property_read_string(dev, "dr_mode", &dr_mode); if (err < 0) return USB_DR_MODE_UNKNOWN; - for (i = 0; i < ARRAY_SIZE(usb_dr_modes); i++) - if (!strcmp(dr_mode, usb_dr_modes[i])) - return i; - - return USB_DR_MODE_UNKNOWN; + return usb_get_dr_mode_from_string(dr_mode); } EXPORT_SYMBOL_GPL(usb_get_dr_mode); #ifdef CONFIG_OF +/** + * of_usb_get_dr_mode_by_phy - Get dual role mode for the controller device + * which is associated with the given phy device_node + * @np: Pointer to the given phy device_node + * + * In dts a usb controller associates with phy devices. The function gets + * the string from property 'dr_mode' of the controller associated with the + * given phy device node, and returns the correspondig enum usb_dr_mode. + */ +enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np) +{ + struct device_node *controller = NULL; + struct device_node *phy; + const char *dr_mode; + int index; + int err; + + do { + controller = of_find_node_with_property(controller, "phys"); + index = 0; + do { + phy = of_parse_phandle(controller, "phys", index); + of_node_put(phy); + if (phy == phy_np) + goto finish; + index++; + } while (phy); + } while (controller); + +finish: + err = of_property_read_string(controller, "dr_mode", &dr_mode); + of_node_put(controller); + + if (err < 0) + return USB_DR_MODE_UNKNOWN; + + return usb_get_dr_mode_from_string(dr_mode); +} +EXPORT_SYMBOL_GPL(of_usb_get_dr_mode_by_phy); + /** * of_usb_host_tpl_support - to get if Targeted Peripheral List is supported * for given targeted hosts (non-PC hosts) diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index c3fe9e48ce27..3805757dcdc2 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -12,10 +12,15 @@ #include #if IS_ENABLED(CONFIG_OF) +enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np); bool of_usb_host_tpl_support(struct device_node *np); int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps); #else +enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np) +{ + return USB_DR_MODE_UNKNOWN; +} static inline bool of_usb_host_tpl_support(struct device_node *np) { return false; -- cgit v1.2.3 From 375da6271b685e97d2d936fffa6e405b93674c26 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 4 Dec 2015 17:04:25 +0100 Subject: usb: phy: Remove unused Renesas R-Car (Gen1) USB PHY driver As of commit 3d7608e4c169af03 ("ARM: shmobile: bockw: remove legacy board file and config"), the Renesas R-Car (Gen1) USB PHY driver is no longer used. In theory it could still be used on R-Car Gen1 SoCs, but that would require adding DT support to the driver. Instead, a new driver using the generic PHY framework should be written, as was done for R-Car Gen2. Remove the driver for good. Acked-by: Simon Horman Signed-off-by: Geert Uytterhoeven Signed-off-by: Felipe Balbi --- drivers/usb/phy/Kconfig | 13 -- drivers/usb/phy/Makefile | 1 - drivers/usb/phy/phy-rcar-usb.c | 247 ----------------------------- include/linux/platform_data/usb-rcar-phy.h | 28 ---- 4 files changed, 289 deletions(-) delete mode 100644 drivers/usb/phy/phy-rcar-usb.c delete mode 100644 include/linux/platform_data/usb-rcar-phy.h (limited to 'include/linux') diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index 22e8ecb6bfbd..155694c1a536 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -186,19 +186,6 @@ config USB_MXS_PHY MXS Phy is used by some of the i.MX SoCs, for example imx23/28/6x. -config USB_RCAR_PHY - tristate "Renesas R-Car USB PHY support" - depends on USB || USB_GADGET - depends on ARCH_R8A7778 || ARCH_R8A7779 || COMPILE_TEST - select USB_PHY - help - Say Y here to add support for the Renesas R-Car USB common PHY driver. - This chip is typically used as USB PHY for USB host, gadget. - This driver supports R8A7778 and R8A7779. - - To compile this driver as a module, choose M here: the - module will be called phy-rcar-usb. - config USB_ULPI bool "Generic ULPI Transceiver Driver" depends on ARM || ARM64 diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile index 19c0dccbb116..b433e5d89be4 100644 --- a/drivers/usb/phy/Makefile +++ b/drivers/usb/phy/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_USB_MSM_OTG) += phy-msm-usb.o obj-$(CONFIG_USB_QCOM_8X16_PHY) += phy-qcom-8x16-usb.o obj-$(CONFIG_USB_MV_OTG) += phy-mv-usb.o obj-$(CONFIG_USB_MXS_PHY) += phy-mxs-usb.o -obj-$(CONFIG_USB_RCAR_PHY) += phy-rcar-usb.o obj-$(CONFIG_USB_ULPI) += phy-ulpi.o obj-$(CONFIG_USB_ULPI_VIEWPORT) += phy-ulpi-viewport.o obj-$(CONFIG_KEYSTONE_USB_PHY) += phy-keystone.o diff --git a/drivers/usb/phy/phy-rcar-usb.c b/drivers/usb/phy/phy-rcar-usb.c deleted file mode 100644 index 1e09b8377885..000000000000 --- a/drivers/usb/phy/phy-rcar-usb.c +++ /dev/null @@ -1,247 +0,0 @@ -/* - * Renesas R-Car USB phy driver - * - * Copyright (C) 2012-2013 Renesas Solutions Corp. - * Kuninori Morimoto - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * 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. - */ - -#include -#include -#include -#include -#include -#include -#include - -/* REGS block */ -#define USBPCTRL0 0x00 -#define USBPCTRL1 0x04 -#define USBST 0x08 -#define USBEH0 0x0C -#define USBOH0 0x1C -#define USBCTL0 0x58 - -/* High-speed signal quality characteristic control registers (R8A7778 only) */ -#define HSQCTL1 0x24 -#define HSQCTL2 0x28 - -/* USBPCTRL0 */ -#define OVC2 (1 << 10) /* (R8A7779 only) */ - /* Switches the OVC input pin for port 2: */ - /* 1: USB_OVC2, 0: OVC2 */ -#define OVC1_VBUS1 (1 << 9) /* Switches the OVC input pin for port 1: */ - /* 1: USB_OVC1, 0: OVC1/VBUS1 */ - /* Function mode: set to 0 */ -#define OVC0 (1 << 8) /* Switches the OVC input pin for port 0: */ - /* 1: USB_OVC0 pin, 0: OVC0 */ -#define OVC2_ACT (1 << 6) /* (R8A7779 only) */ - /* Host mode: OVC2 polarity: */ - /* 1: active-high, 0: active-low */ -#define PENC (1 << 4) /* Function mode: output level of PENC1 pin: */ - /* 1: high, 0: low */ -#define OVC0_ACT (1 << 3) /* Host mode: OVC0 polarity: */ - /* 1: active-high, 0: active-low */ -#define OVC1_ACT (1 << 1) /* Host mode: OVC1 polarity: */ - /* 1: active-high, 0: active-low */ - /* Function mode: be sure to set to 1 */ -#define PORT1 (1 << 0) /* Selects port 1 mode: */ - /* 1: function, 0: host */ -/* USBPCTRL1 */ -#define PHY_RST (1 << 2) -#define PLL_ENB (1 << 1) -#define PHY_ENB (1 << 0) - -/* USBST */ -#define ST_ACT (1 << 31) -#define ST_PLL (1 << 30) - -struct rcar_usb_phy_priv { - struct usb_phy phy; - spinlock_t lock; - - void __iomem *reg0; - void __iomem *reg1; - int counter; -}; - -#define usb_phy_to_priv(p) container_of(p, struct rcar_usb_phy_priv, phy) - - -/* - * USB initial/install operation. - * - * This function setup USB phy. - * The used value and setting order came from - * [USB :: Initial setting] on datasheet. - */ -static int rcar_usb_phy_init(struct usb_phy *phy) -{ - struct rcar_usb_phy_priv *priv = usb_phy_to_priv(phy); - struct device *dev = phy->dev; - struct rcar_phy_platform_data *pdata = dev_get_platdata(dev); - void __iomem *reg0 = priv->reg0; - void __iomem *reg1 = priv->reg1; - static const u8 ovcn_act[] = { OVC0_ACT, OVC1_ACT, OVC2_ACT }; - int i; - u32 val; - unsigned long flags; - - spin_lock_irqsave(&priv->lock, flags); - if (priv->counter++ == 0) { - - /* - * USB phy start-up - */ - - /* (1) USB-PHY standby release */ - iowrite32(PHY_ENB, (reg0 + USBPCTRL1)); - - /* (2) start USB-PHY internal PLL */ - iowrite32(PHY_ENB | PLL_ENB, (reg0 + USBPCTRL1)); - - /* (3) set USB-PHY in accord with the conditions of usage */ - if (reg1) { - u32 hsqctl1 = pdata->ferrite_bead ? 0x41 : 0; - u32 hsqctl2 = pdata->ferrite_bead ? 0x0d : 7; - - iowrite32(hsqctl1, reg1 + HSQCTL1); - iowrite32(hsqctl2, reg1 + HSQCTL2); - } - - /* (4) USB module status check */ - for (i = 0; i < 1024; i++) { - udelay(10); - val = ioread32(reg0 + USBST); - if (val == (ST_ACT | ST_PLL)) - break; - } - - if (val != (ST_ACT | ST_PLL)) { - dev_err(dev, "USB phy not ready\n"); - goto phy_init_end; - } - - /* (5) USB-PHY reset clear */ - iowrite32(PHY_ENB | PLL_ENB | PHY_RST, (reg0 + USBPCTRL1)); - - /* Board specific port settings */ - val = 0; - if (pdata->port1_func) - val |= PORT1; - if (pdata->penc1) - val |= PENC; - for (i = 0; i < 3; i++) { - /* OVCn bits follow each other in the right order */ - if (pdata->ovc_pin[i].select_3_3v) - val |= OVC0 << i; - /* OVCn_ACT bits are spaced by irregular intervals */ - if (pdata->ovc_pin[i].active_high) - val |= ovcn_act[i]; - } - iowrite32(val, (reg0 + USBPCTRL0)); - - /* - * Bus alignment settings - */ - - /* (1) EHCI bus alignment (little endian) */ - iowrite32(0x00000000, (reg0 + USBEH0)); - - /* (1) OHCI bus alignment (little endian) */ - iowrite32(0x00000000, (reg0 + USBOH0)); - } - -phy_init_end: - spin_unlock_irqrestore(&priv->lock, flags); - - return 0; -} - -static void rcar_usb_phy_shutdown(struct usb_phy *phy) -{ - struct rcar_usb_phy_priv *priv = usb_phy_to_priv(phy); - void __iomem *reg0 = priv->reg0; - unsigned long flags; - - spin_lock_irqsave(&priv->lock, flags); - - if (priv->counter-- == 1) /* last user */ - iowrite32(0x00000000, (reg0 + USBPCTRL1)); - - spin_unlock_irqrestore(&priv->lock, flags); -} - -static int rcar_usb_phy_probe(struct platform_device *pdev) -{ - struct rcar_usb_phy_priv *priv; - struct resource *res0, *res1; - struct device *dev = &pdev->dev; - void __iomem *reg0, *reg1 = NULL; - int ret; - - if (!dev_get_platdata(&pdev->dev)) { - dev_err(dev, "No platform data\n"); - return -EINVAL; - } - - res0 = platform_get_resource(pdev, IORESOURCE_MEM, 0); - reg0 = devm_ioremap_resource(dev, res0); - if (IS_ERR(reg0)) - return PTR_ERR(reg0); - - res1 = platform_get_resource(pdev, IORESOURCE_MEM, 1); - reg1 = devm_ioremap_resource(dev, res1); - if (IS_ERR(reg1)) - return PTR_ERR(reg1); - - priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - priv->reg0 = reg0; - priv->reg1 = reg1; - priv->counter = 0; - priv->phy.dev = dev; - priv->phy.label = dev_name(dev); - priv->phy.init = rcar_usb_phy_init; - priv->phy.shutdown = rcar_usb_phy_shutdown; - spin_lock_init(&priv->lock); - - ret = usb_add_phy(&priv->phy, USB_PHY_TYPE_USB2); - if (ret < 0) { - dev_err(dev, "usb phy addition error\n"); - return ret; - } - - platform_set_drvdata(pdev, priv); - - return ret; -} - -static int rcar_usb_phy_remove(struct platform_device *pdev) -{ - struct rcar_usb_phy_priv *priv = platform_get_drvdata(pdev); - - usb_remove_phy(&priv->phy); - - return 0; -} - -static struct platform_driver rcar_usb_phy_driver = { - .driver = { - .name = "rcar_usb_phy", - }, - .probe = rcar_usb_phy_probe, - .remove = rcar_usb_phy_remove, -}; - -module_platform_driver(rcar_usb_phy_driver); - -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Renesas R-Car USB phy"); -MODULE_AUTHOR("Kuninori Morimoto "); diff --git a/include/linux/platform_data/usb-rcar-phy.h b/include/linux/platform_data/usb-rcar-phy.h deleted file mode 100644 index 8ec6964a32a5..000000000000 --- a/include/linux/platform_data/usb-rcar-phy.h +++ /dev/null @@ -1,28 +0,0 @@ -/* - * Copyright (C) 2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc. - * - * 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 __USB_RCAR_PHY_H -#define __USB_RCAR_PHY_H - -#include - -struct rcar_phy_platform_data { - bool ferrite_bead:1; /* (R8A7778 only) */ - - bool port1_func:1; /* true: port 1 used by function, false: host */ - unsigned penc1:1; /* Output of the PENC1 pin in function mode */ - struct { /* Overcurrent pin control for ports 0..2 */ - bool select_3_3v:1; /* true: USB_OVCn pin, false: OVCn pin */ - /* Set to false on port 1 in function mode */ - bool active_high:1; /* true: active high, false: active low */ - /* Set to true on port 1 in function mode */ - } ovc_pin[3]; /* (R8A7778 only has 2 ports) */ -}; - -#endif /* __USB_RCAR_PHY_H */ -- cgit v1.2.3 From 2284b29d3d9dd16490909962574d7f3fef83fd97 Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Mon, 23 Nov 2015 09:56:35 +0100 Subject: usb: gadget: bind UDC by name passed via usb_gadget_driver structure Introduce new 'udc_name' member to usb_gadget_driver structure. The 'udc_name' is a name of UDC that usb_gadget_driver should be bound to. If udc_name is NULL, it will be bound to any available UDC. Tested-by: Maxime Ripard Signed-off-by: Ruslan Bilovol Signed-off-by: Marek Szyprowski Tested-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 24 +++++++++++++++++++----- include/linux/usb/gadget.h | 4 ++++ 2 files changed, 23 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index f660afba715d..429d64e67941 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -549,21 +549,35 @@ EXPORT_SYMBOL_GPL(usb_udc_attach_driver); int usb_gadget_probe_driver(struct usb_gadget_driver *driver) { struct usb_udc *udc = NULL; - int ret; + int ret = -ENODEV; if (!driver || !driver->bind || !driver->setup) return -EINVAL; mutex_lock(&udc_lock); - list_for_each_entry(udc, &udc_list, list) { - /* For now we take the first one */ - if (!udc->driver) + if (driver->udc_name) { + list_for_each_entry(udc, &udc_list, list) { + ret = strcmp(driver->udc_name, dev_name(&udc->dev)); + if (!ret) + break; + } + if (ret) + ret = -ENODEV; + else if (udc->driver) + ret = -EBUSY; + else goto found; + } else { + list_for_each_entry(udc, &udc_list, list) { + /* For now we take the first one */ + if (!udc->driver) + goto found; + } } pr_debug("couldn't find an available UDC\n"); mutex_unlock(&udc_lock); - return -ENODEV; + return ret; found: ret = udc_bind_to_driver(udc, driver); mutex_unlock(&udc_lock); diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 3d583a10b926..63963c21866d 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1012,6 +1012,8 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget) * @reset: Invoked on USB bus reset. It is mandatory for all gadget drivers * and should be called in_interrupt. * @driver: Driver model state for this driver. + * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, + * this driver will be bound to any available UDC. * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -1072,6 +1074,8 @@ struct usb_gadget_driver { /* FIXME support safe rmmod */ struct device_driver driver; + + char *udc_name; }; -- cgit v1.2.3 From 88f73ebdfa75602af18e070a4d5d6d9091bcfada Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Mon, 23 Nov 2015 09:56:37 +0100 Subject: usb: gadget: udc-core: remove unused usb_udc_attach_driver() Now when last user of usb_udc_attach_driver() is switched to passing UDC name via usb_gadget_driver struct, it's safe to remove this function Tested-by: Maxime Ripard Signed-off-by: Ruslan Bilovol Signed-off-by: Marek Szyprowski Tested-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 26 -------------------------- include/linux/usb/gadget.h | 2 -- 2 files changed, 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index 429d64e67941..f76ebc8c1ed2 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -520,32 +520,6 @@ err1: return ret; } -int usb_udc_attach_driver(const char *name, struct usb_gadget_driver *driver) -{ - struct usb_udc *udc = NULL; - int ret = -ENODEV; - - mutex_lock(&udc_lock); - list_for_each_entry(udc, &udc_list, list) { - ret = strcmp(name, dev_name(&udc->dev)); - if (!ret) - break; - } - if (ret) { - ret = -ENODEV; - goto out; - } - if (udc->driver) { - ret = -EBUSY; - goto out; - } - ret = udc_bind_to_driver(udc, driver); -out: - mutex_unlock(&udc_lock); - return ret; -} -EXPORT_SYMBOL_GPL(usb_udc_attach_driver); - int usb_gadget_probe_driver(struct usb_gadget_driver *driver) { struct usb_udc *udc = NULL; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 63963c21866d..ce2188d338e6 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1121,8 +1121,6 @@ extern int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)); extern int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget); extern void usb_del_gadget_udc(struct usb_gadget *gadget); -extern int usb_udc_attach_driver(const char *name, - struct usb_gadget_driver *driver); /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 855ed04a3758b205e84b269f92d26ab36ed8e2f7 Mon Sep 17 00:00:00 2001 From: Ruslan Bilovol Date: Mon, 23 Nov 2015 09:56:38 +0100 Subject: usb: gadget: udc-core: independent registration of gadgets and gadget drivers Change behavior during registration of gadgets and gadget drivers in udc-core. Instead of previous approach when for successful probe of usb gadget driver at least one usb gadget should be already registered use another one where gadget drivers and gadgets can be registered in udc-core independently. Independent registration of gadgets and gadget drivers is useful for built-in into kernel gadget and gadget driver case - because it's possible that gadget is really probed only on late_init stage (due to deferred probe) whereas gadget driver's probe is silently failed on module_init stage due to no any UDC added. Also it is useful for modules case - now there is no difference what module to insert first: gadget module or gadget driver one. Tested-by: Maxime Ripard Signed-off-by: Ruslan Bilovol [simplified code as requested by Alan Stern and Felipe Balbi, fixed checkpatch issues] Signed-off-by: Marek Szyprowski Tested-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 41 ++++++++++++++++++++++++++++++--------- include/linux/usb/gadget.h | 2 ++ 2 files changed, 34 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index f76ebc8c1ed2..fd73a3ea07c2 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -51,8 +51,12 @@ struct usb_udc { static struct class *udc_class; static LIST_HEAD(udc_list); +static LIST_HEAD(gadget_driver_pending_list); static DEFINE_MUTEX(udc_lock); +static int udc_bind_to_driver(struct usb_udc *udc, + struct usb_gadget_driver *driver); + /* ------------------------------------------------------------------------- */ #ifdef CONFIG_HAS_DMA @@ -356,6 +360,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)) { struct usb_udc *udc; + struct usb_gadget_driver *driver; int ret = -ENOMEM; udc = kzalloc(sizeof(*udc), GFP_KERNEL); @@ -403,6 +408,18 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, usb_gadget_set_state(gadget, USB_STATE_NOTATTACHED); udc->vbus = true; + /* pick up one of pending gadget drivers */ + list_for_each_entry(driver, &gadget_driver_pending_list, pending) { + if (!driver->udc_name || strcmp(driver->udc_name, + dev_name(&udc->dev)) == 0) { + ret = udc_bind_to_driver(udc, driver); + if (ret) + goto err4; + list_del(&driver->pending); + break; + } + } + mutex_unlock(&udc_lock); return 0; @@ -473,10 +490,14 @@ void usb_del_gadget_udc(struct usb_gadget *gadget) mutex_lock(&udc_lock); list_del(&udc->list); - mutex_unlock(&udc_lock); - if (udc->driver) + if (udc->driver) { + struct usb_gadget_driver *driver = udc->driver; + usb_gadget_remove_driver(udc); + list_add(&driver->pending, &gadget_driver_pending_list); + } + mutex_unlock(&udc_lock); kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); flush_work(&gadget->work); @@ -535,11 +556,7 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver) if (!ret) break; } - if (ret) - ret = -ENODEV; - else if (udc->driver) - ret = -EBUSY; - else + if (!ret && !udc->driver) goto found; } else { list_for_each_entry(udc, &udc_list, list) { @@ -549,9 +566,11 @@ int usb_gadget_probe_driver(struct usb_gadget_driver *driver) } } - pr_debug("couldn't find an available UDC\n"); + list_add_tail(&driver->pending, &gadget_driver_pending_list); + pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n", + driver->function); mutex_unlock(&udc_lock); - return ret; + return 0; found: ret = udc_bind_to_driver(udc, driver); mutex_unlock(&udc_lock); @@ -577,6 +596,10 @@ int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) break; } + if (ret) { + list_del(&driver->pending); + ret = 0; + } mutex_unlock(&udc_lock); return ret; } diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index ce2188d338e6..92467eea76de 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -1014,6 +1014,7 @@ static inline int usb_gadget_activate(struct usb_gadget *gadget) * @driver: Driver model state for this driver. * @udc_name: A name of UDC this driver should be bound to. If udc_name is NULL, * this driver will be bound to any available UDC. + * @pending: UDC core private data used for deferred probe of this driver. * * Devices are disabled till a gadget driver successfully bind()s, which * means the driver will handle setup() requests needed to enumerate (and @@ -1076,6 +1077,7 @@ struct usb_gadget_driver { struct device_driver driver; char *udc_name; + struct list_head pending; }; -- cgit v1.2.3 From 8055555fc4590fbda32d4bbf7888bdb2cd4b2b74 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 30 Nov 2015 21:37:12 -0800 Subject: usb: musb: core: Fix handling of the phy notifications We currently can't unload omap2430 MUSB platform glue driver module and this cause issues for fixing the MUSB code further. The reason we can't remove omap2430 is because it uses the PHY functions and also exports the omap_musb_mailbox function that some PHY drivers are using. Let's fix the issue by exporting a more generic musb_mailbox function from the MUSB core and allow platform glue layers to register phy_callback function as needed. And now we can now also get rid of the include/linux/musb-omap.h. Cc: Bin Liu Cc: Felipe Balbi Cc: Kishon Vijay Abraham I Cc: NeilBrown Reviewed-by: Kishon Vijay Abraham I Signed-off-by: Tony Lindgren Signed-off-by: Felipe Balbi --- drivers/phy/phy-twl4030-usb.c | 32 ++++++++++++++++---------------- drivers/usb/musb/musb_core.c | 21 +++++++++++++++++++++ drivers/usb/musb/musb_core.h | 2 ++ drivers/usb/musb/omap2430.c | 27 ++++++++++++++------------- drivers/usb/phy/phy-twl6030-usb.c | 30 +++++++++++++++--------------- include/linux/usb/musb-omap.h | 30 ------------------------------ include/linux/usb/musb.h | 15 +++++++++++++++ 7 files changed, 83 insertions(+), 74 deletions(-) delete mode 100644 include/linux/usb/musb-omap.h (limited to 'include/linux') diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 3a707dd14238..4a3fc6e59f8e 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include #include @@ -148,10 +148,10 @@ * If VBUS is valid or ID is ground, then we know a * cable is present and we need to be runtime-enabled */ -static inline bool cable_present(enum omap_musb_vbus_id_status stat) +static inline bool cable_present(enum musb_vbus_id_status stat) { - return stat == OMAP_MUSB_VBUS_VALID || - stat == OMAP_MUSB_ID_GROUND; + return stat == MUSB_VBUS_VALID || + stat == MUSB_ID_GROUND; } struct twl4030_usb { @@ -170,7 +170,7 @@ struct twl4030_usb { enum twl4030_usb_mode usb_mode; int irq; - enum omap_musb_vbus_id_status linkstat; + enum musb_vbus_id_status linkstat; bool vbus_supplied; struct delayed_work id_workaround_work; @@ -276,11 +276,11 @@ static bool twl4030_is_driving_vbus(struct twl4030_usb *twl) return (ret & (ULPI_OTG_DRVVBUS | ULPI_OTG_CHRGVBUS)) ? true : false; } -static enum omap_musb_vbus_id_status +static enum musb_vbus_id_status twl4030_usb_linkstat(struct twl4030_usb *twl) { int status; - enum omap_musb_vbus_id_status linkstat = OMAP_MUSB_UNKNOWN; + enum musb_vbus_id_status linkstat = MUSB_UNKNOWN; twl->vbus_supplied = false; @@ -306,14 +306,14 @@ static enum omap_musb_vbus_id_status } if (status & BIT(2)) - linkstat = OMAP_MUSB_ID_GROUND; + linkstat = MUSB_ID_GROUND; else if (status & BIT(7)) - linkstat = OMAP_MUSB_VBUS_VALID; + linkstat = MUSB_VBUS_VALID; else - linkstat = OMAP_MUSB_VBUS_OFF; + linkstat = MUSB_VBUS_OFF; } else { - if (twl->linkstat != OMAP_MUSB_UNKNOWN) - linkstat = OMAP_MUSB_VBUS_OFF; + if (twl->linkstat != MUSB_UNKNOWN) + linkstat = MUSB_VBUS_OFF; } dev_dbg(twl->dev, "HW_CONDITIONS 0x%02x/%d; link %d\n", @@ -535,7 +535,7 @@ static DEVICE_ATTR(vbus, 0444, twl4030_usb_vbus_show, NULL); static irqreturn_t twl4030_usb_irq(int irq, void *_twl) { struct twl4030_usb *twl = _twl; - enum omap_musb_vbus_id_status status; + enum musb_vbus_id_status status; bool status_changed = false; status = twl4030_usb_linkstat(twl); @@ -567,11 +567,11 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) pm_runtime_mark_last_busy(twl->dev); pm_runtime_put_autosuspend(twl->dev); } - omap_musb_mailbox(status); + musb_mailbox(status); } /* don't schedule during sleep - irq works right then */ - if (status == OMAP_MUSB_ID_GROUND && pm_runtime_active(twl->dev)) { + if (status == MUSB_ID_GROUND && pm_runtime_active(twl->dev)) { cancel_delayed_work(&twl->id_workaround_work); schedule_delayed_work(&twl->id_workaround_work, HZ); } @@ -670,7 +670,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) twl->dev = &pdev->dev; twl->irq = platform_get_irq(pdev, 0); twl->vbus_supplied = false; - twl->linkstat = OMAP_MUSB_UNKNOWN; + twl->linkstat = MUSB_UNKNOWN; twl->phy.dev = twl->dev; twl->phy.label = "twl4030"; diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index cd37e9fc2e62..04548423094b 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -1702,6 +1702,23 @@ EXPORT_SYMBOL_GPL(musb_dma_completion); #define use_dma 0 #endif +static void (*musb_phy_callback)(enum musb_vbus_id_status status); + +/* + * musb_mailbox - optional phy notifier function + * @status phy state change + * + * Optionally gets called from the USB PHY. Note that the USB PHY must be + * disabled at the point the phy_callback is registered or unregistered. + */ +void musb_mailbox(enum musb_vbus_id_status status) +{ + if (musb_phy_callback) + musb_phy_callback(status); + +}; +EXPORT_SYMBOL_GPL(musb_mailbox); + /*-------------------------------------------------------------------------*/ static ssize_t @@ -2114,6 +2131,9 @@ musb_init_controller(struct device *dev, int nIrq, void __iomem *ctrl) musb->xceiv->io_ops = &musb_ulpi_access; } + if (musb->ops->phy_callback) + musb_phy_callback = musb->ops->phy_callback; + pm_runtime_get_sync(musb->controller); if (use_dma && dev->dma_mask) { @@ -2292,6 +2312,7 @@ static int musb_remove(struct platform_device *pdev) */ musb_exit_debugfs(musb); musb_shutdown(pdev); + musb_phy_callback = NULL; if (musb->dma_controller) musb_dma_controller_destroy(musb->dma_controller); diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index 2337d7a7d62d..fd215fb45fd4 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -168,6 +168,7 @@ struct musb_io; * @adjust_channel_params: pre check for standard dma channel_program func * @pre_root_reset_end: called before the root usb port reset flag gets cleared * @post_root_reset_end: called after the root usb port reset flag gets cleared + * @phy_callback: optional callback function for the phy to call */ struct musb_platform_ops { @@ -214,6 +215,7 @@ struct musb_platform_ops { dma_addr_t *dma_addr, u32 *len); void (*pre_root_reset_end)(struct musb *musb); void (*post_root_reset_end)(struct musb *musb); + void (*phy_callback)(enum musb_vbus_id_status status); }; /* diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 1bd9232ff76f..bf05f807729f 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -36,7 +36,7 @@ #include #include #include -#include +#include #include #include @@ -46,7 +46,7 @@ struct omap2430_glue { struct device *dev; struct platform_device *musb; - enum omap_musb_vbus_id_status status; + enum musb_vbus_id_status status; struct work_struct omap_musb_mailbox_work; struct device *control_otghs; }; @@ -234,7 +234,7 @@ static inline void omap2430_low_level_init(struct musb *musb) musb_writel(musb->mregs, OTG_FORCESTDBY, l); } -void omap_musb_mailbox(enum omap_musb_vbus_id_status status) +static void omap2430_musb_mailbox(enum musb_vbus_id_status status) { struct omap2430_glue *glue = _glue; @@ -251,7 +251,6 @@ void omap_musb_mailbox(enum omap_musb_vbus_id_status status) schedule_work(&glue->omap_musb_mailbox_work); } -EXPORT_SYMBOL_GPL(omap_musb_mailbox); static void omap_musb_set_mailbox(struct omap2430_glue *glue) { @@ -262,7 +261,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) struct usb_otg *otg = musb->xceiv->otg; switch (glue->status) { - case OMAP_MUSB_ID_GROUND: + case MUSB_ID_GROUND: dev_dbg(dev, "ID GND\n"); otg->default_a = true; @@ -276,7 +275,7 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) } break; - case OMAP_MUSB_VBUS_VALID: + case MUSB_VBUS_VALID: dev_dbg(dev, "VBUS Connect\n"); otg->default_a = false; @@ -287,8 +286,8 @@ static void omap_musb_set_mailbox(struct omap2430_glue *glue) omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE); break; - case OMAP_MUSB_ID_FLOAT: - case OMAP_MUSB_VBUS_OFF: + case MUSB_ID_FLOAT: + case MUSB_VBUS_OFF: dev_dbg(dev, "VBUS Disconnect\n"); musb->xceiv->last_event = USB_EVENT_NONE; @@ -430,7 +429,7 @@ static int omap2430_musb_init(struct musb *musb) setup_timer(&musb_idle_timer, musb_do_idle, (unsigned long) musb); - if (glue->status != OMAP_MUSB_UNKNOWN) + if (glue->status != MUSB_UNKNOWN) omap_musb_set_mailbox(glue); phy_init(musb->phy); @@ -455,7 +454,7 @@ static void omap2430_musb_enable(struct musb *musb) switch (glue->status) { - case OMAP_MUSB_ID_GROUND: + case MUSB_ID_GROUND: omap_control_usb_set_mode(glue->control_otghs, USB_MODE_HOST); if (data->interface_type != MUSB_INTERFACE_UTMI) break; @@ -474,7 +473,7 @@ static void omap2430_musb_enable(struct musb *musb) } break; - case OMAP_MUSB_VBUS_VALID: + case MUSB_VBUS_VALID: omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DEVICE); break; @@ -488,7 +487,7 @@ static void omap2430_musb_disable(struct musb *musb) struct device *dev = musb->controller; struct omap2430_glue *glue = dev_get_drvdata(dev->parent); - if (glue->status != OMAP_MUSB_UNKNOWN) + if (glue->status != MUSB_UNKNOWN) omap_control_usb_set_mode(glue->control_otghs, USB_MODE_DISCONNECT); } @@ -520,6 +519,8 @@ static const struct musb_platform_ops omap2430_ops = { .enable = omap2430_musb_enable, .disable = omap2430_musb_disable, + + .phy_callback = omap2430_musb_mailbox, }; static u64 omap2430_dmamask = DMA_BIT_MASK(32); @@ -551,7 +552,7 @@ static int omap2430_probe(struct platform_device *pdev) glue->dev = &pdev->dev; glue->musb = musb; - glue->status = OMAP_MUSB_UNKNOWN; + glue->status = MUSB_UNKNOWN; glue->control_otghs = ERR_PTR(-ENODEV); if (np) { diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c index 12741856a75c..014dbbd72132 100644 --- a/drivers/usb/phy/phy-twl6030-usb.c +++ b/drivers/usb/phy/phy-twl6030-usb.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include #include @@ -102,7 +102,7 @@ struct twl6030_usb { int irq1; int irq2; - enum omap_musb_vbus_id_status linkstat; + enum musb_vbus_id_status linkstat; u8 asleep; bool vbus_enable; const char *regulator; @@ -189,13 +189,13 @@ static ssize_t twl6030_usb_vbus_show(struct device *dev, spin_lock_irqsave(&twl->lock, flags); switch (twl->linkstat) { - case OMAP_MUSB_VBUS_VALID: + case MUSB_VBUS_VALID: ret = snprintf(buf, PAGE_SIZE, "vbus\n"); break; - case OMAP_MUSB_ID_GROUND: + case MUSB_ID_GROUND: ret = snprintf(buf, PAGE_SIZE, "id\n"); break; - case OMAP_MUSB_VBUS_OFF: + case MUSB_VBUS_OFF: ret = snprintf(buf, PAGE_SIZE, "none\n"); break; default: @@ -210,7 +210,7 @@ static DEVICE_ATTR(vbus, 0444, twl6030_usb_vbus_show, NULL); static irqreturn_t twl6030_usb_irq(int irq, void *_twl) { struct twl6030_usb *twl = _twl; - enum omap_musb_vbus_id_status status = OMAP_MUSB_UNKNOWN; + enum musb_vbus_id_status status = MUSB_UNKNOWN; u8 vbus_state, hw_state; int ret; @@ -225,14 +225,14 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl) dev_err(twl->dev, "Failed to enable usb3v3\n"); twl->asleep = 1; - status = OMAP_MUSB_VBUS_VALID; + status = MUSB_VBUS_VALID; twl->linkstat = status; - omap_musb_mailbox(status); + musb_mailbox(status); } else { - if (twl->linkstat != OMAP_MUSB_UNKNOWN) { - status = OMAP_MUSB_VBUS_OFF; + if (twl->linkstat != MUSB_UNKNOWN) { + status = MUSB_VBUS_OFF; twl->linkstat = status; - omap_musb_mailbox(status); + musb_mailbox(status); if (twl->asleep) { regulator_disable(twl->usb3v3); twl->asleep = 0; @@ -248,7 +248,7 @@ static irqreturn_t twl6030_usb_irq(int irq, void *_twl) static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl) { struct twl6030_usb *twl = _twl; - enum omap_musb_vbus_id_status status = OMAP_MUSB_UNKNOWN; + enum musb_vbus_id_status status = MUSB_UNKNOWN; u8 hw_state; int ret; @@ -262,9 +262,9 @@ static irqreturn_t twl6030_usbotg_irq(int irq, void *_twl) twl->asleep = 1; twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_CLR); twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_SET); - status = OMAP_MUSB_ID_GROUND; + status = MUSB_ID_GROUND; twl->linkstat = status; - omap_musb_mailbox(status); + musb_mailbox(status); } else { twl6030_writeb(twl, TWL_MODULE_USB, 0x10, USB_ID_INT_EN_HI_CLR); twl6030_writeb(twl, TWL_MODULE_USB, 0x1, USB_ID_INT_EN_HI_SET); @@ -334,7 +334,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) twl->dev = &pdev->dev; twl->irq1 = platform_get_irq(pdev, 0); twl->irq2 = platform_get_irq(pdev, 1); - twl->linkstat = OMAP_MUSB_UNKNOWN; + twl->linkstat = MUSB_UNKNOWN; twl->comparator.set_vbus = twl6030_set_vbus; twl->comparator.start_srp = twl6030_start_srp; diff --git a/include/linux/usb/musb-omap.h b/include/linux/usb/musb-omap.h deleted file mode 100644 index 7774c5986f07..000000000000 --- a/include/linux/usb/musb-omap.h +++ /dev/null @@ -1,30 +0,0 @@ -/* - * Copyright (C) 2011-2012 by Texas Instruments - * - * The Inventra Controller Driver for Linux 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 __MUSB_OMAP_H__ -#define __MUSB_OMAP_H__ - -enum omap_musb_vbus_id_status { - OMAP_MUSB_UNKNOWN = 0, - OMAP_MUSB_ID_GROUND, - OMAP_MUSB_ID_FLOAT, - OMAP_MUSB_VBUS_VALID, - OMAP_MUSB_VBUS_OFF, -}; - -#if (defined(CONFIG_USB_MUSB_OMAP2PLUS) || \ - defined(CONFIG_USB_MUSB_OMAP2PLUS_MODULE)) -void omap_musb_mailbox(enum omap_musb_vbus_id_status status); -#else -static inline void omap_musb_mailbox(enum omap_musb_vbus_id_status status) -{ -} -#endif - -#endif /* __MUSB_OMAP_H__ */ diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index fa6dc132bd1b..96ddfb7ab018 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -133,6 +133,21 @@ struct musb_hdrc_platform_data { const void *platform_ops; }; +enum musb_vbus_id_status { + MUSB_UNKNOWN = 0, + MUSB_ID_GROUND, + MUSB_ID_FLOAT, + MUSB_VBUS_VALID, + MUSB_VBUS_OFF, +}; + +#if IS_ENABLED(CONFIG_USB_MUSB_HDRC) +void musb_mailbox(enum musb_vbus_id_status status); +#else +static inline void musb_mailbox(enum musb_vbus_id_status status) +{ +} +#endif /* TUSB 6010 support */ -- cgit v1.2.3 From b8bbd6b2923279f1c9c74d59638b38a1eace78e8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 12 Nov 2015 13:36:06 +0100 Subject: serial: sh-sci: Add BRG register definitions Add register definitions for the Baud Rate Generator for External Clock (BRG), as found in some SCIF and in HSCIF, including a new regtype for the "SH-4(A)"-derived SCIF variant with BRG. Signed-off-by: Geert Uytterhoeven Acked-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 46 +++++++++++++++++++++++++++++++++++++++++++++ drivers/tty/serial/sh-sci.h | 10 ++++++++++ include/linux/serial_sci.h | 1 + 3 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 5b120757c02a..fb5eac2e3182 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -161,6 +161,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -183,6 +185,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -204,6 +208,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = { 0x30, 16 }, [SCPDR] = { 0x34, 16 }, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -225,6 +231,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = { 0x30, 16 }, [SCPDR] = { 0x34, 16 }, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -247,6 +255,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -268,6 +278,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -289,6 +301,32 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, + }, + + /* + * Common SCIF definitions for ports with a Baud Rate Generator for + * External Clock (BRG). + */ + [SCIx_SH4_SCIF_BRG_REGTYPE] = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x04, 8 }, + [SCSCR] = { 0x08, 16 }, + [SCxTDR] = { 0x0c, 8 }, + [SCxSR] = { 0x10, 16 }, + [SCxRDR] = { 0x14, 8 }, + [SCFCR] = { 0x18, 16 }, + [SCFDR] = { 0x1c, 16 }, + [SCTFDR] = sci_reg_invalid, + [SCRFDR] = sci_reg_invalid, + [SCSPTR] = { 0x20, 16 }, + [SCLSR] = { 0x24, 16 }, + [HSSRR] = sci_reg_invalid, + [SCPCR] = sci_reg_invalid, + [SCPDR] = sci_reg_invalid, + [SCDL] = { 0x30, 16 }, + [SCCKS] = { 0x34, 16 }, }, /* @@ -310,6 +348,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = { 0x40, 16 }, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = { 0x30, 16 }, + [SCCKS] = { 0x34, 16 }, }, /* @@ -332,6 +372,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -354,6 +396,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, /* @@ -376,6 +420,8 @@ static const struct plat_sci_reg sci_regmap[SCIx_NR_REGTYPES][SCIx_NR_REGS] = { [HSSRR] = sci_reg_invalid, [SCPCR] = sci_reg_invalid, [SCPDR] = sci_reg_invalid, + [SCDL] = sci_reg_invalid, + [SCCKS] = sci_reg_invalid, }, }; diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h index bf69bbdcc1f9..fb1760250421 100644 --- a/drivers/tty/serial/sh-sci.h +++ b/drivers/tty/serial/sh-sci.h @@ -27,6 +27,8 @@ enum { HSSRR, /* Sampling Rate Register */ SCPCR, /* Serial Port Control Register */ SCPDR, /* Serial Port Data Register */ + SCDL, /* BRG Frequency Division Register */ + SCCKS, /* BRG Clock Select Register */ SCIx_NR_REGS, }; @@ -109,6 +111,14 @@ enum { #define SCPDR_RTSD BIT(4) /* Serial Port RTS Output Pin Data */ #define SCPDR_CTSD BIT(3) /* Serial Port CTS Input Pin Data */ +/* + * BRG Clock Select Register (Some SCIF and HSCIF) + * The Baud Rate Generator for external clock can provide a clock source for + * the sampling clock. It outputs either its frequency divided clock, or the + * (undivided) (H)SCK external clock. + */ +#define SCCKS_CKS BIT(15) /* Select (H)SCK (1) or divided SC_CLK (0) */ +#define SCCKS_XIN BIT(14) /* SC_CLK uses bus clock (1) or SCIF_CLK (0) */ #define SCxSR_TEND(port) (((port)->type == PORT_SCI) ? SCI_TEND : SCIF_TEND) #define SCxSR_RDxF(port) (((port)->type == PORT_SCI) ? SCI_RDRF : SCIF_RDF) diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 7c536ac5be05..9f2bfd055742 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -32,6 +32,7 @@ enum { SCIx_SH2_SCIF_FIFODATA_REGTYPE, SCIx_SH3_SCIF_REGTYPE, SCIx_SH4_SCIF_REGTYPE, + SCIx_SH4_SCIF_BRG_REGTYPE, SCIx_SH4_SCIF_NO_SCSPTR_REGTYPE, SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, -- cgit v1.2.3 From be99c84300950e876074916b215b511f69f83d3b Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 17 Dec 2015 09:55:41 -0600 Subject: usb: of: fix build breakage on !OF If OF is disabled, we will try to define a stub for of_usb_get_dr_mode_by_phy(), however that missed a static inline annotation which made us redefine the stub over and over again. Fix that. Fixes: 98bfb3946695 ("usb: of: add an api to get dr_mode by the phy node") Signed-off-by: Felipe Balbi --- include/linux/usb/of.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index 3805757dcdc2..974bce93aa28 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -17,7 +17,8 @@ bool of_usb_host_tpl_support(struct device_node *np); int of_usb_update_otg_caps(struct device_node *np, struct usb_otg_caps *otg_caps); #else -enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np) +static inline enum usb_dr_mode +of_usb_get_dr_mode_by_phy(struct device_node *phy_np) { return USB_DR_MODE_UNKNOWN; } -- cgit v1.2.3 From fcd71d9cc6e301bdbd71829b79e80168473ca609 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 8 Dec 2015 14:17:55 +0530 Subject: of: fix declaration of of_io_request_and_map We are having build failure with linux-next for sparc allmodconfig with the error messages: drivers/built-in.o: In function `meson6_timer_init': meson6_timer.c:(.init.text+0x5fe8): undefined reference to `of_io_request_and_map' drivers/built-in.o: In function `mtk_timer_init': mtk_timer.c:(.init.text+0x6af0): undefined reference to `of_io_request_and_map' drivers/built-in.o: In function `asm9260_timer_init': asm9260_timer.c:(.init.text+0x6c48): undefined reference to `of_io_request_and_map' CONFIG_OF is defined for sparc so it is expected that we have a definition of of_io_request_and_map() but of/address.c is only compiled if it is !SPARC. In other words, CONFIG_OF_ADDRESS is not defined for sparc so we get the build failure. Fixes: e572f844ca66 ("clocksource/drivers/meson6: Add the COMPILE_TEST option") Fixes: bec8c4617611 ("clocksource/drivers/mediatek: Add the COMPILE_TEST option") Fixes: 4a373b45f94a ("clocksource/drivers/asm9260: Add the COMPILE_TEST option") Acked-by: Daniel Lezcano Signed-off-by: Sudip Mukherjee [robh: move include of io.h out of ifdef's] Signed-off-by: Rob Herring --- include/linux/of_address.h | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 507daad0bc8d..01c0a556448b 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,6 +3,7 @@ #include #include #include +#include struct of_pci_range_parser { struct device_node *node; @@ -36,6 +37,8 @@ extern struct device_node *of_find_matching_node_by_address( const struct of_device_id *matches, u64 base_address); extern void __iomem *of_iomap(struct device_node *device, int index); +void __iomem *of_io_request_and_map(struct device_node *device, + int index, const char *name); /* Extract an address from a device, returns the region size and * the address space flags too. The PCI version uses a BAR number @@ -57,6 +60,11 @@ extern int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *size); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ +static inline void __iomem *of_io_request_and_map(struct device_node *device, + int index, const char *name) +{ + return IOMEM_ERR_PTR(-EINVAL); +} static inline u64 of_translate_address(struct device_node *np, const __be32 *addr) @@ -112,12 +120,7 @@ static inline bool of_dma_is_coherent(struct device_node *np) extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); void __iomem *of_iomap(struct device_node *node, int index); -void __iomem *of_io_request_and_map(struct device_node *device, - int index, const char *name); #else - -#include - static inline int of_address_to_resource(struct device_node *dev, int index, struct resource *r) { @@ -128,12 +131,6 @@ static inline void __iomem *of_iomap(struct device_node *device, int index) { return NULL; } - -static inline void __iomem *of_io_request_and_map(struct device_node *device, - int index, const char *name) -{ - return IOMEM_ERR_PTR(-EINVAL); -} #endif #if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_PCI) -- cgit v1.2.3 From a8135d0d79e9d0ad3a4ff494fceeaae838becf38 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 14 Dec 2015 22:47:40 +0200 Subject: dmaengine: core: Introduce new, universal API to request a channel The two API function can cover most, if not all current APIs used to request a channel. With minimal effort dmaengine drivers, platforms and dmaengine user drivers can be converted to use the two function. struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask); To request any channel matching with the requested capabilities, can be used to request channel for memcpy, memset, xor, etc where no hardware synchronization is needed. struct dma_chan *dma_request_chan(struct device *dev, const char *name); To request a slave channel. The dma_request_chan() will try to find the channel via DT, ACPI or in case if the kernel booted in non DT/ACPI mode it will use a filter lookup table and retrieves the needed information from the dma_slave_map provided by the DMA drivers. This legacy mode needs changes in platform code, in dmaengine drivers and finally the dmaengine user drivers can be converted: For each dmaengine driver an array of DMA device, slave and the parameter for the filter function needs to be added: static const struct dma_slave_map da830_edma_map[] = { { "davinci-mcasp.0", "rx", EDMA_FILTER_PARAM(0, 0) }, { "davinci-mcasp.0", "tx", EDMA_FILTER_PARAM(0, 1) }, { "davinci-mcasp.1", "rx", EDMA_FILTER_PARAM(0, 2) }, { "davinci-mcasp.1", "tx", EDMA_FILTER_PARAM(0, 3) }, { "davinci-mcasp.2", "rx", EDMA_FILTER_PARAM(0, 4) }, { "davinci-mcasp.2", "tx", EDMA_FILTER_PARAM(0, 5) }, { "spi_davinci.0", "rx", EDMA_FILTER_PARAM(0, 14) }, { "spi_davinci.0", "tx", EDMA_FILTER_PARAM(0, 15) }, { "da830-mmc.0", "rx", EDMA_FILTER_PARAM(0, 16) }, { "da830-mmc.0", "tx", EDMA_FILTER_PARAM(0, 17) }, { "spi_davinci.1", "rx", EDMA_FILTER_PARAM(0, 18) }, { "spi_davinci.1", "tx", EDMA_FILTER_PARAM(0, 19) }, }; This information is going to be needed by the dmaengine driver, so modification to the platform_data is needed, and the driver map should be added to the pdata of the DMA driver: da8xx_edma0_pdata.slave_map = da830_edma_map; da8xx_edma0_pdata.slavecnt = ARRAY_SIZE(da830_edma_map); The DMA driver then needs to configure the needed device -> filter_fn mapping before it registers with dma_async_device_register() : ecc->dma_slave.filter_map.map = info->slave_map; ecc->dma_slave.filter_map.mapcnt = info->slavecnt; ecc->dma_slave.filter_map.fn = edma_filter_fn; When neither DT or ACPI lookup is available the dma_request_chan() will try to match the requester's device name with the filter_map's list of device names, when a match found it will use the information from the dma_slave_map to get the channel with the dma_get_channel() internal function. Signed-off-by: Peter Ujfalusi Reviewed-by: Arnd Bergmann Signed-off-by: Vinod Koul --- Documentation/dmaengine/client.txt | 23 +++------- drivers/dma/dmaengine.c | 89 +++++++++++++++++++++++++++++++++----- include/linux/dmaengine.h | 51 +++++++++++++++++++--- 3 files changed, 127 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/Documentation/dmaengine/client.txt b/Documentation/dmaengine/client.txt index 11fb87ff6cd0..4b04d8988708 100644 --- a/Documentation/dmaengine/client.txt +++ b/Documentation/dmaengine/client.txt @@ -22,25 +22,14 @@ The slave DMA usage consists of following steps: Channel allocation is slightly different in the slave DMA context, client drivers typically need a channel from a particular DMA controller only and even in some cases a specific channel is desired. - To request a channel dma_request_channel() API is used. + To request a channel dma_request_chan() API is used. Interface: - struct dma_chan *dma_request_channel(dma_cap_mask_t mask, - dma_filter_fn filter_fn, - void *filter_param); - where dma_filter_fn is defined as: - typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); - - The 'filter_fn' parameter is optional, but highly recommended for - slave and cyclic channels as they typically need to obtain a specific - DMA channel. - - When the optional 'filter_fn' parameter is NULL, dma_request_channel() - simply returns the first channel that satisfies the capability mask. - - Otherwise, the 'filter_fn' routine will be called once for each free - channel which has a capability in 'mask'. 'filter_fn' is expected to - return 'true' when the desired DMA channel is found. + struct dma_chan *dma_request_chan(struct device *dev, const char *name); + + Which will find and return the 'name' DMA channel associated with the 'dev' + device. The association is done via DT, ACPI or board file based + dma_slave_map matching table. A channel allocated via this interface is exclusive to the caller, until dma_release_channel() is called. diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index 81a36fc445a7..a094dbb54f46 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -43,6 +43,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -665,27 +666,73 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, } EXPORT_SYMBOL_GPL(__dma_request_channel); +static const struct dma_slave_map *dma_filter_match(struct dma_device *device, + const char *name, + struct device *dev) +{ + int i; + + if (!device->filter.mapcnt) + return NULL; + + for (i = 0; i < device->filter.mapcnt; i++) { + const struct dma_slave_map *map = &device->filter.map[i]; + + if (!strcmp(map->devname, dev_name(dev)) && + !strcmp(map->slave, name)) + return map; + } + + return NULL; +} + /** - * dma_request_slave_channel_reason - try to allocate an exclusive slave channel + * dma_request_chan - try to allocate an exclusive slave channel * @dev: pointer to client device structure * @name: slave channel name * * Returns pointer to appropriate DMA channel on success or an error pointer. */ -struct dma_chan *dma_request_slave_channel_reason(struct device *dev, - const char *name) +struct dma_chan *dma_request_chan(struct device *dev, const char *name) { + struct dma_device *d, *_d; + struct dma_chan *chan = NULL; + /* If device-tree is present get slave info from here */ if (dev->of_node) - return of_dma_request_slave_channel(dev->of_node, name); + chan = of_dma_request_slave_channel(dev->of_node, name); /* If device was enumerated by ACPI get slave info from here */ - if (ACPI_HANDLE(dev)) - return acpi_dma_request_slave_chan_by_name(dev, name); + if (has_acpi_companion(dev) && !chan) + chan = acpi_dma_request_slave_chan_by_name(dev, name); + + if (chan) { + /* Valid channel found or requester need to be deferred */ + if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER) + return chan; + } + + /* Try to find the channel via the DMA filter map(s) */ + mutex_lock(&dma_list_mutex); + list_for_each_entry_safe(d, _d, &dma_device_list, global_node) { + dma_cap_mask_t mask; + const struct dma_slave_map *map = dma_filter_match(d, name, dev); + + if (!map) + continue; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); - return ERR_PTR(-ENODEV); + chan = find_candidate(d, &mask, d->filter.fn, map->param); + if (!IS_ERR(chan)) + break; + } + mutex_unlock(&dma_list_mutex); + + return chan ? chan : ERR_PTR(-EPROBE_DEFER); } -EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason); +EXPORT_SYMBOL_GPL(dma_request_chan); /** * dma_request_slave_channel - try to allocate an exclusive slave channel @@ -697,17 +744,35 @@ EXPORT_SYMBOL_GPL(dma_request_slave_channel_reason); struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name) { - struct dma_chan *ch = dma_request_slave_channel_reason(dev, name); + struct dma_chan *ch = dma_request_chan(dev, name); if (IS_ERR(ch)) return NULL; - dma_cap_set(DMA_PRIVATE, ch->device->cap_mask); - ch->device->privatecnt++; - return ch; } EXPORT_SYMBOL_GPL(dma_request_slave_channel); +/** + * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities + * @mask: capabilities that the channel must satisfy + * + * Returns pointer to appropriate DMA channel on success or an error pointer. + */ +struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask) +{ + struct dma_chan *chan; + + if (!mask) + return ERR_PTR(-ENODEV); + + chan = __dma_request_channel(mask, NULL, NULL); + if (!chan) + chan = ERR_PTR(-ENODEV); + + return chan; +} +EXPORT_SYMBOL_GPL(dma_request_chan_by_mask); + void dma_release_channel(struct dma_chan *chan) { mutex_lock(&dma_list_mutex); diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c47c68e535e8..d50a6b51a73d 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -606,12 +606,39 @@ enum dmaengine_alignment { DMAENGINE_ALIGN_64_BYTES = 6, }; +/** + * struct dma_slave_map - associates slave device and it's slave channel with + * parameter to be used by a filter function + * @devname: name of the device + * @slave: slave channel name + * @param: opaque parameter to pass to struct dma_filter.fn + */ +struct dma_slave_map { + const char *devname; + const char *slave; + void *param; +}; + +/** + * struct dma_filter - information for slave device/channel to filter_fn/param + * mapping + * @fn: filter function callback + * @mapcnt: number of slave device/channel in the map + * @map: array of channel to filter mapping data + */ +struct dma_filter { + dma_filter_fn fn; + int mapcnt; + const struct dma_slave_map *map; +}; + /** * struct dma_device - info on the entity supplying DMA services * @chancnt: how many DMA channels are supported * @privatecnt: how many DMA channels are requested by dma_request_channel * @channels: the list of struct dma_chan * @global_node: list_head for global dma_device_list + * @filter: information for device/slave to filter function/param mapping * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability * @max_pq: maximum number of PQ sources and PQ-continue capability @@ -666,6 +693,7 @@ struct dma_device { unsigned int privatecnt; struct list_head channels; struct list_head global_node; + struct dma_filter filter; dma_cap_mask_t cap_mask; unsigned short max_xor; unsigned short max_pq; @@ -1140,9 +1168,11 @@ enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -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); + +struct dma_chan *dma_request_chan(struct device *dev, const char *name); +struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask); + void dma_release_channel(struct dma_chan *chan); int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps); #else @@ -1166,16 +1196,21 @@ static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, { return NULL; } -static inline struct dma_chan *dma_request_slave_channel_reason( - struct device *dev, const char *name) -{ - return ERR_PTR(-ENODEV); -} static inline struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name) { return NULL; } +static inline struct dma_chan *dma_request_chan(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENODEV); +} +static inline struct dma_chan *dma_request_chan_by_mask( + const dma_cap_mask_t *mask) +{ + return ERR_PTR(-ENODEV); +} static inline void dma_release_channel(struct dma_chan *chan) { } @@ -1186,6 +1221,8 @@ static inline int dma_get_slave_caps(struct dma_chan *chan, } #endif +#define dma_request_slave_channel_reason(dev, name) dma_request_chan(dev, name) + static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) { struct dma_slave_caps caps; -- cgit v1.2.3 From 23e6723c060faf5a0fc8d7bfbec440d29943fa99 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 14 Dec 2015 22:47:41 +0200 Subject: dmaengine: edma: Add support for DMA filter mapping to slave devices Add support for providing device to filter_fn mapping so client drivers can switch to use the dma_request_chan() API. Signed-off-by: Peter Ujfalusi Reviewed-by: Arnd Bergmann Signed-off-by: Vinod Koul --- drivers/dma/edma.c | 4 ++++ include/linux/platform_data/edma.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index 6b03e4e84e6b..c7a011f4b860 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -2297,6 +2297,10 @@ static int edma_probe(struct platform_device *pdev) edma_set_chmap(&ecc->slave_chans[i], ecc->dummy_slot); } + ecc->dma_slave.filter.map = info->slave_map; + ecc->dma_slave.filter.mapcnt = info->slavecnt; + ecc->dma_slave.filter.fn = edma_filter_fn; + ret = dma_async_device_register(&ecc->dma_slave); if (ret) { dev_err(dev, "slave ddev registration failed (%d)\n", ret); diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index e2878baeb90e..105700e62ea1 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -53,12 +53,16 @@ enum dma_event_q { #define EDMA_CTLR(i) ((i) >> 16) #define EDMA_CHAN_SLOT(i) ((i) & 0xffff) +#define EDMA_FILTER_PARAM(ctlr, chan) ((int[]) { EDMA_CTLR_CHAN(ctlr, chan) }) + struct edma_rsv_info { const s16 (*rsv_chans)[2]; const s16 (*rsv_slots)[2]; }; +struct dma_slave_map; + /* platform_data for EDMA driver */ struct edma_soc_info { /* @@ -76,6 +80,9 @@ struct edma_soc_info { s8 (*queue_priority_mapping)[2]; const s16 (*xbar_chans)[2]; + + const struct dma_slave_map *slave_map; + int slavecnt; }; #endif -- cgit v1.2.3 From 020c62ae38946cae01571a0b4e6f445dfdb7ec1c Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 14 Dec 2015 22:47:42 +0200 Subject: dmaengine: omap-dma: Add support for DMA filter mapping to slave devices Add support for providing device to filter_fn mapping so client drivers can switch to use the dma_request_chan() API. Signed-off-by: Peter Ujfalusi Reviewed-by: Arnd Bergmann Signed-off-by: Vinod Koul --- drivers/dma/omap-dma.c | 4 ++++ include/linux/omap-dma.h | 6 ++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c index 1dfc71c90123..48f77c289cd3 100644 --- a/drivers/dma/omap-dma.c +++ b/drivers/dma/omap-dma.c @@ -1203,6 +1203,10 @@ static int omap_dma_probe(struct platform_device *pdev) return rc; } + od->ddev.filter.map = od->plat->slave_map; + od->ddev.filter.mapcnt = od->plat->slavecnt; + od->ddev.filter.fn = omap_dma_filter_fn; + rc = dma_async_device_register(&od->ddev); if (rc) { pr_warn("OMAP-DMA: failed to register slave DMA engine device: %d\n", diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h index 88fa8af2b937..1d99b61adc65 100644 --- a/include/linux/omap-dma.h +++ b/include/linux/omap-dma.h @@ -267,6 +267,9 @@ struct omap_dma_reg { u8 type; }; +#define SDMA_FILTER_PARAM(hw_req) ((int[]) { (hw_req) }) +struct dma_slave_map; + /* System DMA platform data structure */ struct omap_system_dma_plat_info { const struct omap_dma_reg *reg_map; @@ -278,6 +281,9 @@ struct omap_system_dma_plat_info { void (*clear_dma)(int lch); void (*dma_write)(u32 val, int reg, int lch); u32 (*dma_read)(int reg, int lch); + + const struct dma_slave_map *slave_map; + int slavecnt; }; #ifdef CONFIG_ARCH_OMAP2PLUS -- cgit v1.2.3 From 9c9eef89ec74433f00593938f8af5113383d898a Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Thu, 10 Dec 2015 09:00:23 +0100 Subject: mtd: nand: sh_flctl: use the mtd instance embedded in struct nand_chip struct nand_chip now embeds an mtd device. Make use of this mtd instance. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/nand/sh_flctl.c | 8 ++++---- include/linux/mtd/sh_flctl.h | 3 +-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c index 57dc52578e07..0ec4b04b3536 100644 --- a/drivers/mtd/nand/sh_flctl.c +++ b/drivers/mtd/nand/sh_flctl.c @@ -607,13 +607,13 @@ static void execmd_read_page_sector(struct mtd_info *mtd, int page_addr) case FL_REPAIRABLE: dev_info(&flctl->pdev->dev, "applied ecc on page 0x%x", page_addr); - flctl->mtd.ecc_stats.corrected++; + mtd->ecc_stats.corrected++; break; case FL_ERROR: dev_warn(&flctl->pdev->dev, "page 0x%x contains corrupted data\n", page_addr); - flctl->mtd.ecc_stats.failed++; + mtd->ecc_stats.failed++; break; default: ; @@ -1120,8 +1120,8 @@ static int flctl_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, flctl); - flctl_mtd = &flctl->mtd; nand = &flctl->chip; + flctl_mtd = nand_to_mtd(nand); nand_set_flash_node(nand, pdev->dev.of_node); flctl_mtd->priv = nand; flctl_mtd->dev.parent = &pdev->dev; @@ -1178,7 +1178,7 @@ static int flctl_remove(struct platform_device *pdev) struct sh_flctl *flctl = platform_get_drvdata(pdev); flctl_release_dma(flctl); - nand_release(&flctl->mtd); + nand_release(nand_to_mtd(&flctl->chip)); pm_runtime_disable(&pdev->dev); return 0; diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 1c28f8879b1c..76e3e88bedfe 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -143,7 +143,6 @@ enum flctl_ecc_res_t { struct dma_chan; struct sh_flctl { - struct mtd_info mtd; struct nand_chip chip; struct platform_device *pdev; struct dev_pm_qos_request pm_qos; @@ -186,7 +185,7 @@ struct sh_flctl_platform_data { static inline struct sh_flctl *mtd_to_flctl(struct mtd_info *mtdinfo) { - return container_of(mtdinfo, struct sh_flctl, mtd); + return container_of(mtd_to_nand(mtdinfo), struct sh_flctl, chip); } #endif /* __SH_FLCTL_H__ */ -- cgit v1.2.3 From 2d3b77bac34bf99d7fdfd712ec2dc4317b3e850b Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Thu, 10 Dec 2015 09:00:33 +0100 Subject: mtd: nand: update mtd_to_nand() Now that all drivers are using the mtd instance embedded in the nand_chip struct we can safely update the mtd_to_nand() implementation to use the container_of macro instead of returning the content of mtd->priv. This will allow us to remove mtd->priv = chip assignments done in all NAND controller drivers. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index b614ed2105ac..9cb7ace6fb1f 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -734,7 +734,7 @@ static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) { - return mtd->priv; + return container_of(mtd, struct nand_chip, mtd); } static inline struct mtd_info *nand_to_mtd(struct nand_chip *chip) -- cgit v1.2.3 From 29574ede097438c560e8115caff9b6b8668730be Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Thu, 10 Dec 2015 09:00:38 +0100 Subject: mtd: nand: kill the chip->flash_node field Now that the nand_chip struct directly embeds an mtd_info struct we can get rid of the ->flash_node field and forward set/get_flash_node requests to the MTD layer. As a side effect, we no longer need the mtd_set_of_node() call done in nand_dt_init(). Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- drivers/mtd/nand/nand_base.c | 3 --- include/linux/mtd/nand.h | 7 ++----- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index ae3fd2a8c2f5..8bb8ebd62aaa 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -3945,9 +3945,6 @@ static int nand_dt_init(struct nand_chip *chip) if (!dn) return 0; - /* MTD can automatically handle DT partitions, etc. */ - mtd_set_of_node(nand_to_mtd(chip), dn); - if (of_get_nand_bus_width(dn) == 16) chip->options |= NAND_BUSWIDTH_16; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9cb7ace6fb1f..2bee2e42ae2f 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -545,7 +545,6 @@ struct nand_buffers { * flash device * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the * flash device. - * @flash_node: [BOARDSPECIFIC] device node describing this instance * @read_byte: [REPLACEABLE] read one byte from the chip * @read_word: [REPLACEABLE] read one word from the chip * @write_byte: [REPLACEABLE] write a single byte to the chip on the @@ -645,8 +644,6 @@ struct nand_chip { void __iomem *IO_ADDR_R; void __iomem *IO_ADDR_W; - struct device_node *flash_node; - uint8_t (*read_byte)(struct mtd_info *mtd); u16 (*read_word)(struct mtd_info *mtd); void (*write_byte)(struct mtd_info *mtd, uint8_t byte); @@ -724,12 +721,12 @@ struct nand_chip { static inline void nand_set_flash_node(struct nand_chip *chip, struct device_node *np) { - chip->flash_node = np; + mtd_set_of_node(&chip->mtd, np); } static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) { - return chip->flash_node; + return mtd_get_of_node(&chip->mtd); } static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) -- cgit v1.2.3 From 8142b47ef33c655a34e08efd46b65732fe190675 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Mon, 14 Dec 2015 16:13:31 +0100 Subject: mtd: nand: remove unused and buggy get_platform_nandchip() helper function Nobody uses the get_platform_nandchip() helper function which is supposed to return a pointer to a platform_nand_chip struct from an mtd_info pointer. Moreover, this function is buggy since the introduction of the plat_nand layer (chip->priv is now storing a pointer to an intermediate plat_nand_data structure allocated in plat_nand_probe(), and we have no way to retrieve a pointer to the provided platform_nand_chip struct from this plat_nand_data pointer). While we are at it, remove the useless (and buggy, since it's pointing to something stored on the stack) data->chip.priv assignment. Signed-off-by: Boris Brezillon Fixes: 711fdf627ce1 ("[MTD] [NAND] platform NAND driver: add driver") Cc: Vitaly Wool Signed-off-by: Brian Norris --- drivers/mtd/nand/plat_nand.c | 1 - include/linux/mtd/nand.h | 9 --------- 2 files changed, 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c index dc88a58d5cde..a0e26dea1424 100644 --- a/drivers/mtd/nand/plat_nand.c +++ b/drivers/mtd/nand/plat_nand.c @@ -56,7 +56,6 @@ static int plat_nand_probe(struct platform_device *pdev) if (IS_ERR(data->io_base)) return PTR_ERR(data->io_base); - data->chip.priv = &data; nand_set_flash_node(&data->chip, pdev->dev.of_node); mtd = nand_to_mtd(&data->chip); mtd->dev.parent = &pdev->dev; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 2bee2e42ae2f..3e92be1d2d43 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -927,15 +927,6 @@ struct platform_nand_data { struct platform_nand_ctrl ctrl; }; -/* Some helpers to access the data structures */ -static inline -struct platform_nand_chip *get_platform_nandchip(struct mtd_info *mtd) -{ - struct nand_chip *chip = mtd->priv; - - return chip->priv; -} - /* return the supported features. */ static inline int onfi_feature(struct nand_chip *chip) { -- cgit v1.2.3 From 052876f8e5aec887d22c4d06e54aa5531ffcec75 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 18 Dec 2015 17:20:09 -0800 Subject: Input: uinput - add new UINPUT_DEV_SETUP and UI_ABS_SETUP ioctl This adds two new ioctls, UINPUT_DEV_SETUP and UI_ABS_SETUP, that replaces the old device setup method (by write()'ing "struct uinput_user_dev" to the node). The old method is not easily extendable and requires huge payloads. Furthermore, overloading write() without properly versioned objects is error-prone. Therefore, we introduce two new ioctls to replace the old method. These ioctls support all features of the old method, plus a "resolution" field for absinfo. Furthermore, it's properly forward-compatible to new ABS codes and a growing "struct input_absinfo" structure. UI_ABS_SETUP also allows user-space to skip unknown axes if not set. There is no need to copy the whole array temporarily into the kernel, but instead the caller issues several ioctl where we copy each value manually. Signed-off-by: David Herrmann Signed-off-by: Benjamin Tissoires Reviewed-by: David Herrmann Signed-off-by: Dmitry Torokhov --- drivers/input/misc/uinput.c | 86 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/uinput.h | 5 +++ include/uapi/linux/uinput.h | 83 +++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 168 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index 5adbcedcb81c..a16fc4a4bb1f 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -370,8 +370,78 @@ static int uinput_allocate_device(struct uinput_device *udev) return 0; } -static int uinput_setup_device(struct uinput_device *udev, - const char __user *buffer, size_t count) +static int uinput_dev_setup(struct uinput_device *udev, + struct uinput_setup __user *arg) +{ + struct uinput_setup setup; + struct input_dev *dev; + int retval; + + if (udev->state == UIST_CREATED) + return -EINVAL; + + if (copy_from_user(&setup, arg, sizeof(setup))) + return -EFAULT; + + if (!setup.name[0]) + return -EINVAL; + + dev = udev->dev; + dev->id = setup.id; + udev->ff_effects_max = setup.ff_effects_max; + + kfree(dev->name); + dev->name = kstrndup(setup.name, UINPUT_MAX_NAME_SIZE, GFP_KERNEL); + if (!dev->name) + return -ENOMEM; + + retval = uinput_validate_absbits(dev); + if (retval < 0) + return retval; + + udev->state = UIST_SETUP_COMPLETE; + return 0; +} + +static int uinput_abs_setup(struct uinput_device *udev, + struct uinput_setup __user *arg, size_t size) +{ + struct uinput_abs_setup setup = {}; + struct input_dev *dev; + + if (size > sizeof(setup)) + return -E2BIG; + + if (udev->state == UIST_CREATED) + return -EINVAL; + + if (copy_from_user(&setup, arg, size)) + return -EFAULT; + + if (setup.code > ABS_MAX) + return -ERANGE; + + dev = udev->dev; + + input_alloc_absinfo(dev); + if (!dev->absinfo) + return -ENOMEM; + + set_bit(setup.code, dev->absbit); + dev->absinfo[setup.code] = setup.absinfo; + + /* + * We restore the state to UIST_NEW_DEVICE because the user has to call + * UI_DEV_SETUP in the last place before UI_DEV_CREATE to check the + * validity of the absbits. + */ + udev->state = UIST_NEW_DEVICE; + return 0; +} + +/* legacy setup via write() */ +static int uinput_setup_device_legacy(struct uinput_device *udev, + const char __user *buffer, size_t count) { struct uinput_user_dev *user_dev; struct input_dev *dev; @@ -474,7 +544,7 @@ static ssize_t uinput_write(struct file *file, const char __user *buffer, retval = udev->state == UIST_CREATED ? uinput_inject_events(udev, buffer, count) : - uinput_setup_device(udev, buffer, count); + uinput_setup_device_legacy(udev, buffer, count); mutex_unlock(&udev->mutex); @@ -735,6 +805,12 @@ static long uinput_ioctl_handler(struct file *file, unsigned int cmd, uinput_destroy_device(udev); goto out; + case UI_DEV_SETUP: + retval = uinput_dev_setup(udev, p); + goto out; + + /* UI_ABS_SETUP is handled in the variable size ioctls */ + case UI_SET_EVBIT: retval = uinput_set_bit(arg, evbit, EV_MAX); goto out; @@ -879,6 +955,10 @@ static long uinput_ioctl_handler(struct file *file, unsigned int cmd, name = dev_name(&udev->dev->dev); retval = uinput_str_to_user(p, name, size); goto out; + + case UI_ABS_SETUP & ~IOCSIZE_MASK: + retval = uinput_abs_setup(udev, p, size); + goto out; } retval = -EINVAL; diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 0994c0d01a09..75de43da2301 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -20,6 +20,11 @@ * Author: Aristeu Sergio Rozanski Filho * * Changes/Revisions: + * 0.5 08/13/2015 (David Herrmann & + * Benjamin Tissoires ) + * - add UI_DEV_SETUP ioctl + * - add UI_ABS_SETUP ioctl + * - add UI_GET_VERSION ioctl * 0.4 01/09/2014 (Benjamin Tissoires ) * - add UI_GET_SYSNAME ioctl * 0.3 24/05/2006 (Anssi Hannula ) diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h index 013c9d8db372..77b8cf73a178 100644 --- a/include/uapi/linux/uinput.h +++ b/include/uapi/linux/uinput.h @@ -20,6 +20,11 @@ * Author: Aristeu Sergio Rozanski Filho * * Changes/Revisions: + * 0.5 08/13/2015 (David Herrmann & + * Benjamin Tissoires ) + * - add UI_DEV_SETUP ioctl + * - add UI_ABS_SETUP ioctl + * - add UI_GET_VERSION ioctl * 0.4 01/09/2014 (Benjamin Tissoires ) * - add UI_GET_SYSNAME ioctl * 0.3 24/05/2006 (Anssi Hannula ) @@ -37,8 +42,8 @@ #include #include -#define UINPUT_VERSION 4 - +#define UINPUT_VERSION 5 +#define UINPUT_MAX_NAME_SIZE 80 struct uinput_ff_upload { __u32 request_id; @@ -58,6 +63,79 @@ struct uinput_ff_erase { #define UI_DEV_CREATE _IO(UINPUT_IOCTL_BASE, 1) #define UI_DEV_DESTROY _IO(UINPUT_IOCTL_BASE, 2) +struct uinput_setup { + struct input_id id; + char name[UINPUT_MAX_NAME_SIZE]; + __u32 ff_effects_max; +}; + +/** + * UI_DEV_SETUP - Set device parameters for setup + * + * This ioctl sets parameters for the input device to be created. It must be + * issued *before* calling UI_DEV_CREATE or it will fail. This ioctl supersedes + * the old "struct uinput_user_dev" method, which wrote this data via write(). + * To actually set the absolute axes, you also need to call the ioctl + * UI_ABS_SETUP *before* calling this ioctl. + * + * This ioctl takes a "struct uinput_setup" object as argument. The fields of + * this object are as follows: + * id: See the description of "struct input_id". This field is + * copied unchanged into the new device. + * name: This is used unchanged as name for the new device. + * ff_effects_max: This limits the maximum numbers of force-feedback effects. + * See below for a description of FF with uinput. + * + * This ioctl can be called multiple times and will overwrite previous values. + * If this ioctl fails with -EINVAL, you're recommended to use the old + * "uinput_user_dev" method via write() as fallback, in case you run on an old + * kernel that does not support this ioctl. + * + * This ioctl may fail with -EINVAL if it is not supported or if you passed + * incorrect values, -ENOMEM if the kernel runs out of memory or -EFAULT if the + * passed uinput_setup object cannot be read/written. + * If this call fails, partial data may have already been applied to the + * internal device. + */ +#define UI_DEV_SETUP _IOW(UINPUT_IOCTL_BASE, 3, struct uinput_setup) + +struct uinput_abs_setup { + __u16 code; /* axis code */ + /* __u16 filler; */ + struct input_absinfo absinfo; +}; + +/** + * UI_ABS_SETUP - Set absolute axis information for the device to setup + * + * This ioctl sets one absolute axis information for the input device to be + * created. It must be issued *before* calling UI_DEV_SETUP and UI_DEV_CREATE + * for every absolute axis the device exports. + * This ioctl supersedes the old "struct uinput_user_dev" method, which wrote + * part of this data and the content of UI_DEV_SETUP via write(). + * + * This ioctl takes a "struct uinput_abs_setup" object as argument. The fields + * of this object are as follows: + * code: The corresponding input code associated with this axis + * (ABS_X, ABS_Y, etc...) + * absinfo: See "struct input_absinfo" for a description of this field. + * This field is copied unchanged into the kernel for the + * specified axis. If the axis is not enabled via + * UI_SET_ABSBIT, this ioctl will enable it. + * + * This ioctl can be called multiple times and will overwrite previous values. + * If this ioctl fails with -EINVAL, you're recommended to use the old + * "uinput_user_dev" method via write() as fallback, in case you run on an old + * kernel that does not support this ioctl. + * + * This ioctl may fail with -EINVAL if it is not supported or if you passed + * incorrect values, -ENOMEM if the kernel runs out of memory or -EFAULT if the + * passed uinput_setup object cannot be read/written. + * If this call fails, partial data may have already been applied to the + * internal device. + */ +#define UI_ABS_SETUP _IOW(UINPUT_IOCTL_BASE, 4, struct uinput_abs_setup) + #define UI_SET_EVBIT _IOW(UINPUT_IOCTL_BASE, 100, int) #define UI_SET_KEYBIT _IOW(UINPUT_IOCTL_BASE, 101, int) #define UI_SET_RELBIT _IOW(UINPUT_IOCTL_BASE, 102, int) @@ -144,7 +222,6 @@ struct uinput_ff_erase { #define UI_FF_UPLOAD 1 #define UI_FF_ERASE 2 -#define UINPUT_MAX_NAME_SIZE 80 struct uinput_user_dev { char name[UINPUT_MAX_NAME_SIZE]; struct input_id id; -- cgit v1.2.3 From 1873315fb156cbc8e46f28e8b128f17ff6c31728 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 8 Dec 2015 16:38:12 +0100 Subject: mtd: sh_flctl: pass FIFO as physical address By convention, the FIFO address we pass using dmaengine_slave_config is a physical address in the form that is understood by the DMA engine, as a dma_addr_t, phys_addr_t or resource_size_t. The sh_flctl driver however passes a virtual __iomem address that gets cast to dma_addr_t in the slave driver. This happens to work on shmobile because that platform sets up an identity mapping for its MMIO regions, but such code is not portable to other platforms, and prevents us from ever changing the platform mapping or reusing the driver on other architectures like ARM64 that might not have the mapping. We also get a warning about a type mismatch for the case that dma_addr_t is wider than a pointer, i.e. when CONFIG_LPAE is set: drivers/mtd/nand/sh_flctl.c: In function 'flctl_setup_dma': drivers/mtd/nand/sh_flctl.c:163:17: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] cfg.dst_addr = (dma_addr_t)FLDTFIFO(flctl); This changes the driver to instead pass the physical address of the FIFO that is extracted from the MMIO resource, making the code more portable and avoiding the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Brian Norris --- drivers/mtd/nand/sh_flctl.c | 5 +++-- include/linux/mtd/sh_flctl.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c index c7126b75fb01..4814402902f9 100644 --- a/drivers/mtd/nand/sh_flctl.c +++ b/drivers/mtd/nand/sh_flctl.c @@ -160,7 +160,7 @@ static void flctl_setup_dma(struct sh_flctl *flctl) memset(&cfg, 0, sizeof(cfg)); cfg.direction = DMA_MEM_TO_DEV; - cfg.dst_addr = (dma_addr_t)FLDTFIFO(flctl); + cfg.dst_addr = flctl->fifo; cfg.src_addr = 0; ret = dmaengine_slave_config(flctl->chan_fifo0_tx, &cfg); if (ret < 0) @@ -176,7 +176,7 @@ static void flctl_setup_dma(struct sh_flctl *flctl) cfg.direction = DMA_DEV_TO_MEM; cfg.dst_addr = 0; - cfg.src_addr = (dma_addr_t)FLDTFIFO(flctl); + cfg.src_addr = flctl->fifo; ret = dmaengine_slave_config(flctl->chan_fifo0_rx, &cfg); if (ret < 0) goto err; @@ -1095,6 +1095,7 @@ static int flctl_probe(struct platform_device *pdev) flctl->reg = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(flctl->reg)) return PTR_ERR(flctl->reg); + flctl->fifo = res->start + 0x24; /* FLDTFIFO */ irq = platform_get_irq(pdev, 0); if (irq < 0) { diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 76e3e88bedfe..2251add65fa7 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -147,6 +147,7 @@ struct sh_flctl { struct platform_device *pdev; struct dev_pm_qos_request pm_qos; void __iomem *reg; + resource_size_t fifo; uint8_t done_buff[2048 + 64]; /* max size 2048 + 64 */ int read_bytes; -- cgit v1.2.3 From 9955a7835bf376e12482583958b2661f501b868b Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Mon, 21 Dec 2015 14:24:13 +0530 Subject: phy: omap-usb2: use *syscon* framework API to power on/off the PHY Deprecate using phy-omap-control driver to power on/off the PHY, and use *syscon* framework to do the same. This handles powering on/off the PHY for the USB2 PHYs used in various TI SoCs. Signed-off-by: Kishon Vijay Abraham I --- Documentation/devicetree/bindings/phy/ti-phy.txt | 8 ++- drivers/phy/phy-omap-usb2.c | 92 +++++++++++++++++++----- include/linux/phy/omap_usb.h | 23 ++++++ 3 files changed, 105 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt index 49e5b0c6ed87..a3b394587874 100644 --- a/Documentation/devicetree/bindings/phy/ti-phy.txt +++ b/Documentation/devicetree/bindings/phy/ti-phy.txt @@ -31,6 +31,8 @@ OMAP USB2 PHY Required properties: - compatible: Should be "ti,omap-usb2" + Should be "ti,dra7x-usb2-phy2" for the 2nd instance of USB2 PHY + in DRA7x - reg : Address and length of the register set for the device. - #phy-cells: determine the number of cells that should be given in the phandle while referencing this phy. @@ -40,10 +42,14 @@ Required properties: * "wkupclk" - wakeup clock. * "refclk" - reference clock (optional). -Optional properties: +Deprecated properties: - ctrl-module : phandle of the control module used by PHY driver to power on the PHY. +Recommended properies: +- syscon-phy-power : phandle/offset pair. Phandle to the system control + module and the register offset to power on/off the PHY. + This is usually a subnode of ocp2scp to which it is connected. usb2phy@4a0ad080 { diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c index c79633efd7fc..c134989052f5 100644 --- a/drivers/phy/phy-omap-usb2.c +++ b/drivers/phy/phy-omap-usb2.c @@ -29,6 +29,8 @@ #include #include #include +#include +#include #include #define USB2PHY_DISCON_BYP_LATCH (1 << 31) @@ -97,22 +99,38 @@ static int omap_usb_set_peripheral(struct usb_otg *otg, return 0; } +static int omap_usb_phy_power(struct omap_usb *phy, int on) +{ + u32 val; + int ret; + + if (!phy->syscon_phy_power) { + omap_control_phy_power(phy->control_dev, on); + return 0; + } + + if (on) + val = phy->power_on; + else + val = phy->power_off; + + ret = regmap_update_bits(phy->syscon_phy_power, phy->power_reg, + phy->mask, val); + return ret; +} + static int omap_usb_power_off(struct phy *x) { struct omap_usb *phy = phy_get_drvdata(x); - omap_control_phy_power(phy->control_dev, 0); - - return 0; + return omap_usb_phy_power(phy, false); } static int omap_usb_power_on(struct phy *x) { struct omap_usb *phy = phy_get_drvdata(x); - omap_control_phy_power(phy->control_dev, 1); - - return 0; + return omap_usb_phy_power(phy, true); } static int omap_usb_init(struct phy *x) @@ -147,21 +165,38 @@ static const struct phy_ops ops = { static const struct usb_phy_data omap_usb2_data = { .label = "omap_usb2", .flags = OMAP_USB2_HAS_START_SRP | OMAP_USB2_HAS_SET_VBUS, + .mask = OMAP_DEV_PHY_PD, + .power_off = OMAP_DEV_PHY_PD, }; static const struct usb_phy_data omap5_usb2_data = { .label = "omap5_usb2", .flags = 0, + .mask = OMAP_DEV_PHY_PD, + .power_off = OMAP_DEV_PHY_PD, }; static const struct usb_phy_data dra7x_usb2_data = { .label = "dra7x_usb2", .flags = OMAP_USB2_CALIBRATE_FALSE_DISCONNECT, + .mask = OMAP_DEV_PHY_PD, + .power_off = OMAP_DEV_PHY_PD, +}; + +static const struct usb_phy_data dra7x_usb2_phy2_data = { + .label = "dra7x_usb2_phy2", + .flags = OMAP_USB2_CALIBRATE_FALSE_DISCONNECT, + .mask = OMAP_USB2_PHY_PD, + .power_off = OMAP_USB2_PHY_PD, }; static const struct usb_phy_data am437x_usb2_data = { .label = "am437x_usb2", .flags = 0, + .mask = AM437X_USB2_PHY_PD | AM437X_USB2_OTG_PD | + AM437X_USB2_OTGVDET_EN | AM437X_USB2_OTGSESSEND_EN, + .power_on = AM437X_USB2_OTGVDET_EN | AM437X_USB2_OTGSESSEND_EN, + .power_off = AM437X_USB2_PHY_PD | AM437X_USB2_OTG_PD, }; static const struct of_device_id omap_usb2_id_table[] = { @@ -177,6 +212,10 @@ static const struct of_device_id omap_usb2_id_table[] = { .compatible = "ti,dra7x-usb2", .data = &dra7x_usb2_data, }, + { + .compatible = "ti,dra7x-usb2-phy2", + .data = &dra7x_usb2_phy2_data, + }, { .compatible = "ti,am437x-usb2", .data = &am437x_usb2_data, @@ -219,6 +258,9 @@ static int omap_usb2_probe(struct platform_device *pdev) phy->phy.label = phy_data->label; phy->phy.otg = otg; phy->phy.type = USB_PHY_TYPE_USB2; + phy->mask = phy_data->mask; + phy->power_on = phy_data->power_on; + phy->power_off = phy_data->power_off; if (phy_data->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) { res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -228,20 +270,36 @@ static int omap_usb2_probe(struct platform_device *pdev) phy->flags |= OMAP_USB2_CALIBRATE_FALSE_DISCONNECT; } - control_node = of_parse_phandle(node, "ctrl-module", 0); - if (!control_node) { - dev_err(&pdev->dev, "Failed to get control device phandle\n"); - return -EINVAL; - } + phy->syscon_phy_power = syscon_regmap_lookup_by_phandle(node, + "syscon-phy-power"); + if (IS_ERR(phy->syscon_phy_power)) { + dev_dbg(&pdev->dev, + "can't get syscon-phy-power, using control device\n"); + phy->syscon_phy_power = NULL; + + control_node = of_parse_phandle(node, "ctrl-module", 0); + if (!control_node) { + dev_err(&pdev->dev, + "Failed to get control device phandle\n"); + return -EINVAL; + } - control_pdev = of_find_device_by_node(control_node); - if (!control_pdev) { - dev_err(&pdev->dev, "Failed to get control device\n"); - return -EINVAL; + control_pdev = of_find_device_by_node(control_node); + if (!control_pdev) { + dev_err(&pdev->dev, "Failed to get control device\n"); + return -EINVAL; + } + phy->control_dev = &control_pdev->dev; + } else { + if (of_property_read_u32_index(node, + "syscon-phy-power", 1, + &phy->power_reg)) { + dev_err(&pdev->dev, + "couldn't get power reg. offset\n"); + return -EINVAL; + } } - phy->control_dev = &control_pdev->dev; - otg->set_host = omap_usb_set_host; otg->set_peripheral = omap_usb_set_peripheral; if (phy_data->flags & OMAP_USB2_HAS_SET_VBUS) diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h index dc2c541a619b..2e5fb870efa9 100644 --- a/include/linux/phy/omap_usb.h +++ b/include/linux/phy/omap_usb.h @@ -30,6 +30,12 @@ struct usb_dpll_params { u32 mf; }; +enum omap_usb_phy_type { + TYPE_USB2, /* USB2_PHY, power down in CONTROL_DEV_CONF */ + TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */ + TYPE_AM437USB2, /* USB2 PHY, power e.g. AM437x */ +}; + struct omap_usb { struct usb_phy phy; struct phy_companion *comparator; @@ -40,11 +46,20 @@ struct omap_usb { struct clk *wkupclk; struct clk *optclk; u8 flags; + enum omap_usb_phy_type type; + struct regmap *syscon_phy_power; /* ctrl. reg. acces */ + unsigned int power_reg; /* power reg. index within syscon */ + u32 mask; + u32 power_on; + u32 power_off; }; struct usb_phy_data { const char *label; u8 flags; + u32 mask; + u32 power_on; + u32 power_off; }; /* Driver Flags */ @@ -52,6 +67,14 @@ struct usb_phy_data { #define OMAP_USB2_HAS_SET_VBUS (1 << 1) #define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT (1 << 2) +#define OMAP_DEV_PHY_PD BIT(0) +#define OMAP_USB2_PHY_PD BIT(28) + +#define AM437X_USB2_PHY_PD BIT(0) +#define AM437X_USB2_OTG_PD BIT(1) +#define AM437X_USB2_OTGVDET_EN BIT(19) +#define AM437X_USB2_OTGSESSEND_EN BIT(20) + #define phy_to_omapusb(x) container_of((x), struct omap_usb, phy) #if defined(CONFIG_OMAP_USB2) || defined(CONFIG_OMAP_USB2_MODULE) -- cgit v1.2.3 From 2048157ad02e65f6327118dd4a7b9c9f1fd12f77 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 21 Dec 2015 12:21:22 -0800 Subject: Drivers: hv: vmbus: fix the building warning with hyperv-keyboard With the recent change af3ff643ea91ba64dd8d0b1cbed54d44512f96cd (Drivers: hv: vmbus: Use uuid_le type consistently), we always get this warning: CC [M] drivers/input/serio/hyperv-keyboard.o drivers/input/serio/hyperv-keyboard.c:427:2: warning: missing braces around initializer [-Wmissing-braces] { HV_KBD_GUID, }, ^ drivers/input/serio/hyperv-keyboard.c:427:2: warning: (near initialization for .id_table[0].guid.b.) [-Wmissing-braces] The patch fixes the warning. Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- drivers/input/serio/hyperv-keyboard.c | 10 ---------- include/linux/hyperv.h | 8 ++++++++ 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/input/serio/hyperv-keyboard.c b/drivers/input/serio/hyperv-keyboard.c index e74e5d6e5f9f..c948866edf87 100644 --- a/drivers/input/serio/hyperv-keyboard.c +++ b/drivers/input/serio/hyperv-keyboard.c @@ -412,16 +412,6 @@ static int hv_kbd_remove(struct hv_device *hv_dev) return 0; } -/* - * Keyboard GUID - * {f912ad6d-2b17-48ea-bd65-f927a61c7684} - */ -#define HV_KBD_GUID \ - .guid = { \ - 0x6d, 0xad, 0x12, 0xf9, 0x17, 0x2b, 0xea, 0x48, \ - 0xbd, 0x65, 0xf9, 0x27, 0xa6, 0x1c, 0x76, 0x84 \ - } - static const struct hv_vmbus_device_id id_table[] = { /* Keyboard guid */ { HV_KBD_GUID, }, diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 179ff330af59..753dbad0bf94 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1078,6 +1078,14 @@ u64 hv_do_hypercall(u64 control, void *input, void *output); .guid = UUID_LE(0xcfa8b69e, 0x5b4a, 0x4cc0, 0xb9, 0x8b, \ 0x8b, 0xa1, 0xa1, 0xf3, 0xf9, 0x5a) +/* + * Keyboard GUID + * {f912ad6d-2b17-48ea-bd65-f927a61c7684} + */ +#define HV_KBD_GUID \ + .guid = UUID_LE(0xf912ad6d, 0x2b17, 0x48ea, 0xbd, 0x65, \ + 0xf9, 0x27, 0xa6, 0x1c, 0x76, 0x84) + /* * VSS (Backup/Restore) GUID */ -- cgit v1.2.3 From 03a76b60f8ba27974e2d252bc555d2c103420e15 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 21 Dec 2015 15:13:33 -0700 Subject: vfio: Include No-IOMMU mode There is really no way to safely give a user full access to a DMA capable device without an IOMMU to protect the host system. There is also no way to provide DMA translation, for use cases such as device assignment to virtual machines. However, there are still those users that want userspace drivers even under those conditions. The UIO driver exists for this use case, but does not provide the degree of device access and programming that VFIO has. In an effort to avoid code duplication, this introduces a No-IOMMU mode for VFIO. This mode requires building VFIO with CONFIG_VFIO_NOIOMMU and enabling the "enable_unsafe_noiommu_mode" option on the vfio driver. This should make it very clear that this mode is not safe. Additionally, CAP_SYS_RAWIO privileges are necessary to work with groups and containers using this mode. Groups making use of this support are named /dev/vfio/noiommu-$GROUP and can only make use of the special VFIO_NOIOMMU_IOMMU for the container. Use of this mode, specifically binding a device without a native IOMMU group to a VFIO bus driver will taint the kernel and should therefore not be considered supported. This patch includes no-iommu support for the vfio-pci bus driver only. Signed-off-by: Alex Williamson Acked-by: Michael S. Tsirkin --- drivers/vfio/Kconfig | 15 ++++ drivers/vfio/pci/vfio_pci.c | 8 +- drivers/vfio/vfio.c | 184 +++++++++++++++++++++++++++++++++++++++++++- include/linux/vfio.h | 3 + include/uapi/linux/vfio.h | 7 ++ 5 files changed, 210 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 850d86ca685b..da6e2ce77495 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,6 +31,21 @@ menuconfig VFIO If you don't know what to do here, say N. +menuconfig VFIO_NOIOMMU + bool "VFIO No-IOMMU support" + depends on VFIO + help + VFIO is built on the ability to isolate devices using the IOMMU. + Only with an IOMMU can userspace access to DMA capable devices be + considered secure. VFIO No-IOMMU mode enables IOMMU groups for + devices without IOMMU backing for the purpose of re-using the VFIO + infrastructure in a non-secure mode. Use of this mode will result + in an unsupportable kernel and will therefore taint the kernel. + Device assignment to virtual machines is also not possible with + this mode since there is no IOMMU to provide DMA translation. + + If you don't know what to do here, say N. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 56bf6dbb93db..2760a7ba3f30 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = iommu_group_get(&pdev->dev); + group = vfio_iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - iommu_group_put(pdev->dev.iommu_group); + vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); kfree(vdev); if (vfio_pci_is_vga(pdev)) { diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6070b793cbcb..82f25cc1c460 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -62,6 +62,7 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; + bool noiommu; }; struct vfio_unbound_dev { @@ -84,6 +85,7 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; + bool noiommu; }; struct vfio_device { @@ -95,6 +97,128 @@ struct vfio_device { void *device_data; }; +#ifdef CONFIG_VFIO_NOIOMMU +static bool noiommu __read_mostly; +module_param_named(enable_unsafe_noiommu_mode, + noiommu, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); +#endif + +/* + * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe + * and remove functions, any use cases other than acquiring the first + * reference for the purpose of calling vfio_add_group_dev() or removing + * that symmetric reference after vfio_del_group_dev() should use the raw + * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() + * removes the device from the dummy group and cannot be nested. + */ +struct iommu_group *vfio_iommu_group_get(struct device *dev) +{ + struct iommu_group *group; + int __maybe_unused ret; + + group = iommu_group_get(dev); + +#ifdef CONFIG_VFIO_NOIOMMU + /* + * With noiommu enabled, an IOMMU group will be created for a device + * that doesn't already have one and doesn't have an iommu_ops on their + * bus. We use iommu_present() again in the main code to detect these + * fake groups. + */ + if (group || !noiommu || iommu_present(dev->bus)) + return group; + + group = iommu_group_alloc(); + if (IS_ERR(group)) + return NULL; + + iommu_group_set_name(group, "vfio-noiommu"); + ret = iommu_group_add_device(group, dev); + iommu_group_put(group); + if (ret) + return NULL; + + /* + * Where to taint? At this point we've added an IOMMU group for a + * device that is not backed by iommu_ops, therefore any iommu_ + * callback using iommu_ops can legitimately Oops. So, while we may + * be about to give a DMA capable device to a user without IOMMU + * protection, which is clearly taint-worthy, let's go ahead and do + * it here. + */ + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); +#endif + + return group; +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_get); + +void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) +{ +#ifdef CONFIG_VFIO_NOIOMMU + if (!iommu_present(dev->bus)) + iommu_group_remove_device(dev); +#endif + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_put); + +#ifdef CONFIG_VFIO_NOIOMMU +static void *vfio_noiommu_open(unsigned long arg) +{ + if (arg != VFIO_NOIOMMU_IOMMU) + return ERR_PTR(-EINVAL); + if (!capable(CAP_SYS_RAWIO)) + return ERR_PTR(-EPERM); + + return NULL; +} + +static void vfio_noiommu_release(void *iommu_data) +{ +} + +static long vfio_noiommu_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + if (cmd == VFIO_CHECK_EXTENSION) + return noiommu && (arg == VFIO_NOIOMMU_IOMMU) ? 1 : 0; + + return -ENOTTY; +} + +static int vfio_iommu_present(struct device *dev, void *unused) +{ + return iommu_present(dev->bus) ? 1 : 0; +} + +static int vfio_noiommu_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + return iommu_group_for_each_dev(iommu_group, NULL, + vfio_iommu_present) ? -EINVAL : 0; +} + +static void vfio_noiommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ +} + +static const struct vfio_iommu_driver_ops vfio_noiommu_ops = { + .name = "vfio-noiommu", + .owner = THIS_MODULE, + .open = vfio_noiommu_open, + .release = vfio_noiommu_release, + .ioctl = vfio_noiommu_ioctl, + .attach_group = vfio_noiommu_attach_group, + .detach_group = vfio_noiommu_detach_group, +}; +#endif + + /** * IOMMU driver registration */ @@ -199,7 +323,8 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, + bool iommu_present) { struct vfio_group *group, *tmp; struct device *dev; @@ -217,6 +342,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; + group->noiommu = !iommu_present; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -252,7 +378,8 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%d", iommu_group_id(iommu_group)); + group, "%s%d", group->noiommu ? "noiommu-" : "", + iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -640,7 +767,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group); + group = vfio_create_group(iommu_group, iommu_present(dev->bus)); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -854,6 +981,14 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, mutex_lock(&vfio.iommu_drivers_lock); list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { + +#ifdef CONFIG_VFIO_NOIOMMU + if (!list_empty(&container->group_list) && + (container->noiommu != + (driver->ops == &vfio_noiommu_ops))) + continue; +#endif + if (!try_module_get(driver->ops->owner)) continue; @@ -925,6 +1060,15 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { void *data; +#ifdef CONFIG_VFIO_NOIOMMU + /* + * Only noiommu containers can use vfio-noiommu and noiommu + * containers can only use vfio-noiommu. + */ + if (container->noiommu != (driver->ops == &vfio_noiommu_ops)) + continue; +#endif + if (!try_module_get(driver->ops->owner)) continue; @@ -1187,6 +1331,9 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1202,6 +1349,13 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); + /* Real groups and fake groups cannot mix */ + if (!list_empty(&container->group_list) && + container->noiommu != group->noiommu) { + ret = -EPERM; + goto unlock_out; + } + driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1211,6 +1365,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; + container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1241,6 +1396,9 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1283,6 +1441,10 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); + if (group->noiommu) + dev_warn(device->dev, "vfio-noiommu device opened by user " + "(%s:%d)\n", current->comm, task_pid_nr(current)); + return ret; } @@ -1371,6 +1533,11 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) { + vfio_group_put(group); + return -EPERM; + } + /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1533,6 +1700,11 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); + if (group->noiommu) { + atomic_dec(&group->container_users); + return ERR_PTR(-EPERM); + } + if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); @@ -1625,6 +1797,9 @@ static int __init vfio_init(void) request_module_nowait("vfio_iommu_type1"); request_module_nowait("vfio_iommu_spapr_tce"); +#ifdef CONFIG_VFIO_NOIOMMU + vfio_register_iommu_driver(&vfio_noiommu_ops); +#endif return 0; err_cdev_add: @@ -1641,6 +1816,9 @@ static void __exit vfio_cleanup(void) { WARN_ON(!list_empty(&vfio.group_list)); +#ifdef CONFIG_VFIO_NOIOMMU + vfio_unregister_iommu_driver(&vfio_noiommu_ops); +#endif idr_destroy(&vfio.group_idr); cdev_del(&vfio.group_cdev); unregister_chrdev_region(vfio.group_devt, MINORMASK); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ddb440975382..610a86a892b8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,6 +44,9 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; +extern struct iommu_group *vfio_iommu_group_get(struct device *dev); +extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); + extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d1172331ca62..7d7a4c6f2090 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -38,6 +38,13 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 +/* + * The No-IOMMU IOMMU offers no translation or isolation for devices and + * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU + * code will taint the host kernel and should be used with extreme caution. + */ +#define VFIO_NOIOMMU_IOMMU 8 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between -- cgit v1.2.3 From 7d2c2acac577959dbbddefefa91d1ba1b80460b3 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 14 Dec 2015 16:35:57 -0600 Subject: iio: Make IIO value formating function globally available. Make IIO value formating function globally available to allow IIO drivers to output values as the core does. Signed-off-by: Andrew F. Davis Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 1 + include/linux/iio/iio.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index d0a84febd435..a45eb2c53d0f 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -470,6 +470,7 @@ ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals) return 0; } } +EXPORT_SYMBOL_GPL(iio_format_value); static ssize_t iio_read_channel_info(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 19c94c9acc81..b5894118755f 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -636,6 +636,8 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) } #endif +ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals); + int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, int *fract); -- cgit v1.2.3 From 8a0859b65b06ea07461271ce4f1fe25b48d1ec55 Mon Sep 17 00:00:00 2001 From: "Du, Changbin" Date: Fri, 18 Dec 2015 15:36:40 +0800 Subject: usb: gadget: forbid queuing request to a disabled ep Queue a request to disabled ep doesn't make sense, and induce caller make mistakes. Here is a example for the android mtp gadget function driver. A mem corruption can happen on below senario. 1) On disconnect, mtp driver disable its EPs, 2) During send_file_work and receive_file_work, mtp queues a request to ep. (The mtp driver need improve its synchronization logic!) 3) mtp_function_unbind is invoked and all mtp requests are freed. 4) when udc process the request queued on step 2, will cause kernel NULL pointer dereference exception. Signed-off-by: Du, Changbin Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 92467eea76de..d82d0068872b 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -402,6 +402,9 @@ static inline void usb_ep_free_request(struct usb_ep *ep, static inline int usb_ep_queue(struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags) { + if (WARN_ON_ONCE(!ep->enabled && ep->address)) + return -ESHUTDOWN; + return ep->ops->queue(ep, req, gfp_flags); } -- cgit v1.2.3 From de2dd0eb30af55d3893979d5641c50c7a8969c99 Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 30 Nov 2015 10:48:52 +0800 Subject: genalloc:support memory-allocation with bytes-alignment to genalloc Bytes alignment is required to manage some special RAM, so add gen_pool_first_fit_align to genalloc, meanwhile add gen_pool_alloc_algo to pass algo in case user layer using more than one algo, and pass data to gen_pool_first_fit_align(modify gen_pool_alloc as a wrapper) Signed-off-by: Zhao Qiang Signed-off-by: Scott Wood --- include/linux/genalloc.h | 27 +++++++++++++++++---- lib/genalloc.c | 61 +++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 78 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 7ff168d06967..3c676ce46ee0 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -30,10 +30,12 @@ #ifndef __GENALLOC_H__ #define __GENALLOC_H__ +#include #include struct device; struct device_node; +struct gen_pool; /** * Allocation callback function type definition @@ -47,7 +49,7 @@ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, - void *data); + void *data, struct gen_pool *pool); /* * General purpose special memory pool descriptor. @@ -75,6 +77,13 @@ struct gen_pool_chunk { unsigned long bits[0]; /* bitmap for allocating memory chunk */ }; +/* + * gen_pool data descriptor for gen_pool_first_fit_align. + */ +struct genpool_data_align { + int align; /* alignment by bytes for starting address */ +}; + extern struct gen_pool *gen_pool_create(int, int); extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long); extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t, @@ -98,6 +107,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr, } extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); +extern unsigned long gen_pool_alloc_algo(struct gen_pool *, size_t, + genpool_algo_t algo, void *data); extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size, dma_addr_t *dma); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); @@ -110,14 +121,22 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data); extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data); + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool); + +extern unsigned long gen_pool_first_fit_align(unsigned long *map, + unsigned long size, unsigned long start, unsigned int nr, + void *data, struct gen_pool *pool); + extern unsigned long gen_pool_first_fit_order_align(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, - void *data); + void *data, struct gen_pool *pool); extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data); + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool); + extern struct gen_pool *devm_gen_pool_create(struct device *dev, int min_alloc_order, int nid, const char *name); diff --git a/lib/genalloc.c b/lib/genalloc.c index 116a166b096f..b8cf89d9e17d 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -269,6 +269,25 @@ EXPORT_SYMBOL(gen_pool_destroy); * NMI-safe cmpxchg implementation. */ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) +{ + return gen_pool_alloc_algo(pool, size, pool->algo, pool->data); +} +EXPORT_SYMBOL(gen_pool_alloc); + +/** + * gen_pool_alloc_algo - allocate special memory from the pool + * @pool: pool to allocate from + * @size: number of bytes to allocate from the pool + * @algo: algorithm passed from caller + * @data: data passed to algorithm + * + * Allocate the requested number of bytes from the specified pool. + * Uses the pool allocation function (with first-fit algorithm by default). + * Can not be used in NMI handler on architectures without + * NMI-safe cmpxchg implementation. + */ +unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size, + genpool_algo_t algo, void *data) { struct gen_pool_chunk *chunk; unsigned long addr = 0; @@ -290,8 +309,8 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size) end_bit = chunk_size(chunk) >> order; retry: - start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits, - pool->data); + start_bit = algo(chunk->bits, end_bit, start_bit, + nbits, data, pool); if (start_bit >= end_bit) continue; remain = bitmap_set_ll(chunk->bits, start_bit, nbits); @@ -310,7 +329,7 @@ retry: rcu_read_unlock(); return addr; } -EXPORT_SYMBOL(gen_pool_alloc); +EXPORT_SYMBOL(gen_pool_alloc_algo); /** * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage @@ -501,14 +520,41 @@ EXPORT_SYMBOL(gen_pool_set_algo); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from */ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data) + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) { return bitmap_find_next_zero_area(map, size, start, nr, 0); } EXPORT_SYMBOL(gen_pool_first_fit); +/** + * gen_pool_first_fit_align - find the first available region + * of memory matching the size requirement (alignment constraint) + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: data for alignment + * @pool: pool to get order from + */ +unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) +{ + struct genpool_data_align *alignment; + unsigned long align_mask; + int order; + + alignment = data; + order = pool->min_alloc_order; + align_mask = ((alignment->align + (1UL << order) - 1) >> order) - 1; + return bitmap_find_next_zero_area(map, size, start, nr, align_mask); +} +EXPORT_SYMBOL(gen_pool_first_fit_align); + /** * gen_pool_first_fit_order_align - find the first available region * of memory matching the size requirement. The region will be aligned @@ -518,10 +564,11 @@ EXPORT_SYMBOL(gen_pool_first_fit); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from */ unsigned long gen_pool_first_fit_order_align(unsigned long *map, unsigned long size, unsigned long start, - unsigned int nr, void *data) + unsigned int nr, void *data, struct gen_pool *pool) { unsigned long align_mask = roundup_pow_of_two(nr) - 1; @@ -537,12 +584,14 @@ EXPORT_SYMBOL(gen_pool_first_fit_order_align); * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @data: additional data - unused + * @pool: pool to find the fit region memory from * * Iterate over the bitmap to find the smallest free region * which we can allocate the memory. */ unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size, - unsigned long start, unsigned int nr, void *data) + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) { unsigned long start_bit = size; unsigned long len = size + 1; -- cgit v1.2.3 From b26981c8f743d3cb64a6907eb1f5c6c4ba6ca672 Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 30 Nov 2015 10:48:53 +0800 Subject: genalloc:support allocating specific region Add new algo for genalloc, it reserve a specific region of memory Signed-off-by: Zhao Qiang Signed-off-by: Scott Wood --- include/linux/genalloc.h | 11 +++++++++++ lib/genalloc.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 3c676ce46ee0..29d4385903d4 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -84,6 +84,13 @@ struct genpool_data_align { int align; /* alignment by bytes for starting address */ }; +/* + * gen_pool data descriptor for gen_pool_fixed_alloc. + */ +struct genpool_data_fixed { + unsigned long offset; /* The offset of the specific region */ +}; + extern struct gen_pool *gen_pool_create(int, int); extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long); extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t, @@ -124,6 +131,10 @@ extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data, struct gen_pool *pool); +extern unsigned long gen_pool_fixed_alloc(unsigned long *map, + unsigned long size, unsigned long start, unsigned int nr, + void *data, struct gen_pool *pool); + extern unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, void *data, struct gen_pool *pool); diff --git a/lib/genalloc.c b/lib/genalloc.c index b8cf89d9e17d..5ec83cd93284 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -555,6 +555,38 @@ unsigned long gen_pool_first_fit_align(unsigned long *map, unsigned long size, } EXPORT_SYMBOL(gen_pool_first_fit_align); +/** + * gen_pool_fixed_alloc - reserve a specific region + * @map: The address to base the search on + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + * @nr: The number of zeroed bits we're looking for + * @data: data for alignment + * @pool: pool to get order from + */ +unsigned long gen_pool_fixed_alloc(unsigned long *map, unsigned long size, + unsigned long start, unsigned int nr, void *data, + struct gen_pool *pool) +{ + struct genpool_data_fixed *fixed_data; + int order; + unsigned long offset_bit; + unsigned long start_bit; + + fixed_data = data; + order = pool->min_alloc_order; + offset_bit = fixed_data->offset >> order; + if (WARN_ON(fixed_data->offset & (1UL << order - 1))) + return size; + + start_bit = bitmap_find_next_zero_area(map, size, + start + offset_bit, nr, 0); + if (start_bit != offset_bit) + start_bit = size; + return start_bit; +} +EXPORT_SYMBOL(gen_pool_fixed_alloc); + /** * gen_pool_first_fit_order_align - find the first available region * of memory matching the size requirement. The region will be aligned -- cgit v1.2.3 From c3d4879e01bec484f50a78c108341f039d470e96 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Fri, 11 Dec 2015 16:45:58 -0500 Subject: sunrpc: Add a function to close temporary transports immediately Add a function svc_age_temp_xprts_now() to close temporary transports whose xpt_local matches the address passed in server_addr immediately instead of waiting for them to be closed by the timer function. The function is intended to be used by notifier_blocks that will be added to nfsd and lockd that will run when an ip address is deleted. This will eliminate the ACK storms and client hangs that occur in HA-NFS configurations where nfsd & lockd is left running on the cluster nodes all the time and the NFS 'service' is migrated back and forth within a short timeframe. Signed-off-by: Scott Mayhew Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 1 + net/sunrpc/svc_xprt.c | 45 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 78512cfe1fe6..b7dabc4baafd 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -128,6 +128,7 @@ struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, const unsigned short port); int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen); void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *xprt); +void svc_age_temp_xprts_now(struct svc_serv *, struct sockaddr *); static inline void svc_xprt_get(struct svc_xprt *xprt) { diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index a6cbb2104667..7422f28818b2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -10,11 +10,13 @@ #include #include #include +#include #include #include #include #include #include +#include #include #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -938,6 +940,49 @@ static void svc_age_temp_xprts(unsigned long closure) mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } +/* Close temporary transports whose xpt_local matches server_addr immediately + * instead of waiting for them to be picked up by the timer. + * + * This is meant to be called from a notifier_block that runs when an ip + * address is deleted. + */ +void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) +{ + struct svc_xprt *xprt; + struct svc_sock *svsk; + struct socket *sock; + struct list_head *le, *next; + LIST_HEAD(to_be_closed); + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + spin_lock_bh(&serv->sv_lock); + list_for_each_safe(le, next, &serv->sv_tempsocks) { + xprt = list_entry(le, struct svc_xprt, xpt_list); + if (rpc_cmp_addr(server_addr, (struct sockaddr *) + &xprt->xpt_local)) { + dprintk("svc_age_temp_xprts_now: found %p\n", xprt); + list_move(le, &to_be_closed); + } + } + spin_unlock_bh(&serv->sv_lock); + + while (!list_empty(&to_be_closed)) { + le = to_be_closed.next; + list_del_init(le); + xprt = list_entry(le, struct svc_xprt, xpt_list); + dprintk("svc_age_temp_xprts_now: closing %p\n", xprt); + svsk = container_of(xprt, struct svc_sock, sk_xprt); + sock = svsk->sk_sock; + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); + svc_close_xprt(xprt); + } +} +EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now); + static void call_xpt_users(struct svc_xprt *xprt) { struct svc_xpt_user *u; -- cgit v1.2.3 From d8ce9bf5551bfea431893bdd0a943f24a5170828 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Sun, 27 Dec 2015 17:25:20 +0800 Subject: HID: move to_hid_device() to hid.h to_hid_device() macro is defined in both hid-lg4ff.c and hid-logitech-hidpp.c. So I move it to include/linux/hid.h. Signed-off-by: Geliang Tang Signed-off-by: Jiri Kosina --- drivers/hid/hid-lg4ff.c | 2 -- drivers/hid/hid-logitech-hidpp.c | 2 -- include/linux/hid.h | 3 +++ 3 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index fbddcb37ae98..3e160ff5f218 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -33,8 +33,6 @@ #include "hid-lg4ff.h" #include "hid-ids.h" -#define to_hid_device(pdev) container_of(pdev, struct hid_device, dev) - #define LG4FF_MMODE_IS_MULTIMODE 0 #define LG4FF_MMODE_SWITCHED 1 #define LG4FF_MMODE_NOT_MULTIMODE 2 diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index f2a481125522..bd2ab476c65e 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -1310,8 +1310,6 @@ struct g920_private_data { u16 range; }; -#define to_hid_device(pdev) container_of(pdev, struct hid_device, dev) - static ssize_t g920_range_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/include/linux/hid.h b/include/linux/hid.h index a6d7a3fc2cb3..1472026367ed 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -565,6 +565,9 @@ struct hid_device { /* device report descriptor */ wait_queue_head_t debug_wait; }; +#define to_hid_device(pdev) \ + container_of(pdev, struct hid_device, dev) + static inline void *hid_get_drvdata(struct hid_device *hdev) { return dev_get_drvdata(&hdev->dev); -- cgit v1.2.3 From ba91a96718d17160890e161f702db6e60747248a Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Sun, 27 Dec 2015 17:25:22 +0800 Subject: HID: add a new helper to_hid_driver() Add a new helper to_hid_driver() and use it in hid-core.c. Signed-off-by: Geliang Tang Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 7 +++---- include/linux/hid.h | 3 +++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index a6e24e00a37b..9d75205a511e 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2077,7 +2077,7 @@ struct hid_dynid { static ssize_t store_new_id(struct device_driver *drv, const char *buf, size_t count) { - struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver); + struct hid_driver *hdrv = to_hid_driver(drv); struct hid_dynid *dynid; __u32 bus, vendor, product; unsigned long driver_data = 0; @@ -2139,7 +2139,7 @@ static const struct hid_device_id *hid_match_device(struct hid_device *hdev, static int hid_bus_match(struct device *dev, struct device_driver *drv) { - struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver); + struct hid_driver *hdrv = to_hid_driver(drv); struct hid_device *hdev = to_hid_device(dev); return hid_match_device(hdev, hdrv) != NULL; @@ -2147,8 +2147,7 @@ static int hid_bus_match(struct device *dev, struct device_driver *drv) static int hid_device_probe(struct device *dev) { - struct hid_driver *hdrv = container_of(dev->driver, - struct hid_driver, driver); + struct hid_driver *hdrv = to_hid_driver(dev->driver); struct hid_device *hdev = to_hid_device(dev); const struct hid_device_id *id; int ret = 0; diff --git a/include/linux/hid.h b/include/linux/hid.h index 1472026367ed..75b66eccc692 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -717,6 +717,9 @@ struct hid_driver { struct device_driver driver; }; +#define to_hid_driver(pdrv) \ + container_of(pdrv, struct hid_driver, driver) + /** * hid_ll_driver - low level driver callbacks * @start: called on probe to start the device -- cgit v1.2.3 From 9a4bf31d05a801e2358d96f69b39fb8ce2c69dd8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 10 Dec 2015 10:41:58 -0500 Subject: nfs: add new tracepoint for pnfs_update_layout pnfs_update_layout is really the "nexus" of layout handling. If it returns NULL then we end up going through the MDS. This patch adds some tracepoints to that function that allow us to determine the cause when we end up going through the MDS unexpectedly. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- fs/nfs/nfs4trace.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/nfs/pnfs.c | 38 +++++++++++++++++++++++++++++------ include/linux/nfs4.h | 14 +++++++++++++ 3 files changed, 102 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 8704372ac38f..238925c1aafd 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1442,6 +1442,62 @@ DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn); DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close); +#define show_pnfs_update_layout_reason(reason) \ + __print_symbolic(reason, \ + { PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" }, \ + { PNFS_UPDATE_LAYOUT_NO_PNFS, "no pnfs" }, \ + { PNFS_UPDATE_LAYOUT_RD_ZEROLEN, "read+zerolen" }, \ + { PNFS_UPDATE_LAYOUT_MDSTHRESH, "mdsthresh" }, \ + { PNFS_UPDATE_LAYOUT_NOMEM, "nomem" }, \ + { PNFS_UPDATE_LAYOUT_BULK_RECALL, "bulk recall" }, \ + { PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, "io test fail" }, \ + { PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \ + { PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \ + { PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \ + { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" }) + +TRACE_EVENT(pnfs_update_layout, + TP_PROTO(struct inode *inode, + loff_t pos, + u64 count, + enum pnfs_iomode iomode, + struct pnfs_layout_segment *lseg, + enum pnfs_update_layout_reason reason + ), + TP_ARGS(inode, pos, count, iomode, lseg, reason), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, fileid) + __field(u32, fhandle) + __field(loff_t, pos) + __field(u64, count) + __field(enum pnfs_iomode, iomode) + __field(struct pnfs_layout_segment *, lseg) + __field(enum pnfs_update_layout_reason, reason) + ), + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = NFS_FILEID(inode); + __entry->fhandle = nfs_fhandle_hash(NFS_FH(inode)); + __entry->pos = pos; + __entry->count = count; + __entry->iomode = iomode; + __entry->lseg = lseg; + __entry->reason = reason; + ), + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "iomode=%s pos=%llu count=%llu lseg=%p (%s)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + show_pnfs_iomode(__entry->iomode), + (unsigned long long)__entry->pos, + (unsigned long long)__entry->count, __entry->lseg, + show_pnfs_update_layout_reason(__entry->reason) + ) +); + #endif /* CONFIG_NFS_V4_1 */ #endif /* _TRACE_NFS4_H */ diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bec0384499f7..1489065bb051 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1520,14 +1520,23 @@ pnfs_update_layout(struct inode *ino, struct pnfs_layout_segment *lseg = NULL; bool first; - if (!pnfs_enabled_sb(NFS_SERVER(ino))) + if (!pnfs_enabled_sb(NFS_SERVER(ino))) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_NO_PNFS); goto out; + } - if (iomode == IOMODE_READ && i_size_read(ino) == 0) + if (iomode == IOMODE_READ && i_size_read(ino) == 0) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_RD_ZEROLEN); goto out; + } - if (pnfs_within_mdsthreshold(ctx, ino, iomode)) + if (pnfs_within_mdsthreshold(ctx, ino, iomode)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_MDSTHRESH); goto out; + } lookup_again: first = false; @@ -1535,19 +1544,26 @@ lookup_again: lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { spin_unlock(&ino->i_lock); + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_NOMEM); goto out; } /* Do we even need to bother with this? */ if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_BULK_RECALL); dprintk("%s matches recall, use MDS\n", __func__); goto out_unlock; } /* if LAYOUTGET already failed once we don't try again */ if (pnfs_layout_io_test_failed(lo, iomode) && - !pnfs_should_retry_layoutget(lo)) + !pnfs_should_retry_layoutget(lo)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_IO_TEST_FAIL); goto out_unlock; + } first = list_empty(&lo->plh_segs); if (first) { @@ -1567,8 +1583,11 @@ lookup_again: * already exists */ lseg = pnfs_find_lseg(lo, &arg); - if (lseg) + if (lseg) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_FOUND_CACHED); goto out_unlock; + } } /* @@ -1585,11 +1604,16 @@ lookup_again: dprintk("%s retrying\n", __func__); goto lookup_again; } + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_RETURN); goto out_put_layout_hdr; } - if (pnfs_layoutgets_blocked(lo)) + if (pnfs_layoutgets_blocked(lo)) { + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_BLOCKED); goto out_unlock; + } atomic_inc(&lo->plh_outstanding); spin_unlock(&ino->i_lock); @@ -1614,6 +1638,8 @@ lookup_again: lseg = send_layoutget(lo, ctx, &arg, gfp_flags); pnfs_clear_retry_layoutget(lo); atomic_dec(&lo->plh_outstanding); + trace_pnfs_update_layout(ino, pos, count, iomode, lseg, + PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET); out_put_layout_hdr: if (first) pnfs_clear_first_layoutget(lo); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e7e78537aea2..0e30f2c5ff49 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -592,4 +592,18 @@ enum data_content4 { NFS4_CONTENT_HOLE = 1, }; +enum pnfs_update_layout_reason { + PNFS_UPDATE_LAYOUT_UNKNOWN = 0, + PNFS_UPDATE_LAYOUT_NO_PNFS, + PNFS_UPDATE_LAYOUT_RD_ZEROLEN, + PNFS_UPDATE_LAYOUT_MDSTHRESH, + PNFS_UPDATE_LAYOUT_NOMEM, + PNFS_UPDATE_LAYOUT_BULK_RECALL, + PNFS_UPDATE_LAYOUT_IO_TEST_FAIL, + PNFS_UPDATE_LAYOUT_FOUND_CACHED, + PNFS_UPDATE_LAYOUT_RETURN, + PNFS_UPDATE_LAYOUT_BLOCKED, + PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, +}; + #endif -- cgit v1.2.3 From 99ade3c71b1e40e7174d6527709399a87f3d05e0 Mon Sep 17 00:00:00 2001 From: Andrew Elble Date: Wed, 2 Dec 2015 09:39:51 -0500 Subject: nfs: machine credential support for additional operations Allow LAYOUTRETURN and DELEGRETURN to use machine credentials if the server supports it. Add request for OPEN_DOWNGRADE as the close path also uses that. Signed-off-by: Andrew Elble Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 20 ++++++++++++++++++++ include/linux/nfs_fs_sb.h | 1 + 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 18d862db15b6..a7d564a83665 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5383,6 +5383,11 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co if (data == NULL) return -ENOMEM; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); + + nfs4_state_protect(server->nfs_client, + NFS_SP4_MACH_CRED_CLEANUP, + &task_setup_data.rpc_client, &msg); + data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; data->args.bitmask = server->cache_consistency_bitmask; @@ -6859,10 +6864,13 @@ static const struct nfs41_state_protection nfs4_sp4_mach_cred_request = { }, .allow.u.words = { [0] = 1 << (OP_CLOSE) | + 1 << (OP_OPEN_DOWNGRADE) | 1 << (OP_LOCKU) | + 1 << (OP_DELEGRETURN) | 1 << (OP_COMMIT), [1] = 1 << (OP_SECINFO - 32) | 1 << (OP_SECINFO_NO_NAME - 32) | + 1 << (OP_LAYOUTRETURN - 32) | 1 << (OP_TEST_STATEID - 32) | 1 << (OP_FREE_STATEID - 32) | 1 << (OP_WRITE - 32) @@ -6927,11 +6935,19 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, } if (test_bit(OP_CLOSE, sp->allow.u.longs) && + test_bit(OP_OPEN_DOWNGRADE, sp->allow.u.longs) && + test_bit(OP_DELEGRETURN, sp->allow.u.longs) && test_bit(OP_LOCKU, sp->allow.u.longs)) { dfprintk(MOUNT, " cleanup mode enabled\n"); set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); } + if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) { + dfprintk(MOUNT, " pnfs cleanup mode enabled\n"); + set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &clp->cl_sp4_flags); + } + if (test_bit(OP_SECINFO, sp->allow.u.longs) && test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { dfprintk(MOUNT, " secinfo mode enabled\n"); @@ -8084,6 +8100,10 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) }; int status = 0; + nfs4_state_protect(NFS_SERVER(lrp->args.inode)->nfs_client, + NFS_SP4_MACH_CRED_PNFS_CLEANUP, + &task_setup_data.rpc_client, &msg); + dprintk("--> %s\n", __func__); if (!sync) { lrp->inode = nfs_igrab_and_active(lrp->args.inode); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2469ab0bb3a1..7fcc13c8cf1f 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -102,6 +102,7 @@ struct nfs_client { #define NFS_SP4_MACH_CRED_STATEID 4 /* TEST_STATEID and FREE_STATEID */ #define NFS_SP4_MACH_CRED_WRITE 5 /* WRITE */ #define NFS_SP4_MACH_CRED_COMMIT 6 /* COMMIT */ +#define NFS_SP4_MACH_CRED_PNFS_CLEANUP 7 /* LAYOUTRETURN */ #endif /* CONFIG_NFS_V4 */ /* Our own IP address, as a null-terminated string. -- cgit v1.2.3 From d6c843b96e1cb5199147e3281a724e3c0b69a9ab Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 5 Dec 2015 16:20:43 +0800 Subject: nfs: only remove page from mapping if launder_page fails Instead of dropping pages when write fails, only do it when we get fatal failure in launder_page write back. Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/file.c | 2 +- fs/nfs/write.c | 39 +++++++++++++++++++++++---------------- include/linux/nfs_fs.h | 14 +++++++++++++- 3 files changed, 37 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 93e236429c5d..f188dd071dfc 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -545,7 +545,7 @@ static int nfs_launder_page(struct page *page) inode->i_ino, (long long)page_offset(page)); nfs_fscache_wait_on_page_write(nfsi, page); - return nfs_wb_page(inode, page); + return nfs_wb_launder_page(inode, page); } static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9dafb08ddae5..4d254232d728 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -559,7 +559,8 @@ static void nfs_write_error_remove_page(struct nfs_page *req) * May return an error if the user signalled nfs_wait_on_request(). */ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page, bool nonblock) + struct page *page, bool nonblock, + bool launder) { struct nfs_page *req; int ret = 0; @@ -578,17 +579,19 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, if (!nfs_pageio_add_request(pgio, req)) { ret = pgio->pg_error; /* - * Remove the problematic req upon fatal errors, - * while other dirty pages can still be around - * until they get flushed. + * Remove the problematic req upon fatal errors + * in launder case, while other dirty pages can + * still be around until they get flushed. */ if (nfs_error_is_fatal(ret)) { nfs_context_set_write_error(req->wb_context, ret); - nfs_write_error_remove_page(req); - } else { - nfs_redirty_request(req); - ret = -EAGAIN; + if (launder) { + nfs_write_error_remove_page(req); + goto out; + } } + nfs_redirty_request(req); + ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); @@ -596,12 +599,14 @@ out: return ret; } -static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) +static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, + struct nfs_pageio_descriptor *pgio, bool launder) { int ret; nfs_pageio_cond_complete(pgio, page_file_index(page)); - ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE, + launder); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; @@ -612,7 +617,9 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st /* * Write an mmapped page to the server. */ -static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc) +static int nfs_writepage_locked(struct page *page, + struct writeback_control *wbc, + bool launder) { struct nfs_pageio_descriptor pgio; struct inode *inode = page_file_mapping(page)->host; @@ -621,7 +628,7 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); - err = nfs_do_writepage(page, wbc, &pgio); + err = nfs_do_writepage(page, wbc, &pgio, launder); nfs_pageio_complete(&pgio); if (err < 0) return err; @@ -634,7 +641,7 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) { int ret; - ret = nfs_writepage_locked(page, wbc); + ret = nfs_writepage_locked(page, wbc, false); unlock_page(page); return ret; } @@ -643,7 +650,7 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * { int ret; - ret = nfs_do_writepage(page, wbc, data); + ret = nfs_do_writepage(page, wbc, data, false); unlock_page(page); return ret; } @@ -1931,7 +1938,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) /* * Write back all requests on one page - we do this before reading it. */ -int nfs_wb_page(struct inode *inode, struct page *page) +int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder) { loff_t range_start = page_file_offset(page); loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); @@ -1948,7 +1955,7 @@ int nfs_wb_page(struct inode *inode, struct page *page) for (;;) { wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { - ret = nfs_writepage_locked(page, &wbc); + ret = nfs_writepage_locked(page, &wbc, launder); if (ret < 0) goto out_error; continue; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..b88fc46cfbb8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -517,12 +517,24 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned */ extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); -extern int nfs_wb_page(struct inode *inode, struct page* page); +extern int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder); extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); +static inline int +nfs_wb_launder_page(struct inode *inode, struct page *page) +{ + return nfs_wb_single_page(inode, page, true); +} + +static inline int +nfs_wb_page(struct inode *inode, struct page *page) +{ + return nfs_wb_single_page(inode, page, false); +} + static inline int nfs_have_writebacks(struct inode *inode) { -- cgit v1.2.3 From 37e9ed22b1552fa94ee7db2901a5e7d8bdf60b15 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 22 Dec 2015 12:30:24 -0500 Subject: pNFS: Add flag to track if we've called nfs4_ff_layout_stat_io_start_read/write Signed-off-by: Trond Myklebust --- fs/nfs/flexfilelayout/flexfilelayout.c | 95 +++++++++++++++++++++++++--------- include/linux/nfs_xdr.h | 2 + 2 files changed, 72 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 14109a82ce84..9257679a15ba 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1279,14 +1279,31 @@ ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx) return ff_layout_test_devid_unavailable(node); } -static int ff_layout_read_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_read_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_read(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} + +static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_read(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, + hdr->res.count); +} +static int ff_layout_read_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1302,6 +1319,7 @@ static int ff_layout_read_prepare_common(struct rpc_task *task, } hdr->pgio_done_cb = ff_layout_read_done_cb; + ff_layout_read_record_layoutstats_start(task, hdr); return 0; } @@ -1360,10 +1378,6 @@ static void ff_layout_read_call_done(struct rpc_task *task, void *data) dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); - nfs4_ff_layout_stat_io_end_read(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags) && task->tk_status == 0) { nfs4_sequence_done(task, &hdr->res.seq_res); @@ -1378,6 +1392,7 @@ static void ff_layout_read_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; + ff_layout_read_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_READ]); } @@ -1453,14 +1468,31 @@ static int ff_layout_commit_done_cb(struct rpc_task *task, return 0; } -static int ff_layout_write_prepare_common(struct rpc_task *task, - struct nfs_pgio_header *hdr) +static void ff_layout_write_record_layoutstats_start(struct rpc_task *task, + struct nfs_pgio_header *hdr) { + if (test_and_set_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; nfs4_ff_layout_stat_io_start_write(hdr->inode, FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), hdr->args.count, task->tk_start); +} + +static void ff_layout_write_record_layoutstats_done(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ + if (!test_and_clear_bit(NFS_IOHDR_STAT, &hdr->flags)) + return; + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), + hdr->args.count, hdr->res.count, + hdr->res.verf->committed); +} +static int ff_layout_write_prepare_common(struct rpc_task *task, + struct nfs_pgio_header *hdr) +{ if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) { rpc_exit(task, -EIO); return -EIO; @@ -1477,6 +1509,7 @@ static int ff_layout_write_prepare_common(struct rpc_task *task, return -EAGAIN; } + ff_layout_write_record_layoutstats_start(task, hdr); return 0; } @@ -1526,23 +1559,45 @@ static void ff_layout_write_count_stats(struct rpc_task *task, void *data) { struct nfs_pgio_header *hdr = data; - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(hdr->lseg, hdr->pgio_mirror_idx), - hdr->args.count, hdr->res.count, - hdr->res.verf->committed); - + ff_layout_write_record_layoutstats_done(task, hdr); rpc_count_iostats_metrics(task, &NFS_CLIENT(hdr->inode)->cl_metrics[NFSPROC4_CLNT_WRITE]); } -static void ff_layout_commit_prepare_common(struct rpc_task *task, +static void ff_layout_commit_record_layoutstats_start(struct rpc_task *task, struct nfs_commit_data *cdata) { + if (test_and_set_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; nfs4_ff_layout_stat_io_start_write(cdata->inode, FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), 0, task->tk_start); } +static void ff_layout_commit_record_layoutstats_done(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + struct nfs_page *req; + __u64 count = 0; + + if (!test_and_clear_bit(NFS_IOHDR_STAT, &cdata->flags)) + return; + + if (task->tk_status == 0) { + list_for_each_entry(req, &cdata->pages, wb_list) + count += req->wb_bytes; + } + nfs4_ff_layout_stat_io_end_write(task, + FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), + count, count, NFS_FILE_SYNC); +} + +static void ff_layout_commit_prepare_common(struct rpc_task *task, + struct nfs_commit_data *cdata) +{ + ff_layout_commit_record_layoutstats_start(task, cdata); +} + static void ff_layout_commit_prepare_v3(struct rpc_task *task, void *data) { ff_layout_commit_prepare_common(task, data); @@ -1569,18 +1624,8 @@ static void ff_layout_commit_done(struct rpc_task *task, void *data) static void ff_layout_commit_count_stats(struct rpc_task *task, void *data) { struct nfs_commit_data *cdata = data; - struct nfs_page *req; - __u64 count = 0; - - if (task->tk_status == 0) { - list_for_each_entry(req, &cdata->pages, wb_list) - count += req->wb_bytes; - } - - nfs4_ff_layout_stat_io_end_write(task, - FF_LAYOUT_COMP(cdata->lseg, cdata->ds_commit_index), - count, count, NFS_FILE_SYNC); + ff_layout_commit_record_layoutstats_done(task, cdata); rpc_count_iostats_metrics(task, &NFS_CLIENT(cdata->inode)->cl_metrics[NFSPROC4_CLNT_COMMIT]); } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 11bbae44f4cb..7b30ac0c7def 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1375,6 +1375,7 @@ enum { NFS_IOHDR_ERROR = 0, NFS_IOHDR_EOF, NFS_IOHDR_REDO, + NFS_IOHDR_STAT, }; struct nfs_pgio_header { @@ -1454,6 +1455,7 @@ struct nfs_commit_data { const struct rpc_call_ops *mds_ops; const struct nfs_commit_completion_ops *completion_ops; int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data); + unsigned long flags; }; struct nfs_pgio_completion_ops { -- cgit v1.2.3 From dc602dd706cb64036132a7903ead1c67d9a7bcb9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 31 Dec 2015 11:44:06 -0500 Subject: NFS/pNFS: Fix up pNFS write reschedule layering violations and bugs The flexfiles layout in particular, seems to want to poke around in the O_DIRECT flags when retransmitting. This patch sets up an interface to allow it to call back into O_DIRECT to handle retransmission correctly. It also fixes a potential bug whereby we could change the behaviour of O_DIRECT if an error is already pending. Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 21 +++++++++++++++------ fs/nfs/flexfilelayout/flexfilelayout.c | 13 +------------ fs/nfs/internal.h | 1 - fs/nfs/write.c | 6 ++++++ include/linux/nfs_xdr.h | 1 + 5 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4b1d08f56aba..e73693f75dee 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -117,12 +117,6 @@ static inline int put_dreq(struct nfs_direct_req *dreq) return atomic_dec_and_test(&dreq->io_count); } -void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq) -{ - dreq->flags = NFS_ODIRECT_RESCHED_WRITES; -} -EXPORT_SYMBOL_GPL(nfs_direct_set_resched_writes); - static void nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr) { @@ -839,10 +833,25 @@ static void nfs_write_sync_pgio_error(struct list_head *head) } } +static void nfs_direct_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + struct nfs_direct_req *dreq = hdr->dreq; + + spin_lock(&dreq->lock); + if (dreq->error == 0) { + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + /* fake unstable write to let common nfs resend pages */ + hdr->verf.committed = NFS_UNSTABLE; + hdr->good_bytes = hdr->args.count; + } + spin_unlock(&dreq->lock); +} + static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { .error_cleanup = nfs_write_sync_pgio_error, .init_hdr = nfs_direct_pgio_init, .completion = nfs_direct_write_completion, + .reschedule_io = nfs_direct_write_reschedule_io, }; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 03516c80855a..df475d42df77 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -912,18 +912,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) hdr->args.count, (unsigned long long)hdr->args.offset); - if (!hdr->dreq) { - struct nfs_open_context *ctx; - - ctx = nfs_list_entry(hdr->pages.next)->wb_context; - set_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - hdr->completion_ops->error_cleanup(&hdr->pages); - } else { - nfs_direct_set_resched_writes(hdr->dreq); - /* fake unstable write to let common nfs resend pages */ - hdr->verf.committed = NFS_UNSTABLE; - hdr->good_bytes = hdr->args.count; - } + hdr->completion_ops->reschedule_io(hdr); return; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 313d55402238..99a2919047e9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -519,7 +519,6 @@ static inline void nfs_inode_dio_wait(struct inode *inode) inode_dio_wait(inode); } extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq); -extern void nfs_direct_set_resched_writes(struct nfs_direct_req *dreq); /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_pgio_header *); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7b9316406930..0aa3e6b3db70 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1326,9 +1326,15 @@ static void nfs_async_write_error(struct list_head *head) } } +static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) +{ + nfs_async_write_error(&hdr->pages); +} + static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { .error_cleanup = nfs_async_write_error, .completion = nfs_write_completion, + .reschedule_io = nfs_async_write_reschedule_io, }; void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 11bbae44f4cb..e89dbb14138c 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1460,6 +1460,7 @@ struct nfs_pgio_completion_ops { void (*error_cleanup)(struct list_head *head); void (*init_hdr)(struct nfs_pgio_header *hdr); void (*completion)(struct nfs_pgio_header *hdr); + void (*reschedule_io)(struct nfs_pgio_header *hdr); }; struct nfs_unlinkdata { -- cgit v1.2.3 From af7cf057933f01dc7f33ddfb5e436ad598ed17ad Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 29 Sep 2015 20:34:05 -0400 Subject: NFS: Allow multiple commit requests in flight per file Allow synchronous RPC calls to wait for pending RPC calls to finish, but also allow asynchronous ones to just fire off another commit. With this patch, the xfstests generic/074 test completes in 226s instead of 242s Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 6 ----- fs/nfs/file.c | 2 +- fs/nfs/nfstrace.h | 1 - fs/nfs/pnfs_nfs.c | 5 +--- fs/nfs/write.c | 70 +++++++++++++++++++++++-------------------------- include/linux/nfs_fs.h | 1 - include/linux/nfs_xdr.h | 1 - 7 files changed, 35 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index e73693f75dee..14f77df79c25 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -721,14 +721,8 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_direct_write_complete(dreq, data->inode); } -static void nfs_direct_error_cleanup(struct nfs_inode *nfsi) -{ - /* There is no lock to clear */ -} - static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { .completion = nfs_direct_commit_complete, - .error_cleanup = nfs_direct_error_cleanup, }; static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 93e236429c5d..e6ef80ec699c 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -514,7 +514,7 @@ static void nfs_check_dirty_writeback(struct page *page, * so it will not block due to pages that will shortly be freeable. */ nfsi = NFS_I(mapping->host); - if (test_bit(NFS_INO_COMMIT, &nfsi->flags)) { + if (atomic_read(&nfsi->commit_info.rpcs_out)) { *writeback = true; return; } diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 59f838cdc009..9f80a086b612 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -39,7 +39,6 @@ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \ { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ - { 1 << NFS_INO_COMMIT, "COMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMIT, "NEED_LAYOUTCOMMIT" }, \ { 1 << NFS_INO_LAYOUTCOMMITTING, "LAYOUTCOMMIT" }) diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 24655b807d44..3c8e3a44e6ea 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -266,17 +266,14 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, } else { nfs_retry_commit(mds_pages, NULL, cinfo, 0); pnfs_generic_retry_commit(cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } } nreq += pnfs_generic_alloc_ds_commits(cinfo, &list); - if (nreq == 0) { - cinfo->completion_ops->error_cleanup(NFS_I(inode)); + if (nreq == 0) goto out; - } atomic_add(nreq, &cinfo->mds->rpcs_out); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 0aa3e6b3db70..ae29f082c9c2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -21,6 +21,8 @@ #include #include #include +#include +#include #include @@ -1535,27 +1537,29 @@ static void nfs_writeback_result(struct rpc_task *task, } } +static int nfs_wait_atomic_killable(atomic_t *key) +{ + if (fatal_signal_pending(current)) + return -ERESTARTSYS; + freezable_schedule_unsafe(); + return 0; +} -static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) +static int wait_on_commit(struct nfs_mds_commit_info *cinfo) { - int ret; + return wait_on_atomic_t(&cinfo->rpcs_out, + nfs_wait_atomic_killable, TASK_KILLABLE); +} - if (!test_and_set_bit(NFS_INO_COMMIT, &nfsi->flags)) - return 1; - if (!may_wait) - return 0; - ret = out_of_line_wait_on_bit_lock(&nfsi->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - return (ret < 0) ? ret : 1; +static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +{ + atomic_inc(&cinfo->rpcs_out); } -static void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) { - clear_bit(NFS_INO_COMMIT, &nfsi->flags); - smp_mb__after_atomic(); - wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); + if (atomic_dec_and_test(&cinfo->rpcs_out)) + wake_up_atomic_t(&cinfo->rpcs_out); } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1693,7 +1697,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, data->mds_ops, how, 0); out_bad: nfs_retry_commit(head, NULL, cinfo, 0); - cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1755,8 +1758,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); nfs_init_cinfo(&cinfo, data->inode, data->dreq); - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) - nfs_commit_clear_lock(NFS_I(data->inode)); + nfs_commit_end(cinfo.mds); } static void nfs_commit_release(void *calldata) @@ -1775,7 +1777,6 @@ static const struct rpc_call_ops nfs_commit_ops = { static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { .completion = nfs_commit_release_pages, - .error_cleanup = nfs_commit_clear_lock, }; int nfs_generic_commit_list(struct inode *inode, struct list_head *head, @@ -1794,30 +1795,25 @@ int nfs_commit_inode(struct inode *inode, int how) LIST_HEAD(head); struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; + int error = 0; int res; - res = nfs_commit_set_lock(NFS_I(inode), may_wait); - if (res <= 0) - goto out_mark_dirty; nfs_init_cinfo_from_inode(&cinfo, inode); + nfs_commit_begin(cinfo.mds); res = nfs_scan_commit(inode, &head, &cinfo); - if (res) { - int error; - + if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); - if (error < 0) - return error; - if (!may_wait) - goto out_mark_dirty; - error = wait_on_bit_action(&NFS_I(inode)->flags, - NFS_INO_COMMIT, - nfs_wait_bit_killable, - TASK_KILLABLE); - if (error < 0) - return error; - } else - nfs_commit_clear_lock(NFS_I(inode)); + nfs_commit_end(cinfo.mds); + if (error < 0) + goto out_error; + if (!may_wait) + goto out_mark_dirty; + error = wait_on_commit(cinfo.mds); + if (error < 0) + return error; return res; +out_error: + res = error; /* Note: If we exit without ensuring that the commit is complete, * we must mark the inode as dirty. Otherwise, future calls to * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..ebf0bd72a42b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -216,7 +216,6 @@ struct nfs_inode { #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -#define NFS_INO_COMMIT (7) /* inode is committing unstable writes */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e89dbb14138c..a8905b7d4d7f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1423,7 +1423,6 @@ struct nfs_mds_commit_info { struct nfs_commit_data; struct nfs_inode; struct nfs_commit_completion_ops { - void (*error_cleanup) (struct nfs_inode *nfsi); void (*completion) (struct nfs_commit_data *data); }; -- cgit v1.2.3 From b20135d0b2431900a3a5395970ffb7e4f3767c8b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 31 Dec 2015 09:28:06 -0500 Subject: NFSv4.1/pNFS: Don't queue up a new commit if the layout segment is invalid If the layout segment is invalid, then we should not be adding more write requests to the commit list. Instead, those writes should be replayed after requesting a new layout. Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 2 ++ fs/nfs/direct.c | 12 ++++++++++++ fs/nfs/pnfs.c | 3 +++ fs/nfs/pnfs.h | 6 ++++++ fs/nfs/pnfs_nfs.c | 5 +++++ fs/nfs/write.c | 9 +++++++++ include/linux/nfs_xdr.h | 2 ++ 7 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index e4dbab5dce6e..2be8b252e3b1 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -233,6 +233,8 @@ static u32 initiate_file_draining(struct nfs_client *clp, unlock: spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&free_me_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(ino, 0); pnfs_put_layout_hdr(lo); trace_nfs4_cb_layoutrecall_file(clp, &args->cbl_fh, ino, &args->cbl_stateid, -rv); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 14f77df79c25..a9a93927fe3e 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -721,8 +721,20 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_direct_write_complete(dreq, data->inode); } +static void nfs_direct_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) +{ + struct nfs_direct_req *dreq = cinfo->dreq; + + spin_lock(&dreq->lock); + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + nfs_mark_request_commit(req, NULL, cinfo, 0); +} + static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { .completion = nfs_direct_commit_complete, + .resched_write = nfs_direct_resched_write, }; static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 360fe95c97b5..6593be7c0129 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -703,6 +703,8 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, ret = -EAGAIN; spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); + /* Free all lsegs that are attached to commit buckets */ + nfs_commit_inode(inode, 0); pnfs_put_layout_hdr(lo); iput(inode); } @@ -1811,6 +1813,7 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, pnfs_mark_matching_lsegs_return(lo, &free_me, &range); spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&free_me); + nfs_commit_inode(inode, 0); } EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index d93c2ebc0fd3..4bd7faf9ce50 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -412,6 +412,12 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg) return lseg; } +static inline bool +pnfs_is_valid_lseg(struct pnfs_layout_segment *lseg) +{ + return test_bit(NFS_LSEG_VALID, &lseg->pls_flags) != 0; +} + /* Return true if a layout driver is being used for this mountpoint */ static inline int pnfs_enabled_sb(struct nfs_server *nfss) { diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 3c8e3a44e6ea..81ac6480f9e7 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -868,6 +868,11 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, buckets = cinfo->ds->buckets; list = &buckets[ds_commit_idx].written; if (list_empty(list)) { + if (!pnfs_is_valid_lseg(lseg)) { + spin_unlock(cinfo->lock); + cinfo->completion_ops->resched_write(cinfo, req); + return; + } /* Non-empty buckets hold a reference on the lseg. That ref * is normally transferred to the COMMIT call and released * there. It could also be released if the last req is pulled diff --git a/fs/nfs/write.c b/fs/nfs/write.c index ae29f082c9c2..0aa8d6f23b4c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1676,6 +1676,13 @@ void nfs_retry_commit(struct list_head *page_list, } EXPORT_SYMBOL_GPL(nfs_retry_commit); +static void +nfs_commit_resched_write(struct nfs_commit_info *cinfo, + struct nfs_page *req) +{ + __set_page_dirty_nobuffers(req->wb_page); +} + /* * Commit dirty pages */ @@ -1777,6 +1784,7 @@ static const struct rpc_call_ops nfs_commit_ops = { static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { .completion = nfs_commit_release_pages, + .resched_write = nfs_commit_resched_write, }; int nfs_generic_commit_list(struct inode *inode, struct list_head *head, @@ -1823,6 +1831,7 @@ out_mark_dirty: __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return res; } +EXPORT_SYMBOL_GPL(nfs_commit_inode); int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a8905b7d4d7f..bee3e60a7006 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1420,10 +1420,12 @@ struct nfs_mds_commit_info { struct list_head list; }; +struct nfs_commit_info; struct nfs_commit_data; struct nfs_inode; struct nfs_commit_completion_ops { void (*completion) (struct nfs_commit_data *data); + void (*resched_write) (struct nfs_commit_info *, struct nfs_page *); }; struct nfs_commit_info { -- cgit v1.2.3 From d1b98c23f7547cc37c8f230acbedb26f0d47e9e1 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Fri, 1 Jan 2016 08:53:37 +0100 Subject: quota: constify qtree_fmt_operations structures The qtree_fmt_operations structures are never modified, so declare them as const. Done with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: Jan Kara --- fs/ocfs2/quota.h | 2 +- fs/ocfs2/quota_global.c | 2 +- fs/quota/quota_v2.c | 4 ++-- include/linux/dqblk_qtree.h | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index b6d51333ad02..d153e6e31529 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -82,7 +82,7 @@ struct ocfs2_quota_chunk { extern struct kmem_cache *ocfs2_dquot_cachep; extern struct kmem_cache *ocfs2_qf_chunk_cachep; -extern struct qtree_fmt_operations ocfs2_global_ops; +extern const struct qtree_fmt_operations ocfs2_global_ops; struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery( struct ocfs2_super *osb, int slot_num); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index c93d67220887..fde9ef18cff3 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -123,7 +123,7 @@ static int ocfs2_global_is_id(void *dp, struct dquot *dquot) dquot->dq_id); } -struct qtree_fmt_operations ocfs2_global_ops = { +const struct qtree_fmt_operations ocfs2_global_ops = { .mem2disk_dqblk = ocfs2_global_mem2diskdqb, .disk2mem_dqblk = ocfs2_global_disk2memdqb, .is_id = ocfs2_global_is_id, diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 2aa012a68e90..ed85d4f35c04 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -30,13 +30,13 @@ static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); -static struct qtree_fmt_operations v2r0_qtree_ops = { +static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; -static struct qtree_fmt_operations v2r1_qtree_ops = { +static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, diff --git a/include/linux/dqblk_qtree.h b/include/linux/dqblk_qtree.h index 82a16527b367..ff8b55359648 100644 --- a/include/linux/dqblk_qtree.h +++ b/include/linux/dqblk_qtree.h @@ -34,7 +34,7 @@ struct qtree_mem_dqinfo { unsigned int dqi_entry_size; /* Size of quota entry in quota file */ unsigned int dqi_usable_bs; /* Space usable in block for quota data */ unsigned int dqi_qtree_depth; /* Precomputed depth of quota tree */ - struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ + const struct qtree_fmt_operations *dqi_ops; /* Operations for entry manipulation */ }; int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot); -- cgit v1.2.3 From 4acad4aae10d1fa79a075b38b5c73772c44f576c Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Wed, 2 Dec 2015 10:38:21 +0000 Subject: spi: expose master transfer size limitation. On some SPI controllers it is not feasible to transfer arbitrary amount of data at once. When the limit on transfer size is a few kilobytes at least it makes sense to use the SPI hardware rather than reverting to gpio driver. The protocol drivers need a way to check that they do not sent overly long messages, though. Signed-off-by: Michal Suchanek Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index cce80e6dc7d1..3eebc6c235fb 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -425,6 +425,12 @@ struct spi_master { #define SPI_MASTER_MUST_RX BIT(3) /* requires rx */ #define SPI_MASTER_MUST_TX BIT(4) /* requires tx */ + /* + * on some hardware transfer size may be constrained + * the limit may depend on device transfer settings + */ + size_t (*max_transfer_size)(struct spi_device *spi); + /* lock and mutex for SPI bus locking */ spinlock_t bus_lock_spinlock; struct mutex bus_lock_mutex; @@ -832,6 +838,15 @@ extern int spi_async(struct spi_device *spi, struct spi_message *message); extern int spi_async_locked(struct spi_device *spi, struct spi_message *message); +static inline size_t +spi_max_transfer_size(struct spi_device *spi) +{ + struct spi_master *master = spi->master; + if (!master->max_transfer_size) + return SIZE_MAX; + return master->max_transfer_size(spi); +} + /*---------------------------------------------------------------------------*/ /* All these synchronous SPI transfer routines are utilities layered -- cgit v1.2.3 From 6e9411923b8f4c0e568cbae0f35b7ee4eb989914 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Wed, 30 Dec 2015 20:32:03 +0100 Subject: mtd: nand: return consistent error codes in ecc.correct() implementations The error code returned by the ecc.correct() are not consistent over the all implementations. Document the expected behavior in include/linux/mtd/nand.h and fix offending implementations. [Brian: this looks like a bugfix for the ECC reporting in the bf5xx_nand driver, but we haven't seen any testing results for it] Signed-off-by: Boris Brezillon Tested-by: Franklin S Cooper Jr. Signed-off-by: Brian Norris --- drivers/mtd/nand/atmel_nand.c | 2 +- drivers/mtd/nand/bf5xx_nand.c | 20 ++++++++++++++------ drivers/mtd/nand/davinci_nand.c | 6 +++--- drivers/mtd/nand/jz4740_nand.c | 4 ++-- drivers/mtd/nand/mxc_nand.c | 4 ++-- drivers/mtd/nand/nand_bch.c | 2 +- drivers/mtd/nand/nand_ecc.c | 2 +- drivers/mtd/nand/omap2.c | 6 +++--- drivers/mtd/nand/r852.c | 4 ++-- include/linux/mtd/nand.h | 8 +++++++- include/linux/mtd/nand_bch.h | 2 +- 11 files changed, 37 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c index 18c4e14ec29f..b216bf521349 100644 --- a/drivers/mtd/nand/atmel_nand.c +++ b/drivers/mtd/nand/atmel_nand.c @@ -1445,7 +1445,7 @@ static int atmel_nand_correct(struct mtd_info *mtd, u_char *dat, * We can't correct so many errors */ dev_dbg(host->dev, "atmel_nand : multiple errors detected." " Unable to correct.\n"); - return -EIO; + return -EBADMSG; } /* if there's a single bit error : we can correct it */ diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c index 9514e136542f..89d9414c5593 100644 --- a/drivers/mtd/nand/bf5xx_nand.c +++ b/drivers/mtd/nand/bf5xx_nand.c @@ -252,7 +252,7 @@ static int bf5xx_nand_correct_data_256(struct mtd_info *mtd, u_char *dat, */ if (hweight32(syndrome[0]) == 1) { dev_err(info->device, "ECC data was incorrect!\n"); - return 1; + return -EBADMSG; } syndrome[1] = (calced & 0x7FF) ^ (stored & 0x7FF); @@ -285,7 +285,7 @@ static int bf5xx_nand_correct_data_256(struct mtd_info *mtd, u_char *dat, data = data ^ (0x1 << failing_bit); *(dat + failing_byte) = data; - return 0; + return 1; } /* @@ -298,26 +298,34 @@ static int bf5xx_nand_correct_data_256(struct mtd_info *mtd, u_char *dat, dev_err(info->device, "Please discard data, mark bad block\n"); - return 1; + return -EBADMSG; } static int bf5xx_nand_correct_data(struct mtd_info *mtd, u_char *dat, u_char *read_ecc, u_char *calc_ecc) { struct nand_chip *chip = mtd_to_nand(mtd); - int ret; + int ret, bitflips = 0; ret = bf5xx_nand_correct_data_256(mtd, dat, read_ecc, calc_ecc); + if (ret < 0) + return ret; + + bitflips = ret; /* If ecc size is 512, correct second 256 bytes */ if (chip->ecc.size == 512) { dat += 256; read_ecc += 3; calc_ecc += 3; - ret |= bf5xx_nand_correct_data_256(mtd, dat, read_ecc, calc_ecc); + ret = bf5xx_nand_correct_data_256(mtd, dat, read_ecc, calc_ecc); + if (ret < 0) + return ret; + + bitflips += ret; } - return ret; + return bitflips; } static void bf5xx_nand_enable_hwecc(struct mtd_info *mtd, int mode) diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c index 3b49fe86625d..ddb73c331936 100644 --- a/drivers/mtd/nand/davinci_nand.c +++ b/drivers/mtd/nand/davinci_nand.c @@ -207,7 +207,7 @@ static int nand_davinci_correct_1bit(struct mtd_info *mtd, u_char *dat, dat[diff >> (12 + 3)] ^= BIT((diff >> 12) & 7); return 1; } else { - return -1; + return -EBADMSG; } } else if (!(diff & (diff - 1))) { /* Single bit ECC error in the ECC itself, @@ -215,7 +215,7 @@ static int nand_davinci_correct_1bit(struct mtd_info *mtd, u_char *dat, return 1; } else { /* Uncorrectable error */ - return -1; + return -EBADMSG; } } @@ -391,7 +391,7 @@ compare: return 0; case 1: /* five or more errors detected */ davinci_nand_readl(info, NAND_ERR_ERRVAL1_OFFSET); - return -EIO; + return -EBADMSG; case 2: /* error addresses computed */ case 3: num_errors = 1 + ((fsr >> 16) & 0x03); diff --git a/drivers/mtd/nand/jz4740_nand.c b/drivers/mtd/nand/jz4740_nand.c index a2363d33cecc..adccae3da120 100644 --- a/drivers/mtd/nand/jz4740_nand.c +++ b/drivers/mtd/nand/jz4740_nand.c @@ -254,7 +254,7 @@ static int jz_nand_correct_ecc_rs(struct mtd_info *mtd, uint8_t *dat, } while (!(status & JZ_NAND_STATUS_DEC_FINISH) && --timeout); if (timeout == 0) - return -1; + return -ETIMEDOUT; reg = readl(nand->base + JZ_REG_NAND_ECC_CTRL); reg &= ~JZ_NAND_ECC_CTRL_ENABLE; @@ -262,7 +262,7 @@ static int jz_nand_correct_ecc_rs(struct mtd_info *mtd, uint8_t *dat, if (status & JZ_NAND_STATUS_ERROR) { if (status & JZ_NAND_STATUS_UNCOR_ERROR) - return -1; + return -EBADMSG; error_count = (status & JZ_NAND_STATUS_ERR_COUNT) >> 29; diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c index 95400992c3e9..66e56bb22c0f 100644 --- a/drivers/mtd/nand/mxc_nand.c +++ b/drivers/mtd/nand/mxc_nand.c @@ -674,7 +674,7 @@ static int mxc_nand_correct_data_v1(struct mtd_info *mtd, u_char *dat, if (((ecc_status & 0x3) == 2) || ((ecc_status >> 2) == 2)) { pr_debug("MXC_NAND: HWECC uncorrectable 2-bit ECC error\n"); - return -1; + return -EBADMSG; } return 0; @@ -701,7 +701,7 @@ static int mxc_nand_correct_data_v2_v3(struct mtd_info *mtd, u_char *dat, err = ecc_stat & ecc_bit_mask; if (err > err_limit) { printk(KERN_WARNING "UnCorrectable RS-ECC Error\n"); - return -1; + return -EBADMSG; } else { ret += err; } diff --git a/drivers/mtd/nand/nand_bch.c b/drivers/mtd/nand/nand_bch.c index e5758d885943..a87c1b628dfc 100644 --- a/drivers/mtd/nand/nand_bch.c +++ b/drivers/mtd/nand/nand_bch.c @@ -98,7 +98,7 @@ int nand_bch_correct_data(struct mtd_info *mtd, unsigned char *buf, } } else if (count < 0) { printk(KERN_ERR "ecc unrecoverable error\n"); - count = -1; + count = -EBADMSG; } return count; } diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c index e6129851bfd8..d1770b066396 100644 --- a/drivers/mtd/nand/nand_ecc.c +++ b/drivers/mtd/nand/nand_ecc.c @@ -507,7 +507,7 @@ int __nand_correct_data(unsigned char *buf, return 1; /* error in ECC data; no action needed */ pr_err("%s: uncorrectable ECC error\n", __func__); - return -1; + return -EBADMSG; } EXPORT_SYMBOL(__nand_correct_data); diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index e9cbbc63c566..c553f78ab83f 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -826,12 +826,12 @@ static int omap_compare_ecc(u8 *ecc_data1, /* read from NAND memory */ case 1: /* Uncorrectable error */ pr_debug("ECC UNCORRECTED_ERROR 1\n"); - return -1; + return -EBADMSG; case 11: /* UN-Correctable error */ pr_debug("ECC UNCORRECTED_ERROR B\n"); - return -1; + return -EBADMSG; case 12: /* Correctable error */ @@ -861,7 +861,7 @@ static int omap_compare_ecc(u8 *ecc_data1, /* read from NAND memory */ return 0; } pr_debug("UNCORRECTED_ERROR default\n"); - return -1; + return -EBADMSG; } } diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c index cb0bf09214d5..5b15f2faee38 100644 --- a/drivers/mtd/nand/r852.c +++ b/drivers/mtd/nand/r852.c @@ -477,7 +477,7 @@ static int r852_ecc_correct(struct mtd_info *mtd, uint8_t *dat, if (dev->dma_error) { dev->dma_error = 0; - return -1; + return -EIO; } r852_write_reg(dev, R852_CTL, dev->ctlreg | R852_CTL_ECC_ACCESS); @@ -491,7 +491,7 @@ static int r852_ecc_correct(struct mtd_info *mtd, uint8_t *dat, /* ecc uncorrectable error */ if (ecc_status & R852_ECC_FAIL) { dbg("ecc: unrecoverable error, in half %d", i); - error = -1; + error = -EBADMSG; goto exit; } diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 3e92be1d2d43..518958115182 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -456,7 +456,13 @@ struct nand_hw_control { * @hwctl: function to control hardware ECC generator. Must only * be provided if an hardware ECC is available * @calculate: function for ECC calculation or readback from ECC hardware - * @correct: function for ECC correction, matching to ECC generator (sw/hw) + * @correct: function for ECC correction, matching to ECC generator (sw/hw). + * Should return a positive number representing the number of + * corrected bitflips, -EBADMSG if the number of bitflips exceed + * ECC strength, or any other error code if the error is not + * directly related to correction. + * If -EBADMSG is returned the input buffers should be left + * untouched. * @read_page_raw: function to read a raw page without ECC. This function * should hide the specific layout used by the ECC * controller and always return contiguous in-band and diff --git a/include/linux/mtd/nand_bch.h b/include/linux/mtd/nand_bch.h index 74acf5367556..fb0bc3420a10 100644 --- a/include/linux/mtd/nand_bch.h +++ b/include/linux/mtd/nand_bch.h @@ -55,7 +55,7 @@ static inline int nand_bch_correct_data(struct mtd_info *mtd, unsigned char *buf, unsigned char *read_ecc, unsigned char *calc_ecc) { - return -1; + return -ENOTSUPP; } static inline struct nand_bch_control * -- cgit v1.2.3 From 40cbe6eee97b706f27bcc4c6aa1018bbe4f1e577 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Wed, 30 Dec 2015 20:32:04 +0100 Subject: mtd: nand: use nand_check_erased_ecc_chunk in default ECC read functions The default NAND read functions are relying on the underlying controller driver to correct bitflips, but some of those controllers cannot properly fix bitflips in erased pages. Check for bitflips in erased pages in default core functions if the driver delegated the this check by setting the NAND_ECC_GENERIC_ERASED_CHECK flag. Signed-off-by: Boris Brezillon Tested-by: Franklin S Cooper Jr. Signed-off-by: Brian Norris --- drivers/mtd/nand/nand_base.c | 53 ++++++++++++++++++++++++++++++++++++++------ include/linux/mtd/nand.h | 10 +++++++++ 2 files changed, 56 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 50514f2501bb..f2c8ff398d6c 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1426,6 +1426,16 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip, stat = chip->ecc.correct(mtd, p, &chip->buffers->ecccode[i], &chip->buffers->ecccalc[i]); + if (stat == -EBADMSG && + (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { + /* check for empty pages with bitflips */ + stat = nand_check_erased_ecc_chunk(p, chip->ecc.size, + &chip->buffers->ecccode[i], + chip->ecc.bytes, + NULL, 0, + chip->ecc.strength); + } + if (stat < 0) { mtd->ecc_stats.failed++; } else { @@ -1475,6 +1485,15 @@ static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip, int stat; stat = chip->ecc.correct(mtd, p, &ecc_code[i], &ecc_calc[i]); + if (stat == -EBADMSG && + (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { + /* check for empty pages with bitflips */ + stat = nand_check_erased_ecc_chunk(p, eccsize, + &ecc_code[i], eccbytes, + NULL, 0, + chip->ecc.strength); + } + if (stat < 0) { mtd->ecc_stats.failed++; } else { @@ -1527,6 +1546,15 @@ static int nand_read_page_hwecc_oob_first(struct mtd_info *mtd, chip->ecc.calculate(mtd, p, &ecc_calc[i]); stat = chip->ecc.correct(mtd, p, &ecc_code[i], NULL); + if (stat == -EBADMSG && + (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { + /* check for empty pages with bitflips */ + stat = nand_check_erased_ecc_chunk(p, eccsize, + &ecc_code[i], eccbytes, + NULL, 0, + chip->ecc.strength); + } + if (stat < 0) { mtd->ecc_stats.failed++; } else { @@ -1554,6 +1582,7 @@ static int nand_read_page_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int i, eccsize = chip->ecc.size; int eccbytes = chip->ecc.bytes; int eccsteps = chip->ecc.steps; + int eccpadbytes = eccbytes + chip->ecc.prepad + chip->ecc.postpad; uint8_t *p = buf; uint8_t *oob = chip->oob_poi; unsigned int max_bitflips = 0; @@ -1573,19 +1602,29 @@ static int nand_read_page_syndrome(struct mtd_info *mtd, struct nand_chip *chip, chip->read_buf(mtd, oob, eccbytes); stat = chip->ecc.correct(mtd, p, oob, NULL); - if (stat < 0) { - mtd->ecc_stats.failed++; - } else { - mtd->ecc_stats.corrected += stat; - max_bitflips = max_t(unsigned int, max_bitflips, stat); - } - oob += eccbytes; if (chip->ecc.postpad) { chip->read_buf(mtd, oob, chip->ecc.postpad); oob += chip->ecc.postpad; } + + if (stat == -EBADMSG && + (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { + /* check for empty pages with bitflips */ + stat = nand_check_erased_ecc_chunk(p, chip->ecc.size, + oob - eccpadbytes, + eccpadbytes, + NULL, 0, + chip->ecc.strength); + } + + if (stat < 0) { + mtd->ecc_stats.failed++; + } else { + mtd->ecc_stats.corrected += stat; + max_bitflips = max_t(unsigned int, max_bitflips, stat); + } } /* Calculate remaining oob bytes */ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 518958115182..86487dbe7358 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -129,6 +129,14 @@ typedef enum { /* Enable Hardware ECC before syndrome is read back from flash */ #define NAND_ECC_READSYN 2 +/* + * Enable generic NAND 'page erased' check. This check is only done when + * ecc.correct() returns -EBADMSG. + * Set this flag if your implementation does not fix bitflips in erased + * pages and you want to rely on the default implementation. + */ +#define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) + /* Bit mask for flags passed to do_nand_read_ecc */ #define NAND_GET_DEVICE 0x80 @@ -451,6 +459,7 @@ struct nand_hw_control { * @total: total number of ECC bytes per page * @prepad: padding information for syndrome based ECC generators * @postpad: padding information for syndrome based ECC generators + * @options: ECC specific options (see NAND_ECC_XXX flags defined above) * @layout: ECC layout control struct pointer * @priv: pointer to private ECC control data * @hwctl: function to control hardware ECC generator. Must only @@ -500,6 +509,7 @@ struct nand_ecc_ctrl { int strength; int prepad; int postpad; + unsigned int options; struct nand_ecclayout *layout; void *priv; void (*hwctl)(struct mtd_info *mtd, int mode); -- cgit v1.2.3 From 2a297450dd188a5d4e5e428c189b2de54f9073ba Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Wed, 23 Dec 2015 22:25:13 +0100 Subject: lockd: constify nlmsvc_binding structure The nlmsvc_binding structure is never modified, so declare it as const. Done with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: J. Bruce Fields --- fs/lockd/svc.c | 2 +- fs/nfsd/lockd.c | 2 +- include/linux/lockd/bind.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index b4006c720f55..154a107cd376 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -48,7 +48,7 @@ static struct svc_program nlmsvc_program; -struct nlmsvc_binding * nlmsvc_ops; +const struct nlmsvc_binding *nlmsvc_ops; EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 77e7a5cca888..1a03bc3059e8 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -58,7 +58,7 @@ nlm_fclose(struct file *filp) fput(filp); } -static struct nlmsvc_binding nfsd_nlm_ops = { +static const struct nlmsvc_binding nfsd_nlm_ops = { .fopen = nlm_fopen, /* open file for locking */ .fclose = nlm_fclose, /* close file */ }; diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h index 4d24d64578c4..140edab64446 100644 --- a/include/linux/lockd/bind.h +++ b/include/linux/lockd/bind.h @@ -29,7 +29,7 @@ struct nlmsvc_binding { void (*fclose)(struct file *); }; -extern struct nlmsvc_binding * nlmsvc_ops; +extern const struct nlmsvc_binding *nlmsvc_ops; /* * Similar to nfs_client_initdata, but without the NFS-specific -- cgit v1.2.3 From d39ddbd9ef70949bb78283a067e1b3366111dd90 Mon Sep 17 00:00:00 2001 From: Boris BREZILLON Date: Thu, 10 Dec 2015 09:00:39 +0100 Subject: mtd: nand: add helpers to access ->priv Add two helpers to access the field reserved for private controller data. This makes it clearer what this field is reserved for and ease future refactoring. Signed-off-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 86487dbe7358..bdd68e22b5a5 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -755,6 +755,16 @@ static inline struct mtd_info *nand_to_mtd(struct nand_chip *chip) return &chip->mtd; } +static inline void *nand_get_controller_data(struct nand_chip *chip) +{ + return chip->priv; +} + +static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) +{ + chip->priv = priv; +} + /* * NAND Flash Manufacturer ID Codes */ -- cgit v1.2.3 From 210c7c1750fdf769647d1d526c9ea34c412c9eee Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Wed, 6 Jan 2016 10:40:18 -0500 Subject: NFS: Use wait_on_atomic_t() for unlock after readahead The use of wait_on_atomic_t() for waiting on I/O to complete before unlocking allows us to git rid of the NFS_IO_INPROGRESS flag, and thus the nfs_iocounter's flags member, and finally the nfs_iocounter altogether. The count of I/O is moved to the lock context, and the counter increment/decrement functions become simple enough to open-code. Signed-off-by: Benjamin Coddington [Trond: Fix up conflict with existing function nfs_wait_atomic_killable()] Signed-off-by: Trond Myklebust --- fs/nfs/file.c | 2 +- fs/nfs/inode.c | 18 ++++++++++++------ fs/nfs/internal.h | 9 ++------- fs/nfs/pagelist.c | 48 +++++++----------------------------------------- fs/nfs/write.c | 8 -------- include/linux/nfs_fs.h | 8 +------- 6 files changed, 23 insertions(+), 70 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 178ec8da028f..4ef8f5addcad 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -756,7 +756,7 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) l_ctx = nfs_get_lock_context(nfs_file_open_context(filp)); if (!IS_ERR(l_ctx)) { - status = nfs_iocounter_wait(&l_ctx->io_count); + status = nfs_iocounter_wait(l_ctx); nfs_put_lock_context(l_ctx); if (status < 0) return status; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 74fb1223c2f5..4b63d1bd5820 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -71,19 +71,25 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } -/** - * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks - * @word: long word containing the bit lock - */ -int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) +static int nfs_wait_killable(int mode) { freezable_schedule_unsafe(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } + +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) +{ + return nfs_wait_killable(mode); +} EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); +int nfs_wait_atomic_killable(atomic_t *p) +{ + return nfs_wait_killable(TASK_KILLABLE); +} + /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid @@ -699,7 +705,7 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) l_ctx->lockowner.l_owner = current->files; l_ctx->lockowner.l_pid = current->tgid; INIT_LIST_HEAD(&l_ctx->list); - nfs_iocounter_init(&l_ctx->io_count); + atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index ee81792d2886..4e8cc942336c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -238,7 +238,7 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr, void (*release)(struct nfs_pgio_header *hdr)); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); -int nfs_iocounter_wait(struct nfs_io_counter *c); +int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); @@ -252,12 +252,6 @@ void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc); -static inline void nfs_iocounter_init(struct nfs_io_counter *c) -{ - c->flags = 0; - atomic_set(&c->io_count, 0); -} - static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) { WARN_ON_ONCE(desc->pg_mirror_count < 1); @@ -386,6 +380,7 @@ extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); +extern int nfs_wait_atomic_killable(atomic_t *p); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index eeddbf0bf4c4..cb7e73ba059c 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -101,53 +101,18 @@ nfs_page_free(struct nfs_page *p) kmem_cache_free(nfs_page_cachep, p); } -static void -nfs_iocounter_inc(struct nfs_io_counter *c) -{ - atomic_inc(&c->io_count); -} - -static void -nfs_iocounter_dec(struct nfs_io_counter *c) -{ - if (atomic_dec_and_test(&c->io_count)) { - clear_bit(NFS_IO_INPROGRESS, &c->flags); - smp_mb__after_atomic(); - wake_up_bit(&c->flags, NFS_IO_INPROGRESS); - } -} - -static int -__nfs_iocounter_wait(struct nfs_io_counter *c) -{ - wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS); - DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS); - int ret = 0; - - do { - prepare_to_wait(wq, &q.wait, TASK_KILLABLE); - set_bit(NFS_IO_INPROGRESS, &c->flags); - if (atomic_read(&c->io_count) == 0) - break; - ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE); - } while (atomic_read(&c->io_count) != 0 && !ret); - finish_wait(wq, &q.wait); - return ret; -} - /** * nfs_iocounter_wait - wait for i/o to complete - * @c: nfs_io_counter to use + * @l_ctx: nfs_lock_context with io_counter to use * * returns -ERESTARTSYS if interrupted by a fatal signal. * Otherwise returns 0 once the io_count hits 0. */ int -nfs_iocounter_wait(struct nfs_io_counter *c) +nfs_iocounter_wait(struct nfs_lock_context *l_ctx) { - if (atomic_read(&c->io_count) == 0) - return 0; - return __nfs_iocounter_wait(c); + return wait_on_atomic_t(&l_ctx->io_count, nfs_wait_atomic_killable, + TASK_KILLABLE); } /* @@ -370,7 +335,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, return ERR_CAST(l_ctx); } req->wb_lock_context = l_ctx; - nfs_iocounter_inc(&l_ctx->io_count); + atomic_inc(&l_ctx->io_count); /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in @@ -431,7 +396,8 @@ static void nfs_clear_request(struct nfs_page *req) req->wb_page = NULL; } if (l_ctx != NULL) { - nfs_iocounter_dec(&l_ctx->io_count); + if (atomic_dec_and_test(&l_ctx->io_count)) + wake_up_atomic_t(&l_ctx->io_count); nfs_put_lock_context(l_ctx); req->wb_lock_context = NULL; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 94828b3f8c95..8ba4f717b413 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1565,14 +1565,6 @@ static void nfs_writeback_result(struct rpc_task *task, } } -static int nfs_wait_atomic_killable(atomic_t *key) -{ - if (fatal_signal_pending(current)) - return -ERESTARTSYS; - freezable_schedule_unsafe(); - return 0; -} - static int wait_on_commit(struct nfs_mds_commit_info *cinfo) { return wait_on_atomic_t(&cinfo->rpcs_out, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9eee972863a7..196aaceafda7 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -60,18 +60,12 @@ struct nfs_lockowner { pid_t l_pid; }; -#define NFS_IO_INPROGRESS 0 -struct nfs_io_counter { - unsigned long flags; - atomic_t io_count; -}; - struct nfs_lock_context { atomic_t count; struct list_head list; struct nfs_open_context *open_context; struct nfs_lockowner lockowner; - struct nfs_io_counter io_count; + atomic_t io_count; }; struct nfs4_state; -- cgit v1.2.3 From 5a023cdba50c5f5f2bc351783b3131699deb3937 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 30 Nov 2015 10:20:29 -0800 Subject: block: enable dax for raw block devices If an application wants exclusive access to all of the persistent memory provided by an NVDIMM namespace it can use this raw-block-dax facility to forgo establishing a filesystem. This capability is targeted primarily to hypervisors wanting to provision persistent memory for guests. It can be disabled / enabled dynamically via the new BLKDAXSET ioctl. Cc: Jeff Moyer Cc: Christoph Hellwig Cc: Dave Chinner Cc: Andrew Morton Cc: Ross Zwisler Reported-by: kbuild test robot Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- block/ioctl.c | 61 ++++++++++++++++++++++++++++ fs/block_dev.c | 103 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/fs.h | 11 ++++++ include/uapi/linux/fs.h | 2 + 4 files changed, 169 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/ioctl.c b/block/ioctl.c index 0918aed2d847..7a964d842913 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -406,6 +406,62 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } +#ifdef CONFIG_FS_DAX +bool blkdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + + if (!disk->fops->direct_access) + return false; + + /* + * If the partition is not aligned on a page boundary, we can't + * do dax I/O to it. + */ + if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) + || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + return false; + + return true; +} + +static int blkdev_daxset(struct block_device *bdev, unsigned long argp) +{ + unsigned long arg; + int rc = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (get_user(arg, (int __user *)(argp))) + return -EFAULT; + arg = !!arg; + if (arg == !!(bdev->bd_inode->i_flags & S_DAX)) + return 0; + + if (arg) + arg = S_DAX; + + if (arg && !blkdev_dax_capable(bdev)) + return -ENOTTY; + + mutex_lock(&bdev->bd_inode->i_mutex); + if (bdev->bd_map_count == 0) + inode_set_flags(bdev->bd_inode, arg, S_DAX); + else + rc = -EBUSY; + mutex_unlock(&bdev->bd_inode->i_mutex); + return rc; +} +#else +static int blkdev_daxset(struct block_device *bdev, int arg) +{ + if (arg) + return -ENOTTY; + return 0; +} +#endif + static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { @@ -568,6 +624,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); + case BLKDAXSET: + return blkdev_daxset(bdev, arg); + case BLKDAXGET: + return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); + break; case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: diff --git a/fs/block_dev.c b/fs/block_dev.c index 52248bce42d2..5c0b2cba870e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1235,8 +1235,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + if (!blkdev_dax_capable(bdev)) + bdev->bd_inode->i_flags &= ~S_DAX; + } /* * If the device is invalidated, rescan partition @@ -1250,6 +1253,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) else if (ret == -ENOMEDIUM) invalidate_partitions(disk, bdev); } + if (ret) goto out_clear; } else { @@ -1270,12 +1274,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); - /* - * If the partition is not aligned on a page - * boundary, we can't do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) || - (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + if (!blkdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } } else { @@ -1713,13 +1712,101 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; +#ifdef CONFIG_FS_DAX +/* + * In the raw block case we do not need to contend with truncation nor + * unwritten file extents. Without those concerns there is no need for + * additional locking beyond the mmap_sem context that these routines + * are already executing under. + * + * Note, there is no protection if the block device is dynamically + * resized (partition grow/shrink) during a fault. A stable block device + * size is already not enforced in the blkdev_direct_IO path. + * + * For DAX, it is the responsibility of the block device driver to + * ensure the whole-disk device size is stable while requests are in + * flight. + * + * Finally, unlike the filemap_page_mkwrite() case there is no + * filesystem superblock to sync against freezing. We still include a + * pfn_mkwrite callback for dax drivers to receive write fault + * notifications. + */ +static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return __dax_fault(vma, vmf, blkdev_get_block, NULL); +} + +static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags) +{ + return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); +} + +static void blkdev_vm_open(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + mutex_unlock(&bd_inode->i_mutex); +} + +static void blkdev_vm_close(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count--; + mutex_unlock(&bd_inode->i_mutex); +} + +static const struct vm_operations_struct blkdev_dax_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = blkdev_dax_fault, + .pmd_fault = blkdev_dax_pmd_fault, + .pfn_mkwrite = blkdev_dax_fault, +}; + +static const struct vm_operations_struct blkdev_default_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, +}; + +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(bd_inode); + + file_accessed(file); + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + if (IS_DAX(bd_inode)) { + vma->vm_ops = &blkdev_dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + } else { + vma->vm_ops = &blkdev_default_vm_ops; + } + mutex_unlock(&bd_inode->i_mutex); + + return 0; +} +#else +#define blkdev_mmap generic_file_mmap +#endif + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..96fabc93b583 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -482,6 +482,9 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; +#ifdef CONFIG_FS_DAX + int bd_map_count; +#endif }; /* @@ -2264,6 +2267,14 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); +#ifdef CONFIG_FS_DAX +extern bool blkdev_dax_capable(struct block_device *bdev); +#else +static inline bool blkdev_dax_capable(struct block_device *bdev) +{ + return false; +} +#endif extern struct super_block *blockdev_superblock; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f15d980249b5..401c409e9239 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -152,6 +152,8 @@ struct inodes_stat_t { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +#define BLKDAXSET _IO(0x12,128) +#define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 9e0e252a048b0ba5066f0dc15c3b2468ffe5c422 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 24 Dec 2015 19:20:32 -0700 Subject: badblocks: Add core badblock management code Take the core badblocks implementation from md, and make it generally available. This follows the same style as kernel implementations of linked lists, rb-trees etc, where you can have a structure that can be embedded anywhere, and accessor functions to manipulate the data. The only changes in this copy of the code are ones to generalize function/variable names from md-specific ones. Also add init and free functions. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- block/Makefile | 2 +- block/badblocks.c | 561 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/badblocks.h | 53 +++++ 3 files changed, 615 insertions(+), 1 deletion(-) create mode 100644 block/badblocks.c create mode 100644 include/linux/badblocks.h (limited to 'include/linux') diff --git a/block/Makefile b/block/Makefile index 00ecc97629db..db5f622c9d67 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \ blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \ genhd.o scsi_ioctl.o partition-generic.o ioprio.o \ - partitions/ + badblocks.o partitions/ obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o diff --git a/block/badblocks.c b/block/badblocks.c new file mode 100644 index 000000000000..96aeb9194a2e --- /dev/null +++ b/block/badblocks.c @@ -0,0 +1,561 @@ +/* + * Bad block management + * + * - Heavily based on MD badblocks code from Neil Brown + * + * Copyright (c) 2015, Intel Corporation. + * + * 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. + */ + +#include +#include +#include +#include +#include +#include +#include + +/** + * badblocks_check() - check a given range for bad sectors + * @bb: the badblocks structure that holds all badblock information + * @s: sector (start) at which to check for badblocks + * @sectors: number of sectors to check for badblocks + * @first_bad: pointer to store location of the first badblock + * @bad_sectors: pointer to store number of badblocks after @first_bad + * + * We can record which blocks on each device are 'bad' and so just + * fail those blocks, or that stripe, rather than the whole device. + * Entries in the bad-block table are 64bits wide. This comprises: + * Length of bad-range, in sectors: 0-511 for lengths 1-512 + * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes) + * A 'shift' can be set so that larger blocks are tracked and + * consequently larger devices can be covered. + * 'Acknowledged' flag - 1 bit. - the most significant bit. + * + * Locking of the bad-block table uses a seqlock so badblocks_check + * might need to retry if it is very unlucky. + * We will sometimes want to check for bad blocks in a bi_end_io function, + * so we use the write_seqlock_irq variant. + * + * When looking for a bad block we specify a range and want to + * know if any block in the range is bad. So we binary-search + * to the last range that starts at-or-before the given endpoint, + * (or "before the sector after the target range") + * then see if it ends after the given start. + * + * Return: + * 0: there are no known bad blocks in the range + * 1: there are known bad block which are all acknowledged + * -1: there are bad blocks which have not yet been acknowledged in metadata. + * plus the start/length of the first bad section we overlap. + */ +int badblocks_check(struct badblocks *bb, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors) +{ + int hi; + int lo; + u64 *p = bb->page; + int rv; + sector_t target = s + sectors; + unsigned seq; + + if (bb->shift > 0) { + /* round the start down, and the end up */ + s >>= bb->shift; + target += (1<shift) - 1; + target >>= bb->shift; + sectors = target - s; + } + /* 'target' is now the first block after the bad range */ + +retry: + seq = read_seqbegin(&bb->lock); + lo = 0; + rv = 0; + hi = bb->count; + + /* Binary search between lo and hi for 'target' + * i.e. for the last range that starts before 'target' + */ + /* INVARIANT: ranges before 'lo' and at-or-after 'hi' + * are known not to be the last range before target. + * VARIANT: hi-lo is the number of possible + * ranges, and decreases until it reaches 1 + */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + /* This could still be the one, earlier ranges + * could not. + */ + lo = mid; + else + /* This and later ranges are definitely out. */ + hi = mid; + } + /* 'lo' might be the last that started before target, but 'hi' isn't */ + if (hi > lo) { + /* need to check all range that end after 's' to see if + * any are unacknowledged. + */ + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + if (BB_OFFSET(p[lo]) < target) { + /* starts before the end, and finishes after + * the start, so they must overlap + */ + if (rv != -1 && BB_ACK(p[lo])) + rv = 1; + else + rv = -1; + *first_bad = BB_OFFSET(p[lo]); + *bad_sectors = BB_LEN(p[lo]); + } + lo--; + } + } + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_check); + +/** + * badblocks_set() - Add a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * @acknowledged: weather to mark the bad sectors as acknowledged + * + * This might extend the table, or might contract it if two adjacent ranges + * can be merged. We binary-search to find the 'insertion' point, then + * decide how best to handle it. + * + * Return: + * 0: success + * 1: failed to set badblocks (out of space) + */ +int badblocks_set(struct badblocks *bb, sector_t s, int sectors, + int acknowledged) +{ + u64 *p; + int lo, hi; + int rv = 0; + unsigned long flags; + + if (bb->shift < 0) + /* badblocks are disabled */ + return 0; + + if (bb->shift) { + /* round the start down, and the end up */ + sector_t next = s + sectors; + + s >>= bb->shift; + next += (1<shift) - 1; + next >>= bb->shift; + sectors = next - s; + } + + write_seqlock_irqsave(&bb->lock, flags); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts at-or-before 's' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a <= s) + lo = mid; + else + hi = mid; + } + if (hi > lo && BB_OFFSET(p[lo]) > s) + hi = lo; + + if (hi > lo) { + /* we found a range that might merge with the start + * of our new range + */ + sector_t a = BB_OFFSET(p[lo]); + sector_t e = a + BB_LEN(p[lo]); + int ack = BB_ACK(p[lo]); + + if (e >= s) { + /* Yes, we can merge with a previous range */ + if (s == a && s + sectors >= e) + /* new range covers old */ + ack = acknowledged; + else + ack = ack && acknowledged; + + if (e < s + sectors) + e = s + sectors; + if (e - a <= BB_MAX_LEN) { + p[lo] = BB_MAKE(a, e-a, ack); + s = e; + } else { + /* does not all fit in one range, + * make p[lo] maximal + */ + if (BB_LEN(p[lo]) != BB_MAX_LEN) + p[lo] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + } + } + if (sectors && hi < bb->count) { + /* 'hi' points to the first range that starts after 's'. + * Maybe we can merge with the start of that range + */ + sector_t a = BB_OFFSET(p[hi]); + sector_t e = a + BB_LEN(p[hi]); + int ack = BB_ACK(p[hi]); + + if (a <= s + sectors) { + /* merging is possible */ + if (e <= s + sectors) { + /* full overlap */ + e = s + sectors; + ack = acknowledged; + } else + ack = ack && acknowledged; + + a = s; + if (e - a <= BB_MAX_LEN) { + p[hi] = BB_MAKE(a, e-a, ack); + s = e; + } else { + p[hi] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + lo = hi; + hi++; + } + } + if (sectors == 0 && hi < bb->count) { + /* we might be able to combine lo and hi */ + /* Note: 's' is at the end of 'lo' */ + sector_t a = BB_OFFSET(p[hi]); + int lolen = BB_LEN(p[lo]); + int hilen = BB_LEN(p[hi]); + int newlen = lolen + hilen - (s - a); + + if (s >= a && newlen < BB_MAX_LEN) { + /* yes, we can combine them */ + int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]); + + p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack); + memmove(p + hi, p + hi + 1, + (bb->count - hi - 1) * 8); + bb->count--; + } + } + while (sectors) { + /* didn't merge (it all). + * Need to add a range just before 'hi' + */ + if (bb->count >= MAX_BADBLOCKS) { + /* No room for more */ + rv = 1; + break; + } else { + int this_sectors = sectors; + + memmove(p + hi + 1, p + hi, + (bb->count - hi) * 8); + bb->count++; + + if (this_sectors > BB_MAX_LEN) + this_sectors = BB_MAX_LEN; + p[hi] = BB_MAKE(s, this_sectors, acknowledged); + sectors -= this_sectors; + s += this_sectors; + } + } + + bb->changed = 1; + if (!acknowledged) + bb->unacked_exist = 1; + write_sequnlock_irqrestore(&bb->lock, flags); + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_set); + +/** + * badblocks_clear() - Remove a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * + * This may involve extending the table if we spilt a region, + * but it must not fail. So if the table becomes full, we just + * drop the remove request. + * + * Return: + * 0: success + * 1: failed to clear badblocks + */ +int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) +{ + u64 *p; + int lo, hi; + sector_t target = s + sectors; + int rv = 0; + + if (bb->shift > 0) { + /* When clearing we round the start up and the end down. + * This should not matter as the shift should align with + * the block size and no rounding should ever be needed. + * However it is better the think a block is bad when it + * isn't than to think a block is not bad when it is. + */ + s += (1<shift) - 1; + s >>= bb->shift; + target >>= bb->shift; + sectors = target - s; + } + + write_seqlock_irq(&bb->lock); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts before 'target' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + lo = mid; + else + hi = mid; + } + if (hi > lo) { + /* p[lo] is the last range that could overlap the + * current range. Earlier ranges could also overlap, + * but only this one can overlap the end of the range. + */ + if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) { + /* Partial overlap, leave the tail of this range */ + int ack = BB_ACK(p[lo]); + sector_t a = BB_OFFSET(p[lo]); + sector_t end = a + BB_LEN(p[lo]); + + if (a < s) { + /* we need to split this range */ + if (bb->count >= MAX_BADBLOCKS) { + rv = -ENOSPC; + goto out; + } + memmove(p+lo+1, p+lo, (bb->count - lo) * 8); + bb->count++; + p[lo] = BB_MAKE(a, s-a, ack); + lo++; + } + p[lo] = BB_MAKE(target, end - target, ack); + /* there is no longer an overlap */ + hi = lo; + lo--; + } + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + /* This range does overlap */ + if (BB_OFFSET(p[lo]) < s) { + /* Keep the early parts of this range. */ + int ack = BB_ACK(p[lo]); + sector_t start = BB_OFFSET(p[lo]); + + p[lo] = BB_MAKE(start, s - start, ack); + /* now low doesn't overlap, so.. */ + break; + } + lo--; + } + /* 'lo' is strictly before, 'hi' is strictly after, + * anything between needs to be discarded + */ + if (hi - lo > 1) { + memmove(p+lo+1, p+hi, (bb->count - hi) * 8); + bb->count -= (hi - lo - 1); + } + } + + bb->changed = 1; +out: + write_sequnlock_irq(&bb->lock); + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_clear); + +/** + * ack_all_badblocks() - Acknowledge all bad blocks in a list. + * @bb: the badblocks structure that holds all badblock information + * + * This only succeeds if ->changed is clear. It is used by + * in-kernel metadata updates + */ +void ack_all_badblocks(struct badblocks *bb) +{ + if (bb->page == NULL || bb->changed) + /* no point even trying */ + return; + write_seqlock_irq(&bb->lock); + + if (bb->changed == 0 && bb->unacked_exist) { + u64 *p = bb->page; + int i; + + for (i = 0; i < bb->count ; i++) { + if (!BB_ACK(p[i])) { + sector_t start = BB_OFFSET(p[i]); + int len = BB_LEN(p[i]); + + p[i] = BB_MAKE(start, len, 1); + } + } + bb->unacked_exist = 0; + } + write_sequnlock_irq(&bb->lock); +} +EXPORT_SYMBOL_GPL(ack_all_badblocks); + +/** + * badblocks_show() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of returned data + */ +ssize_t badblocks_show(struct badblocks *bb, char *page, int unack) +{ + size_t len; + int i; + u64 *p = bb->page; + unsigned seq; + + if (bb->shift < 0) + return 0; + +retry: + seq = read_seqbegin(&bb->lock); + + len = 0; + i = 0; + + while (len < PAGE_SIZE && i < bb->count) { + sector_t s = BB_OFFSET(p[i]); + unsigned int length = BB_LEN(p[i]); + int ack = BB_ACK(p[i]); + + i++; + + if (unack && ack) + continue; + + len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n", + (unsigned long long)s << bb->shift, + length << bb->shift); + } + if (unack && len == 0) + bb->unacked_exist = 0; + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return len; +} +EXPORT_SYMBOL_GPL(badblocks_show); + +/** + * badblocks_store() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @len: length of data received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of the buffer processed or -ve error. + */ +ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, + int unack) +{ + unsigned long long sector; + int length; + char newline; + + switch (sscanf(page, "%llu %d%c", §or, &length, &newline)) { + case 3: + if (newline != '\n') + return -EINVAL; + case 2: + if (length <= 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (badblocks_set(bb, sector, length, !unack)) + return -ENOSPC; + else + return len; +} +EXPORT_SYMBOL_GPL(badblocks_store); + +/** + * badblocks_init() - initialize the badblocks structure + * @bb: the badblocks structure that holds all badblock information + * @enable: weather to enable badblocks accounting + * + * Return: + * 0: success + * -ve errno: on error + */ +int badblocks_init(struct badblocks *bb, int enable) +{ + bb->count = 0; + if (enable) + bb->shift = 0; + else + bb->shift = -1; + bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (bb->page == (u64 *)0) { + bb->shift = -1; + return -ENOMEM; + } + seqlock_init(&bb->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(badblocks_init); + +/** + * badblocks_free() - free the badblocks structure + * @bb: the badblocks structure that holds all badblock information + */ +void badblocks_free(struct badblocks *bb) +{ + kfree(bb->page); + bb->page = NULL; +} +EXPORT_SYMBOL_GPL(badblocks_free); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h new file mode 100644 index 000000000000..929344630b51 --- /dev/null +++ b/include/linux/badblocks.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_BADBLOCKS_H +#define _LINUX_BADBLOCKS_H + +#include +#include +#include +#include + +#define BB_LEN_MASK (0x00000000000001FFULL) +#define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL) +#define BB_ACK_MASK (0x8000000000000000ULL) +#define BB_MAX_LEN 512 +#define BB_OFFSET(x) (((x) & BB_OFFSET_MASK) >> 9) +#define BB_LEN(x) (((x) & BB_LEN_MASK) + 1) +#define BB_ACK(x) (!!((x) & BB_ACK_MASK)) +#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63)) + +/* Bad block numbers are stored sorted in a single page. + * 64bits is used for each block or extent. + * 54 bits are sector number, 9 bits are extent size, + * 1 bit is an 'acknowledged' flag. + */ +#define MAX_BADBLOCKS (PAGE_SIZE/8) + +struct badblocks { + int count; /* count of bad blocks */ + int unacked_exist; /* there probably are unacknowledged + * bad blocks. This is only cleared + * when a read discovers none + */ + int shift; /* shift from sectors to block size + * a -ve shift means badblocks are + * disabled.*/ + u64 *page; /* badblock list */ + int changed; + seqlock_t lock; + sector_t sector; + sector_t size; /* in sectors */ +}; + +int badblocks_check(struct badblocks *bb, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors); +int badblocks_set(struct badblocks *bb, sector_t s, int sectors, + int acknowledged); +int badblocks_clear(struct badblocks *bb, sector_t s, int sectors); +void ack_all_badblocks(struct badblocks *bb); +ssize_t badblocks_show(struct badblocks *bb, char *page, int unack); +ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, + int unack); +int badblocks_init(struct badblocks *bb, int enable); +void badblocks_free(struct badblocks *bb); + +#endif -- cgit v1.2.3 From 99e6608c9e7414ae4f2168df8bf8fae3eb49e41f Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Sat, 9 Jan 2016 08:36:51 -0800 Subject: block: Add badblock management for gendisks NVDIMM devices, which can behave more like DRAM rather than block devices, may develop bad cache lines, or 'poison'. A block device exposed by the pmem driver can then consume poison via a read (or write), and cause a machine check. On platforms without machine check recovery features, this would mean a crash. The block device maintaining a runtime list of all known sectors that have poison can directly avoid this, and also provide a path forward to enable proper handling/recovery for DAX faults on such a device. Use the new badblock management interfaces to add a badblocks list to gendisks. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- block/genhd.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/genhd.h | 7 +++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 1a971bebbbfe..88579cf373b8 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "blk.h" @@ -505,6 +506,16 @@ static int exact_lock(dev_t devt, void *data) return 0; } +int disk_alloc_badblocks(struct gendisk *disk) +{ + disk->bb = kzalloc(sizeof(*(disk->bb)), GFP_KERNEL); + if (!disk->bb) + return -ENOMEM; + + return badblocks_init(disk->bb, 1); +} +EXPORT_SYMBOL(disk_alloc_badblocks); + static void register_disk(struct gendisk *disk) { struct device *ddev = disk_to_dev(disk); @@ -659,6 +670,11 @@ void del_gendisk(struct gendisk *disk) blk_unregister_queue(disk); blk_unregister_region(disk_devt(disk), disk->minors); + if (disk->bb) { + badblocks_free(disk->bb); + kfree(disk->bb); + } + part_stat_set_all(&disk->part0, 0); disk->part0.stamp = 0; @@ -671,6 +687,63 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); +/* + * The gendisk usage of badblocks does not track acknowledgements for + * badblocks. We always assume they are acknowledged. + */ +int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors); +} +EXPORT_SYMBOL(disk_check_badblocks); + +int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_set(disk->bb, s, sectors, 1); +} +EXPORT_SYMBOL(disk_set_badblocks); + +int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_clear(disk->bb, s, sectors); +} +EXPORT_SYMBOL(disk_clear_badblocks); + +/* sysfs access to bad-blocks list. */ +static ssize_t disk_badblocks_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return sprintf(page, "\n"); + + return badblocks_show(disk->bb, page, 0); +} + +static ssize_t disk_badblocks_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t len) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return -ENXIO; + + return badblocks_store(disk->bb, page, len, 0); +} + /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for @@ -989,6 +1062,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); +static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show, + disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -1010,6 +1085,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, + &dev_attr_badblocks.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 847cc1d91634..0bbec6880051 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -162,6 +162,7 @@ struct disk_part_tbl { }; struct disk_events; +struct badblocks; #if defined(CONFIG_BLK_DEV_INTEGRITY) @@ -213,6 +214,7 @@ struct gendisk { struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ int node_id; + struct badblocks *bb; }; static inline struct gendisk *part_to_disk(struct hd_struct *part) @@ -433,6 +435,11 @@ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); +int disk_alloc_badblocks(struct gendisk *disk); +extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors); +extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors); +extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); -- cgit v1.2.3 From 0caeef63e6d2f866d85bb507bf63e0ce8ec91cef Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 24 Dec 2015 19:21:43 -0700 Subject: libnvdimm: Add a poison list and export badblocks During region creation, perform Address Range Scrubs (ARS) for the SPA (System Physical Address) ranges to retrieve known poison locations from firmware. Add a new data structure 'nd_poison' which is used as a list in nvdimm_bus to store these poison locations. When creating a pmem namespace, if there is any known poison associated with its physical address space, convert the poison ranges to bad sectors that are exposed using the badblocks interface. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 203 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/core.c | 187 ++++++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/nd-core.h | 3 + drivers/nvdimm/nd.h | 6 ++ drivers/nvdimm/pmem.c | 6 ++ include/linux/libnvdimm.h | 1 + 6 files changed, 406 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index e7ed39bab97d..e1dbc8da09b7 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1473,6 +1474,201 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus, /* devm will free nfit_blk */ } +static int ars_get_cap(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_cap *cmd, u64 addr, u64 length) +{ + cmd->address = addr; + cmd->length = length; + + return nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd, + sizeof(*cmd)); +} + +static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_start *cmd, u64 addr, u64 length) +{ + int rc; + + cmd->address = addr; + cmd->length = length; + cmd->type = ND_ARS_PERSISTENT; + + while (1) { + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, cmd, + sizeof(*cmd)); + if (rc) + return rc; + switch (cmd->status) { + case 0: + return 0; + case 1: + /* ARS unsupported, but we should never get here */ + return 0; + case 2: + return -EINVAL; + case 3: + /* ARS is in progress */ + msleep(1000); + break; + default: + return -ENXIO; + } + } +} + +static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_status *cmd) +{ + int rc; + + while (1) { + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd, + sizeof(*cmd)); + if (rc || cmd->status & 0xffff) + return -ENXIO; + + /* Check extended status (Upper two bytes) */ + switch (cmd->status >> 16) { + case 0: + return 0; + case 1: + /* ARS is in progress */ + msleep(1000); + break; + case 2: + /* No ARS performed for the current boot */ + return 0; + default: + return -ENXIO; + } + } +} + +static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus, + struct nd_cmd_ars_status *ars_status, u64 start) +{ + int rc; + u32 i; + + /* + * The address field returned by ars_status should be either + * less than or equal to the address we last started ARS for. + * The (start, length) returned by ars_status should also have + * non-zero overlap with the range we started ARS for. + * If this is not the case, bail. + */ + if (ars_status->address > start || + (ars_status->address + ars_status->length < start)) + return -ENXIO; + + for (i = 0; i < ars_status->num_records; i++) { + rc = nvdimm_bus_add_poison(nvdimm_bus, + ars_status->records[i].err_address, + ars_status->records[i].length); + if (rc) + return rc; + } + + return 0; +} + +static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, + struct nd_region_desc *ndr_desc) +{ + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; + struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; + struct nd_cmd_ars_status *ars_status = NULL; + struct nd_cmd_ars_start *ars_start = NULL; + struct nd_cmd_ars_cap *ars_cap = NULL; + u64 start, len, cur, remaining; + int rc; + + ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL); + if (!ars_cap) + return -ENOMEM; + + start = ndr_desc->res->start; + len = ndr_desc->res->end - ndr_desc->res->start + 1; + + rc = ars_get_cap(nd_desc, ars_cap, start, len); + if (rc) + goto out; + + /* + * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in + * extended status is not set, skip this but continue initialization + */ + if ((ars_cap->status & 0xffff) || + !(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) { + dev_warn(acpi_desc->dev, + "ARS unsupported (status: 0x%x), won't create an error list\n", + ars_cap->status); + goto out; + } + + /* + * Check if a full-range ARS has been run. If so, use those results + * without having to start a new ARS. + */ + ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status), + GFP_KERNEL); + if (!ars_status) { + rc = -ENOMEM; + goto out; + } + + rc = ars_get_status(nd_desc, ars_status); + if (rc) + goto out; + + if (ars_status->address <= start && + (ars_status->address + ars_status->length >= start + len)) { + rc = ars_status_process_records(nvdimm_bus, ars_status, start); + goto out; + } + + /* + * ARS_STATUS can overflow if the number of poison entries found is + * greater than the maximum buffer size (ars_cap->max_ars_out) + * To detect overflow, check if the length field of ars_status + * is less than the length we supplied. If so, process the + * error entries we got, adjust the start point, and start again + */ + ars_start = kzalloc(sizeof(*ars_start), GFP_KERNEL); + if (!ars_start) + return -ENOMEM; + + cur = start; + remaining = len; + do { + u64 done, end; + + rc = ars_do_start(nd_desc, ars_start, cur, remaining); + if (rc) + goto out; + + rc = ars_get_status(nd_desc, ars_status); + if (rc) + goto out; + + rc = ars_status_process_records(nvdimm_bus, ars_status, cur); + if (rc) + goto out; + + end = min(cur + remaining, + ars_status->address + ars_status->length); + done = end - cur; + cur += done; + remaining -= done; + } while (remaining); + + out: + kfree(ars_cap); + kfree(ars_start); + kfree(ars_status); + return rc; +} + static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc, struct acpi_nfit_memory_map *memdev, @@ -1585,6 +1781,13 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, nvdimm_bus = acpi_desc->nvdimm_bus; if (nfit_spa_type(spa) == NFIT_SPA_PM) { + rc = acpi_nfit_find_poison(acpi_desc, ndr_desc); + if (rc) { + dev_err(acpi_desc->dev, + "error while performing ARS to find poison: %d\n", + rc); + return rc; + } if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc)) return -ENOMEM; } else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) { diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 82c49bb87055..21003b7f0b38 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -325,6 +325,7 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, if (!nvdimm_bus) return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); + INIT_LIST_HEAD(&nvdimm_bus->poison_list); init_waitqueue_head(&nvdimm_bus->probe_wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); mutex_init(&nvdimm_bus->reconfig_mutex); @@ -359,6 +360,191 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, } EXPORT_SYMBOL_GPL(__nvdimm_bus_register); +/** + * __add_badblock_range() - Convert a physical address range to bad sectors + * @disk: the disk associated with the namespace + * @ns_offset: namespace offset where the error range begins (in bytes) + * @len: number of bytes of poison to be added + * + * This assumes that the range provided with (ns_offset, len) is within + * the bounds of physical addresses for this namespace, i.e. lies in the + * interval [ns_start, ns_start + ns_size) + */ +static int __add_badblock_range(struct gendisk *disk, u64 ns_offset, u64 len) +{ + unsigned int sector_size = queue_logical_block_size(disk->queue); + sector_t start_sector; + u64 num_sectors; + u32 rem; + int rc; + + start_sector = div_u64(ns_offset, sector_size); + num_sectors = div_u64_rem(len, sector_size, &rem); + if (rem) + num_sectors++; + + if (!disk->bb) { + rc = disk_alloc_badblocks(disk); + if (rc) + return rc; + } + + if (unlikely(num_sectors > (u64)INT_MAX)) { + u64 remaining = num_sectors; + sector_t s = start_sector; + + while (remaining) { + int done = min_t(u64, remaining, INT_MAX); + + rc = disk_set_badblocks(disk, s, done); + if (rc) + return rc; + remaining -= done; + s += done; + } + return 0; + } else + return disk_set_badblocks(disk, start_sector, num_sectors); +} + +/** + * nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks + * @disk: the gendisk associated with the namespace where badblocks + * will be stored + * @offset: offset at the start of the namespace before 'sector 0' + * @ndns: the namespace containing poison ranges + * + * The poison list generated during NFIT initialization may contain multiple, + * possibly overlapping ranges in the SPA (System Physical Address) space. + * Compare each of these ranges to the namespace currently being initialized, + * and add badblocks to the gendisk for all matching sub-ranges + * + * Return: + * 0 - Success + */ +int nvdimm_namespace_add_poison(struct gendisk *disk, resource_size_t offset, + struct nd_namespace_common *ndns) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct nd_region *nd_region = to_nd_region(ndns->dev.parent); + struct nvdimm_bus *nvdimm_bus; + struct list_head *poison_list; + u64 ns_start, ns_end, ns_size; + struct nd_poison *pl; + int rc; + + ns_size = nvdimm_namespace_capacity(ndns) - offset; + ns_start = nsio->res.start + offset; + ns_end = nsio->res.end; + + nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent); + poison_list = &nvdimm_bus->poison_list; + if (list_empty(poison_list)) + return 0; + + list_for_each_entry(pl, poison_list, list) { + u64 pl_end = pl->start + pl->length - 1; + + /* Discard intervals with no intersection */ + if (pl_end < ns_start) + continue; + if (pl->start > ns_end) + continue; + /* Deal with any overlap after start of the namespace */ + if (pl->start >= ns_start) { + u64 start = pl->start; + u64 len; + + if (pl_end <= ns_end) + len = pl->length; + else + len = ns_start + ns_size - pl->start; + + rc = __add_badblock_range(disk, start - ns_start, len); + if (rc) + return rc; + dev_info(&nvdimm_bus->dev, + "Found a poison range (0x%llx, 0x%llx)\n", + start, len); + continue; + } + /* Deal with overlap for poison starting before the namespace */ + if (pl->start < ns_start) { + u64 len; + + if (pl_end < ns_end) + len = pl->start + pl->length - ns_start; + else + len = ns_size; + + rc = __add_badblock_range(disk, 0, len); + if (rc) + return rc; + dev_info(&nvdimm_bus->dev, + "Found a poison range (0x%llx, 0x%llx)\n", + pl->start, len); + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(nvdimm_namespace_add_poison); + +static int __add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length) +{ + struct nd_poison *pl; + + pl = kzalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + + pl->start = addr; + pl->length = length; + list_add_tail(&pl->list, &nvdimm_bus->poison_list); + + return 0; +} + +int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length) +{ + struct nd_poison *pl; + + if (list_empty(&nvdimm_bus->poison_list)) + return __add_poison(nvdimm_bus, addr, length); + + /* + * There is a chance this is a duplicate, check for those first. + * This will be the common case as ARS_STATUS returns all known + * errors in the SPA space, and we can't query it per region + */ + list_for_each_entry(pl, &nvdimm_bus->poison_list, list) + if (pl->start == addr) { + /* If length has changed, update this list entry */ + if (pl->length != length) + pl->length = length; + return 0; + } + + /* + * If not a duplicate or a simple length update, add the entry as is, + * as any overlapping ranges will get resolved when the list is consumed + * and converted to badblocks + */ + return __add_poison(nvdimm_bus, addr, length); +} +EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison); + +static void free_poison_list(struct list_head *poison_list) +{ + struct nd_poison *pl, *next; + + list_for_each_entry_safe(pl, next, poison_list, list) { + list_del(&pl->list); + kfree(pl); + } + list_del_init(poison_list); +} + static int child_unregister(struct device *dev, void *data) { /* @@ -385,6 +571,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus) nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); + free_poison_list(&nvdimm_bus->poison_list); nvdimm_bus_destroy_ndctl(nvdimm_bus); device_unregister(&nvdimm_bus->dev); diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 159aed532042..d3b7ea78df96 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -30,6 +30,7 @@ struct nvdimm_bus { struct list_head list; struct device dev; int id, probe_active; + struct list_head poison_list; struct mutex reconfig_mutex; }; @@ -89,4 +90,6 @@ bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach, ssize_t nd_namespace_store(struct device *dev, struct nd_namespace_common **_ndns, const char *buf, size_t len); +int nvdimm_namespace_add_poison(struct gendisk *disk, resource_size_t offset, + struct nd_namespace_common *ndns); #endif /* __ND_CORE_H__ */ diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 417e521d299c..ba91fcd5818d 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -38,6 +38,12 @@ enum { #endif }; +struct nd_poison { + u64 start; + u64 length; + struct list_head list; +}; + struct nvdimm_drvdata { struct device *dev; int nsindex_size; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 8ee79893d2f5..5b95043443a3 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -27,6 +27,7 @@ #include #include #include +#include "nd-core.h" #include "pfn.h" #include "nd.h" @@ -168,6 +169,7 @@ static int pmem_attach_disk(struct device *dev, { int nid = dev_to_node(dev); struct gendisk *disk; + int ret; pmem->pmem_queue = blk_alloc_queue_node(GFP_KERNEL, nid); if (!pmem->pmem_queue) @@ -196,6 +198,10 @@ static int pmem_attach_disk(struct device *dev, set_capacity(disk, (pmem->size - pmem->data_offset) / 512); pmem->pmem_disk = disk; + ret = nvdimm_namespace_add_poison(disk, pmem->data_offset, ndns); + if (ret) + return ret; + add_disk(disk); revalidate_disk(disk); diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 3f021dc5da8c..bed40dff0e86 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -116,6 +116,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } +int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length); struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, struct nvdimm_bus_descriptor *nfit_desc, struct module *module); #define nvdimm_bus_register(parent, desc) \ -- cgit v1.2.3 From d3b407fb3f782bd915db64e266010ea30a2d381e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Jan 2016 12:19:22 -0800 Subject: badblocks: rename badblocks_free to badblocks_exit For symmetry with badblocks_init() make it clear that this path only destroys incremental allocations of a badblocks instance, and does not free the badblocks instance itself. Signed-off-by: Dan Williams --- block/badblocks.c | 6 +++--- block/genhd.c | 2 +- drivers/md/md.c | 2 +- include/linux/badblocks.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/badblocks.c b/block/badblocks.c index 96aeb9194a2e..fabf6b64c2d1 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -550,12 +550,12 @@ int badblocks_init(struct badblocks *bb, int enable) EXPORT_SYMBOL_GPL(badblocks_init); /** - * badblocks_free() - free the badblocks structure + * badblocks_exit() - free the badblocks structure * @bb: the badblocks structure that holds all badblock information */ -void badblocks_free(struct badblocks *bb) +void badblocks_exit(struct badblocks *bb) { kfree(bb->page); bb->page = NULL; } -EXPORT_SYMBOL_GPL(badblocks_free); +EXPORT_SYMBOL_GPL(badblocks_exit); diff --git a/block/genhd.c b/block/genhd.c index 88579cf373b8..f463c67e6ba2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -671,7 +671,7 @@ void del_gendisk(struct gendisk *disk) blk_unregister_region(disk_devt(disk), disk->minors); if (disk->bb) { - badblocks_free(disk->bb); + badblocks_exit(disk->bb); kfree(disk->bb); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 1e48aa9de352..96a991821ae6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -710,7 +710,7 @@ void md_rdev_clear(struct md_rdev *rdev) put_page(rdev->bb_page); rdev->bb_page = NULL; } - badblocks_free(&rdev->badblocks); + badblocks_exit(&rdev->badblocks); } EXPORT_SYMBOL_GPL(md_rdev_clear); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h index 929344630b51..2d98c026c57f 100644 --- a/include/linux/badblocks.h +++ b/include/linux/badblocks.h @@ -48,6 +48,6 @@ ssize_t badblocks_show(struct badblocks *bb, char *page, int unack); ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); int badblocks_init(struct badblocks *bb, int enable); -void badblocks_free(struct badblocks *bb); +void badblocks_exit(struct badblocks *bb); #endif -- cgit v1.2.3 From 16263ff6c72eb4cc00aa287230144dda12ccad12 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 4 Jan 2016 23:50:23 -0800 Subject: block, badblocks: introduce devm_init_badblocks Provide a devres interface for initializing a badblocks instance. The pmem driver has several scenarios where it will be beneficial to have this structure automatically freed when the device is disabled / fails probe. Signed-off-by: Dan Williams --- block/badblocks.c | 48 ++++++++++++++++++++++++++++++++++------------- include/linux/badblocks.h | 14 +++++++++++++- 2 files changed, 48 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/block/badblocks.c b/block/badblocks.c index 37e5c0a2ef69..7be53cb1cc3c 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -522,24 +523,20 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, } EXPORT_SYMBOL_GPL(badblocks_store); -/** - * badblocks_init() - initialize the badblocks structure - * @bb: the badblocks structure that holds all badblock information - * @enable: weather to enable badblocks accounting - * - * Return: - * 0: success - * -ve errno: on error - */ -int badblocks_init(struct badblocks *bb, int enable) +static int __badblocks_init(struct device *dev, struct badblocks *bb, + int enable) { + bb->dev = dev; bb->count = 0; if (enable) bb->shift = 0; else bb->shift = -1; - bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (bb->page == (u64 *)0) { + if (dev) + bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL); + else + bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!bb->page) { bb->shift = -1; return -ENOMEM; } @@ -547,8 +544,30 @@ int badblocks_init(struct badblocks *bb, int enable) return 0; } + +/** + * badblocks_init() - initialize the badblocks structure + * @bb: the badblocks structure that holds all badblock information + * @enable: weather to enable badblocks accounting + * + * Return: + * 0: success + * -ve errno: on error + */ +int badblocks_init(struct badblocks *bb, int enable) +{ + return __badblocks_init(NULL, bb, enable); +} EXPORT_SYMBOL_GPL(badblocks_init); +int devm_init_badblocks(struct device *dev, struct badblocks *bb) +{ + if (!bb) + return -EINVAL; + return __badblocks_init(dev, bb, 1); +} +EXPORT_SYMBOL_GPL(devm_init_badblocks); + /** * badblocks_exit() - free the badblocks structure * @bb: the badblocks structure that holds all badblock information @@ -557,7 +576,10 @@ void badblocks_exit(struct badblocks *bb) { if (!bb) return; - kfree(bb->page); + if (bb->dev) + devm_kfree(bb->dev, bb->page); + else + kfree(bb->page); bb->page = NULL; } EXPORT_SYMBOL_GPL(badblocks_exit); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h index 2d98c026c57f..c3bdf8c59480 100644 --- a/include/linux/badblocks.h +++ b/include/linux/badblocks.h @@ -2,6 +2,7 @@ #define _LINUX_BADBLOCKS_H #include +#include #include #include #include @@ -23,6 +24,7 @@ #define MAX_BADBLOCKS (PAGE_SIZE/8) struct badblocks { + struct device *dev; /* set by devm_init_badblocks */ int count; /* count of bad blocks */ int unacked_exist; /* there probably are unacknowledged * bad blocks. This is only cleared @@ -49,5 +51,15 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); int badblocks_init(struct badblocks *bb, int enable); void badblocks_exit(struct badblocks *bb); - +struct device; +int devm_init_badblocks(struct device *dev, struct badblocks *bb); +static inline void devm_exit_badblocks(struct device *dev, struct badblocks *bb) +{ + if (bb->dev != dev) { + dev_WARN_ONCE(dev, 1, "%s: badblocks instance not associated\n", + __func__); + return; + } + badblocks_exit(bb); +} #endif -- cgit v1.2.3 From 55f5560d8c18fe33fc169f8d244a9247dcac7612 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 5 Jan 2016 00:28:18 -0800 Subject: block: kill disk_{check|set|clear|alloc}_badblocks These actions are completely managed by a block driver or can use the badblocks api directly. Signed-off-by: Dan Williams --- block/genhd.c | 42 ------------------------------------------ include/linux/genhd.h | 5 ----- 2 files changed, 47 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index aa38cd0a66c7..5aaeb2ad0fd3 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -506,16 +506,6 @@ static int exact_lock(dev_t devt, void *data) return 0; } -int disk_alloc_badblocks(struct gendisk *disk) -{ - disk->bb = kzalloc(sizeof(*(disk->bb)), GFP_KERNEL); - if (!disk->bb) - return -ENOMEM; - - return badblocks_init(disk->bb, 1); -} -EXPORT_SYMBOL(disk_alloc_badblocks); - static void register_disk(struct gendisk *disk) { struct device *ddev = disk_to_dev(disk); @@ -682,38 +672,6 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); -/* - * The gendisk usage of badblocks does not track acknowledgements for - * badblocks. We always assume they are acknowledged. - */ -int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors); -} -EXPORT_SYMBOL(disk_check_badblocks); - -int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_set(disk->bb, s, sectors, 1); -} -EXPORT_SYMBOL(disk_set_badblocks); - -int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_clear(disk->bb, s, sectors); -} -EXPORT_SYMBOL(disk_clear_badblocks); - /* sysfs access to bad-blocks list. */ static ssize_t disk_badblocks_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0bbec6880051..5c706765404a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -435,11 +435,6 @@ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); -int disk_alloc_badblocks(struct gendisk *disk); -extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors); -extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors); -extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); -- cgit v1.2.3 From f199d39349beabcb1a374cb02e0845a0ae84f3fd Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 14 Dec 2015 10:19:11 +0000 Subject: mfd: arizona: Add device tree binding to specify mono outputs Add device tree bindings to support specifying outputs from the chip as mono outputs. Whilst we are doing it change the out_mono pdata from a bool to an int, because Sparse gets upset about using ARRAY_SIZE on bools. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- drivers/mfd/arizona-core.c | 10 ++++++++++ include/linux/mfd/arizona/pdata.h | 2 +- 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c index b9489a0d7fab..4bb486679110 100644 --- a/drivers/mfd/arizona-core.c +++ b/drivers/mfd/arizona-core.c @@ -861,6 +861,16 @@ static int arizona_of_get_core_pdata(struct arizona *arizona) count++; } + count = 0; + of_property_for_each_u32(arizona->dev->of_node, "wlf,out-mono", prop, + cur, val) { + if (count == ARRAY_SIZE(pdata->out_mono)) + break; + + pdata->out_mono[count] = !!val; + count++; + } + return 0; } diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h index 57b45caaea80..64faeeff698c 100644 --- a/include/linux/mfd/arizona/pdata.h +++ b/include/linux/mfd/arizona/pdata.h @@ -171,7 +171,7 @@ struct arizona_pdata { int inmode[ARIZONA_MAX_INPUT]; /** Mode for outputs */ - bool out_mono[ARIZONA_MAX_OUTPUT]; + int out_mono[ARIZONA_MAX_OUTPUT]; /** PDM speaker mute setting */ unsigned int spk_mute[ARIZONA_MAX_PDM_SPK]; -- cgit v1.2.3 From c698d639f72b55686ec3518d2bc8dc5f2eca9354 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sun, 13 Dec 2015 15:33:19 -0500 Subject: i2c: create builtin_i2c_driver to avoid registration boilerplate In commit f309d4443130bf814e991f836e919dca22df37ae ("platform_device: better support builtin boilerplate avoidance") we introduced the builtin_driver macro. Here we use that support and extend it to I2C driver registration, so where a driver is clearly non-modular and builtin-only, we can register it in a similar fashion. And existing code that is clearly non-modular can be updated with the simple mapping of module_i2c_driver(...) ---> builtin_i2c_driver(...) We've essentially cloned the former to make the latter, and taken out the remove/module_exit parts since those never get used in a non-modular build of the code. A similar thing was done in commit b4eb6cdbbd13698704863f680c643c569909e1c2 ("PCI: Add builtin_pci_driver() to avoid registration boilerplate"). Signed-off-by: Paul Gortmaker Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index bc2b19ad9357..200cf13b00f6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -655,7 +655,7 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) } /** - * module_i2c_driver() - Helper macro for registering a I2C driver + * module_i2c_driver() - Helper macro for registering a modular I2C driver * @__i2c_driver: i2c_driver struct * * Helper macro for I2C drivers which do not do anything special in module @@ -666,6 +666,17 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap) module_driver(__i2c_driver, i2c_add_driver, \ i2c_del_driver) +/** + * builtin_i2c_driver() - Helper macro for registering a builtin I2C driver + * @__i2c_driver: i2c_driver struct + * + * Helper macro for I2C drivers which do not do anything special in their + * init. This eliminates a lot of boilerplate. Each driver may only + * use this macro once, and calling it replaces device_initcall(). + */ +#define builtin_i2c_driver(__i2c_driver) \ + builtin_driver(__i2c_driver, i2c_add_driver) + #endif /* I2C */ #if IS_ENABLED(CONFIG_OF) -- cgit v1.2.3 From c510eff6bebaa244e577b8f499e86606b5e5d4c7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 14 Jan 2016 15:16:59 -0800 Subject: fsnotify: destroy marks with call_srcu instead of dedicated thread At the time that this code was originally written, call_srcu didn't exist, so this thread was required to ensure that we waited for that SRCU grace period to settle before finally freeing the object. It does exist now however and we can much more efficiently use call_srcu to handle this. That also allows us to potentially use srcu_barrier to ensure that they are all of the callbacks have run before proceeding. In order to conserve space, we union the rcu_head with the g_list. This will be necessary for nfsd which will allocate marks from a dedicated slabcache. We have to be able to ensure that all of the objects are destroyed before destroying the cache. That's fairly Signed-off-by: Jeff Layton Cc: Eric Paris Reviewed-by: Jan Kara Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 66 +++++++++------------------------------- include/linux/fsnotify_backend.h | 5 ++- 2 files changed, 18 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/mark.c b/fs/notify/mark.c index fc0df4442f7b..cfcbf114676e 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -92,9 +92,6 @@ #include "fsnotify.h" struct srcu_struct fsnotify_mark_srcu; -static DEFINE_SPINLOCK(destroy_lock); -static LIST_HEAD(destroy_list); -static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -168,10 +165,19 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark) atomic_dec(&group->num_marks); } +static void +fsnotify_mark_free_rcu(struct rcu_head *rcu) +{ + struct fsnotify_mark *mark; + + mark = container_of(rcu, struct fsnotify_mark, g_rcu); + fsnotify_put_mark(mark); +} + /* - * Free fsnotify mark. The freeing is actually happening from a kthread which - * first waits for srcu period end. Caller must have a reference to the mark - * or be protected by fsnotify_mark_srcu. + * Free fsnotify mark. The freeing is actually happening from a call_srcu + * callback. Caller must have a reference to the mark or be protected by + * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { @@ -186,10 +192,7 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); - spin_lock(&destroy_lock); - list_add(&mark->g_list, &destroy_list); - spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); + call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); /* * Some groups like to know that marks are being freed. This is a @@ -385,11 +388,7 @@ err: spin_unlock(&mark->lock); - spin_lock(&destroy_lock); - list_add(&mark->g_list, &destroy_list); - spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); - + call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); return ret; } @@ -492,40 +491,3 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } - -static int fsnotify_mark_destroy(void *ignored) -{ - struct fsnotify_mark *mark, *next; - struct list_head private_destroy_list; - - for (;;) { - spin_lock(&destroy_lock); - /* exchange the list head */ - list_replace_init(&destroy_list, &private_destroy_list); - spin_unlock(&destroy_lock); - - synchronize_srcu(&fsnotify_mark_srcu); - - list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { - list_del_init(&mark->g_list); - fsnotify_put_mark(mark); - } - - wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list)); - } - - return 0; -} - -static int __init fsnotify_mark_init(void) -{ - struct task_struct *thread; - - thread = kthread_run(fsnotify_mark_destroy, NULL, - "fsnotify_mark"); - if (IS_ERR(thread)) - panic("unable to start fsnotify mark destruction thread."); - - return 0; -} -device_initcall(fsnotify_mark_init); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 533c4408529a..6b7e89f45aa4 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,7 +220,10 @@ struct fsnotify_mark { /* List of marks by group->i_fsnotify_marks. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ - struct list_head g_list; + union { + struct list_head g_list; + struct rcu_head g_rcu; + }; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [obj_lock] */ -- cgit v1.2.3 From 2bd03e49d66775da8cebdcc8d5bec7d68512ae87 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 14 Jan 2016 15:17:53 -0800 Subject: include/linux/dcache.h: remove semicolons from HASH_LEN_DECLARE A little cleanup - the invocation site provdes the semicolon. Cc: Rasmus Villemoes Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d67ae119cf4e..7781ce110503 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -27,10 +27,10 @@ struct vfsmount; /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN - #define HASH_LEN_DECLARE u32 hash; u32 len; + #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else - #define HASH_LEN_DECLARE u32 len; u32 hash; + #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif -- cgit v1.2.3 From 20b5c30398639b458371c228abfda829854b61c5 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Jan 2016 15:18:08 -0800 Subject: Revert "gfp: add __GFP_NOACCOUNT" This reverts commit 8f4fc071b192 ("gfp: add __GFP_NOACCOUNT"). Black-list kmem accounting policy (aka __GFP_NOACCOUNT) turned out to be fragile and difficult to maintain, because there seem to be many more allocations that should not be accounted than those that should be. Besides, false accounting an allocation might result in much worse consequences than not accounting at all, namely increased memory consumption due to pinned dead kmem caches. So it was decided to switch to the white-list policy. This patch reverts bits introducing the black-list policy. The white-list policy will be introduced later in the series. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Greg Thelen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 -- include/linux/memcontrol.h | 2 -- mm/kmemleak.c | 3 +-- 3 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8942af0813e3..075b014448f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,7 +30,6 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_ATOMIC 0x80000u -#define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -104,7 +103,6 @@ struct vm_area_struct; #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) -#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* * Reclaim modifiers diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index cd0e2413c358..2103f36b3bd3 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -773,8 +773,6 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp) { if (!memcg_kmem_enabled()) return true; - if (gfp & __GFP_NOACCOUNT) - return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; return false; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 19423a45d7d7..25c0ad36fe38 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -122,8 +122,7 @@ #define BYTES_PER_POINTER sizeof(void *) /* GFP bitmask for kmemleak internal allocations */ -#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \ - __GFP_NOACCOUNT)) | \ +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ __GFP_NOWARN) -- cgit v1.2.3 From a9bb7e620efdfd29b6d1c238041173e411670996 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Jan 2016 15:18:12 -0800 Subject: memcg: only account kmem allocations marked as __GFP_ACCOUNT Black-list kmem accounting policy (aka __GFP_NOACCOUNT) turned out to be fragile and difficult to maintain, because there seem to be many more allocations that should not be accounted than those that should be. Besides, false accounting an allocation might result in much worse consequences than not accounting at all, namely increased memory consumption due to pinned dead kmem caches. So this patch switches kmem accounting to the white-policy: now only those kmem allocations that are marked as __GFP_ACCOUNT are accounted to memcg. Currently, no kmem allocations are marked like this. The following patches will mark several kmem allocations that are known to be easily triggered from userspace and therefore should be accounted to memcg. Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Greg Thelen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 9 +++++++++ include/linux/memcontrol.h | 2 ++ mm/page_alloc.c | 3 ++- 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 075b014448f5..1dd59abe541d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,6 +30,7 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_ATOMIC 0x80000u +#define ___GFP_ACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_DIRECT_RECLAIM 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -72,11 +73,15 @@ struct vm_area_struct; * * __GFP_THISNODE forces the allocation to be satisified from the requested * node with no fallbacks or placement policy enforcements. + * + * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg (only relevant + * to kmem allocations). */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) +#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /* * Watermark modifiers -- controls access to emergency reserves @@ -195,6 +200,9 @@ struct vm_area_struct; * GFP_KERNEL is typical for kernel-internal allocations. The caller requires * ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * + * GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is + * accounted to kmemcg. + * * GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * @@ -234,6 +242,7 @@ struct vm_area_struct; */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2103f36b3bd3..c9d9a8e7b45f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -773,6 +773,8 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp) { if (!memcg_kmem_enabled()) return true; + if (!(gfp & __GFP_ACCOUNT)) + return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; return false; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9d666df5ef95..ca58bfcdadac 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3402,7 +3402,8 @@ EXPORT_SYMBOL(__free_page_frag); /* * alloc_kmem_pages charges newly allocated pages to the kmem resource counter - * of the current memory cgroup. + * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is + * equivalent to alloc_pages. * * It should be used when the caller would like to use kmalloc, but since the * allocation is large, it has to fall back to the page allocator. -- cgit v1.2.3 From 230e9fc2860450fbb1f33bdcf9093d92d7d91f5b Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Jan 2016 15:18:15 -0800 Subject: slab: add SLAB_ACCOUNT flag Currently, if we want to account all objects of a particular kmem cache, we have to pass __GFP_ACCOUNT to each kmem_cache_alloc call, which is inconvenient. This patch introduces SLAB_ACCOUNT flag which if passed to kmem_cache_create will force accounting for every allocation from this cache even if __GFP_ACCOUNT is not passed. This patch does not make any of the existing caches use this flag - it will be done later in the series. Note, a cache with SLAB_ACCOUNT cannot be merged with a cache w/o SLAB_ACCOUNT, because merged caches share the same kmem_cache struct and hence cannot have different sets of SLAB_* flags. Thus using this flag will probably reduce the number of merged slabs even if kmem accounting is not used (only compiled in). Signed-off-by: Vladimir Davydov Suggested-by: Tejun Heo Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Greg Thelen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 15 +++++++-------- include/linux/slab.h | 5 +++++ mm/memcontrol.c | 8 +++++++- mm/slab.h | 5 +++-- mm/slab_common.c | 3 ++- mm/slub.c | 2 ++ 6 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c9d9a8e7b45f..5c97265c1c6e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -766,15 +766,13 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); +struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); void __memcg_kmem_put_cache(struct kmem_cache *cachep); -static inline bool __memcg_kmem_bypass(gfp_t gfp) +static inline bool __memcg_kmem_bypass(void) { if (!memcg_kmem_enabled()) return true; - if (!(gfp & __GFP_ACCOUNT)) - return true; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) return true; return false; @@ -791,7 +789,9 @@ static inline bool __memcg_kmem_bypass(gfp_t gfp) static __always_inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { - if (__memcg_kmem_bypass(gfp)) + if (__memcg_kmem_bypass()) + return 0; + if (!(gfp & __GFP_ACCOUNT)) return 0; return __memcg_kmem_charge(page, gfp, order); } @@ -810,16 +810,15 @@ static __always_inline void memcg_kmem_uncharge(struct page *page, int order) /** * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation * @cachep: the original global kmem cache - * @gfp: allocation flags. * * All memory allocated from a per-memcg cache is charged to the owner memcg. */ static __always_inline struct kmem_cache * memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { - if (__memcg_kmem_bypass(gfp)) + if (__memcg_kmem_bypass()) return cachep; - return __memcg_kmem_get_cache(cachep); + return __memcg_kmem_get_cache(cachep, gfp); } static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) diff --git a/include/linux/slab.h b/include/linux/slab.h index 2037a861e367..3ffee7422012 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -86,6 +86,11 @@ #else # define SLAB_FAILSLAB 0x00000000UL #endif +#ifdef CONFIG_MEMCG_KMEM +# define SLAB_ACCOUNT 0x04000000UL /* Account to memcg */ +#else +# define SLAB_ACCOUNT 0x00000000UL +#endif /* The following flags affect the page allocator grouping pages by mobility */ #define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 14cb1db4c52b..4bd6c4513393 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2356,7 +2356,7 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, * Can't be called in interrupt context or from kernel threads. * This function needs to be called with rcu_read_lock() held. */ -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) +struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; @@ -2364,6 +2364,12 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) VM_BUG_ON(!is_root_cache(cachep)); + if (cachep->flags & SLAB_ACCOUNT) + gfp |= __GFP_ACCOUNT; + + if (!(gfp & __GFP_ACCOUNT)) + return cachep; + if (current->memcg_kmem_skip_account) return cachep; diff --git a/mm/slab.h b/mm/slab.h index 7b6087197997..c63b8699cfa3 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -128,10 +128,11 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, #if defined(CONFIG_SLAB) #define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \ - SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | SLAB_NOTRACK) + SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \ + SLAB_NOTRACK | SLAB_ACCOUNT) #elif defined(CONFIG_SLUB) #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ - SLAB_TEMPORARY | SLAB_NOTRACK) + SLAB_TEMPORARY | SLAB_NOTRACK | SLAB_ACCOUNT) #else #define SLAB_CACHE_FLAGS (0) #endif diff --git a/mm/slab_common.c b/mm/slab_common.c index 3c6a86b4ec25..e016178063e1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,7 +37,8 @@ struct kmem_cache *kmem_cache; SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \ SLAB_FAILSLAB) -#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK) +#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ + SLAB_NOTRACK | SLAB_ACCOUNT) /* * Merge control. If this is set then no merging of slab caches will occur. diff --git a/mm/slub.c b/mm/slub.c index 46997517406e..2d0e610d195a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5362,6 +5362,8 @@ static char *create_unique_id(struct kmem_cache *s) *p++ = 'F'; if (!(s->flags & SLAB_NOTRACK)) *p++ = 't'; + if (s->flags & SLAB_ACCOUNT) + *p++ = 'A'; if (p != name + 1) *p++ = '-'; p += sprintf(p, "%07d", s->size); -- cgit v1.2.3 From 5d097056c9a017a3b720849efb5432f37acabbac Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Jan 2016 15:18:21 -0800 Subject: kmemcg: account certain kmem allocations to memcg Mark those kmem allocations that are known to be easily triggered from userspace as __GFP_ACCOUNT/SLAB_ACCOUNT, which makes them accounted to memcg. For the list, see below: - threadinfo - task_struct - task_delay_info - pid - cred - mm_struct - vm_area_struct and vm_region (nommu) - anon_vma and anon_vma_chain - signal_struct - sighand_struct - fs_struct - files_struct - fdtable and fdtable->full_fds_bits - dentry and external_name - inode for all filesystems. This is the most tedious part, because most filesystems overwrite the alloc_inode method. The list is far from complete, so feel free to add more objects. Nevertheless, it should be close to "account everything" approach and keep most workloads within bounds. Malevolent users will be able to breach the limit, but this was possible even with the former "account everything" approach (simply because it did not account everything in fact). [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Greg Thelen Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- drivers/staging/lustre/lustre/llite/super25.c | 3 ++- fs/9p/v9fs.c | 2 +- fs/adfs/super.c | 2 +- fs/affs/super.c | 2 +- fs/afs/super.c | 2 +- fs/befs/linuxvfs.c | 2 +- fs/bfs/inode.c | 2 +- fs/block_dev.c | 2 +- fs/btrfs/inode.c | 3 ++- fs/ceph/super.c | 4 ++-- fs/cifs/cifsfs.c | 2 +- fs/coda/inode.c | 6 +++--- fs/dcache.c | 5 +++-- fs/ecryptfs/main.c | 6 ++++-- fs/efs/super.c | 6 +++--- fs/exofs/super.c | 4 ++-- fs/ext2/super.c | 2 +- fs/ext4/super.c | 2 +- fs/f2fs/super.c | 5 +++-- fs/fat/inode.c | 2 +- fs/file.c | 7 ++++--- fs/fuse/inode.c | 4 ++-- fs/gfs2/main.c | 3 ++- fs/hfs/super.c | 4 ++-- fs/hfsplus/super.c | 2 +- fs/hostfs/hostfs_kern.c | 2 +- fs/hpfs/super.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/inode.c | 2 +- fs/isofs/inode.c | 2 +- fs/jffs2/super.c | 2 +- fs/jfs/super.c | 2 +- fs/logfs/inode.c | 3 ++- fs/minix/inode.c | 2 +- fs/ncpfs/inode.c | 2 +- fs/nfs/inode.c | 2 +- fs/nilfs2/super.c | 3 ++- fs/ntfs/super.c | 4 ++-- fs/ocfs2/dlmfs/dlmfs.c | 2 +- fs/ocfs2/super.c | 2 +- fs/openpromfs/inode.c | 2 +- fs/proc/inode.c | 3 ++- fs/qnx4/inode.c | 2 +- fs/qnx6/inode.c | 2 +- fs/reiserfs/super.c | 3 ++- fs/romfs/super.c | 4 ++-- fs/squashfs/super.c | 3 ++- fs/sysv/inode.c | 2 +- fs/ubifs/super.c | 4 ++-- fs/udf/super.c | 3 ++- fs/ufs/super.c | 2 +- fs/xfs/kmem.h | 1 + fs/xfs/xfs_super.c | 4 ++-- include/linux/thread_info.h | 5 +++-- ipc/mqueue.c | 2 +- kernel/cred.c | 4 ++-- kernel/delayacct.c | 2 +- kernel/fork.c | 22 +++++++++++++--------- kernel/pid.c | 2 +- mm/nommu.c | 2 +- mm/rmap.c | 6 ++++-- mm/shmem.c | 2 +- net/socket.c | 2 +- net/sunrpc/rpc_pipe.c | 2 +- 65 files changed, 114 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 11634fa7ab3c..ad4840f86be1 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -767,7 +767,7 @@ static int __init spufs_init(void) ret = -ENOMEM; spufs_inode_cache = kmem_cache_create("spufs_inode_cache", sizeof(struct spufs_inode_info), 0, - SLAB_HWCACHE_ALIGN, spufs_init_once); + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, spufs_init_once); if (!spufs_inode_cache) goto out; diff --git a/drivers/staging/lustre/lustre/llite/super25.c b/drivers/staging/lustre/lustre/llite/super25.c index 7a9fafc67693..86c371ef71ea 100644 --- a/drivers/staging/lustre/lustre/llite/super25.c +++ b/drivers/staging/lustre/lustre/llite/super25.c @@ -106,7 +106,8 @@ static int __init init_lustre_lite(void) rc = -ENOMEM; ll_inode_cachep = kmem_cache_create("lustre_inode_cache", sizeof(struct ll_inode_info), - 0, SLAB_HWCACHE_ALIGN, NULL); + 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, + NULL); if (ll_inode_cachep == NULL) goto out_cache; diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 6caca025019d..072e7599583a 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -575,7 +575,7 @@ static int v9fs_init_inode_cache(void) v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache", sizeof(struct v9fs_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), v9fs_inode_init_once); if (!v9fs_inode_cache) return -ENOMEM; diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 4d4a0df8344f..c9fdfb112933 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -271,7 +271,7 @@ static int __init init_inodecache(void) adfs_inode_cachep = kmem_cache_create("adfs_inode_cache", sizeof(struct adfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (adfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/affs/super.c b/fs/affs/super.c index 8836df5f1e11..2a6713b6b9f4 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -132,7 +132,7 @@ static int __init init_inodecache(void) affs_inode_cachep = kmem_cache_create("affs_inode_cache", sizeof(struct affs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (affs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/afs/super.c b/fs/afs/super.c index 1fb4a5129f7d..81afefe7d8a6 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -91,7 +91,7 @@ int __init afs_fs_init(void) afs_inode_cachep = kmem_cache_create("afs_inode_cache", sizeof(struct afs_vnode), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, afs_i_init_once); if (!afs_inode_cachep) { printk(KERN_NOTICE "kAFS: Failed to allocate inode cache\n"); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 25250fa87086..cc0e08252913 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -434,7 +434,7 @@ befs_init_inodecache(void) befs_inode_cachep = kmem_cache_create("befs_inode_cache", sizeof (struct befs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (befs_inode_cachep == NULL) { pr_err("%s: Couldn't initialize inode slabcache\n", __func__); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index fdcb4d69f430..1e5c896f6b79 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -270,7 +270,7 @@ static int __init init_inodecache(void) bfs_inode_cachep = kmem_cache_create("bfs_inode_cache", sizeof(struct bfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (bfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/block_dev.c b/fs/block_dev.c index d878e4860fb7..d33071dd683e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -595,7 +595,7 @@ void __init bdev_cache_init(void) bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_PANIC), + SLAB_MEM_SPREAD|SLAB_ACCOUNT|SLAB_PANIC), init_once); err = register_filesystem(&bd_type); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3b8856e182ae..394017831692 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9161,7 +9161,8 @@ int btrfs_init_cachep(void) { btrfs_inode_cachep = kmem_cache_create("btrfs_inode", sizeof(struct btrfs_inode), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT, + init_once); if (!btrfs_inode_cachep) goto fail; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index f446afada328..ca4d5e8457f1 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -639,8 +639,8 @@ static int __init init_caches(void) ceph_inode_cachep = kmem_cache_create("ceph_inode_info", sizeof(struct ceph_inode_info), __alignof__(struct ceph_inode_info), - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), - ceph_inode_init_once); + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, ceph_inode_init_once); if (ceph_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b7fcb3151103..c4c1169814b2 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1092,7 +1092,7 @@ cifs_init_inodecache(void) cifs_inode_cachep = kmem_cache_create("cifs_inode_cache", sizeof(struct cifsInodeInfo), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), cifs_init_once); if (cifs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index cac1390b87a3..57e81cbba0fa 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -74,9 +74,9 @@ static void init_once(void *foo) int __init coda_init_inodecache(void) { coda_inode_cachep = kmem_cache_create("coda_inode_cache", - sizeof(struct coda_inode_info), - 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - init_once); + sizeof(struct coda_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, init_once); if (coda_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/dcache.c b/fs/dcache.c index 8d38cd07b207..b4539e84e577 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1571,7 +1571,8 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); - struct external_name *p = kmalloc(size + name->len, GFP_KERNEL); + struct external_name *p = kmalloc(size + name->len, + GFP_KERNEL_ACCOUNT); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; @@ -3415,7 +3416,7 @@ static void __init dcache_init(void) * of the dcache. */ dentry_cache = KMEM_CACHE(dentry, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD); + SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 4f4d0474bee9..e25b6b06bacf 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -663,6 +663,7 @@ static struct ecryptfs_cache_info { struct kmem_cache **cache; const char *name; size_t size; + unsigned long flags; void (*ctor)(void *obj); } ecryptfs_cache_infos[] = { { @@ -684,6 +685,7 @@ static struct ecryptfs_cache_info { .cache = &ecryptfs_inode_info_cache, .name = "ecryptfs_inode_cache", .size = sizeof(struct ecryptfs_inode_info), + .flags = SLAB_ACCOUNT, .ctor = inode_info_init_once, }, { @@ -755,8 +757,8 @@ static int ecryptfs_init_kmem_caches(void) struct ecryptfs_cache_info *info; info = &ecryptfs_cache_infos[i]; - *(info->cache) = kmem_cache_create(info->name, info->size, - 0, SLAB_HWCACHE_ALIGN, info->ctor); + *(info->cache) = kmem_cache_create(info->name, info->size, 0, + SLAB_HWCACHE_ALIGN | info->flags, info->ctor); if (!*(info->cache)) { ecryptfs_free_kmem_caches(); ecryptfs_printk(KERN_WARNING, "%s: " diff --git a/fs/efs/super.c b/fs/efs/super.c index c8411a30f7da..cb68dac4f9d3 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -94,9 +94,9 @@ static void init_once(void *foo) static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", - sizeof(struct efs_inode_info), - 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - init_once); + sizeof(struct efs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/exofs/super.c b/fs/exofs/super.c index b795c567b5e1..6658a50530a0 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -194,8 +194,8 @@ static int init_inodecache(void) { exofs_inode_cachep = kmem_cache_create("exofs_inode_cache", sizeof(struct exofs_i_info), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, - exofs_init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT, exofs_init_once); if (exofs_inode_cachep == NULL) return -ENOMEM; return 0; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 748d35afc902..2a188413a2b0 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -203,7 +203,7 @@ static int __init init_inodecache(void) ext2_inode_cachep = kmem_cache_create("ext2_inode_cache", sizeof(struct ext2_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ext2_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c9ab67da6e5a..f1b56ff01208 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -966,7 +966,7 @@ static int __init init_inodecache(void) ext4_inode_cachep = kmem_cache_create("ext4_inode_cache", sizeof(struct ext4_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ext4_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3bf990b80026..6134832baaaf 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1541,8 +1541,9 @@ MODULE_ALIAS_FS("f2fs"); static int __init init_inodecache(void) { - f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache", - sizeof(struct f2fs_inode_info)); + f2fs_inode_cachep = kmem_cache_create("f2fs_inode_cache", + sizeof(struct f2fs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, NULL); if (!f2fs_inode_cachep) return -ENOMEM; return 0; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 509411dd3698..6aece96df19f 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -677,7 +677,7 @@ static int __init fat_init_inodecache(void) fat_inode_cachep = kmem_cache_create("fat_inode_cache", sizeof(struct msdos_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (fat_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/file.c b/fs/file.c index 1aed0add16a2..1fbc5c0555a9 100644 --- a/fs/file.c +++ b/fs/file.c @@ -37,11 +37,12 @@ static void *alloc_fdmem(size_t size) * vmalloc() if the allocation size will be considered "large" by the VM. */ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY); + void *data = kmalloc(size, GFP_KERNEL_ACCOUNT | + __GFP_NOWARN | __GFP_NORETRY); if (data != NULL) return data; } - return vmalloc(size); + return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL); } static void __free_fdtable(struct fdtable *fdt) @@ -126,7 +127,7 @@ static struct fdtable * alloc_fdtable(unsigned int nr) if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; - fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL); + fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2913db2a5b99..4d69d5c0bedc 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1255,8 +1255,8 @@ static int __init fuse_fs_init(void) int err; fuse_inode_cachep = kmem_cache_create("fuse_inode", - sizeof(struct fuse_inode), - 0, SLAB_HWCACHE_ALIGN, + sizeof(struct fuse_inode), 0, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, fuse_inode_init_once); err = -ENOMEM; if (!fuse_inode_cachep) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 1d709d496364..f99f8e94de3f 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -114,7 +114,8 @@ static int __init init_gfs2_fs(void) gfs2_inode_cachep = kmem_cache_create("gfs2_inode", sizeof(struct gfs2_inode), 0, SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD, + SLAB_MEM_SPREAD| + SLAB_ACCOUNT, gfs2_init_inode_once); if (!gfs2_inode_cachep) goto fail; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 4574fdd3d421..1ca95c232bb5 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -483,8 +483,8 @@ static int __init init_hfs_fs(void) int err; hfs_inode_cachep = kmem_cache_create("hfs_inode_cache", - sizeof(struct hfs_inode_info), 0, SLAB_HWCACHE_ALIGN, - hfs_init_once); + sizeof(struct hfs_inode_info), 0, + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfs_init_once); if (!hfs_inode_cachep) return -ENOMEM; err = register_filesystem(&hfs_fs_type); diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 7302d96ae8bf..5d54490a136d 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -663,7 +663,7 @@ static int __init init_hfsplus_fs(void) int err; hfsplus_inode_cachep = kmem_cache_create("hfsplus_icache", - HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN, + HFSPLUS_INODE_SIZE, 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, hfsplus_init_once); if (!hfsplus_inode_cachep) return -ENOMEM; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f49be23e78aa..cfaa18c7a337 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -223,7 +223,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) { struct hostfs_inode_info *hi; - hi = kmalloc(sizeof(*hi), GFP_KERNEL); + hi = kmalloc(sizeof(*hi), GFP_KERNEL_ACCOUNT); if (hi == NULL) return NULL; hi->fd = -1; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index a561591896bd..458cf463047b 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -261,7 +261,7 @@ static int init_inodecache(void) hpfs_inode_cachep = kmem_cache_create("hpfs_inode_cache", sizeof(struct hpfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (hpfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d8f51ee8126b..f6820ecf0a11 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1322,7 +1322,7 @@ static int __init init_hugetlbfs_fs(void) error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), - 0, 0, init_once); + 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) goto out2; diff --git a/fs/inode.c b/fs/inode.c index 4230f66b7410..e491e54d2430 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1883,7 +1883,7 @@ void __init inode_init(void) sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 61abdc4920da..bcd2d41b318a 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -94,7 +94,7 @@ static int __init init_inodecache(void) isofs_inode_cachep = kmem_cache_create("isofs_inode_cache", sizeof(struct iso_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (isofs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index d86c5e3176a1..bb080c272149 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -387,7 +387,7 @@ static int __init init_jffs2_fs(void) jffs2_inode_cachep = kmem_cache_create("jffs2_i", sizeof(struct jffs2_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), jffs2_i_init_once); if (!jffs2_inode_cachep) { pr_err("error: Failed to initialise inode cache\n"); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8f9176caf098..900925b5eb8c 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -898,7 +898,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create("jfs_ip", sizeof(struct jfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, init_once); if (jfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index 0fce46d62b9c..db9cfc598883 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -409,7 +409,8 @@ const struct super_operations logfs_super_operations = { int logfs_init_inode_cache(void) { logfs_inode_cache = kmem_cache_create("logfs_inode_cache", - sizeof(struct logfs_inode), 0, SLAB_RECLAIM_ACCOUNT, + sizeof(struct logfs_inode), 0, + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, logfs_init_once); if (!logfs_inode_cache) return -ENOMEM; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index cb1789ca1ee6..f975d667c539 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -91,7 +91,7 @@ static int __init init_inodecache(void) minix_inode_cachep = kmem_cache_create("minix_inode_cache", sizeof(struct minix_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (minix_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index ce1eb3f9dfe8..1af15fcbe57b 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -82,7 +82,7 @@ static int init_inodecache(void) ncp_inode_cachep = kmem_cache_create("ncp_inode_cache", sizeof(struct ncp_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ncp_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bdb4dc7b4ecd..48fd8a87affe 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1933,7 +1933,7 @@ static int __init nfs_init_inodecache(void) nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index c7343844e6b6..7f5d3d9f1c37 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1416,7 +1416,8 @@ static int __init nilfs_init_cachep(void) { nilfs_inode_cachep = kmem_cache_create("nilfs2_inode_cache", sizeof(struct nilfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT, nilfs_inode_init_once); + SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + nilfs_inode_init_once); if (!nilfs_inode_cachep) goto fail; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index d1a853585b53..2f77f8dfb861 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -3139,8 +3139,8 @@ static int __init init_ntfs_fs(void) ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name, sizeof(big_ntfs_inode), 0, - SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, - ntfs_big_inode_init_once); + SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| + SLAB_ACCOUNT, ntfs_big_inode_init_once); if (!ntfs_big_inode_cache) { pr_crit("Failed to create %s!\n", ntfs_big_inode_cache_name); goto big_inode_err_out; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index b5cf27dcb18a..03768bb3aab1 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -638,7 +638,7 @@ static int __init init_dlmfs_fs(void) dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache", sizeof(struct dlmfs_inode_private), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), dlmfs_init_once); if (!dlmfs_inode_cache) { status = -ENOMEM; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c62d761d6bf0..faa1365097bc 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1766,7 +1766,7 @@ static int ocfs2_initialize_mem_caches(void) sizeof(struct ocfs2_inode_info), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), ocfs2_inode_init_once); ocfs2_dquot_cachep = kmem_cache_create("ocfs2_dquot_cache", sizeof(struct ocfs2_dquot), diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 15e4500cda3e..b61b883c8ff8 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -443,7 +443,7 @@ static int __init init_openprom_fs(void) sizeof(struct op_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | SLAB_ACCOUNT), op_inode_init_once); if (!op_inode_cachep) return -ENOMEM; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index d0e9b9b6223e..42305ddcbaa0 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -95,7 +95,8 @@ void __init proc_init_inodecache(void) proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD|SLAB_PANIC), + SLAB_MEM_SPREAD|SLAB_ACCOUNT| + SLAB_PANIC), init_once); } diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index f37b3deb01b4..3a67cfb142d8 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -365,7 +365,7 @@ static int init_inodecache(void) qnx4_inode_cachep = kmem_cache_create("qnx4_inode_cache", sizeof(struct qnx4_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (qnx4_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 9728b5499e1d..47bb1de07155 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -625,7 +625,7 @@ static int init_inodecache(void) qnx6_inode_cachep = kmem_cache_create("qnx6_inode_cache", sizeof(struct qnx6_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!qnx6_inode_cachep) return -ENOMEM; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 4a62fe8cc3bf..05db7473bcb5 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -626,7 +626,8 @@ static int __init init_inodecache(void) sizeof(struct reiserfs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD| + SLAB_ACCOUNT), init_once); if (reiserfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index bb894e78a821..6b00ca357c58 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -619,8 +619,8 @@ static int __init init_romfs_fs(void) romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, - SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, - romfs_i_init_once); + SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | + SLAB_ACCOUNT, romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index dded920cbc8f..5e79bfa4f260 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -419,7 +419,8 @@ static int __init init_inodecache(void) { squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache", sizeof(struct squashfs_inode_info), 0, - SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT, init_once); + SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, + init_once); return squashfs_inode_cachep ? 0 : -ENOMEM; } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 07ac18c355e7..d62c423a5a2d 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -346,7 +346,7 @@ int __init sysv_init_icache(void) { sysv_inode_cachep = kmem_cache_create("sysv_inode_cache", sizeof(struct sysv_inode_info), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, + SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, init_once); if (!sysv_inode_cachep) return -ENOMEM; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1fd90c079537..a233ba913be4 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2248,8 +2248,8 @@ static int __init ubifs_init(void) ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab", sizeof(struct ubifs_inode), 0, - SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT, - &inode_slab_ctor); + SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT | + SLAB_ACCOUNT, &inode_slab_ctor); if (!ubifs_inode_slab) return -ENOMEM; diff --git a/fs/udf/super.c b/fs/udf/super.c index 81155b9b445b..9c64a3ca9837 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -179,7 +179,8 @@ static int __init init_inodecache(void) udf_inode_cachep = kmem_cache_create("udf_inode_cache", sizeof(struct udf_inode_info), 0, (SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | + SLAB_ACCOUNT), init_once); if (!udf_inode_cachep) return -ENOMEM; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index f6390eec02ca..442fd52ebffe 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1427,7 +1427,7 @@ static int __init init_inodecache(void) ufs_inode_cachep = kmem_cache_create("ufs_inode_cache", sizeof(struct ufs_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (ufs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index cc6b768fc068..d1c66e465ca5 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -84,6 +84,7 @@ kmem_zalloc(size_t size, xfs_km_flags_t flags) #define KM_ZONE_HWALIGN SLAB_HWCACHE_ALIGN #define KM_ZONE_RECLAIM SLAB_RECLAIM_ACCOUNT #define KM_ZONE_SPREAD SLAB_MEM_SPREAD +#define KM_ZONE_ACCOUNT SLAB_ACCOUNT #define kmem_zone kmem_cache #define kmem_zone_t struct kmem_cache diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index b35775752b74..59c9b7bd958d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1714,8 +1714,8 @@ xfs_init_zones(void) xfs_inode_zone = kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode", - KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD, - xfs_fs_inode_init_once); + KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD | + KM_ZONE_ACCOUNT, xfs_fs_inode_init_once); if (!xfs_inode_zone) goto out_destroy_efi_zone; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ff307b548ed3..b4c2a485b28a 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -56,9 +56,10 @@ extern long do_no_restart_syscall(struct restart_block *parm); #ifdef __KERNEL__ #ifdef CONFIG_DEBUG_STACK_USAGE -# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) +# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ + __GFP_ZERO) #else -# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK) +# define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK) #endif /* diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 161a1807e6ef..f4617cf07069 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1438,7 +1438,7 @@ static int __init init_mqueue_fs(void) mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache", sizeof(struct mqueue_inode_info), 0, - SLAB_HWCACHE_ALIGN, init_once); + SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, init_once); if (mqueue_inode_cachep == NULL) return -ENOMEM; diff --git a/kernel/cred.c b/kernel/cred.c index 71179a09c1d6..0c0cd8a62285 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -569,8 +569,8 @@ EXPORT_SYMBOL(revert_creds); void __init cred_init(void) { /* allocate a slab in which we can store credentials */ - cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); } /** diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ef90b04d783f..435c14a45118 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -34,7 +34,7 @@ __setup("nodelayacct", delayacct_setup_disable); void delayacct_init(void) { - delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC); + delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT); delayacct_tsk_init(&init_task); } diff --git a/kernel/fork.c b/kernel/fork.c index 6774e6b2e96d..51915842f1c0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -300,9 +300,9 @@ void __init fork_init(void) #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ - task_struct_cachep = - kmem_cache_create("task_struct", arch_task_struct_size, - ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); + task_struct_cachep = kmem_cache_create("task_struct", + arch_task_struct_size, ARCH_MIN_TASKALIGN, + SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL); #endif /* do the arch specific task caches init */ @@ -1848,16 +1848,19 @@ void __init proc_caches_init(void) sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| - SLAB_NOTRACK, sighand_ctor); + SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); /* * FIXME! The "sizeof(struct mm_struct)" currently includes the * whole struct cpumask for the OFFSTACK case. We could change @@ -1867,8 +1870,9 @@ void __init proc_caches_init(void) */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); - vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } diff --git a/kernel/pid.c b/kernel/pid.c index 78b3d9f80d44..f4ad91b746f1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -604,5 +604,5 @@ void __init pidmap_init(void) atomic_dec(&init_pid_ns.pidmap[0].nr_free); init_pid_ns.pid_cachep = KMEM_CACHE(pid, - SLAB_HWCACHE_ALIGN | SLAB_PANIC); + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } diff --git a/mm/nommu.c b/mm/nommu.c index 92be862c859b..fbf6f0f1d6c9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -560,7 +560,7 @@ void __init mmap_init(void) ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); - vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC); + vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT); } /* diff --git a/mm/rmap.c b/mm/rmap.c index b577fbb98d4b..3c3f1d21f075 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -428,8 +428,10 @@ static void anon_vma_ctor(void *data) void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), - 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC, anon_vma_ctor); - anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); + 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, + anon_vma_ctor); + anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, + SLAB_PANIC|SLAB_ACCOUNT); } /* diff --git a/mm/shmem.c b/mm/shmem.c index 5813b7fa85b6..9e60093aca3f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3064,7 +3064,7 @@ static int shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), - 0, SLAB_PANIC, shmem_init_inode); + 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); return 0; } diff --git a/net/socket.c b/net/socket.c index 91c2de6f5020..c044d1e8508c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -294,7 +294,7 @@ static int init_inodecache(void) 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | SLAB_ACCOUNT), init_once); if (sock_inode_cachep == NULL) return -ENOMEM; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index d81186d34558..14f45bf0410c 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1500,7 +1500,7 @@ int register_rpc_pipefs(void) rpc_inode_cachep = kmem_cache_create("rpc_inode_cache", sizeof(struct rpc_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!rpc_inode_cachep) return -ENOMEM; -- cgit v1.2.3 From 8f235d1a3eb7198affe7cadf676a10afb8a46a1a Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Thu, 14 Jan 2016 15:18:33 -0800 Subject: mm: add PHYS_PFN, use it in __phys_to_pfn() __phys_to_pfn and __pfn_to_phys are symmetric, PHYS_PFN and PFN_PHYS are semmetric: - y = (phys_addr_t)x << PAGE_SHIFT - y >> PAGE_SHIFT = (phys_add_t)x - (unsigned long)(y >> PAGE_SHIFT) = x [akpm@linux-foundation.org: use macro arg name `x'] [arnd@arndb.de: include linux/pfn.h for PHYS_PFN definition] Signed-off-by: Chen Gang Cc: Oleg Nesterov Signed-off-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/memory_model.h | 4 +++- include/linux/pfn.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 4b4b056a6eb0..5148150cc80b 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -1,6 +1,8 @@ #ifndef __ASM_MEMORY_MODEL_H #define __ASM_MEMORY_MODEL_H +#include + #ifndef __ASSEMBLY__ #if defined(CONFIG_FLATMEM) @@ -72,7 +74,7 @@ /* * Convert a physical address to a Page Frame Number and back */ -#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) +#define __phys_to_pfn(paddr) PHYS_PFN(paddr) #define __pfn_to_phys(pfn) PFN_PHYS(pfn) #define page_to_pfn __page_to_pfn diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 7646637221f3..97f3e88aead4 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -9,5 +9,6 @@ #define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) #define PFN_DOWN(x) ((x) >> PAGE_SHIFT) #define PFN_PHYS(x) ((phys_addr_t)(x) << PAGE_SHIFT) +#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT)) #endif -- cgit v1.2.3 From 4a8c7bb59ac85b038c29adf6d32ff56e11fbb267 Mon Sep 17 00:00:00 2001 From: Nathan Zimmer Date: Thu, 14 Jan 2016 15:18:36 -0800 Subject: mm/mempolicy.c: convert the shared_policy lock to a rwlock When running the SPECint_rate gcc on some very large boxes it was noticed that the system was spending lots of time in mpol_shared_policy_lookup(). The gamess benchmark can also show it and is what I mostly used to chase down the issue since the setup for that I found to be easier. To be clear the binaries were on tmpfs because of disk I/O requirements. We then used text replication to avoid icache misses and having all the copies banging on the memory where the instruction code resides. This results in us hitting a bottleneck in mpol_shared_policy_lookup() since lookup is serialised by the shared_policy lock. I have only reproduced this on very large (3k+ cores) boxes. The problem starts showing up at just a few hundred ranks getting worse until it threatens to livelock once it gets large enough. For example on the gamess benchmark at 128 ranks this area consumes only ~1% of time, at 512 ranks it consumes nearly 13%, and at 2k ranks it is over 90%. To alleviate the contention in this area I converted the spinlock to an rwlock. This allows a large number of lookups to happen simultaneously. The results were quite good reducing this consumtion at max ranks to around 2%. [akpm@linux-foundation.org: tidy up code comments] Signed-off-by: Nathan Zimmer Acked-by: David Rientjes Acked-by: Vlastimil Babka Cc: Nadia Yvette Chambers Cc: Naoya Horiguchi Cc: Mel Gorman Cc: "Aneesh Kumar K.V" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 2 +- include/linux/mempolicy.h | 2 +- mm/mempolicy.c | 30 +++++++++++++++++------------- 3 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f6820ecf0a11..a1cb8fd2289b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -738,7 +738,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, /* * The policy is initialized here even if we are creating a * private inode because initialization simply creates an - * an empty rb tree and calls spin_lock_init(), later when we + * an empty rb tree and calls rwlock_init(), later when we * call mpol_free_shared_policy() it will just return because * the rb tree will still be empty. */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3d385c81c153..2696c1f05ed1 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -122,7 +122,7 @@ struct sp_node { struct shared_policy { struct rb_root root; - spinlock_t lock; + rwlock_t lock; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 87a177917cb2..d8caff071a30 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2142,12 +2142,14 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. - * They are protected by the sp->lock spinlock, which should be held + * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ -/* lookup first element intersecting start-end */ -/* Caller holds sp->lock */ +/* + * lookup first element intersecting start-end. Caller holds sp->lock for + * reading or for writing + */ static struct sp_node * sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) { @@ -2178,8 +2180,10 @@ sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) return rb_entry(n, struct sp_node, nd); } -/* Insert a new shared policy into the list. */ -/* Caller holds sp->lock */ +/* + * Insert a new shared policy into the list. Caller holds sp->lock for + * writing. + */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; @@ -2211,13 +2215,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) if (!sp->root.rb_node) return NULL; - spin_lock(&sp->lock); + read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } - spin_unlock(&sp->lock); + read_unlock(&sp->lock); return pol; } @@ -2360,7 +2364,7 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start, int ret = 0; restart: - spin_lock(&sp->lock); + write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { @@ -2393,7 +2397,7 @@ restart: } if (new) sp_insert(sp, new); - spin_unlock(&sp->lock); + write_unlock(&sp->lock); ret = 0; err_out: @@ -2405,7 +2409,7 @@ err_out: return ret; alloc_new: - spin_unlock(&sp->lock); + write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) @@ -2431,7 +2435,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ - spin_lock_init(&sp->lock); + rwlock_init(&sp->lock); if (mpol) { struct vm_area_struct pvma; @@ -2497,14 +2501,14 @@ void mpol_free_shared_policy(struct shared_policy *p) if (!p->root.rb_node) return; - spin_lock(&p->lock); + write_lock(&p->lock); next = rb_first(&p->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(p, n); } - spin_unlock(&p->lock); + write_unlock(&p->lock); } #ifdef CONFIG_NUMA_BALANCING -- cgit v1.2.3 From 719ff32162865522273d8fa975bf99b32875738b Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 14 Jan 2016 15:18:51 -0800 Subject: include/linux/hugetlb.h: is_file_hugepages() can be boolean Make is_file_hugepages() return bool to improve readability due to this particular function only using either one or zero as its return value. This patch also removed the if condition to make is_file_hugepages return directly. No functional change. Signed-off-by: Yaowei Bai Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index b0eb06423d5e..e76574d8f9b5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -263,20 +263,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, struct user_struct **user, int creat_flags, int page_size_log); -static inline int is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(struct file *file) { if (file->f_op == &hugetlbfs_file_operations) - return 1; - if (is_file_shm_hugepages(file)) - return 1; + return true; - return 0; + return is_file_shm_hugepages(file); } #else /* !CONFIG_HUGETLBFS */ -#define is_file_hugepages(file) 0 +#define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, struct user_struct **user, int creat_flags, -- cgit v1.2.3 From b4ad0c7e004a2cc0e52790eff72f5176b59ca386 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 14 Jan 2016 15:18:54 -0800 Subject: mm/memblock.c: memblock_is_memory()/reserved() can be boolean Make memblock_is_memory() and memblock_is_reserved return bool to improve readability due to these particular functions only using either one or zero as their return value. No functional change. Signed-off-by: Yaowei Bai Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- mm/memblock.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fec66f86eeff..3a092fba2eb2 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -325,10 +325,10 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -int memblock_is_memory(phys_addr_t addr); +bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -int memblock_is_reserved(phys_addr_t addr); +bool memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); diff --git a/mm/memblock.c b/mm/memblock.c index 07ff069fef25..9695398a14c0 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1528,12 +1528,12 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -int __init memblock_is_reserved(phys_addr_t addr) +bool __init memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } -int __init_memblock memblock_is_memory(phys_addr_t addr) +bool __init_memblock memblock_is_memory(phys_addr_t addr) { return memblock_search(&memblock.memory, addr) != -1; } -- cgit v1.2.3 From 06640290bfc6688062387f915c5df094e9872133 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 14 Jan 2016 15:18:57 -0800 Subject: include/linux/mmzone.h: remove unused is_unevictable_lru() Since commit a0b8cab3b9b2 ("mm: remove lru parameter from __pagevec_lru_add and remove parts of pagevec API") there's no user of this function anymore, so remove it. Signed-off-by: Yaowei Bai Acked-by: Michal Hocko Acked-by: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e23a9e704536..996384672c73 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -195,11 +195,6 @@ static inline int is_active_lru(enum lru_list lru) return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } -static inline int is_unevictable_lru(enum lru_list lru) -{ - return (lru == LRU_UNEVICTABLE); -} - struct zone_reclaim_stat { /* * The pageout code in vmscan.c keeps track of how many of the -- cgit v1.2.3 From c00eb15a8914b8ba84032a36044a5aaf7f71709d Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 14 Jan 2016 15:19:00 -0800 Subject: mm/zonelist: enumerate zonelists array index Hardcoding index to zonelists array in gfp_zonelist() is not a good idea, let's enumerate it to improve readability. No functional change. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix CONFIG_NUMA=n build] [n-horiguchi@ah.jp.nec.com: fix warning in comparing enumerator] Signed-off-by: Yaowei Bai Cc: Michal Hocko Cc: David Rientjes Signed-off-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 9 +++++---- include/linux/mmzone.h | 20 +++++++++----------- mm/page_alloc.c | 9 ++++----- 3 files changed, 18 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 1dd59abe541d..91f74e741aa2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -384,10 +384,11 @@ static inline enum zone_type gfp_zone(gfp_t flags) static inline int gfp_zonelist(gfp_t flags) { - if (IS_ENABLED(CONFIG_NUMA) && unlikely(flags & __GFP_THISNODE)) - return 1; - - return 0; +#ifdef CONFIG_NUMA + if (unlikely(flags & __GFP_THISNODE)) + return ZONELIST_NOFALLBACK; +#endif + return ZONELIST_FALLBACK; } /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 996384672c73..12c98dfc31b1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -571,19 +571,17 @@ static inline bool zone_is_empty(struct zone *zone) /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) +enum { + ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA - -/* - * The NUMA zonelists are doubled because we need zonelists that restrict the - * allocations to a single node for __GFP_THISNODE. - * - * [0] : Zonelist with fallback - * [1] : No fallback (__GFP_THISNODE) - */ -#define MAX_ZONELISTS 2 -#else -#define MAX_ZONELISTS 1 + /* + * The NUMA zonelists are doubled because we need zonelists that + * restrict the allocations to a single node for __GFP_THISNODE. + */ + ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif + MAX_ZONELISTS +}; /* * This struct contains information about a zone in a zonelist. It is stored diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2f6d30db4c94..e40e702ce919 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4148,8 +4148,7 @@ static void set_zonelist_order(void) static void build_zonelists(pg_data_t *pgdat) { - int j, node, load; - enum zone_type i; + int i, node, load; nodemask_t used_mask; int local_node, prev_node; struct zonelist *zonelist; @@ -4169,7 +4168,7 @@ static void build_zonelists(pg_data_t *pgdat) nodes_clear(used_mask); memset(node_order, 0, sizeof(node_order)); - j = 0; + i = 0; while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { /* @@ -4186,12 +4185,12 @@ static void build_zonelists(pg_data_t *pgdat) if (order == ZONELIST_ORDER_NODE) build_zonelists_in_node_order(pgdat, node); else - node_order[j++] = node; /* remember order */ + node_order[i++] = node; /* remember order */ } if (order == ZONELIST_ORDER_ZONE) { /* calculate node order -- i.e., DMA last! */ - build_zonelists_in_zone_order(pgdat, j); + build_zonelists_in_zone_order(pgdat, i); } build_thisnode_zonelists(pgdat); -- cgit v1.2.3 From 5b80287a65da927742c6d43b1369bd5ed133aad1 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 14 Jan 2016 15:19:11 -0800 Subject: mm/mmzone.c: memmap_valid_within() can be boolean Make memmap_valid_within return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++--- mm/mmzone.c | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 12c98dfc31b1..3b6fb71bbeb3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1200,13 +1200,13 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); * the zone and PFN linkages are still valid. This is expensive, but walkers * of the full memmap are extremely rare. */ -int memmap_valid_within(unsigned long pfn, +bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone); #else -static inline int memmap_valid_within(unsigned long pfn, +static inline bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone) { - return 1; + return true; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ diff --git a/mm/mmzone.c b/mm/mmzone.c index 7d87ebb0d632..52687fb4de6f 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -72,16 +72,16 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, } #ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL -int memmap_valid_within(unsigned long pfn, +bool memmap_valid_within(unsigned long pfn, struct page *page, struct zone *zone) { if (page_to_pfn(page) != pfn) - return 0; + return false; if (page_zone(page) != zone) - return 0; + return false; - return 1; + return true; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ -- cgit v1.2.3 From 6a15a37097c7e02390bb08d83dac433c9f10144f Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 14 Jan 2016 15:19:20 -0800 Subject: mm, proc: reduce cost of /proc/pid/smaps for shmem mappings The previous patch has improved swap accounting for shmem mapping, which however made /proc/pid/smaps more expensive for shmem mappings, as we consult the radix tree for each pte_none entry, so the overal complexity is O(n*log(n)). We can reduce this significantly for mappings that cannot contain COWed pages, because then we can either use the statistics tha shmem object itself tracks (if the mapping contains the whole object, or the swap usage of the whole object is zero), or use the radix tree iterator, which is much more effective than repeated find_get_entry() calls. This patch therefore introduces a function shmem_swap_usage(vma) and makes /proc/pid/smaps use it when possible. Only for writable private mappings of shmem objects (i.e. tmpfs files) with the shmem object itself (partially) swapped outwe have to resort to the find_get_entry() approach. Hopefully such mappings are relatively uncommon. To demonstrate the diference, I have measured this on a process that creates a 2GB mapping and dirties single pages with a stride of 2MB, and time how long does it take to cat /proc/pid/smaps of this process 100 times. Private writable mapping of a /dev/shm/file (the most complex case): real 0m3.831s user 0m0.180s sys 0m3.212s Shared mapping of an almost full mapping of a partially swapped /dev/shm/file (which needs to employ the radix tree iterator). real 0m1.351s user 0m0.096s sys 0m0.768s Same, but with /dev/shm/file not swapped (so no radix tree walk needed) real 0m0.935s user 0m0.128s sys 0m0.344s Private anonymous mapping: real 0m0.949s user 0m0.116s sys 0m0.348s The cost is now much closer to the private anonymous mapping case, unless the shmem mapping is private and writable. Signed-off-by: Vlastimil Babka Cc: Hugh Dickins Cc: Jerome Marchand Cc: Konstantin Khlebnikov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 22 +++++++++++++-- include/linux/shmem_fs.h | 2 ++ mm/shmem.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 92 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85ef60fdf2c0..5830b2e129ed 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -717,8 +718,25 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) #ifdef CONFIG_SHMEM if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { - mss.check_shmem_swap = true; - smaps_walk.pte_hole = smaps_pte_hole; + /* + * For shared or readonly shmem mappings we know that all + * swapped out pages belong to the shmem object, and we can + * obtain the swap value much more efficiently. For private + * writable mappings, we might have COW pages that are + * not affected by the parent swapped out pages of the shmem + * object, so we have to distinguish them during the page walk. + * Unless we know that the shmem object (or the part mapped by + * our VMA) has no swapped out pages at all. + */ + unsigned long shmem_swapped = shmem_swap_usage(vma); + + if (!shmem_swapped || (vma->vm_flags & VM_SHARED) || + !(vma->vm_flags & VM_WRITE)) { + mss.swap = shmem_swapped; + } else { + mss.check_shmem_swap = true; + smaps_walk.pte_hole = smaps_pte_hole; + } } #endif diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 50777b5b1e4c..bd58be5e7a2a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -60,6 +60,8 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); +extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); + static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { diff --git a/mm/shmem.c b/mm/shmem.c index 9e60093aca3f..e978621de1ef 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -359,6 +359,76 @@ static int shmem_free_swap(struct address_space *mapping, return 0; } +/* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given vma is swapped out. + * + * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct address_space *mapping = inode->i_mapping; + unsigned long swapped; + pgoff_t start, end; + struct radix_tree_iter iter; + void **slot; + struct page *page; + + /* Be careful as we don't hold info->lock */ + swapped = READ_ONCE(info->swapped); + + /* + * The easier cases are when the shmem object has nothing in swap, or + * the vma maps it whole. Then we can simply use the stats that we + * already track. + */ + if (!swapped) + return 0; + + if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) + return swapped << PAGE_SHIFT; + + swapped = 0; + + /* Here comes the more involved part */ + start = linear_page_index(vma, vma->vm_start); + end = linear_page_index(vma, vma->vm_end); + + rcu_read_lock(); + +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + if (iter.index >= end) + break; + + page = radix_tree_deref_slot(slot); + + /* + * This should only be possible to happen at index 0, so we + * don't need to reset the counter, nor do we risk infinite + * restarts. + */ + if (radix_tree_deref_retry(page)) + goto restart; + + if (radix_tree_exceptional_entry(page)) + swapped++; + + if (need_resched()) { + cond_resched_rcu(); + start = iter.index + 1; + goto restart; + } + } + + rcu_read_unlock(); + + return swapped << PAGE_SHIFT; +} + /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ -- cgit v1.2.3 From 48131e03ca4ed71d73fbe55c311a258c6fa2a090 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 14 Jan 2016 15:19:23 -0800 Subject: mm, proc: reduce cost of /proc/pid/smaps for unpopulated shmem mappings Following the previous patch, further reduction of /proc/pid/smaps cost is possible for private writable shmem mappings with unpopulated areas where the page walk invokes the .pte_hole function. We can use radix tree iterator for each such area instead of calling find_get_entry() in a loop. This is possible at the extra maintenance cost of introducing another shmem function shmem_partial_swap_usage(). To demonstrate the diference, I have measured this on a process that creates a private writable 2GB mapping of a partially swapped out /dev/shm/file (which cannot employ the optimizations from the prvious patch) and doesn't populate it at all. I time how long does it take to cat /proc/pid/smaps of this process 100 times. Before this patch: real 0m3.831s user 0m0.180s sys 0m3.212s After this patch: real 0m1.176s user 0m0.180s sys 0m0.684s The time is similar to the case where a radix tree iterator is employed on the whole mapping. Signed-off-by: Vlastimil Babka Cc: Hugh Dickins Cc: Jerome Marchand Cc: Konstantin Khlebnikov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 42 ++++++++++--------------------- include/linux/shmem_fs.h | 2 ++ mm/shmem.c | 65 ++++++++++++++++++++++++++++-------------------- 3 files changed, 53 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5830b2e129ed..8a03759bda38 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -488,42 +488,16 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, } #ifdef CONFIG_SHMEM -static unsigned long smaps_shmem_swap(struct vm_area_struct *vma, - unsigned long addr) -{ - struct page *page; - - page = find_get_entry(vma->vm_file->f_mapping, - linear_page_index(vma, addr)); - if (!page) - return 0; - - if (radix_tree_exceptional_entry(page)) - return PAGE_SIZE; - - page_cache_release(page); - return 0; - -} - static int smaps_pte_hole(unsigned long addr, unsigned long end, struct mm_walk *walk) { struct mem_size_stats *mss = walk->private; - while (addr < end) { - mss->swap += smaps_shmem_swap(walk->vma, addr); - addr += PAGE_SIZE; - } + mss->swap += shmem_partial_swap_usage( + walk->vma->vm_file->f_mapping, addr, end); return 0; } -#else -static unsigned long smaps_shmem_swap(struct vm_area_struct *vma, - unsigned long addr) -{ - return 0; -} #endif static void smaps_pte_entry(pte_t *pte, unsigned long addr, @@ -555,7 +529,17 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, page = migration_entry_to_page(swpent); } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap && pte_none(*pte))) { - mss->swap += smaps_shmem_swap(vma, addr); + page = find_get_entry(vma->vm_file->f_mapping, + linear_page_index(vma, addr)); + if (!page) + return; + + if (radix_tree_exceptional_entry(page)) + mss->swap += PAGE_SIZE; + else + page_cache_release(page); + + return; } if (!page) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index bd58be5e7a2a..a43f41cb3c43 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -61,6 +61,8 @@ extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(swp_entry_t entry, struct page *page); extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, + pgoff_t start, pgoff_t end); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) diff --git a/mm/shmem.c b/mm/shmem.c index e978621de1ef..760d90cf2a41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -361,41 +361,18 @@ static int shmem_free_swap(struct address_space *mapping, /* * Determine (in bytes) how many of the shmem object's pages mapped by the - * given vma is swapped out. + * given offsets are swapped out. * * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ -unsigned long shmem_swap_usage(struct vm_area_struct *vma) +unsigned long shmem_partial_swap_usage(struct address_space *mapping, + pgoff_t start, pgoff_t end) { - struct inode *inode = file_inode(vma->vm_file); - struct shmem_inode_info *info = SHMEM_I(inode); - struct address_space *mapping = inode->i_mapping; - unsigned long swapped; - pgoff_t start, end; struct radix_tree_iter iter; void **slot; struct page *page; - - /* Be careful as we don't hold info->lock */ - swapped = READ_ONCE(info->swapped); - - /* - * The easier cases are when the shmem object has nothing in swap, or - * the vma maps it whole. Then we can simply use the stats that we - * already track. - */ - if (!swapped) - return 0; - - if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) - return swapped << PAGE_SHIFT; - - swapped = 0; - - /* Here comes the more involved part */ - start = linear_page_index(vma, vma->vm_start); - end = linear_page_index(vma, vma->vm_end); + unsigned long swapped = 0; rcu_read_lock(); @@ -429,6 +406,40 @@ restart: return swapped << PAGE_SHIFT; } +/* + * Determine (in bytes) how many of the shmem object's pages mapped by the + * given vma is swapped out. + * + * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * as long as the inode doesn't go away and racy results are not a problem. + */ +unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + struct inode *inode = file_inode(vma->vm_file); + struct shmem_inode_info *info = SHMEM_I(inode); + struct address_space *mapping = inode->i_mapping; + unsigned long swapped; + + /* Be careful as we don't hold info->lock */ + swapped = READ_ONCE(info->swapped); + + /* + * The easier cases are when the shmem object has nothing in swap, or + * the vma maps it whole. Then we can simply use the stats that we + * already track. + */ + if (!swapped) + return 0; + + if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) + return swapped << PAGE_SHIFT; + + /* Here comes the more involved part */ + return shmem_partial_swap_usage(mapping, + linear_page_index(vma, vma->vm_start), + linear_page_index(vma, vma->vm_end)); +} + /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ -- cgit v1.2.3 From eca56ff906bdd0239485e8b47154a6e73dd9a2f3 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Thu, 14 Jan 2016 15:19:26 -0800 Subject: mm, shmem: add internal shmem resident memory accounting Currently looking at /proc//status or statm, there is no way to distinguish shmem pages from pages mapped to a regular file (shmem pages are mapped to /dev/zero), even though their implication in actual memory use is quite different. The internal accounting currently counts shmem pages together with regular files. As a preparation to extend the userspace interfaces, this patch adds MM_SHMEMPAGES counter to mm_rss_stat to account for shmem pages separately from MM_FILEPAGES. The next patch will expose it to userspace - this patch doesn't change the exported values yet, by adding up MM_SHMEMPAGES to MM_FILEPAGES at places where MM_FILEPAGES was used before. The only user-visible change after this patch is the OOM killer message that separates the reported "shmem-rss" from "file-rss". [vbabka@suse.cz: forward-porting, tweak changelog] Signed-off-by: Jerome Marchand Signed-off-by: Vlastimil Babka Acked-by: Konstantin Khlebnikov Acked-by: Michal Hocko Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 5 +---- fs/proc/task_mmu.c | 3 ++- include/linux/mm.h | 18 +++++++++++++++++- include/linux/mm_types.h | 7 ++++--- kernel/events/uprobes.c | 2 +- mm/memory.c | 30 ++++++++++-------------------- mm/oom_kill.c | 5 +++-- mm/rmap.c | 12 +++--------- 8 files changed, 41 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 63b039899a5e..aa34af0a0b26 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -603,10 +603,7 @@ static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm) else if (is_migration_entry(entry)) { struct page *page = migration_entry_to_page(entry); - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } free_swap_and_cache(entry); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 8a03759bda38..45eb24145978 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -83,7 +83,8 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, MM_FILEPAGES); + *shared = get_mm_counter(mm, MM_FILEPAGES) + + get_mm_counter(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->total_vm - mm->shared_vm; diff --git a/include/linux/mm.h b/include/linux/mm.h index 00bad7793788..a8ab1fc0e9bc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1361,10 +1361,26 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member) atomic_long_dec(&mm->rss_stat.count[member]); } +/* Optimized variant when page is already known not to be PageAnon */ +static inline int mm_counter_file(struct page *page) +{ + if (PageSwapBacked(page)) + return MM_SHMEMPAGES; + return MM_FILEPAGES; +} + +static inline int mm_counter(struct page *page) +{ + if (PageAnon(page)) + return MM_ANONPAGES; + return mm_counter_file(page); +} + static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + - get_mm_counter(mm, MM_ANONPAGES); + get_mm_counter(mm, MM_ANONPAGES) + + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8d1492a114f..207890be93c8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -369,9 +369,10 @@ struct core_state { }; enum { - MM_FILEPAGES, - MM_ANONPAGES, - MM_SWAPENTS, + MM_FILEPAGES, /* Resident file mapping pages */ + MM_ANONPAGES, /* Resident anonymous pages */ + MM_SWAPENTS, /* Anonymous swap entries */ + MM_SHMEMPAGES, /* Resident shared memory pages */ NR_MM_COUNTERS }; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 7dad84913abf..bb0669169716 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, lru_cache_add_active_or_unevictable(kpage, vma); if (!PageAnon(page)) { - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter_file(page)); inc_mm_counter(mm, MM_ANONPAGES); } diff --git a/mm/memory.c b/mm/memory.c index c387430f06c3..f7026c035940 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -832,10 +832,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; + rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { @@ -874,10 +871,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (page) { get_page(page); page_dup_rmap(page); - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; + rss[mm_counter(page)]++; } out_set_pte: @@ -1113,9 +1107,8 @@ again: tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else { + + if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); @@ -1123,8 +1116,8 @@ again: if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); - rss[MM_FILEPAGES]--; } + rss[mm_counter(page)]--; page_remove_rmap(page); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); @@ -1146,11 +1139,7 @@ again: struct page *page; page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; + rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); @@ -1460,7 +1449,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr, /* Ok, finally just insert the thing.. */ get_page(page); - inc_mm_counter_fast(mm, MM_FILEPAGES); + inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page); set_pte_at(mm, addr, pte, mk_pte(page, prot)); @@ -2097,7 +2086,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, if (likely(pte_same(*page_table, orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { - dec_mm_counter_fast(mm, MM_FILEPAGES); + dec_mm_counter_fast(mm, + mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { @@ -2820,7 +2810,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); } else { - inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES); + inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page); } set_pte_at(vma->vm_mm, address, pte, entry); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index c12680993ff3..dc490c06941b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -585,10 +585,11 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, */ do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); mark_oom_victim(victim); - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", + pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), - K(get_mm_counter(victim->mm, MM_FILEPAGES))); + K(get_mm_counter(victim->mm, MM_FILEPAGES)), + K(get_mm_counter(victim->mm, MM_SHMEMPAGES))); task_unlock(victim); /* diff --git a/mm/rmap.c b/mm/rmap.c index 3c3f1d21f075..622756c16ac8 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1364,10 +1364,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHuge(page)) { hugetlb_count_sub(1 << compound_order(page), mm); } else { - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } set_pte_at(mm, address, pte, swp_entry_to_pte(make_hwpoison_entry(page))); @@ -1377,10 +1374,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * interest anymore. Simply discard the pte, vmscan * will take care of the rest. */ - if (PageAnon(page)) - dec_mm_counter(mm, MM_ANONPAGES); - else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter(page)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { swp_entry_t entry; pte_t swp_pte; @@ -1420,7 +1414,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); } else - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter_file(page)); page_remove_rmap(page); page_cache_release(page); -- cgit v1.2.3 From 244d63ee345bd9d45c87f665ef5e3f7bcd5db45b Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 14 Jan 2016 15:19:35 -0800 Subject: mm, vmalloc: remove VM_VPAGES VM_VPAGES is unnecessary, it's easier to check is_vmalloc_addr() when reading /proc/vmallocinfo. [akpm@linux-foundation.org: remove VM_VPAGES reference via kvfree()] Signed-off-by: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 1 - mm/vmalloc.c | 8 ++------ 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3bff87a25a42..d1f1d338af20 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,7 +14,6 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #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 */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 7007fe85840e..58ceeb107960 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1479,10 +1479,7 @@ static void __vunmap(const void *addr, int deallocate_pages) __free_kmem_pages(page, 0); } - if (area->flags & VM_VPAGES) - vfree(area->pages); - else - kfree(area->pages); + kvfree(area->pages); } kfree(area); @@ -1592,7 +1589,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM, PAGE_KERNEL, node, area->caller); - area->flags |= VM_VPAGES; } else { pages = kmalloc_node(array_size, nested_gfp, node); } @@ -2650,7 +2646,7 @@ static int s_show(struct seq_file *m, void *p) if (v->flags & VM_USERMAP) seq_puts(m, " user"); - if (v->flags & VM_VPAGES) + if (is_vmalloc_addr(v->pages)) seq_puts(m, " vpages"); show_numa_info(m, v); -- cgit v1.2.3 From 9ee11ba4251dddf1b0e507d184b25b1bd7820773 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 Jan 2016 15:19:41 -0800 Subject: memcg: do not allow to disable tcp accounting after limit is set There are two bits defined for cg_proto->flags - MEMCG_SOCK_ACTIVATED and MEMCG_SOCK_ACTIVE - both are set in tcp_update_limit, but the former is never cleared while the latter can be cleared by unsetting the limit. This allows to disable tcp socket accounting for new sockets after it was enabled by writing -1 to memory.kmem.tcp.limit_in_bytes while still guaranteeing that memcg_socket_limit_enabled static key will be decremented on memcg destruction. This functionality looks dubious, because it is not clear what a use case would be. By enabling tcp accounting a user accepts the price. If they then find the performance degradation unacceptable, they can always restart their workload with tcp accounting disabled. It does not seem there is any need to flip it while the workload is running. Besides, it contradicts to how kmem accounting API works: writing whatever to memory.kmem.limit_in_bytes enables kmem accounting for the cgroup in question, after which it cannot be disabled. Therefore one might expect that writing -1 to memory.kmem.tcp.limit_in_bytes just enables socket accounting w/o limiting it, which might be useful by itself, but it isn't true. Since this API peculiarity is not documented anywhere, I propose to drop it. This will allow to simplify the code by dropping cg_proto->flags. 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 | 12 +----------- mm/memcontrol.c | 2 +- net/ipv4/tcp_memcontrol.c | 17 +++++------------ 3 files changed, 7 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5c97265c1c6e..78a1ec2e23fc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -85,22 +85,12 @@ enum mem_cgroup_events_target { MEM_CGROUP_NTARGETS, }; -/* - * Bits in struct cg_proto.flags - */ -enum cg_proto_flags { - /* Currently active and new sockets should be assigned to cgroups */ - MEMCG_SOCK_ACTIVE, - /* It was ever activated; we must disarm static keys on destruction */ - MEMCG_SOCK_ACTIVATED, -}; - struct cg_proto { struct page_counter memory_allocated; /* Current allocated memory. */ struct percpu_counter sockets_allocated; /* Current number of sockets. */ int memory_pressure; + bool active; long sysctl_mem[3]; - unsigned long flags; /* * memcg field is used to find which memcg we belong directly * Each memcg struct can hold more than one cg_proto, so container_of diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4bd6c4513393..0bc140d998ad 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -316,7 +316,7 @@ void sock_update_memcg(struct sock *sk) rcu_read_lock(); memcg = mem_cgroup_from_task(current); cg_proto = sk->sk_prot->proto_cgroup(memcg); - if (cg_proto && test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags) && + if (cg_proto && cg_proto->active && css_tryget_online(&memcg->css)) { sk->sk_cgrp = cg_proto; } diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 2379c1b4efb2..d07579ada001 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -48,7 +48,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) percpu_counter_destroy(&cg_proto->sockets_allocated); - if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) + if (cg_proto->active) static_key_slow_dec(&memcg_socket_limit_enabled); } @@ -72,11 +72,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) cg_proto->sysctl_mem[i] = min_t(long, nr_pages, sysctl_tcp_mem[i]); - if (nr_pages == PAGE_COUNTER_MAX) - clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else { + if (!cg_proto->active) { /* - * The active bit needs to be written after the static_key + * The active flag needs to be written after the static_key * update. This is what guarantees that the socket activation * function is the last one to run. See sock_update_memcg() for * details, and note that we don't mark any socket as belonging @@ -90,14 +88,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * We never race with the readers in sock_update_memcg(), * because when this value change, the code to process it is not * patched in yet. - * - * The activated bit is used to guarantee that no two writers - * will do the update in the same memcg. Without that, we can't - * properly shutdown the static key. */ - if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_inc(&memcg_socket_limit_enabled); - set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + static_key_slow_inc(&memcg_socket_limit_enabled); + cg_proto->active = true; } return 0; -- cgit v1.2.3 From d07e22597d1d355829b7b18ac19afa912cf758d1 Mon Sep 17 00:00:00 2001 From: Daniel Cashman Date: Thu, 14 Jan 2016 15:19:53 -0800 Subject: mm: mmap: add new /proc tunable for mmap_base ASLR Address Space Layout Randomization (ASLR) provides a barrier to exploitation of user-space processes in the presence of security vulnerabilities by making it more difficult to find desired code/data which could help an attack. This is done by adding a random offset to the location of regions in the process address space, with a greater range of potential offset values corresponding to better protection/a larger search-space for brute force, but also to greater potential for fragmentation. The offset added to the mmap_base address, which provides the basis for the majority of the mappings for a process, is set once on process exec in arch_pick_mmap_layout() and is done via hard-coded per-arch values, which reflect, hopefully, the best compromise for all systems. The trade-off between increased entropy in the offset value generation and the corresponding increased variability in address space fragmentation is not absolute, however, and some platforms may tolerate higher amounts of entropy. This patch introduces both new Kconfig values and a sysctl interface which may be used to change the amount of entropy used for offset generation on a system. The direct motivation for this change was in response to the libstagefright vulnerabilities that affected Android, specifically to information provided by Google's project zero at: http://googleprojectzero.blogspot.com/2015/09/stagefrightened.html The attack presented therein, by Google's project zero, specifically targeted the limited randomness used to generate the offset added to the mmap_base address in order to craft a brute-force-based attack. Concretely, the attack was against the mediaserver process, which was limited to respawning every 5 seconds, on an arm device. The hard-coded 8 bits used resulted in an average expected success rate of defeating the mmap ASLR after just over 10 minutes (128 tries at 5 seconds a piece). With this patch, and an accompanying increase in the entropy value to 16 bits, the same attack would take an average expected time of over 45 hours (32768 tries), which makes it both less feasible and more likely to be noticed. The introduced Kconfig and sysctl options are limited by per-arch minimum and maximum values, the minimum of which was chosen to match the current hard-coded value and the maximum of which was chosen so as to give the greatest flexibility without generating an invalid mmap_base address, generally a 3-4 bits less than the number of bits in the user-space accessible virtual address space. When decided whether or not to change the default value, a system developer should consider that mmap_base address could be placed anywhere up to 2^(value) bits away from the non-randomized location, which would introduce variable-sized areas above and below the mmap_base address such that the maximum vm_area_struct size may be reduced, preventing very large allocations. This patch (of 4): ASLR only uses as few as 8 bits to generate the random offset for the mmap base address on 32 bit architectures. This value was chosen to prevent a poorly chosen value from dividing the address space in such a way as to prevent large allocations. This may not be an issue on all platforms. Allow the specification of a minimum number of bits so that platforms desiring greater ASLR protection may determine where to place the trade-off. Signed-off-by: Daniel Cashman Cc: Russell King Acked-by: Kees Cook Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Don Zickus Cc: Eric W. Biederman Cc: Heinrich Schuchardt Cc: Josh Poimboeuf Cc: Kirill A. Shutemov Cc: Naoya Horiguchi Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Thomas Gleixner Cc: David Rientjes Cc: Mark Salyzyn Cc: Jeff Vander Stoep Cc: Nick Kralevich Cc: Catalin Marinas Cc: Will Deacon Cc: "H. Peter Anvin" Cc: Hector Marco-Gisbert Cc: Borislav Petkov Cc: Ralf Baechle Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 29 +++++++++++++++++++ arch/Kconfig | 68 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 11 ++++++++ kernel/sysctl.c | 22 +++++++++++++++ mm/mmap.c | 12 ++++++++ 5 files changed, 142 insertions(+) (limited to 'include/linux') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index f72370b440b1..ee763f3d3b52 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -42,6 +42,8 @@ Currently, these files are in /proc/sys/vm: - min_slab_ratio - min_unmapped_ratio - mmap_min_addr +- mmap_rnd_bits +- mmap_rnd_compat_bits - nr_hugepages - nr_overcommit_hugepages - nr_trim_pages (only if CONFIG_MMU=n) @@ -485,6 +487,33 @@ against future potential kernel bugs. ============================================================== +mmap_rnd_bits: + +This value can be used to select the number of bits to use to +determine the random offset to the base address of vma regions +resulting from mmap allocations on architectures which support +tuning address space randomization. This value will be bounded +by the architecture's minimum and maximum supported values. + +This value can be changed after boot using the +/proc/sys/vm/mmap_rnd_bits tunable + +============================================================== + +mmap_rnd_compat_bits: + +This value can be used to select the number of bits to use to +determine the random offset to the base address of vma regions +resulting from mmap allocations for applications run in +compatibility mode on architectures which support tuning address +space randomization. This value will be bounded by the +architecture's minimum and maximum supported values. + +This value can be changed after boot using the +/proc/sys/vm/mmap_rnd_compat_bits tunable + +============================================================== + nr_hugepages Change the minimum size of the hugepage pool. diff --git a/arch/Kconfig b/arch/Kconfig index 4e949e58b192..ba1b626bca00 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -511,6 +511,74 @@ config ARCH_HAS_ELF_RANDOMIZE - arch_mmap_rnd() - arch_randomize_brk() +config HAVE_ARCH_MMAP_RND_BITS + bool + help + An arch should select this symbol if it supports setting a variable + number of bits for use in establishing the base address for mmap + allocations, has MMU enabled and provides values for both: + - ARCH_MMAP_RND_BITS_MIN + - ARCH_MMAP_RND_BITS_MAX + +config ARCH_MMAP_RND_BITS_MIN + int + +config ARCH_MMAP_RND_BITS_MAX + int + +config ARCH_MMAP_RND_BITS_DEFAULT + int + +config ARCH_MMAP_RND_BITS + int "Number of bits to use for ASLR of mmap base address" if EXPERT + range ARCH_MMAP_RND_BITS_MIN ARCH_MMAP_RND_BITS_MAX + default ARCH_MMAP_RND_BITS_DEFAULT if ARCH_MMAP_RND_BITS_DEFAULT + default ARCH_MMAP_RND_BITS_MIN + depends on HAVE_ARCH_MMAP_RND_BITS + help + This value can be used to select the number of bits to use to + determine the random offset to the base address of vma regions + resulting from mmap allocations. This value will be bounded + by the architecture's minimum and maximum supported values. + + This value can be changed after boot using the + /proc/sys/vm/mmap_rnd_bits tunable + +config HAVE_ARCH_MMAP_RND_COMPAT_BITS + bool + help + An arch should select this symbol if it supports running applications + in compatibility mode, supports setting a variable number of bits for + use in establishing the base address for mmap allocations, has MMU + enabled and provides values for both: + - ARCH_MMAP_RND_COMPAT_BITS_MIN + - ARCH_MMAP_RND_COMPAT_BITS_MAX + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + int + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + int + +config ARCH_MMAP_RND_COMPAT_BITS_DEFAULT + int + +config ARCH_MMAP_RND_COMPAT_BITS + int "Number of bits to use for ASLR of mmap base address for compatible applications" if EXPERT + range ARCH_MMAP_RND_COMPAT_BITS_MIN ARCH_MMAP_RND_COMPAT_BITS_MAX + default ARCH_MMAP_RND_COMPAT_BITS_DEFAULT if ARCH_MMAP_RND_COMPAT_BITS_DEFAULT + default ARCH_MMAP_RND_COMPAT_BITS_MIN + depends on HAVE_ARCH_MMAP_RND_COMPAT_BITS + help + This value can be used to select the number of bits to use to + determine the random offset to the base address of vma regions + resulting from mmap allocations for compatible applications This + value will be bounded by the architecture's minimum and maximum + supported values. + + This value can be changed after boot using the + /proc/sys/vm/mmap_rnd_compat_bits tunable + config HAVE_COPY_THREAD_TLS bool help diff --git a/include/linux/mm.h b/include/linux/mm.h index a8ab1fc0e9bc..d396753c0577 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -51,6 +51,17 @@ extern int sysctl_legacy_va_layout; #define sysctl_legacy_va_layout 0 #endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +extern const int mmap_rnd_bits_min; +extern const int mmap_rnd_bits_max; +extern int mmap_rnd_bits __read_mostly; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +extern const int mmap_rnd_compat_bits_min; +extern const int mmap_rnd_compat_bits_max; +extern int mmap_rnd_compat_bits __read_mostly; +#endif + #include #include #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5faf89ac9ec0..c810f8afdb7f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1568,6 +1568,28 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS + { + .procname = "mmap_rnd_bits", + .data = &mmap_rnd_bits, + .maxlen = sizeof(mmap_rnd_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_bits_min, + .extra2 = (void *)&mmap_rnd_bits_max, + }, +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS + { + .procname = "mmap_rnd_compat_bits", + .data = &mmap_rnd_compat_bits, + .maxlen = sizeof(mmap_rnd_compat_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_compat_bits_min, + .extra2 = (void *)&mmap_rnd_compat_bits_max, + }, +#endif { } }; diff --git a/mm/mmap.c b/mm/mmap.c index c311bfd8005b..f32b84ad621a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -58,6 +58,18 @@ #define arch_rebalance_pgtables(addr, len) (addr) #endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS +const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; +const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; +int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS +const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; +const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; +int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; +#endif + + static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); -- cgit v1.2.3 From c20cd45eb01748f0fba77a504f956b000df4ea73 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 14 Jan 2016 15:20:12 -0800 Subject: mm: allow GFP_{FS,IO} for page_cache_read page cache allocation page_cache_read has been historically using page_cache_alloc_cold to allocate a new page. This means that mapping_gfp_mask is used as the base for the gfp_mask. Many filesystems are setting this mask to GFP_NOFS to prevent from fs recursion issues. page_cache_read is called from the vm_operations_struct::fault() context during the page fault. This context doesn't need the reclaim protection normally. ceph and ocfs2 which call filemap_fault from their fault handlers seem to be OK because they are not taking any fs lock before invoking generic implementation. xfs which takes XFS_MMAPLOCK_SHARED is safe from the reclaim recursion POV because this lock serializes truncate and punch hole with the page faults and it doesn't get involved in the reclaim. There is simply no reason to deliberately use a weaker allocation context when a __GFP_FS | __GFP_IO can be used. The GFP_NOFS protection might be even harmful. There is a push to fail GFP_NOFS allocations rather than loop within allocator indefinitely with a very limited reclaim ability. Once we start failing those requests the OOM killer might be triggered prematurely because the page cache allocation failure is propagated up the page fault path and end up in pagefault_out_of_memory. We cannot play with mapping_gfp_mask directly because that would be racy wrt. parallel page faults and it might interfere with other users who really rely on NOFS semantic from the stored gfp_mask. The mask is also inode proper so it would even be a layering violation. What we can do instead is to push the gfp_mask into struct vm_fault and allow fs layer to overwrite it should the callback need to be called with a different allocation context. Initialize the default to (mapping_gfp_mask | __GFP_FS | __GFP_IO) because this should be safe from the page fault path normally. Why do we care about mapping_gfp_mask at all then? Because this doesn't hold only reclaim protection flags but it also might contain zone and movability restrictions (GFP_DMA32, __GFP_MOVABLE and others) so we have to respect those. Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Acked-by: Jan Kara Acked-by: Vlastimil Babka Cc: Tetsuo Handa Cc: Mel Gorman Cc: Dave Chinner Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ mm/filemap.c | 9 ++++----- mm/memory.c | 17 +++++++++++++++++ 3 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d396753c0577..ec9d4559514d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -236,10 +236,14 @@ extern pgprot_t protection_map[16]; * ->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. * + * MM layer fills up gfp_mask for page allocations but fault handler might + * alter it if its implementation requires a different allocation context. + * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ + gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ void __user *virtual_address; /* Faulting virtual address */ diff --git a/mm/filemap.c b/mm/filemap.c index 1bb007624b53..ff42d31c891a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1812,19 +1812,18 @@ EXPORT_SYMBOL(generic_file_read_iter); * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */ -static int page_cache_read(struct file *file, pgoff_t offset) +static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) { struct address_space *mapping = file->f_mapping; struct page *page; int ret; do { - page = page_cache_alloc_cold(mapping); + page = __page_cache_alloc(gfp_mask|__GFP_COLD); if (!page) return -ENOMEM; - ret = add_to_page_cache_lru(page, mapping, offset, - mapping_gfp_constraint(mapping, GFP_KERNEL)); + ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask & GFP_KERNEL); if (ret == 0) ret = mapping->a_ops->readpage(file, page); else if (ret == -EEXIST) @@ -2005,7 +2004,7 @@ no_cached_page: * We're only likely to ever get here if MADV_RANDOM is in * effect. */ - error = page_cache_read(file, offset); + error = page_cache_read(file, offset, vmf->gfp_mask); /* * The page we want has now been added to the page cache. diff --git a/mm/memory.c b/mm/memory.c index f7026c035940..d4e4d37c1989 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1938,6 +1938,20 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo copy_user_highpage(dst, src, va, vma); } +static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) +{ + struct file *vm_file = vma->vm_file; + + if (vm_file) + return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; + + /* + * Special mappings (e.g. VDSO) do not have any file so fake + * a default GFP_KERNEL for them. + */ + return GFP_KERNEL; +} + /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. @@ -1953,6 +1967,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, vmf.virtual_address = (void __user *)(address & PAGE_MASK); vmf.pgoff = page->index; vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vmf.page = page; vmf.cow_page = NULL; @@ -2757,6 +2772,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, vmf.pgoff = pgoff; vmf.flags = flags; vmf.page = NULL; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vmf.cow_page = cow_page; ret = vma->vm_ops->fault(vma, &vmf); @@ -2923,6 +2939,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address, vmf.pgoff = pgoff; vmf.max_pgoff = max_pgoff; vmf.flags = flags; + vmf.gfp_mask = __get_fault_gfp_mask(vma); vma->vm_ops->map_pages(vma, &vmf); } -- cgit v1.2.3 From a8d0143730d7b42c9fe6d1435d92ecce6863a62a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:20:15 -0800 Subject: mm: page_alloc: generalize the dirty balance reserve The dirty balance reserve that dirty throttling has to consider is merely memory not available to userspace allocations. There is nothing writeback-specific about it. Generalize the name so that it's reusable outside of that context. Signed-off-by: Johannes Weiner Cc: Rik van Riel Cc: Mel Gorman Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++--- include/linux/swap.h | 1 - mm/page-writeback.c | 14 ++++++++++++-- mm/page_alloc.c | 21 +++------------------ 4 files changed, 18 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3b6fb71bbeb3..33bb1b19273e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -356,10 +356,10 @@ struct zone { struct per_cpu_pageset __percpu *pageset; /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. + * This is a per-zone reserve of pages that are not available + * to userspace allocations. */ - unsigned long dirty_balance_reserve; + unsigned long totalreserve_pages; #ifndef CONFIG_SPARSEMEM /* diff --git a/include/linux/swap.h b/include/linux/swap.h index 7ba7dccaf0e7..066bd21765ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -287,7 +287,6 @@ static inline void workingset_node_shadows_dec(struct radix_tree_node *node) /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; -extern unsigned long dirty_balance_reserve; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d15d88c8efa1..6fe7d15bd1f7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -278,7 +278,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone) unsigned long nr_pages; nr_pages = zone_page_state(zone, NR_FREE_PAGES); - nr_pages -= min(nr_pages, zone->dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + nr_pages -= min(nr_pages, zone->totalreserve_pages); nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); @@ -332,7 +337,12 @@ static unsigned long global_dirtyable_memory(void) unsigned long x; x = global_page_state(NR_FREE_PAGES); - x -= min(x, dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + x -= min(x, totalreserve_pages); x += global_page_state(NR_INACTIVE_FILE); x += global_page_state(NR_ACTIVE_FILE); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2a6fe377cafc..1e9a56065400 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -114,13 +114,6 @@ static DEFINE_SPINLOCK(managed_page_count_lock); unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -/* - * When calculating the number of globally allowed dirty pages, there - * is a certain number of per-zone reserves that should not be - * considered dirtyable memory. This is the sum of those reserves - * over all existing zones that contribute dirtyable memory. - */ -unsigned long dirty_balance_reserve __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; @@ -5942,20 +5935,12 @@ static void calculate_totalreserve_pages(void) if (max > zone->managed_pages) max = zone->managed_pages; + + zone->totalreserve_pages = max; + reserve_pages += max; - /* - * Lowmem reserves are not available to - * GFP_HIGHUSER page cache allocations and - * kswapd tries to balance zones to their high - * watermark. As a result, neither should be - * regarded as dirtyable memory, to prevent a - * situation where reclaim has to clean pages - * in order to balance the zones. - */ - zone->dirty_balance_reserve = max; } } - dirty_balance_reserve = reserve_pages; totalreserve_pages = reserve_pages; } -- cgit v1.2.3 From 8c9c1701c7c23a57ebfd1a0b27b87053ae43cfb5 Mon Sep 17 00:00:00 2001 From: Alexander Kuleshov Date: Thu, 14 Jan 2016 15:20:42 -0800 Subject: mm/memblock: introduce for_each_memblock_type() We already have the for_each_memblock() macro in which provides ability to iterate over memblock regions of a known type. The for_each_memblock() macro allows us to pass the pointer to the struct memblock_type, instead we need to pass name of the type. This patch introduces a new macro for_each_memblock_type() which allows us iterate over memblock regions with the given type when the type is unknown. Signed-off-by: Alexander Kuleshov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 5 +++++ mm/memblock.c | 32 ++++++++++++++++---------------- 2 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 3a092fba2eb2..c0c4208a286f 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -399,6 +399,11 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \ region++) +#define for_each_memblock_type(memblock_type, rgn) \ + idx = 0; \ + rgn = &memblock_type->regions[idx]; \ + for (idx = 0; idx < memblock_type->cnt; \ + idx++,rgn = &memblock_type->regions[idx]) #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit diff --git a/mm/memblock.c b/mm/memblock.c index c33a2a2ae69f..d2ed81e59a94 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -525,7 +525,8 @@ int __init_memblock memblock_add_range(struct memblock_type *type, bool insert = false; phys_addr_t obase = base; phys_addr_t end = base + memblock_cap_size(base, &size); - int i, nr_new; + int idx, nr_new; + struct memblock_region *rgn; if (!size) return 0; @@ -549,8 +550,7 @@ repeat: base = obase; nr_new = 0; - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; @@ -569,7 +569,7 @@ repeat: WARN_ON(flags != rgn->flags); nr_new++; if (insert) - memblock_insert_region(type, i++, base, + memblock_insert_region(type, idx++, base, rbase - base, nid, flags); } @@ -581,7 +581,7 @@ repeat: if (base < end) { nr_new++; if (insert) - memblock_insert_region(type, i, base, end - base, + memblock_insert_region(type, idx, base, end - base, nid, flags); } @@ -648,7 +648,8 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, int *start_rgn, int *end_rgn) { phys_addr_t end = base + memblock_cap_size(base, &size); - int i; + int idx; + struct memblock_region *rgn; *start_rgn = *end_rgn = 0; @@ -660,8 +661,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, if (memblock_double_array(type, base, size) < 0) return -ENOMEM; - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { phys_addr_t rbase = rgn->base; phys_addr_t rend = rbase + rgn->size; @@ -678,7 +678,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->base = base; rgn->size -= base - rbase; type->total_size -= base - rbase; - memblock_insert_region(type, i, rbase, base - rbase, + memblock_insert_region(type, idx, rbase, base - rbase, memblock_get_region_node(rgn), rgn->flags); } else if (rend > end) { @@ -689,14 +689,14 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type, rgn->base = end; rgn->size -= end - rbase; type->total_size -= end - rbase; - memblock_insert_region(type, i--, rbase, end - rbase, + memblock_insert_region(type, idx--, rbase, end - rbase, memblock_get_region_node(rgn), rgn->flags); } else { /* @rgn is fully contained, record it */ if (!*end_rgn) - *start_rgn = i; - *end_rgn = i + 1; + *start_rgn = idx; + *end_rgn = idx + 1; } } @@ -1638,12 +1638,12 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name { unsigned long long base, size; unsigned long flags; - int i; + int idx; + struct memblock_region *rgn; pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; + for_each_memblock_type(type, rgn) { char nid_buf[32] = ""; base = rgn->base; @@ -1655,7 +1655,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type, char *name memblock_get_region_node(rgn)); #endif pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n", - name, i, base, base + size - 1, size, nid_buf, flags); + name, idx, base, base + size - 1, size, nid_buf, flags); } } -- cgit v1.2.3 From 7d828602e5ef3297a69392a2d31264e4ab9c8bb7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:20:56 -0800 Subject: mm: memcontrol: export root_mem_cgroup A later patch will need this symbol in files other than memcontrol.c, so export it now and replace mem_cgroup_root_css at the same time. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 ++- mm/backing-dev.c | 2 +- mm/memcontrol.c | 5 ++--- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 78a1ec2e23fc..d0c724f53691 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -265,7 +265,8 @@ struct mem_cgroup { struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; -extern struct cgroup_subsys_state *mem_cgroup_root_css; + +extern struct mem_cgroup *root_mem_cgroup; /** * mem_cgroup_events - count memory events against a cgroup diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7340353f8aea..cc5d29d2da9b 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -672,7 +672,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { - bdi->wb.memcg_css = mem_cgroup_root_css; + bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0bc140d998ad..44ed2dee8f0c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -76,9 +76,9 @@ struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); +struct mem_cgroup *root_mem_cgroup __read_mostly; + #define MEM_CGROUP_RECLAIM_RETRIES 5 -static struct mem_cgroup *root_mem_cgroup __read_mostly; -struct cgroup_subsys_state *mem_cgroup_root_css __read_mostly; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP @@ -4241,7 +4241,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) /* root ? */ if (parent_css == NULL) { root_mem_cgroup = memcg; - mem_cgroup_root_css = &memcg->css; page_counter_init(&memcg->memory, NULL); memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; -- cgit v1.2.3 From 3d596f7b907b0281b997cf30c92994a71ad0a1a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:05 -0800 Subject: net: tcp_memcontrol: protect all tcp_memcontrol calls by jump-label Move the jump-label from sock_update_memcg() and sock_release_memcg() to the callsite, and so eliminate those function calls when socket accounting is not enabled. This also eliminates the need for dummy functions because the calls will be optimized away if the Kconfig options are not enabled. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 9 -------- mm/memcontrol.c | 56 +++++++++++++++++++++------------------------- net/core/sock.c | 9 ++------ net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_ipv4.c | 4 +++- 5 files changed, 32 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d0c724f53691..85c437b0cbc0 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -694,17 +694,8 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; -#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); -#else -static inline void sock_update_memcg(struct sock *sk) -{ -} -static inline void sock_release_memcg(struct sock *sk) -{ -} -#endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */ #ifdef CONFIG_MEMCG_KMEM extern struct static_key memcg_kmem_enabled_key; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 44ed2dee8f0c..d9344dad207e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -293,46 +293,40 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) void sock_update_memcg(struct sock *sk) { - if (mem_cgroup_sockets_enabled) { - struct mem_cgroup *memcg; - struct cg_proto *cg_proto; + struct mem_cgroup *memcg; + struct cg_proto *cg_proto; - BUG_ON(!sk->sk_prot->proto_cgroup); + BUG_ON(!sk->sk_prot->proto_cgroup); - /* Socket cloning can throw us here with sk_cgrp already - * filled. It won't however, necessarily happen from - * process context. So the test for root memcg given - * the current task's memcg won't help us in this case. - * - * Respecting the original socket's memcg is a better - * decision in this case. - */ - if (sk->sk_cgrp) { - BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); - css_get(&sk->sk_cgrp->memcg->css); - return; - } + /* Socket cloning can throw us here with sk_cgrp already + * filled. It won't however, necessarily happen from + * process context. So the test for root memcg given + * the current task's memcg won't help us in this case. + * + * Respecting the original socket's memcg is a better + * decision in this case. + */ + if (sk->sk_cgrp) { + BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); + css_get(&sk->sk_cgrp->memcg->css); + return; + } - rcu_read_lock(); - memcg = mem_cgroup_from_task(current); - cg_proto = sk->sk_prot->proto_cgroup(memcg); - if (cg_proto && cg_proto->active && - css_tryget_online(&memcg->css)) { - sk->sk_cgrp = cg_proto; - } - rcu_read_unlock(); + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + cg_proto = sk->sk_prot->proto_cgroup(memcg); + if (cg_proto && cg_proto->active && + css_tryget_online(&memcg->css)) { + sk->sk_cgrp = cg_proto; } + rcu_read_unlock(); } EXPORT_SYMBOL(sock_update_memcg); void sock_release_memcg(struct sock *sk) { - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct mem_cgroup *memcg; - WARN_ON(!sk->sk_cgrp->memcg); - memcg = sk->sk_cgrp->memcg; - css_put(&sk->sk_cgrp->memcg->css); - } + WARN_ON(!sk->sk_cgrp->memcg); + css_put(&sk->sk_cgrp->memcg->css); } struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) diff --git a/net/core/sock.c b/net/core/sock.c index 51270238e269..6c5dab01105b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1507,12 +1507,6 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); -static void sk_update_clone(const struct sock *sk, struct sock *newsk) -{ - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - sock_update_memcg(newsk); -} - /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1607,7 +1601,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; - sk_update_clone(sk, newsk); + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_update_memcg(newsk); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7bb1b091efd1..fd17eec93525 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -422,7 +422,8 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - sock_update_memcg(sk); + if (mem_cgroup_sockets_enabled) + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 65947c1f4733..eb39e02899e5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1818,7 +1818,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); - sock_release_memcg(sk); + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); -- cgit v1.2.3 From af95d7df4059cfeab7e7c244f3564214aada7dad Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:08 -0800 Subject: net: tcp_memcontrol: remove dead per-memcg count of allocated sockets The number of allocated sockets is used for calculations in the soft limit phase, where packets are accepted but the socket is under memory pressure. Since there is no soft limit phase in tcp_memcontrol, and memory pressure is only entered when packets are already dropped, this is actually dead code. Remove it. As this is the last user of parent_cg_proto(), remove that too. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - include/net/sock.h | 39 +++------------------------------------ net/ipv4/tcp_memcontrol.c | 3 --- 3 files changed, 3 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 85c437b0cbc0..15acc04ebdd3 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -87,7 +87,6 @@ enum mem_cgroup_events_target { struct cg_proto { struct page_counter memory_allocated; /* Current allocated memory. */ - struct percpu_counter sockets_allocated; /* Current number of sockets. */ int memory_pressure; bool active; long sysctl_mem[3]; diff --git a/include/net/sock.h b/include/net/sock.h index d3b035c7362b..1f15937ec208 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1098,19 +1098,9 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) extern struct static_key memcg_socket_limit_enabled; -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg)); -} #define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) #else #define mem_cgroup_sockets_enabled 0 -static inline struct cg_proto *parent_cg_proto(struct proto *proto, - struct cg_proto *cg_proto) -{ - return NULL; -} #endif static inline bool sk_stream_memory_free(const struct sock *sk) @@ -1236,41 +1226,18 @@ sk_memory_allocated_sub(struct sock *sk, int amt) static inline void sk_sockets_allocated_dec(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_dec(&cg_proto->sockets_allocated); - } - - percpu_counter_dec(prot->sockets_allocated); + percpu_counter_dec(sk->sk_prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - struct cg_proto *cg_proto = sk->sk_cgrp; - - for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - percpu_counter_inc(&cg_proto->sockets_allocated); - } - - percpu_counter_inc(prot->sockets_allocated); + percpu_counter_inc(sk->sk_prot->sockets_allocated); } static inline int sk_sockets_allocated_read_positive(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return percpu_counter_read_positive(&sk->sk_cgrp->sockets_allocated); - - return percpu_counter_read_positive(prot->sockets_allocated); + return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index d07579ada001..6759e0d6bba1 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -32,7 +32,6 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) counter_parent = &parent_cg->memory_allocated; page_counter_init(&cg_proto->memory_allocated, counter_parent); - percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL); return 0; } @@ -46,8 +45,6 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) if (!cg_proto) return; - percpu_counter_destroy(&cg_proto->sockets_allocated); - if (cg_proto->active) static_key_slow_dec(&memcg_socket_limit_enabled); -- cgit v1.2.3 From 80f23124f57c77915a7b4201d8dcba38a38b23f0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:11 -0800 Subject: net: tcp_memcontrol: simplify the per-memcg limit access tcp_memcontrol replicates the global sysctl_mem limit array per cgroup, but it only ever sets these entries to the value of the memory_allocated page_counter limit. Use the latter directly. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 1 - include/net/sock.h | 8 +++++--- net/ipv4/tcp_memcontrol.c | 8 -------- 3 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 15acc04ebdd3..6c91c1b73951 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -89,7 +89,6 @@ struct cg_proto { struct page_counter memory_allocated; /* Current allocated memory. */ int memory_pressure; bool active; - long sysctl_mem[3]; /* * memcg field is used to find which memcg we belong directly * Each memcg struct can hold more than one cg_proto, so container_of diff --git a/include/net/sock.h b/include/net/sock.h index 1f15937ec208..8b1f8e5d3a48 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1162,10 +1162,12 @@ static inline void sk_enter_memory_pressure(struct sock *sk) static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long *prot = sk->sk_prot->sysctl_mem; + long limit = sk->sk_prot->sysctl_mem[index]; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - prot = sk->sk_cgrp->sysctl_mem; - return prot[index]; + limit = min_t(long, limit, sk->sk_cgrp->memory_allocated.limit); + + return limit; } static inline void memcg_memory_allocated_add(struct cg_proto *prot, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 6759e0d6bba1..ef4268d12e43 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -21,9 +21,6 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) if (!cg_proto) return 0; - cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0]; - cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1]; - cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2]; cg_proto->memory_pressure = 0; cg_proto->memcg = memcg; @@ -54,7 +51,6 @@ EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) { struct cg_proto *cg_proto; - int i; int ret; cg_proto = tcp_prot.proto_cgroup(memcg); @@ -65,10 +61,6 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) if (ret) return ret; - for (i = 0; i < 3; i++) - cg_proto->sysctl_mem[i] = min_t(long, nr_pages, - sysctl_tcp_mem[i]); - if (!cg_proto->active) { /* * The active flag needs to be written after the static_key -- cgit v1.2.3 From e805605c721021879a1469bdae45c6f80bc985f4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:14 -0800 Subject: net: tcp_memcontrol: sanitize tcp memory accounting callbacks There won't be a tcp control soft limit, so integrating the memcg code into the global skmem limiting scheme complicates things unnecessarily. Replace this with simple and clear charge and uncharge calls--hidden behind a jump label--to account skb memory. Note that this is not purely aesthetic: as a result of shoehorning the per-memcg code into the same memory accounting functions that handle the global level, the old code would compare the per-memcg consumption against the smaller of the per-memcg limit and the global limit. This allowed the total consumption of multiple sockets to exceed the global limit, as long as the individual sockets stayed within bounds. After this change, the code will always compare the per-memcg consumption to the per-memcg limit, and the global consumption to the global limit, and thus close this loophole. Without a soft limit, the per-memcg memory pressure state in sockets is generally questionable. However, we did it until now, so we continue to enter it when the hard limit is hit, and packets are dropped, to let other sockets in the cgroup know that they shouldn't grow their transmit windows, either. However, keep it simple in the new callback model and leave memory pressure lazily when the next packet is accepted (as opposed to doing it synchroneously when packets are processed). When packets are dropped, network performance will already be in the toilet, so that should be a reasonable trade-off. As described above, consumption is now checked on the per-memcg level and the global level separately. Likewise, memory pressure states are maintained on both the per-memcg level and the global level, and a socket is considered under pressure when either level asserts as much. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 +++++++++----- include/net/sock.h | 64 ++++++---------------------------------------- include/net/tcp.h | 5 ++-- mm/memcontrol.c | 32 +++++++++++++++++++++++ net/core/sock.c | 26 +++++++++++-------- net/ipv4/tcp_output.c | 7 +++-- 6 files changed, 77 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6c91c1b73951..e4e77bd1dd39 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -660,12 +660,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) } #endif /* CONFIG_MEMCG */ -enum { - UNDER_LIMIT, - SOFT_LIMIT, - OVER_LIMIT, -}; - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg); @@ -694,6 +688,19 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, struct sock; void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); +bool mem_cgroup_charge_skmem(struct cg_proto *proto, unsigned int nr_pages); +void mem_cgroup_uncharge_skmem(struct cg_proto *proto, unsigned int nr_pages); +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) +static inline bool mem_cgroup_under_socket_pressure(struct cg_proto *proto) +{ + return proto->memory_pressure; +} +#else +static inline bool mem_cgroup_under_pressure(struct cg_proto *proto) +{ + return false; +} +#endif #ifdef CONFIG_MEMCG_KMEM extern struct static_key memcg_kmem_enabled_key; diff --git a/include/net/sock.h b/include/net/sock.h index 8b1f8e5d3a48..94a6c1a740b9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1129,8 +1129,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) if (!sk->sk_prot->memory_pressure) return false; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp && + mem_cgroup_under_socket_pressure(sk->sk_cgrp)) + return true; return !!*sk->sk_prot->memory_pressure; } @@ -1144,9 +1145,6 @@ static inline void sk_leave_memory_pressure(struct sock *sk) if (*memory_pressure) *memory_pressure = 0; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - sk->sk_cgrp->memory_pressure = 0; } static inline void sk_enter_memory_pressure(struct sock *sk) @@ -1154,76 +1152,30 @@ static inline void sk_enter_memory_pressure(struct sock *sk) if (!sk->sk_prot->enter_memory_pressure) return; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - sk->sk_cgrp->memory_pressure = 1; - sk->sk_prot->enter_memory_pressure(sk); } static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long limit = sk->sk_prot->sysctl_mem[index]; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - limit = min_t(long, limit, sk->sk_cgrp->memory_allocated.limit); - - return limit; -} - -static inline void memcg_memory_allocated_add(struct cg_proto *prot, - unsigned long amt, - int *parent_status) -{ - struct page_counter *counter; - - if (page_counter_try_charge(&prot->memory_allocated, amt, &counter)) - return; - - page_counter_charge(&prot->memory_allocated, amt); - *parent_status = OVER_LIMIT; -} - -static inline void memcg_memory_allocated_sub(struct cg_proto *prot, - unsigned long amt) -{ - page_counter_uncharge(&prot->memory_allocated, amt); + return sk->sk_prot->sysctl_mem[index]; } static inline long sk_memory_allocated(const struct sock *sk) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return page_counter_read(&sk->sk_cgrp->memory_allocated); - - return atomic_long_read(prot->memory_allocated); + return atomic_long_read(sk->sk_prot->memory_allocated); } static inline long -sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) +sk_memory_allocated_add(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) { - memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status); - /* update the root cgroup regardless */ - atomic_long_add_return(amt, prot->memory_allocated); - return page_counter_read(&sk->sk_cgrp->memory_allocated); - } - - return atomic_long_add_return(amt, prot->memory_allocated); + return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - struct proto *prot = sk->sk_prot; - - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - memcg_memory_allocated_sub(sk->sk_cgrp, amt); - - atomic_long_sub(amt, prot->memory_allocated); + atomic_long_sub(amt, sk->sk_prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index a80255f4ca33..d9df80deba31 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -289,8 +289,9 @@ extern int tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - return !!sk->sk_cgrp->memory_pressure; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp && + mem_cgroup_under_socket_pressure(sk->sk_cgrp)) + return true; return tcp_memory_pressure; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d9344dad207e..f5de783860b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -338,6 +338,38 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(tcp_proto_cgroup); +/** + * mem_cgroup_charge_skmem - charge socket memory + * @proto: proto to charge + * @nr_pages: number of pages to charge + * + * Charges @nr_pages to @proto. Returns %true if the charge fit within + * @proto's configured limit, %false if the charge had to be forced. + */ +bool mem_cgroup_charge_skmem(struct cg_proto *proto, unsigned int nr_pages) +{ + struct page_counter *counter; + + if (page_counter_try_charge(&proto->memory_allocated, + nr_pages, &counter)) { + proto->memory_pressure = 0; + return true; + } + page_counter_charge(&proto->memory_allocated, nr_pages); + proto->memory_pressure = 1; + return false; +} + +/** + * mem_cgroup_uncharge_skmem - uncharge socket memory + * @proto - proto to uncharge + * @nr_pages - number of pages to uncharge + */ +void mem_cgroup_uncharge_skmem(struct cg_proto *proto, unsigned int nr_pages) +{ + page_counter_uncharge(&proto->memory_allocated, nr_pages); +} + #endif #ifdef CONFIG_MEMCG_KMEM diff --git a/net/core/sock.c b/net/core/sock.c index 6c5dab01105b..89ae859d2dc5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2084,27 +2084,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); long allocated; - int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = sk_memory_allocated_add(sk, amt, &parent_status); + allocated = sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp && + !mem_cgroup_charge_skmem(sk->sk_cgrp, amt)) + goto suppress_allocation; /* Under limit. */ - if (parent_status == UNDER_LIMIT && - allocated <= sk_prot_mem_limits(sk, 0)) { + if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. (we or our parents) */ - if ((parent_status > SOFT_LIMIT) || - allocated > sk_prot_mem_limits(sk, 1)) + /* Under pressure. */ + if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); - /* Over hard limit (we or our parents) */ - if ((parent_status == OVER_LIMIT) || - (allocated > sk_prot_mem_limits(sk, 2))) + /* Over hard limit. */ + if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ @@ -2153,6 +2153,9 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + mem_cgroup_uncharge_skmem(sk->sk_cgrp, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -2168,6 +2171,9 @@ void __sk_mem_reclaim(struct sock *sk, int amount) sk_memory_allocated_sub(sk, amount); sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + mem_cgroup_uncharge_skmem(sk->sk_cgrp, amount); + if (sk_under_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 412a920fe0ec..493b48945f0c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2813,13 +2813,16 @@ begin_fwd: */ void sk_forced_mem_schedule(struct sock *sk, int size) { - int amt, status; + int amt; if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - sk_memory_allocated_add(sk, amt, &status); + sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + mem_cgroup_charge_skmem(sk->sk_cgrp, amt); } /* Send a FIN. The caller locks the socket for us. -- cgit v1.2.3 From baac50bbc3cdfd184ebf586b1704edbfcee866df Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:17 -0800 Subject: net: tcp_memcontrol: simplify linkage between socket and page counter There won't be any separate counters for socket memory consumed by protocols other than TCP in the future. Remove the indirection and link sockets directly to their owning memory cgroup. Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 20 ++++--------- include/net/sock.h | 25 +++-------------- include/net/tcp.h | 4 +-- include/net/tcp_memcontrol.h | 1 - mm/memcontrol.c | 57 +++++++++++++++---------------------- net/core/sock.c | 52 +++++----------------------------- net/ipv4/tcp_ipv4.c | 7 +---- net/ipv4/tcp_memcontrol.c | 67 +++++++++++++++++--------------------------- net/ipv4/tcp_output.c | 4 +-- net/ipv6/tcp_ipv6.c | 3 -- 10 files changed, 69 insertions(+), 171 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e4e77bd1dd39..7c085e4636ba 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -89,16 +89,6 @@ struct cg_proto { struct page_counter memory_allocated; /* Current allocated memory. */ int memory_pressure; bool active; - /* - * memcg field is used to find which memcg we belong directly - * Each memcg struct can hold more than one cg_proto, so container_of - * won't really cut. - * - * The elegant solution would be having an inverse function to - * proto_cgroup in struct proto, but that means polluting the structure - * for everybody, instead of just for memcg users. - */ - struct mem_cgroup *memcg; }; #ifdef CONFIG_MEMCG @@ -688,15 +678,15 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, struct sock; void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); -bool mem_cgroup_charge_skmem(struct cg_proto *proto, unsigned int nr_pages); -void mem_cgroup_uncharge_skmem(struct cg_proto *proto, unsigned int nr_pages); +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); +void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) -static inline bool mem_cgroup_under_socket_pressure(struct cg_proto *proto) +static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { - return proto->memory_pressure; + return memcg->tcp_mem.memory_pressure; } #else -static inline bool mem_cgroup_under_pressure(struct cg_proto *proto) +static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } diff --git a/include/net/sock.h b/include/net/sock.h index 94a6c1a740b9..be96a8dcbc74 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -71,22 +71,6 @@ #include #include -struct cgroup; -struct cgroup_subsys; -#ifdef CONFIG_NET -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss); -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg); -#else -static inline -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - return 0; -} -static inline -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ -} -#endif /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of @@ -245,7 +229,6 @@ struct sock_common { /* public: */ }; -struct cg_proto; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock @@ -310,7 +293,7 @@ struct cg_proto; * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup - * @sk_cgrp: this socket's cgroup-specific proto data + * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed @@ -446,7 +429,7 @@ struct sock { void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; - struct cg_proto *sk_cgrp; + struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); @@ -1129,8 +1112,8 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) if (!sk->sk_prot->memory_pressure) return false; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp && - mem_cgroup_under_socket_pressure(sk->sk_cgrp)) + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return !!*sk->sk_prot->memory_pressure; diff --git a/include/net/tcp.h b/include/net/tcp.h index d9df80deba31..8ea19977ea53 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -289,8 +289,8 @@ extern int tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) { - if (mem_cgroup_sockets_enabled && sk->sk_cgrp && - mem_cgroup_under_socket_pressure(sk->sk_cgrp)) + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return tcp_memory_pressure; diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h index 05b94d9453de..3a17b16ae8aa 100644 --- a/include/net/tcp_memcontrol.h +++ b/include/net/tcp_memcontrol.h @@ -1,7 +1,6 @@ #ifndef _TCP_MEMCG_H #define _TCP_MEMCG_H -struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg); int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss); void tcp_destroy_cgroup(struct mem_cgroup *memcg); #endif /* _TCP_MEMCG_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f5de783860b8..eaaa86126277 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -294,9 +294,6 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) void sock_update_memcg(struct sock *sk) { struct mem_cgroup *memcg; - struct cg_proto *cg_proto; - - BUG_ON(!sk->sk_prot->proto_cgroup); /* Socket cloning can throw us here with sk_cgrp already * filled. It won't however, necessarily happen from @@ -306,68 +303,58 @@ void sock_update_memcg(struct sock *sk) * Respecting the original socket's memcg is a better * decision in this case. */ - if (sk->sk_cgrp) { - BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg)); - css_get(&sk->sk_cgrp->memcg->css); + if (sk->sk_memcg) { + BUG_ON(mem_cgroup_is_root(sk->sk_memcg)); + css_get(&sk->sk_memcg->css); return; } rcu_read_lock(); memcg = mem_cgroup_from_task(current); - cg_proto = sk->sk_prot->proto_cgroup(memcg); - if (cg_proto && cg_proto->active && - css_tryget_online(&memcg->css)) { - sk->sk_cgrp = cg_proto; - } + if (memcg != root_mem_cgroup && + memcg->tcp_mem.active && + css_tryget_online(&memcg->css)) + sk->sk_memcg = memcg; rcu_read_unlock(); } EXPORT_SYMBOL(sock_update_memcg); void sock_release_memcg(struct sock *sk) { - WARN_ON(!sk->sk_cgrp->memcg); - css_put(&sk->sk_cgrp->memcg->css); -} - -struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) -{ - if (!memcg || mem_cgroup_is_root(memcg)) - return NULL; - - return &memcg->tcp_mem; + WARN_ON(!sk->sk_memcg); + css_put(&sk->sk_memcg->css); } -EXPORT_SYMBOL(tcp_proto_cgroup); /** * mem_cgroup_charge_skmem - charge socket memory - * @proto: proto to charge + * @memcg: memcg to charge * @nr_pages: number of pages to charge * - * Charges @nr_pages to @proto. Returns %true if the charge fit within - * @proto's configured limit, %false if the charge had to be forced. + * Charges @nr_pages to @memcg. Returns %true if the charge fit within + * @memcg's configured limit, %false if the charge had to be forced. */ -bool mem_cgroup_charge_skmem(struct cg_proto *proto, unsigned int nr_pages) +bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { struct page_counter *counter; - if (page_counter_try_charge(&proto->memory_allocated, + if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated, nr_pages, &counter)) { - proto->memory_pressure = 0; + memcg->tcp_mem.memory_pressure = 0; return true; } - page_counter_charge(&proto->memory_allocated, nr_pages); - proto->memory_pressure = 1; + page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages); + memcg->tcp_mem.memory_pressure = 1; return false; } /** * mem_cgroup_uncharge_skmem - uncharge socket memory - * @proto - proto to uncharge + * @memcg - memcg to uncharge * @nr_pages - number of pages to uncharge */ -void mem_cgroup_uncharge_skmem(struct cg_proto *proto, unsigned int nr_pages) +void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { - page_counter_uncharge(&proto->memory_allocated, nr_pages); + page_counter_uncharge(&memcg->tcp_mem.memory_allocated, nr_pages); } #endif @@ -3653,7 +3640,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) if (ret) return ret; - return mem_cgroup_sockets_init(memcg, ss); + return tcp_init_cgroup(memcg, ss); } static void memcg_deactivate_kmem(struct mem_cgroup *memcg) @@ -3709,7 +3696,7 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg) static_key_slow_dec(&memcg_kmem_enabled_key); WARN_ON(page_counter_read(&memcg->kmem)); } - mem_cgroup_sockets_destroy(memcg); + tcp_destroy_cgroup(memcg); } #else static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) diff --git a/net/core/sock.c b/net/core/sock.c index 89ae859d2dc5..3535bffa45f3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -195,44 +195,6 @@ bool sk_net_capable(const struct sock *sk, int cap) } EXPORT_SYMBOL(sk_net_capable); - -#ifdef CONFIG_MEMCG_KMEM -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - struct proto *proto; - int ret = 0; - - mutex_lock(&proto_list_mutex); - list_for_each_entry(proto, &proto_list, node) { - if (proto->init_cgroup) { - ret = proto->init_cgroup(memcg, ss); - if (ret) - goto out; - } - } - - mutex_unlock(&proto_list_mutex); - return ret; -out: - list_for_each_entry_continue_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); - return ret; -} - -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ - struct proto *proto; - - mutex_lock(&proto_list_mutex); - list_for_each_entry_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); -} -#endif - /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -1601,7 +1563,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + if (mem_cgroup_sockets_enabled && sk->sk_memcg) sock_update_memcg(newsk); if (newsk->sk_prot->sockets_allocated) @@ -2089,8 +2051,8 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) allocated = sk_memory_allocated_add(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_cgrp && - !mem_cgroup_charge_skmem(sk->sk_cgrp, amt)) + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + !mem_cgroup_charge_skmem(sk->sk_memcg, amt)) goto suppress_allocation; /* Under limit. */ @@ -2153,8 +2115,8 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - mem_cgroup_uncharge_skmem(sk->sk_cgrp, amt); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; } @@ -2171,8 +2133,8 @@ void __sk_mem_reclaim(struct sock *sk, int amount) sk_memory_allocated_sub(sk, amount); sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - mem_cgroup_uncharge_skmem(sk->sk_cgrp, amount); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); if (sk_under_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eb39e02899e5..c7d1fb50f381 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1819,7 +1819,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk_sockets_allocated_dec(sk); - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + if (mem_cgroup_sockets_enabled && sk->sk_memcg) sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2343,11 +2343,6 @@ struct proto tcp_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, -#endif -#ifdef CONFIG_MEMCG_KMEM - .init_cgroup = tcp_init_cgroup, - .destroy_cgroup = tcp_destroy_cgroup, - .proto_cgroup = tcp_proto_cgroup, #endif .diag_destroy = tcp_abort, }; diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index ef4268d12e43..e5078259cbe3 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -8,60 +8,47 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct page_counter *counter_parent = NULL; /* * The root cgroup does not use page_counters, but rather, * rely on the data already collected by the network * subsystem */ - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct page_counter *counter_parent = NULL; - struct cg_proto *cg_proto, *parent_cg; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - cg_proto->memory_pressure = 0; - cg_proto->memcg = memcg; + memcg->tcp_mem.memory_pressure = 0; - parent_cg = tcp_prot.proto_cgroup(parent); - if (parent_cg) - counter_parent = &parent_cg->memory_allocated; + if (parent) + counter_parent = &parent->tcp_mem.memory_allocated; - page_counter_init(&cg_proto->memory_allocated, counter_parent); + page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent); return 0; } -EXPORT_SYMBOL(tcp_init_cgroup); void tcp_destroy_cgroup(struct mem_cgroup *memcg) { - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return; - if (cg_proto->active) + if (memcg->tcp_mem.active) static_key_slow_dec(&memcg_socket_limit_enabled); - } -EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) { - struct cg_proto *cg_proto; int ret; - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return -EINVAL; - ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages); + ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages); if (ret) return ret; - if (!cg_proto->active) { + if (!memcg->tcp_mem.active) { /* * The active flag needs to be written after the static_key * update. This is what guarantees that the socket activation @@ -79,7 +66,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * patched in yet. */ static_key_slow_inc(&memcg_socket_limit_enabled); - cg_proto->active = true; + memcg->tcp_mem.active = true; } return 0; @@ -123,32 +110,32 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg); u64 val; switch (cft->private) { case RES_LIMIT: - if (!cg_proto) - return PAGE_COUNTER_MAX; - val = cg_proto->memory_allocated.limit; + if (memcg == root_mem_cgroup) + val = PAGE_COUNTER_MAX; + else + val = memcg->tcp_mem.memory_allocated.limit; val *= PAGE_SIZE; break; case RES_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) val = atomic_long_read(&tcp_memory_allocated); else - val = page_counter_read(&cg_proto->memory_allocated); + val = page_counter_read(&memcg->tcp_mem.memory_allocated); val *= PAGE_SIZE; break; case RES_FAILCNT: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.failcnt; + val = memcg->tcp_mem.memory_allocated.failcnt; break; case RES_MAX_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.watermark; + val = memcg->tcp_mem.memory_allocated.watermark; val *= PAGE_SIZE; break; default: @@ -161,19 +148,17 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg; - struct cg_proto *cg_proto; memcg = mem_cgroup_from_css(of_css(of)); - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return nbytes; switch (of_cft(of)->private) { case RES_MAX_USAGE: - page_counter_reset_watermark(&cg_proto->memory_allocated); + page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated); break; case RES_FAILCNT: - cg_proto->memory_allocated.failcnt = 0; + memcg->tcp_mem.memory_allocated.failcnt = 0; break; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 493b48945f0c..fda379cd600d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2821,8 +2821,8 @@ void sk_forced_mem_schedule(struct sock *sk, int size) sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; sk_memory_allocated_add(sk, amt); - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - mem_cgroup_charge_skmem(sk->sk_cgrp, amt); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index db9f1c318afc..4ad8edb46f7c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1888,9 +1888,6 @@ struct proto tcpv6_prot = { #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, -#endif -#ifdef CONFIG_MEMCG_KMEM - .proto_cgroup = tcp_proto_cgroup, #endif .clear_sk = tcp_v6_clear_sk, .diag_destroy = tcp_abort, -- cgit v1.2.3 From 80e95fe0fdcde2812c341ad4209d62dc1a7af53b Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:20 -0800 Subject: mm: memcontrol: generalize the socket accounting jump label The unified hierarchy memory controller is going to use this jump label as well to control the networking callbacks. Move it to the memory controller code and give it a more generic name. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Acked-by: David S. Miller Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 3 +++ include/net/sock.h | 7 ------- mm/memcontrol.c | 3 +++ net/core/sock.c | 5 ----- net/ipv4/tcp_memcontrol.c | 4 ++-- 5 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7c085e4636ba..03090e8e7fff 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -681,11 +681,14 @@ void sock_release_memcg(struct sock *sk); bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) +extern struct static_key memcg_sockets_enabled_key; +#define mem_cgroup_sockets_enabled static_key_false(&memcg_sockets_enabled_key) static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return memcg->tcp_mem.memory_pressure; } #else +#define mem_cgroup_sockets_enabled 0 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; diff --git a/include/net/sock.h b/include/net/sock.h index be96a8dcbc74..b9e7b3d863a0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1079,13 +1079,6 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) -extern struct static_key memcg_socket_limit_enabled; -#define mem_cgroup_sockets_enabled static_key_false(&memcg_socket_limit_enabled) -#else -#define mem_cgroup_sockets_enabled 0 -#endif - static inline bool sk_stream_memory_free(const struct sock *sk) { if (sk->sk_wmem_queued >= sk->sk_sndbuf) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index eaaa86126277..08ef3d2ca663 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -291,6 +291,9 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) /* Writing them here to avoid exposing memcg's inner layout */ #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) +struct static_key memcg_sockets_enabled_key; +EXPORT_SYMBOL(memcg_sockets_enabled_key); + void sock_update_memcg(struct sock *sk) { struct mem_cgroup *memcg; diff --git a/net/core/sock.c b/net/core/sock.c index 3535bffa45f3..6c1c8bc93412 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -202,11 +202,6 @@ EXPORT_SYMBOL(sk_net_capable); static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; -#if defined(CONFIG_MEMCG_KMEM) -struct static_key memcg_socket_limit_enabled; -EXPORT_SYMBOL(memcg_socket_limit_enabled); -#endif - /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index e5078259cbe3..9a22e2dfd64a 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -34,7 +34,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) return; if (memcg->tcp_mem.active) - static_key_slow_dec(&memcg_socket_limit_enabled); + static_key_slow_dec(&memcg_sockets_enabled_key); } static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) @@ -65,7 +65,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * because when this value change, the code to process it is not * patched in yet. */ - static_key_slow_inc(&memcg_socket_limit_enabled); + static_key_slow_inc(&memcg_sockets_enabled_key); memcg->tcp_mem.active = true; } -- cgit v1.2.3 From f7e1cb6ec51b041335b5ad4dd7aefb37a56d79a6 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:29 -0800 Subject: mm: memcontrol: account socket memory in unified hierarchy memory controller Socket memory can be a significant share of overall memory consumed by common workloads. In order to provide reasonable resource isolation in the unified hierarchy, this type of memory needs to be included in the tracking/accounting of a cgroup under active memory resource control. Overhead is only incurred when a non-root control group is created AND the memory controller is instructed to track and account the memory footprint of that group. cgroup.memory=nosocket can be specified on the boot commandline to override any runtime configuration and forcibly exclude socket memory from active memory resource control. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 4 ++ include/linux/memcontrol.h | 9 ++- mm/memcontrol.c | 122 +++++++++++++++++++++++++++++------- 3 files changed, 110 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index b7d44871effc..168fd79dc697 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -608,6 +608,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. cut the overhead, others just disable the usage. So only cgroup_disable=memory is actually worthy} + cgroup.memory= [KNL] Pass options to the cgroup memory controller. + Format: + nosocket -- Disable socket memory accounting. + checkreqprot [SELINUX] Set initial checkreqprot flag value. Format: { "0" | "1" } See security/selinux/Kconfig help text. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 03090e8e7fff..a355f61a2ed3 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -170,6 +170,9 @@ struct mem_cgroup { unsigned long low; unsigned long high; + /* Range enforcement for interrupt charges */ + struct work_struct high_work; + unsigned long soft_limit; /* vmpressure notifications */ @@ -680,12 +683,16 @@ void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) +#if defined(CONFIG_MEMCG) && defined(CONFIG_INET) extern struct static_key memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_key_false(&memcg_sockets_enabled_key) static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { +#ifdef CONFIG_MEMCG_KMEM return memcg->tcp_mem.memory_pressure; +#else + return false; +#endif } #else #define mem_cgroup_sockets_enabled 0 diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6aac8d2e31d7..60ebc486c2aa 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -80,6 +80,9 @@ struct mem_cgroup *root_mem_cgroup __read_mostly; #define MEM_CGROUP_RECLAIM_RETRIES 5 +/* Socket memory accounting disabled? */ +static bool cgroup_memory_nosocket; + /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP int do_swap_account __read_mostly; @@ -1945,6 +1948,26 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, return NOTIFY_OK; } +static void reclaim_high(struct mem_cgroup *memcg, + unsigned int nr_pages, + gfp_t gfp_mask) +{ + do { + if (page_counter_read(&memcg->memory) <= memcg->high) + continue; + mem_cgroup_events(memcg, MEMCG_HIGH, 1); + try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + } while ((memcg = parent_mem_cgroup(memcg))); +} + +static void high_work_func(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, high_work); + reclaim_high(memcg, CHARGE_BATCH, GFP_KERNEL); +} + /* * Scheduled by try_charge() to be executed from the userland return path * and reclaims memory over the high limit. @@ -1952,20 +1975,13 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb, void mem_cgroup_handle_over_high(void) { unsigned int nr_pages = current->memcg_nr_pages_over_high; - struct mem_cgroup *memcg, *pos; + struct mem_cgroup *memcg; if (likely(!nr_pages)) return; - pos = memcg = get_mem_cgroup_from_mm(current->mm); - - do { - if (page_counter_read(&pos->memory) <= pos->high) - continue; - mem_cgroup_events(pos, MEMCG_HIGH, 1); - try_to_free_mem_cgroup_pages(pos, nr_pages, GFP_KERNEL, true); - } while ((pos = parent_mem_cgroup(pos))); - + memcg = get_mem_cgroup_from_mm(current->mm); + reclaim_high(memcg, nr_pages, GFP_KERNEL); css_put(&memcg->css); current->memcg_nr_pages_over_high = 0; } @@ -2100,6 +2116,11 @@ done_restock: */ do { if (page_counter_read(&memcg->memory) > memcg->high) { + /* Don't bother a random interrupted task */ + if (in_interrupt()) { + schedule_work(&memcg->high_work); + break; + } current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; @@ -4150,6 +4171,8 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; + cancel_work_sync(&memcg->high_work); + mem_cgroup_remove_from_trees(memcg); for_each_node(node) @@ -4196,6 +4219,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_init(&memcg->kmem, NULL); } + INIT_WORK(&memcg->high_work, high_work_func); memcg->last_scanned_node = MAX_NUMNODES; INIT_LIST_HEAD(&memcg->oom_notify); memcg->move_charge_at_immigrate = 0; @@ -4267,6 +4291,11 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (ret) return ret; +#ifdef CONFIG_INET + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_key_slow_inc(&memcg_sockets_enabled_key); +#endif + /* * Make sure the memcg is initialized: mem_cgroup_iter() * orders reading memcg->initialized against its callers @@ -4313,6 +4342,10 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) struct mem_cgroup *memcg = mem_cgroup_from_css(css); memcg_destroy_kmem(memcg); +#ifdef CONFIG_INET + if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) + static_key_slow_dec(&memcg_sockets_enabled_key); +#endif __mem_cgroup_free(memcg); } @@ -5533,8 +5566,7 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg, true); } -/* Writing them here to avoid exposing memcg's inner layout */ -#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM) +#ifdef CONFIG_INET struct static_key memcg_sockets_enabled_key; EXPORT_SYMBOL(memcg_sockets_enabled_key); @@ -5559,10 +5591,15 @@ void sock_update_memcg(struct sock *sk) rcu_read_lock(); memcg = mem_cgroup_from_task(current); - if (memcg != root_mem_cgroup && - memcg->tcp_mem.active && - css_tryget_online(&memcg->css)) + if (memcg == root_mem_cgroup) + goto out; +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcp_mem.active) + goto out; +#endif + if (css_tryget_online(&memcg->css)) sk->sk_memcg = memcg; +out: rcu_read_unlock(); } EXPORT_SYMBOL(sock_update_memcg); @@ -5583,15 +5620,30 @@ void sock_release_memcg(struct sock *sk) */ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { - struct page_counter *counter; + gfp_t gfp_mask = GFP_KERNEL; - if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated, - nr_pages, &counter)) { - memcg->tcp_mem.memory_pressure = 0; - return true; +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + struct page_counter *counter; + + if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated, + nr_pages, &counter)) { + memcg->tcp_mem.memory_pressure = 0; + return true; + } + page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages); + memcg->tcp_mem.memory_pressure = 1; + return false; } - page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages); - memcg->tcp_mem.memory_pressure = 1; +#endif + /* Don't block in the packet receive path */ + if (in_softirq()) + gfp_mask = GFP_NOWAIT; + + if (try_charge(memcg, gfp_mask, nr_pages) == 0) + return true; + + try_charge(memcg, gfp_mask|__GFP_NOFAIL, nr_pages); return false; } @@ -5602,10 +5654,32 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) */ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { - page_counter_uncharge(&memcg->tcp_mem.memory_allocated, nr_pages); +#ifdef CONFIG_MEMCG_KMEM + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + page_counter_uncharge(&memcg->tcp_mem.memory_allocated, + nr_pages); + return; + } +#endif + page_counter_uncharge(&memcg->memory, nr_pages); + css_put_many(&memcg->css, nr_pages); } -#endif +#endif /* CONFIG_INET */ + +static int __init cgroup_memory(char *s) +{ + char *token; + + while ((token = strsep(&s, ",")) != NULL) { + if (!*token) + continue; + if (!strcmp(token, "nosocket")) + cgroup_memory_nosocket = true; + } + return 0; +} +__setup("cgroup.memory=", cgroup_memory); /* * subsys_initcall() for memory controller. -- cgit v1.2.3 From 8e8ae645249b85c8ed6c178557f8db8613a6bcc7 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:32 -0800 Subject: mm: memcontrol: hook up vmpressure to socket pressure Let the networking stack know when a memcg is under reclaim pressure so that it can clamp its transmit windows accordingly. Whenever the reclaim efficiency of a cgroup's LRU lists drops low enough for a MEDIUM or HIGH vmpressure event to occur, assert a pressure state in the socket and tcp memory code that tells it to curb consumption growth from sockets associated with said control group. Traditionally, vmpressure reports for the entire subtree of a memcg under pressure, which drops useful information on the individual groups reclaimed. However, it's too late to change the userinterface, so add a second reporting mode that reports on the level of reclaim instead of at the level of pressure, and use that report for sockets. vmpressure events are naturally edge triggered, so for hysteresis assert socket pressure for a second to allow for subsequent vmpressure events to occur before letting the socket code return to normal. This will likely need finetuning for a wider variety of workloads, but for now stick to the vmpressure presets and keep hysteresis simple. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reviewed-by: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 32 ++++++++++++++++--- include/linux/vmpressure.h | 7 +++-- mm/memcontrol.c | 17 ++-------- mm/vmpressure.c | 78 +++++++++++++++++++++++++++++++++++----------- mm/vmscan.c | 10 +++++- 5 files changed, 104 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a355f61a2ed3..c5a51039df57 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -249,6 +249,10 @@ struct mem_cgroup { struct wb_domain cgwb_domain; #endif +#ifdef CONFIG_INET + unsigned long socket_pressure; +#endif + /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; @@ -290,18 +294,34 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); -struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } +#define mem_cgroup_from_counter(counter, member) \ + container_of(counter, struct mem_cgroup, member) + struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +/** + * parent_mem_cgroup - find the accounting parent of a memcg + * @memcg: memcg whose parent to find + * + * Returns the parent memcg, or NULL if this is the root or the memory + * controller is in legacy no-hierarchy mode. + */ +static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) +{ + if (!memcg->memory.parent) + return NULL; + return mem_cgroup_from_counter(memcg->memory.parent, memory); +} + static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { @@ -689,10 +709,14 @@ extern struct static_key memcg_sockets_enabled_key; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { #ifdef CONFIG_MEMCG_KMEM - return memcg->tcp_mem.memory_pressure; -#else - return false; + if (memcg->tcp_mem.memory_pressure) + return true; #endif + do { + if (time_before(jiffies, memcg->socket_pressure)) + return true; + } while ((memcg = parent_mem_cgroup(memcg))); + return false; } #else #define mem_cgroup_sockets_enabled 0 diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h index 3e4535876d37..3347cc3ec0ab 100644 --- a/include/linux/vmpressure.h +++ b/include/linux/vmpressure.h @@ -12,6 +12,9 @@ struct vmpressure { unsigned long scanned; unsigned long reclaimed; + + unsigned long tree_scanned; + unsigned long tree_reclaimed; /* The lock is used to keep the scanned/reclaimed above in sync. */ struct spinlock sr_lock; @@ -26,7 +29,7 @@ struct vmpressure { struct mem_cgroup; #ifdef CONFIG_MEMCG -extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed); extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio); @@ -40,7 +43,7 @@ extern int vmpressure_register_event(struct mem_cgroup *memcg, extern void vmpressure_unregister_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd); #else -static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) {} static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) {} diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 60ebc486c2aa..df7f144a5a4b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1113,9 +1113,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) return ret; } -#define mem_cgroup_from_counter(counter, member) \ - container_of(counter, struct mem_cgroup, member) - /** * mem_cgroup_margin - calculate chargeable space of a memory cgroup * @memcg: the memory cgroup @@ -4183,17 +4180,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) kfree(memcg); } -/* - * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. - */ -struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) -{ - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); -} -EXPORT_SYMBOL(parent_mem_cgroup); - static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -4233,6 +4219,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #endif #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); +#endif +#ifdef CONFIG_INET + memcg->socket_pressure = jiffies; #endif return &memcg->css; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index c5afd573d7da..506f03e4be47 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -137,14 +137,11 @@ struct vmpressure_event { }; static bool vmpressure_event(struct vmpressure *vmpr, - unsigned long scanned, unsigned long reclaimed) + enum vmpressure_levels level) { struct vmpressure_event *ev; - enum vmpressure_levels level; bool signalled = false; - level = vmpressure_calc_level(scanned, reclaimed); - mutex_lock(&vmpr->events_lock); list_for_each_entry(ev, &vmpr->events, node) { @@ -164,6 +161,7 @@ static void vmpressure_work_fn(struct work_struct *work) struct vmpressure *vmpr = work_to_vmpressure(work); unsigned long scanned; unsigned long reclaimed; + enum vmpressure_levels level; spin_lock(&vmpr->sr_lock); /* @@ -174,19 +172,21 @@ static void vmpressure_work_fn(struct work_struct *work) * here. No need for any locks here since we don't care if * vmpr->reclaimed is in sync. */ - scanned = vmpr->scanned; + scanned = vmpr->tree_scanned; if (!scanned) { spin_unlock(&vmpr->sr_lock); return; } - reclaimed = vmpr->reclaimed; - vmpr->scanned = 0; - vmpr->reclaimed = 0; + reclaimed = vmpr->tree_reclaimed; + vmpr->tree_scanned = 0; + vmpr->tree_reclaimed = 0; spin_unlock(&vmpr->sr_lock); + level = vmpressure_calc_level(scanned, reclaimed); + do { - if (vmpressure_event(vmpr, scanned, reclaimed)) + if (vmpressure_event(vmpr, level)) break; /* * If not handled, propagate the event upward into the @@ -199,6 +199,7 @@ static void vmpressure_work_fn(struct work_struct *work) * vmpressure() - Account memory pressure through scanned/reclaimed ratio * @gfp: reclaimer's gfp mask * @memcg: cgroup memory controller handle + * @tree: legacy subtree mode * @scanned: number of pages scanned * @reclaimed: number of pages reclaimed * @@ -206,9 +207,16 @@ static void vmpressure_work_fn(struct work_struct *work) * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw * pressure index is then further refined and averaged over time. * + * If @tree is set, vmpressure is in traditional userspace reporting + * mode: @memcg is considered the pressure root and userspace is + * notified of the entire subtree's reclaim efficiency. + * + * If @tree is not set, reclaim efficiency is recorded for @memcg, and + * only in-kernel users are notified. + * * This function does not return any value. */ -void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, +void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, unsigned long scanned, unsigned long reclaimed) { struct vmpressure *vmpr = memcg_to_vmpressure(memcg); @@ -238,15 +246,47 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, if (!scanned) return; - spin_lock(&vmpr->sr_lock); - vmpr->scanned += scanned; - vmpr->reclaimed += reclaimed; - scanned = vmpr->scanned; - spin_unlock(&vmpr->sr_lock); + if (tree) { + spin_lock(&vmpr->sr_lock); + vmpr->tree_scanned += scanned; + vmpr->tree_reclaimed += reclaimed; + scanned = vmpr->scanned; + spin_unlock(&vmpr->sr_lock); - if (scanned < vmpressure_win) - return; - schedule_work(&vmpr->work); + if (scanned < vmpressure_win) + return; + schedule_work(&vmpr->work); + } else { + enum vmpressure_levels level; + + /* For now, no users for root-level efficiency */ + if (memcg == root_mem_cgroup) + return; + + spin_lock(&vmpr->sr_lock); + scanned = vmpr->scanned += scanned; + reclaimed = vmpr->reclaimed += reclaimed; + if (scanned < vmpressure_win) { + spin_unlock(&vmpr->sr_lock); + return; + } + vmpr->scanned = vmpr->reclaimed = 0; + spin_unlock(&vmpr->sr_lock); + + level = vmpressure_calc_level(scanned, reclaimed); + + if (level > VMPRESSURE_LOW) { + /* + * Let the socket buffer allocator know that + * we are having trouble reclaiming LRU pages. + * + * For hysteresis keep the pressure state + * asserted for a second in which subsequent + * pressure events can occur. + */ + memcg->socket_pressure = jiffies + HZ; + } + } } /** @@ -276,7 +316,7 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * to the vmpressure() basically means that we signal 'critical' * level. */ - vmpressure(gfp, memcg, vmpressure_win, 0); + vmpressure(gfp, memcg, true, vmpressure_win, 0); } /** diff --git a/mm/vmscan.c b/mm/vmscan.c index e36d766dade9..bb0cbd4c9f01 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2396,6 +2396,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg = mem_cgroup_iter(root, NULL, &reclaim); do { unsigned long lru_pages; + unsigned long reclaimed; unsigned long scanned; struct lruvec *lruvec; int swappiness; @@ -2408,6 +2409,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); + reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, swappiness, sc, &lru_pages); @@ -2418,6 +2420,11 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg, sc->nr_scanned - scanned, lru_pages); + /* Record the group's reclaim efficiency */ + vmpressure(sc->gfp_mask, memcg, false, + sc->nr_scanned - scanned, + sc->nr_reclaimed - reclaimed); + /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the @@ -2449,7 +2456,8 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, reclaim_state->reclaimed_slab = 0; } - vmpressure(sc->gfp_mask, sc->target_mem_cgroup, + /* Record the subtree's reclaim efficiency */ + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); -- cgit v1.2.3 From ef12947c9c5a96af549c49f10e5503f0612a397c Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 14 Jan 2016 15:21:34 -0800 Subject: mm: memcontrol: switch to the updated jump-label API According to the direct use of struct static_key is deprecated. Update the socket and slab accounting code accordingly. Signed-off-by: Johannes Weiner Acked-by: David S. Miller Reported-by: Jason Baron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 8 ++++---- mm/memcontrol.c | 12 ++++++------ net/ipv4/tcp_memcontrol.c | 4 ++-- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c5a51039df57..2292468f2a30 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -704,8 +704,8 @@ void sock_release_memcg(struct sock *sk); bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #if defined(CONFIG_MEMCG) && defined(CONFIG_INET) -extern struct static_key memcg_sockets_enabled_key; -#define mem_cgroup_sockets_enabled static_key_false(&memcg_sockets_enabled_key) +extern struct static_key_false memcg_sockets_enabled_key; +#define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { #ifdef CONFIG_MEMCG_KMEM @@ -727,7 +727,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) #endif #ifdef CONFIG_MEMCG_KMEM -extern struct static_key memcg_kmem_enabled_key; +extern struct static_key_false memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); @@ -743,7 +743,7 @@ void memcg_put_cache_ids(void); static inline bool memcg_kmem_enabled(void) { - return static_key_false(&memcg_kmem_enabled_key); + return static_branch_unlikely(&memcg_kmem_enabled_key); } static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index df7f144a5a4b..54eae4f19d80 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -346,7 +346,7 @@ void memcg_put_cache_ids(void) * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well */ -struct static_key memcg_kmem_enabled_key; +DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key); #endif /* CONFIG_MEMCG_KMEM */ @@ -2907,7 +2907,7 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, err = page_counter_limit(&memcg->kmem, nr_pages); VM_BUG_ON(err); - static_key_slow_inc(&memcg_kmem_enabled_key); + static_branch_inc(&memcg_kmem_enabled_key); /* * A memory cgroup is considered kmem-active as soon as it gets * kmemcg_id. Setting the id after enabling static branching will @@ -3646,7 +3646,7 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg) { if (memcg->kmem_acct_activated) { memcg_destroy_kmem_caches(memcg); - static_key_slow_dec(&memcg_kmem_enabled_key); + static_branch_dec(&memcg_kmem_enabled_key); WARN_ON(page_counter_read(&memcg->kmem)); } tcp_destroy_cgroup(memcg); @@ -4282,7 +4282,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) #ifdef CONFIG_INET if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) - static_key_slow_inc(&memcg_sockets_enabled_key); + static_branch_inc(&memcg_sockets_enabled_key); #endif /* @@ -4333,7 +4333,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) memcg_destroy_kmem(memcg); #ifdef CONFIG_INET if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) - static_key_slow_dec(&memcg_sockets_enabled_key); + static_branch_dec(&memcg_sockets_enabled_key); #endif __mem_cgroup_free(memcg); } @@ -5557,7 +5557,7 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) #ifdef CONFIG_INET -struct static_key memcg_sockets_enabled_key; +DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); EXPORT_SYMBOL(memcg_sockets_enabled_key); void sock_update_memcg(struct sock *sk) diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 9a22e2dfd64a..18bc7f745e9c 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -34,7 +34,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) return; if (memcg->tcp_mem.active) - static_key_slow_dec(&memcg_sockets_enabled_key); + static_branch_dec(&memcg_sockets_enabled_key); } static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) @@ -65,7 +65,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * because when this value change, the code to process it is not * patched in yet. */ - static_key_slow_inc(&memcg_sockets_enabled_key); + static_branch_inc(&memcg_sockets_enabled_key); memcg->tcp_mem.active = true; } -- cgit v1.2.3 From 0eb77e9880321915322d42913c3b53241739c8aa Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 14 Jan 2016 15:21:40 -0800 Subject: vmstat: make vmstat_updater deferrable again and shut down on idle Currently the vmstat updater is not deferrable as a result of commit ba4877b9ca51 ("vmstat: do not use deferrable delayed work for vmstat_update"). This in turn can cause multiple interruptions of the applications because the vmstat updater may run at Make vmstate_update deferrable again and provide a function that folds the differentials when the processor is going to idle mode thus addressing the issue of the above commit in a clean way. Note that the shepherd thread will continue scanning the differentials from another processor and will reenable the vmstat workers if it detects any changes. Fixes: ba4877b9ca51 ("vmstat: do not use deferrable delayed work for vmstat_update") Signed-off-by: Christoph Lameter Cc: Michal Hocko Cc: Johannes Weiner Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 2 ++ kernel/sched/idle.c | 1 + mm/vmstat.c | 69 ++++++++++++++++++++++++++++++++------------------ 3 files changed, 47 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3e5d9075960f..73fae8c4a5fb 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -189,6 +189,7 @@ extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); +void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); @@ -249,6 +250,7 @@ static inline void __dec_zone_page_state(struct page *page, static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } +static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 4a2ef5a02fd3..2489140a7c51 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -219,6 +219,7 @@ static void cpu_idle_loop(void) */ __current_set_polling(); + quiet_vmstat(); tick_nohz_idle_enter(); while (!need_resched()) { diff --git a/mm/vmstat.c b/mm/vmstat.c index c54fd2924f25..83a003bc3cae 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -460,7 +460,7 @@ static int fold_diff(int *diff) * * The function returns the number of global counters updated. */ -static int refresh_cpu_vm_stats(void) +static int refresh_cpu_vm_stats(bool do_pagesets) { struct zone *zone; int i; @@ -484,33 +484,35 @@ static int refresh_cpu_vm_stats(void) #endif } } - cond_resched(); #ifdef CONFIG_NUMA - /* - * Deal with draining the remote pageset of this - * processor - * - * Check if there are pages remaining in this pageset - * if not then there is nothing to expire. - */ - if (!__this_cpu_read(p->expire) || + if (do_pagesets) { + cond_resched(); + /* + * Deal with draining the remote pageset of this + * processor + * + * Check if there are pages remaining in this pageset + * if not then there is nothing to expire. + */ + if (!__this_cpu_read(p->expire) || !__this_cpu_read(p->pcp.count)) - continue; + continue; - /* - * We never drain zones local to this processor. - */ - if (zone_to_nid(zone) == numa_node_id()) { - __this_cpu_write(p->expire, 0); - continue; - } + /* + * We never drain zones local to this processor. + */ + if (zone_to_nid(zone) == numa_node_id()) { + __this_cpu_write(p->expire, 0); + continue; + } - if (__this_cpu_dec_return(p->expire)) - continue; + if (__this_cpu_dec_return(p->expire)) + continue; - if (__this_cpu_read(p->pcp.count)) { - drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); - changes++; + if (__this_cpu_read(p->pcp.count)) { + drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + changes++; + } } #endif } @@ -1386,7 +1388,7 @@ static cpumask_var_t cpu_stat_off; static void vmstat_update(struct work_struct *w) { - if (refresh_cpu_vm_stats()) { + if (refresh_cpu_vm_stats(true)) { /* * Counters were updated so we expect more updates * to occur in the future. Keep on running the @@ -1417,6 +1419,23 @@ static void vmstat_update(struct work_struct *w) } } +/* + * Switch off vmstat processing and then fold all the remaining differentials + * until the diffs stay at zero. The function is used by NOHZ and can only be + * invoked when tick processing is not active. + */ +void quiet_vmstat(void) +{ + if (system_state != SYSTEM_RUNNING) + return; + + do { + if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) + cancel_delayed_work(this_cpu_ptr(&vmstat_work)); + + } while (refresh_cpu_vm_stats(false)); +} + /* * Check if the diffs for a certain cpu indicate that * an update is needed. @@ -1449,7 +1468,7 @@ static bool need_update(int cpu) */ static void vmstat_shepherd(struct work_struct *w); -static DECLARE_DELAYED_WORK(shepherd, vmstat_shepherd); +static DECLARE_DEFERRABLE_WORK(shepherd, vmstat_shepherd); static void vmstat_shepherd(struct work_struct *w) { -- cgit v1.2.3 From d72ee911130631b50a8ccc615a7d4622c2062194 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 14 Jan 2016 15:22:01 -0800 Subject: mm: move lru_to_page to mm_inline.h Move lru_to_page() from internal.h to mm_inline.h. Signed-off-by: Geliang Tang Acked-by: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 2 ++ mm/internal.h | 2 -- mm/readahead.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index cf55945c83fb..712e8c37a200 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -100,4 +100,6 @@ static __always_inline enum lru_list page_lru(struct page *page) return lru; } +#define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) + #endif diff --git a/mm/internal.h b/mm/internal.h index 016452d2fede..38e24b89e4c4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -119,8 +119,6 @@ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); extern bool zone_reclaimable(struct zone *zone); -#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) - /* * in mm/rmap.c: */ diff --git a/mm/readahead.c b/mm/readahead.c index 0aff760b09d4..20e58e820e44 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internal.h" -- cgit v1.2.3 From d30b5545bdcf802ffc24ec7dbc6dc4036f6e3820 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 14 Jan 2016 15:22:04 -0800 Subject: include/linux/memblock.h: fix ordering of 'flags' argument in comments for_each_free_mem_range() and for_each_free_mem_range_reverse() both accept a 'flags' argument, the comment surrounding the macro placed the 'flags' documentation at the very end, while 'flags' is in fact the 3rd argument to the macro, so let's preserve natural ordering here. Fixes: fc6daaf931518 ("mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute") Signed-off-by: Florian Fainelli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index c0c4208a286f..173fb44e22f1 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -216,10 +216,10 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * for_each_free_mem_range - iterate through free memblock areas * @i: u64 used as loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL - * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock. Available as * soon as memblock is initialized. @@ -232,10 +232,10 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, * for_each_free_mem_range_reverse - rev-iterate through free memblock areas * @i: u64 used as loop variable * @nid: node selector, %NUMA_NO_NODE for all nodes + * @flags: pick from blocks based on memory attributes * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL * @p_nid: ptr to int for nid of the range, can be %NULL - * @flags: pick from blocks based on memory attributes * * Walks over free (memory && !reserved) areas of memblock in reverse * order. Available as soon as memblock is initialized. -- cgit v1.2.3 From 84638335900f1995495838fe1bd4870c43ec1f67 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 14 Jan 2016 15:22:07 -0800 Subject: mm: rework virtual memory accounting When inspecting a vague code inside prctl(PR_SET_MM_MEM) call (which testing the RLIMIT_DATA value to figure out if we're allowed to assign new @start_brk, @brk, @start_data, @end_data from mm_struct) it's been commited that RLIMIT_DATA in a form it's implemented now doesn't do anything useful because most of user-space libraries use mmap() syscall for dynamic memory allocations. Linus suggested to convert RLIMIT_DATA rlimit into something suitable for anonymous memory accounting. But in this patch we go further, and the changes are bundled together as: * keep vma counting if CONFIG_PROC_FS=n, will be used for limits * replace mm->shared_vm with better defined mm->data_vm * account anonymous executable areas as executable * account file-backed growsdown/up areas as stack * drop struct file* argument from vm_stat_account * enforce RLIMIT_DATA for size of data areas This way code looks cleaner: now code/stack/data classification depends only on vm_flags state: VM_EXEC & ~VM_WRITE -> code (VmExe + VmLib in proc) VM_GROWSUP | VM_GROWSDOWN -> stack (VmStk) VM_WRITE & ~VM_SHARED & !stack -> data (VmData) The rest (VmSize - VmData - VmStk - VmExe - VmLib) could be called "shared", but that might be strange beast like readonly-private or VM_IO area. - RLIMIT_AS limits whole address space "VmSize" - RLIMIT_STACK limits stack "VmStk" (but each vma individually) - RLIMIT_DATA now limits "VmData" Signed-off-by: Konstantin Khlebnikov Signed-off-by: Cyrill Gorcunov Cc: Quentin Casasnovas Cc: Vegard Nossum Acked-by: Linus Torvalds Cc: Willy Tarreau Cc: Andy Lutomirski Cc: Kees Cook Cc: Vladimir Davydov Cc: Pavel Emelyanov Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/perfmon.c | 3 +-- fs/proc/task_mmu.c | 7 +++--- include/linux/mm.h | 13 +++------- include/linux/mm_types.h | 2 +- kernel/fork.c | 5 ++-- mm/debug.c | 4 +-- mm/mmap.c | 63 +++++++++++++++++++++++----------------------- mm/mprotect.c | 8 ++++-- mm/mremap.c | 7 +++--- 9 files changed, 54 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 60e02f7747ff..9cd607b06964 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2332,8 +2332,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t */ insert_vm_struct(mm, vma); - vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file, - vma_pages(vma)); + vm_stat_account(vma->vm_mm, vma->vm_flags, vma_pages(vma)); up_write(&task->mm->mmap_sem); /* diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 46d9619d0aea..a353b4c6e86e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -23,7 +23,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap, ptes, pmds, anon, file, shmem; + unsigned long text, lib, swap, ptes, pmds, anon, file, shmem; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; anon = get_mm_counter(mm, MM_ANONPAGES); @@ -44,7 +44,6 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) if (hiwater_rss < mm->hiwater_rss) hiwater_rss = mm->hiwater_rss; - data = mm->total_vm - mm->shared_vm - mm->stack_vm; text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); @@ -76,7 +75,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) anon << (PAGE_SHIFT-10), file << (PAGE_SHIFT-10), shmem << (PAGE_SHIFT-10), - data << (PAGE_SHIFT-10), + mm->data_vm << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, ptes >> 10, pmds >> 10, @@ -97,7 +96,7 @@ unsigned long task_statm(struct mm_struct *mm, get_mm_counter(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; - *data = mm->total_vm - mm->shared_vm; + *data = mm->data_vm + mm->stack_vm; *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); return mm->total_vm; } diff --git a/include/linux/mm.h b/include/linux/mm.h index ec9d4559514d..839d9e9a1c38 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1929,7 +1929,9 @@ extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); -extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); +extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); +extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); + extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, @@ -2147,15 +2149,6 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -#ifdef CONFIG_PROC_FS -void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); -#else -static inline void vm_stat_account(struct mm_struct *mm, - unsigned long flags, struct file *file, long pages) -{ - mm->total_vm += pages; -} -#endif /* CONFIG_PROC_FS */ #ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 207890be93c8..6bc9a0ce2253 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -427,7 +427,7 @@ struct mm_struct { unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ unsigned long pinned_vm; /* Refcount permanently increased */ - unsigned long shared_vm; /* Shared pages (files) */ + unsigned long data_vm; /* VM_WRITE & ~VM_SHARED/GROWSDOWN */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE */ unsigned long stack_vm; /* VM_GROWSUP/DOWN */ unsigned long def_flags; diff --git a/kernel/fork.c b/kernel/fork.c index 51915842f1c0..2e391c754ae7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -414,7 +414,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); mm->total_vm = oldmm->total_vm; - mm->shared_vm = oldmm->shared_vm; + mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; @@ -433,8 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { - vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, - -vma_pages(mpnt)); + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; diff --git a/mm/debug.c b/mm/debug.c index 668aa35191ca..5d2072ed8d5e 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -175,7 +175,7 @@ void dump_mm(const struct mm_struct *mm) "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" - "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" + "pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" "start_brk %lx brk %lx start_stack %lx\n" "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" @@ -209,7 +209,7 @@ void dump_mm(const struct mm_struct *mm) mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, - mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, + mm->pinned_vm, mm->data_vm, mm->exec_vm, mm->stack_vm, mm->start_code, mm->end_code, mm->start_data, mm->end_data, mm->start_brk, mm->brk, mm->start_stack, mm->arg_start, mm->arg_end, mm->env_start, mm->env_end, diff --git a/mm/mmap.c b/mm/mmap.c index f32b84ad621a..b3f00b616b81 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1220,24 +1220,6 @@ none: return NULL; } -#ifdef CONFIG_PROC_FS -void vm_stat_account(struct mm_struct *mm, unsigned long flags, - struct file *file, long pages) -{ - const unsigned long stack_flags - = VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN); - - mm->total_vm += pages; - - if (file) { - mm->shared_vm += pages; - if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC) - mm->exec_vm += pages; - } else if (flags & stack_flags) - mm->stack_vm += pages; -} -#endif /* CONFIG_PROC_FS */ - /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr @@ -1556,7 +1538,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long charged = 0; /* Check against address space limit. */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { + if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* @@ -1565,7 +1547,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ nr_pages = count_vma_pages_range(mm, addr, addr + len); - if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages)) + if (!may_expand_vm(mm, vm_flags, + (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } @@ -1664,7 +1647,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, out: perf_event_mmap(vma); - vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT); + vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if (!((vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))) @@ -2111,7 +2094,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns unsigned long new_start, actual_size; /* address space limit tests */ - if (!may_expand_vm(mm, grow)) + if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ @@ -2208,8 +2191,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, - vma->vm_file, grow); + vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; anon_vma_interval_tree_post_update_vma(vma); @@ -2284,8 +2266,7 @@ int expand_downwards(struct vm_area_struct *vma, spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; - vm_stat_account(mm, vma->vm_flags, - vma->vm_file, grow); + vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; @@ -2399,7 +2380,7 @@ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; - vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages); + vm_stat_account(mm, vma->vm_flags, -nrpages); vma = remove_vma(vma); } while (vma); vm_unacct_memory(nr_accounted); @@ -2769,7 +2750,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) } /* Check against address space limits *after* clearing old maps... */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) + if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) @@ -2804,6 +2785,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; + mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vma->vm_flags |= VM_SOFTDIRTY; @@ -2995,9 +2977,28 @@ out: * Return true if the calling process may expand its vm space by the passed * number of pages */ -int may_expand_vm(struct mm_struct *mm, unsigned long npages) +bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { - return mm->total_vm + npages <= rlimit(RLIMIT_AS) >> PAGE_SHIFT; + if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) + return false; + + if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS & + (VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE) + return mm->data_vm + npages <= rlimit(RLIMIT_DATA); + + return true; +} + +void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) +{ + mm->total_vm += npages; + + if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC) + mm->exec_vm += npages; + else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) + mm->stack_vm += npages; + else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + mm->data_vm += npages; } static int special_mapping_fault(struct vm_area_struct *vma, @@ -3079,7 +3080,7 @@ static struct vm_area_struct *__install_special_mapping( if (ret) goto out; - mm->total_vm += len >> PAGE_SHIFT; + vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); diff --git a/mm/mprotect.c b/mm/mprotect.c index ef5be8eaab00..c764402c464f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -278,6 +278,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, * even if read-only so there is no need to account for them here */ if (newflags & VM_WRITE) { + /* Check space limits when area turns into data. */ + if (!may_expand_vm(mm, newflags, nrpages) && + may_expand_vm(mm, oldflags, nrpages)) + return -ENOMEM; if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| VM_SHARED|VM_NORESERVE))) { charged = nrpages; @@ -334,8 +338,8 @@ success: populate_vma_page_range(vma, start, end, NULL); } - vm_stat_account(mm, oldflags, vma->vm_file, -nrpages); - vm_stat_account(mm, newflags, vma->vm_file, nrpages); + vm_stat_account(mm, oldflags, -nrpages); + vm_stat_account(mm, newflags, nrpages); perf_event_mmap(vma); return 0; diff --git a/mm/mremap.c b/mm/mremap.c index de824e72c3e8..e55b157865d5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -317,7 +317,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, * If this were a serious issue, we'd add a flag to do_munmap(). */ hiwater_vm = mm->hiwater_vm; - vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT); + vm_stat_account(mm, vma->vm_flags, new_len >> PAGE_SHIFT); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) @@ -383,7 +383,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, return ERR_PTR(-EAGAIN); } - if (!may_expand_vm(mm, (new_len - old_len) >> PAGE_SHIFT)) + if (!may_expand_vm(mm, vma->vm_flags, + (new_len - old_len) >> PAGE_SHIFT)) return ERR_PTR(-ENOMEM); if (vma->vm_flags & VM_ACCOUNT) { @@ -545,7 +546,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, goto out; } - vm_stat_account(mm, vma->vm_flags, vma->vm_file, pages); + vm_stat_account(mm, vma->vm_flags, pages); if (vma->vm_flags & VM_LOCKED) { mm->locked_vm += pages; locked = true; -- cgit v1.2.3 From 543dfb2df8ebb3eb0b499eae1d63de1701a99b40 Mon Sep 17 00:00:00 2001 From: Joshua Clayton Date: Thu, 14 Jan 2016 15:22:10 -0800 Subject: mm: fix noisy sparse warning in LIBCFS_ALLOC_PRE() Running sparse on drivers/staging/lustre results in dozens of warnings: include/linux/gfp.h:281:41: warning: odd constant _Bool cast (400000 becomes 1) Use "!!" to explicitly convert to bool and get rid of the warning. Signed-off-by: Joshua Clayton Cc: Mel Gorman Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 91f74e741aa2..28ad5f6494b0 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -278,7 +278,7 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { - return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM); + return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM -- cgit v1.2.3 From 9207f9d45b0ad071baa128e846d7e7ed85016df3 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 8 Jan 2016 15:21:46 +0300 Subject: net: preserve IP control block during GSO segmentation Skb_gso_segment() uses skb control block during segmentation. This patch adds 32-bytes room for previous control block which will be copied into all resulting segments. This patch fixes kernel crash during fragmenting forwarded packets. Fragmentation requires valid IP CB in skb for clearing ip options. Also patch removes custom save/restore in ovs code, now it's redundant. Signed-off-by: Konstantin Khlebnikov Link: http://lkml.kernel.org/r/CALYGNiP-0MZ-FExV2HutTvE9U-QQtkKSoE--KN=JQE5STYsjAA@mail.gmail.com Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- net/core/dev.c | 5 +++++ net/ipv4/ip_output.c | 1 + net/openvswitch/datapath.c | 5 +---- net/xfrm/xfrm_output.c | 2 ++ 5 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 07f9ccd28654..11f935c1a090 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3551,7 +3551,8 @@ struct skb_gso_cb { int encap_level; __u16 csum_start; }; -#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) +#define SKB_SGO_CB_OFFSET 32 +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_SGO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { diff --git a/net/core/dev.c b/net/core/dev.c index 0ca95d5d7af0..cc9e3652cf93 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2695,6 +2695,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. + * + * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -2709,6 +2711,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 512a44778cf2..64878efa045c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -239,6 +239,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * from host network stack. */ features = netif_skb_features(skb); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 91a8b004dc51..deadfdab1bc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -336,12 +336,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, unsigned short gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; - struct ovs_skb_cb ovs_cb; int err; - ovs_cb = *OVS_CB(skb); + BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); - *OVS_CB(skb) = ovs_cb; if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) @@ -359,7 +357,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, /* Queue all of the segments. */ skb = segs; do { - *OVS_CB(skb) = ovs_cb; if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index cc3676eb6239..ff4a91fcab9f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb { struct sk_buff *segs; + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) -- cgit v1.2.3