From 0f3a8c3f34f728e7c96651bb7271e1c388c9aac2 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 25 Apr 2016 16:15:51 +0300 Subject: iio: Add support for creating IIO devices via configfs This is similar with support for creating triggers via configfs. Devices will be hosted under: * /config/iio/devices We allow users to register "device types" under: * /config/iio/devices// Signed-off-by: Daniel Baluta Signed-off-by: Jonathan Cameron --- include/linux/iio/sw_device.h | 70 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 include/linux/iio/sw_device.h (limited to 'include') diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h new file mode 100644 index 000000000000..23ca41515527 --- /dev/null +++ b/include/linux/iio/sw_device.h @@ -0,0 +1,70 @@ +/* + * Industrial I/O software device interface + * + * Copyright (c) 2016 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_DEVICE +#define __IIO_SW_DEVICE + +#include +#include +#include +#include + +#define module_iio_sw_device_driver(__iio_sw_device_type) \ + module_driver(__iio_sw_device_type, iio_register_sw_device_type, \ + iio_unregister_sw_device_type) + +struct iio_sw_device_ops; + +struct iio_sw_device_type { + const char *name; + struct module *owner; + const struct iio_sw_device_ops *ops; + struct list_head list; + struct config_group *group; +}; + +struct iio_sw_device { + struct iio_dev *device; + struct iio_sw_device_type *device_type; + struct config_group group; +}; + +struct iio_sw_device_ops { + struct iio_sw_device* (*probe)(const char *); + int (*remove)(struct iio_sw_device *); +}; + +static inline +struct iio_sw_device *to_iio_sw_device(struct config_item *item) +{ + return container_of(to_config_group(item), struct iio_sw_device, + group); +} + +int iio_register_sw_device_type(struct iio_sw_device_type *dt); +void iio_unregister_sw_device_type(struct iio_sw_device_type *dt); + +struct iio_sw_device *iio_sw_device_create(const char *, const char *); +void iio_sw_device_destroy(struct iio_sw_device *); + +int iio_sw_device_type_configfs_register(struct iio_sw_device_type *dt); +void iio_sw_device_type_configfs_unregister(struct iio_sw_device_type *dt); + +static inline +void iio_swd_group_init_type_name(struct iio_sw_device *d, + const char *name, + struct config_item_type *type) +{ +#ifdef CONFIG_CONFIGFS_FS + config_group_init_type_name(&d->group, name, type); +#endif +} + +#endif /* __IIO_SW_DEVICE */ -- cgit v1.2.3 From dfe3ab1af0765eb800da5ce4cb4c685783096d9c Mon Sep 17 00:00:00 2001 From: Gregor Boirie Date: Tue, 19 Apr 2016 11:18:38 +0200 Subject: iio:st_sensors: unexport st_sensors_get_buffer_element Remove st_sensors_get_buffer_element symbol export since not explicitly used outside of st_sensors driver. Signed-off-by: Gregor Boirie Signed-off-by: Jonathan Cameron --- drivers/iio/common/st_sensors/st_sensors_buffer.c | 3 +-- include/linux/iio/common/st_sensors.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index c55898543a47..4ccc438afb5f 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -22,7 +22,7 @@ #include -int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) +static int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) { int i, len; int total = 0; @@ -49,7 +49,6 @@ int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf) return total; } -EXPORT_SYMBOL(st_sensors_get_buffer_element); irqreturn_t st_sensors_trigger_handler(int irq, void *p) { diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index d029ffac0d69..78a193494370 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -251,8 +251,6 @@ struct st_sensor_data { #ifdef CONFIG_IIO_BUFFER irqreturn_t st_sensors_trigger_handler(int irq, void *p); - -int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf); #endif #ifdef CONFIG_IIO_TRIGGER -- cgit v1.2.3 From 14f295c846063c4f1812b09427195cee522aa006 Mon Sep 17 00:00:00 2001 From: Gregor Boirie Date: Tue, 19 Apr 2016 11:18:40 +0200 Subject: iio:st_sensors: fix power regulator usage Ensure failure to enable power regulators is properly handled. Signed-off-by: Gregor Boirie Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 12 ++++++---- drivers/iio/common/st_sensors/st_sensors_core.c | 29 ++++++++++++++++++++----- drivers/iio/gyro/st_gyro_core.c | 12 ++++++---- drivers/iio/magnetometer/st_magn_core.c | 12 ++++++---- drivers/iio/pressure/st_pressure_core.c | 12 ++++++---- include/linux/iio/common/st_sensors.h | 2 +- 6 files changed, 57 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index dc73f2d85e6d..b8d3c3c91b4d 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -757,13 +757,15 @@ int st_accel_common_probe(struct iio_dev *indio_dev) indio_dev->info = &accel_info; mutex_init(&adata->tb.buf_lock); - st_sensors_power_enable(indio_dev); + err = st_sensors_power_enable(indio_dev); + if (err) + return err; err = st_sensors_check_device_support(indio_dev, ARRAY_SIZE(st_accel_sensors_settings), st_accel_sensors_settings); if (err < 0) - return err; + goto st_accel_power_off; adata->num_data_channels = ST_ACCEL_NUMBER_DATA_CHANNELS; adata->multiread_bit = adata->sensor_settings->multi_read_bit; @@ -780,11 +782,11 @@ int st_accel_common_probe(struct iio_dev *indio_dev) err = st_sensors_init_sensor(indio_dev, adata->dev->platform_data); if (err < 0) - return err; + goto st_accel_power_off; err = st_accel_allocate_ring(indio_dev); if (err < 0) - return err; + goto st_accel_power_off; if (irq > 0) { err = st_sensors_allocate_trigger(indio_dev, @@ -807,6 +809,8 @@ st_accel_device_register_error: st_sensors_deallocate_trigger(indio_dev); st_accel_probe_trigger_error: st_accel_deallocate_ring(indio_dev); +st_accel_power_off: + st_sensors_power_disable(indio_dev); return err; } diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index dffe00692169..00078b5fe33c 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -228,7 +228,7 @@ int st_sensors_set_axis_enable(struct iio_dev *indio_dev, u8 axis_enable) } EXPORT_SYMBOL(st_sensors_set_axis_enable); -void st_sensors_power_enable(struct iio_dev *indio_dev) +int st_sensors_power_enable(struct iio_dev *indio_dev) { struct st_sensor_data *pdata = iio_priv(indio_dev); int err; @@ -237,18 +237,37 @@ void st_sensors_power_enable(struct iio_dev *indio_dev) pdata->vdd = devm_regulator_get_optional(indio_dev->dev.parent, "vdd"); if (!IS_ERR(pdata->vdd)) { err = regulator_enable(pdata->vdd); - if (err != 0) + if (err != 0) { dev_warn(&indio_dev->dev, "Failed to enable specified Vdd supply\n"); + return err; + } + } else { + err = PTR_ERR(pdata->vdd); + if (err != -ENODEV) + return err; } pdata->vdd_io = devm_regulator_get_optional(indio_dev->dev.parent, "vddio"); if (!IS_ERR(pdata->vdd_io)) { err = regulator_enable(pdata->vdd_io); - if (err != 0) + if (err != 0) { dev_warn(&indio_dev->dev, "Failed to enable specified Vdd_IO supply\n"); + goto st_sensors_disable_vdd; + } + } else { + err = PTR_ERR(pdata->vdd_io); + if (err != -ENODEV) + goto st_sensors_disable_vdd; } + + return 0; + +st_sensors_disable_vdd: + if (!IS_ERR_OR_NULL(pdata->vdd)) + regulator_disable(pdata->vdd); + return err; } EXPORT_SYMBOL(st_sensors_power_enable); @@ -256,10 +275,10 @@ void st_sensors_power_disable(struct iio_dev *indio_dev) { struct st_sensor_data *pdata = iio_priv(indio_dev); - if (!IS_ERR(pdata->vdd)) + if (!IS_ERR_OR_NULL(pdata->vdd)) regulator_disable(pdata->vdd); - if (!IS_ERR(pdata->vdd_io)) + if (!IS_ERR_OR_NULL(pdata->vdd_io)) regulator_disable(pdata->vdd_io); } EXPORT_SYMBOL(st_sensors_power_disable); diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index 52a3c87c375c..ae1377da9a0b 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -425,13 +425,15 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) indio_dev->info = &gyro_info; mutex_init(&gdata->tb.buf_lock); - st_sensors_power_enable(indio_dev); + err = st_sensors_power_enable(indio_dev); + if (err) + return err; err = st_sensors_check_device_support(indio_dev, ARRAY_SIZE(st_gyro_sensors_settings), st_gyro_sensors_settings); if (err < 0) - return err; + goto st_gyro_power_off; gdata->num_data_channels = ST_GYRO_NUMBER_DATA_CHANNELS; gdata->multiread_bit = gdata->sensor_settings->multi_read_bit; @@ -445,11 +447,11 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) err = st_sensors_init_sensor(indio_dev, (struct st_sensors_platform_data *)&gyro_pdata); if (err < 0) - return err; + goto st_gyro_power_off; err = st_gyro_allocate_ring(indio_dev); if (err < 0) - return err; + goto st_gyro_power_off; if (irq > 0) { err = st_sensors_allocate_trigger(indio_dev, @@ -472,6 +474,8 @@ st_gyro_device_register_error: st_sensors_deallocate_trigger(indio_dev); st_gyro_probe_trigger_error: st_gyro_deallocate_ring(indio_dev); +st_gyro_power_off: + st_sensors_power_disable(indio_dev); return err; } diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 62036d2a9956..7c94adc3ff1d 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -588,13 +588,15 @@ int st_magn_common_probe(struct iio_dev *indio_dev) indio_dev->info = &magn_info; mutex_init(&mdata->tb.buf_lock); - st_sensors_power_enable(indio_dev); + err = st_sensors_power_enable(indio_dev); + if (err) + return err; err = st_sensors_check_device_support(indio_dev, ARRAY_SIZE(st_magn_sensors_settings), st_magn_sensors_settings); if (err < 0) - return err; + goto st_magn_power_off; mdata->num_data_channels = ST_MAGN_NUMBER_DATA_CHANNELS; mdata->multiread_bit = mdata->sensor_settings->multi_read_bit; @@ -607,11 +609,11 @@ int st_magn_common_probe(struct iio_dev *indio_dev) err = st_sensors_init_sensor(indio_dev, NULL); if (err < 0) - return err; + goto st_magn_power_off; err = st_magn_allocate_ring(indio_dev); if (err < 0) - return err; + goto st_magn_power_off; if (irq > 0) { err = st_sensors_allocate_trigger(indio_dev, @@ -634,6 +636,8 @@ st_magn_device_register_error: st_sensors_deallocate_trigger(indio_dev); st_magn_probe_trigger_error: st_magn_deallocate_ring(indio_dev); +st_magn_power_off: + st_sensors_power_disable(indio_dev); return err; } diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index c0ff3bf071d8..4d317af55405 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -527,13 +527,15 @@ int st_press_common_probe(struct iio_dev *indio_dev) indio_dev->info = &press_info; mutex_init(&press_data->tb.buf_lock); - st_sensors_power_enable(indio_dev); + err = st_sensors_power_enable(indio_dev); + if (err) + return err; err = st_sensors_check_device_support(indio_dev, ARRAY_SIZE(st_press_sensors_settings), st_press_sensors_settings); if (err < 0) - return err; + goto st_press_power_off; press_data->num_data_channels = ST_PRESS_NUMBER_DATA_CHANNELS; press_data->multiread_bit = press_data->sensor_settings->multi_read_bit; @@ -554,11 +556,11 @@ int st_press_common_probe(struct iio_dev *indio_dev) err = st_sensors_init_sensor(indio_dev, press_data->dev->platform_data); if (err < 0) - return err; + goto st_press_power_off; err = st_press_allocate_ring(indio_dev); if (err < 0) - return err; + goto st_press_power_off; if (irq > 0) { err = st_sensors_allocate_trigger(indio_dev, @@ -581,6 +583,8 @@ st_press_device_register_error: st_sensors_deallocate_trigger(indio_dev); st_press_probe_trigger_error: st_press_deallocate_ring(indio_dev); +st_press_power_off: + st_sensors_power_disable(indio_dev); return err; } diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 78a193494370..91d5f684a53a 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -278,7 +278,7 @@ int st_sensors_set_enable(struct iio_dev *indio_dev, bool enable); int st_sensors_set_axis_enable(struct iio_dev *indio_dev, u8 axis_enable); -void st_sensors_power_enable(struct iio_dev *indio_dev); +int st_sensors_power_enable(struct iio_dev *indio_dev); void st_sensors_power_disable(struct iio_dev *indio_dev); -- cgit v1.2.3 From 4b9d2090a444d44f16788b9ad60180011d133f97 Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Tue, 24 May 2016 21:29:19 -0700 Subject: iio: electricalconductivity: add IIO_ELECTRICALCONDUCTIVITY type Signed-off-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 7 +++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index df44998e7506..e7f590c6ef8e 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1565,3 +1565,10 @@ Description: * X is in the plane of the propellers, perpendicular to Y axis, and positive towards the starboard side of the UAV ; * Z is perpendicular to propellers plane and positive upwards. + +What: /sys/bus/iio/devices/iio:deviceX/in_electricalconductivity_raw +KernelVersion: 4.8 +Contact: linux-iio@vger.kernel.org +Description: + Raw (unscaled no offset etc.) electric conductivity reading that + can be processed to siemens per meter. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index e6319a9346b2..2a85bd888619 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -80,6 +80,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_RESISTANCE] = "resistance", [IIO_PH] = "ph", [IIO_UVINDEX] = "uvindex", + [IIO_ELECTRICALCONDUCTIVITY] = "electricalconductivity", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index b0916fc72cce..22e5e589a274 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -39,6 +39,7 @@ enum iio_chan_type { IIO_RESISTANCE, IIO_PH, IIO_UVINDEX, + IIO_ELECTRICALCONDUCTIVITY, }; enum iio_modifier { -- cgit v1.2.3 From 97c79a38cd454602645f0470ffb444b3b75ce574 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 28 Apr 2016 13:16:33 -0300 Subject: perf core: Per event callchain limit Additionally to being able to control the system wide maximum depth via /proc/sys/kernel/perf_event_max_stack, now we are able to ask for different depths per event, using perf_event_attr.sample_max_stack for that. This uses an u16 hole at the end of perf_event_attr, that, when perf_event_attr.sample_type has the PERF_SAMPLE_CALLCHAIN, if sample_max_stack is zero, means use perf_event_max_stack, otherwise it'll be bounds checked under callchain_mutex. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Brendan Gregg Cc: David Ahern Cc: Frederic Weisbecker Cc: He Kuang Cc: Jiri Olsa Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Milian Wolff Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: Wang Nan Cc: Zefan Li Link: http://lkml.kernel.org/n/tip-kolmn1yo40p7jhswxwrc7rrd@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 +- include/uapi/linux/perf_event.h | 6 +++++- kernel/bpf/stackmap.c | 2 +- kernel/events/callchain.c | 14 ++++++++++++-- kernel/events/core.c | 5 ++++- 5 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 6b87be908790..0e43355c7aad 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1076,7 +1076,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); -extern int get_callchain_buffers(void); +extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern int sysctl_perf_event_max_stack; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 36ce552cf6a9..c66a485a24ac 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -276,6 +276,9 @@ enum perf_event_read_format { /* * Hardware event_id to monitor via a performance monitoring event: + * + * @sample_max_stack: Max number of frame pointers in a callchain, + * should be < /proc/sys/kernel/perf_event_max_stack */ struct perf_event_attr { @@ -385,7 +388,8 @@ struct perf_event_attr { * Wakeup watermark for AUX area */ __u32 aux_watermark; - __u32 __reserved_2; /* align to __u64 */ + __u16 sample_max_stack; + __u16 __reserved_2; /* align to __u64 */ }; #define perf_flags(attr) (*(&(attr)->read_format + 1)) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index a82d7605db3f..f1de5c1a2af6 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -99,7 +99,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (err) goto free_smap; - err = get_callchain_buffers(); + err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) goto free_smap; diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 179ef4640964..e9fdb5203de5 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -104,7 +104,7 @@ fail: return -ENOMEM; } -int get_callchain_buffers(void) +int get_callchain_buffers(int event_max_stack) { int err = 0; int count; @@ -121,6 +121,15 @@ int get_callchain_buffers(void) /* If the allocation failed, give up */ if (!callchain_cpus_entries) err = -ENOMEM; + /* + * If requesting per event more than the global cap, + * return a different error to help userspace figure + * this out. + * + * And also do it here so that we have &callchain_mutex held. + */ + if (event_max_stack > sysctl_perf_event_max_stack) + err = -EOVERFLOW; goto exit; } @@ -174,11 +183,12 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) bool user = !event->attr.exclude_callchain_user; /* Disallow cross-task user callchains. */ bool crosstask = event->ctx->task && event->ctx->task != current; + const u32 max_stack = event->attr.sample_max_stack; if (!kernel && !user) return NULL; - return get_perf_callchain(regs, 0, kernel, user, sysctl_perf_event_max_stack, crosstask, true); + return get_perf_callchain(regs, 0, kernel, user, max_stack, crosstask, true); } struct perf_callchain_entry * diff --git a/kernel/events/core.c b/kernel/events/core.c index 050a290c72c7..79363f298445 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8843,7 +8843,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, if (!event->parent) { if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { - err = get_callchain_buffers(); + err = get_callchain_buffers(attr->sample_max_stack); if (err) goto err_addr_filters; } @@ -9165,6 +9165,9 @@ SYSCALL_DEFINE5(perf_event_open, return -EINVAL; } + if (!attr.sample_max_stack) + attr.sample_max_stack = sysctl_perf_event_max_stack; + /* * In cgroup mode, the pid argument is used to pass the fd * opened to the cgroup directory in cgroupfs. The cpu argument -- cgit v1.2.3 From 150593bf869393d10a79f6bd3df2585ecc20a9bb Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 18 May 2016 19:02:18 +0200 Subject: sched/api: Introduce task_rcu_dereference() and try_get_task_struct() Generally task_struct is only protected by RCU if it was found on a RCU protected list (say, for_each_process() or find_task_by_vpid()). As Kirill pointed out rq->curr isn't protected by RCU, the scheduler drops the (potentially) last reference without RCU gp, this means that we need to fix the code which uses foreign_rq->curr under rcu_read_lock(). Add a new helper which can be used to dereference rq->curr or any other pointer to task_struct assuming that it should be cleared or updated before the final put_task_struct(). It returns non-NULL only if this task can't go away before rcu_read_unlock(). ( Also add try_get_task_struct() to make it easier to use this API correctly. ) Suggested-by: Kirill Tkhai Signed-off-by: Oleg Nesterov [ Updated comments; added try_get_task_struct()] Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Kirill Tkhai Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vladimir Davydov Link: http://lkml.kernel.org/r/20160518170218.GY3192@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++ kernel/exit.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6e42ada26345..dee41bf59e6b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2139,6 +2139,9 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +struct task_struct *task_rcu_dereference(struct task_struct **ptask); +struct task_struct *try_get_task_struct(struct task_struct **ptask); + #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime); diff --git a/kernel/exit.c b/kernel/exit.c index 9e6e1356e6bb..2fb4d44c51b1 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -210,6 +210,82 @@ repeat: goto repeat; } +/* + * Note that if this function returns a valid task_struct pointer (!NULL) + * task->usage must remain >0 for the duration of the RCU critical section. + */ +struct task_struct *task_rcu_dereference(struct task_struct **ptask) +{ + struct sighand_struct *sighand; + struct task_struct *task; + + /* + * We need to verify that release_task() was not called and thus + * delayed_put_task_struct() can't run and drop the last reference + * before rcu_read_unlock(). We check task->sighand != NULL, + * but we can read the already freed and reused memory. + */ +retry: + task = rcu_dereference(*ptask); + if (!task) + return NULL; + + probe_kernel_address(&task->sighand, sighand); + + /* + * Pairs with atomic_dec_and_test() in put_task_struct(). If this task + * was already freed we can not miss the preceding update of this + * pointer. + */ + smp_rmb(); + if (unlikely(task != READ_ONCE(*ptask))) + goto retry; + + /* + * We've re-checked that "task == *ptask", now we have two different + * cases: + * + * 1. This is actually the same task/task_struct. In this case + * sighand != NULL tells us it is still alive. + * + * 2. This is another task which got the same memory for task_struct. + * We can't know this of course, and we can not trust + * sighand != NULL. + * + * In this case we actually return a random value, but this is + * correct. + * + * If we return NULL - we can pretend that we actually noticed that + * *ptask was updated when the previous task has exited. Or pretend + * that probe_slab_address(&sighand) reads NULL. + * + * If we return the new task (because sighand is not NULL for any + * reason) - this is fine too. This (new) task can't go away before + * another gp pass. + * + * And note: We could even eliminate the false positive if re-read + * task->sighand once again to avoid the falsely NULL. But this case + * is very unlikely so we don't care. + */ + if (!sighand) + return NULL; + + return task; +} + +struct task_struct *try_get_task_struct(struct task_struct **ptask) +{ + struct task_struct *task; + + rcu_read_lock(); + task = task_rcu_dereference(ptask); + if (task) + get_task_struct(task); + rcu_read_unlock(); + + return task; +} + /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected -- cgit v1.2.3 From f2fb6bef92514432398a653df1c2f1041d79ac46 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 23 Mar 2016 11:24:37 -0700 Subject: perf/core: Optimize side-band event delivery The perf_event_aux() function iterates all PMUs and all events in their respective per-CPU contexts to find the events to deliver side-band records to. For example, the brk test case in lkp triggers many mmap() operations, which, if we're also running perf, results in many perf_event_aux() invocations. If we enable uncore PMU support (even when uncore events are not used), dozens of uncore PMUs will be iterated, which can significantly decrease brk_test's throughput. For example, the brk throughput: without uncore PMUs: 2647573 ops_per_sec with uncore PMUs: 1768444 ops_per_sec ... a 33% reduction. To get at the per-CPU events that need side-band records, this patch puts these events on a per-CPU list, this avoids iterating the PMUs and any events that do not need side-band records. Per task events are unchanged to avoid extra overhead on the context switch paths. Suggested-by: Peter Zijlstra (Intel) Reported-by: Huang, Ying Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1458757477-3781-1-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 ++++ kernel/events/core.c | 85 +++++++++++++++++++++++++++++++++++++++------- 2 files changed, 79 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0e43355c7aad..92e9ce737432 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -517,6 +517,11 @@ struct swevent_hlist { struct perf_cgroup; struct ring_buffer; +struct pmu_event_list { + raw_spinlock_t lock; + struct list_head list; +}; + /** * struct perf_event - performance event kernel representation: */ @@ -675,6 +680,7 @@ struct perf_event { int cgrp_defer_enabled; #endif + struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 79363f298445..6615c8922ee3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -335,6 +335,7 @@ static atomic_t perf_sched_count; static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(int, perf_sched_cb_usages); +static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events); static atomic_t nr_mmap_events __read_mostly; static atomic_t nr_comm_events __read_mostly; @@ -3665,6 +3666,26 @@ static void free_event_rcu(struct rcu_head *head) static void ring_buffer_attach(struct perf_event *event, struct ring_buffer *rb); +static void detach_sb_event(struct perf_event *event) +{ + struct pmu_event_list *pel = per_cpu_ptr(&pmu_sb_events, event->cpu); + + raw_spin_lock(&pel->lock); + list_del_rcu(&event->sb_list); + raw_spin_unlock(&pel->lock); +} + +static void unaccount_pmu_sb_event(struct perf_event *event) +{ + if (event->parent) + return; + + if (event->attach_state & PERF_ATTACH_TASK) + return; + + detach_sb_event(event); +} + static void unaccount_event_cpu(struct perf_event *event, int cpu) { if (event->parent) @@ -3728,6 +3749,8 @@ static void unaccount_event(struct perf_event *event) } unaccount_event_cpu(event, event->cpu); + + unaccount_pmu_sb_event(event); } static void perf_sched_delayed(struct work_struct *work) @@ -5888,13 +5911,25 @@ perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data, rcu_read_unlock(); } +static void perf_event_sb_iterate(perf_event_aux_output_cb output, void *data) +{ + struct pmu_event_list *pel = this_cpu_ptr(&pmu_sb_events); + struct perf_event *event; + + list_for_each_entry_rcu(event, &pel->list, sb_list) { + if (event->state < PERF_EVENT_STATE_INACTIVE) + continue; + if (!event_filter_match(event)) + continue; + output(event, data); + } +} + static void perf_event_aux(perf_event_aux_output_cb output, void *data, struct perf_event_context *task_ctx) { - struct perf_cpu_context *cpuctx; struct perf_event_context *ctx; - struct pmu *pmu; int ctxn; /* @@ -5909,20 +5944,15 @@ perf_event_aux(perf_event_aux_output_cb output, void *data, } rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_aux_ctx(&cpuctx->ctx, output, data, false); - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; + preempt_disable(); + perf_event_sb_iterate(output, data); + + for_each_task_context_nr(ctxn) { ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); if (ctx) perf_event_aux_ctx(ctx, output, data, false); -next: - put_cpu_ptr(pmu->pmu_cpu_context); } + preempt_enable(); rcu_read_unlock(); } @@ -8615,6 +8645,32 @@ unlock: return pmu; } +static void attach_sb_event(struct perf_event *event) +{ + struct pmu_event_list *pel = per_cpu_ptr(&pmu_sb_events, event->cpu); + + raw_spin_lock(&pel->lock); + list_add_rcu(&event->sb_list, &pel->list); + raw_spin_unlock(&pel->lock); +} + +static void account_pmu_sb_event(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + + if (event->parent) + return; + + if (event->attach_state & PERF_ATTACH_TASK) + return; + + if (attr->mmap || attr->mmap_data || attr->mmap2 || + attr->comm || attr->comm_exec || + attr->task || + attr->context_switch) + attach_sb_event(event); +} + static void account_event_cpu(struct perf_event *event, int cpu) { if (event->parent) @@ -8695,6 +8751,8 @@ static void account_event(struct perf_event *event) enabled: account_event_cpu(event, event->cpu); + + account_pmu_sb_event(event); } /* @@ -10203,6 +10261,9 @@ static void __init perf_event_init_all_cpus(void) swhash = &per_cpu(swevent_htable, cpu); mutex_init(&swhash->hlist_mutex); INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu)); + + INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu)); + raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu)); } } -- cgit v1.2.3 From fc07e9f983b4b11922c22b6cccadc1f342f05a4c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 19 May 2016 17:09:56 -0700 Subject: perf/x86: Support sysfs files depending on SMT status Add a way to show different sysfs events attributes depending on HyperThreading is on or off. This is difficult to determine early at boot, so we just do it dynamically when the sysfs attribute is read. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: jolsa@kernel.org Link: http://lkml.kernel.org/r/1463703002-19686-3-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 23 +++++++++++++++++++++++ arch/x86/events/perf_event.h | 10 ++++++++++ include/linux/perf_event.h | 7 +++++++ 3 files changed, 40 insertions(+) (limited to 'include') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee817f0..929655db5084 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1622,6 +1622,29 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, cha } EXPORT_SYMBOL_GPL(events_sysfs_show); +ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_ht_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_ht_attr, attr); + + /* + * Report conditional events depending on Hyper-Threading. + * + * This is overly conservative as usually the HT special + * handling is not needed if the other CPU thread is idle. + * + * Note this does not (and cannot) handle the case when thread + * siblings are invisible, for example with virtualization + * if they are owned by some other guest. The user tool + * has to re-read when a thread sibling gets onlined later. + */ + return sprintf(page, "%s", + topology_max_smt_threads() > 1 ? + pmu_attr->event_str_ht : + pmu_attr->event_str_noht); +} + EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); EVENT_ATTR(cache-references, CACHE_REFERENCES ); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 8bd764df815d..e2d7285a2dac 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -668,6 +668,14 @@ static struct perf_pmu_events_attr event_attr_##v = { \ .event_str = str, \ }; +#define EVENT_ATTR_STR_HT(_name, v, noht, ht) \ +static struct perf_pmu_events_ht_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\ + .id = 0, \ + .event_str_noht = noht, \ + .event_str_ht = ht, \ +} + extern struct x86_pmu x86_pmu __read_mostly; static inline bool x86_pmu_has_lbr_callstack(void) @@ -803,6 +811,8 @@ struct attribute **merge_attr(struct attribute **a, struct attribute **b); ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); +ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); #ifdef CONFIG_CPU_SUP_AMD diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 92e9ce737432..a7593d653b40 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1334,6 +1334,13 @@ struct perf_pmu_events_attr { const char *event_str; }; +struct perf_pmu_events_ht_attr { + struct device_attribute attr; + u64 id; + const char *event_str_ht; + const char *event_str_noht; +}; + ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); -- cgit v1.2.3 From ed8ebd1d514126c0e54fbdbd231427dc91c877c2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 May 2016 16:11:57 -0400 Subject: percpu, locking: Revert ("percpu: Replace smp_read_barrier_depends() with lockless_dereference()") lockless_dereference() is planned to grow a sanity check to ensure that the input parameter is a pointer. __ref_is_percpu() passes in an unsinged long value which is a combination of a pointer and a flag. While it can be casted to a pointer lvalue, the casting looks messy and it's a special case anyway. Let's revert back to open-coding READ_ONCE() and explicit barrier. This doesn't cause any functional changes. Signed-off-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul McKenney Cc: Peter Zijlstra Cc: Pranith Kumar Cc: Thomas Gleixner Cc: kernel-team@fb.com Link: http://lkml.kernel.org/g/20160522185040.GA23664@p183.telecom.by Signed-off-by: Ingo Molnar --- include/linux/percpu-refcount.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 84f542df7ff5..1c7eec09e5eb 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -136,14 +136,12 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref, * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that - * ACCESS_ONCE() is required when fetching it. - * - * Also, we need a data dependency barrier to be paired with - * smp_store_release() in __percpu_ref_switch_to_percpu(). - * - * Use lockless deref which contains both. + * READ_ONCE() is required when fetching it. */ - percpu_ptr = lockless_dereference(ref->percpu_count_ptr); + percpu_ptr = READ_ONCE(ref->percpu_count_ptr); + + /* paired with smp_store_release() in __percpu_ref_switch_to_percpu() */ + smp_read_barrier_depends(); /* * Theoretically, the following could test just ATOMIC; however, -- cgit v1.2.3 From 7150bc9b4d43471fa37b26f5839892d4cf1fe09b Mon Sep 17 00:00:00 2001 From: Wenyou Yang Date: Wed, 8 Jun 2016 12:15:10 +0800 Subject: usb: ohci-at91: Forcibly suspend ports while USB suspend In order to the save power consumption, as a workaround, suspend forcibly the USB PORTA/B/C via set the SUSPEND_A/B/C bits of OHCI Interrupt Configuration Register in the SFRs while OHCI USB suspend. This suspend operation must be done before the USB clock is disabled, resume after the USB clock is enabled. Signed-off-by: Wenyou Yang Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/atmel-usb.txt | 6 +- drivers/usb/host/ohci-at91.c | 80 +++++++++++++++++++++- include/soc/at91/at91_sfr.h | 29 ++++++++ 3 files changed, 112 insertions(+), 3 deletions(-) create mode 100644 include/soc/at91/at91_sfr.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/usb/atmel-usb.txt b/Documentation/devicetree/bindings/usb/atmel-usb.txt index 5883b73ea1b5..888deaa8a4ca 100644 --- a/Documentation/devicetree/bindings/usb/atmel-usb.txt +++ b/Documentation/devicetree/bindings/usb/atmel-usb.txt @@ -3,8 +3,10 @@ Atmel SOC USB controllers OHCI Required properties: - - compatible: Should be "atmel,at91rm9200-ohci" for USB controllers - used in host mode. + - compatible: Should be one of the following + "atmel,at91rm9200-ohci" for USB controllers used in host mode. + "atmel,sama5d2-ohci" for USB controllers used in host mode + on SAMA5D2 which can force to suspend. - reg: Address and length of the register set for the device - interrupts: Should contain ehci interrupt - clocks: Should reference the peripheral, host and system clocks diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index d177372bb357..54e8feb8a964 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -21,8 +21,11 @@ #include #include #include +#include +#include #include #include +#include #include "ohci.h" @@ -45,12 +48,18 @@ struct at91_usbh_data { u8 overcurrent_changed[AT91_MAX_USBH_PORTS]; }; +struct ohci_at91_caps { + bool suspend_ctrl; +}; + struct ohci_at91_priv { struct clk *iclk; struct clk *fclk; struct clk *hclk; bool clocked; bool wakeup; /* Saved wake-up state for resume */ + const struct ohci_at91_caps *caps; + struct regmap *sfr_regmap; }; /* interface and function clocks; sometimes also an AHB clock */ @@ -132,6 +141,17 @@ static void at91_stop_hc(struct platform_device *pdev) /*-------------------------------------------------------------------------*/ +struct regmap *at91_dt_syscon_sfr(void) +{ + struct regmap *regmap; + + regmap = syscon_regmap_lookup_by_compatible("atmel,sama5d2-sfr"); + if (IS_ERR(regmap)) + regmap = NULL; + + return regmap; +} + static void usb_hcd_at91_remove (struct usb_hcd *, struct platform_device *); /* configure so an HC device and id are always provided */ @@ -197,6 +217,17 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver, goto err; } + ohci_at91->caps = (const struct ohci_at91_caps *) + of_device_get_match_data(&pdev->dev); + if (!ohci_at91->caps) + return -ENODEV; + + if (ohci_at91->caps->suspend_ctrl) { + ohci_at91->sfr_regmap = at91_dt_syscon_sfr(); + if (!ohci_at91->sfr_regmap) + dev_warn(dev, "failed to find sfr node\n"); + } + board = hcd->self.controller->platform_data; ohci = hcd_to_ohci(hcd); ohci->num_ports = board->ports; @@ -440,8 +471,17 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data) return IRQ_HANDLED; } +static const struct ohci_at91_caps at91rm9200_caps = { + .suspend_ctrl = false, +}; + +static const struct ohci_at91_caps sama5d2_caps = { + .suspend_ctrl = true, +}; + static const struct of_device_id at91_ohci_dt_ids[] = { - { .compatible = "atmel,at91rm9200-ohci" }, + { .compatible = "atmel,at91rm9200-ohci", .data = &at91rm9200_caps }, + { .compatible = "atmel,sama5d2-ohci", .data = &sama5d2_caps }, { /* sentinel */ } }; @@ -581,6 +621,38 @@ static int ohci_hcd_at91_drv_remove(struct platform_device *pdev) return 0; } +static int ohci_at91_port_ctrl(struct regmap *regmap, bool enable) +{ + u32 regval; + int ret; + + if (!regmap) + return -EINVAL; + + ret = regmap_read(regmap, SFR_OHCIICR, ®val); + if (ret) + return ret; + + if (enable) + regval &= ~SFR_OHCIICR_USB_SUSPEND; + else + regval |= SFR_OHCIICR_USB_SUSPEND; + + regmap_write(regmap, SFR_OHCIICR, regval); + + return 0; +} + +static int ohci_at91_port_suspend(struct regmap *regmap) +{ + return ohci_at91_port_ctrl(regmap, false); +} + +static int ohci_at91_port_resume(struct regmap *regmap) +{ + return ohci_at91_port_ctrl(regmap, true); +} + static int __maybe_unused ohci_hcd_at91_drv_suspend(struct device *dev) { @@ -618,6 +690,9 @@ ohci_hcd_at91_drv_suspend(struct device *dev) ohci_writel(ohci, ohci->hc_control, &ohci->regs->control); ohci->rh_state = OHCI_RH_HALTED; + if (ohci_at91->caps->suspend_ctrl) + ohci_at91_port_suspend(ohci_at91->sfr_regmap); + /* flush the writes */ (void) ohci_readl (ohci, &ohci->regs->control); at91_stop_clock(ohci_at91); @@ -637,6 +712,9 @@ ohci_hcd_at91_drv_resume(struct device *dev) at91_start_clock(ohci_at91); + if (ohci_at91->caps->suspend_ctrl) + ohci_at91_port_resume(ohci_at91->sfr_regmap); + ohci_resume(hcd, false); return 0; } diff --git a/include/soc/at91/at91_sfr.h b/include/soc/at91/at91_sfr.h new file mode 100644 index 000000000000..04a3a1eee22e --- /dev/null +++ b/include/soc/at91/at91_sfr.h @@ -0,0 +1,29 @@ +/* + * Header file for the Atmel DDR/SDR SDRAM Controller + * + * Copyright (C) 2016 Atmel Corporation + * + * Author: Wenyou Yang + * + * 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 __AT91_SFR_H__ +#define __AT91_SFR_H__ + +#define SFR_DDRCFG 0x04 /* DDR Configuration Register */ +/* 0x08 ~ 0x0c: Reserved */ +#define SFR_OHCIICR 0x10 /* OHCI Interrupt Configuration Register */ +#define SFR_OHCIISR 0x14 /* OHCI Interrupt Status Register */ + +#define SFR_OHCIICR_SUSPEND_A BIT(8) +#define SFR_OHCIICR_SUSPEND_B BIT(9) +#define SFR_OHCIICR_SUSPEND_C BIT(10) + +#define SFR_OHCIICR_USB_SUSPEND (SFR_OHCIICR_SUSPEND_A | \ + SFR_OHCIICR_SUSPEND_B | \ + SFR_OHCIICR_SUSPEND_C) + +#endif -- cgit v1.2.3 From 331b6d8c7afc2e5b900b9dcd850c265e1ba8d8e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 22 May 2016 12:48:27 +0200 Subject: locking/barriers: Validate lockless_dereference() is used on a pointer type Use the type to validate the argument @p is indeed a pointer type. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Paul McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160522104827.GP3193@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 793c0829e3a3..06f27fd9d760 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -545,10 +545,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * Similar to rcu_dereference(), but for situations where the pointed-to * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. + * + * The seemingly unused void * variable is to validate @p is indeed a pointer + * type. All pointer types silently cast to void *. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ + __maybe_unused const void * const _________p2 = _________p1; \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3 From 8ee62b1870be8e630158701632a533d0378e15b8 Mon Sep 17 00:00:00 2001 From: Jason Low Date: Fri, 3 Jun 2016 22:26:02 -0700 Subject: locking/rwsem: Convert sem->count to 'atomic_long_t' Convert the rwsem count variable to an atomic_long_t since we use it as an atomic variable. This also allows us to remove the rwsem_atomic_{add,update}() "abstraction" which would now be an unnecesary level of indirection. In follow up patches, we also remove the rwsem_atomic_{add,update}() definitions across the various architectures. Suggested-by: Peter Zijlstra Signed-off-by: Jason Low [ Build warning fixes on various architectures. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Davidlohr Bueso Cc: Fenghua Yu Cc: Heiko Carstens Cc: Jason Low Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Paul E. McKenney Cc: Peter Hurley Cc: Terry Rudd Cc: Thomas Gleixner Cc: Tim Chen Cc: Tony Luck Cc: Waiman Long Link: http://lkml.kernel.org/r/1465017963-4839-2-git-send-email-jason.low2@hpe.com Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/rwsem.h | 26 +++++++++++++------------- arch/ia64/include/asm/rwsem.h | 24 ++++++++++++------------ include/asm-generic/rwsem.h | 6 +++--- include/linux/rwsem.h | 8 +++++--- kernel/locking/rwsem-xadd.c | 32 +++++++++++++++++--------------- 5 files changed, 50 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h index 0131a7058778..b40021aabb9f 100644 --- a/arch/alpha/include/asm/rwsem.h +++ b/arch/alpha/include/asm/rwsem.h @@ -25,8 +25,8 @@ static inline void __down_read(struct rw_semaphore *sem) { long oldcount; #ifndef CONFIG_SMP - oldcount = sem->count; - sem->count += RWSEM_ACTIVE_READ_BIAS; + oldcount = sem->count.counter; + sem->count.counter += RWSEM_ACTIVE_READ_BIAS; #else long temp; __asm__ __volatile__( @@ -52,13 +52,13 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) { long old, new, res; - res = sem->count; + res = atomic_long_read(&sem->count); do { new = res + RWSEM_ACTIVE_READ_BIAS; if (new <= 0) break; old = res; - res = cmpxchg(&sem->count, old, new); + res = atomic_long_cmpxchg(&sem->count, old, new); } while (res != old); return res >= 0 ? 1 : 0; } @@ -67,8 +67,8 @@ static inline long ___down_write(struct rw_semaphore *sem) { long oldcount; #ifndef CONFIG_SMP - oldcount = sem->count; - sem->count += RWSEM_ACTIVE_WRITE_BIAS; + oldcount = sem->count.counter; + sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS; #else long temp; __asm__ __volatile__( @@ -106,7 +106,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem) */ static inline int __down_write_trylock(struct rw_semaphore *sem) { - long ret = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); if (ret == RWSEM_UNLOCKED_VALUE) return 1; @@ -117,8 +117,8 @@ static inline void __up_read(struct rw_semaphore *sem) { long oldcount; #ifndef CONFIG_SMP - oldcount = sem->count; - sem->count -= RWSEM_ACTIVE_READ_BIAS; + oldcount = sem->count.counter; + sem->count.counter -= RWSEM_ACTIVE_READ_BIAS; #else long temp; __asm__ __volatile__( @@ -142,8 +142,8 @@ static inline void __up_write(struct rw_semaphore *sem) { long count; #ifndef CONFIG_SMP - sem->count -= RWSEM_ACTIVE_WRITE_BIAS; - count = sem->count; + sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS; + count = sem->count.counter; #else long temp; __asm__ __volatile__( @@ -171,8 +171,8 @@ static inline void __downgrade_write(struct rw_semaphore *sem) { long oldcount; #ifndef CONFIG_SMP - oldcount = sem->count; - sem->count -= RWSEM_WAITING_BIAS; + oldcount = sem->count.counter; + sem->count.counter -= RWSEM_WAITING_BIAS; #else long temp; __asm__ __volatile__( diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h index 8b23e070b844..c5d544f188ed 100644 --- a/arch/ia64/include/asm/rwsem.h +++ b/arch/ia64/include/asm/rwsem.h @@ -40,7 +40,7 @@ static inline void __down_read (struct rw_semaphore *sem) { - long result = ia64_fetchadd8_acq((unsigned long *)&sem->count, 1); + long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1); if (result < 0) rwsem_down_read_failed(sem); @@ -55,9 +55,9 @@ ___down_write (struct rw_semaphore *sem) long old, new; do { - old = sem->count; + old = atomic_long_read(&sem->count); new = old + RWSEM_ACTIVE_WRITE_BIAS; - } while (cmpxchg_acq(&sem->count, old, new) != old); + } while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old); return old; } @@ -85,7 +85,7 @@ __down_write_killable (struct rw_semaphore *sem) static inline void __up_read (struct rw_semaphore *sem) { - long result = ia64_fetchadd8_rel((unsigned long *)&sem->count, -1); + long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1); if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0) rwsem_wake(sem); @@ -100,9 +100,9 @@ __up_write (struct rw_semaphore *sem) long old, new; do { - old = sem->count; + old = atomic_long_read(&sem->count); new = old - RWSEM_ACTIVE_WRITE_BIAS; - } while (cmpxchg_rel(&sem->count, old, new) != old); + } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0) rwsem_wake(sem); @@ -115,8 +115,8 @@ static inline int __down_read_trylock (struct rw_semaphore *sem) { long tmp; - while ((tmp = sem->count) >= 0) { - if (tmp == cmpxchg_acq(&sem->count, tmp, tmp+1)) { + while ((tmp = atomic_long_read(&sem->count)) >= 0) { + if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) { return 1; } } @@ -129,8 +129,8 @@ __down_read_trylock (struct rw_semaphore *sem) static inline int __down_write_trylock (struct rw_semaphore *sem) { - long tmp = cmpxchg_acq(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); + long tmp = atomic_long_cmpxchg_acquire(&sem->count, + RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); return tmp == RWSEM_UNLOCKED_VALUE; } @@ -143,9 +143,9 @@ __downgrade_write (struct rw_semaphore *sem) long old, new; do { - old = sem->count; + old = atomic_long_read(&sem->count); new = old - RWSEM_WAITING_BIAS; - } while (cmpxchg_rel(&sem->count, old, new) != old); + } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); if (old < 0) rwsem_downgrade_wake(sem); diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index 3fc94a046bf5..a3a93eca766c 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -41,8 +41,8 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) { long tmp; - while ((tmp = sem->count) >= 0) { - if (tmp == cmpxchg_acquire(&sem->count, tmp, + while ((tmp = atomic_long_read(&sem->count)) >= 0) { + if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp + RWSEM_ACTIVE_READ_BIAS)) { return 1; } @@ -79,7 +79,7 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) { long tmp; - tmp = cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, + tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); return tmp == RWSEM_UNLOCKED_VALUE; } diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index d37fbb34d06f..dd1d14250340 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -23,10 +23,11 @@ struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK #include /* use a generic implementation */ +#define __RWSEM_INIT_COUNT(name) .count = RWSEM_UNLOCKED_VALUE #else /* All arch specific implementations share the same struct */ struct rw_semaphore { - long count; + atomic_long_t count; struct list_head wait_list; raw_spinlock_t wait_lock; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER @@ -54,9 +55,10 @@ extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) { - return sem->count != 0; + return atomic_long_read(&sem->count) != 0; } +#define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) #endif /* Common initializer macros and functions */ @@ -74,7 +76,7 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) #endif #define __RWSEM_INITIALIZER(name) \ - { .count = RWSEM_UNLOCKED_VALUE, \ + { __RWSEM_INIT_COUNT(name), \ .wait_list = LIST_HEAD_INIT((name).wait_list), \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \ __RWSEM_OPT_INIT(name) \ diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index b957da7fcb19..63b40a5c62ec 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -80,7 +80,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name, debug_check_no_locks_freed((void *)sem, sizeof(*sem)); lockdep_init_map(&sem->dep_map, name, key, 0); #endif - sem->count = RWSEM_UNLOCKED_VALUE; + atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE); raw_spin_lock_init(&sem->wait_lock); INIT_LIST_HEAD(&sem->wait_list); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER @@ -153,10 +153,11 @@ __rwsem_mark_wake(struct rw_semaphore *sem, if (wake_type != RWSEM_WAKE_READ_OWNED) { adjustment = RWSEM_ACTIVE_READ_BIAS; try_reader_grant: - oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; + oldcount = atomic_long_add_return(adjustment, &sem->count) - adjustment; + if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { /* A writer stole the lock. Undo our reader grant. */ - if (rwsem_atomic_update(-adjustment, sem) & + if (atomic_long_sub_return(adjustment, &sem->count) & RWSEM_ACTIVE_MASK) goto out; /* Last active locker left. Retry waking readers. */ @@ -186,7 +187,7 @@ __rwsem_mark_wake(struct rw_semaphore *sem, adjustment -= RWSEM_WAITING_BIAS; if (adjustment) - rwsem_atomic_add(adjustment, sem); + atomic_long_add(adjustment, &sem->count); next = sem->wait_list.next; loop = woken; @@ -233,7 +234,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) list_add_tail(&waiter.list, &sem->wait_list); /* we're now waiting on the lock, but no longer actively locking */ - count = rwsem_atomic_update(adjustment, sem); + count = atomic_long_add_return(adjustment, &sem->count); /* If there are no active locks, wake the front queued process(es). * @@ -282,7 +283,8 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) RWSEM_ACTIVE_WRITE_BIAS : RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS; - if (cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) { + if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count) + == RWSEM_WAITING_BIAS) { rwsem_set_owner(sem); return true; } @@ -296,13 +298,13 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) */ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) { - long old, count = READ_ONCE(sem->count); + long old, count = atomic_long_read(&sem->count); while (true) { if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; - old = cmpxchg_acquire(&sem->count, count, + old = atomic_long_cmpxchg_acquire(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); if (old == count) { rwsem_set_owner(sem); @@ -324,7 +326,7 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) rcu_read_lock(); owner = READ_ONCE(sem->owner); if (!owner) { - long count = READ_ONCE(sem->count); + long count = atomic_long_read(&sem->count); /* * If sem->owner is not set, yet we have just recently entered the * slowpath with the lock being active, then there is a possibility @@ -375,7 +377,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner) * held by readers. Check the counter to verify the * state. */ - count = READ_ONCE(sem->count); + count = atomic_long_read(&sem->count); return (count == 0 || count == RWSEM_WAITING_BIAS); } @@ -460,7 +462,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) WAKE_Q(wake_q); /* undo write bias from down_write operation, stop active locking */ - count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem); + count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count); /* do optimistic spinning and steal lock if possible */ if (rwsem_optimistic_spin(sem)) @@ -483,7 +485,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) /* we're now waiting on the lock, but no longer actively locking */ if (waiting) { - count = READ_ONCE(sem->count); + count = atomic_long_read(&sem->count); /* * If there were already threads queued before us and there are @@ -505,7 +507,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) } } else - count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); + count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count); /* wait until we successfully acquire the lock */ set_current_state(state); @@ -521,7 +523,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) schedule(); set_current_state(state); - } while ((count = sem->count) & RWSEM_ACTIVE_MASK); + } while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK); raw_spin_lock_irq(&sem->wait_lock); } @@ -536,7 +538,7 @@ out_nolock: raw_spin_lock_irq(&sem->wait_lock); list_del(&waiter.list); if (list_empty(&sem->wait_list)) - rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem); + atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count); else __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); -- cgit v1.2.3 From d157bd860f1c828593730dca594d0ce51956833b Mon Sep 17 00:00:00 2001 From: Jason Low Date: Mon, 16 May 2016 17:38:02 -0700 Subject: locking/rwsem: Remove rwsem_atomic_add() and rwsem_atomic_update() The rwsem-xadd count has been converted to an atomic variable and the rwsem code now directly uses atomic_long_add() and atomic_long_add_return(), so we can remove the arch implementations of rwsem_atomic_add() and rwsem_atomic_update(). Signed-off-by: Jason Low Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Arnd Bergmann Cc: Christoph Lameter Cc: Davidlohr Bueso Cc: Fenghua Yu Cc: Heiko Carstens Cc: Ivan Kokshaysky Cc: Jason Low Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Matt Turner Cc: Paul E. McKenney Cc: Peter Hurley Cc: Peter Zijlstra Cc: Richard Henderson Cc: Terry Rudd Cc: Thomas Gleixner Cc: Tim Chen Cc: Tony Luck Cc: Waiman Long Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/rwsem.h | 42 ------------------------------------------ arch/ia64/include/asm/rwsem.h | 7 ------- arch/s390/include/asm/rwsem.h | 37 ------------------------------------- arch/x86/include/asm/rwsem.h | 18 ------------------ include/asm-generic/rwsem.h | 16 ---------------- 5 files changed, 120 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h index b40021aabb9f..77873d0ad293 100644 --- a/arch/alpha/include/asm/rwsem.h +++ b/arch/alpha/include/asm/rwsem.h @@ -191,47 +191,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } -static inline void rwsem_atomic_add(long val, struct rw_semaphore *sem) -{ -#ifndef CONFIG_SMP - sem->count += val; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%2,%0\n" - " stq_c %0,%1\n" - " beq %0,2f\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (temp), "=m" (sem->count) - :"Ir" (val), "m" (sem->count)); -#endif -} - -static inline long rwsem_atomic_update(long val, struct rw_semaphore *sem) -{ -#ifndef CONFIG_SMP - sem->count += val; - return sem->count; -#else - long ret, temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " addq %0,%3,%0\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (ret), "=m" (sem->count), "=&r" (temp) - :"Ir" (val), "m" (sem->count)); - - return ret; -#endif -} - #endif /* __KERNEL__ */ #endif /* _ALPHA_RWSEM_H */ diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h index c5d544f188ed..8fa98dd303b4 100644 --- a/arch/ia64/include/asm/rwsem.h +++ b/arch/ia64/include/asm/rwsem.h @@ -151,11 +151,4 @@ __downgrade_write (struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } -/* - * Implement atomic add functionality. These used to be "inline" functions, but GCC v3.1 - * doesn't quite optimize this stuff right and ends up with bad calls to fetchandadd. - */ -#define rwsem_atomic_add(delta, sem) atomic64_add(delta, (atomic64_t *)(&(sem)->count)) -#define rwsem_atomic_update(delta, sem) atomic64_add_return(delta, (atomic64_t *)(&(sem)->count)) - #endif /* _ASM_IA64_RWSEM_H */ diff --git a/arch/s390/include/asm/rwsem.h b/arch/s390/include/asm/rwsem.h index c75e4471e618..597e7e96b59e 100644 --- a/arch/s390/include/asm/rwsem.h +++ b/arch/s390/include/asm/rwsem.h @@ -207,41 +207,4 @@ static inline void __downgrade_write(struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) -{ - signed long old, new; - - asm volatile( - " lg %0,%2\n" - "0: lgr %1,%0\n" - " agr %1,%4\n" - " csg %0,%1,%2\n" - " jl 0b" - : "=&d" (old), "=&d" (new), "=Q" (sem->count) - : "Q" (sem->count), "d" (delta) - : "cc", "memory"); -} - -/* - * implement exchange and add functionality - */ -static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) -{ - signed long old, new; - - asm volatile( - " lg %0,%2\n" - "0: lgr %1,%0\n" - " agr %1,%4\n" - " csg %0,%1,%2\n" - " jl 0b" - : "=&d" (old), "=&d" (new), "=Q" (sem->count) - : "Q" (sem->count), "d" (delta) - : "cc", "memory"); - return new; -} - #endif /* _S390_RWSEM_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 453744c1d347..089ced4edbbc 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -213,23 +213,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem) : "memory", "cc"); } -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) -{ - asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0" - : "+m" (sem->count) - : "er" (delta)); -} - -/* - * implement exchange and add functionality - */ -static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) -{ - return delta + xadd(&sem->count, delta); -} - #endif /* __KERNEL__ */ #endif /* _ASM_X86_RWSEM_H */ diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h index a3a93eca766c..5be122e3d326 100644 --- a/include/asm-generic/rwsem.h +++ b/include/asm-generic/rwsem.h @@ -106,14 +106,6 @@ static inline void __up_write(struct rw_semaphore *sem) rwsem_wake(sem); } -/* - * implement atomic add functionality - */ -static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) -{ - atomic_long_add(delta, (atomic_long_t *)&sem->count); -} - /* * downgrade write lock to read lock */ @@ -134,13 +126,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem) rwsem_downgrade_wake(sem); } -/* - * implement exchange and add functionality - */ -static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) -{ - return atomic_long_add_return(delta, (atomic_long_t *)&sem->count); -} - #endif /* __KERNEL__ */ #endif /* _ASM_GENERIC_RWSEM_H */ -- cgit v1.2.3 From 6428671bae97caa7040e24e79e969fd87908f4f3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 1 Jun 2016 20:58:15 +0200 Subject: locking/mutex: Optimize mutex_trylock() fast-path A while back Viro posted a number of 'interesting' mutex_is_locked() users on IRC, one of those was RCU. RCU seems to use mutex_is_locked() to avoid doing mutex_trylock(), the regular load before modify pattern. While the use isn't wrong per se, its curious in that its needed at all, mutex_trylock() should be good enough on its own to avoid the pointless cacheline bounces. So fix those and remove the mutex_is_locked() (ab)use from RCU. Reported-by: Al Viro Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paul McKenney Acked-by: Davidlohr Bueso Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Link: http://lkml.kernel.org/r/20160601185815.GW3190@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- arch/ia64/include/asm/mutex.h | 2 +- arch/powerpc/include/asm/mutex.h | 2 +- arch/x86/include/asm/mutex_32.h | 2 +- arch/x86/include/asm/mutex_64.h | 6 +++--- include/asm-generic/mutex-dec.h | 2 +- include/asm-generic/mutex-xchg.h | 6 +++++- kernel/rcu/tree.c | 1 - 7 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/mutex.h b/arch/ia64/include/asm/mutex.h index f41e66d65e31..28cb819e0ff9 100644 --- a/arch/ia64/include/asm/mutex.h +++ b/arch/ia64/include/asm/mutex.h @@ -82,7 +82,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (cmpxchg_acq(count, 1, 0) == 1) + if (atomic_read(count) == 1 && cmpxchg_acq(count, 1, 0) == 1) return 1; return 0; } diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h index 127ab23e1f6c..078155fa1189 100644 --- a/arch/powerpc/include/asm/mutex.h +++ b/arch/powerpc/include/asm/mutex.h @@ -124,7 +124,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1)) + if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1)) return 1; return 0; } diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h index 85e6cda45a02..e9355a84fc67 100644 --- a/arch/x86/include/asm/mutex_32.h +++ b/arch/x86/include/asm/mutex_32.h @@ -101,7 +101,7 @@ static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { /* cmpxchg because it never induces a false contention state. */ - if (likely(atomic_cmpxchg(count, 1, 0) == 1)) + if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) return 1; return 0; diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h index 07537a44216e..d9850758464e 100644 --- a/arch/x86/include/asm/mutex_64.h +++ b/arch/x86/include/asm/mutex_64.h @@ -118,10 +118,10 @@ do { \ static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (likely(atomic_cmpxchg(count, 1, 0) == 1)) + if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) return 1; - else - return 0; + + return 0; } #endif /* _ASM_X86_MUTEX_64_H */ diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h index fd694cfd678a..c54829d3de37 100644 --- a/include/asm-generic/mutex-dec.h +++ b/include/asm-generic/mutex-dec.h @@ -80,7 +80,7 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - if (likely(atomic_cmpxchg_acquire(count, 1, 0) == 1)) + if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1)) return 1; return 0; } diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h index a6b4a7bd6ac9..3269ec4e195f 100644 --- a/include/asm-generic/mutex-xchg.h +++ b/include/asm-generic/mutex-xchg.h @@ -91,8 +91,12 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *)) static inline int __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *)) { - int prev = atomic_xchg_acquire(count, 0); + int prev; + if (atomic_read(count) != 1) + return 0; + + prev = atomic_xchg_acquire(count, 0); if (unlikely(prev < 0)) { /* * The lock was marked contended so we must restore that diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c7f1bc4f817c..b7326893221f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3681,7 +3681,6 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) && (rnp == rnp_root || ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) && - !mutex_is_locked(&rsp->exp_mutex) && mutex_trylock(&rsp->exp_mutex)) goto fastpath; -- cgit v1.2.3 From ca50e426f96c905e7d14a9c7a6bd4e0330516047 Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Fri, 3 Jun 2016 16:38:14 +0800 Subject: locking/qspinlock: Use atomic_sub_return_release() in queued_spin_unlock() The existing version uses a heavy barrier while only release semantics is required. So use atomic_sub_return_release() instead. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arnd@arndb.de Cc: waiman.long@hp.com Link: http://lkml.kernel.org/r/1464943094-3129-1-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/asm-generic/qspinlock.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 05f05f17a7c2..9f0681bf1e87 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -111,10 +111,9 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock) static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* - * smp_mb__before_atomic() in order to guarantee release semantics + * unlock() needs release semantics: */ - smp_mb__before_atomic(); - atomic_sub(_Q_LOCKED_VAL, &lock->val); + (void)atomic_sub_return_release(_Q_LOCKED_VAL, &lock->val); } #endif -- cgit v1.2.3 From 117780eef7740729e803bdcc0d5f2f48137ea8e3 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 8 Jun 2016 12:38:38 -0700 Subject: x86, asm: use bool for bitops and other assembly outputs The gcc people have confirmed that using "bool" when combined with inline assembly always is treated as a byte-sized operand that can be assumed to be 0 or 1, which is exactly what the SET instruction emits. Change the output types and intermediate variables of as many operations as practical to "bool". Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/r/1465414726-197858-3-git-send-email-hpa@linux.intel.com Reviewed-by: Andy Lutomirski Reviewed-by: Borislav Petkov Acked-by: Peter Zijlstra (Intel) --- arch/x86/boot/bitops.h | 8 +++++--- arch/x86/boot/boot.h | 8 ++++---- arch/x86/boot/string.c | 2 +- arch/x86/include/asm/apm.h | 6 +++--- arch/x86/include/asm/archrandom.h | 16 ++++++++-------- arch/x86/include/asm/atomic.h | 8 ++++---- arch/x86/include/asm/atomic64_64.h | 10 +++++----- arch/x86/include/asm/bitops.h | 28 ++++++++++++++-------------- arch/x86/include/asm/local.h | 8 ++++---- arch/x86/include/asm/percpu.h | 8 ++++---- arch/x86/include/asm/rmwcc.h | 4 ++-- arch/x86/include/asm/rwsem.h | 17 +++++++++-------- include/linux/random.h | 12 ++++++------ 13 files changed, 69 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h index 878e4b9940d9..0d41d68131cc 100644 --- a/arch/x86/boot/bitops.h +++ b/arch/x86/boot/bitops.h @@ -16,14 +16,16 @@ #define BOOT_BITOPS_H #define _LINUX_BITOPS_H /* Inhibit inclusion of */ -static inline int constant_test_bit(int nr, const void *addr) +#include + +static inline bool constant_test_bit(int nr, const void *addr) { const u32 *p = (const u32 *)addr; return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0; } -static inline int variable_test_bit(int nr, const void *addr) +static inline bool variable_test_bit(int nr, const void *addr) { - u8 v; + bool v; const u32 *p = (const u32 *)addr; asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr)); diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 9011a88353de..2edb2d53c3a2 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -176,16 +176,16 @@ static inline void wrgs32(u32 v, addr_t addr) } /* Note: these only return true/false, not a signed return value! */ -static inline int memcmp_fs(const void *s1, addr_t s2, size_t len) +static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len) { - u8 diff; + bool diff; asm volatile("fs; repe; cmpsb; setnz %0" : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; } -static inline int memcmp_gs(const void *s1, addr_t s2, size_t len) +static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len) { - u8 diff; + bool diff; asm volatile("gs; repe; cmpsb; setnz %0" : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 318b8465d302..cc3bd583dce1 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -17,7 +17,7 @@ int memcmp(const void *s1, const void *s2, size_t len) { - u8 diff; + bool diff; asm("repe; cmpsb; setnz %0" : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len)); return diff; diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 20370c6db74b..93eebc636c76 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -45,11 +45,11 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, : "memory", "cc"); } -static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, - u32 ecx_in, u32 *eax) +static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, + u32 ecx_in, u32 *eax) { int cx, dx, si; - u8 error; + bool error; /* * N.B. We do NOT need a cld after the BIOS call diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h index 69f1366f1aa3..ab6f599ce2fd 100644 --- a/arch/x86/include/asm/archrandom.h +++ b/arch/x86/include/asm/archrandom.h @@ -43,7 +43,7 @@ #ifdef CONFIG_ARCH_RANDOM /* Instead of arch_get_random_long() when alternatives haven't run. */ -static inline int rdrand_long(unsigned long *v) +static inline bool rdrand_long(unsigned long *v) { int ok; asm volatile("1: " RDRAND_LONG "\n\t" @@ -53,13 +53,13 @@ static inline int rdrand_long(unsigned long *v) "2:" : "=r" (ok), "=a" (*v) : "0" (RDRAND_RETRY_LOOPS)); - return ok; + return !!ok; } /* A single attempt at RDSEED */ static inline bool rdseed_long(unsigned long *v) { - unsigned char ok; + bool ok; asm volatile(RDSEED_LONG "\n\t" "setc %0" : "=qm" (ok), "=a" (*v)); @@ -67,7 +67,7 @@ static inline bool rdseed_long(unsigned long *v) } #define GET_RANDOM(name, type, rdrand, nop) \ -static inline int name(type *v) \ +static inline bool name(type *v) \ { \ int ok; \ alternative_io("movl $0, %0\n\t" \ @@ -80,13 +80,13 @@ static inline int name(type *v) \ X86_FEATURE_RDRAND, \ ASM_OUTPUT2("=r" (ok), "=a" (*v)), \ "0" (RDRAND_RETRY_LOOPS)); \ - return ok; \ + return !!ok; \ } #define GET_SEED(name, type, rdseed, nop) \ -static inline int name(type *v) \ +static inline bool name(type *v) \ { \ - unsigned char ok; \ + bool ok; \ alternative_io("movb $0, %0\n\t" \ nop, \ rdseed "\n\t" \ @@ -119,7 +119,7 @@ GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4); #else -static inline int rdrand_long(unsigned long *v) +static inline bool rdrand_long(unsigned long *v) { return 0; } diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 3e8674288198..17d881248e6c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -75,7 +75,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -static __always_inline int atomic_sub_and_test(int i, atomic_t *v) +static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e"); } @@ -112,7 +112,7 @@ static __always_inline void atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static __always_inline int atomic_dec_and_test(atomic_t *v) +static __always_inline bool atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } @@ -125,7 +125,7 @@ static __always_inline int atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static __always_inline int atomic_inc_and_test(atomic_t *v) +static __always_inline bool atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e"); } @@ -139,7 +139,7 @@ static __always_inline int atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static __always_inline int atomic_add_negative(int i, atomic_t *v) +static __always_inline bool atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s"); } diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 037351022f54..4f881d7f0c39 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -static inline int atomic64_sub_and_test(long i, atomic64_t *v) +static inline bool atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e"); } @@ -109,7 +109,7 @@ static __always_inline void atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline int atomic64_dec_and_test(atomic64_t *v) +static inline bool atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e"); } @@ -122,7 +122,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline int atomic64_inc_and_test(atomic64_t *v) +static inline bool atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e"); } @@ -136,7 +136,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int atomic64_add_negative(long i, atomic64_t *v) +static inline bool atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s"); } @@ -180,7 +180,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new) * Atomically adds @a to @v, so long as it was not @u. * Returns the old value of @v. */ -static inline int atomic64_add_unless(atomic64_t *v, long a, long u) +static inline bool atomic64_add_unless(atomic64_t *v, long a, long u) { long c, old; c = atomic64_read(v); diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index b2b797d1f49a..8cbb7f495546 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c"); } @@ -213,7 +213,7 @@ static __always_inline int test_and_set_bit(long nr, volatile unsigned long *add * * This is the same as test_and_set_bit on x86. */ -static __always_inline int +static __always_inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return test_and_set_bit(nr, addr); @@ -228,9 +228,9 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { - unsigned char oldbit; + bool oldbit; asm("bts %2,%1\n\t" "setc %0" @@ -247,7 +247,7 @@ static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *a * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c"); } @@ -268,9 +268,9 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ -static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { - unsigned char oldbit; + bool oldbit; asm volatile("btr %2,%1\n\t" "setc %0" @@ -280,9 +280,9 @@ static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long } /* WARNING: non atomic and it can be reordered! */ -static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { - unsigned char oldbit; + bool oldbit; asm volatile("btc %2,%1\n\t" "setc %0" @@ -300,20 +300,20 @@ static __always_inline int __test_and_change_bit(long nr, volatile unsigned long * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c"); } -static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } -static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr) +static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { - unsigned char oldbit; + bool oldbit; asm volatile("bt %2,%1\n\t" "setc %0" @@ -329,7 +329,7 @@ static __always_inline int variable_test_bit(long nr, volatile const unsigned lo * @nr: bit number to test * @addr: Address to start counting from */ -static int test_bit(int nr, const volatile unsigned long *addr); +static bool test_bit(int nr, const volatile unsigned long *addr); #endif #define test_bit(nr, addr) \ diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 4ad6560847b1..0cdc65b0d14d 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -50,7 +50,7 @@ static inline void local_sub(long i, local_t *l) * true if the result is zero, or false for all * other cases. */ -static inline int local_sub_and_test(long i, local_t *l) +static inline bool local_sub_and_test(long i, local_t *l) { GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", "e"); } @@ -63,7 +63,7 @@ static inline int local_sub_and_test(long i, local_t *l) * returns true if the result is 0, or false for all other * cases. */ -static inline int local_dec_and_test(local_t *l) +static inline bool local_dec_and_test(local_t *l) { GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e"); } @@ -76,7 +76,7 @@ static inline int local_dec_and_test(local_t *l) * and returns true if the result is zero, or false for all * other cases. */ -static inline int local_inc_and_test(local_t *l) +static inline bool local_inc_and_test(local_t *l) { GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e"); } @@ -90,7 +90,7 @@ static inline int local_inc_and_test(local_t *l) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int local_add_negative(long i, local_t *l) +static inline bool local_add_negative(long i, local_t *l) { GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", "s"); } diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 65039e9571db..184d7f3ecb9f 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -510,14 +510,14 @@ do { \ /* This is not atomic against other CPUs -- CPU preemption needs to be off */ #define x86_test_and_clear_bit_percpu(bit, var) \ ({ \ - unsigned char old__; \ + bool old__; \ asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0" \ : "=qm" (old__), "+m" (var) \ : "dIr" (bit)); \ old__; \ }) -static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr, +static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr, const unsigned long __percpu *addr) { unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG; @@ -529,10 +529,10 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr, #endif } -static inline int x86_this_cpu_variable_test_bit(int nr, +static inline bool x86_this_cpu_variable_test_bit(int nr, const unsigned long __percpu *addr) { - unsigned char oldbit; + bool oldbit; asm volatile("bt "__percpu_arg(2)",%1\n\t" "setc %0" diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 8f7866a5b9a4..a15b73d90be3 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -23,11 +23,11 @@ cc_label: \ #define __GEN_RMWcc(fullop, var, cc, ...) \ do { \ - char c; \ + bool c; \ asm volatile (fullop "; set" cc " %1" \ : "+m" (var), "=qm" (c) \ : __VA_ARGS__ : "memory"); \ - return c != 0; \ + return c; \ } while (0) #define GEN_UNARY_RMWcc(op, var, arg0, cc) \ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 453744c1d347..c5087706c02e 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -77,7 +77,7 @@ static inline void __down_read(struct rw_semaphore *sem) /* * trylock for reading -- returns 1 if successful, 0 if contention */ -static inline int __down_read_trylock(struct rw_semaphore *sem) +static inline bool __down_read_trylock(struct rw_semaphore *sem) { long result, tmp; asm volatile("# beginning __down_read_trylock\n\t" @@ -93,7 +93,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) : "+m" (sem->count), "=&a" (result), "=&r" (tmp) : "i" (RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); - return result >= 0 ? 1 : 0; + return result >= 0; } /* @@ -134,9 +134,10 @@ static inline int __down_write_killable(struct rw_semaphore *sem) /* * trylock for writing -- returns 1 if successful, 0 if contention */ -static inline int __down_write_trylock(struct rw_semaphore *sem) +static inline bool __down_write_trylock(struct rw_semaphore *sem) { - long result, tmp; + bool result; + long tmp0, tmp1; asm volatile("# beginning __down_write_trylock\n\t" " mov %0,%1\n\t" "1:\n\t" @@ -144,14 +145,14 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) /* was the active mask 0 before? */ " jnz 2f\n\t" " mov %1,%2\n\t" - " add %3,%2\n\t" + " add %4,%2\n\t" LOCK_PREFIX " cmpxchg %2,%0\n\t" " jnz 1b\n\t" "2:\n\t" - " sete %b1\n\t" - " movzbl %b1, %k1\n\t" + " sete %3\n\t" "# ending __down_write_trylock\n\t" - : "+m" (sem->count), "=&a" (result), "=&r" (tmp) + : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1), + "=qm" (result) : "er" (RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); return result; diff --git a/include/linux/random.h b/include/linux/random.h index e47e533742b5..3d6e9815cd85 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -95,27 +95,27 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) #ifdef CONFIG_ARCH_RANDOM # include #else -static inline int arch_get_random_long(unsigned long *v) +static inline bool arch_get_random_long(unsigned long *v) { return 0; } -static inline int arch_get_random_int(unsigned int *v) +static inline bool arch_get_random_int(unsigned int *v) { return 0; } -static inline int arch_has_random(void) +static inline bool arch_has_random(void) { return 0; } -static inline int arch_get_random_seed_long(unsigned long *v) +static inline bool arch_get_random_seed_long(unsigned long *v) { return 0; } -static inline int arch_get_random_seed_int(unsigned int *v) +static inline bool arch_get_random_seed_int(unsigned int *v) { return 0; } -static inline int arch_has_random_seed(void) +static inline bool arch_has_random_seed(void) { return 0; } -- cgit v1.2.3 From 830ae442202e314c2bdf7cb4c7cc64d76db0e197 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Tue, 31 May 2016 17:32:30 +0900 Subject: extcon: Remove the deprecated extcon functions This patch removes the deprecated extcon functions using string type to identify the type of external connector. The Commit 2a9de9c0f08d61 ("extcon: Use the unique id for external connector instead of string) uses the unique id to separate the type of external connector instead of string name. - extcon_register_interest() - extcon_unregister_interest() - extcon_set_cable_state() - extcon_get_cable_state() And, extcon_register_interest() finds the first extcon device to include the requested external connector from extcon client device and then register the notifier if extcon device argument is NULL. Instead, extcon_register_notifier() supports this feature. But, this patch remains the deprecatd function definition to prevent the build break. Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon.c | 201 ++++++------------------------------------------ include/linux/extcon.h | 80 ++++++------------- 2 files changed, 47 insertions(+), 234 deletions(-) (limited to 'include') diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 21a123cadf78..4fef9ab4b148 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -127,38 +127,6 @@ static int find_cable_index_by_id(struct extcon_dev *edev, const unsigned int id return -EINVAL; } -static int find_cable_id_by_name(struct extcon_dev *edev, const char *name) -{ - int id = -EINVAL; - int i = 0; - - /* Find the id of extcon cable */ - while (extcon_name[i]) { - if (!strncmp(extcon_name[i], name, CABLE_NAME_MAX)) { - id = i; - break; - } - i++; - } - - return id; -} - -static int find_cable_index_by_name(struct extcon_dev *edev, const char *name) -{ - int id; - - if (edev->max_supported == 0) - return -EINVAL; - - /* Find the the number of extcon cable */ - id = find_cable_id_by_name(edev, name); - if (id < 0) - return id; - - return find_cable_index_by_id(edev, id); -} - static bool is_extcon_changed(u32 prev, u32 new, int idx, bool *attached) { if (((prev >> idx) & 0x1) != ((new >> idx) & 0x1)) { @@ -373,25 +341,6 @@ int extcon_get_cable_state_(struct extcon_dev *edev, const unsigned int id) } EXPORT_SYMBOL_GPL(extcon_get_cable_state_); -/** - * extcon_get_cable_state() - Get the status of a specific cable. - * @edev: the extcon device that has the cable. - * @cable_name: cable name. - * - * Note that this is slower than extcon_get_cable_state_. - */ -int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name) -{ - int id; - - id = find_cable_id_by_name(edev, cable_name); - if (id < 0) - return id; - - return extcon_get_cable_state_(edev, id); -} -EXPORT_SYMBOL_GPL(extcon_get_cable_state); - /** * extcon_set_cable_state_() - Set the status of a specific cable. * @edev: the extcon device that has the cable. @@ -421,28 +370,6 @@ int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, } EXPORT_SYMBOL_GPL(extcon_set_cable_state_); -/** - * extcon_set_cable_state() - Set the status of a specific cable. - * @edev: the extcon device that has the cable. - * @cable_name: cable name. - * @cable_state: the new cable status. The default semantics is - * true: attached / false: detached. - * - * Note that this is slower than extcon_set_cable_state_. - */ -int extcon_set_cable_state(struct extcon_dev *edev, - const char *cable_name, bool cable_state) -{ - int id; - - id = find_cable_id_by_name(edev, cable_name); - if (id < 0) - return id; - - return extcon_set_cable_state_(edev, id, cable_state); -} -EXPORT_SYMBOL_GPL(extcon_set_cable_state); - /** * extcon_get_extcon_dev() - Get the extcon device instance from the name * @extcon_name: The extcon name provided with extcon_dev_register() @@ -466,105 +393,6 @@ out: } EXPORT_SYMBOL_GPL(extcon_get_extcon_dev); -/** - * extcon_register_interest() - Register a notifier for a state change of a - * specific cable, not an entier set of cables of a - * extcon device. - * @obj: an empty extcon_specific_cable_nb object to be returned. - * @extcon_name: the name of extcon device. - * if NULL, extcon_register_interest will register - * every cable with the target cable_name given. - * @cable_name: the target cable name. - * @nb: the notifier block to get notified. - * - * Provide an empty extcon_specific_cable_nb. extcon_register_interest() sets - * the struct for you. - * - * extcon_register_interest is a helper function for those who want to get - * notification for a single specific cable's status change. If a user wants - * to get notification for any changes of all cables of a extcon device, - * he/she should use the general extcon_register_notifier(). - * - * Note that the second parameter given to the callback of nb (val) is - * "old_state", not the current state. The current state can be retrieved - * by looking at the third pameter (edev pointer)'s state value. - */ -int extcon_register_interest(struct extcon_specific_cable_nb *obj, - const char *extcon_name, const char *cable_name, - struct notifier_block *nb) -{ - unsigned long flags; - int ret; - - if (!obj || !cable_name || !nb) - return -EINVAL; - - if (extcon_name) { - obj->edev = extcon_get_extcon_dev(extcon_name); - if (!obj->edev) - return -ENODEV; - - obj->cable_index = find_cable_index_by_name(obj->edev, - cable_name); - if (obj->cable_index < 0) - return obj->cable_index; - - obj->user_nb = nb; - - spin_lock_irqsave(&obj->edev->lock, flags); - ret = raw_notifier_chain_register( - &obj->edev->nh[obj->cable_index], - obj->user_nb); - spin_unlock_irqrestore(&obj->edev->lock, flags); - } else { - struct class_dev_iter iter; - struct extcon_dev *extd; - struct device *dev; - - if (!extcon_class) - return -ENODEV; - class_dev_iter_init(&iter, extcon_class, NULL, NULL); - while ((dev = class_dev_iter_next(&iter))) { - extd = dev_get_drvdata(dev); - - if (find_cable_index_by_name(extd, cable_name) < 0) - continue; - - class_dev_iter_exit(&iter); - return extcon_register_interest(obj, extd->name, - cable_name, nb); - } - - ret = -ENODEV; - } - - return ret; -} -EXPORT_SYMBOL_GPL(extcon_register_interest); - -/** - * extcon_unregister_interest() - Unregister the notifier registered by - * extcon_register_interest(). - * @obj: the extcon_specific_cable_nb object returned by - * extcon_register_interest(). - */ -int extcon_unregister_interest(struct extcon_specific_cable_nb *obj) -{ - unsigned long flags; - int ret; - - if (!obj) - return -EINVAL; - - spin_lock_irqsave(&obj->edev->lock, flags); - ret = raw_notifier_chain_unregister( - &obj->edev->nh[obj->cable_index], obj->user_nb); - spin_unlock_irqrestore(&obj->edev->lock, flags); - - return ret; -} -EXPORT_SYMBOL_GPL(extcon_unregister_interest); - /** * extcon_register_notifier() - Register a notifiee to get notified by * any attach status changes from the extcon. @@ -582,14 +410,33 @@ int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, unsigned long flags; int ret, idx; - if (!edev || !nb) + if (!nb) return -EINVAL; - idx = find_cable_index_by_id(edev, id); + if (edev) { + idx = find_cable_index_by_id(edev, id); - spin_lock_irqsave(&edev->lock, flags); - ret = raw_notifier_chain_register(&edev->nh[idx], nb); - spin_unlock_irqrestore(&edev->lock, flags); + spin_lock_irqsave(&edev->lock, flags); + ret = raw_notifier_chain_register(&edev->nh[idx], nb); + spin_unlock_irqrestore(&edev->lock, flags); + } else { + struct extcon_dev *extd; + + mutex_lock(&extcon_dev_list_lock); + list_for_each_entry(extd, &extcon_dev_list, entry) { + idx = find_cable_index_by_id(extd, id); + if (idx >= 0) + break; + } + mutex_unlock(&extcon_dev_list_lock); + + if (idx >= 0) { + edev = extd; + return extcon_register_notifier(extd, id, nb); + } else { + ret = -ENODEV; + } + } return ret; } diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 7abf674c388c..cec5c543afc6 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -146,22 +146,6 @@ struct extcon_cable { struct attribute *attrs[3]; /* to be fed to attr_g.attrs */ }; -/** - * struct extcon_specific_cable_nb - An internal data for - * extcon_register_interest(). - * @user_nb: user provided notifier block for events from - * a specific cable. - * @cable_index: the target cable. - * @edev: the target extcon device. - * @previous_value: the saved previous event value. - */ -struct extcon_specific_cable_nb { - struct notifier_block *user_nb; - int cable_index; - struct extcon_dev *edev; - unsigned long previous_value; -}; - #if IS_ENABLED(CONFIG_EXTCON) /* @@ -207,23 +191,6 @@ extern int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id); extern int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, bool cable_state); -extern int extcon_get_cable_state(struct extcon_dev *edev, - const char *cable_name); -extern int extcon_set_cable_state(struct extcon_dev *edev, - const char *cable_name, bool cable_state); - -/* - * Following APIs are for notifiees (those who want to be notified) - * to register a callback for events from a specific cable of the extcon. - * Notifiees are the connected device drivers wanting to get notified by - * a specific external port of a connection device. - */ -extern int extcon_register_interest(struct extcon_specific_cable_nb *obj, - const char *extcon_name, - const char *cable_name, - struct notifier_block *nb); -extern int extcon_unregister_interest(struct extcon_specific_cable_nb *nb); - /* * Following APIs are to monitor every action of a notifier. * Registrar gets notified for every external port of a connection device. @@ -246,6 +213,7 @@ extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, /* Following API to get information of extcon device */ extern const char *extcon_get_edev_name(struct extcon_dev *edev); + #else /* CONFIG_EXTCON */ static inline int extcon_dev_register(struct extcon_dev *edev) { @@ -306,18 +274,6 @@ static inline int extcon_set_cable_state_(struct extcon_dev *edev, return 0; } -static inline int extcon_get_cable_state(struct extcon_dev *edev, - const char *cable_name) -{ - return 0; -} - -static inline int extcon_set_cable_state(struct extcon_dev *edev, - const char *cable_name, int state) -{ - return 0; -} - static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { return NULL; @@ -337,24 +293,34 @@ static inline int extcon_unregister_notifier(struct extcon_dev *edev, return 0; } -static inline int extcon_register_interest(struct extcon_specific_cable_nb *obj, - const char *extcon_name, - const char *cable_name, - struct notifier_block *nb) +static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, + int index) { - return 0; + return ERR_PTR(-ENODEV); } +#endif /* CONFIG_EXTCON */ -static inline int extcon_unregister_interest(struct extcon_specific_cable_nb - *obj) +/* + * Following structure and API are deprecated. EXTCON remains the function + * definition to prevent the build break. + */ +struct extcon_specific_cable_nb { + struct notifier_block *user_nb; + int cable_index; + struct extcon_dev *edev; + unsigned long previous_value; +}; + +static inline int extcon_register_interest(struct extcon_specific_cable_nb *obj, + const char *extcon_name, const char *cable_name, + struct notifier_block *nb) { - return 0; + return -EINVAL; } -static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, - int index) +static inline int extcon_unregister_interest(struct extcon_specific_cable_nb + *obj) { - return ERR_PTR(-ENODEV); + return -EINVAL; } -#endif /* CONFIG_EXTCON */ #endif /* __LINUX_EXTCON_H__ */ -- cgit v1.2.3 From 1e2a7d78499ec8859d2b469051b7b80bad3b08aa Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 7 Jun 2016 16:12:28 +0100 Subject: irqdomain: Don't set type when mapping an IRQ Some IRQ chips, such as GPIO controllers or secondary level interrupt controllers, may require require additional runtime power management control to ensure they are accessible. For such IRQ chips, it makes sense to enable the IRQ chip when interrupts are requested and disabled them again once all interrupts have been freed. When mapping an IRQ, the IRQ type settings are read and then programmed. The mapping of the IRQ happens before the IRQ is requested and so the programming of the type settings occurs before the IRQ is requested. This is a problem for IRQ chips that require additional power management control because they may not be accessible yet. Therefore, when mapping the IRQ, don't program the type settings, just save them and then program these saved settings when the IRQ is requested (so long as if they are not overridden via the call to request the IRQ). Add a stub function for irq_domain_free_irqs() to avoid any compilation errors when CONFIG_IRQ_DOMAIN_HIERARCHY is not selected. Signed-off-by: Jon Hunter Reviewed-by: Marc Zyngier Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 3 +++ kernel/irq/irqdomain.c | 23 ++++++++++++++++++----- 2 files changed, 21 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index f1f36e04d885..317503763314 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -452,6 +452,9 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, return -1; } +static inline void irq_domain_free_irqs(unsigned int virq, + unsigned int nr_irqs) { } + static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return false; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index f3ff1eb8dd09..caa6a63d26f0 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -567,6 +567,7 @@ static void of_phandle_args_to_fwspec(struct of_phandle_args *irq_data, unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) { struct irq_domain *domain; + struct irq_data *irq_data; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; int virq; @@ -614,7 +615,11 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) * it now and return the interrupt number. */ if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) { - irq_set_irq_type(virq, type); + irq_data = irq_get_irq_data(virq); + if (!irq_data) + return 0; + + irqd_set_trigger_type(irq_data, type); return virq; } @@ -634,10 +639,18 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) return virq; } - /* Set type if specified and different than the current one */ - if (type != IRQ_TYPE_NONE && - type != irq_get_trigger_type(virq)) - irq_set_irq_type(virq, type); + irq_data = irq_get_irq_data(virq); + if (!irq_data) { + if (irq_domain_is_hierarchy(domain)) + irq_domain_free_irqs(virq, 1); + else + irq_dispose_mapping(virq); + return 0; + } + + /* Store trigger type */ + irqd_set_trigger_type(irq_data, type); + return virq; } EXPORT_SYMBOL_GPL(irq_create_fwspec_mapping); -- cgit v1.2.3 From be45beb2df6909d42a6b3b0052601b3eef878fc0 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 7 Jun 2016 16:12:29 +0100 Subject: genirq: Add runtime power management support for IRQ chips Some IRQ chips may be located in a power domain outside of the CPU subsystem and hence will require device specific runtime power management. In order to support such IRQ chips, add a pointer for a device structure to the irq_chip structure, and if this pointer is populated by the IRQ chip driver and CONFIG_PM is selected in the kernel configuration, then the pm_runtime_get/put APIs for this chip will be called when an IRQ is requested/freed, respectively. Reviewed-by: Kevin Hilman Signed-off-by: Jon Hunter Signed-off-by: Marc Zyngier --- include/linux/irq.h | 4 ++++ kernel/irq/chip.c | 40 ++++++++++++++++++++++++++++++++++++++++ kernel/irq/internals.h | 1 + kernel/irq/manage.c | 31 ++++++++++++++++++++++++++++++- 4 files changed, 75 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4d758a7c604a..6c92a847394d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -315,6 +315,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) /** * struct irq_chip - hardware interrupt chip descriptor * + * @parent_device: pointer to parent device for irqchip * @name: name for /proc/interrupts * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) @@ -354,6 +355,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @flags: chip specific flags */ struct irq_chip { + struct device *parent_device; const char *name; unsigned int (*irq_startup)(struct irq_data *data); void (*irq_shutdown)(struct irq_data *data); @@ -488,6 +490,8 @@ extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); +extern int irq_chip_pm_get(struct irq_data *data); +extern int irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 2f9f2b0e79f2..ad8131473774 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1093,3 +1093,43 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } + +/** + * irq_chip_pm_get - Enable power for an IRQ chip + * @data: Pointer to interrupt specific data + * + * Enable the power to the IRQ chip referenced by the interrupt data + * structure. + */ +int irq_chip_pm_get(struct irq_data *data) +{ + int retval; + + if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) { + retval = pm_runtime_get_sync(data->chip->parent_device); + if (retval < 0) { + pm_runtime_put_noidle(data->chip->parent_device); + return retval; + } + } + + return 0; +} + +/** + * irq_chip_pm_put - Disable power for an IRQ chip + * @data: Pointer to interrupt specific data + * + * Disable the power to the IRQ chip referenced by the interrupt data + * structure, belongs. Note that power will only be disabled, once this + * function has been called for all IRQs that have called irq_chip_pm_get(). + */ +int irq_chip_pm_put(struct irq_data *data) +{ + int retval = 0; + + if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) + retval = pm_runtime_put(data->chip->parent_device); + + return (retval < 0) ? retval : 0; +} diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 09be2c903c6d..d5edcdc9382a 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -7,6 +7,7 @@ */ #include #include +#include #ifdef CONFIG_SPARSE_IRQ # define IRQ_BITMAP_BITS (NR_IRQS + 8196) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f78b0846afb1..00cfc852cca8 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1416,10 +1416,18 @@ int setup_irq(unsigned int irq, struct irqaction *act) if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return -EINVAL; + + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + return retval; + chip_bus_lock(desc); retval = __setup_irq(irq, desc, act); chip_bus_sync_unlock(desc); + if (retval) + irq_chip_pm_put(&desc->irq_data); + return retval; } EXPORT_SYMBOL_GPL(setup_irq); @@ -1513,6 +1521,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) } } + irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); kfree(action->secondary); return action; @@ -1655,11 +1664,16 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, action->name = devname; action->dev_id = dev_id; + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + return retval; + chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); chip_bus_sync_unlock(desc); if (retval) { + irq_chip_pm_put(&desc->irq_data); kfree(action->secondary); kfree(action); } @@ -1836,6 +1850,7 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_ unregister_handler_proc(irq, action); + irq_chip_pm_put(&desc->irq_data); module_put(desc->owner); return action; @@ -1898,10 +1913,18 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) if (!desc || !irq_settings_is_per_cpu_devid(desc)) return -EINVAL; + + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + return retval; + chip_bus_lock(desc); retval = __setup_irq(irq, desc, act); chip_bus_sync_unlock(desc); + if (retval) + irq_chip_pm_put(&desc->irq_data); + return retval; } @@ -1945,12 +1968,18 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, action->name = devname; action->percpu_dev_id = dev_id; + retval = irq_chip_pm_get(&desc->irq_data); + if (retval < 0) + return retval; + chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); chip_bus_sync_unlock(desc); - if (retval) + if (retval) { + irq_chip_pm_put(&desc->irq_data); kfree(action); + } return retval; } -- cgit v1.2.3 From cdbb813db6925f9dcd352841d8ba28f2edd83ff8 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 7 Jun 2016 16:12:32 +0100 Subject: irqchip/gic: Prepare for adding platform driver To support GICs that require runtime power management, it is necessary to add a platform driver, so that the probing of the chip can be deferred if resources, such as a power-domain, is not yet available. To prepare for adding a platform driver: 1. Drop the __init section from the gic_dist_config() so this can be re-used by the platform driver. 2. Add prototypes for functions required by the platform driver to the GIC header file so they can be re-used. Signed-off-by: Jon Hunter Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-common.c | 4 ++-- drivers/irqchip/irq-gic.c | 14 +++++++------- include/linux/irqchip/arm-gic.h | 5 +++++ 3 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index 89e7423f0ebb..9ae71804b5dd 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -90,8 +90,8 @@ int gic_configure_irq(unsigned int irq, unsigned int type, return ret; } -void __init gic_dist_config(void __iomem *base, int gic_irqs, - void (*sync_access)(void)) +void gic_dist_config(void __iomem *base, int gic_irqs, + void (*sync_access)(void)) { unsigned int i; diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 94eab6e23124..141ea5801784 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -449,7 +449,7 @@ static void gic_cpu_if_up(struct gic_chip_data *gic) } -static void __init gic_dist_init(struct gic_chip_data *gic) +static void gic_dist_init(struct gic_chip_data *gic) { unsigned int i; u32 cpumask; @@ -535,7 +535,7 @@ int gic_cpu_if_down(unsigned int gic_nr) * this function, no interrupts will be delivered by the GIC, and another * platform-specific wakeup source must be enabled. */ -static void gic_dist_save(struct gic_chip_data *gic) +void gic_dist_save(struct gic_chip_data *gic) { unsigned int gic_irqs; void __iomem *dist_base; @@ -574,7 +574,7 @@ static void gic_dist_save(struct gic_chip_data *gic) * handled normally, but any edge interrupts that occured will not be seen by * the GIC and need to be handled by the platform-specific wakeup source. */ -static void gic_dist_restore(struct gic_chip_data *gic) +void gic_dist_restore(struct gic_chip_data *gic) { unsigned int gic_irqs; unsigned int i; @@ -620,7 +620,7 @@ static void gic_dist_restore(struct gic_chip_data *gic) writel_relaxed(GICD_ENABLE, dist_base + GIC_DIST_CTRL); } -static void gic_cpu_save(struct gic_chip_data *gic) +void gic_cpu_save(struct gic_chip_data *gic) { int i; u32 *ptr; @@ -650,7 +650,7 @@ static void gic_cpu_save(struct gic_chip_data *gic) } -static void gic_cpu_restore(struct gic_chip_data *gic) +void gic_cpu_restore(struct gic_chip_data *gic) { int i; u32 *ptr; @@ -727,7 +727,7 @@ static struct notifier_block gic_notifier_block = { .notifier_call = gic_notifier, }; -static int __init gic_pm_init(struct gic_chip_data *gic) +static int gic_pm_init(struct gic_chip_data *gic) { gic->saved_ppi_enable = __alloc_percpu(DIV_ROUND_UP(32, 32) * 4, sizeof(u32)); @@ -757,7 +757,7 @@ free_ppi_enable: return -ENOMEM; } #else -static int __init gic_pm_init(struct gic_chip_data *gic) +static int gic_pm_init(struct gic_chip_data *gic) { return 0; } diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index fd051855539b..ffcbd8b9a4ff 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -101,9 +101,14 @@ #include struct device_node; +struct gic_chip_data; void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); int gic_cpu_if_down(unsigned int gic_nr); +void gic_cpu_save(struct gic_chip_data *gic); +void gic_cpu_restore(struct gic_chip_data *gic); +void gic_dist_save(struct gic_chip_data *gic); +void gic_dist_restore(struct gic_chip_data *gic); /* * Subdrivers that need some preparatory work can initialize their -- cgit v1.2.3 From 9c8edddfc9924cb473a7570c37ca466db70728f8 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 7 Jun 2016 16:12:34 +0100 Subject: irqchip/gic: Add platform driver for non-root GICs that require RPM Add a platform driver to support non-root GICs that require runtime power-management. Currently, only non-root GICs are supported because the functions, smp_cross_call() and set_handle_irq(), that need to be called for a root controller are located in the __init section and so cannot be called by the platform driver. The GIC platform driver re-uses many functions from the existing GIC driver including some functions to save and restore the GIC context during power transitions. The functions for saving and restoring the GIC context are currently only defined if CONFIG_CPU_PM is enabled and to ensure that these functions are always defined when the platform driver is enabled, a dependency on CONFIG_ARM_GIC_PM (which selects the platform driver) has been added. In order to re-use the private GIC initialisation code, a new public function, gic_of_init_child(), has been added which calls various private functions to initialise the GIC. This is different from the existing gic_of_init() because it only supports non-root GICs (ie. does not call smp_cross_call() is set_handle_irq()) and is not located in the __init section (so can be used by platform drivers). Furthermore, gic_of_init_child() dynamically allocates memory for the GIC chip data which is also different from gic_of_init(). There is no specific suspend handling for GICs registered as platform devices. Non-wakeup interrupts will be disabled by the kernel during late suspend, however, this alone will not power down the GIC if interrupts have been requested and not freed. Therefore, requestors of non-wakeup interrupts will need to free them on entering suspend in order to power-down the GIC. Signed-off-by: Jon Hunter Signed-off-by: Marc Zyngier --- drivers/irqchip/Kconfig | 6 ++ drivers/irqchip/Makefile | 1 + drivers/irqchip/irq-gic-pm.c | 184 ++++++++++++++++++++++++++++++++++++++++ drivers/irqchip/irq-gic.c | 40 ++++++++- include/linux/irqchip/arm-gic.h | 6 ++ 5 files changed, 233 insertions(+), 4 deletions(-) create mode 100644 drivers/irqchip/irq-gic-pm.c (limited to 'include') diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index fa33c50b0e5a..5495a5ba8039 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -8,6 +8,12 @@ config ARM_GIC select IRQ_DOMAIN_HIERARCHY select MULTI_IRQ_HANDLER +config ARM_GIC_PM + bool + depends on PM + select ARM_GIC + select PM_CLK + config ARM_GIC_MAX_NR int default 2 if ARCH_REALVIEW diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile index 38853a187607..bd0257e0aab6 100644 --- a/drivers/irqchip/Makefile +++ b/drivers/irqchip/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_ARCH_SUNXI) += irq-sun4i.o obj-$(CONFIG_ARCH_SUNXI) += irq-sunxi-nmi.o obj-$(CONFIG_ARCH_SPEAR3XX) += spear-shirq.o obj-$(CONFIG_ARM_GIC) += irq-gic.o irq-gic-common.o +obj-$(CONFIG_ARM_GIC_PM) += irq-gic-pm.o obj-$(CONFIG_REALVIEW_DT) += irq-gic-realview.o obj-$(CONFIG_ARM_GIC_V2M) += irq-gic-v2m.o obj-$(CONFIG_ARM_GIC_V3) += irq-gic-v3.o irq-gic-common.o diff --git a/drivers/irqchip/irq-gic-pm.c b/drivers/irqchip/irq-gic-pm.c new file mode 100644 index 000000000000..4cbffba3ff13 --- /dev/null +++ b/drivers/irqchip/irq-gic-pm.c @@ -0,0 +1,184 @@ +/* + * Copyright (C) 2016 NVIDIA CORPORATION, All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct gic_clk_data { + unsigned int num_clocks; + const char *const *clocks; +}; + +static int gic_runtime_resume(struct device *dev) +{ + struct gic_chip_data *gic = dev_get_drvdata(dev); + int ret; + + ret = pm_clk_resume(dev); + if (ret) + return ret; + + /* + * On the very first resume, the pointer to the driver data + * will be NULL and this is intentional, because we do not + * want to restore the GIC on the very first resume. So if + * the pointer is not valid just return. + */ + if (!gic) + return 0; + + gic_dist_restore(gic); + gic_cpu_restore(gic); + + return 0; +} + +static int gic_runtime_suspend(struct device *dev) +{ + struct gic_chip_data *gic = dev_get_drvdata(dev); + + gic_dist_save(gic); + gic_cpu_save(gic); + + return pm_clk_suspend(dev); +} + +static int gic_get_clocks(struct device *dev, const struct gic_clk_data *data) +{ + struct clk *clk; + unsigned int i; + int ret; + + if (!dev || !data) + return -EINVAL; + + ret = pm_clk_create(dev); + if (ret) + return ret; + + for (i = 0; i < data->num_clocks; i++) { + clk = of_clk_get_by_name(dev->of_node, data->clocks[i]); + if (IS_ERR(clk)) { + dev_err(dev, "failed to get clock %s\n", + data->clocks[i]); + ret = PTR_ERR(clk); + goto error; + } + + ret = pm_clk_add_clk(dev, clk); + if (ret) { + dev_err(dev, "failed to add clock at index %d\n", i); + clk_put(clk); + goto error; + } + } + + return 0; + +error: + pm_clk_destroy(dev); + + return ret; +} + +static int gic_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct gic_clk_data *data; + struct gic_chip_data *gic; + int ret, irq; + + data = of_device_get_match_data(&pdev->dev); + if (!data) { + dev_err(&pdev->dev, "no device match found\n"); + return -ENODEV; + } + + irq = irq_of_parse_and_map(dev->of_node, 0); + if (!irq) { + dev_err(dev, "no parent interrupt found!\n"); + return -EINVAL; + } + + ret = gic_get_clocks(dev, data); + if (ret) + goto irq_dispose; + + pm_runtime_enable(dev); + + ret = pm_runtime_get_sync(dev); + if (ret < 0) + goto rpm_disable; + + ret = gic_of_init_child(dev, &gic, irq); + if (ret) + goto rpm_put; + + platform_set_drvdata(pdev, gic); + + pm_runtime_put(dev); + + dev_info(dev, "GIC IRQ controller registered\n"); + + return 0; + +rpm_put: + pm_runtime_put_sync(dev); +rpm_disable: + pm_runtime_disable(dev); + pm_clk_destroy(dev); +irq_dispose: + irq_dispose_mapping(irq); + + return ret; +} + +static const struct dev_pm_ops gic_pm_ops = { + SET_RUNTIME_PM_OPS(gic_runtime_suspend, + gic_runtime_resume, NULL) +}; + +static const char * const gic400_clocks[] = { + "clk", +}; + +static const struct gic_clk_data gic400_data = { + .num_clocks = ARRAY_SIZE(gic400_clocks), + .clocks = gic400_clocks, +}; + +static const struct of_device_id gic_match[] = { + { .compatible = "nvidia,tegra210-agic", .data = &gic400_data }, + {}, +}; +MODULE_DEVICE_TABLE(of, gic_match); + +static struct platform_driver gic_driver = { + .probe = gic_probe, + .driver = { + .name = "gic", + .of_match_table = gic_match, + .pm = &gic_pm_ops, + } +}; + +builtin_platform_driver(gic_driver); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 141ea5801784..1de07eb5839c 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -75,7 +75,7 @@ struct gic_chip_data { void __iomem *raw_dist_base; void __iomem *raw_cpu_base; u32 percpu_offset; -#ifdef CONFIG_CPU_PM +#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM) u32 saved_spi_enable[DIV_ROUND_UP(1020, 32)]; u32 saved_spi_active[DIV_ROUND_UP(1020, 32)]; u32 saved_spi_conf[DIV_ROUND_UP(1020, 16)]; @@ -528,7 +528,7 @@ int gic_cpu_if_down(unsigned int gic_nr) return 0; } -#ifdef CONFIG_CPU_PM +#if defined(CONFIG_CPU_PM) || defined(CONFIG_ARM_GIC_PM) /* * Saves the GIC distributor registers during suspend or idle. Must be called * with interrupts disabled but before powering down the GIC. After calling @@ -1272,7 +1272,7 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base) return true; } -static int __init gic_of_setup(struct gic_chip_data *gic, struct device_node *node) +static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node) { if (!gic || !node) return -EINVAL; @@ -1296,6 +1296,34 @@ error: return -ENOMEM; } +int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq) +{ + int ret; + + if (!dev || !dev->of_node || !gic || !irq) + return -EINVAL; + + *gic = devm_kzalloc(dev, sizeof(**gic), GFP_KERNEL); + if (!*gic) + return -ENOMEM; + + gic_init_chip(*gic, dev, dev->of_node->name, false); + + ret = gic_of_setup(*gic, dev->of_node); + if (ret) + return ret; + + ret = gic_init_bases(*gic, -1, &dev->of_node->fwnode); + if (ret) { + gic_teardown(*gic); + return ret; + } + + irq_set_chained_handler_and_data(irq, gic_handle_cascade_irq, *gic); + + return 0; +} + static void __init gic_of_setup_kvm_info(struct device_node *node) { int ret; @@ -1375,7 +1403,11 @@ IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init); IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init); IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init); IRQCHIP_DECLARE(pl390, "arm,pl390", gic_of_init); - +#else +int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq) +{ + return -ENOTSUPP; +} #endif #ifdef CONFIG_ACPI diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index ffcbd8b9a4ff..eafc965b3eb8 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -116,6 +116,12 @@ void gic_dist_restore(struct gic_chip_data *gic); */ int gic_of_init(struct device_node *node, struct device_node *parent); +/* + * Initialises and registers a non-root or child GIC chip. Memory for + * the gic_chip_data structure is dynamically allocated. + */ +int gic_of_init_child(struct device *dev, struct gic_chip_data **gic, int irq); + /* * Legacy platforms not converted to DT yet must use this to init * their GIC -- cgit v1.2.3 From 9347359ad0aeeed16bf8c2d4576a2c40edaa9c85 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Mon, 6 Jun 2016 18:17:30 -0500 Subject: irqchip/gicv3-its: Split its_alloc_tables() into two functions The function is getting out of control, it has too many goto statements and would be too complicated for adding a feature two-level device table. So, it is time for us to cleanup and move some of the logic to a separate function without affecting the existing functionality. Signed-off-by: Shanker Donthineni Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 242 +++++++++++++++++++------------------ include/linux/irqchip/arm-gic-v3.h | 1 + 2 files changed, 127 insertions(+), 116 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 5cfa29991eed..146189b1b587 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -56,13 +56,14 @@ struct its_collection { }; /* - * The ITS_BASER structure - contains memory information and cached - * value of BASER register configuration. + * The ITS_BASER structure - contains memory information, cached + * value of BASER register configuration and ITS page size. */ struct its_baser { void *base; u64 val; u32 order; + u32 psz; }; /* @@ -840,6 +841,110 @@ static void its_write_baser(struct its_node *its, struct its_baser *baser, baser->val = its_read_baser(its, baser); } +static int its_setup_baser(struct its_node *its, struct its_baser *baser, + u64 cache, u64 shr, u32 psz, u32 order) +{ + u64 val = its_read_baser(its, baser); + u64 esz = GITS_BASER_ENTRY_SIZE(val); + u64 type = GITS_BASER_TYPE(val); + u32 alloc_pages; + void *base; + u64 tmp; + +retry_alloc_baser: + alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); + if (alloc_pages > GITS_BASER_PAGES_MAX) { + pr_warn("ITS@%pa: %s too large, reduce ITS pages %u->%u\n", + &its->phys_base, its_base_type_string[type], + alloc_pages, GITS_BASER_PAGES_MAX); + alloc_pages = GITS_BASER_PAGES_MAX; + order = get_order(GITS_BASER_PAGES_MAX * psz); + } + + base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!base) + return -ENOMEM; + +retry_baser: + val = (virt_to_phys(base) | + (type << GITS_BASER_TYPE_SHIFT) | + ((esz - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) | + ((alloc_pages - 1) << GITS_BASER_PAGES_SHIFT) | + cache | + shr | + GITS_BASER_VALID); + + switch (psz) { + case SZ_4K: + val |= GITS_BASER_PAGE_SIZE_4K; + break; + case SZ_16K: + val |= GITS_BASER_PAGE_SIZE_16K; + break; + case SZ_64K: + val |= GITS_BASER_PAGE_SIZE_64K; + break; + } + + its_write_baser(its, baser, val); + tmp = baser->val; + + if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) { + /* + * Shareability didn't stick. Just use + * whatever the read reported, which is likely + * to be the only thing this redistributor + * supports. If that's zero, make it + * non-cacheable as well. + */ + shr = tmp & GITS_BASER_SHAREABILITY_MASK; + if (!shr) { + cache = GITS_BASER_nC; + __flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order)); + } + goto retry_baser; + } + + if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) { + /* + * Page size didn't stick. Let's try a smaller + * size and retry. If we reach 4K, then + * something is horribly wrong... + */ + free_pages((unsigned long)base, order); + baser->base = NULL; + + switch (psz) { + case SZ_16K: + psz = SZ_4K; + goto retry_alloc_baser; + case SZ_64K: + psz = SZ_16K; + goto retry_alloc_baser; + } + } + + if (val != tmp) { + pr_err("ITS@%pa: %s doesn't stick: %lx %lx\n", + &its->phys_base, its_base_type_string[type], + (unsigned long) val, (unsigned long) tmp); + free_pages((unsigned long)base, order); + return -ENXIO; + } + + baser->order = order; + baser->base = base; + baser->psz = psz; + + pr_info("ITS@%pa: allocated %d %s @%lx (psz %dK, shr %d)\n", + &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / esz), + its_base_type_string[type], + (unsigned long)virt_to_phys(base), + psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); + + return 0; +} + static void its_parse_baser_device(struct its_node *its, struct its_baser *baser, u32 *order) { @@ -879,25 +984,20 @@ static void its_free_tables(struct its_node *its) static int its_alloc_tables(const char *node_name, struct its_node *its) { - int err; - int i; - int psz = SZ_64K; + u64 typer = readq_relaxed(its->base + GITS_TYPER); + u32 ids = GITS_TYPER_DEVBITS(typer); u64 shr = GITS_BASER_InnerShareable; - u64 cache; - u64 typer; - u32 ids; + u64 cache = GITS_BASER_WaWb; + u32 psz = SZ_64K; + int err, i; if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_22375) { /* - * erratum 22375: only alloc 8MB table size - * erratum 24313: ignore memory access type - */ - cache = 0; - ids = 0x14; /* 20 bits, 8MB */ - } else { - cache = GITS_BASER_WaWb; - typer = readq_relaxed(its->base + GITS_TYPER); - ids = GITS_TYPER_DEVBITS(typer); + * erratum 22375: only alloc 8MB table size + * erratum 24313: ignore memory access type + */ + cache = GITS_BASER_nCnB; + ids = 0x14; /* 20 bits, 8MB */ } its->device_ids = ids; @@ -906,11 +1006,7 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) struct its_baser *baser = its->tables + i; u64 val = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(val); - u64 entry_size = GITS_BASER_ENTRY_SIZE(val); - int order = get_order(psz); - int alloc_pages; - u64 tmp; - void *base; + u32 order = get_order(psz); if (type == GITS_BASER_TYPE_NONE) continue; @@ -918,105 +1014,19 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) if (type == GITS_BASER_TYPE_DEVICE) its_parse_baser_device(its, baser, &order); -retry_alloc_baser: - alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); - if (alloc_pages > GITS_BASER_PAGES_MAX) { - alloc_pages = GITS_BASER_PAGES_MAX; - order = get_order(GITS_BASER_PAGES_MAX * psz); - pr_warn("%s: Device Table too large, reduce its page order to %u (%u pages)\n", - node_name, order, alloc_pages); - } - - base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, order); - if (!base) { - err = -ENOMEM; - goto out_free; - } - - its->tables[i].base = base; - its->tables[i].order = order; - -retry_baser: - val = (virt_to_phys(base) | - (type << GITS_BASER_TYPE_SHIFT) | - ((entry_size - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) | - cache | - shr | - GITS_BASER_VALID); - - switch (psz) { - case SZ_4K: - val |= GITS_BASER_PAGE_SIZE_4K; - break; - case SZ_16K: - val |= GITS_BASER_PAGE_SIZE_16K; - break; - case SZ_64K: - val |= GITS_BASER_PAGE_SIZE_64K; - break; - } - - val |= alloc_pages - 1; - - its_write_baser_cache(its, baser, val); - tmp = baser->val; - - if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) { - /* - * Shareability didn't stick. Just use - * whatever the read reported, which is likely - * to be the only thing this redistributor - * supports. If that's zero, make it - * non-cacheable as well. - */ - shr = tmp & GITS_BASER_SHAREABILITY_MASK; - if (!shr) { - cache = GITS_BASER_nC; - __flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order)); - } - goto retry_baser; - } - - if ((val ^ tmp) & GITS_BASER_PAGE_SIZE_MASK) { - /* - * Page size didn't stick. Let's try a smaller - * size and retry. If we reach 4K, then - * something is horribly wrong... - */ - free_pages((unsigned long)base, order); - its->tables[i].base = NULL; - - switch (psz) { - case SZ_16K: - psz = SZ_4K; - goto retry_alloc_baser; - case SZ_64K: - psz = SZ_16K; - goto retry_alloc_baser; - } - } - - if (val != tmp) { - pr_err("ITS: %s: GITS_BASER%d doesn't stick: %lx %lx\n", - node_name, i, - (unsigned long) val, (unsigned long) tmp); - err = -ENXIO; - goto out_free; + err = its_setup_baser(its, baser, cache, shr, psz, order); + if (err < 0) { + its_free_tables(its); + return err; } - pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n", - (int)(PAGE_ORDER_TO_SIZE(order) / entry_size), - its_base_type_string[type], - (unsigned long)virt_to_phys(base), - psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); + /* Update settings which will be used for next BASERn */ + psz = baser->psz; + cache = baser->val & GITS_BASER_CACHEABILITY_MASK; + shr = baser->val & GITS_BASER_SHAREABILITY_MASK; } return 0; - -out_free: - its_free_tables(its); - - return err; } static int its_alloc_collections(struct its_node *its) diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index dc493e0f0ff7..01cf171ef97d 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -228,6 +228,7 @@ #define GITS_BASER_PAGE_SIZE_64K (2UL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGE_SIZE_MASK (3UL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGES_MAX 256 +#define GITS_BASER_PAGES_SHIFT (0) #define GITS_BASER_TYPE_NONE 0 #define GITS_BASER_TYPE_DEVICE 1 -- cgit v1.2.3 From 3faf24ea894a34887c0ca412f1643540251b9d82 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Mon, 6 Jun 2016 18:17:32 -0500 Subject: irqchip/gicv3-its: Implement two-level(indirect) device table support Since device IDs are extremely sparse, the single, a.k.a flat table is not sufficient for the following two reasons. 1) According to ARM-GIC spec, ITS hw can access maximum of 256(pages)* 64K(pageszie) bytes. In the best case, it supports upto DEVid=21 sparse with minimum device table entry size 8bytes. 2) The maximum memory size that is possible without memblock depends on MAX_ORDER. 4MB on 4K page size kernel with default MAX_ORDER, so it supports DEVid range 19bits. The two-level device table feature brings us two advantages, the first is a very high possibility of supporting upto 32bit sparse, and the second one is the best utilization of memory allocation. The feature is enabled automatically during driver probe if the memory requirement is more than 2*ITS-pages and the hardware is capable of two-level table walk. Signed-off-by: Shanker Donthineni Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 107 +++++++++++++++++++++++++++++++------ include/linux/irqchip/arm-gic-v3.h | 3 ++ 2 files changed, 93 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7afac33e2f9e..7ceaba81efb4 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -842,7 +842,8 @@ static void its_write_baser(struct its_node *its, struct its_baser *baser, } static int its_setup_baser(struct its_node *its, struct its_baser *baser, - u64 cache, u64 shr, u32 psz, u32 order) + u64 cache, u64 shr, u32 psz, u32 order, + bool indirect) { u64 val = its_read_baser(its, baser); u64 esz = GITS_BASER_ENTRY_SIZE(val); @@ -874,6 +875,8 @@ retry_baser: shr | GITS_BASER_VALID); + val |= indirect ? GITS_BASER_INDIRECT : 0x0; + switch (psz) { case SZ_4K: val |= GITS_BASER_PAGE_SIZE_4K; @@ -935,28 +938,55 @@ retry_baser: baser->order = order; baser->base = base; baser->psz = psz; + tmp = indirect ? GITS_LVL1_ENTRY_SIZE : esz; - pr_info("ITS@%pa: allocated %d %s @%lx (psz %dK, shr %d)\n", - &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / esz), + pr_info("ITS@%pa: allocated %d %s @%lx (%s, esz %d, psz %dK, shr %d)\n", + &its->phys_base, (int)(PAGE_ORDER_TO_SIZE(order) / tmp), its_base_type_string[type], (unsigned long)virt_to_phys(base), + indirect ? "indirect" : "flat", (int)esz, psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); return 0; } -static void its_parse_baser_device(struct its_node *its, struct its_baser *baser, - u32 *order) +static bool its_parse_baser_device(struct its_node *its, struct its_baser *baser, + u32 psz, u32 *order) { u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser)); + u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb; u32 ids = its->device_ids; u32 new_order = *order; + bool indirect = false; + + /* No need to enable Indirection if memory requirement < (psz*2)bytes */ + if ((esz << ids) > (psz * 2)) { + /* + * Find out whether hw supports a single or two-level table by + * table by reading bit at offset '62' after writing '1' to it. + */ + its_write_baser(its, baser, val | GITS_BASER_INDIRECT); + indirect = !!(baser->val & GITS_BASER_INDIRECT); + + if (indirect) { + /* + * The size of the lvl2 table is equal to ITS page size + * which is 'psz'. For computing lvl1 table size, + * subtract ID bits that sparse lvl2 table from 'ids' + * which is reported by ITS hardware times lvl1 table + * entry size. + */ + ids -= ilog2(psz / esz); + esz = GITS_LVL1_ENTRY_SIZE; + } + } /* * Allocate as many entries as required to fit the * range of device IDs that the ITS can grok... The ID * space being incredibly sparse, this results in a - * massive waste of memory. + * massive waste of memory if two-level device table + * feature is not supported by hardware. */ new_order = max_t(u32, get_order(esz << ids), new_order); if (new_order >= MAX_ORDER) { @@ -967,6 +997,8 @@ static void its_parse_baser_device(struct its_node *its, struct its_baser *baser } *order = new_order; + + return indirect; } static void its_free_tables(struct its_node *its) @@ -1007,14 +1039,15 @@ static int its_alloc_tables(struct its_node *its) u64 val = its_read_baser(its, baser); u64 type = GITS_BASER_TYPE(val); u32 order = get_order(psz); + bool indirect = false; if (type == GITS_BASER_TYPE_NONE) continue; if (type == GITS_BASER_TYPE_DEVICE) - its_parse_baser_device(its, baser, &order); + indirect = its_parse_baser_device(its, baser, psz, &order); - err = its_setup_baser(its, baser, cache, shr, psz, order); + err = its_setup_baser(its, baser, cache, shr, psz, order, indirect); if (err < 0) { its_free_tables(its); return err; @@ -1214,10 +1247,57 @@ static struct its_baser *its_get_baser(struct its_node *its, u32 type) return NULL; } +static bool its_alloc_device_table(struct its_node *its, u32 dev_id) +{ + struct its_baser *baser; + struct page *page; + u32 esz, idx; + __le64 *table; + + baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE); + + /* Don't allow device id that exceeds ITS hardware limit */ + if (!baser) + return (ilog2(dev_id) < its->device_ids); + + /* Don't allow device id that exceeds single, flat table limit */ + esz = GITS_BASER_ENTRY_SIZE(baser->val); + if (!(baser->val & GITS_BASER_INDIRECT)) + return (dev_id < (PAGE_ORDER_TO_SIZE(baser->order) / esz)); + + /* Compute 1st level table index & check if that exceeds table limit */ + idx = dev_id >> ilog2(baser->psz / esz); + if (idx >= (PAGE_ORDER_TO_SIZE(baser->order) / GITS_LVL1_ENTRY_SIZE)) + return false; + + table = baser->base; + + /* Allocate memory for 2nd level table */ + if (!table[idx]) { + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, get_order(baser->psz)); + if (!page) + return false; + + /* Flush Lvl2 table to PoC if hw doesn't support coherency */ + if (!(baser->val & GITS_BASER_SHAREABILITY_MASK)) + __flush_dcache_area(page_address(page), baser->psz); + + table[idx] = cpu_to_le64(page_to_phys(page) | GITS_BASER_VALID); + + /* Flush Lvl1 entry to PoC if hw doesn't support coherency */ + if (!(baser->val & GITS_BASER_SHAREABILITY_MASK)) + __flush_dcache_area(table + idx, GITS_LVL1_ENTRY_SIZE); + + /* Ensure updated table contents are visible to ITS hardware */ + dsb(sy); + } + + return true; +} + static struct its_device *its_create_device(struct its_node *its, u32 dev_id, int nvecs) { - struct its_baser *baser; struct its_device *dev; unsigned long *lpi_map; unsigned long flags; @@ -1228,14 +1308,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, int nr_ites; int sz; - baser = its_get_baser(its, GITS_BASER_TYPE_DEVICE); - - /* Don't allow 'dev_id' that exceeds single, flat table limit */ - if (baser) { - if (dev_id >= (PAGE_ORDER_TO_SIZE(baser->order) / - GITS_BASER_ENTRY_SIZE(baser->val))) - return NULL; - } else if (ilog2(dev_id) >= its->device_ids) + if (!its_alloc_device_table(its, dev_id)) return NULL; dev = kzalloc(sizeof(*dev), GFP_KERNEL); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 01cf171ef97d..107eed475b94 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -204,6 +204,7 @@ #define GITS_BASER_NR_REGS 8 #define GITS_BASER_VALID (1UL << 63) +#define GITS_BASER_INDIRECT (1UL << 62) #define GITS_BASER_nCnB (0UL << 59) #define GITS_BASER_nC (1UL << 59) #define GITS_BASER_RaWt (2UL << 59) @@ -239,6 +240,8 @@ #define GITS_BASER_TYPE_RESERVED6 6 #define GITS_BASER_TYPE_RESERVED7 7 +#define GITS_LVL1_ENTRY_SIZE (8UL) + /* * ITS commands */ -- cgit v1.2.3 From 2c95afc1e83d93fac3be6923465e1753c2c53b0a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 9 Jun 2016 06:14:38 -0700 Subject: perf/x86/intel, watchdog: Switch NMI watchdog to ref cycles on x86 The NMI watchdog uses either the fixed cycles or a generic cycles counter. This causes a lot of conflicts with users of the PMU who want to run a full group including the cycles fixed counter, for example the --topdown support recently added to perf stat. The code needs to fall back to not use groups, which can cause measurement inaccuracy due to multiplexing errors. This patch switches the NMI watchdog to use reference cycles on Intel systems. This is actually more accurate than cycles, because cycles can tick faster than the measured CPU Frequency due to Turbo mode. The ref cycles always tick at their frequency, or slower when the system is idling. That means the NMI watchdog can never expire too early, unlike with cycles. The reference cycles tick roughly at the frequency of the TSC, so the same period computation can be used. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: jolsa@kernel.org Link: http://lkml.kernel.org/r/1465478079-19993-1-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/hw_nmi.c | 8 ++++++++ include/linux/nmi.h | 1 + kernel/watchdog.c | 7 +++++++ 3 files changed, 16 insertions(+) (limited to 'include') diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 7788ce643bf4..016f4263fad4 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -18,8 +18,16 @@ #include #include #include +#include #ifdef CONFIG_HARDLOCKUP_DETECTOR +int hw_nmi_get_event(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return PERF_COUNT_HW_REF_CPU_CYCLES; + return PERF_COUNT_HW_CPU_CYCLES; +} + u64 hw_nmi_get_sample_period(int watchdog_thresh) { return (u64)(cpu_khz) * 1000 * watchdog_thresh; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 4630eeae18e0..79858af27209 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -66,6 +66,7 @@ static inline bool trigger_allbutself_cpu_backtrace(void) #ifdef CONFIG_LOCKUP_DETECTOR u64 hw_nmi_get_sample_period(int watchdog_thresh); +int hw_nmi_get_event(void); extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 9acb29f280ec..8dd30fcd91be 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -315,6 +315,12 @@ static int is_softlockup(unsigned long touch_ts) #ifdef CONFIG_HARDLOCKUP_DETECTOR +/* Can be overriden by architecture */ +__weak int hw_nmi_get_event(void) +{ + return PERF_COUNT_HW_CPU_CYCLES; +} + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -604,6 +610,7 @@ static int watchdog_nmi_enable(unsigned int cpu) wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); + wd_attr->config = hw_nmi_get_event(); /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); -- cgit v1.2.3 From 1f03e8d2919270bd6ef64f39a45ce8df8a9f012a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Apr 2016 10:57:12 +0200 Subject: locking/barriers: Replace smp_cond_acquire() with smp_cond_load_acquire() This new form allows using hardware assisted waiting. Some hardware (ARM64 and x86) allow monitoring an address for changes, so by providing a pointer we can use this to replace the cpu_relax() with hardware optimized methods in the future. Requested-by: Will Deacon Suggested-by: Linus Torvalds Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 25 +++++++++++++++++++------ kernel/locking/qspinlock.c | 12 ++++++------ kernel/sched/core.c | 8 ++++---- kernel/sched/sched.h | 2 +- kernel/smp.c | 2 +- 5 files changed, 31 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 06f27fd9d760..2bcaedc0f032 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -305,21 +305,34 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s }) /** - * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering + * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering + * @ptr: pointer to the variable to wait on * @cond: boolean expression to wait for * * Equivalent to using smp_load_acquire() on the condition variable but employs * the control dependency of the wait to reduce the barrier on many platforms. * + * Due to C lacking lambda expressions we load the value of *ptr into a + * pre-named variable @VAL to be used in @cond. + * * The control dependency provides a LOAD->STORE order, the additional RMB * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, * aka. ACQUIRE. */ -#define smp_cond_acquire(cond) do { \ - while (!(cond)) \ - cpu_relax(); \ - smp_rmb(); /* ctrl + rmb := acquire */ \ -} while (0) +#ifndef smp_cond_load_acquire +#define smp_cond_load_acquire(ptr, cond_expr) ({ \ + typeof(ptr) __PTR = (ptr); \ + typeof(*ptr) VAL; \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + cpu_relax(); \ + } \ + smp_rmb(); /* ctrl + rmb := acquire */ \ + VAL; \ +}) +#endif #endif /* __KERNEL__ */ diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 2f9153b183c9..1b8dda90ebfa 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -475,7 +475,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * sequentiality; this is because not all clear_pending_set_locked() * implementations imply full barriers. */ - smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK)); + smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK)); /* * take ownership and clear the pending bit. @@ -562,7 +562,7 @@ queue: * * The PV pv_wait_head_or_lock function, if active, will acquire * the lock and return a non-zero value. So we have to skip the - * smp_cond_acquire() call. As the next PV queue head hasn't been + * smp_cond_load_acquire() call. As the next PV queue head hasn't been * designated yet, there is no way for the locked value to become * _Q_SLOW_VAL. So both the set_locked() and the * atomic_cmpxchg_relaxed() calls will be safe. @@ -573,7 +573,7 @@ queue: if ((val = pv_wait_head_or_lock(lock, node))) goto locked; - smp_cond_acquire(!((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK)); + val = smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_PENDING_MASK)); locked: /* @@ -593,9 +593,9 @@ locked: break; } /* - * The smp_cond_acquire() call above has provided the necessary - * acquire semantics required for locking. At most two - * iterations of this loop may be ran. + * The smp_cond_load_acquire() call above has provided the + * necessary acquire semantics required for locking. At most + * two iterations of this loop may be ran. */ old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL); if (old == val) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 017d5394f5dc..5cd6931cb2cb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1935,7 +1935,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * chain to provide order. Instead we do: * * 1) smp_store_release(X->on_cpu, 0) - * 2) smp_cond_acquire(!X->on_cpu) + * 2) smp_cond_load_acquire(!X->on_cpu) * * Example: * @@ -1946,7 +1946,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * sched-out X * smp_store_release(X->on_cpu, 0); * - * smp_cond_acquire(!X->on_cpu); + * smp_cond_load_acquire(&X->on_cpu, !VAL); * X->state = WAKING * set_task_cpu(X,2) * @@ -1972,7 +1972,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * This means that any means of doing remote wakeups must order the CPU doing * the wakeup against the CPU the task is going to end up running on. This, * however, is already required for the regular Program-Order guarantee above, - * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire). + * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire). * */ @@ -2045,7 +2045,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * This ensures that tasks getting woken will be fully ordered against * their previous state and preserve Program Order. */ - smp_cond_acquire(!p->on_cpu); + smp_cond_load_acquire(&p->on_cpu, !VAL); p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 72f1f3087b04..425bf5ddaa5a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1113,7 +1113,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * In particular, the load of prev->state in finish_task_switch() must * happen before this. * - * Pairs with the smp_cond_acquire() in try_to_wake_up(). + * Pairs with the smp_cond_load_acquire() in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); #endif diff --git a/kernel/smp.c b/kernel/smp.c index 74165443c240..36552beed397 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -107,7 +107,7 @@ void __init call_function_init(void) */ static __always_inline void csd_lock_wait(struct call_single_data *csd) { - smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK)); + smp_cond_load_acquire(&csd->flags, !(VAL & CSD_FLAG_LOCK)); } static __always_inline void csd_lock(struct call_single_data *csd) -- cgit v1.2.3 From 33ac279677dcc2441cb93d8cb9cf7a74df62814d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 24 May 2016 13:17:12 +0200 Subject: locking/barriers: Introduce smp_acquire__after_ctrl_dep() Introduce smp_acquire__after_ctrl_dep(), this construct is not uncommon, but the lack of this barrier is. Use it to better express smp_rmb() uses in WRITE_ONCE(), the IPC semaphore code and the qspinlock code. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 17 ++++++++++++----- ipc/sem.c | 14 ++------------ kernel/locking/qspinlock.c | 2 +- 3 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 2bcaedc0f032..59a7004fc7dd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -304,6 +304,17 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) +/** + * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency + * + * A control dependency provides a LOAD->STORE order, the additional RMB + * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, + * aka. (load)-ACQUIRE. + * + * Architectures that do not do load speculation can have this be barrier(). + */ +#define smp_acquire__after_ctrl_dep() smp_rmb() + /** * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering * @ptr: pointer to the variable to wait on @@ -314,10 +325,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * * Due to C lacking lambda expressions we load the value of *ptr into a * pre-named variable @VAL to be used in @cond. - * - * The control dependency provides a LOAD->STORE order, the additional RMB - * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, - * aka. ACQUIRE. */ #ifndef smp_cond_load_acquire #define smp_cond_load_acquire(ptr, cond_expr) ({ \ @@ -329,7 +336,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s break; \ cpu_relax(); \ } \ - smp_rmb(); /* ctrl + rmb := acquire */ \ + smp_acquire__after_ctrl_dep(); \ VAL; \ }) #endif diff --git a/ipc/sem.c b/ipc/sem.c index b3757ea0694b..84dff3df11a4 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -259,16 +259,6 @@ static void sem_rcu_free(struct rcu_head *head) ipc_rcu_free(head); } -/* - * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they - * are only control barriers. - * The code must pair with spin_unlock(&sem->lock) or - * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient. - * - * smp_rmb() is sufficient, as writes cannot pass the control barrier. - */ -#define ipc_smp_acquire__after_spin_is_unlocked() smp_rmb() - /* * Wait until all currently ongoing simple ops have completed. * Caller must own sem_perm.lock. @@ -292,7 +282,7 @@ static void sem_wait_array(struct sem_array *sma) sem = sma->sem_base + i; spin_unlock_wait(&sem->lock); } - ipc_smp_acquire__after_spin_is_unlocked(); + smp_acquire__after_ctrl_dep(); } /* @@ -350,7 +340,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, * complex_count++; * spin_unlock(sem_perm.lock); */ - ipc_smp_acquire__after_spin_is_unlocked(); + smp_acquire__after_ctrl_dep(); /* * Now repeat the test of complex_count: diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 1b8dda90ebfa..730655533440 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -379,7 +379,7 @@ void queued_spin_unlock_wait(struct qspinlock *lock) cpu_relax(); done: - smp_rmb(); /* CTRL + RMB -> ACQUIRE */ + smp_acquire__after_ctrl_dep(); } EXPORT_SYMBOL(queued_spin_unlock_wait); #endif -- cgit v1.2.3 From 7cb45c0fe9858f92cc264f6bf9d2f6a0e7d3b249 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 1 Jun 2016 19:23:54 +0200 Subject: locking/barriers: Move smp_cond_load_acquire() to asm-generic/barrier.h Since all asm/barrier.h should/must include asm-generic/barrier.h the latter is a good place for generic infrastructure like this. This also allows archs to override the new smp_acquire__after_ctrl_dep(). Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/asm-generic/barrier.h | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/compiler.h | 37 ------------------------------------- 2 files changed, 39 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 1cceca146905..ab7b0bd7d4dd 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -207,5 +207,44 @@ do { \ #define virt_store_release(p, v) __smp_store_release(p, v) #define virt_load_acquire(p) __smp_load_acquire(p) +/** + * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency + * + * A control dependency provides a LOAD->STORE order, the additional RMB + * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, + * aka. (load)-ACQUIRE. + * + * Architectures that do not do load speculation can have this be barrier(). + */ +#ifndef smp_acquire__after_ctrl_dep +#define smp_acquire__after_ctrl_dep() smp_rmb() +#endif + +/** + * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering + * @ptr: pointer to the variable to wait on + * @cond: boolean expression to wait for + * + * Equivalent to using smp_load_acquire() on the condition variable but employs + * the control dependency of the wait to reduce the barrier on many platforms. + * + * Due to C lacking lambda expressions we load the value of *ptr into a + * pre-named variable @VAL to be used in @cond. + */ +#ifndef smp_cond_load_acquire +#define smp_cond_load_acquire(ptr, cond_expr) ({ \ + typeof(ptr) __PTR = (ptr); \ + typeof(*ptr) VAL; \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + cpu_relax(); \ + } \ + smp_acquire__after_ctrl_dep(); \ + VAL; \ +}) +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_GENERIC_BARRIER_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 59a7004fc7dd..2e853b679a5d 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -304,43 +304,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) -/** - * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency - * - * A control dependency provides a LOAD->STORE order, the additional RMB - * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, - * aka. (load)-ACQUIRE. - * - * Architectures that do not do load speculation can have this be barrier(). - */ -#define smp_acquire__after_ctrl_dep() smp_rmb() - -/** - * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering - * @ptr: pointer to the variable to wait on - * @cond: boolean expression to wait for - * - * Equivalent to using smp_load_acquire() on the condition variable but employs - * the control dependency of the wait to reduce the barrier on many platforms. - * - * Due to C lacking lambda expressions we load the value of *ptr into a - * pre-named variable @VAL to be used in @cond. - */ -#ifndef smp_cond_load_acquire -#define smp_cond_load_acquire(ptr, cond_expr) ({ \ - typeof(ptr) __PTR = (ptr); \ - typeof(*ptr) VAL; \ - for (;;) { \ - VAL = READ_ONCE(*__PTR); \ - if (cond_expr) \ - break; \ - cpu_relax(); \ - } \ - smp_acquire__after_ctrl_dep(); \ - VAL; \ -}) -#endif - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 726328d92a42b6d4b76078e2659f43067f82c4e8 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 May 2016 10:35:03 +0200 Subject: locking/spinlock, arch: Update and fix spin_unlock_wait() implementations This patch updates/fixes all spin_unlock_wait() implementations. The update is in semantics; where it previously was only a control dependency, we now upgrade to a full load-acquire to match the store-release from the spin_unlock() we waited on. This ensures that when spin_unlock_wait() returns, we're guaranteed to observe the full critical section we waited on. This fixes a number of spin_unlock_wait() users that (not unreasonably) rely on this. I also fixed a number of ticket lock versions to only wait on the current lock holder, instead of for a full unlock, as this is sufficient. Furthermore; again for ticket locks; I added an smp_rmb() in between the initial ticket load and the spin loop testing the current value because I could not convince myself the address dependency is sufficient, esp. if the loads are of different sizes. I'm more than happy to remove this smp_rmb() again if people are certain the address dependency does indeed work as expected. Note: PPC32 will be fixed independently Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: chris@zankel.net Cc: cmetcalf@mellanox.com Cc: davem@davemloft.net Cc: dhowells@redhat.com Cc: james.hogan@imgtec.com Cc: jejb@parisc-linux.org Cc: linux@armlinux.org.uk Cc: mpe@ellerman.id.au Cc: ralf@linux-mips.org Cc: realmz6@gmail.com Cc: rkuo@codeaurora.org Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: vgupta@synopsys.com Cc: ysato@users.sourceforge.jp Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/spinlock.h | 9 +++++++-- arch/arc/include/asm/spinlock.h | 7 +++++-- arch/arm/include/asm/spinlock.h | 19 +++++++++++++++++-- arch/blackfin/include/asm/spinlock.h | 5 +++-- arch/hexagon/include/asm/spinlock.h | 10 ++++++++-- arch/ia64/include/asm/spinlock.h | 4 ++++ arch/m32r/include/asm/spinlock.h | 9 +++++++-- arch/metag/include/asm/spinlock.h | 14 ++++++++++++-- arch/mips/include/asm/spinlock.h | 19 +++++++++++++++++-- arch/mn10300/include/asm/spinlock.h | 8 +++++++- arch/parisc/include/asm/spinlock.h | 9 +++++++-- arch/s390/include/asm/spinlock.h | 3 +++ arch/sh/include/asm/spinlock.h | 10 ++++++++-- arch/sparc/include/asm/spinlock_32.h | 7 +++++-- arch/sparc/include/asm/spinlock_64.h | 10 +++++++--- arch/tile/lib/spinlock_32.c | 6 ++++++ arch/tile/lib/spinlock_64.c | 6 ++++++ arch/xtensa/include/asm/spinlock.h | 10 ++++++++-- include/asm-generic/barrier.h | 2 +- include/linux/spinlock_up.h | 10 +++++++--- 20 files changed, 145 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h index fed9c6f44c19..a40b9fc0c6c3 100644 --- a/arch/alpha/include/asm/spinlock.h +++ b/arch/alpha/include/asm/spinlock.h @@ -3,6 +3,8 @@ #include #include +#include +#include /* * Simple spin lock operations. There are two variants, one clears IRQ's @@ -13,8 +15,11 @@ #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #define arch_spin_is_locked(x) ((x)->lock != 0) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while ((x)->lock) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline int arch_spin_value_unlocked(arch_spinlock_t lock) { diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index cded4a9b5438..233d5ffe6ec7 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -15,8 +15,11 @@ #define arch_spin_is_locked(x) ((x)->slock != __ARCH_SPIN_LOCK_UNLOCKED__) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} #ifdef CONFIG_ARC_HAS_LLSC diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index 0fa418463f49..4bec45442072 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -6,6 +6,8 @@ #endif #include +#include +#include /* * sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K @@ -50,8 +52,21 @@ static inline void dsb_sev(void) * memory. */ -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + u16 owner = READ_ONCE(lock->tickets.owner); + + for (;;) { + arch_spinlock_t tmp = READ_ONCE(*lock); + + if (tmp.tickets.owner == tmp.tickets.next || + tmp.tickets.owner != owner) + break; + + wfe(); + } + smp_acquire__after_ctrl_dep(); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/blackfin/include/asm/spinlock.h b/arch/blackfin/include/asm/spinlock.h index 490c7caa02d9..c58f4a83ed6f 100644 --- a/arch/blackfin/include/asm/spinlock.h +++ b/arch/blackfin/include/asm/spinlock.h @@ -12,6 +12,8 @@ #else #include +#include +#include asmlinkage int __raw_spin_is_locked_asm(volatile int *ptr); asmlinkage void __raw_spin_lock_asm(volatile int *ptr); @@ -48,8 +50,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { - while (arch_spin_is_locked(lock)) - cpu_relax(); + smp_cond_load_acquire(&lock->lock, !VAL); } static inline int arch_read_can_lock(arch_rwlock_t *rw) diff --git a/arch/hexagon/include/asm/spinlock.h b/arch/hexagon/include/asm/spinlock.h index 12ca4ebc0338..a1c55788c5d6 100644 --- a/arch/hexagon/include/asm/spinlock.h +++ b/arch/hexagon/include/asm/spinlock.h @@ -23,6 +23,8 @@ #define _ASM_SPINLOCK_H #include +#include +#include /* * This file is pulled in for SMP builds. @@ -176,8 +178,12 @@ static inline unsigned int arch_spin_trylock(arch_spinlock_t *lock) * SMP spinlocks are intended to allow only a single CPU at the lock */ #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(lock) \ - do {while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} + #define arch_spin_is_locked(x) ((x)->lock != 0) #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 45698cd15b7b..ca9e76149a4a 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -15,6 +15,8 @@ #include #include +#include +#include #define arch_spin_lock_init(x) ((x)->lock = 0) @@ -86,6 +88,8 @@ static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock) return; cpu_relax(); } + + smp_acquire__after_ctrl_dep(); } static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) diff --git a/arch/m32r/include/asm/spinlock.h b/arch/m32r/include/asm/spinlock.h index fa13694eaae3..323c7fc953cd 100644 --- a/arch/m32r/include/asm/spinlock.h +++ b/arch/m32r/include/asm/spinlock.h @@ -13,6 +13,8 @@ #include #include #include +#include +#include /* * Your basic SMP spinlocks, allowing only a single CPU anywhere @@ -27,8 +29,11 @@ #define arch_spin_is_locked(x) (*(volatile int *)(&(x)->slock) <= 0) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, VAL > 0); +} /** * arch_spin_trylock - Try spin lock and return a result diff --git a/arch/metag/include/asm/spinlock.h b/arch/metag/include/asm/spinlock.h index 86a7cf3d1386..c0c7a22be1ae 100644 --- a/arch/metag/include/asm/spinlock.h +++ b/arch/metag/include/asm/spinlock.h @@ -1,14 +1,24 @@ #ifndef __ASM_SPINLOCK_H #define __ASM_SPINLOCK_H +#include +#include + #ifdef CONFIG_METAG_ATOMICITY_LOCK1 #include #else #include #endif -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +/* + * both lock1 and lnkget are test-and-set spinlocks with 0 unlocked and 1 + * locked. + */ + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h index 40196bebe849..f485afe51514 100644 --- a/arch/mips/include/asm/spinlock.h +++ b/arch/mips/include/asm/spinlock.h @@ -12,6 +12,7 @@ #include #include +#include #include #include @@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) } #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - while (arch_spin_is_locked(x)) { cpu_relax(); } + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + u16 owner = READ_ONCE(lock->h.serving_now); + smp_rmb(); + for (;;) { + arch_spinlock_t tmp = READ_ONCE(*lock); + + if (tmp.h.serving_now == tmp.h.ticket || + tmp.h.serving_now != owner) + break; + + cpu_relax(); + } + smp_acquire__after_ctrl_dep(); +} static inline int arch_spin_is_contended(arch_spinlock_t *lock) { diff --git a/arch/mn10300/include/asm/spinlock.h b/arch/mn10300/include/asm/spinlock.h index 1ae580f38933..9c7b8f7942d8 100644 --- a/arch/mn10300/include/asm/spinlock.h +++ b/arch/mn10300/include/asm/spinlock.h @@ -12,6 +12,8 @@ #define _ASM_SPINLOCK_H #include +#include +#include #include #include @@ -23,7 +25,11 @@ */ #define arch_spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) != 0) -#define arch_spin_unlock_wait(x) do { barrier(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} static inline void arch_spin_unlock(arch_spinlock_t *lock) { diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index 64f2992e439f..e32936cd7f10 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -13,8 +13,13 @@ static inline int arch_spin_is_locked(arch_spinlock_t *x) } #define arch_spin_lock(lock) arch_spin_lock_flags(lock, 0) -#define arch_spin_unlock_wait(x) \ - do { cpu_relax(); } while (arch_spin_is_locked(x)) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *x) +{ + volatile unsigned int *a = __ldcw_align(x); + + smp_cond_load_acquire(a, VAL); +} static inline void arch_spin_lock_flags(arch_spinlock_t *x, unsigned long flags) diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 63ebf37d3143..7e9e09f600fa 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -10,6 +10,8 @@ #define __ASM_SPINLOCK_H #include +#include +#include #define SPINLOCK_LOCKVAL (S390_lowcore.spinlock_lockval) @@ -97,6 +99,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { while (arch_spin_is_locked(lock)) arch_spin_relax(lock); + smp_acquire__after_ctrl_dep(); } /* diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h index bdc0f3b6c56a..416834b60ad0 100644 --- a/arch/sh/include/asm/spinlock.h +++ b/arch/sh/include/asm/spinlock.h @@ -19,14 +19,20 @@ #error "Need movli.l/movco.l for spinlocks" #endif +#include +#include + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere */ #define arch_spin_is_locked(x) ((x)->lock <= 0) #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#define arch_spin_unlock_wait(x) \ - do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, VAL > 0); +} /* * Simple spin lock operations. There are two variants, one clears IRQ's diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index bcc98fc35281..d9c5876c6121 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -9,12 +9,15 @@ #ifndef __ASSEMBLY__ #include +#include #include /* for cpu_relax */ #define arch_spin_is_locked(lock) (*((volatile unsigned char *)(lock)) != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 968917694978..87990b7c6b0d 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -8,6 +8,9 @@ #ifndef __ASSEMBLY__ +#include +#include + /* To get debugging spinlocks which detect and catch * deadlock situations, set CONFIG_DEBUG_SPINLOCK * and rebuild your kernel. @@ -23,9 +26,10 @@ #define arch_spin_is_locked(lp) ((lp)->lock != 0) -#define arch_spin_unlock_wait(lp) \ - do { rmb(); \ - } while((lp)->lock) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->lock, !VAL); +} static inline void arch_spin_lock(arch_spinlock_t *lock) { diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c index 88c2a53362e7..076c6cc43113 100644 --- a/arch/tile/lib/spinlock_32.c +++ b/arch/tile/lib/spinlock_32.c @@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock) do { delay_backoff(iterations++); } while (READ_ONCE(lock->current_ticket) == curr); + + /* + * The TILE architecture doesn't do read speculation; therefore + * a control dependency guarantees a LOAD->{LOAD,STORE} order. + */ + barrier(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c index c8d1f94ff1fe..a4b5b2cbce93 100644 --- a/arch/tile/lib/spinlock_64.c +++ b/arch/tile/lib/spinlock_64.c @@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock) do { delay_backoff(iterations++); } while (arch_spin_current(READ_ONCE(lock->lock)) == curr); + + /* + * The TILE architecture doesn't do read speculation; therefore + * a control dependency guarantees a LOAD->{LOAD,STORE} order. + */ + barrier(); } EXPORT_SYMBOL(arch_spin_unlock_wait); diff --git a/arch/xtensa/include/asm/spinlock.h b/arch/xtensa/include/asm/spinlock.h index 1d95fa5dcd10..a36221cf6363 100644 --- a/arch/xtensa/include/asm/spinlock.h +++ b/arch/xtensa/include/asm/spinlock.h @@ -11,6 +11,9 @@ #ifndef _XTENSA_SPINLOCK_H #define _XTENSA_SPINLOCK_H +#include +#include + /* * spinlock * @@ -29,8 +32,11 @@ */ #define arch_spin_is_locked(x) ((x)->slock != 0) -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, !VAL); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index ab7b0bd7d4dd..fe297b599b0a 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -194,7 +194,7 @@ do { \ }) #endif -#endif +#endif /* CONFIG_SMP */ /* Barriers for virtual machine guests when talking to an SMP host */ #define virt_mb() __smp_mb() diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 8b3ac0d718eb..0d9848de677d 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -6,6 +6,7 @@ #endif #include /* for cpu_relax() */ +#include /* * include/linux/spinlock_up.h - UP-debug version of spinlocks. @@ -25,6 +26,11 @@ #ifdef CONFIG_DEBUG_SPINLOCK #define arch_spin_is_locked(x) ((x)->slock == 0) +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + smp_cond_load_acquire(&lock->slock, VAL); +} + static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; @@ -67,6 +73,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) +#define arch_spin_unlock_wait(lock) do { barrier(); (void)(lock); } while (0) /* for sched/core.c and kernel_lock.c: */ # define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) # define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) @@ -79,7 +86,4 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define arch_read_can_lock(lock) (((void)(lock), 1)) #define arch_write_can_lock(lock) (((void)(lock), 1)) -#define arch_spin_unlock_wait(lock) \ - do { cpu_relax(); } while (arch_spin_is_locked(lock)) - #endif /* __LINUX_SPINLOCK_UP_H */ -- cgit v1.2.3 From 810ce8b5df1c8338065f2ae1d2ec08cc566fbb8b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 20 Apr 2016 09:22:15 -0700 Subject: rcu: Document RCU_NONIDLE() restrictions in comment header Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5f1533e3d032..c61b6b9506e7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -379,12 +379,13 @@ static inline void rcu_init_nohz(void) * in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) - * will tell RCU that it needs to pay attending, invoke its argument - * (in this example, a call to the do_something_with_RCU() function), + * will tell RCU that it needs to pay attention, invoke its argument + * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible - * to nest RCU_NONIDLE() wrappers, but the nesting level is currently - * quite limited. If deeper nesting is required, it will be necessary - * to adjust DYNTICK_TASK_NESTING_VALUE accordingly. + * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is + * on the order of a million or so, even on 32-bit systems). It is + * not legal to block within RCU_NONIDLE(), nor is it permissible to + * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ -- cgit v1.2.3 From d95f5ba90fa6043a366958897fdef705af968b70 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 20 Apr 2016 17:18:41 -0700 Subject: torture: Break online and offline functions out of torture_onoff() This commit breaks torture_online() and torture_offline() out of torture_onoff() in preparation for allowing waketorture finer-grained control of its CPU-hotplug workload. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 4 ++ kernel/torture.c | 168 ++++++++++++++++++++++++++++++------------------ 2 files changed, 108 insertions(+), 64 deletions(-) (limited to 'include') diff --git a/include/linux/torture.h b/include/linux/torture.h index 7759fc3c622d..6685a73736a2 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -50,6 +50,10 @@ do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); } while (0) /* Definitions for online/offline exerciser. */ +bool torture_offline(int cpu, long *n_onl_attempts, long *n_onl_successes, + unsigned long *sum_offl, int *min_onl, int *max_onl); +bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, + unsigned long *sum_onl, int *min_onl, int *max_onl); int torture_onoff_init(long ooholdoff, long oointerval); void torture_onoff_stats(void); bool torture_onoff_failures(void); diff --git a/kernel/torture.c b/kernel/torture.c index fa0bdeee17ac..fb39a06bbef5 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -81,6 +81,104 @@ static unsigned long sum_online; static int min_online = -1; static int max_online; +/* + * Attempt to take a CPU offline. Return false if the CPU is already + * offline or if it is not subject to CPU-hotplug operations. The + * caller can detect other failures by looking at the statistics. + */ +bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes, + unsigned long *sum_offl, int *min_offl, int *max_offl) +{ + unsigned long delta; + int ret; + unsigned long starttime; + + if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) + return false; + + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlining %d\n", + torture_type, cpu); + starttime = jiffies; + (*n_offl_attempts)++; + ret = cpu_down(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offline %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: offlined %d\n", + torture_type, cpu); + (*n_offl_successes)++; + delta = jiffies - starttime; + sum_offl += delta; + if (*min_offl < 0) { + *min_offl = delta; + *max_offl = delta; + } + if (*min_offl > delta) + *min_offl = delta; + if (*max_offl < delta) + *max_offl = delta; + } + + return true; +} +EXPORT_SYMBOL_GPL(torture_offline); + +/* + * Attempt to bring a CPU online. Return false if the CPU is already + * online or if it is not subject to CPU-hotplug operations. The + * caller can detect other failures by looking at the statistics. + */ +bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes, + unsigned long *sum_onl, int *min_onl, int *max_onl) +{ + unsigned long delta; + int ret; + unsigned long starttime; + + if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu)) + return false; + + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlining %d\n", + torture_type, cpu); + starttime = jiffies; + (*n_onl_attempts)++; + ret = cpu_up(cpu); + if (ret) { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: online %d failed: errno %d\n", + torture_type, cpu, ret); + } else { + if (verbose) + pr_alert("%s" TORTURE_FLAG + "torture_onoff task: onlined %d\n", + torture_type, cpu); + (*n_onl_successes)++; + delta = jiffies - starttime; + *sum_onl += delta; + if (*min_onl < 0) { + *min_onl = delta; + *max_onl = delta; + } + if (*min_onl > delta) + *min_onl = delta; + if (*max_onl < delta) + *max_onl = delta; + } + + return true; +} +EXPORT_SYMBOL_GPL(torture_online); + /* * Execute random CPU-hotplug operations at the interval specified * by the onoff_interval. @@ -89,11 +187,8 @@ static int torture_onoff(void *arg) { int cpu; - unsigned long delta; int maxcpu = -1; DEFINE_TORTURE_RANDOM(rand); - int ret; - unsigned long starttime; VERBOSE_TOROUT_STRING("torture_onoff task started"); for_each_online_cpu(cpu) @@ -106,67 +201,12 @@ torture_onoff(void *arg) } while (!torture_must_stop()) { cpu = (torture_random(&rand) >> 4) % (maxcpu + 1); - if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: offlining %d\n", - torture_type, cpu); - starttime = jiffies; - n_offline_attempts++; - ret = cpu_down(cpu); - if (ret) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: offline %d failed: errno %d\n", - torture_type, cpu, ret); - } else { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: offlined %d\n", - torture_type, cpu); - n_offline_successes++; - delta = jiffies - starttime; - sum_offline += delta; - if (min_offline < 0) { - min_offline = delta; - max_offline = delta; - } - if (min_offline > delta) - min_offline = delta; - if (max_offline < delta) - max_offline = delta; - } - } else if (cpu_is_hotpluggable(cpu)) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: onlining %d\n", - torture_type, cpu); - starttime = jiffies; - n_online_attempts++; - ret = cpu_up(cpu); - if (ret) { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: online %d failed: errno %d\n", - torture_type, cpu, ret); - } else { - if (verbose) - pr_alert("%s" TORTURE_FLAG - "torture_onoff task: onlined %d\n", - torture_type, cpu); - n_online_successes++; - delta = jiffies - starttime; - sum_online += delta; - if (min_online < 0) { - min_online = delta; - max_online = delta; - } - if (min_online > delta) - min_online = delta; - if (max_online < delta) - max_online = delta; - } - } + if (!torture_offline(cpu, + &n_offline_attempts, &n_offline_successes, + &sum_offline, &min_offline, &max_offline)) + torture_online(cpu, + &n_online_attempts, &n_online_successes, + &sum_online, &min_online, &max_online); schedule_timeout_interruptible(onoff_interval); } torture_kthread_stopping("torture_onoff"); -- cgit v1.2.3 From 3a37f7275cda5ad25c1fe9be8f20c76c60d175fa Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 1 May 2016 18:46:54 -0700 Subject: rcu: No ordering for rcu_assign_pointer() of NULL This commit does a compile-time check for rcu_assign_pointer() of NULL, and uses WRITE_ONCE() rather than smp_store_release() in that case. Reported-by: Christoph Hellwig Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c61b6b9506e7..a8af79738a0e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -650,7 +650,16 @@ static inline void rcu_preempt_sleep_check(void) * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ -#define rcu_assign_pointer(p, v) smp_store_release(&p, RCU_INITIALIZER(v)) +#define rcu_assign_pointer(p, v) \ +({ \ + uintptr_t _r_a_p__v = (uintptr_t)(v); \ + \ + if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ + WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ + else \ + smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ + _r_a_p__v; \ +}) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing -- cgit v1.2.3 From 4929c913bda505dbe44bb42c00da06011fee6c9d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 2 May 2016 11:58:56 -0700 Subject: rcu: Make call_rcu_tasks() tolerate first call with irqs disabled Currently, if the very first call to call_rcu_tasks() has irqs disabled, it will create the rcu_tasks_kthread with irqs disabled, which will result in a splat in the memory allocator, which kthread_run() invokes with the expectation that irqs are enabled. This commit fixes this problem by deferring kthread creation if called with irqs disabled. The first call to call_rcu_tasks() that has irqs enabled will create the kthread. This bug was detected by rcutorture changes that were motivated by Iftekhar Ahmed's mutation-testing efforts. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 + kernel/rcu/update.c | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a8af79738a0e..3bc5de08c0b7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -45,6 +45,7 @@ #include #include #include +#include #include diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 3e888cd5a594..f0d8322bc3ec 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -528,6 +528,7 @@ static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; module_param(rcu_task_stall_timeout, int, 0644); static void rcu_spawn_tasks_kthread(void); +static struct task_struct *rcu_tasks_kthread_ptr; /* * Post an RCU-tasks callback. First call must be from process context @@ -537,6 +538,7 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) { unsigned long flags; bool needwake; + bool havetask = READ_ONCE(rcu_tasks_kthread_ptr); rhp->next = NULL; rhp->func = func; @@ -545,7 +547,9 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) *rcu_tasks_cbs_tail = rhp; rcu_tasks_cbs_tail = &rhp->next; raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); - if (needwake) { + /* We can't create the thread unless interrupts are enabled. */ + if ((needwake && havetask) || + (!havetask && !irqs_disabled_flags(flags))) { rcu_spawn_tasks_kthread(); wake_up(&rcu_tasks_cbs_wq); } @@ -790,7 +794,6 @@ static int __noreturn rcu_tasks_kthread(void *arg) static void rcu_spawn_tasks_kthread(void) { static DEFINE_MUTEX(rcu_tasks_kthread_mutex); - static struct task_struct *rcu_tasks_kthread_ptr; struct task_struct *t; if (READ_ONCE(rcu_tasks_kthread_ptr)) { -- cgit v1.2.3 From 088e9d253d3a4ab7e058dd84bb532c32dadf1882 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Thu, 2 Jun 2016 13:51:41 -0300 Subject: rcu: sysctl: Panic on RCU Stall It is not always easy to determine the cause of an RCU stall just by analysing the RCU stall messages, mainly when the problem is caused by the indirect starvation of rcu threads. For example, when preempt_rcu is not awakened due to the starvation of a timer softirq. We have been hard coding panic() in the RCU stall functions for some time while testing the kernel-rt. But this is not possible in some scenarios, like when supporting customers. This patch implements the sysctl kernel.panic_on_rcu_stall. If set to 1, the system will panic() when an RCU stall takes place, enabling the capture of a vmcore. The vmcore provides a way to analyze all kernel/tasks states, helping out to point to the culprit and the solution for the stall. The kernel.panic_on_rcu_stall sysctl is disabled by default. Changes from v1: - Fixed a typo in the git log - The if(sysctl_panic_on_rcu_stall) panic() is in a static function - Fixed the CONFIG_TINY_RCU compilation issue - The var sysctl_panic_on_rcu_stall is now __read_mostly Cc: Jonathan Corbet Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Steven Rostedt Cc: Mathieu Desnoyers Cc: Lai Jiangshan Acked-by: Christian Borntraeger Reviewed-by: Josh Triplett Reviewed-by: Arnaldo Carvalho de Melo Tested-by: "Luis Claudio R. Goncalves" Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Paul E. McKenney --- Documentation/sysctl/kernel.txt | 12 ++++++++++++ include/linux/kernel.h | 1 + kernel/rcu/tree.c | 12 ++++++++++++ kernel/sysctl.c | 11 +++++++++++ 4 files changed, 36 insertions(+) (limited to 'include') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index a3683ce2a2f3..33204604de6c 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -58,6 +58,7 @@ show up in /proc/sys/kernel: - panic_on_stackoverflow - panic_on_unrecovered_nmi - panic_on_warn +- panic_on_rcu_stall - perf_cpu_time_max_percent - perf_event_paranoid - perf_event_max_stack @@ -618,6 +619,17 @@ a kernel rebuild when attempting to kdump at the location of a WARN(). ============================================================== +panic_on_rcu_stall: + +When set to 1, calls panic() after RCU stall detection messages. This +is useful to define the root cause of RCU stalls using a vmcore. + +0: do not panic() when RCU stall takes place, default behavior. + +1: panic() after printing RCU stall messages. + +============================================================== + perf_cpu_time_max_percent: Hints to the kernel how much CPU time it should be allowed to diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 94aa10ffe156..c42082112ec8 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -451,6 +451,7 @@ extern int panic_on_oops; extern int panic_on_unrecovered_nmi; extern int panic_on_io_nmi; extern int panic_on_warn; +extern int sysctl_panic_on_rcu_stall; extern int sysctl_panic_on_stackoverflow; extern bool crash_kexec_post_notifiers; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c844b6142a86..e5ca15a461b9 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -125,6 +125,8 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; /* Number of rcu_nodes at specified level. */ static int num_rcu_lvl[] = NUM_RCU_LVL_INIT; int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ +/* panic() on RCU Stall sysctl. */ +int sysctl_panic_on_rcu_stall __read_mostly; /* * The rcu_scheduler_active variable transitions from zero to one just @@ -1312,6 +1314,12 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp) } } +static inline void panic_on_rcu_stall(void) +{ + if (sysctl_panic_on_rcu_stall) + panic("RCU Stall\n"); +} + static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) { int cpu; @@ -1391,6 +1399,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) rcu_check_gp_kthread_starvation(rsp); + panic_on_rcu_stall(); + force_quiescent_state(rsp); /* Kick them all. */ } @@ -1431,6 +1441,8 @@ static void print_cpu_stall(struct rcu_state *rsp) jiffies + 3 * rcu_jiffies_till_stall_check() + 3); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + panic_on_rcu_stall(); + /* * Attempt to revive the RCU machinery by forcing a context switch. * diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 87b2fc38398b..35f0dcb1cb4f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1204,6 +1204,17 @@ static struct ctl_table kern_table[] = { .extra1 = &one, .extra2 = &one, }, +#endif +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) + { + .procname = "panic_on_rcu_stall", + .data = &sysctl_panic_on_rcu_stall, + .maxlen = sizeof(sysctl_panic_on_rcu_stall), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, #endif { } }; -- cgit v1.2.3 From e12133324b7daaa176bb687c1eb59e1a6b203da4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:52:13 +0200 Subject: locking/atomic: Fix atomic64_relaxed() bits We should only expand the atomic64 relaxed bits once we've included all relevant headers. So move it down until after we potentially include asm-generic/atomic64.h. In practise this will not have made a difference so far, since the generic bits will not define _relaxed versions. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Davidlohr Bueso Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 306 ++++++++++++++++++++++++------------------------- 1 file changed, 153 insertions(+), 153 deletions(-) (limited to 'include') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index e451534fe54d..351f89e1d15c 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -211,159 +211,6 @@ #endif #endif /* atomic_cmpxchg_relaxed */ -#ifndef atomic64_read_acquire -#define atomic64_read_acquire(v) smp_load_acquire(&(v)->counter) -#endif - -#ifndef atomic64_set_release -#define atomic64_set_release(v, i) smp_store_release(&(v)->counter, (i)) -#endif - -/* atomic64_add_return_relaxed */ -#ifndef atomic64_add_return_relaxed -#define atomic64_add_return_relaxed atomic64_add_return -#define atomic64_add_return_acquire atomic64_add_return -#define atomic64_add_return_release atomic64_add_return - -#else /* atomic64_add_return_relaxed */ - -#ifndef atomic64_add_return_acquire -#define atomic64_add_return_acquire(...) \ - __atomic_op_acquire(atomic64_add_return, __VA_ARGS__) -#endif - -#ifndef atomic64_add_return_release -#define atomic64_add_return_release(...) \ - __atomic_op_release(atomic64_add_return, __VA_ARGS__) -#endif - -#ifndef atomic64_add_return -#define atomic64_add_return(...) \ - __atomic_op_fence(atomic64_add_return, __VA_ARGS__) -#endif -#endif /* atomic64_add_return_relaxed */ - -/* atomic64_inc_return_relaxed */ -#ifndef atomic64_inc_return_relaxed -#define atomic64_inc_return_relaxed atomic64_inc_return -#define atomic64_inc_return_acquire atomic64_inc_return -#define atomic64_inc_return_release atomic64_inc_return - -#else /* atomic64_inc_return_relaxed */ - -#ifndef atomic64_inc_return_acquire -#define atomic64_inc_return_acquire(...) \ - __atomic_op_acquire(atomic64_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic64_inc_return_release -#define atomic64_inc_return_release(...) \ - __atomic_op_release(atomic64_inc_return, __VA_ARGS__) -#endif - -#ifndef atomic64_inc_return -#define atomic64_inc_return(...) \ - __atomic_op_fence(atomic64_inc_return, __VA_ARGS__) -#endif -#endif /* atomic64_inc_return_relaxed */ - - -/* atomic64_sub_return_relaxed */ -#ifndef atomic64_sub_return_relaxed -#define atomic64_sub_return_relaxed atomic64_sub_return -#define atomic64_sub_return_acquire atomic64_sub_return -#define atomic64_sub_return_release atomic64_sub_return - -#else /* atomic64_sub_return_relaxed */ - -#ifndef atomic64_sub_return_acquire -#define atomic64_sub_return_acquire(...) \ - __atomic_op_acquire(atomic64_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic64_sub_return_release -#define atomic64_sub_return_release(...) \ - __atomic_op_release(atomic64_sub_return, __VA_ARGS__) -#endif - -#ifndef atomic64_sub_return -#define atomic64_sub_return(...) \ - __atomic_op_fence(atomic64_sub_return, __VA_ARGS__) -#endif -#endif /* atomic64_sub_return_relaxed */ - -/* atomic64_dec_return_relaxed */ -#ifndef atomic64_dec_return_relaxed -#define atomic64_dec_return_relaxed atomic64_dec_return -#define atomic64_dec_return_acquire atomic64_dec_return -#define atomic64_dec_return_release atomic64_dec_return - -#else /* atomic64_dec_return_relaxed */ - -#ifndef atomic64_dec_return_acquire -#define atomic64_dec_return_acquire(...) \ - __atomic_op_acquire(atomic64_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic64_dec_return_release -#define atomic64_dec_return_release(...) \ - __atomic_op_release(atomic64_dec_return, __VA_ARGS__) -#endif - -#ifndef atomic64_dec_return -#define atomic64_dec_return(...) \ - __atomic_op_fence(atomic64_dec_return, __VA_ARGS__) -#endif -#endif /* atomic64_dec_return_relaxed */ - -/* atomic64_xchg_relaxed */ -#ifndef atomic64_xchg_relaxed -#define atomic64_xchg_relaxed atomic64_xchg -#define atomic64_xchg_acquire atomic64_xchg -#define atomic64_xchg_release atomic64_xchg - -#else /* atomic64_xchg_relaxed */ - -#ifndef atomic64_xchg_acquire -#define atomic64_xchg_acquire(...) \ - __atomic_op_acquire(atomic64_xchg, __VA_ARGS__) -#endif - -#ifndef atomic64_xchg_release -#define atomic64_xchg_release(...) \ - __atomic_op_release(atomic64_xchg, __VA_ARGS__) -#endif - -#ifndef atomic64_xchg -#define atomic64_xchg(...) \ - __atomic_op_fence(atomic64_xchg, __VA_ARGS__) -#endif -#endif /* atomic64_xchg_relaxed */ - -/* atomic64_cmpxchg_relaxed */ -#ifndef atomic64_cmpxchg_relaxed -#define atomic64_cmpxchg_relaxed atomic64_cmpxchg -#define atomic64_cmpxchg_acquire atomic64_cmpxchg -#define atomic64_cmpxchg_release atomic64_cmpxchg - -#else /* atomic64_cmpxchg_relaxed */ - -#ifndef atomic64_cmpxchg_acquire -#define atomic64_cmpxchg_acquire(...) \ - __atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic64_cmpxchg_release -#define atomic64_cmpxchg_release(...) \ - __atomic_op_release(atomic64_cmpxchg, __VA_ARGS__) -#endif - -#ifndef atomic64_cmpxchg -#define atomic64_cmpxchg(...) \ - __atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__) -#endif -#endif /* atomic64_cmpxchg_relaxed */ - /* cmpxchg_relaxed */ #ifndef cmpxchg_relaxed #define cmpxchg_relaxed cmpxchg @@ -583,6 +430,159 @@ static inline int atomic_fetch_or(int mask, atomic_t *p) #include #endif +#ifndef atomic64_read_acquire +#define atomic64_read_acquire(v) smp_load_acquire(&(v)->counter) +#endif + +#ifndef atomic64_set_release +#define atomic64_set_release(v, i) smp_store_release(&(v)->counter, (i)) +#endif + +/* atomic64_add_return_relaxed */ +#ifndef atomic64_add_return_relaxed +#define atomic64_add_return_relaxed atomic64_add_return +#define atomic64_add_return_acquire atomic64_add_return +#define atomic64_add_return_release atomic64_add_return + +#else /* atomic64_add_return_relaxed */ + +#ifndef atomic64_add_return_acquire +#define atomic64_add_return_acquire(...) \ + __atomic_op_acquire(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return_release +#define atomic64_add_return_release(...) \ + __atomic_op_release(atomic64_add_return, __VA_ARGS__) +#endif + +#ifndef atomic64_add_return +#define atomic64_add_return(...) \ + __atomic_op_fence(atomic64_add_return, __VA_ARGS__) +#endif +#endif /* atomic64_add_return_relaxed */ + +/* atomic64_inc_return_relaxed */ +#ifndef atomic64_inc_return_relaxed +#define atomic64_inc_return_relaxed atomic64_inc_return +#define atomic64_inc_return_acquire atomic64_inc_return +#define atomic64_inc_return_release atomic64_inc_return + +#else /* atomic64_inc_return_relaxed */ + +#ifndef atomic64_inc_return_acquire +#define atomic64_inc_return_acquire(...) \ + __atomic_op_acquire(atomic64_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic64_inc_return_release +#define atomic64_inc_return_release(...) \ + __atomic_op_release(atomic64_inc_return, __VA_ARGS__) +#endif + +#ifndef atomic64_inc_return +#define atomic64_inc_return(...) \ + __atomic_op_fence(atomic64_inc_return, __VA_ARGS__) +#endif +#endif /* atomic64_inc_return_relaxed */ + + +/* atomic64_sub_return_relaxed */ +#ifndef atomic64_sub_return_relaxed +#define atomic64_sub_return_relaxed atomic64_sub_return +#define atomic64_sub_return_acquire atomic64_sub_return +#define atomic64_sub_return_release atomic64_sub_return + +#else /* atomic64_sub_return_relaxed */ + +#ifndef atomic64_sub_return_acquire +#define atomic64_sub_return_acquire(...) \ + __atomic_op_acquire(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return_release +#define atomic64_sub_return_release(...) \ + __atomic_op_release(atomic64_sub_return, __VA_ARGS__) +#endif + +#ifndef atomic64_sub_return +#define atomic64_sub_return(...) \ + __atomic_op_fence(atomic64_sub_return, __VA_ARGS__) +#endif +#endif /* atomic64_sub_return_relaxed */ + +/* atomic64_dec_return_relaxed */ +#ifndef atomic64_dec_return_relaxed +#define atomic64_dec_return_relaxed atomic64_dec_return +#define atomic64_dec_return_acquire atomic64_dec_return +#define atomic64_dec_return_release atomic64_dec_return + +#else /* atomic64_dec_return_relaxed */ + +#ifndef atomic64_dec_return_acquire +#define atomic64_dec_return_acquire(...) \ + __atomic_op_acquire(atomic64_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic64_dec_return_release +#define atomic64_dec_return_release(...) \ + __atomic_op_release(atomic64_dec_return, __VA_ARGS__) +#endif + +#ifndef atomic64_dec_return +#define atomic64_dec_return(...) \ + __atomic_op_fence(atomic64_dec_return, __VA_ARGS__) +#endif +#endif /* atomic64_dec_return_relaxed */ + +/* atomic64_xchg_relaxed */ +#ifndef atomic64_xchg_relaxed +#define atomic64_xchg_relaxed atomic64_xchg +#define atomic64_xchg_acquire atomic64_xchg +#define atomic64_xchg_release atomic64_xchg + +#else /* atomic64_xchg_relaxed */ + +#ifndef atomic64_xchg_acquire +#define atomic64_xchg_acquire(...) \ + __atomic_op_acquire(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg_release +#define atomic64_xchg_release(...) \ + __atomic_op_release(atomic64_xchg, __VA_ARGS__) +#endif + +#ifndef atomic64_xchg +#define atomic64_xchg(...) \ + __atomic_op_fence(atomic64_xchg, __VA_ARGS__) +#endif +#endif /* atomic64_xchg_relaxed */ + +/* atomic64_cmpxchg_relaxed */ +#ifndef atomic64_cmpxchg_relaxed +#define atomic64_cmpxchg_relaxed atomic64_cmpxchg +#define atomic64_cmpxchg_acquire atomic64_cmpxchg +#define atomic64_cmpxchg_release atomic64_cmpxchg + +#else /* atomic64_cmpxchg_relaxed */ + +#ifndef atomic64_cmpxchg_acquire +#define atomic64_cmpxchg_acquire(...) \ + __atomic_op_acquire(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg_release +#define atomic64_cmpxchg_release(...) \ + __atomic_op_release(atomic64_cmpxchg, __VA_ARGS__) +#endif + +#ifndef atomic64_cmpxchg +#define atomic64_cmpxchg(...) \ + __atomic_op_fence(atomic64_cmpxchg, __VA_ARGS__) +#endif +#endif /* atomic64_cmpxchg_relaxed */ + #ifndef atomic64_andnot static inline void atomic64_andnot(long long i, atomic64_t *v) { -- cgit v1.2.3 From 28aa2bda2211f4327d83b44a4f917b4a061b1c56 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:54:38 +0200 Subject: locking/atomic: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}() Now that all the architectures have implemented support for these new atomic primitives add on the generic infrastructure to expose and use it. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Arnd Bergmann Cc: Boqun Feng Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-long.h | 36 +++- include/asm-generic/atomic.h | 49 ++++++ include/asm-generic/atomic64.h | 15 +- include/linux/atomic.h | 336 ++++++++++++++++++++++++++++++++++++++ lib/atomic64.c | 32 +++- lib/atomic64_test.c | 34 ++++ 6 files changed, 493 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h index 5e1f345b58dd..2d0d3cf791ab 100644 --- a/include/asm-generic/atomic-long.h +++ b/include/asm-generic/atomic-long.h @@ -112,6 +112,40 @@ static __always_inline void atomic_long_dec(atomic_long_t *l) ATOMIC_LONG_PFX(_dec)(v); } +#define ATOMIC_LONG_FETCH_OP(op, mo) \ +static inline long \ +atomic_long_fetch_##op##mo(long i, atomic_long_t *l) \ +{ \ + ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ + \ + return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(i, v); \ +} + +ATOMIC_LONG_FETCH_OP(add, ) +ATOMIC_LONG_FETCH_OP(add, _relaxed) +ATOMIC_LONG_FETCH_OP(add, _acquire) +ATOMIC_LONG_FETCH_OP(add, _release) +ATOMIC_LONG_FETCH_OP(sub, ) +ATOMIC_LONG_FETCH_OP(sub, _relaxed) +ATOMIC_LONG_FETCH_OP(sub, _acquire) +ATOMIC_LONG_FETCH_OP(sub, _release) +ATOMIC_LONG_FETCH_OP(and, ) +ATOMIC_LONG_FETCH_OP(and, _relaxed) +ATOMIC_LONG_FETCH_OP(and, _acquire) +ATOMIC_LONG_FETCH_OP(and, _release) +ATOMIC_LONG_FETCH_OP(andnot, ) +ATOMIC_LONG_FETCH_OP(andnot, _relaxed) +ATOMIC_LONG_FETCH_OP(andnot, _acquire) +ATOMIC_LONG_FETCH_OP(andnot, _release) +ATOMIC_LONG_FETCH_OP(or, ) +ATOMIC_LONG_FETCH_OP(or, _relaxed) +ATOMIC_LONG_FETCH_OP(or, _acquire) +ATOMIC_LONG_FETCH_OP(or, _release) +ATOMIC_LONG_FETCH_OP(xor, ) +ATOMIC_LONG_FETCH_OP(xor, _relaxed) +ATOMIC_LONG_FETCH_OP(xor, _acquire) +ATOMIC_LONG_FETCH_OP(xor, _release) + #define ATOMIC_LONG_OP(op) \ static __always_inline void \ atomic_long_##op(long i, atomic_long_t *l) \ @@ -124,9 +158,9 @@ atomic_long_##op(long i, atomic_long_t *l) \ ATOMIC_LONG_OP(add) ATOMIC_LONG_OP(sub) ATOMIC_LONG_OP(and) +ATOMIC_LONG_OP(andnot) ATOMIC_LONG_OP(or) ATOMIC_LONG_OP(xor) -ATOMIC_LONG_OP(andnot) #undef ATOMIC_LONG_OP diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 74f1a3704d7a..a2304ccf4ed0 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -61,6 +61,18 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ return c c_op i; \ } +#define ATOMIC_FETCH_OP(op, c_op) \ +static inline int atomic_fetch_##op(int i, atomic_t *v) \ +{ \ + int c, old; \ + \ + c = v->counter; \ + while ((old = cmpxchg(&v->counter, c, c c_op i)) != c) \ + c = old; \ + \ + return c; \ +} + #else #include @@ -88,6 +100,20 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ return ret; \ } +#define ATOMIC_FETCH_OP(op, c_op) \ +static inline int atomic_fetch_##op(int i, atomic_t *v) \ +{ \ + unsigned long flags; \ + int ret; \ + \ + raw_local_irq_save(flags); \ + ret = v->counter; \ + v->counter = v->counter c_op i; \ + raw_local_irq_restore(flags); \ + \ + return ret; \ +} + #endif /* CONFIG_SMP */ #ifndef atomic_add_return @@ -98,6 +124,28 @@ ATOMIC_OP_RETURN(add, +) ATOMIC_OP_RETURN(sub, -) #endif +#ifndef atomic_fetch_add +ATOMIC_FETCH_OP(add, +) +#endif + +#ifndef atomic_fetch_sub +ATOMIC_FETCH_OP(sub, -) +#endif + +#ifndef atomic_fetch_and +ATOMIC_FETCH_OP(and, &) +#endif + +#ifndef atomic_fetch_or +#define atomic_fetch_or atomic_fetch_or + +ATOMIC_FETCH_OP(or, |) +#endif + +#ifndef atomic_fetch_xor +ATOMIC_FETCH_OP(xor, ^) +#endif + #ifndef atomic_and ATOMIC_OP(and, &) #endif @@ -110,6 +158,7 @@ ATOMIC_OP(or, |) ATOMIC_OP(xor, ^) #endif +#undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h index d48e78ccad3d..dad68bf46c77 100644 --- a/include/asm-generic/atomic64.h +++ b/include/asm-generic/atomic64.h @@ -27,16 +27,23 @@ extern void atomic64_##op(long long a, atomic64_t *v); #define ATOMIC64_OP_RETURN(op) \ extern long long atomic64_##op##_return(long long a, atomic64_t *v); -#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) +#define ATOMIC64_FETCH_OP(op) \ +extern long long atomic64_fetch_##op(long long a, atomic64_t *v); + +#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op) ATOMIC64_OPS(add) ATOMIC64_OPS(sub) -ATOMIC64_OP(and) -ATOMIC64_OP(or) -ATOMIC64_OP(xor) +#undef ATOMIC64_OPS +#define ATOMIC64_OPS(op) ATOMIC64_OP(op) ATOMIC64_FETCH_OP(op) + +ATOMIC64_OPS(and) +ATOMIC64_OPS(or) +ATOMIC64_OPS(xor) #undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 351f89e1d15c..2e6c013ac5a4 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -163,6 +163,154 @@ #endif #endif /* atomic_dec_return_relaxed */ + +/* atomic_fetch_add_relaxed */ +#ifndef atomic_fetch_add_relaxed +#define atomic_fetch_add_relaxed atomic_fetch_add +#define atomic_fetch_add_acquire atomic_fetch_add +#define atomic_fetch_add_release atomic_fetch_add + +#else /* atomic_fetch_add_relaxed */ + +#ifndef atomic_fetch_add_acquire +#define atomic_fetch_add_acquire(...) \ + __atomic_op_acquire(atomic_fetch_add, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_add_release +#define atomic_fetch_add_release(...) \ + __atomic_op_release(atomic_fetch_add, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_add +#define atomic_fetch_add(...) \ + __atomic_op_fence(atomic_fetch_add, __VA_ARGS__) +#endif +#endif /* atomic_fetch_add_relaxed */ + +/* atomic_fetch_sub_relaxed */ +#ifndef atomic_fetch_sub_relaxed +#define atomic_fetch_sub_relaxed atomic_fetch_sub +#define atomic_fetch_sub_acquire atomic_fetch_sub +#define atomic_fetch_sub_release atomic_fetch_sub + +#else /* atomic_fetch_sub_relaxed */ + +#ifndef atomic_fetch_sub_acquire +#define atomic_fetch_sub_acquire(...) \ + __atomic_op_acquire(atomic_fetch_sub, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_sub_release +#define atomic_fetch_sub_release(...) \ + __atomic_op_release(atomic_fetch_sub, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_sub +#define atomic_fetch_sub(...) \ + __atomic_op_fence(atomic_fetch_sub, __VA_ARGS__) +#endif +#endif /* atomic_fetch_sub_relaxed */ + +/* atomic_fetch_or_relaxed */ +#ifndef atomic_fetch_or_relaxed +#define atomic_fetch_or_relaxed atomic_fetch_or +#define atomic_fetch_or_acquire atomic_fetch_or +#define atomic_fetch_or_release atomic_fetch_or + +#else /* atomic_fetch_or_relaxed */ + +#ifndef atomic_fetch_or_acquire +#define atomic_fetch_or_acquire(...) \ + __atomic_op_acquire(atomic_fetch_or, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_or_release +#define atomic_fetch_or_release(...) \ + __atomic_op_release(atomic_fetch_or, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_or +#define atomic_fetch_or(...) \ + __atomic_op_fence(atomic_fetch_or, __VA_ARGS__) +#endif +#endif /* atomic_fetch_or_relaxed */ + +/* atomic_fetch_and_relaxed */ +#ifndef atomic_fetch_and_relaxed +#define atomic_fetch_and_relaxed atomic_fetch_and +#define atomic_fetch_and_acquire atomic_fetch_and +#define atomic_fetch_and_release atomic_fetch_and + +#else /* atomic_fetch_and_relaxed */ + +#ifndef atomic_fetch_and_acquire +#define atomic_fetch_and_acquire(...) \ + __atomic_op_acquire(atomic_fetch_and, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_and_release +#define atomic_fetch_and_release(...) \ + __atomic_op_release(atomic_fetch_and, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_and +#define atomic_fetch_and(...) \ + __atomic_op_fence(atomic_fetch_and, __VA_ARGS__) +#endif +#endif /* atomic_fetch_and_relaxed */ + +#ifdef atomic_andnot +/* atomic_fetch_andnot_relaxed */ +#ifndef atomic_fetch_andnot_relaxed +#define atomic_fetch_andnot_relaxed atomic_fetch_andnot +#define atomic_fetch_andnot_acquire atomic_fetch_andnot +#define atomic_fetch_andnot_release atomic_fetch_andnot + +#else /* atomic_fetch_andnot_relaxed */ + +#ifndef atomic_fetch_andnot_acquire +#define atomic_fetch_andnot_acquire(...) \ + __atomic_op_acquire(atomic_fetch_andnot, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_andnot_release +#define atomic_fetch_andnot_release(...) \ + __atomic_op_release(atomic_fetch_andnot, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_andnot +#define atomic_fetch_andnot(...) \ + __atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__) +#endif +#endif /* atomic_fetch_andnot_relaxed */ +#endif /* atomic_andnot */ + +/* atomic_fetch_xor_relaxed */ +#ifndef atomic_fetch_xor_relaxed +#define atomic_fetch_xor_relaxed atomic_fetch_xor +#define atomic_fetch_xor_acquire atomic_fetch_xor +#define atomic_fetch_xor_release atomic_fetch_xor + +#else /* atomic_fetch_xor_relaxed */ + +#ifndef atomic_fetch_xor_acquire +#define atomic_fetch_xor_acquire(...) \ + __atomic_op_acquire(atomic_fetch_xor, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_xor_release +#define atomic_fetch_xor_release(...) \ + __atomic_op_release(atomic_fetch_xor, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_xor +#define atomic_fetch_xor(...) \ + __atomic_op_fence(atomic_fetch_xor, __VA_ARGS__) +#endif +#endif /* atomic_fetch_xor_relaxed */ + + /* atomic_xchg_relaxed */ #ifndef atomic_xchg_relaxed #define atomic_xchg_relaxed atomic_xchg @@ -310,6 +458,26 @@ static inline void atomic_andnot(int i, atomic_t *v) { atomic_and(~i, v); } + +static inline int atomic_fetch_andnot(int i, atomic_t *v) +{ + return atomic_fetch_and(~i, v); +} + +static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v) +{ + return atomic_fetch_and_relaxed(~i, v); +} + +static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v) +{ + return atomic_fetch_and_acquire(~i, v); +} + +static inline int atomic_fetch_andnot_release(int i, atomic_t *v) +{ + return atomic_fetch_and_release(~i, v); +} #endif static inline __deprecated void atomic_clear_mask(unsigned int mask, atomic_t *v) @@ -535,6 +703,154 @@ static inline int atomic_fetch_or(int mask, atomic_t *p) #endif #endif /* atomic64_dec_return_relaxed */ + +/* atomic64_fetch_add_relaxed */ +#ifndef atomic64_fetch_add_relaxed +#define atomic64_fetch_add_relaxed atomic64_fetch_add +#define atomic64_fetch_add_acquire atomic64_fetch_add +#define atomic64_fetch_add_release atomic64_fetch_add + +#else /* atomic64_fetch_add_relaxed */ + +#ifndef atomic64_fetch_add_acquire +#define atomic64_fetch_add_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_add, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_add_release +#define atomic64_fetch_add_release(...) \ + __atomic_op_release(atomic64_fetch_add, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_add +#define atomic64_fetch_add(...) \ + __atomic_op_fence(atomic64_fetch_add, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_add_relaxed */ + +/* atomic64_fetch_sub_relaxed */ +#ifndef atomic64_fetch_sub_relaxed +#define atomic64_fetch_sub_relaxed atomic64_fetch_sub +#define atomic64_fetch_sub_acquire atomic64_fetch_sub +#define atomic64_fetch_sub_release atomic64_fetch_sub + +#else /* atomic64_fetch_sub_relaxed */ + +#ifndef atomic64_fetch_sub_acquire +#define atomic64_fetch_sub_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_sub, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_sub_release +#define atomic64_fetch_sub_release(...) \ + __atomic_op_release(atomic64_fetch_sub, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_sub +#define atomic64_fetch_sub(...) \ + __atomic_op_fence(atomic64_fetch_sub, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_sub_relaxed */ + +/* atomic64_fetch_or_relaxed */ +#ifndef atomic64_fetch_or_relaxed +#define atomic64_fetch_or_relaxed atomic64_fetch_or +#define atomic64_fetch_or_acquire atomic64_fetch_or +#define atomic64_fetch_or_release atomic64_fetch_or + +#else /* atomic64_fetch_or_relaxed */ + +#ifndef atomic64_fetch_or_acquire +#define atomic64_fetch_or_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_or, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_or_release +#define atomic64_fetch_or_release(...) \ + __atomic_op_release(atomic64_fetch_or, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_or +#define atomic64_fetch_or(...) \ + __atomic_op_fence(atomic64_fetch_or, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_or_relaxed */ + +/* atomic64_fetch_and_relaxed */ +#ifndef atomic64_fetch_and_relaxed +#define atomic64_fetch_and_relaxed atomic64_fetch_and +#define atomic64_fetch_and_acquire atomic64_fetch_and +#define atomic64_fetch_and_release atomic64_fetch_and + +#else /* atomic64_fetch_and_relaxed */ + +#ifndef atomic64_fetch_and_acquire +#define atomic64_fetch_and_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_and, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_and_release +#define atomic64_fetch_and_release(...) \ + __atomic_op_release(atomic64_fetch_and, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_and +#define atomic64_fetch_and(...) \ + __atomic_op_fence(atomic64_fetch_and, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_and_relaxed */ + +#ifdef atomic64_andnot +/* atomic64_fetch_andnot_relaxed */ +#ifndef atomic64_fetch_andnot_relaxed +#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot +#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot +#define atomic64_fetch_andnot_release atomic64_fetch_andnot + +#else /* atomic64_fetch_andnot_relaxed */ + +#ifndef atomic64_fetch_andnot_acquire +#define atomic64_fetch_andnot_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_andnot, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_andnot_release +#define atomic64_fetch_andnot_release(...) \ + __atomic_op_release(atomic64_fetch_andnot, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_andnot +#define atomic64_fetch_andnot(...) \ + __atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_andnot_relaxed */ +#endif /* atomic64_andnot */ + +/* atomic64_fetch_xor_relaxed */ +#ifndef atomic64_fetch_xor_relaxed +#define atomic64_fetch_xor_relaxed atomic64_fetch_xor +#define atomic64_fetch_xor_acquire atomic64_fetch_xor +#define atomic64_fetch_xor_release atomic64_fetch_xor + +#else /* atomic64_fetch_xor_relaxed */ + +#ifndef atomic64_fetch_xor_acquire +#define atomic64_fetch_xor_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_xor, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_xor_release +#define atomic64_fetch_xor_release(...) \ + __atomic_op_release(atomic64_fetch_xor, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_xor +#define atomic64_fetch_xor(...) \ + __atomic_op_fence(atomic64_fetch_xor, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_xor_relaxed */ + + /* atomic64_xchg_relaxed */ #ifndef atomic64_xchg_relaxed #define atomic64_xchg_relaxed atomic64_xchg @@ -588,6 +904,26 @@ static inline void atomic64_andnot(long long i, atomic64_t *v) { atomic64_and(~i, v); } + +static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v) +{ + return atomic64_fetch_and(~i, v); +} + +static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v) +{ + return atomic64_fetch_and_relaxed(~i, v); +} + +static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v) +{ + return atomic64_fetch_and_acquire(~i, v); +} + +static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v) +{ + return atomic64_fetch_and_release(~i, v); +} #endif #include diff --git a/lib/atomic64.c b/lib/atomic64.c index 2886ebac6567..53c2d5edc826 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -96,17 +96,41 @@ long long atomic64_##op##_return(long long a, atomic64_t *v) \ } \ EXPORT_SYMBOL(atomic64_##op##_return); +#define ATOMIC64_FETCH_OP(op, c_op) \ +long long atomic64_fetch_##op(long long a, atomic64_t *v) \ +{ \ + unsigned long flags; \ + raw_spinlock_t *lock = lock_addr(v); \ + long long val; \ + \ + raw_spin_lock_irqsave(lock, flags); \ + val = v->counter; \ + v->counter c_op a; \ + raw_spin_unlock_irqrestore(lock, flags); \ + return val; \ +} \ +EXPORT_SYMBOL(atomic64_fetch_##op); + #define ATOMIC64_OPS(op, c_op) \ ATOMIC64_OP(op, c_op) \ - ATOMIC64_OP_RETURN(op, c_op) + ATOMIC64_OP_RETURN(op, c_op) \ + ATOMIC64_FETCH_OP(op, c_op) ATOMIC64_OPS(add, +=) ATOMIC64_OPS(sub, -=) -ATOMIC64_OP(and, &=) -ATOMIC64_OP(or, |=) -ATOMIC64_OP(xor, ^=) #undef ATOMIC64_OPS +#define ATOMIC64_OPS(op, c_op) \ + ATOMIC64_OP(op, c_op) \ + ATOMIC64_OP_RETURN(op, c_op) \ + ATOMIC64_FETCH_OP(op, c_op) + +ATOMIC64_OPS(and, &=) +ATOMIC64_OPS(or, |=) +ATOMIC64_OPS(xor, ^=) + +#undef ATOMIC64_OPS +#undef ATOMIC64_FETCH_OP #undef ATOMIC64_OP_RETURN #undef ATOMIC64_OP diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index 123481814320..dbb369145dda 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -53,11 +53,25 @@ do { \ BUG_ON(atomic##bit##_read(&v) != r); \ } while (0) +#define TEST_FETCH(bit, op, c_op, val) \ +do { \ + atomic##bit##_set(&v, v0); \ + r = v0; \ + r c_op val; \ + BUG_ON(atomic##bit##_##op(val, &v) != v0); \ + BUG_ON(atomic##bit##_read(&v) != r); \ +} while (0) + #define RETURN_FAMILY_TEST(bit, op, c_op, val) \ do { \ FAMILY_TEST(TEST_RETURN, bit, op, c_op, val); \ } while (0) +#define FETCH_FAMILY_TEST(bit, op, c_op, val) \ +do { \ + FAMILY_TEST(TEST_FETCH, bit, op, c_op, val); \ +} while (0) + #define TEST_ARGS(bit, op, init, ret, expect, args...) \ do { \ atomic##bit##_set(&v, init); \ @@ -114,6 +128,16 @@ static __init void test_atomic(void) RETURN_FAMILY_TEST(, sub_return, -=, onestwos); RETURN_FAMILY_TEST(, sub_return, -=, -one); + FETCH_FAMILY_TEST(, fetch_add, +=, onestwos); + FETCH_FAMILY_TEST(, fetch_add, +=, -one); + FETCH_FAMILY_TEST(, fetch_sub, -=, onestwos); + FETCH_FAMILY_TEST(, fetch_sub, -=, -one); + + FETCH_FAMILY_TEST(, fetch_or, |=, v1); + FETCH_FAMILY_TEST(, fetch_and, &=, v1); + FETCH_FAMILY_TEST(, fetch_andnot, &= ~, v1); + FETCH_FAMILY_TEST(, fetch_xor, ^=, v1); + INC_RETURN_FAMILY_TEST(, v0); DEC_RETURN_FAMILY_TEST(, v0); @@ -154,6 +178,16 @@ static __init void test_atomic64(void) RETURN_FAMILY_TEST(64, sub_return, -=, onestwos); RETURN_FAMILY_TEST(64, sub_return, -=, -one); + FETCH_FAMILY_TEST(64, fetch_add, +=, onestwos); + FETCH_FAMILY_TEST(64, fetch_add, +=, -one); + FETCH_FAMILY_TEST(64, fetch_sub, -=, onestwos); + FETCH_FAMILY_TEST(64, fetch_sub, -=, -one); + + FETCH_FAMILY_TEST(64, fetch_or, |=, v1); + FETCH_FAMILY_TEST(64, fetch_and, &=, v1); + FETCH_FAMILY_TEST(64, fetch_andnot, &= ~, v1); + FETCH_FAMILY_TEST(64, fetch_xor, ^=, v1); + INIT(v0); atomic64_inc(&v); r += one; -- cgit v1.2.3 From b53d6bedbe781974097fd8c38263f6cc78ff9ea7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 00:58:25 +0200 Subject: locking/atomic: Remove linux/atomic.h:atomic_fetch_or() Since all architectures have this implemented now natively, remove this dead code. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/alpha/include/asm/atomic.h | 2 -- arch/arc/include/asm/atomic.h | 2 -- arch/arm/include/asm/atomic.h | 2 -- arch/arm64/include/asm/atomic.h | 2 -- arch/avr32/include/asm/atomic.h | 2 -- arch/frv/include/asm/atomic.h | 2 -- arch/h8300/include/asm/atomic.h | 2 -- arch/hexagon/include/asm/atomic.h | 2 -- arch/m32r/include/asm/atomic.h | 2 -- arch/m68k/include/asm/atomic.h | 2 -- arch/metag/include/asm/atomic.h | 2 -- arch/mips/include/asm/atomic.h | 2 -- arch/mn10300/include/asm/atomic.h | 2 -- arch/parisc/include/asm/atomic.h | 2 -- arch/s390/include/asm/atomic.h | 2 -- arch/sh/include/asm/atomic.h | 2 -- arch/sparc/include/asm/atomic.h | 1 - arch/sparc/include/asm/atomic_32.h | 2 -- arch/tile/include/asm/atomic.h | 2 -- arch/x86/include/asm/atomic.h | 2 -- arch/xtensa/include/asm/atomic.h | 2 -- include/asm-generic/atomic.h | 2 -- include/linux/atomic.h | 21 --------------------- 23 files changed, 64 deletions(-) (limited to 'include') diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index 8243f17999e3..5377ca8bb503 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -153,8 +153,6 @@ ATOMIC_OPS(sub) #define atomic_andnot atomic_andnot #define atomic64_andnot atomic64_andnot -#define atomic_fetch_or atomic_fetch_or - #undef ATOMIC_OPS #define ATOMIC_OPS(op, asm) \ ATOMIC_OP(op, asm) \ diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index c066a21caaaf..bd9c51cb2bfd 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -189,8 +189,6 @@ ATOMIC_OPS(sub, -=, sub) #define atomic_andnot atomic_andnot -#define atomic_fetch_or atomic_fetch_or - #undef ATOMIC_OPS #define ATOMIC_OPS(op, c_op, asm_op) \ ATOMIC_OP(op, c_op, asm_op) \ diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 0feb110ec542..66d0e215a773 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -201,8 +201,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ return val; \ } -#define atomic_fetch_or atomic_fetch_or - static inline int atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 3128c3d7c1ff..c0235e0ff849 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -128,8 +128,6 @@ #define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) #define atomic_andnot atomic_andnot -#define atomic_fetch_or atomic_fetch_or - /* * 64-bit atomic operations. */ diff --git a/arch/avr32/include/asm/atomic.h b/arch/avr32/include/asm/atomic.h index b8681fd495ef..3d5ce38a6f0b 100644 --- a/arch/avr32/include/asm/atomic.h +++ b/arch/avr32/include/asm/atomic.h @@ -66,8 +66,6 @@ ATOMIC_OP_RETURN(add, add, r) ATOMIC_FETCH_OP (sub, sub, rKs21) ATOMIC_FETCH_OP (add, add, r) -#define atomic_fetch_or atomic_fetch_or - #define ATOMIC_OPS(op, asm_op) \ ATOMIC_OP_RETURN(op, asm_op, r) \ static inline void atomic_##op(int i, atomic_t *v) \ diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h index e3e06da0cd59..1c2a5e264fc7 100644 --- a/arch/frv/include/asm/atomic.h +++ b/arch/frv/include/asm/atomic.h @@ -74,8 +74,6 @@ static inline void atomic_dec(atomic_t *v) #define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0) #define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0) -#define atomic_fetch_or atomic_fetch_or - /* * 64-bit atomic ops */ diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index 0961b618bdde..349a47a918db 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -54,8 +54,6 @@ static inline void atomic_##op(int i, atomic_t *v) \ ATOMIC_OP_RETURN(add, +=) ATOMIC_OP_RETURN(sub, -=) -#define atomic_fetch_or atomic_fetch_or - #define ATOMIC_OPS(op, c_op) \ ATOMIC_OP(op, c_op) \ ATOMIC_FETCH_OP(op, c_op) diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h index 07dbb3332b4a..a62ba368b27d 100644 --- a/arch/hexagon/include/asm/atomic.h +++ b/arch/hexagon/include/asm/atomic.h @@ -152,8 +152,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/m32r/include/asm/atomic.h b/arch/m32r/include/asm/atomic.h index 8ba8a0ab5d5d..640cc1c7099f 100644 --- a/arch/m32r/include/asm/atomic.h +++ b/arch/m32r/include/asm/atomic.h @@ -121,8 +121,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h index 5cf9b3b1b6ac..3e03de7ae33b 100644 --- a/arch/m68k/include/asm/atomic.h +++ b/arch/m68k/include/asm/atomic.h @@ -119,8 +119,6 @@ ATOMIC_OPS(sub, -=, sub) ATOMIC_OP(op, c_op, asm_op) \ ATOMIC_FETCH_OP(op, c_op, asm_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, eor) diff --git a/arch/metag/include/asm/atomic.h b/arch/metag/include/asm/atomic.h index 6ca210de8a7d..470e365f04ea 100644 --- a/arch/metag/include/asm/atomic.h +++ b/arch/metag/include/asm/atomic.h @@ -17,8 +17,6 @@ #include #endif -#define atomic_fetch_or atomic_fetch_or - #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic_dec_return(v) atomic_sub_return(1, (v)) diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 431079f8e483..387ce288334e 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -194,8 +194,6 @@ ATOMIC_OPS(sub, -=, subu) ATOMIC_OP(op, c_op, asm_op) \ ATOMIC_FETCH_OP(op, c_op, asm_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=, and) ATOMIC_OPS(or, |=, or) ATOMIC_OPS(xor, ^=, xor) diff --git a/arch/mn10300/include/asm/atomic.h b/arch/mn10300/include/asm/atomic.h index 3580f789f3a6..36389efd45e8 100644 --- a/arch/mn10300/include/asm/atomic.h +++ b/arch/mn10300/include/asm/atomic.h @@ -113,8 +113,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 29df1f871910..5394b9c5f914 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -148,8 +148,6 @@ ATOMIC_OPS(sub, -=) ATOMIC_OP(op, c_op) \ ATOMIC_FETCH_OP(op, c_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &=) ATOMIC_OPS(or, |=) ATOMIC_OPS(xor, ^=) diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 2324e759b544..d28cc2f5b7b2 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -135,8 +135,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ return __ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_BARRIER); \ } -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, AND) ATOMIC_OPS(or, OR) ATOMIC_OPS(xor, XOR) diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h index d93ed7ce1b2f..c399e1c55685 100644 --- a/arch/sh/include/asm/atomic.h +++ b/arch/sh/include/asm/atomic.h @@ -25,8 +25,6 @@ #include #endif -#define atomic_fetch_or atomic_fetch_or - #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0) #define atomic_dec_return(v) atomic_sub_return(1, (v)) #define atomic_inc_return(v) atomic_add_return(1, (v)) diff --git a/arch/sparc/include/asm/atomic.h b/arch/sparc/include/asm/atomic.h index 1f741bcc73b7..8ff83d8cc33f 100644 --- a/arch/sparc/include/asm/atomic.h +++ b/arch/sparc/include/asm/atomic.h @@ -5,5 +5,4 @@ #else #include #endif -#define atomic_fetch_or atomic_fetch_or #endif diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 5cfb20a599d9..ee3f11c43cda 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -36,8 +36,6 @@ void atomic_set(atomic_t *, int); #define atomic_inc(v) ((void)atomic_add_return( 1, (v))) #define atomic_dec(v) ((void)atomic_add_return( -1, (v))) -#define atomic_fetch_or atomic_fetch_or - #define atomic_and(i, v) ((void)atomic_fetch_and((i), (v))) #define atomic_or(i, v) ((void)atomic_fetch_or((i), (v))) #define atomic_xor(i, v) ((void)atomic_fetch_xor((i), (v))) diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h index 9807030557c4..8dda3c8ff5ab 100644 --- a/arch/tile/include/asm/atomic.h +++ b/arch/tile/include/asm/atomic.h @@ -48,8 +48,6 @@ static inline int atomic_read(const atomic_t *v) #define atomic_fetch_sub(i, v) atomic_fetch_add(-(int)(i), (v)) -#define atomic_fetch_or atomic_fetch_or - /** * atomic_sub - subtract integer from atomic variable * @i: integer value to subtract diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 73b8463b89e9..a58b99811105 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -217,8 +217,6 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ ATOMIC_OP(op) \ ATOMIC_FETCH_OP(op, c_op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and, &) ATOMIC_OPS(or , |) ATOMIC_OPS(xor, ^) diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h index d95a8aa1a6d3..e7a23f2a519a 100644 --- a/arch/xtensa/include/asm/atomic.h +++ b/arch/xtensa/include/asm/atomic.h @@ -188,8 +188,6 @@ ATOMIC_OPS(sub) #undef ATOMIC_OPS #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_FETCH_OP(op) -#define atomic_fetch_or atomic_fetch_or - ATOMIC_OPS(and) ATOMIC_OPS(or) ATOMIC_OPS(xor) diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index a2304ccf4ed0..9ed8b987185b 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -137,8 +137,6 @@ ATOMIC_FETCH_OP(and, &) #endif #ifndef atomic_fetch_or -#define atomic_fetch_or atomic_fetch_or - ATOMIC_FETCH_OP(or, |) #endif diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 2e6c013ac5a4..0b3802d33125 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -573,27 +573,6 @@ static inline int atomic_dec_if_positive(atomic_t *v) } #endif -/** - * atomic_fetch_or - perform *p |= mask and return old value of *p - * @mask: mask to OR on the atomic_t - * @p: pointer to atomic_t - */ -#ifndef atomic_fetch_or -static inline int atomic_fetch_or(int mask, atomic_t *p) -{ - int old, val = atomic_read(p); - - for (;;) { - old = atomic_cmpxchg(p, val, val | mask); - if (old == val) - break; - val = old; - } - - return old; -} -#endif - #ifdef CONFIG_GENERIC_ATOMIC64 #include #endif -- cgit v1.2.3 From e37837fb62f95a81bdcefa86ceea043df84937d7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Apr 2016 01:01:27 +0200 Subject: locking/atomic: Remove the deprecated atomic_{set,clear}_mask() functions These functions have been deprecated for a while and there is only the one user left, convert and kill. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Boqun Feng Cc: Davidlohr Bueso Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 10 ---------- kernel/locking/qspinlock_paravirt.h | 4 ++-- 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 0b3802d33125..12d910d61b83 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -480,16 +480,6 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v) } #endif -static inline __deprecated void atomic_clear_mask(unsigned int mask, atomic_t *v) -{ - atomic_andnot(mask, v); -} - -static inline __deprecated void atomic_set_mask(unsigned int mask, atomic_t *v) -{ - atomic_or(mask, v); -} - /** * atomic_inc_not_zero_hint - increment if not null * @v: pointer of type atomic_t diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 21ede57f68b3..37649e69056c 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -112,12 +112,12 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock) #else /* _Q_PENDING_BITS == 8 */ static __always_inline void set_pending(struct qspinlock *lock) { - atomic_set_mask(_Q_PENDING_VAL, &lock->val); + atomic_or(_Q_PENDING_VAL, &lock->val); } static __always_inline void clear_pending(struct qspinlock *lock) { - atomic_clear_mask(_Q_PENDING_VAL, &lock->val); + atomic_andnot(_Q_PENDING_VAL, &lock->val); } static __always_inline int trylock_clear_pending(struct qspinlock *lock) -- cgit v1.2.3 From 0431b9065f28ecf6c320fefebe0241620049984f Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Tue, 31 May 2016 16:59:04 -0300 Subject: staging/android: bring struct sync_pt back Move the list_head members from sync_pt to struct fence was a mistake, they will not be used by struct fence as planned before, so here we create sync_pt again to bring the list heads back. Signed-off-by: Gustavo Padovan Reviewed-by: Daniel Vetter Reviewed-by: Sumit Semwal Signed-off-by: Greg Kroah-Hartman --- drivers/staging/android/sync.c | 40 ++++++++++++++++++------------------ drivers/staging/android/sync.h | 29 ++++++++++++++++++++++---- drivers/staging/android/sync_debug.c | 16 +++++++-------- include/linux/fence.h | 2 -- 4 files changed, 53 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c index c83a599e2221..aab80ec7bce6 100644 --- a/drivers/staging/android/sync.c +++ b/drivers/staging/android/sync.c @@ -28,8 +28,6 @@ #define CREATE_TRACE_POINTS #include "trace/sync.h" -static const struct fence_ops timeline_fence_ops; - struct sync_timeline *sync_timeline_create(const char *drv_name, const char *name) { @@ -90,7 +88,7 @@ EXPORT_SYMBOL(sync_timeline_destroy); void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) { unsigned long flags; - struct fence *fence, *next; + struct sync_pt *pt, *next; trace_sync_timeline(obj); @@ -98,37 +96,37 @@ void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc) obj->value += inc; - list_for_each_entry_safe(fence, next, &obj->active_list_head, + list_for_each_entry_safe(pt, next, &obj->active_list_head, active_list) { - if (fence_is_signaled_locked(fence)) - list_del_init(&fence->active_list); + if (fence_is_signaled_locked(&pt->base)) + list_del_init(&pt->active_list); } spin_unlock_irqrestore(&obj->child_list_lock, flags); } EXPORT_SYMBOL(sync_timeline_signal); -struct fence *sync_pt_create(struct sync_timeline *obj, int size, +struct sync_pt *sync_pt_create(struct sync_timeline *obj, int size, unsigned int value) { unsigned long flags; - struct fence *fence; + struct sync_pt *pt; - if (size < sizeof(*fence)) + if (size < sizeof(*pt)) return NULL; - fence = kzalloc(size, GFP_KERNEL); - if (!fence) + pt = kzalloc(size, GFP_KERNEL); + if (!pt) return NULL; spin_lock_irqsave(&obj->child_list_lock, flags); sync_timeline_get(obj); - fence_init(fence, &timeline_fence_ops, &obj->child_list_lock, + fence_init(&pt->base, &timeline_fence_ops, &obj->child_list_lock, obj->context, value); - list_add_tail(&fence->child_list, &obj->child_list_head); - INIT_LIST_HEAD(&fence->active_list); + list_add_tail(&pt->child_list, &obj->child_list_head); + INIT_LIST_HEAD(&pt->active_list); spin_unlock_irqrestore(&obj->child_list_lock, flags); - return fence; + return pt; } EXPORT_SYMBOL(sync_pt_create); @@ -148,13 +146,14 @@ static const char *timeline_fence_get_timeline_name(struct fence *fence) static void timeline_fence_release(struct fence *fence) { + struct sync_pt *pt = fence_to_sync_pt(fence); struct sync_timeline *parent = fence_parent(fence); unsigned long flags; spin_lock_irqsave(fence->lock, flags); - list_del(&fence->child_list); - if (WARN_ON_ONCE(!list_empty(&fence->active_list))) - list_del(&fence->active_list); + list_del(&pt->child_list); + if (WARN_ON_ONCE(!list_empty(&pt->active_list))) + list_del(&pt->active_list); spin_unlock_irqrestore(fence->lock, flags); sync_timeline_put(parent); @@ -170,12 +169,13 @@ static bool timeline_fence_signaled(struct fence *fence) static bool timeline_fence_enable_signaling(struct fence *fence) { + struct sync_pt *pt = fence_to_sync_pt(fence); struct sync_timeline *parent = fence_parent(fence); if (timeline_fence_signaled(fence)) return false; - list_add_tail(&fence->active_list, &parent->active_list_head); + list_add_tail(&pt->active_list, &parent->active_list_head); return true; } @@ -193,7 +193,7 @@ static void timeline_fence_timeline_value_str(struct fence *fence, snprintf(str, size, "%d", parent->value); } -static const struct fence_ops timeline_fence_ops = { +const struct fence_ops timeline_fence_ops = { .get_driver_name = timeline_fence_get_driver_name, .get_timeline_name = timeline_fence_get_timeline_name, .enable_signaling = timeline_fence_enable_signaling, diff --git a/drivers/staging/android/sync.h b/drivers/staging/android/sync.h index f2fbf984ec6b..14b61cb18824 100644 --- a/drivers/staging/android/sync.h +++ b/drivers/staging/android/sync.h @@ -60,6 +60,27 @@ static inline struct sync_timeline *fence_parent(struct fence *fence) child_list_lock); } +/** + * struct sync_pt - sync_pt object + * @base: base fence object + * @child_list: sync timeline child's list + * @active_list: sync timeline active child's list + */ +struct sync_pt { + struct fence base; + struct list_head child_list; + struct list_head active_list; +}; + +extern const struct fence_ops timeline_fence_ops; + +static inline struct sync_pt *fence_to_sync_pt(struct fence *fence) +{ + if (fence->ops != &timeline_fence_ops) + return NULL; + return container_of(fence, struct sync_pt, base); +} + /* * API for sync_timeline implementers */ @@ -101,13 +122,13 @@ void sync_timeline_signal(struct sync_timeline *obj, unsigned int inc); * @size: size to allocate for this pt * @inc: value of the fence * - * Creates a new fence as a child of @parent. @size bytes will be + * Creates a new sync_pt as a child of @parent. @size bytes will be * allocated allowing for implementation specific data to be kept after - * the generic sync_timeline struct. Returns the fence object or + * the generic sync_timeline struct. Returns the sync_pt object or * NULL in case of error. */ -struct fence *sync_pt_create(struct sync_timeline *parent, int size, - unsigned int inc); +struct sync_pt *sync_pt_create(struct sync_timeline *parent, int size, + unsigned int inc); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/staging/android/sync_debug.c b/drivers/staging/android/sync_debug.c index cb0f8883cdb3..703f198abe5a 100644 --- a/drivers/staging/android/sync_debug.c +++ b/drivers/staging/android/sync_debug.c @@ -140,9 +140,9 @@ static void sync_print_obj(struct seq_file *s, struct sync_timeline *obj) spin_lock_irqsave(&obj->child_list_lock, flags); list_for_each(pos, &obj->child_list_head) { - struct fence *fence = - container_of(pos, struct fence, child_list); - sync_print_fence(s, fence, false); + struct sync_pt *pt = + container_of(pos, struct sync_pt, child_list); + sync_print_fence(s, &pt->base, false); } spin_unlock_irqrestore(&obj->child_list_lock, flags); } @@ -240,7 +240,7 @@ static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, { int fd = get_unused_fd_flags(O_CLOEXEC); int err; - struct fence *fence; + struct sync_pt *pt; struct sync_file *sync_file; struct sw_sync_create_fence_data data; @@ -252,15 +252,15 @@ static long sw_sync_ioctl_create_fence(struct sync_timeline *obj, goto err; } - fence = sync_pt_create(obj, sizeof(*fence), data.value); - if (!fence) { + pt = sync_pt_create(obj, sizeof(*pt), data.value); + if (!pt) { err = -ENOMEM; goto err; } - sync_file = sync_file_create(fence); + sync_file = sync_file_create(&pt->base); if (!sync_file) { - fence_put(fence); + fence_put(&pt->base); err = -ENOMEM; goto err; } diff --git a/include/linux/fence.h b/include/linux/fence.h index 2056e9fd0138..1de1b3f6fb76 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -81,8 +81,6 @@ struct fence { unsigned long flags; ktime_t timestamp; int status; - struct list_head child_list; - struct list_head active_list; }; enum fence_flag_bits { -- cgit v1.2.3 From edd14cfebc4404698544d407ecf8eda6e19aa19e Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 17 Jun 2016 16:00:20 -0600 Subject: genirq: Add untracked irq handler This adds a software irq handler for controllers that multiplex interrupts from multiple devices, but don't know which device generated the interrupt. For these devices, the irq handler that demuxes must check every action for every software irq using the same h/w irq in order to find out which device generated the interrupt. This will inevitably trigger spurious interrupt detection if we are noting the irq. The new irq handler does not track the handling for spurious interrupt detection. An irq that uses this also won't get stats tracked since it didn't generate the interrupt, nor added to randomness since they are not random. Signed-off-by: Keith Busch Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: Jon Derrick Link: http://lkml.kernel.org/r/1466200821-29159-1-git-send-email-keith.busch@intel.com Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 1 + kernel/irq/chip.c | 43 +++++++++++++++++++++++++++++++++++++++++++ kernel/irq/handle.c | 18 ++++++++++++++---- kernel/irq/internals.h | 1 + 4 files changed, 59 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 6c92a847394d..562cef010aa8 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -484,6 +484,7 @@ extern void handle_fasteoi_irq(struct irq_desc *desc); extern void handle_edge_irq(struct irq_desc *desc); extern void handle_edge_eoi_irq(struct irq_desc *desc); extern void handle_simple_irq(struct irq_desc *desc); +extern void handle_untracked_irq(struct irq_desc *desc); extern void handle_percpu_irq(struct irq_desc *desc); extern void handle_percpu_devid_irq(struct irq_desc *desc); extern void handle_bad_irq(struct irq_desc *desc); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index ad8131473774..b4c1bc7c9ca2 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -426,6 +426,49 @@ out_unlock: } EXPORT_SYMBOL_GPL(handle_simple_irq); +/** + * handle_untracked_irq - Simple and software-decoded IRQs. + * @desc: the interrupt description structure for this irq + * + * Untracked interrupts are sent from a demultiplexing interrupt + * handler when the demultiplexer does not know which device it its + * multiplexed irq domain generated the interrupt. IRQ's handled + * through here are not subjected to stats tracking, randomness, or + * spurious interrupt detection. + * + * Note: Like handle_simple_irq, the caller is expected to handle + * the ack, clear, mask and unmask issues if necessary. + */ +void handle_untracked_irq(struct irq_desc *desc) +{ + unsigned int flags = 0; + + raw_spin_lock(&desc->lock); + + if (!irq_may_run(desc)) + goto out_unlock; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + goto out_unlock; + } + + desc->istate &= ~IRQS_PENDING; + irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); + raw_spin_unlock(&desc->lock); + + __handle_irq_event_percpu(desc, &flags); + + raw_spin_lock(&desc->lock); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + +out_unlock: + raw_spin_unlock(&desc->lock); +} +EXPORT_SYMBOL_GPL(handle_untracked_irq); + /* * Called unconditionally from handle_level_irq() and only for oneshot * interrupts from handle_fasteoi_irq() diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a15b5485b446..d3f24905852c 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,10 +132,10 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) wake_up_process(action->thread); } -irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags) { irqreturn_t retval = IRQ_NONE; - unsigned int flags = 0, irq = desc->irq_data.irq; + unsigned int irq = desc->irq_data.irq; struct irqaction *action; for_each_action_of_desc(desc, action) { @@ -164,7 +164,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) /* Fall through to add to randomness */ case IRQ_HANDLED: - flags |= action->flags; + *flags |= action->flags; break; default: @@ -174,7 +174,17 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval |= res; } - add_interrupt_randomness(irq, flags); + return retval; +} + +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) +{ + irqreturn_t retval; + unsigned int flags = 0; + + retval = __handle_irq_event_percpu(desc, &flags); + + add_interrupt_randomness(desc->irq_data.irq, flags); if (!noirqdebug) note_interrupt(desc, retval); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index d5edcdc9382a..0c6f35ba9cc0 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -84,6 +84,7 @@ extern void irq_mark_irq(unsigned int irq); extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); -- cgit v1.2.3 From aa5e94a2e13377e374795de5400e346c978f46be Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 20 Jun 2016 07:42:07 -0700 Subject: Revert "usb: ohci-at91: Forcibly suspend ports while USB suspend" This reverts commit 7150bc9b4d43471fa37b26f5839892d4cf1fe09b. It is not correct, based on review from others. Reported-by: Wenyou Yang Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/atmel-usb.txt | 6 +- drivers/usb/host/ohci-at91.c | 80 +--------------------- include/soc/at91/at91_sfr.h | 29 -------- 3 files changed, 3 insertions(+), 112 deletions(-) delete mode 100644 include/soc/at91/at91_sfr.h (limited to 'include') diff --git a/Documentation/devicetree/bindings/usb/atmel-usb.txt b/Documentation/devicetree/bindings/usb/atmel-usb.txt index 888deaa8a4ca..5883b73ea1b5 100644 --- a/Documentation/devicetree/bindings/usb/atmel-usb.txt +++ b/Documentation/devicetree/bindings/usb/atmel-usb.txt @@ -3,10 +3,8 @@ Atmel SOC USB controllers OHCI Required properties: - - compatible: Should be one of the following - "atmel,at91rm9200-ohci" for USB controllers used in host mode. - "atmel,sama5d2-ohci" for USB controllers used in host mode - on SAMA5D2 which can force to suspend. + - compatible: Should be "atmel,at91rm9200-ohci" for USB controllers + used in host mode. - reg: Address and length of the register set for the device - interrupts: Should contain ehci interrupt - clocks: Should reference the peripheral, host and system clocks diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c index 54e8feb8a964..d177372bb357 100644 --- a/drivers/usb/host/ohci-at91.c +++ b/drivers/usb/host/ohci-at91.c @@ -21,11 +21,8 @@ #include #include #include -#include -#include #include #include -#include #include "ohci.h" @@ -48,18 +45,12 @@ struct at91_usbh_data { u8 overcurrent_changed[AT91_MAX_USBH_PORTS]; }; -struct ohci_at91_caps { - bool suspend_ctrl; -}; - struct ohci_at91_priv { struct clk *iclk; struct clk *fclk; struct clk *hclk; bool clocked; bool wakeup; /* Saved wake-up state for resume */ - const struct ohci_at91_caps *caps; - struct regmap *sfr_regmap; }; /* interface and function clocks; sometimes also an AHB clock */ @@ -141,17 +132,6 @@ static void at91_stop_hc(struct platform_device *pdev) /*-------------------------------------------------------------------------*/ -struct regmap *at91_dt_syscon_sfr(void) -{ - struct regmap *regmap; - - regmap = syscon_regmap_lookup_by_compatible("atmel,sama5d2-sfr"); - if (IS_ERR(regmap)) - regmap = NULL; - - return regmap; -} - static void usb_hcd_at91_remove (struct usb_hcd *, struct platform_device *); /* configure so an HC device and id are always provided */ @@ -217,17 +197,6 @@ static int usb_hcd_at91_probe(const struct hc_driver *driver, goto err; } - ohci_at91->caps = (const struct ohci_at91_caps *) - of_device_get_match_data(&pdev->dev); - if (!ohci_at91->caps) - return -ENODEV; - - if (ohci_at91->caps->suspend_ctrl) { - ohci_at91->sfr_regmap = at91_dt_syscon_sfr(); - if (!ohci_at91->sfr_regmap) - dev_warn(dev, "failed to find sfr node\n"); - } - board = hcd->self.controller->platform_data; ohci = hcd_to_ohci(hcd); ohci->num_ports = board->ports; @@ -471,17 +440,8 @@ static irqreturn_t ohci_hcd_at91_overcurrent_irq(int irq, void *data) return IRQ_HANDLED; } -static const struct ohci_at91_caps at91rm9200_caps = { - .suspend_ctrl = false, -}; - -static const struct ohci_at91_caps sama5d2_caps = { - .suspend_ctrl = true, -}; - static const struct of_device_id at91_ohci_dt_ids[] = { - { .compatible = "atmel,at91rm9200-ohci", .data = &at91rm9200_caps }, - { .compatible = "atmel,sama5d2-ohci", .data = &sama5d2_caps }, + { .compatible = "atmel,at91rm9200-ohci" }, { /* sentinel */ } }; @@ -621,38 +581,6 @@ static int ohci_hcd_at91_drv_remove(struct platform_device *pdev) return 0; } -static int ohci_at91_port_ctrl(struct regmap *regmap, bool enable) -{ - u32 regval; - int ret; - - if (!regmap) - return -EINVAL; - - ret = regmap_read(regmap, SFR_OHCIICR, ®val); - if (ret) - return ret; - - if (enable) - regval &= ~SFR_OHCIICR_USB_SUSPEND; - else - regval |= SFR_OHCIICR_USB_SUSPEND; - - regmap_write(regmap, SFR_OHCIICR, regval); - - return 0; -} - -static int ohci_at91_port_suspend(struct regmap *regmap) -{ - return ohci_at91_port_ctrl(regmap, false); -} - -static int ohci_at91_port_resume(struct regmap *regmap) -{ - return ohci_at91_port_ctrl(regmap, true); -} - static int __maybe_unused ohci_hcd_at91_drv_suspend(struct device *dev) { @@ -690,9 +618,6 @@ ohci_hcd_at91_drv_suspend(struct device *dev) ohci_writel(ohci, ohci->hc_control, &ohci->regs->control); ohci->rh_state = OHCI_RH_HALTED; - if (ohci_at91->caps->suspend_ctrl) - ohci_at91_port_suspend(ohci_at91->sfr_regmap); - /* flush the writes */ (void) ohci_readl (ohci, &ohci->regs->control); at91_stop_clock(ohci_at91); @@ -712,9 +637,6 @@ ohci_hcd_at91_drv_resume(struct device *dev) at91_start_clock(ohci_at91); - if (ohci_at91->caps->suspend_ctrl) - ohci_at91_port_resume(ohci_at91->sfr_regmap); - ohci_resume(hcd, false); return 0; } diff --git a/include/soc/at91/at91_sfr.h b/include/soc/at91/at91_sfr.h deleted file mode 100644 index 04a3a1eee22e..000000000000 --- a/include/soc/at91/at91_sfr.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Header file for the Atmel DDR/SDR SDRAM Controller - * - * Copyright (C) 2016 Atmel Corporation - * - * Author: Wenyou Yang - * - * 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 __AT91_SFR_H__ -#define __AT91_SFR_H__ - -#define SFR_DDRCFG 0x04 /* DDR Configuration Register */ -/* 0x08 ~ 0x0c: Reserved */ -#define SFR_OHCIICR 0x10 /* OHCI Interrupt Configuration Register */ -#define SFR_OHCIISR 0x14 /* OHCI Interrupt Status Register */ - -#define SFR_OHCIICR_SUSPEND_A BIT(8) -#define SFR_OHCIICR_SUSPEND_B BIT(9) -#define SFR_OHCIICR_SUSPEND_C BIT(10) - -#define SFR_OHCIICR_USB_SUSPEND (SFR_OHCIICR_SUSPEND_A | \ - SFR_OHCIICR_SUSPEND_B | \ - SFR_OHCIICR_SUSPEND_C) - -#endif -- cgit v1.2.3 From af4afb40085f04f8b2ea8d28df878f7f0be02f89 Mon Sep 17 00:00:00 2001 From: Pratyush Patel Date: Tue, 14 Jun 2016 11:00:42 +0200 Subject: alarmtimer: Fix comments describing structure fields Updated struct alarm and struct alarm_timer descriptions. Cc: Prarit Bhargava Cc: Richard Cochran Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Pratyush Patel Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 6 +++--- kernel/time/alarmtimer.c | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 52f3b7da4f2d..9d8031257a90 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -26,10 +26,10 @@ enum alarmtimer_restart { * struct alarm - Alarm timer structure * @node: timerqueue node for adding to the event list this value * also includes the expiration time. - * @period: Period for recuring alarms + * @timer: hrtimer used to schedule events while running * @function: Function pointer to be executed when the timer fires. - * @type: Alarm type (BOOTTIME/REALTIME) - * @enabled: Flag that represents if the alarm is set to fire or not + * @type: Alarm type (BOOTTIME/REALTIME). + * @state: Flag that represents if the alarm is set to fire or not. * @data: Internal data value. */ struct alarm { diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index e840ed867a5d..c3aad685bbc0 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -30,7 +30,6 @@ * struct alarm_base - Alarm timer bases * @lock: Lock for syncrhonized access to the base * @timerqueue: Timerqueue head managing the list of events - * @timer: hrtimer used to schedule events while running * @gettime: Function to read the time correlating to the base * @base_clockid: clockid for the base */ -- cgit v1.2.3 From e6c2682a1da36a2e79d9bab470412374434ce89e Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 8 Jun 2016 22:04:59 -0700 Subject: time: Add time64_to_tm() time_to_tm() takes time_t as an argument. time_t is not y2038 safe. Add time64_to_tm() that takes time64_t as an argument which is y2038 safe. The plan is to eventually replace all calls to time_to_tm() by time64_to_tm(). Cc: Prarit Bhargava Cc: Richard Cochran Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Deepa Dinamani Signed-off-by: John Stultz --- include/linux/time.h | 15 ++++++++++++++- kernel/time/timeconv.c | 11 ++++++----- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/time.h b/include/linux/time.h index 297f09f23896..4cea09d94208 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -205,7 +205,20 @@ struct tm { int tm_yday; }; -void time_to_tm(time_t totalsecs, int offset, struct tm *result); +void time64_to_tm(time64_t totalsecs, int offset, struct tm *result); + +/** + * time_to_tm - converts the calendar time to local broken-down time + * + * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, + * Coordinated Universal Time (UTC). + * @offset offset seconds adding to totalsecs. + * @result pointer to struct tm variable to receive broken-down time + */ +static inline void time_to_tm(time_t totalsecs, int offset, struct tm *result) +{ + time64_to_tm(totalsecs, offset, result); +} /** * timespec_to_ns - Convert timespec to nanoseconds diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c index 86628e755f38..7142580ad94f 100644 --- a/kernel/time/timeconv.c +++ b/kernel/time/timeconv.c @@ -67,20 +67,21 @@ static const unsigned short __mon_yday[2][13] = { #define SECS_PER_DAY (SECS_PER_HOUR * 24) /** - * time_to_tm - converts the calendar time to local broken-down time + * time64_to_tm - converts the calendar time to local broken-down time * * @totalsecs the number of seconds elapsed since 00:00:00 on January 1, 1970, * Coordinated Universal Time (UTC). * @offset offset seconds adding to totalsecs. * @result pointer to struct tm variable to receive broken-down time */ -void time_to_tm(time_t totalsecs, int offset, struct tm *result) +void time64_to_tm(time64_t totalsecs, int offset, struct tm *result) { long days, rem, y; + int remainder; const unsigned short *ip; - days = totalsecs / SECS_PER_DAY; - rem = totalsecs % SECS_PER_DAY; + days = div_s64_rem(totalsecs, SECS_PER_DAY, &remainder); + rem = remainder; rem += offset; while (rem < 0) { rem += SECS_PER_DAY; @@ -124,4 +125,4 @@ void time_to_tm(time_t totalsecs, int offset, struct tm *result) result->tm_mon = y; result->tm_mday = days + 1; } -EXPORT_SYMBOL(time_to_tm); +EXPORT_SYMBOL(time64_to_tm); -- cgit v1.2.3 From 5a8d651a2bde01e00caf78496390d6ae46df80af Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 31 May 2016 13:07:47 +0300 Subject: usb: gadget: move gadget API functions to udc-core instead of defining all functions as static inlines, let's move them to udc-core and export them with EXPORT_SYMBOL_GPL, that way we can make sure that only GPL drivers will use them. As a side effect, it'll be nicer to add tracepoints to the gadget API. While at that, also fix Kconfig dependencies to avoid randconfig build failures. Acked-By: Sebastian Reichel Acked-by: Peter Chen Signed-off-by: Felipe Balbi --- drivers/phy/Kconfig | 1 + drivers/power/Kconfig | 1 + drivers/usb/gadget/udc/udc-core.c | 573 +++++++++++++++++++++++++++++++++++++ drivers/usb/host/Kconfig | 2 +- drivers/usb/phy/Kconfig | 11 +- include/linux/usb/gadget.h | 585 ++++---------------------------------- 6 files changed, 645 insertions(+), 528 deletions(-) (limited to 'include') diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index b869b98835f4..8d1cfb7f3ea2 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -176,6 +176,7 @@ config TWL4030_USB tristate "TWL4030 USB Transceiver Driver" depends on TWL4030_CORE && REGULATOR_TWL4030 && USB_MUSB_OMAP2PLUS depends on USB_SUPPORT + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't 'y' select GENERIC_PHY select USB_PHY help diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig index 421770ddafa3..0f11a0f4c369 100644 --- a/drivers/power/Kconfig +++ b/drivers/power/Kconfig @@ -309,6 +309,7 @@ config BATTERY_RX51 config CHARGER_ISP1704 tristate "ISP1704 USB Charger Detection" depends on USB_PHY + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' help Say Y to enable support for USB Charger Detection with ISP1707/ISP1704 USB transceivers. diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index e1b2dcebdc2e..abf013865e51 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -59,6 +59,579 @@ static int udc_bind_to_driver(struct usb_udc *udc, /* ------------------------------------------------------------------------- */ +/** + * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint + * @ep:the endpoint being configured + * @maxpacket_limit:value of maximum packet size limit + * + * This function should be used only in UDC drivers to initialize endpoint + * (usually in probe function). + */ +void usb_ep_set_maxpacket_limit(struct usb_ep *ep, + unsigned maxpacket_limit) +{ + ep->maxpacket_limit = maxpacket_limit; + ep->maxpacket = maxpacket_limit; +} +EXPORT_SYMBOL_GPL(usb_ep_set_maxpacket_limit); + +/** + * usb_ep_enable - configure endpoint, making it usable + * @ep:the endpoint being configured. may not be the endpoint named "ep0". + * drivers discover endpoints through the ep_list of a usb_gadget. + * + * When configurations are set, or when interface settings change, the driver + * will enable or disable the relevant endpoints. while it is enabled, an + * endpoint may be used for i/o until the driver receives a disconnect() from + * the host or until the endpoint is disabled. + * + * the ep0 implementation (which calls this routine) must ensure that the + * hardware capabilities of each endpoint match the descriptor provided + * for it. for example, an endpoint named "ep2in-bulk" would be usable + * for interrupt transfers as well as bulk, but it likely couldn't be used + * for iso transfers or for endpoint 14. some endpoints are fully + * configurable, with more generic names like "ep-a". (remember that for + * USB, "in" means "towards the USB master".) + * + * returns zero, or a negative error code. + */ +int usb_ep_enable(struct usb_ep *ep) +{ + int ret; + + if (ep->enabled) + return 0; + + ret = ep->ops->enable(ep, ep->desc); + if (ret) + return ret; + + ep->enabled = true; + + return 0; +} +EXPORT_SYMBOL_GPL(usb_ep_enable); + +/** + * usb_ep_disable - endpoint is no longer usable + * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". + * + * no other task may be using this endpoint when this is called. + * any pending and uncompleted requests will complete with status + * indicating disconnect (-ESHUTDOWN) before this call returns. + * gadget drivers must call usb_ep_enable() again before queueing + * requests to the endpoint. + * + * returns zero, or a negative error code. + */ +int usb_ep_disable(struct usb_ep *ep) +{ + int ret; + + if (!ep->enabled) + return 0; + + ret = ep->ops->disable(ep); + if (ret) + return ret; + + ep->enabled = false; + + return 0; +} +EXPORT_SYMBOL_GPL(usb_ep_disable); + +/** + * usb_ep_alloc_request - allocate a request object to use with this endpoint + * @ep:the endpoint to be used with with the request + * @gfp_flags:GFP_* flags to use + * + * Request objects must be allocated with this call, since they normally + * need controller-specific setup and may even need endpoint-specific + * resources such as allocation of DMA descriptors. + * Requests may be submitted with usb_ep_queue(), and receive a single + * completion callback. Free requests with usb_ep_free_request(), when + * they are no longer needed. + * + * Returns the request, or null if one could not be allocated. + */ +struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, + gfp_t gfp_flags) +{ + return ep->ops->alloc_request(ep, gfp_flags); +} +EXPORT_SYMBOL_GPL(usb_ep_alloc_request); + +/** + * usb_ep_free_request - frees a request object + * @ep:the endpoint associated with the request + * @req:the request being freed + * + * Reverses the effect of usb_ep_alloc_request(). + * Caller guarantees the request is not queued, and that it will + * no longer be requeued (or otherwise used). + */ +void usb_ep_free_request(struct usb_ep *ep, + struct usb_request *req) +{ + ep->ops->free_request(ep, req); +} +EXPORT_SYMBOL_GPL(usb_ep_free_request); + +/** + * usb_ep_queue - queues (submits) an I/O request to an endpoint. + * @ep:the endpoint associated with the request + * @req:the request being submitted + * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't + * pre-allocate all necessary memory with the request. + * + * This tells the device controller to perform the specified request through + * that endpoint (reading or writing a buffer). When the request completes, + * including being canceled by usb_ep_dequeue(), the request's completion + * routine is called to return the request to the driver. Any endpoint + * (except control endpoints like ep0) may have more than one transfer + * request queued; they complete in FIFO order. Once a gadget driver + * submits a request, that request may not be examined or modified until it + * is given back to that driver through the completion callback. + * + * Each request is turned into one or more packets. The controller driver + * never merges adjacent requests into the same packet. OUT transfers + * will sometimes use data that's already buffered in the hardware. + * Drivers can rely on the fact that the first byte of the request's buffer + * always corresponds to the first byte of some USB packet, for both + * IN and OUT transfers. + * + * Bulk endpoints can queue any amount of data; the transfer is packetized + * automatically. The last packet will be short if the request doesn't fill it + * out completely. Zero length packets (ZLPs) should be avoided in portable + * protocols since not all usb hardware can successfully handle zero length + * packets. (ZLPs may be explicitly written, and may be implicitly written if + * the request 'zero' flag is set.) Bulk endpoints may also be used + * for interrupt transfers; but the reverse is not true, and some endpoints + * won't support every interrupt transfer. (Such as 768 byte packets.) + * + * Interrupt-only endpoints are less functional than bulk endpoints, for + * example by not supporting queueing or not handling buffers that are + * larger than the endpoint's maxpacket size. They may also treat data + * toggle differently. + * + * Control endpoints ... after getting a setup() callback, the driver queues + * one response (even if it would be zero length). That enables the + * status ack, after transferring data as specified in the response. Setup + * functions may return negative error codes to generate protocol stalls. + * (Note that some USB device controllers disallow protocol stall responses + * in some cases.) When control responses are deferred (the response is + * written after the setup callback returns), then usb_ep_set_halt() may be + * used on ep0 to trigger protocol stalls. Depending on the controller, + * it may not be possible to trigger a status-stage protocol stall when the + * data stage is over, that is, from within the response's completion + * routine. + * + * For periodic endpoints, like interrupt or isochronous ones, the usb host + * arranges to poll once per interval, and the gadget driver usually will + * have queued some data to transfer at that time. + * + * Returns zero, or a negative error code. Endpoints that are not enabled + * report errors; errors will also be + * reported when the usb peripheral is disconnected. + */ +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); +} +EXPORT_SYMBOL_GPL(usb_ep_queue); + +/** + * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint + * @ep:the endpoint associated with the request + * @req:the request being canceled + * + * If the request is still active on the endpoint, it is dequeued and its + * completion routine is called (with status -ECONNRESET); else a negative + * error code is returned. This is guaranteed to happen before the call to + * usb_ep_dequeue() returns. + * + * Note that some hardware can't clear out write fifos (to unlink the request + * at the head of the queue) except as part of disconnecting from usb. Such + * restrictions prevent drivers from supporting configuration changes, + * even to configuration zero (a "chapter 9" requirement). + */ +int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) +{ + return ep->ops->dequeue(ep, req); +} +EXPORT_SYMBOL_GPL(usb_ep_dequeue); + +/** + * usb_ep_set_halt - sets the endpoint halt feature. + * @ep: the non-isochronous endpoint being stalled + * + * Use this to stall an endpoint, perhaps as an error report. + * Except for control endpoints, + * the endpoint stays halted (will not stream any data) until the host + * clears this feature; drivers may need to empty the endpoint's request + * queue first, to make sure no inappropriate transfers happen. + * + * Note that while an endpoint CLEAR_FEATURE will be invisible to the + * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the + * current altsetting, see usb_ep_clear_halt(). When switching altsettings, + * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. + * + * Returns zero, or a negative error code. On success, this call sets + * underlying hardware state that blocks data transfers. + * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any + * transfer requests are still queued, or if the controller hardware + * (usually a FIFO) still holds bytes that the host hasn't collected. + */ +int usb_ep_set_halt(struct usb_ep *ep) +{ + return ep->ops->set_halt(ep, 1); +} +EXPORT_SYMBOL_GPL(usb_ep_set_halt); + +/** + * usb_ep_clear_halt - clears endpoint halt, and resets toggle + * @ep:the bulk or interrupt endpoint being reset + * + * Use this when responding to the standard usb "set interface" request, + * for endpoints that aren't reconfigured, after clearing any other state + * in the endpoint's i/o queue. + * + * Returns zero, or a negative error code. On success, this call clears + * the underlying hardware state reflecting endpoint halt and data toggle. + * Note that some hardware can't support this request (like pxa2xx_udc), + * and accordingly can't correctly implement interface altsettings. + */ +int usb_ep_clear_halt(struct usb_ep *ep) +{ + return ep->ops->set_halt(ep, 0); +} +EXPORT_SYMBOL_GPL(usb_ep_clear_halt); + +/** + * usb_ep_set_wedge - sets the halt feature and ignores clear requests + * @ep: the endpoint being wedged + * + * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) + * requests. If the gadget driver clears the halt status, it will + * automatically unwedge the endpoint. + * + * Returns zero on success, else negative errno. + */ +int usb_ep_set_wedge(struct usb_ep *ep) +{ + if (ep->ops->set_wedge) + return ep->ops->set_wedge(ep); + else + return ep->ops->set_halt(ep, 1); +} +EXPORT_SYMBOL_GPL(usb_ep_set_wedge); + +/** + * usb_ep_fifo_status - returns number of bytes in fifo, or error + * @ep: the endpoint whose fifo status is being checked. + * + * FIFO endpoints may have "unclaimed data" in them in certain cases, + * such as after aborted transfers. Hosts may not have collected all + * the IN data written by the gadget driver (and reported by a request + * completion). The gadget driver may not have collected all the data + * written OUT to it by the host. Drivers that need precise handling for + * fault reporting or recovery may need to use this call. + * + * This returns the number of such bytes in the fifo, or a negative + * errno if the endpoint doesn't use a FIFO or doesn't support such + * precise handling. + */ +int usb_ep_fifo_status(struct usb_ep *ep) +{ + if (ep->ops->fifo_status) + return ep->ops->fifo_status(ep); + else + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(usb_ep_fifo_status); + +/** + * usb_ep_fifo_flush - flushes contents of a fifo + * @ep: the endpoint whose fifo is being flushed. + * + * This call may be used to flush the "unclaimed data" that may exist in + * an endpoint fifo after abnormal transaction terminations. The call + * must never be used except when endpoint is not being used for any + * protocol translation. + */ +void usb_ep_fifo_flush(struct usb_ep *ep) +{ + if (ep->ops->fifo_flush) + ep->ops->fifo_flush(ep); +} +EXPORT_SYMBOL_GPL(usb_ep_fifo_flush); + +/* ------------------------------------------------------------------------- */ + +/** + * usb_gadget_frame_number - returns the current frame number + * @gadget: controller that reports the frame number + * + * Returns the usb frame number, normally eleven bits from a SOF packet, + * or negative errno if this device doesn't support this capability. + */ +int usb_gadget_frame_number(struct usb_gadget *gadget) +{ + return gadget->ops->get_frame(gadget); +} +EXPORT_SYMBOL_GPL(usb_gadget_frame_number); + +/** + * usb_gadget_wakeup - tries to wake up the host connected to this gadget + * @gadget: controller used to wake up the host + * + * Returns zero on success, else negative error code if the hardware + * doesn't support such attempts, or its support has not been enabled + * by the usb host. Drivers must return device descriptors that report + * their ability to support this, or hosts won't enable it. + * + * This may also try to use SRP to wake the host and start enumeration, + * even if OTG isn't otherwise in use. OTG devices may also start + * remote wakeup even when hosts don't explicitly enable it. + */ +int usb_gadget_wakeup(struct usb_gadget *gadget) +{ + if (!gadget->ops->wakeup) + return -EOPNOTSUPP; + return gadget->ops->wakeup(gadget); +} +EXPORT_SYMBOL_GPL(usb_gadget_wakeup); + +/** + * usb_gadget_set_selfpowered - sets the device selfpowered feature. + * @gadget:the device being declared as self-powered + * + * this affects the device status reported by the hardware driver + * to reflect that it now has a local power supply. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_set_selfpowered(struct usb_gadget *gadget) +{ + if (!gadget->ops->set_selfpowered) + return -EOPNOTSUPP; + return gadget->ops->set_selfpowered(gadget, 1); +} +EXPORT_SYMBOL_GPL(usb_gadget_set_selfpowered); + +/** + * usb_gadget_clear_selfpowered - clear the device selfpowered feature. + * @gadget:the device being declared as bus-powered + * + * this affects the device status reported by the hardware driver. + * some hardware may not support bus-powered operation, in which + * case this feature's value can never change. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) +{ + if (!gadget->ops->set_selfpowered) + return -EOPNOTSUPP; + return gadget->ops->set_selfpowered(gadget, 0); +} +EXPORT_SYMBOL_GPL(usb_gadget_clear_selfpowered); + +/** + * usb_gadget_vbus_connect - Notify controller that VBUS is powered + * @gadget:The device which now has VBUS power. + * Context: can sleep + * + * This call is used by a driver for an external transceiver (or GPIO) + * that detects a VBUS power session starting. Common responses include + * resuming the controller, activating the D+ (or D-) pullup to let the + * host detect that a USB device is attached, and starting to draw power + * (8mA or possibly more, especially after SET_CONFIGURATION). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_connect(struct usb_gadget *gadget) +{ + if (!gadget->ops->vbus_session) + return -EOPNOTSUPP; + return gadget->ops->vbus_session(gadget, 1); +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_connect); + +/** + * usb_gadget_vbus_draw - constrain controller's VBUS power usage + * @gadget:The device whose VBUS usage is being described + * @mA:How much current to draw, in milliAmperes. This should be twice + * the value listed in the configuration descriptor bMaxPower field. + * + * This call is used by gadget drivers during SET_CONFIGURATION calls, + * reporting how much power the device may consume. For example, this + * could affect how quickly batteries are recharged. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) +{ + if (!gadget->ops->vbus_draw) + return -EOPNOTSUPP; + return gadget->ops->vbus_draw(gadget, mA); +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_draw); + +/** + * usb_gadget_vbus_disconnect - notify controller about VBUS session end + * @gadget:the device whose VBUS supply is being described + * Context: can sleep + * + * This call is used by a driver for an external transceiver (or GPIO) + * that detects a VBUS power session ending. Common responses include + * reversing everything done in usb_gadget_vbus_connect(). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) +{ + if (!gadget->ops->vbus_session) + return -EOPNOTSUPP; + return gadget->ops->vbus_session(gadget, 0); +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); + +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). This pullup is always enabled unless + * usb_gadget_disconnect() has been used to disable it. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) +{ + int ret; + + if (!gadget->ops->pullup) + return -EOPNOTSUPP; + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will be connected automatically after activation. + */ + gadget->connected = true; + return 0; + } + + ret = gadget->ops->pullup(gadget, 1); + if (!ret) + gadget->connected = 1; + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_connect); + +/** + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected + * + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_disconnect(struct usb_gadget *gadget) +{ + int ret; + + if (!gadget->ops->pullup) + return -EOPNOTSUPP; + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will stay disconnected after activation. + */ + gadget->connected = false; + return 0; + } + + ret = gadget->ops->pullup(gadget, 0); + if (!ret) + gadget->connected = 0; + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_disconnect); + +/** + * usb_gadget_deactivate - deactivate function which is not ready to work + * @gadget: the peripheral being deactivated + * + * This routine may be used during the gadget driver bind() call to prevent + * the peripheral from ever being visible to the USB host, unless later + * usb_gadget_activate() is called. For example, user mode components may + * need to be activated before the system can talk to hosts. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_deactivate(struct usb_gadget *gadget) +{ + int ret; + + if (gadget->deactivated) + return 0; + + if (gadget->connected) { + ret = usb_gadget_disconnect(gadget); + if (ret) + return ret; + /* + * If gadget was being connected before deactivation, we want + * to reconnect it in usb_gadget_activate(). + */ + gadget->connected = true; + } + gadget->deactivated = true; + + return 0; +} +EXPORT_SYMBOL_GPL(usb_gadget_deactivate); + +/** + * usb_gadget_activate - activate function which is not ready to work + * @gadget: the peripheral being activated + * + * This routine activates gadget which was previously deactivated with + * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_activate(struct usb_gadget *gadget) +{ + if (!gadget->deactivated) + return 0; + + gadget->deactivated = false; + + /* + * If gadget has been connected before deactivation, or became connected + * while it was being deactivated, we call usb_gadget_connect(). + */ + if (gadget->connected) + return usb_gadget_connect(gadget); + + return 0; +} +EXPORT_SYMBOL_GPL(usb_gadget_activate); + +/* ------------------------------------------------------------------------- */ + #ifdef CONFIG_HAS_DMA int usb_gadget_map_request_by_dev(struct device *dev, diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index d8f5674809e8..2e710a4cca52 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -180,7 +180,7 @@ config USB_EHCI_MXC config USB_EHCI_HCD_OMAP tristate "EHCI support for OMAP3 and later chips" depends on ARCH_OMAP - select NOP_USB_XCEIV + depends on NOP_USB_XCEIV default y ---help--- Enables support for the on-chip EHCI controller on diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index c6904742e2aa..b9c409a18faa 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -21,6 +21,7 @@ config AB8500_USB config FSL_USB2_OTG bool "Freescale USB OTG Transceiver Driver" depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help Enable this to support Freescale USB OTG transceiver. @@ -29,6 +30,7 @@ config ISP1301_OMAP tristate "Philips ISP1301 with OMAP OTG" depends on I2C && ARCH_OMAP_OTG depends on USB + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help If you say yes here you get support for the Philips ISP1301 @@ -43,7 +45,7 @@ config ISP1301_OMAP config KEYSTONE_USB_PHY tristate "Keystone USB PHY Driver" depends on ARCH_KEYSTONE || COMPILE_TEST - select NOP_USB_XCEIV + depends on NOP_USB_XCEIV help Enable this to support Keystone USB phy. This driver provides interface to interact with USB 2.0 and USB 3.0 PHY that is part @@ -51,6 +53,7 @@ config KEYSTONE_USB_PHY config NOP_USB_XCEIV tristate "NOP USB Transceiver Driver" + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, NOP can't be built-in select USB_PHY help This driver is to be used by all the usb transceiver which are either @@ -63,9 +66,9 @@ config AM335X_CONTROL_USB config AM335X_PHY_USB tristate "AM335x USB PHY Driver" depends on ARM || COMPILE_TEST + depends on NOP_USB_XCEIV select USB_PHY select AM335X_CONTROL_USB - select NOP_USB_XCEIV select USB_COMMON help This driver provides PHY support for that phy which part for the @@ -92,6 +95,7 @@ config TWL6030_USB config USB_GPIO_VBUS tristate "GPIO based peripheral-only VBUS sensing 'transceiver'" depends on GPIOLIB || COMPILE_TEST + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help Provides simple GPIO VBUS sensing for controllers with an @@ -112,6 +116,7 @@ config OMAP_OTG config TAHVO_USB tristate "Tahvo USB transceiver driver" depends on MFD_RETU && EXTCON + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help Enable this to support USB transceiver on Tahvo. This is used @@ -140,6 +145,7 @@ config USB_ISP1301 config USB_MSM_OTG tristate "Qualcomm on-chip USB OTG controller support" depends on (USB || USB_GADGET) && (ARCH_QCOM || COMPILE_TEST) + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' depends on RESET_CONTROLLER depends on EXTCON select USB_PHY @@ -169,6 +175,7 @@ config USB_QCOM_8X16_PHY config USB_MV_OTG tristate "Marvell USB OTG support" depends on USB_EHCI_MV && USB_MV_UDC && PM && USB_OTG + depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help Say Y here if you want to build Marvell USB OTG transciever diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index fefe8b06a63d..c6e1149ddb0d 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -228,307 +228,49 @@ struct usb_ep { /*-------------------------------------------------------------------------*/ -/** - * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint - * @ep:the endpoint being configured - * @maxpacket_limit:value of maximum packet size limit - * - * This function should be used only in UDC drivers to initialize endpoint - * (usually in probe function). - */ +#if IS_ENABLED(CONFIG_USB_GADGET) +void usb_ep_set_maxpacket_limit(struct usb_ep *ep, unsigned maxpacket_limit); +int usb_ep_enable(struct usb_ep *ep); +int usb_ep_disable(struct usb_ep *ep); +struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, gfp_t gfp_flags); +void usb_ep_free_request(struct usb_ep *ep, struct usb_request *req); +int usb_ep_queue(struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags); +int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req); +int usb_ep_set_halt(struct usb_ep *ep); +int usb_ep_clear_halt(struct usb_ep *ep); +int usb_ep_set_wedge(struct usb_ep *ep); +int usb_ep_fifo_status(struct usb_ep *ep); +void usb_ep_fifo_flush(struct usb_ep *ep); +#else static inline void usb_ep_set_maxpacket_limit(struct usb_ep *ep, - unsigned maxpacket_limit) -{ - ep->maxpacket_limit = maxpacket_limit; - ep->maxpacket = maxpacket_limit; -} - -/** - * usb_ep_enable - configure endpoint, making it usable - * @ep:the endpoint being configured. may not be the endpoint named "ep0". - * drivers discover endpoints through the ep_list of a usb_gadget. - * - * When configurations are set, or when interface settings change, the driver - * will enable or disable the relevant endpoints. while it is enabled, an - * endpoint may be used for i/o until the driver receives a disconnect() from - * the host or until the endpoint is disabled. - * - * the ep0 implementation (which calls this routine) must ensure that the - * hardware capabilities of each endpoint match the descriptor provided - * for it. for example, an endpoint named "ep2in-bulk" would be usable - * for interrupt transfers as well as bulk, but it likely couldn't be used - * for iso transfers or for endpoint 14. some endpoints are fully - * configurable, with more generic names like "ep-a". (remember that for - * USB, "in" means "towards the USB master".) - * - * returns zero, or a negative error code. - */ + unsigned maxpacket_limit) +{ } static inline int usb_ep_enable(struct usb_ep *ep) -{ - int ret; - - if (ep->enabled) - return 0; - - ret = ep->ops->enable(ep, ep->desc); - if (ret) - return ret; - - ep->enabled = true; - - return 0; -} - -/** - * usb_ep_disable - endpoint is no longer usable - * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". - * - * no other task may be using this endpoint when this is called. - * any pending and uncompleted requests will complete with status - * indicating disconnect (-ESHUTDOWN) before this call returns. - * gadget drivers must call usb_ep_enable() again before queueing - * requests to the endpoint. - * - * returns zero, or a negative error code. - */ +{ return 0; } static inline int usb_ep_disable(struct usb_ep *ep) -{ - int ret; - - if (!ep->enabled) - return 0; - - ret = ep->ops->disable(ep); - if (ret) - return ret; - - ep->enabled = false; - - return 0; -} - -/** - * usb_ep_alloc_request - allocate a request object to use with this endpoint - * @ep:the endpoint to be used with with the request - * @gfp_flags:GFP_* flags to use - * - * Request objects must be allocated with this call, since they normally - * need controller-specific setup and may even need endpoint-specific - * resources such as allocation of DMA descriptors. - * Requests may be submitted with usb_ep_queue(), and receive a single - * completion callback. Free requests with usb_ep_free_request(), when - * they are no longer needed. - * - * Returns the request, or null if one could not be allocated. - */ +{ return 0; } static inline struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, - gfp_t gfp_flags) -{ - return ep->ops->alloc_request(ep, gfp_flags); -} - -/** - * usb_ep_free_request - frees a request object - * @ep:the endpoint associated with the request - * @req:the request being freed - * - * Reverses the effect of usb_ep_alloc_request(). - * Caller guarantees the request is not queued, and that it will - * no longer be requeued (or otherwise used). - */ + gfp_t gfp_flags) +{ return NULL; } static inline void usb_ep_free_request(struct usb_ep *ep, - struct usb_request *req) -{ - ep->ops->free_request(ep, req); -} - -/** - * usb_ep_queue - queues (submits) an I/O request to an endpoint. - * @ep:the endpoint associated with the request - * @req:the request being submitted - * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't - * pre-allocate all necessary memory with the request. - * - * This tells the device controller to perform the specified request through - * that endpoint (reading or writing a buffer). When the request completes, - * including being canceled by usb_ep_dequeue(), the request's completion - * routine is called to return the request to the driver. Any endpoint - * (except control endpoints like ep0) may have more than one transfer - * request queued; they complete in FIFO order. Once a gadget driver - * submits a request, that request may not be examined or modified until it - * is given back to that driver through the completion callback. - * - * Each request is turned into one or more packets. The controller driver - * never merges adjacent requests into the same packet. OUT transfers - * will sometimes use data that's already buffered in the hardware. - * Drivers can rely on the fact that the first byte of the request's buffer - * always corresponds to the first byte of some USB packet, for both - * IN and OUT transfers. - * - * Bulk endpoints can queue any amount of data; the transfer is packetized - * automatically. The last packet will be short if the request doesn't fill it - * out completely. Zero length packets (ZLPs) should be avoided in portable - * protocols since not all usb hardware can successfully handle zero length - * packets. (ZLPs may be explicitly written, and may be implicitly written if - * the request 'zero' flag is set.) Bulk endpoints may also be used - * for interrupt transfers; but the reverse is not true, and some endpoints - * won't support every interrupt transfer. (Such as 768 byte packets.) - * - * Interrupt-only endpoints are less functional than bulk endpoints, for - * example by not supporting queueing or not handling buffers that are - * larger than the endpoint's maxpacket size. They may also treat data - * toggle differently. - * - * Control endpoints ... after getting a setup() callback, the driver queues - * one response (even if it would be zero length). That enables the - * status ack, after transferring data as specified in the response. Setup - * functions may return negative error codes to generate protocol stalls. - * (Note that some USB device controllers disallow protocol stall responses - * in some cases.) When control responses are deferred (the response is - * written after the setup callback returns), then usb_ep_set_halt() may be - * used on ep0 to trigger protocol stalls. Depending on the controller, - * it may not be possible to trigger a status-stage protocol stall when the - * data stage is over, that is, from within the response's completion - * routine. - * - * For periodic endpoints, like interrupt or isochronous ones, the usb host - * arranges to poll once per interval, and the gadget driver usually will - * have queued some data to transfer at that time. - * - * Returns zero, or a negative error code. Endpoints that are not enabled - * report errors; errors will also be - * reported when the usb peripheral is disconnected. - */ -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); -} - -/** - * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint - * @ep:the endpoint associated with the request - * @req:the request being canceled - * - * If the request is still active on the endpoint, it is dequeued and its - * completion routine is called (with status -ECONNRESET); else a negative - * error code is returned. This is guaranteed to happen before the call to - * usb_ep_dequeue() returns. - * - * Note that some hardware can't clear out write fifos (to unlink the request - * at the head of the queue) except as part of disconnecting from usb. Such - * restrictions prevent drivers from supporting configuration changes, - * even to configuration zero (a "chapter 9" requirement). - */ + struct usb_request *req) +{ } +static inline int usb_ep_queue(struct usb_ep *ep, struct usb_request *req, + gfp_t gfp_flags) +{ return 0; } static inline int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) -{ - return ep->ops->dequeue(ep, req); -} - -/** - * usb_ep_set_halt - sets the endpoint halt feature. - * @ep: the non-isochronous endpoint being stalled - * - * Use this to stall an endpoint, perhaps as an error report. - * Except for control endpoints, - * the endpoint stays halted (will not stream any data) until the host - * clears this feature; drivers may need to empty the endpoint's request - * queue first, to make sure no inappropriate transfers happen. - * - * Note that while an endpoint CLEAR_FEATURE will be invisible to the - * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the - * current altsetting, see usb_ep_clear_halt(). When switching altsettings, - * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. - * - * Returns zero, or a negative error code. On success, this call sets - * underlying hardware state that blocks data transfers. - * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any - * transfer requests are still queued, or if the controller hardware - * (usually a FIFO) still holds bytes that the host hasn't collected. - */ +{ return 0; } static inline int usb_ep_set_halt(struct usb_ep *ep) -{ - return ep->ops->set_halt(ep, 1); -} - -/** - * usb_ep_clear_halt - clears endpoint halt, and resets toggle - * @ep:the bulk or interrupt endpoint being reset - * - * Use this when responding to the standard usb "set interface" request, - * for endpoints that aren't reconfigured, after clearing any other state - * in the endpoint's i/o queue. - * - * Returns zero, or a negative error code. On success, this call clears - * the underlying hardware state reflecting endpoint halt and data toggle. - * Note that some hardware can't support this request (like pxa2xx_udc), - * and accordingly can't correctly implement interface altsettings. - */ +{ return 0; } static inline int usb_ep_clear_halt(struct usb_ep *ep) -{ - return ep->ops->set_halt(ep, 0); -} - -/** - * usb_ep_set_wedge - sets the halt feature and ignores clear requests - * @ep: the endpoint being wedged - * - * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) - * requests. If the gadget driver clears the halt status, it will - * automatically unwedge the endpoint. - * - * Returns zero on success, else negative errno. - */ -static inline int -usb_ep_set_wedge(struct usb_ep *ep) -{ - if (ep->ops->set_wedge) - return ep->ops->set_wedge(ep); - else - return ep->ops->set_halt(ep, 1); -} - -/** - * usb_ep_fifo_status - returns number of bytes in fifo, or error - * @ep: the endpoint whose fifo status is being checked. - * - * FIFO endpoints may have "unclaimed data" in them in certain cases, - * such as after aborted transfers. Hosts may not have collected all - * the IN data written by the gadget driver (and reported by a request - * completion). The gadget driver may not have collected all the data - * written OUT to it by the host. Drivers that need precise handling for - * fault reporting or recovery may need to use this call. - * - * This returns the number of such bytes in the fifo, or a negative - * errno if the endpoint doesn't use a FIFO or doesn't support such - * precise handling. - */ +{ return 0; } +static inline int usb_ep_set_wedge(struct usb_ep *ep) +{ return 0; } static inline int usb_ep_fifo_status(struct usb_ep *ep) -{ - if (ep->ops->fifo_status) - return ep->ops->fifo_status(ep); - else - return -EOPNOTSUPP; -} - -/** - * usb_ep_fifo_flush - flushes contents of a fifo - * @ep: the endpoint whose fifo is being flushed. - * - * This call may be used to flush the "unclaimed data" that may exist in - * an endpoint fifo after abnormal transaction terminations. The call - * must never be used except when endpoint is not being used for any - * protocol translation. - */ +{ return 0; } static inline void usb_ep_fifo_flush(struct usb_ep *ep) -{ - if (ep->ops->fifo_flush) - ep->ops->fifo_flush(ep); -} - +{ } +#endif /* USB_GADGET */ /*-------------------------------------------------------------------------*/ @@ -760,251 +502,44 @@ static inline int gadget_is_otg(struct usb_gadget *g) #endif } -/** - * usb_gadget_frame_number - returns the current frame number - * @gadget: controller that reports the frame number - * - * Returns the usb frame number, normally eleven bits from a SOF packet, - * or negative errno if this device doesn't support this capability. - */ -static inline int usb_gadget_frame_number(struct usb_gadget *gadget) -{ - return gadget->ops->get_frame(gadget); -} +/*-------------------------------------------------------------------------*/ -/** - * usb_gadget_wakeup - tries to wake up the host connected to this gadget - * @gadget: controller used to wake up the host - * - * Returns zero on success, else negative error code if the hardware - * doesn't support such attempts, or its support has not been enabled - * by the usb host. Drivers must return device descriptors that report - * their ability to support this, or hosts won't enable it. - * - * This may also try to use SRP to wake the host and start enumeration, - * even if OTG isn't otherwise in use. OTG devices may also start - * remote wakeup even when hosts don't explicitly enable it. - */ +#if IS_ENABLED(CONFIG_USB_GADGET) +int usb_gadget_frame_number(struct usb_gadget *gadget); +int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_selfpowered(struct usb_gadget *gadget); +int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); +int usb_gadget_vbus_connect(struct usb_gadget *gadget); +int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA); +int usb_gadget_vbus_disconnect(struct usb_gadget *gadget); +int usb_gadget_connect(struct usb_gadget *gadget); +int usb_gadget_disconnect(struct usb_gadget *gadget); +int usb_gadget_deactivate(struct usb_gadget *gadget); +int usb_gadget_activate(struct usb_gadget *gadget); +#else +static inline int usb_gadget_frame_number(struct usb_gadget *gadget) +{ return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) -{ - if (!gadget->ops->wakeup) - return -EOPNOTSUPP; - return gadget->ops->wakeup(gadget); -} - -/** - * usb_gadget_set_selfpowered - sets the device selfpowered feature. - * @gadget:the device being declared as self-powered - * - * this affects the device status reported by the hardware driver - * to reflect that it now has a local power supply. - * - * returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) -{ - if (!gadget->ops->set_selfpowered) - return -EOPNOTSUPP; - return gadget->ops->set_selfpowered(gadget, 1); -} - -/** - * usb_gadget_clear_selfpowered - clear the device selfpowered feature. - * @gadget:the device being declared as bus-powered - * - * this affects the device status reported by the hardware driver. - * some hardware may not support bus-powered operation, in which - * case this feature's value can never change. - * - * returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) -{ - if (!gadget->ops->set_selfpowered) - return -EOPNOTSUPP; - return gadget->ops->set_selfpowered(gadget, 0); -} - -/** - * usb_gadget_vbus_connect - Notify controller that VBUS is powered - * @gadget:The device which now has VBUS power. - * Context: can sleep - * - * This call is used by a driver for an external transceiver (or GPIO) - * that detects a VBUS power session starting. Common responses include - * resuming the controller, activating the D+ (or D-) pullup to let the - * host detect that a USB device is attached, and starting to draw power - * (8mA or possibly more, especially after SET_CONFIGURATION). - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_vbus_connect(struct usb_gadget *gadget) -{ - if (!gadget->ops->vbus_session) - return -EOPNOTSUPP; - return gadget->ops->vbus_session(gadget, 1); -} - -/** - * usb_gadget_vbus_draw - constrain controller's VBUS power usage - * @gadget:The device whose VBUS usage is being described - * @mA:How much current to draw, in milliAmperes. This should be twice - * the value listed in the configuration descriptor bMaxPower field. - * - * This call is used by gadget drivers during SET_CONFIGURATION calls, - * reporting how much power the device may consume. For example, this - * could affect how quickly batteries are recharged. - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) -{ - if (!gadget->ops->vbus_draw) - return -EOPNOTSUPP; - return gadget->ops->vbus_draw(gadget, mA); -} - -/** - * usb_gadget_vbus_disconnect - notify controller about VBUS session end - * @gadget:the device whose VBUS supply is being described - * Context: can sleep - * - * This call is used by a driver for an external transceiver (or GPIO) - * that detects a VBUS power session ending. Common responses include - * reversing everything done in usb_gadget_vbus_connect(). - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) -{ - if (!gadget->ops->vbus_session) - return -EOPNOTSUPP; - return gadget->ops->vbus_session(gadget, 0); -} - -/** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected - * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). This pullup is always enabled unless - * usb_gadget_disconnect() has been used to disable it. - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - if (!gadget->ops->pullup) - return -EOPNOTSUPP; - - if (gadget->deactivated) { - /* - * If gadget is deactivated we only save new state. - * Gadget will be connected automatically after activation. - */ - gadget->connected = true; - return 0; - } - - ret = gadget->ops->pullup(gadget, 1); - if (!ret) - gadget->connected = 1; - return ret; -} - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - if (!gadget->ops->pullup) - return -EOPNOTSUPP; - - if (gadget->deactivated) { - /* - * If gadget is deactivated we only save new state. - * Gadget will stay disconnected after activation. - */ - gadget->connected = false; - return 0; - } - - ret = gadget->ops->pullup(gadget, 0); - if (!ret) - gadget->connected = 0; - return ret; -} - -/** - * usb_gadget_deactivate - deactivate function which is not ready to work - * @gadget: the peripheral being deactivated - * - * This routine may be used during the gadget driver bind() call to prevent - * the peripheral from ever being visible to the USB host, unless later - * usb_gadget_activate() is called. For example, user mode components may - * need to be activated before the system can talk to hosts. - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_deactivate(struct usb_gadget *gadget) -{ - int ret; - - if (gadget->deactivated) - return 0; - - if (gadget->connected) { - ret = usb_gadget_disconnect(gadget); - if (ret) - return ret; - /* - * If gadget was being connected before deactivation, we want - * to reconnect it in usb_gadget_activate(). - */ - gadget->connected = true; - } - gadget->deactivated = true; - - return 0; -} - -/** - * usb_gadget_activate - activate function which is not ready to work - * @gadget: the peripheral being activated - * - * This routine activates gadget which was previously deactivated with - * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. - * - * Returns zero on success, else negative errno. - */ +{ return 0; } static inline int usb_gadget_activate(struct usb_gadget *gadget) -{ - if (!gadget->deactivated) - return 0; - - gadget->deactivated = false; - - /* - * If gadget has been connected before deactivation, or became connected - * while it was being deactivated, we call usb_gadget_connect(). - */ - if (gadget->connected) - return usb_gadget_connect(gadget); - - return 0; -} +{ return 0; } +#endif /* CONFIG_USB_GADGET */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From 5e42d710a108c23c104e083900d4ba9398e418b0 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Tue, 31 May 2016 13:39:21 +0300 Subject: usb: gadget: add tracepoints to the gadget API This new set of tracepoints will help all gadget drivers and UDC drivers when problem appears. Note that, in order to be able to add tracepoints to udc-core.c we had to rename that to core.c and statically link it with trace.c to form udc-core.o. This is to make sure that module name stays the same. Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/Makefile | 5 + drivers/usb/gadget/udc/core.c | 1523 +++++++++++++++++++++++++++++++++++++ drivers/usb/gadget/udc/trace.c | 18 + drivers/usb/gadget/udc/trace.h | 298 ++++++++ drivers/usb/gadget/udc/udc-core.c | 1373 --------------------------------- include/linux/usb/gadget.h | 4 + 6 files changed, 1848 insertions(+), 1373 deletions(-) create mode 100644 drivers/usb/gadget/udc/core.c create mode 100644 drivers/usb/gadget/udc/trace.c create mode 100644 drivers/usb/gadget/udc/trace.h delete mode 100644 drivers/usb/gadget/udc/udc-core.c (limited to 'include') diff --git a/drivers/usb/gadget/udc/Makefile b/drivers/usb/gadget/udc/Makefile index dfee53446319..98e74ed9f555 100644 --- a/drivers/usb/gadget/udc/Makefile +++ b/drivers/usb/gadget/udc/Makefile @@ -1,3 +1,8 @@ +# define_trace.h needs to know how to find our header +CFLAGS_trace.o := -I$(src) + +udc-core-y := core.o trace.o + # # USB peripheral controller drivers # diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c new file mode 100644 index 000000000000..ff8685ea7219 --- /dev/null +++ b/drivers/usb/gadget/udc/core.c @@ -0,0 +1,1523 @@ +/** + * udc.c - Core UDC Framework + * + * Copyright (C) 2010 Texas Instruments + * Author: Felipe Balbi + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "trace.h" + +/** + * struct usb_udc - describes one usb device controller + * @driver - the gadget driver pointer. For use by the class code + * @dev - the child device to the actual controller + * @gadget - the gadget. For use by the class code + * @list - for use by the udc class driver + * @vbus - for udcs who care about vbus status, this value is real vbus status; + * for udcs who do not care about vbus status, this value is always true + * + * This represents the internal data structure which is used by the UDC-class + * to hold information about udc driver and gadget together. + */ +struct usb_udc { + struct usb_gadget_driver *driver; + struct usb_gadget *gadget; + struct device dev; + struct list_head list; + bool vbus; +}; + +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); + +/* ------------------------------------------------------------------------- */ + +/** + * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint + * @ep:the endpoint being configured + * @maxpacket_limit:value of maximum packet size limit + * + * This function should be used only in UDC drivers to initialize endpoint + * (usually in probe function). + */ +void usb_ep_set_maxpacket_limit(struct usb_ep *ep, + unsigned maxpacket_limit) +{ + ep->maxpacket_limit = maxpacket_limit; + ep->maxpacket = maxpacket_limit; + + trace_usb_ep_set_maxpacket_limit(ep, 0); +} +EXPORT_SYMBOL_GPL(usb_ep_set_maxpacket_limit); + +/** + * usb_ep_enable - configure endpoint, making it usable + * @ep:the endpoint being configured. may not be the endpoint named "ep0". + * drivers discover endpoints through the ep_list of a usb_gadget. + * + * When configurations are set, or when interface settings change, the driver + * will enable or disable the relevant endpoints. while it is enabled, an + * endpoint may be used for i/o until the driver receives a disconnect() from + * the host or until the endpoint is disabled. + * + * the ep0 implementation (which calls this routine) must ensure that the + * hardware capabilities of each endpoint match the descriptor provided + * for it. for example, an endpoint named "ep2in-bulk" would be usable + * for interrupt transfers as well as bulk, but it likely couldn't be used + * for iso transfers or for endpoint 14. some endpoints are fully + * configurable, with more generic names like "ep-a". (remember that for + * USB, "in" means "towards the USB master".) + * + * returns zero, or a negative error code. + */ +int usb_ep_enable(struct usb_ep *ep) +{ + int ret = 0; + + if (ep->enabled) + goto out; + + ret = ep->ops->enable(ep, ep->desc); + if (ret) { + ret = ret; + goto out; + } + + ep->enabled = true; + +out: + trace_usb_ep_enable(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_enable); + +/** + * usb_ep_disable - endpoint is no longer usable + * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". + * + * no other task may be using this endpoint when this is called. + * any pending and uncompleted requests will complete with status + * indicating disconnect (-ESHUTDOWN) before this call returns. + * gadget drivers must call usb_ep_enable() again before queueing + * requests to the endpoint. + * + * returns zero, or a negative error code. + */ +int usb_ep_disable(struct usb_ep *ep) +{ + int ret = 0; + + if (!ep->enabled) + goto out; + + ret = ep->ops->disable(ep); + if (ret) { + ret = ret; + goto out; + } + + ep->enabled = false; + +out: + trace_usb_ep_disable(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_disable); + +/** + * usb_ep_alloc_request - allocate a request object to use with this endpoint + * @ep:the endpoint to be used with with the request + * @gfp_flags:GFP_* flags to use + * + * Request objects must be allocated with this call, since they normally + * need controller-specific setup and may even need endpoint-specific + * resources such as allocation of DMA descriptors. + * Requests may be submitted with usb_ep_queue(), and receive a single + * completion callback. Free requests with usb_ep_free_request(), when + * they are no longer needed. + * + * Returns the request, or null if one could not be allocated. + */ +struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, + gfp_t gfp_flags) +{ + struct usb_request *req = NULL; + + req = ep->ops->alloc_request(ep, gfp_flags); + + trace_usb_ep_alloc_request(ep, req, req ? 0 : -ENOMEM); + + return req; +} +EXPORT_SYMBOL_GPL(usb_ep_alloc_request); + +/** + * usb_ep_free_request - frees a request object + * @ep:the endpoint associated with the request + * @req:the request being freed + * + * Reverses the effect of usb_ep_alloc_request(). + * Caller guarantees the request is not queued, and that it will + * no longer be requeued (or otherwise used). + */ +void usb_ep_free_request(struct usb_ep *ep, + struct usb_request *req) +{ + ep->ops->free_request(ep, req); + trace_usb_ep_free_request(ep, req, 0); +} +EXPORT_SYMBOL_GPL(usb_ep_free_request); + +/** + * usb_ep_queue - queues (submits) an I/O request to an endpoint. + * @ep:the endpoint associated with the request + * @req:the request being submitted + * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't + * pre-allocate all necessary memory with the request. + * + * This tells the device controller to perform the specified request through + * that endpoint (reading or writing a buffer). When the request completes, + * including being canceled by usb_ep_dequeue(), the request's completion + * routine is called to return the request to the driver. Any endpoint + * (except control endpoints like ep0) may have more than one transfer + * request queued; they complete in FIFO order. Once a gadget driver + * submits a request, that request may not be examined or modified until it + * is given back to that driver through the completion callback. + * + * Each request is turned into one or more packets. The controller driver + * never merges adjacent requests into the same packet. OUT transfers + * will sometimes use data that's already buffered in the hardware. + * Drivers can rely on the fact that the first byte of the request's buffer + * always corresponds to the first byte of some USB packet, for both + * IN and OUT transfers. + * + * Bulk endpoints can queue any amount of data; the transfer is packetized + * automatically. The last packet will be short if the request doesn't fill it + * out completely. Zero length packets (ZLPs) should be avoided in portable + * protocols since not all usb hardware can successfully handle zero length + * packets. (ZLPs may be explicitly written, and may be implicitly written if + * the request 'zero' flag is set.) Bulk endpoints may also be used + * for interrupt transfers; but the reverse is not true, and some endpoints + * won't support every interrupt transfer. (Such as 768 byte packets.) + * + * Interrupt-only endpoints are less functional than bulk endpoints, for + * example by not supporting queueing or not handling buffers that are + * larger than the endpoint's maxpacket size. They may also treat data + * toggle differently. + * + * Control endpoints ... after getting a setup() callback, the driver queues + * one response (even if it would be zero length). That enables the + * status ack, after transferring data as specified in the response. Setup + * functions may return negative error codes to generate protocol stalls. + * (Note that some USB device controllers disallow protocol stall responses + * in some cases.) When control responses are deferred (the response is + * written after the setup callback returns), then usb_ep_set_halt() may be + * used on ep0 to trigger protocol stalls. Depending on the controller, + * it may not be possible to trigger a status-stage protocol stall when the + * data stage is over, that is, from within the response's completion + * routine. + * + * For periodic endpoints, like interrupt or isochronous ones, the usb host + * arranges to poll once per interval, and the gadget driver usually will + * have queued some data to transfer at that time. + * + * Returns zero, or a negative error code. Endpoints that are not enabled + * report errors; errors will also be + * reported when the usb peripheral is disconnected. + */ +int usb_ep_queue(struct usb_ep *ep, + struct usb_request *req, gfp_t gfp_flags) +{ + int ret = 0; + + if (WARN_ON_ONCE(!ep->enabled && ep->address)) { + ret = -ESHUTDOWN; + goto out; + } + + ret = ep->ops->queue(ep, req, gfp_flags); + +out: + trace_usb_ep_queue(ep, req, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_queue); + +/** + * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint + * @ep:the endpoint associated with the request + * @req:the request being canceled + * + * If the request is still active on the endpoint, it is dequeued and its + * completion routine is called (with status -ECONNRESET); else a negative + * error code is returned. This is guaranteed to happen before the call to + * usb_ep_dequeue() returns. + * + * Note that some hardware can't clear out write fifos (to unlink the request + * at the head of the queue) except as part of disconnecting from usb. Such + * restrictions prevent drivers from supporting configuration changes, + * even to configuration zero (a "chapter 9" requirement). + */ +int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) +{ + int ret; + + ret = ep->ops->dequeue(ep, req); + trace_usb_ep_dequeue(ep, req, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_dequeue); + +/** + * usb_ep_set_halt - sets the endpoint halt feature. + * @ep: the non-isochronous endpoint being stalled + * + * Use this to stall an endpoint, perhaps as an error report. + * Except for control endpoints, + * the endpoint stays halted (will not stream any data) until the host + * clears this feature; drivers may need to empty the endpoint's request + * queue first, to make sure no inappropriate transfers happen. + * + * Note that while an endpoint CLEAR_FEATURE will be invisible to the + * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the + * current altsetting, see usb_ep_clear_halt(). When switching altsettings, + * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. + * + * Returns zero, or a negative error code. On success, this call sets + * underlying hardware state that blocks data transfers. + * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any + * transfer requests are still queued, or if the controller hardware + * (usually a FIFO) still holds bytes that the host hasn't collected. + */ +int usb_ep_set_halt(struct usb_ep *ep) +{ + int ret; + + ret = ep->ops->set_halt(ep, 1); + trace_usb_ep_set_halt(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_set_halt); + +/** + * usb_ep_clear_halt - clears endpoint halt, and resets toggle + * @ep:the bulk or interrupt endpoint being reset + * + * Use this when responding to the standard usb "set interface" request, + * for endpoints that aren't reconfigured, after clearing any other state + * in the endpoint's i/o queue. + * + * Returns zero, or a negative error code. On success, this call clears + * the underlying hardware state reflecting endpoint halt and data toggle. + * Note that some hardware can't support this request (like pxa2xx_udc), + * and accordingly can't correctly implement interface altsettings. + */ +int usb_ep_clear_halt(struct usb_ep *ep) +{ + int ret; + + ret = ep->ops->set_halt(ep, 0); + trace_usb_ep_clear_halt(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_clear_halt); + +/** + * usb_ep_set_wedge - sets the halt feature and ignores clear requests + * @ep: the endpoint being wedged + * + * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) + * requests. If the gadget driver clears the halt status, it will + * automatically unwedge the endpoint. + * + * Returns zero on success, else negative errno. + */ +int usb_ep_set_wedge(struct usb_ep *ep) +{ + int ret; + + if (ep->ops->set_wedge) + ret = ep->ops->set_wedge(ep); + else + ret = ep->ops->set_halt(ep, 1); + + trace_usb_ep_set_wedge(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_set_wedge); + +/** + * usb_ep_fifo_status - returns number of bytes in fifo, or error + * @ep: the endpoint whose fifo status is being checked. + * + * FIFO endpoints may have "unclaimed data" in them in certain cases, + * such as after aborted transfers. Hosts may not have collected all + * the IN data written by the gadget driver (and reported by a request + * completion). The gadget driver may not have collected all the data + * written OUT to it by the host. Drivers that need precise handling for + * fault reporting or recovery may need to use this call. + * + * This returns the number of such bytes in the fifo, or a negative + * errno if the endpoint doesn't use a FIFO or doesn't support such + * precise handling. + */ +int usb_ep_fifo_status(struct usb_ep *ep) +{ + int ret; + + if (ep->ops->fifo_status) + ret = ep->ops->fifo_status(ep); + else + ret = -EOPNOTSUPP; + + trace_usb_ep_fifo_status(ep, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_ep_fifo_status); + +/** + * usb_ep_fifo_flush - flushes contents of a fifo + * @ep: the endpoint whose fifo is being flushed. + * + * This call may be used to flush the "unclaimed data" that may exist in + * an endpoint fifo after abnormal transaction terminations. The call + * must never be used except when endpoint is not being used for any + * protocol translation. + */ +void usb_ep_fifo_flush(struct usb_ep *ep) +{ + if (ep->ops->fifo_flush) + ep->ops->fifo_flush(ep); + + trace_usb_ep_fifo_flush(ep, 0); +} +EXPORT_SYMBOL_GPL(usb_ep_fifo_flush); + +/* ------------------------------------------------------------------------- */ + +/** + * usb_gadget_frame_number - returns the current frame number + * @gadget: controller that reports the frame number + * + * Returns the usb frame number, normally eleven bits from a SOF packet, + * or negative errno if this device doesn't support this capability. + */ +int usb_gadget_frame_number(struct usb_gadget *gadget) +{ + int ret; + + ret = gadget->ops->get_frame(gadget); + + trace_usb_gadget_frame_number(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_frame_number); + +/** + * usb_gadget_wakeup - tries to wake up the host connected to this gadget + * @gadget: controller used to wake up the host + * + * Returns zero on success, else negative error code if the hardware + * doesn't support such attempts, or its support has not been enabled + * by the usb host. Drivers must return device descriptors that report + * their ability to support this, or hosts won't enable it. + * + * This may also try to use SRP to wake the host and start enumeration, + * even if OTG isn't otherwise in use. OTG devices may also start + * remote wakeup even when hosts don't explicitly enable it. + */ +int usb_gadget_wakeup(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->wakeup) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->wakeup(gadget); + +out: + trace_usb_gadget_wakeup(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_wakeup); + +/** + * usb_gadget_set_selfpowered - sets the device selfpowered feature. + * @gadget:the device being declared as self-powered + * + * this affects the device status reported by the hardware driver + * to reflect that it now has a local power supply. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_set_selfpowered(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->set_selfpowered) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->set_selfpowered(gadget, 1); + +out: + trace_usb_gadget_set_selfpowered(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_set_selfpowered); + +/** + * usb_gadget_clear_selfpowered - clear the device selfpowered feature. + * @gadget:the device being declared as bus-powered + * + * this affects the device status reported by the hardware driver. + * some hardware may not support bus-powered operation, in which + * case this feature's value can never change. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->set_selfpowered) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->set_selfpowered(gadget, 0); + +out: + trace_usb_gadget_clear_selfpowered(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_clear_selfpowered); + +/** + * usb_gadget_vbus_connect - Notify controller that VBUS is powered + * @gadget:The device which now has VBUS power. + * Context: can sleep + * + * This call is used by a driver for an external transceiver (or GPIO) + * that detects a VBUS power session starting. Common responses include + * resuming the controller, activating the D+ (or D-) pullup to let the + * host detect that a USB device is attached, and starting to draw power + * (8mA or possibly more, especially after SET_CONFIGURATION). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_connect(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->vbus_session) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->vbus_session(gadget, 1); + +out: + trace_usb_gadget_vbus_connect(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_connect); + +/** + * usb_gadget_vbus_draw - constrain controller's VBUS power usage + * @gadget:The device whose VBUS usage is being described + * @mA:How much current to draw, in milliAmperes. This should be twice + * the value listed in the configuration descriptor bMaxPower field. + * + * This call is used by gadget drivers during SET_CONFIGURATION calls, + * reporting how much power the device may consume. For example, this + * could affect how quickly batteries are recharged. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) +{ + int ret = 0; + + if (!gadget->ops->vbus_draw) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->vbus_draw(gadget, mA); + if (!ret) + gadget->mA = mA; + +out: + trace_usb_gadget_vbus_draw(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_draw); + +/** + * usb_gadget_vbus_disconnect - notify controller about VBUS session end + * @gadget:the device whose VBUS supply is being described + * Context: can sleep + * + * This call is used by a driver for an external transceiver (or GPIO) + * that detects a VBUS power session ending. Common responses include + * reversing everything done in usb_gadget_vbus_connect(). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->vbus_session) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->vbus_session(gadget, 0); + +out: + trace_usb_gadget_vbus_disconnect(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); + +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). This pullup is always enabled unless + * usb_gadget_disconnect() has been used to disable it. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->pullup) { + ret = -EOPNOTSUPP; + goto out; + } + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will be connected automatically after activation. + */ + gadget->connected = true; + goto out; + } + + ret = gadget->ops->pullup(gadget, 1); + if (!ret) + gadget->connected = 1; + +out: + trace_usb_gadget_connect(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_connect); + +/** + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected + * + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_disconnect(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->ops->pullup) { + ret = -EOPNOTSUPP; + goto out; + } + + if (gadget->deactivated) { + /* + * If gadget is deactivated we only save new state. + * Gadget will stay disconnected after activation. + */ + gadget->connected = false; + goto out; + } + + ret = gadget->ops->pullup(gadget, 0); + if (!ret) + gadget->connected = 0; + +out: + trace_usb_gadget_disconnect(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_disconnect); + +/** + * usb_gadget_deactivate - deactivate function which is not ready to work + * @gadget: the peripheral being deactivated + * + * This routine may be used during the gadget driver bind() call to prevent + * the peripheral from ever being visible to the USB host, unless later + * usb_gadget_activate() is called. For example, user mode components may + * need to be activated before the system can talk to hosts. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_deactivate(struct usb_gadget *gadget) +{ + int ret = 0; + + if (gadget->deactivated) + goto out; + + if (gadget->connected) { + ret = usb_gadget_disconnect(gadget); + if (ret) + goto out; + + /* + * If gadget was being connected before deactivation, we want + * to reconnect it in usb_gadget_activate(). + */ + gadget->connected = true; + } + gadget->deactivated = true; + +out: + trace_usb_gadget_deactivate(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_deactivate); + +/** + * usb_gadget_activate - activate function which is not ready to work + * @gadget: the peripheral being activated + * + * This routine activates gadget which was previously deactivated with + * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_activate(struct usb_gadget *gadget) +{ + int ret = 0; + + if (!gadget->deactivated) + goto out; + + gadget->deactivated = false; + + /* + * If gadget has been connected before deactivation, or became connected + * while it was being deactivated, we call usb_gadget_connect(). + */ + if (gadget->connected) + ret = usb_gadget_connect(gadget); + +out: + trace_usb_gadget_activate(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_activate); + +/* ------------------------------------------------------------------------- */ + +#ifdef CONFIG_HAS_DMA + +int usb_gadget_map_request_by_dev(struct device *dev, + struct usb_request *req, int is_in) +{ + if (req->length == 0) + return 0; + + if (req->num_sgs) { + int mapped; + + mapped = dma_map_sg(dev, req->sg, req->num_sgs, + is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + if (mapped == 0) { + dev_err(dev, "failed to map SGs\n"); + return -EFAULT; + } + + req->num_mapped_sgs = mapped; + } else { + req->dma = dma_map_single(dev, req->buf, req->length, + is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + + if (dma_mapping_error(dev, req->dma)) { + dev_err(dev, "failed to map buffer\n"); + return -EFAULT; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(usb_gadget_map_request_by_dev); + +int usb_gadget_map_request(struct usb_gadget *gadget, + struct usb_request *req, int is_in) +{ + return usb_gadget_map_request_by_dev(gadget->dev.parent, req, is_in); +} +EXPORT_SYMBOL_GPL(usb_gadget_map_request); + +void usb_gadget_unmap_request_by_dev(struct device *dev, + struct usb_request *req, int is_in) +{ + if (req->length == 0) + return; + + if (req->num_mapped_sgs) { + dma_unmap_sg(dev, req->sg, req->num_mapped_sgs, + is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + + req->num_mapped_sgs = 0; + } else { + dma_unmap_single(dev, req->dma, req->length, + is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + } +} +EXPORT_SYMBOL_GPL(usb_gadget_unmap_request_by_dev); + +void usb_gadget_unmap_request(struct usb_gadget *gadget, + struct usb_request *req, int is_in) +{ + usb_gadget_unmap_request_by_dev(gadget->dev.parent, req, is_in); +} +EXPORT_SYMBOL_GPL(usb_gadget_unmap_request); + +#endif /* CONFIG_HAS_DMA */ + +/* ------------------------------------------------------------------------- */ + +/** + * usb_gadget_giveback_request - give the request back to the gadget layer + * Context: in_interrupt() + * + * This is called by device controller drivers in order to return the + * completed request back to the gadget layer. + */ +void usb_gadget_giveback_request(struct usb_ep *ep, + struct usb_request *req) +{ + if (likely(req->status == 0)) + usb_led_activity(USB_LED_EVENT_GADGET); + + trace_usb_gadget_giveback_request(ep, req, 0); + + req->complete(ep, req); +} +EXPORT_SYMBOL_GPL(usb_gadget_giveback_request); + +/* ------------------------------------------------------------------------- */ + +/** + * gadget_find_ep_by_name - returns ep whose name is the same as sting passed + * in second parameter or NULL if searched endpoint not found + * @g: controller to check for quirk + * @name: name of searched endpoint + */ +struct usb_ep *gadget_find_ep_by_name(struct usb_gadget *g, const char *name) +{ + struct usb_ep *ep; + + gadget_for_each_ep(ep, g) { + if (!strcmp(ep->name, name)) + return ep; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(gadget_find_ep_by_name); + +/* ------------------------------------------------------------------------- */ + +int usb_gadget_ep_match_desc(struct usb_gadget *gadget, + struct usb_ep *ep, struct usb_endpoint_descriptor *desc, + struct usb_ss_ep_comp_descriptor *ep_comp) +{ + u8 type; + u16 max; + int num_req_streams = 0; + + /* endpoint already claimed? */ + if (ep->claimed) + return 0; + + type = usb_endpoint_type(desc); + max = 0x7ff & usb_endpoint_maxp(desc); + + if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) + return 0; + if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) + return 0; + + if (max > ep->maxpacket_limit) + return 0; + + /* "high bandwidth" works only at high speed */ + if (!gadget_is_dualspeed(gadget) && usb_endpoint_maxp(desc) & (3<<11)) + return 0; + + switch (type) { + case USB_ENDPOINT_XFER_CONTROL: + /* only support ep0 for portable CONTROL traffic */ + return 0; + case USB_ENDPOINT_XFER_ISOC: + if (!ep->caps.type_iso) + return 0; + /* ISO: limit 1023 bytes full speed, 1024 high/super speed */ + if (!gadget_is_dualspeed(gadget) && max > 1023) + return 0; + break; + case USB_ENDPOINT_XFER_BULK: + if (!ep->caps.type_bulk) + return 0; + if (ep_comp && gadget_is_superspeed(gadget)) { + /* Get the number of required streams from the + * EP companion descriptor and see if the EP + * matches it + */ + num_req_streams = ep_comp->bmAttributes & 0x1f; + if (num_req_streams > ep->max_streams) + return 0; + } + break; + case USB_ENDPOINT_XFER_INT: + /* Bulk endpoints handle interrupt transfers, + * except the toggle-quirky iso-synch kind + */ + if (!ep->caps.type_int && !ep->caps.type_bulk) + return 0; + /* INT: limit 64 bytes full speed, 1024 high/super speed */ + if (!gadget_is_dualspeed(gadget) && max > 64) + return 0; + break; + } + + return 1; +} +EXPORT_SYMBOL_GPL(usb_gadget_ep_match_desc); + +/* ------------------------------------------------------------------------- */ + +static void usb_gadget_state_work(struct work_struct *work) +{ + struct usb_gadget *gadget = work_to_gadget(work); + struct usb_udc *udc = gadget->udc; + + if (udc) + sysfs_notify(&udc->dev.kobj, NULL, "state"); +} + +void usb_gadget_set_state(struct usb_gadget *gadget, + enum usb_device_state state) +{ + gadget->state = state; + schedule_work(&gadget->work); +} +EXPORT_SYMBOL_GPL(usb_gadget_set_state); + +/* ------------------------------------------------------------------------- */ + +static void usb_udc_connect_control(struct usb_udc *udc) +{ + if (udc->vbus) + usb_gadget_connect(udc->gadget); + else + usb_gadget_disconnect(udc->gadget); +} + +/** + * usb_udc_vbus_handler - updates the udc core vbus status, and try to + * connect or disconnect gadget + * @gadget: The gadget which vbus change occurs + * @status: The vbus status + * + * The udc driver calls it when it wants to connect or disconnect gadget + * according to vbus status. + */ +void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) +{ + struct usb_udc *udc = gadget->udc; + + if (udc) { + udc->vbus = status; + usb_udc_connect_control(udc); + } +} +EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); + +/** + * usb_gadget_udc_reset - notifies the udc core that bus reset occurs + * @gadget: The gadget which bus reset occurs + * @driver: The gadget driver we want to notify + * + * If the udc driver has bus reset handler, it needs to call this when the bus + * reset occurs, it notifies the gadget driver that the bus reset occurs as + * well as updates gadget state. + */ +void usb_gadget_udc_reset(struct usb_gadget *gadget, + struct usb_gadget_driver *driver) +{ + driver->reset(gadget); + usb_gadget_set_state(gadget, USB_STATE_DEFAULT); +} +EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); + +/** + * usb_gadget_udc_start - tells usb device controller to start up + * @udc: The UDC to be started + * + * This call is issued by the UDC Class driver when it's about + * to register a gadget driver to the device controller, before + * calling gadget driver's bind() method. + * + * It allows the controller to be powered off until strictly + * necessary to have it powered on. + * + * Returns zero on success, else negative errno. + */ +static inline int usb_gadget_udc_start(struct usb_udc *udc) +{ + return udc->gadget->ops->udc_start(udc->gadget, udc->driver); +} + +/** + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore + * @gadget: The device we want to stop activity + * @driver: The driver to unbind from @gadget + * + * This call is issued by the UDC Class driver after calling + * gadget driver's unbind() method. + * + * The details are implementation specific, but it can go as + * far as powering off UDC completely and disable its data + * line pullups. + */ +static inline void usb_gadget_udc_stop(struct usb_udc *udc) +{ + udc->gadget->ops->udc_stop(udc->gadget); +} + +/** + * usb_udc_release - release the usb_udc struct + * @dev: the dev member within usb_udc + * + * This is called by driver's core in order to free memory once the last + * reference is released. + */ +static void usb_udc_release(struct device *dev) +{ + struct usb_udc *udc; + + udc = container_of(dev, struct usb_udc, dev); + dev_dbg(dev, "releasing '%s'\n", dev_name(dev)); + kfree(udc); +} + +static const struct attribute_group *usb_udc_attr_groups[]; + +static void usb_udc_nop_release(struct device *dev) +{ + dev_vdbg(dev, "%s\n", __func__); +} + +/** + * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list + * @parent: the parent device to this udc. Usually the controller driver's + * device. + * @gadget: the gadget to be added to the list. + * @release: a gadget release function. + * + * Returns zero on success, negative errno otherwise. + */ +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); + if (!udc) + goto err1; + + dev_set_name(&gadget->dev, "gadget"); + INIT_WORK(&gadget->work, usb_gadget_state_work); + gadget->dev.parent = parent; + + if (release) + gadget->dev.release = release; + else + gadget->dev.release = usb_udc_nop_release; + + ret = device_register(&gadget->dev); + if (ret) + goto err2; + + device_initialize(&udc->dev); + udc->dev.release = usb_udc_release; + udc->dev.class = udc_class; + udc->dev.groups = usb_udc_attr_groups; + udc->dev.parent = parent; + ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj)); + if (ret) + goto err3; + + udc->gadget = gadget; + gadget->udc = udc; + + mutex_lock(&udc_lock); + list_add_tail(&udc->list, &udc_list); + + ret = device_add(&udc->dev); + if (ret) + goto err4; + + 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 != -EPROBE_DEFER) + list_del(&driver->pending); + if (ret) + goto err4; + break; + } + } + + mutex_unlock(&udc_lock); + + return 0; + +err4: + list_del(&udc->list); + mutex_unlock(&udc_lock); + +err3: + put_device(&udc->dev); + device_del(&gadget->dev); + +err2: + put_device(&gadget->dev); + kfree(udc); + +err1: + return ret; +} +EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release); + +/** + * usb_get_gadget_udc_name - get the name of the first UDC controller + * This functions returns the name of the first UDC controller in the system. + * Please note that this interface is usefull only for legacy drivers which + * assume that there is only one UDC controller in the system and they need to + * get its name before initialization. There is no guarantee that the UDC + * of the returned name will be still available, when gadget driver registers + * itself. + * + * Returns pointer to string with UDC controller name on success, NULL + * otherwise. Caller should kfree() returned string. + */ +char *usb_get_gadget_udc_name(void) +{ + struct usb_udc *udc; + char *name = NULL; + + /* For now we take the first available UDC */ + mutex_lock(&udc_lock); + list_for_each_entry(udc, &udc_list, list) { + if (!udc->driver) { + name = kstrdup(udc->gadget->name, GFP_KERNEL); + break; + } + } + mutex_unlock(&udc_lock); + return name; +} +EXPORT_SYMBOL_GPL(usb_get_gadget_udc_name); + +/** + * usb_add_gadget_udc - adds a new gadget to the udc class driver list + * @parent: the parent device to this udc. Usually the controller + * driver's device. + * @gadget: the gadget to be added to the list + * + * Returns zero on success, negative errno otherwise. + */ +int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget) +{ + return usb_add_gadget_udc_release(parent, gadget, NULL); +} +EXPORT_SYMBOL_GPL(usb_add_gadget_udc); + +static void usb_gadget_remove_driver(struct usb_udc *udc) +{ + dev_dbg(&udc->dev, "unregistering UDC driver [%s]\n", + udc->driver->function); + + kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); + + usb_gadget_disconnect(udc->gadget); + udc->driver->disconnect(udc->gadget); + udc->driver->unbind(udc->gadget); + usb_gadget_udc_stop(udc); + + udc->driver = NULL; + udc->dev.driver = NULL; + udc->gadget->dev.driver = NULL; +} + +/** + * usb_del_gadget_udc - deletes @udc from udc_list + * @gadget: the gadget to be removed. + * + * This, will call usb_gadget_unregister_driver() if + * the @udc is still busy. + */ +void usb_del_gadget_udc(struct usb_gadget *gadget) +{ + struct usb_udc *udc = gadget->udc; + + if (!udc) + return; + + dev_vdbg(gadget->dev.parent, "unregistering gadget\n"); + + mutex_lock(&udc_lock); + list_del(&udc->list); + + 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); + device_unregister(&udc->dev); + device_unregister(&gadget->dev); +} +EXPORT_SYMBOL_GPL(usb_del_gadget_udc); + +/* ------------------------------------------------------------------------- */ + +static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *driver) +{ + int ret; + + dev_dbg(&udc->dev, "registering UDC driver [%s]\n", + driver->function); + + udc->driver = driver; + udc->dev.driver = &driver->driver; + udc->gadget->dev.driver = &driver->driver; + + ret = driver->bind(udc->gadget, driver); + if (ret) + goto err1; + ret = usb_gadget_udc_start(udc); + if (ret) { + driver->unbind(udc->gadget); + goto err1; + } + usb_udc_connect_control(udc); + + kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); + return 0; +err1: + if (ret != -EISNAM) + dev_err(&udc->dev, "failed to start %s: %d\n", + udc->driver->function, ret); + udc->driver = NULL; + udc->dev.driver = NULL; + udc->gadget->dev.driver = NULL; + return ret; +} + +int usb_gadget_probe_driver(struct usb_gadget_driver *driver) +{ + struct usb_udc *udc = NULL; + int ret = -ENODEV; + + if (!driver || !driver->bind || !driver->setup) + return -EINVAL; + + mutex_lock(&udc_lock); + 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 && !udc->driver) + goto found; + } else { + list_for_each_entry(udc, &udc_list, list) { + /* For now we take the first one */ + if (!udc->driver) + goto found; + } + } + + if (!driver->match_existing_only) { + 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); + ret = 0; + } + + mutex_unlock(&udc_lock); + return ret; +found: + ret = udc_bind_to_driver(udc, driver); + mutex_unlock(&udc_lock); + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_probe_driver); + +int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) +{ + struct usb_udc *udc = NULL; + int ret = -ENODEV; + + if (!driver || !driver->unbind) + return -EINVAL; + + mutex_lock(&udc_lock); + list_for_each_entry(udc, &udc_list, list) + if (udc->driver == driver) { + usb_gadget_remove_driver(udc); + usb_gadget_set_state(udc->gadget, + USB_STATE_NOTATTACHED); + ret = 0; + break; + } + + if (ret) { + list_del(&driver->pending); + ret = 0; + } + mutex_unlock(&udc_lock); + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver); + +/* ------------------------------------------------------------------------- */ + +static ssize_t usb_udc_srp_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t n) +{ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + + if (sysfs_streq(buf, "1")) + usb_gadget_wakeup(udc->gadget); + + return n; +} +static DEVICE_ATTR(srp, S_IWUSR, NULL, usb_udc_srp_store); + +static ssize_t usb_udc_softconn_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t n) +{ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + + if (!udc->driver) { + dev_err(dev, "soft-connect without a gadget driver\n"); + return -EOPNOTSUPP; + } + + if (sysfs_streq(buf, "connect")) { + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); + } else if (sysfs_streq(buf, "disconnect")) { + usb_gadget_disconnect(udc->gadget); + udc->driver->disconnect(udc->gadget); + usb_gadget_udc_stop(udc); + } else { + dev_err(dev, "unsupported command '%s'\n", buf); + return -EINVAL; + } + + return n; +} +static DEVICE_ATTR(soft_connect, S_IWUSR, NULL, usb_udc_softconn_store); + +static ssize_t state_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + struct usb_gadget *gadget = udc->gadget; + + return sprintf(buf, "%s\n", usb_state_string(gadget->state)); +} +static DEVICE_ATTR_RO(state); + +#define USB_UDC_SPEED_ATTR(name, param) \ +ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ + return snprintf(buf, PAGE_SIZE, "%s\n", \ + usb_speed_string(udc->gadget->param)); \ +} \ +static DEVICE_ATTR_RO(name) + +static USB_UDC_SPEED_ATTR(current_speed, speed); +static USB_UDC_SPEED_ATTR(maximum_speed, max_speed); + +#define USB_UDC_ATTR(name) \ +ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ + struct usb_gadget *gadget = udc->gadget; \ + \ + return snprintf(buf, PAGE_SIZE, "%d\n", gadget->name); \ +} \ +static DEVICE_ATTR_RO(name) + +static USB_UDC_ATTR(is_otg); +static USB_UDC_ATTR(is_a_peripheral); +static USB_UDC_ATTR(b_hnp_enable); +static USB_UDC_ATTR(a_hnp_support); +static USB_UDC_ATTR(a_alt_hnp_support); +static USB_UDC_ATTR(is_selfpowered); + +static struct attribute *usb_udc_attrs[] = { + &dev_attr_srp.attr, + &dev_attr_soft_connect.attr, + &dev_attr_state.attr, + &dev_attr_current_speed.attr, + &dev_attr_maximum_speed.attr, + + &dev_attr_is_otg.attr, + &dev_attr_is_a_peripheral.attr, + &dev_attr_b_hnp_enable.attr, + &dev_attr_a_hnp_support.attr, + &dev_attr_a_alt_hnp_support.attr, + &dev_attr_is_selfpowered.attr, + NULL, +}; + +static const struct attribute_group usb_udc_attr_group = { + .attrs = usb_udc_attrs, +}; + +static const struct attribute_group *usb_udc_attr_groups[] = { + &usb_udc_attr_group, + NULL, +}; + +static int usb_udc_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct usb_udc *udc = container_of(dev, struct usb_udc, dev); + int ret; + + ret = add_uevent_var(env, "USB_UDC_NAME=%s", udc->gadget->name); + if (ret) { + dev_err(dev, "failed to add uevent USB_UDC_NAME\n"); + return ret; + } + + if (udc->driver) { + ret = add_uevent_var(env, "USB_UDC_DRIVER=%s", + udc->driver->function); + if (ret) { + dev_err(dev, "failed to add uevent USB_UDC_DRIVER\n"); + return ret; + } + } + + return 0; +} + +static int __init usb_udc_init(void) +{ + udc_class = class_create(THIS_MODULE, "udc"); + if (IS_ERR(udc_class)) { + pr_err("failed to create udc class --> %ld\n", + PTR_ERR(udc_class)); + return PTR_ERR(udc_class); + } + + udc_class->dev_uevent = usb_udc_uevent; + return 0; +} +subsys_initcall(usb_udc_init); + +static void __exit usb_udc_exit(void) +{ + class_destroy(udc_class); +} +module_exit(usb_udc_exit); + +MODULE_DESCRIPTION("UDC Framework"); +MODULE_AUTHOR("Felipe Balbi "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/usb/gadget/udc/trace.c b/drivers/usb/gadget/udc/trace.c new file mode 100644 index 000000000000..8c551ab91ad8 --- /dev/null +++ b/drivers/usb/gadget/udc/trace.c @@ -0,0 +1,18 @@ +/** + * trace.c - USB Gadget Framework Trace Support + * + * Copyright (C) 2016 Intel Corporation + * Author: Felipe Balbi + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/drivers/usb/gadget/udc/trace.h b/drivers/usb/gadget/udc/trace.h new file mode 100644 index 000000000000..da29874b5366 --- /dev/null +++ b/drivers/usb/gadget/udc/trace.h @@ -0,0 +1,298 @@ +/** + * udc.c - Core UDC Framework + * + * Copyright (C) 2016 Intel Corporation + * Author: Felipe Balbi + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM gadget + +#if !defined(__UDC_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define __UDC_TRACE_H + +#include +#include +#include +#include + +DECLARE_EVENT_CLASS(udc_log_gadget, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret), + TP_STRUCT__entry( + __field(enum usb_device_speed, speed) + __field(enum usb_device_speed, max_speed) + __field(enum usb_device_state, state) + __field(unsigned, mA) + __field(unsigned, sg_supported) + __field(unsigned, is_otg) + __field(unsigned, is_a_peripheral) + __field(unsigned, b_hnp_enable) + __field(unsigned, a_hnp_support) + __field(unsigned, hnp_polling_support) + __field(unsigned, host_request_flag) + __field(unsigned, quirk_ep_out_aligned_size) + __field(unsigned, quirk_altset_not_supp) + __field(unsigned, quirk_stall_not_supp) + __field(unsigned, quirk_zlp_not_supp) + __field(unsigned, is_selfpowered) + __field(unsigned, deactivated) + __field(unsigned, connected) + __field(int, ret) + ), + TP_fast_assign( + __entry->speed = g->speed; + __entry->max_speed = g->max_speed; + __entry->state = g->state; + __entry->mA = g->mA; + __entry->sg_supported = g->sg_supported; + __entry->is_otg = g->is_otg; + __entry->is_a_peripheral = g->is_a_peripheral; + __entry->b_hnp_enable = g->b_hnp_enable; + __entry->a_hnp_support = g->a_hnp_support; + __entry->hnp_polling_support = g->hnp_polling_support; + __entry->host_request_flag = g->host_request_flag; + __entry->quirk_ep_out_aligned_size = g->quirk_ep_out_aligned_size; + __entry->quirk_altset_not_supp = g->quirk_altset_not_supp; + __entry->quirk_stall_not_supp = g->quirk_stall_not_supp; + __entry->quirk_zlp_not_supp = g->quirk_zlp_not_supp; + __entry->is_selfpowered = g->is_selfpowered; + __entry->deactivated = g->deactivated; + __entry->connected = g->connected; + __entry->ret = ret; + ), + TP_printk("speed %d/%d state %d %dmA [%s%s%s%s%s%s%s%s%s%s%s%s%s%s] --> %d", + __entry->speed, __entry->max_speed, __entry->state, __entry->mA, + __entry->sg_supported ? "sg:" : "", + __entry->is_otg ? "OTG:" : "", + __entry->is_a_peripheral ? "a_peripheral:" : "", + __entry->b_hnp_enable ? "b_hnp:" : "", + __entry->a_hnp_support ? "a_hnp:" : "", + __entry->hnp_polling_support ? "hnp_poll:" : "", + __entry->host_request_flag ? "hostreq:" : "", + __entry->quirk_ep_out_aligned_size ? "out_aligned:" : "", + __entry->quirk_altset_not_supp ? "no_altset:" : "", + __entry->quirk_stall_not_supp ? "no_stall:" : "", + __entry->quirk_zlp_not_supp ? "no_zlp" : "", + __entry->is_selfpowered ? "self-powered:" : "bus-powered:", + __entry->deactivated ? "deactivated:" : "activated:", + __entry->connected ? "connected" : "disconnected", + __entry->ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_frame_number, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_wakeup, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_set_selfpowered, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_clear_selfpowered, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_vbus_connect, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_vbus_draw, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_vbus_disconnect, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_connect, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_disconnect, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_deactivate, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DEFINE_EVENT(udc_log_gadget, usb_gadget_activate, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + +DECLARE_EVENT_CLASS(udc_log_ep, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret), + TP_STRUCT__entry( + __dynamic_array(char, name, UDC_TRACE_STR_MAX) + __field(unsigned, maxpacket) + __field(unsigned, maxpacket_limit) + __field(unsigned, max_streams) + __field(unsigned, mult) + __field(unsigned, maxburst) + __field(u8, address) + __field(bool, claimed) + __field(bool, enabled) + __field(int, ret) + ), + TP_fast_assign( + snprintf(__get_str(name), UDC_TRACE_STR_MAX, "%s", ep->name); + __entry->maxpacket = ep->maxpacket; + __entry->maxpacket_limit = ep->maxpacket_limit; + __entry->max_streams = ep->max_streams; + __entry->mult = ep->mult; + __entry->maxburst = ep->maxburst; + __entry->address = ep->address, + __entry->claimed = ep->claimed; + __entry->enabled = ep->enabled; + __entry->ret = ret; + ), + TP_printk("%s: mps %d/%d streams %d mult %d burst %d addr %02x %s%s --> %d", + __get_str(name), __entry->maxpacket, __entry->maxpacket_limit, + __entry->max_streams, __entry->mult, __entry->maxburst, + __entry->address, __entry->claimed ? "claimed:" : "released:", + __entry->enabled ? "enabled" : "disabled", ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_set_maxpacket_limit, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_enable, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_disable, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_set_halt, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_clear_halt, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_set_wedge, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_fifo_status, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DEFINE_EVENT(udc_log_ep, usb_ep_fifo_flush, + TP_PROTO(struct usb_ep *ep, int ret), + TP_ARGS(ep, ret) +); + +DECLARE_EVENT_CLASS(udc_log_req, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret), + TP_STRUCT__entry( + __dynamic_array(char, name, UDC_TRACE_STR_MAX) + __field(unsigned, length) + __field(unsigned, actual) + __field(unsigned, num_sgs) + __field(unsigned, num_mapped_sgs) + __field(unsigned, stream_id) + __field(unsigned, no_interrupt) + __field(unsigned, zero) + __field(unsigned, short_not_ok) + __field(int, status) + __field(int, ret) + ), + TP_fast_assign( + snprintf(__get_str(name), UDC_TRACE_STR_MAX, "%s", ep->name); + __entry->length = req->length; + __entry->actual = req->actual; + __entry->num_sgs = req->num_sgs; + __entry->num_mapped_sgs = req->num_mapped_sgs; + __entry->stream_id = req->stream_id; + __entry->no_interrupt = req->no_interrupt; + __entry->zero = req->zero; + __entry->short_not_ok = req->short_not_ok; + __entry->status = req->status; + __entry->ret = ret; + ), + TP_printk("%s: length %d/%d sgs %d/%d stream %d %s%s%s status %d --> %d", + __get_str(name), __entry->actual, __entry->length, + __entry->num_mapped_sgs, __entry->num_sgs, __entry->stream_id, + __entry->zero ? "Z" : "z", + __entry->short_not_ok ? "S" : "s", + __entry->no_interrupt ? "i" : "I", + __entry->status, __entry->ret + ) +); + +DEFINE_EVENT(udc_log_req, usb_ep_alloc_request, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret) +); + +DEFINE_EVENT(udc_log_req, usb_ep_free_request, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret) +); + +DEFINE_EVENT(udc_log_req, usb_ep_queue, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret) +); + +DEFINE_EVENT(udc_log_req, usb_ep_dequeue, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret) +); + +DEFINE_EVENT(udc_log_req, usb_gadget_giveback_request, + TP_PROTO(struct usb_ep *ep, struct usb_request *req, int ret), + TP_ARGS(ep, req, ret) +); + +#endif /* __UDC_TRACE_H */ + +/* this part has to be here */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +#include diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c deleted file mode 100644 index abf013865e51..000000000000 --- a/drivers/usb/gadget/udc/udc-core.c +++ /dev/null @@ -1,1373 +0,0 @@ -/** - * udc.c - Core UDC Framework - * - * Copyright (C) 2010 Texas Instruments - * Author: Felipe Balbi - * - * This program is free software: you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 of - * the License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -/** - * struct usb_udc - describes one usb device controller - * @driver - the gadget driver pointer. For use by the class code - * @dev - the child device to the actual controller - * @gadget - the gadget. For use by the class code - * @list - for use by the udc class driver - * @vbus - for udcs who care about vbus status, this value is real vbus status; - * for udcs who do not care about vbus status, this value is always true - * - * This represents the internal data structure which is used by the UDC-class - * to hold information about udc driver and gadget together. - */ -struct usb_udc { - struct usb_gadget_driver *driver; - struct usb_gadget *gadget; - struct device dev; - struct list_head list; - bool vbus; -}; - -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); - -/* ------------------------------------------------------------------------- */ - -/** - * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint - * @ep:the endpoint being configured - * @maxpacket_limit:value of maximum packet size limit - * - * This function should be used only in UDC drivers to initialize endpoint - * (usually in probe function). - */ -void usb_ep_set_maxpacket_limit(struct usb_ep *ep, - unsigned maxpacket_limit) -{ - ep->maxpacket_limit = maxpacket_limit; - ep->maxpacket = maxpacket_limit; -} -EXPORT_SYMBOL_GPL(usb_ep_set_maxpacket_limit); - -/** - * usb_ep_enable - configure endpoint, making it usable - * @ep:the endpoint being configured. may not be the endpoint named "ep0". - * drivers discover endpoints through the ep_list of a usb_gadget. - * - * When configurations are set, or when interface settings change, the driver - * will enable or disable the relevant endpoints. while it is enabled, an - * endpoint may be used for i/o until the driver receives a disconnect() from - * the host or until the endpoint is disabled. - * - * the ep0 implementation (which calls this routine) must ensure that the - * hardware capabilities of each endpoint match the descriptor provided - * for it. for example, an endpoint named "ep2in-bulk" would be usable - * for interrupt transfers as well as bulk, but it likely couldn't be used - * for iso transfers or for endpoint 14. some endpoints are fully - * configurable, with more generic names like "ep-a". (remember that for - * USB, "in" means "towards the USB master".) - * - * returns zero, or a negative error code. - */ -int usb_ep_enable(struct usb_ep *ep) -{ - int ret; - - if (ep->enabled) - return 0; - - ret = ep->ops->enable(ep, ep->desc); - if (ret) - return ret; - - ep->enabled = true; - - return 0; -} -EXPORT_SYMBOL_GPL(usb_ep_enable); - -/** - * usb_ep_disable - endpoint is no longer usable - * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". - * - * no other task may be using this endpoint when this is called. - * any pending and uncompleted requests will complete with status - * indicating disconnect (-ESHUTDOWN) before this call returns. - * gadget drivers must call usb_ep_enable() again before queueing - * requests to the endpoint. - * - * returns zero, or a negative error code. - */ -int usb_ep_disable(struct usb_ep *ep) -{ - int ret; - - if (!ep->enabled) - return 0; - - ret = ep->ops->disable(ep); - if (ret) - return ret; - - ep->enabled = false; - - return 0; -} -EXPORT_SYMBOL_GPL(usb_ep_disable); - -/** - * usb_ep_alloc_request - allocate a request object to use with this endpoint - * @ep:the endpoint to be used with with the request - * @gfp_flags:GFP_* flags to use - * - * Request objects must be allocated with this call, since they normally - * need controller-specific setup and may even need endpoint-specific - * resources such as allocation of DMA descriptors. - * Requests may be submitted with usb_ep_queue(), and receive a single - * completion callback. Free requests with usb_ep_free_request(), when - * they are no longer needed. - * - * Returns the request, or null if one could not be allocated. - */ -struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, - gfp_t gfp_flags) -{ - return ep->ops->alloc_request(ep, gfp_flags); -} -EXPORT_SYMBOL_GPL(usb_ep_alloc_request); - -/** - * usb_ep_free_request - frees a request object - * @ep:the endpoint associated with the request - * @req:the request being freed - * - * Reverses the effect of usb_ep_alloc_request(). - * Caller guarantees the request is not queued, and that it will - * no longer be requeued (or otherwise used). - */ -void usb_ep_free_request(struct usb_ep *ep, - struct usb_request *req) -{ - ep->ops->free_request(ep, req); -} -EXPORT_SYMBOL_GPL(usb_ep_free_request); - -/** - * usb_ep_queue - queues (submits) an I/O request to an endpoint. - * @ep:the endpoint associated with the request - * @req:the request being submitted - * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't - * pre-allocate all necessary memory with the request. - * - * This tells the device controller to perform the specified request through - * that endpoint (reading or writing a buffer). When the request completes, - * including being canceled by usb_ep_dequeue(), the request's completion - * routine is called to return the request to the driver. Any endpoint - * (except control endpoints like ep0) may have more than one transfer - * request queued; they complete in FIFO order. Once a gadget driver - * submits a request, that request may not be examined or modified until it - * is given back to that driver through the completion callback. - * - * Each request is turned into one or more packets. The controller driver - * never merges adjacent requests into the same packet. OUT transfers - * will sometimes use data that's already buffered in the hardware. - * Drivers can rely on the fact that the first byte of the request's buffer - * always corresponds to the first byte of some USB packet, for both - * IN and OUT transfers. - * - * Bulk endpoints can queue any amount of data; the transfer is packetized - * automatically. The last packet will be short if the request doesn't fill it - * out completely. Zero length packets (ZLPs) should be avoided in portable - * protocols since not all usb hardware can successfully handle zero length - * packets. (ZLPs may be explicitly written, and may be implicitly written if - * the request 'zero' flag is set.) Bulk endpoints may also be used - * for interrupt transfers; but the reverse is not true, and some endpoints - * won't support every interrupt transfer. (Such as 768 byte packets.) - * - * Interrupt-only endpoints are less functional than bulk endpoints, for - * example by not supporting queueing or not handling buffers that are - * larger than the endpoint's maxpacket size. They may also treat data - * toggle differently. - * - * Control endpoints ... after getting a setup() callback, the driver queues - * one response (even if it would be zero length). That enables the - * status ack, after transferring data as specified in the response. Setup - * functions may return negative error codes to generate protocol stalls. - * (Note that some USB device controllers disallow protocol stall responses - * in some cases.) When control responses are deferred (the response is - * written after the setup callback returns), then usb_ep_set_halt() may be - * used on ep0 to trigger protocol stalls. Depending on the controller, - * it may not be possible to trigger a status-stage protocol stall when the - * data stage is over, that is, from within the response's completion - * routine. - * - * For periodic endpoints, like interrupt or isochronous ones, the usb host - * arranges to poll once per interval, and the gadget driver usually will - * have queued some data to transfer at that time. - * - * Returns zero, or a negative error code. Endpoints that are not enabled - * report errors; errors will also be - * reported when the usb peripheral is disconnected. - */ -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); -} -EXPORT_SYMBOL_GPL(usb_ep_queue); - -/** - * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint - * @ep:the endpoint associated with the request - * @req:the request being canceled - * - * If the request is still active on the endpoint, it is dequeued and its - * completion routine is called (with status -ECONNRESET); else a negative - * error code is returned. This is guaranteed to happen before the call to - * usb_ep_dequeue() returns. - * - * Note that some hardware can't clear out write fifos (to unlink the request - * at the head of the queue) except as part of disconnecting from usb. Such - * restrictions prevent drivers from supporting configuration changes, - * even to configuration zero (a "chapter 9" requirement). - */ -int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) -{ - return ep->ops->dequeue(ep, req); -} -EXPORT_SYMBOL_GPL(usb_ep_dequeue); - -/** - * usb_ep_set_halt - sets the endpoint halt feature. - * @ep: the non-isochronous endpoint being stalled - * - * Use this to stall an endpoint, perhaps as an error report. - * Except for control endpoints, - * the endpoint stays halted (will not stream any data) until the host - * clears this feature; drivers may need to empty the endpoint's request - * queue first, to make sure no inappropriate transfers happen. - * - * Note that while an endpoint CLEAR_FEATURE will be invisible to the - * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the - * current altsetting, see usb_ep_clear_halt(). When switching altsettings, - * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. - * - * Returns zero, or a negative error code. On success, this call sets - * underlying hardware state that blocks data transfers. - * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any - * transfer requests are still queued, or if the controller hardware - * (usually a FIFO) still holds bytes that the host hasn't collected. - */ -int usb_ep_set_halt(struct usb_ep *ep) -{ - return ep->ops->set_halt(ep, 1); -} -EXPORT_SYMBOL_GPL(usb_ep_set_halt); - -/** - * usb_ep_clear_halt - clears endpoint halt, and resets toggle - * @ep:the bulk or interrupt endpoint being reset - * - * Use this when responding to the standard usb "set interface" request, - * for endpoints that aren't reconfigured, after clearing any other state - * in the endpoint's i/o queue. - * - * Returns zero, or a negative error code. On success, this call clears - * the underlying hardware state reflecting endpoint halt and data toggle. - * Note that some hardware can't support this request (like pxa2xx_udc), - * and accordingly can't correctly implement interface altsettings. - */ -int usb_ep_clear_halt(struct usb_ep *ep) -{ - return ep->ops->set_halt(ep, 0); -} -EXPORT_SYMBOL_GPL(usb_ep_clear_halt); - -/** - * usb_ep_set_wedge - sets the halt feature and ignores clear requests - * @ep: the endpoint being wedged - * - * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) - * requests. If the gadget driver clears the halt status, it will - * automatically unwedge the endpoint. - * - * Returns zero on success, else negative errno. - */ -int usb_ep_set_wedge(struct usb_ep *ep) -{ - if (ep->ops->set_wedge) - return ep->ops->set_wedge(ep); - else - return ep->ops->set_halt(ep, 1); -} -EXPORT_SYMBOL_GPL(usb_ep_set_wedge); - -/** - * usb_ep_fifo_status - returns number of bytes in fifo, or error - * @ep: the endpoint whose fifo status is being checked. - * - * FIFO endpoints may have "unclaimed data" in them in certain cases, - * such as after aborted transfers. Hosts may not have collected all - * the IN data written by the gadget driver (and reported by a request - * completion). The gadget driver may not have collected all the data - * written OUT to it by the host. Drivers that need precise handling for - * fault reporting or recovery may need to use this call. - * - * This returns the number of such bytes in the fifo, or a negative - * errno if the endpoint doesn't use a FIFO or doesn't support such - * precise handling. - */ -int usb_ep_fifo_status(struct usb_ep *ep) -{ - if (ep->ops->fifo_status) - return ep->ops->fifo_status(ep); - else - return -EOPNOTSUPP; -} -EXPORT_SYMBOL_GPL(usb_ep_fifo_status); - -/** - * usb_ep_fifo_flush - flushes contents of a fifo - * @ep: the endpoint whose fifo is being flushed. - * - * This call may be used to flush the "unclaimed data" that may exist in - * an endpoint fifo after abnormal transaction terminations. The call - * must never be used except when endpoint is not being used for any - * protocol translation. - */ -void usb_ep_fifo_flush(struct usb_ep *ep) -{ - if (ep->ops->fifo_flush) - ep->ops->fifo_flush(ep); -} -EXPORT_SYMBOL_GPL(usb_ep_fifo_flush); - -/* ------------------------------------------------------------------------- */ - -/** - * usb_gadget_frame_number - returns the current frame number - * @gadget: controller that reports the frame number - * - * Returns the usb frame number, normally eleven bits from a SOF packet, - * or negative errno if this device doesn't support this capability. - */ -int usb_gadget_frame_number(struct usb_gadget *gadget) -{ - return gadget->ops->get_frame(gadget); -} -EXPORT_SYMBOL_GPL(usb_gadget_frame_number); - -/** - * usb_gadget_wakeup - tries to wake up the host connected to this gadget - * @gadget: controller used to wake up the host - * - * Returns zero on success, else negative error code if the hardware - * doesn't support such attempts, or its support has not been enabled - * by the usb host. Drivers must return device descriptors that report - * their ability to support this, or hosts won't enable it. - * - * This may also try to use SRP to wake the host and start enumeration, - * even if OTG isn't otherwise in use. OTG devices may also start - * remote wakeup even when hosts don't explicitly enable it. - */ -int usb_gadget_wakeup(struct usb_gadget *gadget) -{ - if (!gadget->ops->wakeup) - return -EOPNOTSUPP; - return gadget->ops->wakeup(gadget); -} -EXPORT_SYMBOL_GPL(usb_gadget_wakeup); - -/** - * usb_gadget_set_selfpowered - sets the device selfpowered feature. - * @gadget:the device being declared as self-powered - * - * this affects the device status reported by the hardware driver - * to reflect that it now has a local power supply. - * - * returns zero on success, else negative errno. - */ -int usb_gadget_set_selfpowered(struct usb_gadget *gadget) -{ - if (!gadget->ops->set_selfpowered) - return -EOPNOTSUPP; - return gadget->ops->set_selfpowered(gadget, 1); -} -EXPORT_SYMBOL_GPL(usb_gadget_set_selfpowered); - -/** - * usb_gadget_clear_selfpowered - clear the device selfpowered feature. - * @gadget:the device being declared as bus-powered - * - * this affects the device status reported by the hardware driver. - * some hardware may not support bus-powered operation, in which - * case this feature's value can never change. - * - * returns zero on success, else negative errno. - */ -int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) -{ - if (!gadget->ops->set_selfpowered) - return -EOPNOTSUPP; - return gadget->ops->set_selfpowered(gadget, 0); -} -EXPORT_SYMBOL_GPL(usb_gadget_clear_selfpowered); - -/** - * usb_gadget_vbus_connect - Notify controller that VBUS is powered - * @gadget:The device which now has VBUS power. - * Context: can sleep - * - * This call is used by a driver for an external transceiver (or GPIO) - * that detects a VBUS power session starting. Common responses include - * resuming the controller, activating the D+ (or D-) pullup to let the - * host detect that a USB device is attached, and starting to draw power - * (8mA or possibly more, especially after SET_CONFIGURATION). - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_vbus_connect(struct usb_gadget *gadget) -{ - if (!gadget->ops->vbus_session) - return -EOPNOTSUPP; - return gadget->ops->vbus_session(gadget, 1); -} -EXPORT_SYMBOL_GPL(usb_gadget_vbus_connect); - -/** - * usb_gadget_vbus_draw - constrain controller's VBUS power usage - * @gadget:The device whose VBUS usage is being described - * @mA:How much current to draw, in milliAmperes. This should be twice - * the value listed in the configuration descriptor bMaxPower field. - * - * This call is used by gadget drivers during SET_CONFIGURATION calls, - * reporting how much power the device may consume. For example, this - * could affect how quickly batteries are recharged. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) -{ - if (!gadget->ops->vbus_draw) - return -EOPNOTSUPP; - return gadget->ops->vbus_draw(gadget, mA); -} -EXPORT_SYMBOL_GPL(usb_gadget_vbus_draw); - -/** - * usb_gadget_vbus_disconnect - notify controller about VBUS session end - * @gadget:the device whose VBUS supply is being described - * Context: can sleep - * - * This call is used by a driver for an external transceiver (or GPIO) - * that detects a VBUS power session ending. Common responses include - * reversing everything done in usb_gadget_vbus_connect(). - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) -{ - if (!gadget->ops->vbus_session) - return -EOPNOTSUPP; - return gadget->ops->vbus_session(gadget, 0); -} -EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); - -/** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected - * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). This pullup is always enabled unless - * usb_gadget_disconnect() has been used to disable it. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - if (!gadget->ops->pullup) - return -EOPNOTSUPP; - - if (gadget->deactivated) { - /* - * If gadget is deactivated we only save new state. - * Gadget will be connected automatically after activation. - */ - gadget->connected = true; - return 0; - } - - ret = gadget->ops->pullup(gadget, 1); - if (!ret) - gadget->connected = 1; - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_connect); - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - if (!gadget->ops->pullup) - return -EOPNOTSUPP; - - if (gadget->deactivated) { - /* - * If gadget is deactivated we only save new state. - * Gadget will stay disconnected after activation. - */ - gadget->connected = false; - return 0; - } - - ret = gadget->ops->pullup(gadget, 0); - if (!ret) - gadget->connected = 0; - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_disconnect); - -/** - * usb_gadget_deactivate - deactivate function which is not ready to work - * @gadget: the peripheral being deactivated - * - * This routine may be used during the gadget driver bind() call to prevent - * the peripheral from ever being visible to the USB host, unless later - * usb_gadget_activate() is called. For example, user mode components may - * need to be activated before the system can talk to hosts. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_deactivate(struct usb_gadget *gadget) -{ - int ret; - - if (gadget->deactivated) - return 0; - - if (gadget->connected) { - ret = usb_gadget_disconnect(gadget); - if (ret) - return ret; - /* - * If gadget was being connected before deactivation, we want - * to reconnect it in usb_gadget_activate(). - */ - gadget->connected = true; - } - gadget->deactivated = true; - - return 0; -} -EXPORT_SYMBOL_GPL(usb_gadget_deactivate); - -/** - * usb_gadget_activate - activate function which is not ready to work - * @gadget: the peripheral being activated - * - * This routine activates gadget which was previously deactivated with - * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_activate(struct usb_gadget *gadget) -{ - if (!gadget->deactivated) - return 0; - - gadget->deactivated = false; - - /* - * If gadget has been connected before deactivation, or became connected - * while it was being deactivated, we call usb_gadget_connect(). - */ - if (gadget->connected) - return usb_gadget_connect(gadget); - - return 0; -} -EXPORT_SYMBOL_GPL(usb_gadget_activate); - -/* ------------------------------------------------------------------------- */ - -#ifdef CONFIG_HAS_DMA - -int usb_gadget_map_request_by_dev(struct device *dev, - struct usb_request *req, int is_in) -{ - if (req->length == 0) - return 0; - - if (req->num_sgs) { - int mapped; - - mapped = dma_map_sg(dev, req->sg, req->num_sgs, - is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - if (mapped == 0) { - dev_err(dev, "failed to map SGs\n"); - return -EFAULT; - } - - req->num_mapped_sgs = mapped; - } else { - req->dma = dma_map_single(dev, req->buf, req->length, - is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - - if (dma_mapping_error(dev, req->dma)) { - dev_err(dev, "failed to map buffer\n"); - return -EFAULT; - } - } - - return 0; -} -EXPORT_SYMBOL_GPL(usb_gadget_map_request_by_dev); - -int usb_gadget_map_request(struct usb_gadget *gadget, - struct usb_request *req, int is_in) -{ - return usb_gadget_map_request_by_dev(gadget->dev.parent, req, is_in); -} -EXPORT_SYMBOL_GPL(usb_gadget_map_request); - -void usb_gadget_unmap_request_by_dev(struct device *dev, - struct usb_request *req, int is_in) -{ - if (req->length == 0) - return; - - if (req->num_mapped_sgs) { - dma_unmap_sg(dev, req->sg, req->num_mapped_sgs, - is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - - req->num_mapped_sgs = 0; - } else { - dma_unmap_single(dev, req->dma, req->length, - is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - } -} -EXPORT_SYMBOL_GPL(usb_gadget_unmap_request_by_dev); - -void usb_gadget_unmap_request(struct usb_gadget *gadget, - struct usb_request *req, int is_in) -{ - usb_gadget_unmap_request_by_dev(gadget->dev.parent, req, is_in); -} -EXPORT_SYMBOL_GPL(usb_gadget_unmap_request); - -#endif /* CONFIG_HAS_DMA */ - -/* ------------------------------------------------------------------------- */ - -/** - * usb_gadget_giveback_request - give the request back to the gadget layer - * Context: in_interrupt() - * - * This is called by device controller drivers in order to return the - * completed request back to the gadget layer. - */ -void usb_gadget_giveback_request(struct usb_ep *ep, - struct usb_request *req) -{ - if (likely(req->status == 0)) - usb_led_activity(USB_LED_EVENT_GADGET); - - req->complete(ep, req); -} -EXPORT_SYMBOL_GPL(usb_gadget_giveback_request); - -/* ------------------------------------------------------------------------- */ - -/** - * gadget_find_ep_by_name - returns ep whose name is the same as sting passed - * in second parameter or NULL if searched endpoint not found - * @g: controller to check for quirk - * @name: name of searched endpoint - */ -struct usb_ep *gadget_find_ep_by_name(struct usb_gadget *g, const char *name) -{ - struct usb_ep *ep; - - gadget_for_each_ep(ep, g) { - if (!strcmp(ep->name, name)) - return ep; - } - - return NULL; -} -EXPORT_SYMBOL_GPL(gadget_find_ep_by_name); - -/* ------------------------------------------------------------------------- */ - -int usb_gadget_ep_match_desc(struct usb_gadget *gadget, - struct usb_ep *ep, struct usb_endpoint_descriptor *desc, - struct usb_ss_ep_comp_descriptor *ep_comp) -{ - u8 type; - u16 max; - int num_req_streams = 0; - - /* endpoint already claimed? */ - if (ep->claimed) - return 0; - - type = usb_endpoint_type(desc); - max = 0x7ff & usb_endpoint_maxp(desc); - - if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) - return 0; - if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) - return 0; - - if (max > ep->maxpacket_limit) - return 0; - - /* "high bandwidth" works only at high speed */ - if (!gadget_is_dualspeed(gadget) && usb_endpoint_maxp(desc) & (3<<11)) - return 0; - - switch (type) { - case USB_ENDPOINT_XFER_CONTROL: - /* only support ep0 for portable CONTROL traffic */ - return 0; - case USB_ENDPOINT_XFER_ISOC: - if (!ep->caps.type_iso) - return 0; - /* ISO: limit 1023 bytes full speed, 1024 high/super speed */ - if (!gadget_is_dualspeed(gadget) && max > 1023) - return 0; - break; - case USB_ENDPOINT_XFER_BULK: - if (!ep->caps.type_bulk) - return 0; - if (ep_comp && gadget_is_superspeed(gadget)) { - /* Get the number of required streams from the - * EP companion descriptor and see if the EP - * matches it - */ - num_req_streams = ep_comp->bmAttributes & 0x1f; - if (num_req_streams > ep->max_streams) - return 0; - } - break; - case USB_ENDPOINT_XFER_INT: - /* Bulk endpoints handle interrupt transfers, - * except the toggle-quirky iso-synch kind - */ - if (!ep->caps.type_int && !ep->caps.type_bulk) - return 0; - /* INT: limit 64 bytes full speed, 1024 high/super speed */ - if (!gadget_is_dualspeed(gadget) && max > 64) - return 0; - break; - } - - return 1; -} -EXPORT_SYMBOL_GPL(usb_gadget_ep_match_desc); - -/* ------------------------------------------------------------------------- */ - -static void usb_gadget_state_work(struct work_struct *work) -{ - struct usb_gadget *gadget = work_to_gadget(work); - struct usb_udc *udc = gadget->udc; - - if (udc) - sysfs_notify(&udc->dev.kobj, NULL, "state"); -} - -void usb_gadget_set_state(struct usb_gadget *gadget, - enum usb_device_state state) -{ - gadget->state = state; - schedule_work(&gadget->work); -} -EXPORT_SYMBOL_GPL(usb_gadget_set_state); - -/* ------------------------------------------------------------------------- */ - -static void usb_udc_connect_control(struct usb_udc *udc) -{ - if (udc->vbus) - usb_gadget_connect(udc->gadget); - else - usb_gadget_disconnect(udc->gadget); -} - -/** - * usb_udc_vbus_handler - updates the udc core vbus status, and try to - * connect or disconnect gadget - * @gadget: The gadget which vbus change occurs - * @status: The vbus status - * - * The udc driver calls it when it wants to connect or disconnect gadget - * according to vbus status. - */ -void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) -{ - struct usb_udc *udc = gadget->udc; - - if (udc) { - udc->vbus = status; - usb_udc_connect_control(udc); - } -} -EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); - -/** - * usb_gadget_udc_reset - notifies the udc core that bus reset occurs - * @gadget: The gadget which bus reset occurs - * @driver: The gadget driver we want to notify - * - * If the udc driver has bus reset handler, it needs to call this when the bus - * reset occurs, it notifies the gadget driver that the bus reset occurs as - * well as updates gadget state. - */ -void usb_gadget_udc_reset(struct usb_gadget *gadget, - struct usb_gadget_driver *driver) -{ - driver->reset(gadget); - usb_gadget_set_state(gadget, USB_STATE_DEFAULT); -} -EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); - -/** - * usb_gadget_udc_start - tells usb device controller to start up - * @udc: The UDC to be started - * - * This call is issued by the UDC Class driver when it's about - * to register a gadget driver to the device controller, before - * calling gadget driver's bind() method. - * - * It allows the controller to be powered off until strictly - * necessary to have it powered on. - * - * Returns zero on success, else negative errno. - */ -static inline int usb_gadget_udc_start(struct usb_udc *udc) -{ - return udc->gadget->ops->udc_start(udc->gadget, udc->driver); -} - -/** - * usb_gadget_udc_stop - tells usb device controller we don't need it anymore - * @gadget: The device we want to stop activity - * @driver: The driver to unbind from @gadget - * - * This call is issued by the UDC Class driver after calling - * gadget driver's unbind() method. - * - * The details are implementation specific, but it can go as - * far as powering off UDC completely and disable its data - * line pullups. - */ -static inline void usb_gadget_udc_stop(struct usb_udc *udc) -{ - udc->gadget->ops->udc_stop(udc->gadget); -} - -/** - * usb_udc_release - release the usb_udc struct - * @dev: the dev member within usb_udc - * - * This is called by driver's core in order to free memory once the last - * reference is released. - */ -static void usb_udc_release(struct device *dev) -{ - struct usb_udc *udc; - - udc = container_of(dev, struct usb_udc, dev); - dev_dbg(dev, "releasing '%s'\n", dev_name(dev)); - kfree(udc); -} - -static const struct attribute_group *usb_udc_attr_groups[]; - -static void usb_udc_nop_release(struct device *dev) -{ - dev_vdbg(dev, "%s\n", __func__); -} - -/** - * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list - * @parent: the parent device to this udc. Usually the controller driver's - * device. - * @gadget: the gadget to be added to the list. - * @release: a gadget release function. - * - * Returns zero on success, negative errno otherwise. - */ -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); - if (!udc) - goto err1; - - dev_set_name(&gadget->dev, "gadget"); - INIT_WORK(&gadget->work, usb_gadget_state_work); - gadget->dev.parent = parent; - - if (release) - gadget->dev.release = release; - else - gadget->dev.release = usb_udc_nop_release; - - ret = device_register(&gadget->dev); - if (ret) - goto err2; - - device_initialize(&udc->dev); - udc->dev.release = usb_udc_release; - udc->dev.class = udc_class; - udc->dev.groups = usb_udc_attr_groups; - udc->dev.parent = parent; - ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj)); - if (ret) - goto err3; - - udc->gadget = gadget; - gadget->udc = udc; - - mutex_lock(&udc_lock); - list_add_tail(&udc->list, &udc_list); - - ret = device_add(&udc->dev); - if (ret) - goto err4; - - 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 != -EPROBE_DEFER) - list_del(&driver->pending); - if (ret) - goto err4; - break; - } - } - - mutex_unlock(&udc_lock); - - return 0; - -err4: - list_del(&udc->list); - mutex_unlock(&udc_lock); - -err3: - put_device(&udc->dev); - device_del(&gadget->dev); - -err2: - put_device(&gadget->dev); - kfree(udc); - -err1: - return ret; -} -EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release); - -/** - * usb_get_gadget_udc_name - get the name of the first UDC controller - * This functions returns the name of the first UDC controller in the system. - * Please note that this interface is usefull only for legacy drivers which - * assume that there is only one UDC controller in the system and they need to - * get its name before initialization. There is no guarantee that the UDC - * of the returned name will be still available, when gadget driver registers - * itself. - * - * Returns pointer to string with UDC controller name on success, NULL - * otherwise. Caller should kfree() returned string. - */ -char *usb_get_gadget_udc_name(void) -{ - struct usb_udc *udc; - char *name = NULL; - - /* For now we take the first available UDC */ - mutex_lock(&udc_lock); - list_for_each_entry(udc, &udc_list, list) { - if (!udc->driver) { - name = kstrdup(udc->gadget->name, GFP_KERNEL); - break; - } - } - mutex_unlock(&udc_lock); - return name; -} -EXPORT_SYMBOL_GPL(usb_get_gadget_udc_name); - -/** - * usb_add_gadget_udc - adds a new gadget to the udc class driver list - * @parent: the parent device to this udc. Usually the controller - * driver's device. - * @gadget: the gadget to be added to the list - * - * Returns zero on success, negative errno otherwise. - */ -int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget) -{ - return usb_add_gadget_udc_release(parent, gadget, NULL); -} -EXPORT_SYMBOL_GPL(usb_add_gadget_udc); - -static void usb_gadget_remove_driver(struct usb_udc *udc) -{ - dev_dbg(&udc->dev, "unregistering UDC driver [%s]\n", - udc->driver->function); - - kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - - usb_gadget_disconnect(udc->gadget); - udc->driver->disconnect(udc->gadget); - udc->driver->unbind(udc->gadget); - usb_gadget_udc_stop(udc); - - udc->driver = NULL; - udc->dev.driver = NULL; - udc->gadget->dev.driver = NULL; -} - -/** - * usb_del_gadget_udc - deletes @udc from udc_list - * @gadget: the gadget to be removed. - * - * This, will call usb_gadget_unregister_driver() if - * the @udc is still busy. - */ -void usb_del_gadget_udc(struct usb_gadget *gadget) -{ - struct usb_udc *udc = gadget->udc; - - if (!udc) - return; - - dev_vdbg(gadget->dev.parent, "unregistering gadget\n"); - - mutex_lock(&udc_lock); - list_del(&udc->list); - - 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); - device_unregister(&udc->dev); - device_unregister(&gadget->dev); -} -EXPORT_SYMBOL_GPL(usb_del_gadget_udc); - -/* ------------------------------------------------------------------------- */ - -static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *driver) -{ - int ret; - - dev_dbg(&udc->dev, "registering UDC driver [%s]\n", - driver->function); - - udc->driver = driver; - udc->dev.driver = &driver->driver; - udc->gadget->dev.driver = &driver->driver; - - ret = driver->bind(udc->gadget, driver); - if (ret) - goto err1; - ret = usb_gadget_udc_start(udc); - if (ret) { - driver->unbind(udc->gadget); - goto err1; - } - usb_udc_connect_control(udc); - - kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - return 0; -err1: - if (ret != -EISNAM) - dev_err(&udc->dev, "failed to start %s: %d\n", - udc->driver->function, ret); - udc->driver = NULL; - udc->dev.driver = NULL; - udc->gadget->dev.driver = NULL; - return ret; -} - -int usb_gadget_probe_driver(struct usb_gadget_driver *driver) -{ - struct usb_udc *udc = NULL; - int ret = -ENODEV; - - if (!driver || !driver->bind || !driver->setup) - return -EINVAL; - - mutex_lock(&udc_lock); - 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 && !udc->driver) - goto found; - } else { - list_for_each_entry(udc, &udc_list, list) { - /* For now we take the first one */ - if (!udc->driver) - goto found; - } - } - - if (!driver->match_existing_only) { - 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); - ret = 0; - } - - mutex_unlock(&udc_lock); - return ret; -found: - ret = udc_bind_to_driver(udc, driver); - mutex_unlock(&udc_lock); - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_probe_driver); - -int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) -{ - struct usb_udc *udc = NULL; - int ret = -ENODEV; - - if (!driver || !driver->unbind) - return -EINVAL; - - mutex_lock(&udc_lock); - list_for_each_entry(udc, &udc_list, list) - if (udc->driver == driver) { - usb_gadget_remove_driver(udc); - usb_gadget_set_state(udc->gadget, - USB_STATE_NOTATTACHED); - ret = 0; - break; - } - - if (ret) { - list_del(&driver->pending); - ret = 0; - } - mutex_unlock(&udc_lock); - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver); - -/* ------------------------------------------------------------------------- */ - -static ssize_t usb_udc_srp_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t n) -{ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); - - if (sysfs_streq(buf, "1")) - usb_gadget_wakeup(udc->gadget); - - return n; -} -static DEVICE_ATTR(srp, S_IWUSR, NULL, usb_udc_srp_store); - -static ssize_t usb_udc_softconn_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t n) -{ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); - - if (!udc->driver) { - dev_err(dev, "soft-connect without a gadget driver\n"); - return -EOPNOTSUPP; - } - - if (sysfs_streq(buf, "connect")) { - usb_gadget_udc_start(udc); - usb_gadget_connect(udc->gadget); - } else if (sysfs_streq(buf, "disconnect")) { - usb_gadget_disconnect(udc->gadget); - udc->driver->disconnect(udc->gadget); - usb_gadget_udc_stop(udc); - } else { - dev_err(dev, "unsupported command '%s'\n", buf); - return -EINVAL; - } - - return n; -} -static DEVICE_ATTR(soft_connect, S_IWUSR, NULL, usb_udc_softconn_store); - -static ssize_t state_show(struct device *dev, struct device_attribute *attr, - char *buf) -{ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); - struct usb_gadget *gadget = udc->gadget; - - return sprintf(buf, "%s\n", usb_state_string(gadget->state)); -} -static DEVICE_ATTR_RO(state); - -#define USB_UDC_SPEED_ATTR(name, param) \ -ssize_t name##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ - return snprintf(buf, PAGE_SIZE, "%s\n", \ - usb_speed_string(udc->gadget->param)); \ -} \ -static DEVICE_ATTR_RO(name) - -static USB_UDC_SPEED_ATTR(current_speed, speed); -static USB_UDC_SPEED_ATTR(maximum_speed, max_speed); - -#define USB_UDC_ATTR(name) \ -ssize_t name##_show(struct device *dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ - struct usb_gadget *gadget = udc->gadget; \ - \ - return snprintf(buf, PAGE_SIZE, "%d\n", gadget->name); \ -} \ -static DEVICE_ATTR_RO(name) - -static USB_UDC_ATTR(is_otg); -static USB_UDC_ATTR(is_a_peripheral); -static USB_UDC_ATTR(b_hnp_enable); -static USB_UDC_ATTR(a_hnp_support); -static USB_UDC_ATTR(a_alt_hnp_support); -static USB_UDC_ATTR(is_selfpowered); - -static struct attribute *usb_udc_attrs[] = { - &dev_attr_srp.attr, - &dev_attr_soft_connect.attr, - &dev_attr_state.attr, - &dev_attr_current_speed.attr, - &dev_attr_maximum_speed.attr, - - &dev_attr_is_otg.attr, - &dev_attr_is_a_peripheral.attr, - &dev_attr_b_hnp_enable.attr, - &dev_attr_a_hnp_support.attr, - &dev_attr_a_alt_hnp_support.attr, - &dev_attr_is_selfpowered.attr, - NULL, -}; - -static const struct attribute_group usb_udc_attr_group = { - .attrs = usb_udc_attrs, -}; - -static const struct attribute_group *usb_udc_attr_groups[] = { - &usb_udc_attr_group, - NULL, -}; - -static int usb_udc_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct usb_udc *udc = container_of(dev, struct usb_udc, dev); - int ret; - - ret = add_uevent_var(env, "USB_UDC_NAME=%s", udc->gadget->name); - if (ret) { - dev_err(dev, "failed to add uevent USB_UDC_NAME\n"); - return ret; - } - - if (udc->driver) { - ret = add_uevent_var(env, "USB_UDC_DRIVER=%s", - udc->driver->function); - if (ret) { - dev_err(dev, "failed to add uevent USB_UDC_DRIVER\n"); - return ret; - } - } - - return 0; -} - -static int __init usb_udc_init(void) -{ - udc_class = class_create(THIS_MODULE, "udc"); - if (IS_ERR(udc_class)) { - pr_err("failed to create udc class --> %ld\n", - PTR_ERR(udc_class)); - return PTR_ERR(udc_class); - } - - udc_class->dev_uevent = usb_udc_uevent; - return 0; -} -subsys_initcall(usb_udc_init); - -static void __exit usb_udc_exit(void) -{ - class_destroy(udc_class); -} -module_exit(usb_udc_exit); - -MODULE_DESCRIPTION("UDC Framework"); -MODULE_AUTHOR("Felipe Balbi "); -MODULE_LICENSE("GPL v2"); diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index c6e1149ddb0d..612dbdfa388e 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -25,6 +25,8 @@ #include #include +#define UDC_TRACE_STR_MAX 512 + struct usb_ep; /** @@ -324,6 +326,7 @@ struct usb_gadget_ops { * @dev: Driver model state for this abstract device. * @out_epnum: last used out ep number * @in_epnum: last used in ep number + * @mA: last set mA value * @otg_caps: OTG capabilities of this gadget. * @sg_supported: true if we can handle scatter-gather * @is_otg: True if the USB device port uses a Mini-AB jack, so that the @@ -380,6 +383,7 @@ struct usb_gadget { struct device dev; unsigned out_epnum; unsigned in_epnum; + unsigned mA; struct usb_otg_caps *otg_caps; unsigned sg_supported:1; -- cgit v1.2.3 From ce15ed4c5dfb3f7757e6611902aed5db253af977 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 10 Jun 2016 11:46:25 +0200 Subject: USB: Fix of_usb_get_dr_mode_by_phy with a shared phy block Some SoCs have a single phy-hw-block with multiple phys, this is modelled by a single phy dts node, so we end up with multiple controller nodes with a phys property pointing to the phy-node of the otg-phy. Only one of these controllers typically is an otg controller, yet we were checking the first controller who uses a phy from the block and then end up looking for a dr_mode property in e.g. the ehci controller. This commit fixes this by adding an arg0 parameter to of_usb_get_dr_mode_by_phy and make of_usb_get_dr_mode_by_phy check that this matches the phandle args[0] value when looking for the otg controller. Signed-off-by: Hans de Goede Signed-off-by: Felipe Balbi --- drivers/usb/common/common.c | 26 ++++++++++++++++++++------ drivers/usb/phy/phy-am335x.c | 2 +- include/linux/usb/of.h | 4 ++-- 3 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index e3d01619d6b3..5ef8da6e67c3 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -131,15 +131,17 @@ EXPORT_SYMBOL_GPL(usb_get_dr_mode); * 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 + * @arg0: phandle args[0] for phy's with #phy-cells >= 1, or -1 for + * phys which do not have phy-cells * * 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) +enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0) { struct device_node *controller = NULL; - struct device_node *phy; + struct of_phandle_args args; const char *dr_mode; int index; int err; @@ -148,12 +150,24 @@ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np) 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) + if (arg0 == -1) { + args.np = of_parse_phandle(controller, "phys", + index); + args.args_count = 0; + } else { + err = of_parse_phandle_with_args(controller, + "phys", "#phy-cells", + index, &args); + if (err) + break; + } + + of_node_put(args.np); + if (args.np == np && (args.args_count == 0 || + args.args[0] == arg0)) goto finish; index++; - } while (phy); + } while (args.np); } while (controller); finish: diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c index a262a4343f29..7e5aece769da 100644 --- a/drivers/usb/phy/phy-am335x.c +++ b/drivers/usb/phy/phy-am335x.c @@ -54,7 +54,7 @@ static int am335x_phy_probe(struct platform_device *pdev) return am_phy->id; } - am_phy->dr_mode = of_usb_get_dr_mode_by_phy(pdev->dev.of_node); + am_phy->dr_mode = of_usb_get_dr_mode_by_phy(pdev->dev.of_node, -1); ret = usb_phy_gen_create_phy(dev, &am_phy->usb_phy_gen, NULL); if (ret) diff --git a/include/linux/usb/of.h b/include/linux/usb/of.h index de3237fce6b2..5ff9032ee1b4 100644 --- a/include/linux/usb/of.h +++ b/include/linux/usb/of.h @@ -12,7 +12,7 @@ #include #if IS_ENABLED(CONFIG_OF) -enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *phy_np); +enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0); 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); @@ -20,7 +20,7 @@ struct device_node *usb_of_get_child_node(struct device_node *parent, int portnum); #else static inline enum usb_dr_mode -of_usb_get_dr_mode_by_phy(struct device_node *phy_np) +of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0) { return USB_DR_MODE_UNKNOWN; } -- cgit v1.2.3 From b9b092319be29bf665f1b004679de722b81c9123 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 May 2016 23:24:06 +0200 Subject: usb: phy: move msm_hsusb.h into driver As a preparation for another cleanup, this moves the header file for the phy-msm-usb driver into the driver itself. No other file includes it any more, and we don't really want it in the global namespace anyway. Signed-off-by: Arnd Bergmann Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-msm-usb.c | 178 ++++++++++++++++++++++++++++++++++++- include/linux/usb/msm_hsusb.h | 200 ------------------------------------------ 2 files changed, 177 insertions(+), 201 deletions(-) delete mode 100644 include/linux/usb/msm_hsusb.h (limited to 'include') diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 72b387d592c2..8a34759727bb 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -35,6 +36,8 @@ #include #include #include +#include +#include #include #include @@ -42,10 +45,183 @@ #include #include #include -#include #include #include +/** + * OTG control + * + * OTG_NO_CONTROL Id/VBUS notifications not required. Useful in host + * only configuration. + * OTG_PHY_CONTROL Id/VBUS notifications comes form USB PHY. + * OTG_PMIC_CONTROL Id/VBUS notifications comes from PMIC hardware. + * OTG_USER_CONTROL Id/VBUS notifcations comes from User via sysfs. + * + */ +enum otg_control_type { + OTG_NO_CONTROL = 0, + OTG_PHY_CONTROL, + OTG_PMIC_CONTROL, + OTG_USER_CONTROL, +}; + +/** + * PHY used in + * + * INVALID_PHY Unsupported PHY + * CI_45NM_INTEGRATED_PHY Chipidea 45nm integrated PHY + * SNPS_28NM_INTEGRATED_PHY Synopsis 28nm integrated PHY + * + */ +enum msm_usb_phy_type { + INVALID_PHY = 0, + CI_45NM_INTEGRATED_PHY, + SNPS_28NM_INTEGRATED_PHY, +}; + +#define IDEV_CHG_MAX 1500 +#define IUNIT 100 + +/** + * Different states involved in USB charger detection. + * + * USB_CHG_STATE_UNDEFINED USB charger is not connected or detection + * process is not yet started. + * USB_CHG_STATE_WAIT_FOR_DCD Waiting for Data pins contact. + * USB_CHG_STATE_DCD_DONE Data pin contact is detected. + * USB_CHG_STATE_PRIMARY_DONE Primary detection is completed (Detects + * between SDP and DCP/CDP). + * USB_CHG_STATE_SECONDARY_DONE Secondary detection is completed (Detects + * between DCP and CDP). + * USB_CHG_STATE_DETECTED USB charger type is determined. + * + */ +enum usb_chg_state { + USB_CHG_STATE_UNDEFINED = 0, + USB_CHG_STATE_WAIT_FOR_DCD, + USB_CHG_STATE_DCD_DONE, + USB_CHG_STATE_PRIMARY_DONE, + USB_CHG_STATE_SECONDARY_DONE, + USB_CHG_STATE_DETECTED, +}; + +/** + * USB charger types + * + * USB_INVALID_CHARGER Invalid USB charger. + * USB_SDP_CHARGER Standard downstream port. Refers to a downstream port + * on USB2.0 compliant host/hub. + * USB_DCP_CHARGER Dedicated charger port (AC charger/ Wall charger). + * USB_CDP_CHARGER Charging downstream port. Enumeration can happen and + * IDEV_CHG_MAX can be drawn irrespective of USB state. + * + */ +enum usb_chg_type { + USB_INVALID_CHARGER = 0, + USB_SDP_CHARGER, + USB_DCP_CHARGER, + USB_CDP_CHARGER, +}; + +/** + * struct msm_otg_platform_data - platform device data + * for msm_otg driver. + * @phy_init_seq: PHY configuration sequence values. Value of -1 is reserved as + * "do not overwrite default vaule at this address". + * @phy_init_sz: PHY configuration sequence size. + * @vbus_power: VBUS power on/off routine. + * @power_budget: VBUS power budget in mA (0 will be treated as 500mA). + * @mode: Supported mode (OTG/peripheral/host). + * @otg_control: OTG switch controlled by user/Id pin + */ +struct msm_otg_platform_data { + int *phy_init_seq; + int phy_init_sz; + void (*vbus_power)(bool on); + unsigned power_budget; + enum usb_dr_mode mode; + enum otg_control_type otg_control; + enum msm_usb_phy_type phy_type; + void (*setup_gpio)(enum usb_otg_state state); +}; + +/** + * struct msm_usb_cable - structure for exteternal connector cable + * state tracking + * @nb: hold event notification callback + * @conn: used for notification registration + */ +struct msm_usb_cable { + struct notifier_block nb; + struct extcon_dev *extcon; +}; + +/** + * struct msm_otg: OTG driver data. Shared by HCD and DCD. + * @otg: USB OTG Transceiver structure. + * @pdata: otg device platform data. + * @irq: IRQ number assigned for HSUSB controller. + * @clk: clock struct of usb_hs_clk. + * @pclk: clock struct of usb_hs_pclk. + * @core_clk: clock struct of usb_hs_core_clk. + * @regs: ioremapped register base address. + * @inputs: OTG state machine inputs(Id, SessValid etc). + * @sm_work: OTG state machine work. + * @in_lpm: indicates low power mode (LPM) state. + * @async_int: Async interrupt arrived. + * @cur_power: The amount of mA available from downstream port. + * @chg_work: Charger detection work. + * @chg_state: The state of charger detection process. + * @chg_type: The type of charger attached. + * @dcd_retires: The retry count used to track Data contact + * detection process. + * @manual_pullup: true if VBUS is not routed to USB controller/phy + * and controller driver therefore enables pull-up explicitly before + * starting controller using usbcmd run/stop bit. + * @vbus: VBUS signal state trakining, using extcon framework + * @id: ID signal state trakining, using extcon framework + * @switch_gpio: Descriptor for GPIO used to control external Dual + * SPDT USB Switch. + * @reboot: Used to inform the driver to route USB D+/D- line to Device + * connector + */ +struct msm_otg { + struct usb_phy phy; + struct msm_otg_platform_data *pdata; + int irq; + struct clk *clk; + struct clk *pclk; + struct clk *core_clk; + void __iomem *regs; +#define ID 0 +#define B_SESS_VLD 1 + unsigned long inputs; + struct work_struct sm_work; + atomic_t in_lpm; + int async_int; + unsigned cur_power; + int phy_number; + struct delayed_work chg_work; + enum usb_chg_state chg_state; + enum usb_chg_type chg_type; + u8 dcd_retries; + struct regulator *v3p3; + struct regulator *v1p8; + struct regulator *vddcx; + + struct reset_control *phy_rst; + struct reset_control *link_rst; + int vdd_levels[3]; + + bool manual_pullup; + + struct msm_usb_cable vbus; + struct msm_usb_cable id; + + struct gpio_desc *switch_gpio; + struct notifier_block reboot; +}; + #define MSM_USB_BASE (motg->regs) #define DRIVER_NAME "msm_otg" diff --git a/include/linux/usb/msm_hsusb.h b/include/linux/usb/msm_hsusb.h deleted file mode 100644 index 8c8f6854c993..000000000000 --- a/include/linux/usb/msm_hsusb.h +++ /dev/null @@ -1,200 +0,0 @@ -/* linux/include/asm-arm/arch-msm/hsusb.h - * - * Copyright (C) 2008 Google, Inc. - * Author: Brian Swetland - * Copyright (c) 2009-2011, Code Aurora Forum. All rights reserved. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * 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 __ASM_ARCH_MSM_HSUSB_H -#define __ASM_ARCH_MSM_HSUSB_H - -#include -#include -#include -#include - -/** - * OTG control - * - * OTG_NO_CONTROL Id/VBUS notifications not required. Useful in host - * only configuration. - * OTG_PHY_CONTROL Id/VBUS notifications comes form USB PHY. - * OTG_PMIC_CONTROL Id/VBUS notifications comes from PMIC hardware. - * OTG_USER_CONTROL Id/VBUS notifcations comes from User via sysfs. - * - */ -enum otg_control_type { - OTG_NO_CONTROL = 0, - OTG_PHY_CONTROL, - OTG_PMIC_CONTROL, - OTG_USER_CONTROL, -}; - -/** - * PHY used in - * - * INVALID_PHY Unsupported PHY - * CI_45NM_INTEGRATED_PHY Chipidea 45nm integrated PHY - * SNPS_28NM_INTEGRATED_PHY Synopsis 28nm integrated PHY - * - */ -enum msm_usb_phy_type { - INVALID_PHY = 0, - CI_45NM_INTEGRATED_PHY, - SNPS_28NM_INTEGRATED_PHY, -}; - -#define IDEV_CHG_MAX 1500 -#define IUNIT 100 - -/** - * Different states involved in USB charger detection. - * - * USB_CHG_STATE_UNDEFINED USB charger is not connected or detection - * process is not yet started. - * USB_CHG_STATE_WAIT_FOR_DCD Waiting for Data pins contact. - * USB_CHG_STATE_DCD_DONE Data pin contact is detected. - * USB_CHG_STATE_PRIMARY_DONE Primary detection is completed (Detects - * between SDP and DCP/CDP). - * USB_CHG_STATE_SECONDARY_DONE Secondary detection is completed (Detects - * between DCP and CDP). - * USB_CHG_STATE_DETECTED USB charger type is determined. - * - */ -enum usb_chg_state { - USB_CHG_STATE_UNDEFINED = 0, - USB_CHG_STATE_WAIT_FOR_DCD, - USB_CHG_STATE_DCD_DONE, - USB_CHG_STATE_PRIMARY_DONE, - USB_CHG_STATE_SECONDARY_DONE, - USB_CHG_STATE_DETECTED, -}; - -/** - * USB charger types - * - * USB_INVALID_CHARGER Invalid USB charger. - * USB_SDP_CHARGER Standard downstream port. Refers to a downstream port - * on USB2.0 compliant host/hub. - * USB_DCP_CHARGER Dedicated charger port (AC charger/ Wall charger). - * USB_CDP_CHARGER Charging downstream port. Enumeration can happen and - * IDEV_CHG_MAX can be drawn irrespective of USB state. - * - */ -enum usb_chg_type { - USB_INVALID_CHARGER = 0, - USB_SDP_CHARGER, - USB_DCP_CHARGER, - USB_CDP_CHARGER, -}; - -/** - * struct msm_otg_platform_data - platform device data - * for msm_otg driver. - * @phy_init_seq: PHY configuration sequence values. Value of -1 is reserved as - * "do not overwrite default vaule at this address". - * @phy_init_sz: PHY configuration sequence size. - * @vbus_power: VBUS power on/off routine. - * @power_budget: VBUS power budget in mA (0 will be treated as 500mA). - * @mode: Supported mode (OTG/peripheral/host). - * @otg_control: OTG switch controlled by user/Id pin - */ -struct msm_otg_platform_data { - int *phy_init_seq; - int phy_init_sz; - void (*vbus_power)(bool on); - unsigned power_budget; - enum usb_dr_mode mode; - enum otg_control_type otg_control; - enum msm_usb_phy_type phy_type; - void (*setup_gpio)(enum usb_otg_state state); -}; - -/** - * struct msm_usb_cable - structure for exteternal connector cable - * state tracking - * @nb: hold event notification callback - * @conn: used for notification registration - */ -struct msm_usb_cable { - struct notifier_block nb; - struct extcon_dev *extcon; -}; - -/** - * struct msm_otg: OTG driver data. Shared by HCD and DCD. - * @otg: USB OTG Transceiver structure. - * @pdata: otg device platform data. - * @irq: IRQ number assigned for HSUSB controller. - * @clk: clock struct of usb_hs_clk. - * @pclk: clock struct of usb_hs_pclk. - * @core_clk: clock struct of usb_hs_core_clk. - * @regs: ioremapped register base address. - * @inputs: OTG state machine inputs(Id, SessValid etc). - * @sm_work: OTG state machine work. - * @in_lpm: indicates low power mode (LPM) state. - * @async_int: Async interrupt arrived. - * @cur_power: The amount of mA available from downstream port. - * @chg_work: Charger detection work. - * @chg_state: The state of charger detection process. - * @chg_type: The type of charger attached. - * @dcd_retires: The retry count used to track Data contact - * detection process. - * @manual_pullup: true if VBUS is not routed to USB controller/phy - * and controller driver therefore enables pull-up explicitly before - * starting controller using usbcmd run/stop bit. - * @vbus: VBUS signal state trakining, using extcon framework - * @id: ID signal state trakining, using extcon framework - * @switch_gpio: Descriptor for GPIO used to control external Dual - * SPDT USB Switch. - * @reboot: Used to inform the driver to route USB D+/D- line to Device - * connector - */ -struct msm_otg { - struct usb_phy phy; - struct msm_otg_platform_data *pdata; - int irq; - struct clk *clk; - struct clk *pclk; - struct clk *core_clk; - void __iomem *regs; -#define ID 0 -#define B_SESS_VLD 1 - unsigned long inputs; - struct work_struct sm_work; - atomic_t in_lpm; - int async_int; - unsigned cur_power; - int phy_number; - struct delayed_work chg_work; - enum usb_chg_state chg_state; - enum usb_chg_type chg_type; - u8 dcd_retries; - struct regulator *v3p3; - struct regulator *v1p8; - struct regulator *vddcx; - - struct reset_control *phy_rst; - struct reset_control *link_rst; - int vdd_levels[3]; - - bool manual_pullup; - - struct msm_usb_cable vbus; - struct msm_usb_cable id; - - struct gpio_desc *switch_gpio; - struct notifier_block reboot; -}; - -#endif -- cgit v1.2.3 From a6c50912508d80164a5e607993b617be85a46d73 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Thu, 2 Jun 2016 12:05:12 +0100 Subject: nvmem: Declare nvmem_cell_read() consistently nvmem_cell_read() is declared as void * if CONFIG_NVMEM is enabled, and as char * otherwise. This can result in a build warning if CONFIG_NVMEM is not enabled and a caller asigns the result to a type other than char * without using a typecast. Use a consistent declaration to avoid the problem. Fixes: e2a5402ec7c6 ("nvmem: Add nvmem_device based consumer apis.") Cc: Srinivas Kandagatla Signed-off-by: Guenter Roeck Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 9bb77d3ed6e0..c2256d746543 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -74,7 +74,7 @@ static inline void nvmem_cell_put(struct nvmem_cell *cell) { } -static inline char *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) +static inline void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) { return ERR_PTR(-ENOSYS); } -- cgit v1.2.3 From 1b0ec88ac1cb0413a717bc3cefea72d6f2533672 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:23 +0200 Subject: vt: remove lines parameter from scrollback It is always called with 0, so remove the parameter and pass the default down to scrolldelta without checking. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/keyboard.c | 2 +- drivers/tty/vt/vt.c | 6 ++---- include/linux/vt_kern.h | 2 +- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c index f973bfce5d08..cd08c103eb47 100644 --- a/drivers/tty/vt/keyboard.c +++ b/drivers/tty/vt/keyboard.c @@ -579,7 +579,7 @@ static void fn_scroll_forw(struct vc_data *vc) static void fn_scroll_back(struct vc_data *vc) { - scrollback(vc, 0); + scrollback(vc); } static void fn_show_mem(struct vc_data *vc) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index dc125322f48f..abc79ae19079 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1102,11 +1102,9 @@ static void gotoxay(struct vc_data *vc, int new_x, int new_y) gotoxy(vc, new_x, vc->vc_decom ? (vc->vc_top + new_y) : new_y); } -void scrollback(struct vc_data *vc, int lines) +void scrollback(struct vc_data *vc) { - if (!lines) - lines = vc->vc_rows / 2; - scrolldelta(-lines); + scrolldelta(-(vc->vc_rows / 2)); } void scrollfront(struct vc_data *vc, int lines) diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 8d7634247fb4..160f81fe3eb8 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -45,7 +45,7 @@ void poke_blanked_console(void); int con_font_op(struct vc_data *vc, struct console_font_op *op); int con_set_cmap(unsigned char __user *cmap); int con_get_cmap(unsigned char __user *cmap); -void scrollback(struct vc_data *vc, int lines); +void scrollback(struct vc_data *vc); void scrollfront(struct vc_data *vc, int lines); void clear_buffer_attributes(struct vc_data *vc); void update_region(struct vc_data *vc, unsigned long start, int count); -- cgit v1.2.3 From a4bedd019ec9690c1e5c7105509a2ef52c5ae3e0 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:24 +0200 Subject: vt: document vc_data by example All those members of vc_data are each explained in short. But it needs an example for one to understand the whole picture. So add an ascii art depicting the most important vc_data members. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/console_struct.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index e329ee2667e1..5fa605c93428 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -21,6 +21,38 @@ struct uni_pagedir; #define NPAR 16 +/* + * Example: vc_data of a console that was scrolled 3 lines down. + * + * Console buffer + * vc_screenbuf ---------> +----------------------+-. + * | initializing W | \ + * | initializing X | | + * | initializing Y | > scroll-back area + * | initializing Z | | + * | | / + * vc_visible_origin ---> ^+----------------------+-: + * (changes by scroll) || Welcome to linux | \ + * || | | + * vc_rows --->< | login: root | | visible on console + * || password: | > (vc_screenbuf_size is + * vc_origin -----------> || | | vc_size_row * vc_rows) + * (start when no scroll) || Last login: 12:28 | / + * v+----------------------+-: + * | Have a lot of fun... | \ + * vc_pos -----------------|--------v | > scroll-front area + * | ~ # cat_ | / + * vc_scr_end -----------> +----------------------+-: + * (vc_origin + | | \ EMPTY, to be filled by + * vc_screenbuf_size) | | / vc_video_erase_char + * +----------------------+-' + * <---- 2 * vc_cols -----> + * <---- vc_size_row -----> + * + * Note that every character in the console buffer is accompanied with an + * attribute in the buffer right after the character. This is not depicted + * in the figure. + */ struct vc_data { struct tty_port port; /* Upper level data */ -- cgit v1.2.3 From 97293de977365fe672daec2523e66ef457104921 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:26 +0200 Subject: tty: vt, consw->con_scrolldelta cleanup * allow NULL consw->con_scrolldelta (some consoles define an empty hook) * => remove empty hooks now * return value of consw->con_scrolldelta is never checked => make the function void * document consw->con_scrolldelta a bit Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: linux-usb@vger.kernel.org Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 2 +- drivers/usb/misc/sisusbvga/sisusb_con.c | 11 +++-------- drivers/video/console/dummycon.c | 1 - drivers/video/console/fbcon.c | 16 +++++++--------- drivers/video/console/mdacon.c | 6 ------ drivers/video/console/newport_con.c | 7 ------- drivers/video/console/sticon.c | 6 ------ drivers/video/console/vgacon.c | 13 +++++-------- include/linux/console.h | 8 +++++++- 9 files changed, 23 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index abc79ae19079..365a91d01a0e 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -2468,7 +2468,7 @@ static void console_callback(struct work_struct *ignored) if (scrollback_delta) { struct vc_data *vc = vc_cons[fg_console].d; clear_selection(); - if (vc->vc_mode == KD_TEXT) + if (vc->vc_mode == KD_TEXT && vc->vc_sw->con_scrolldelta) vc->vc_sw->con_scrolldelta(vc, scrollback_delta); scrollback_delta = 0; } diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index 0ebbf49cd649..a8244ebeb7a7 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -717,24 +717,22 @@ sisusbcon_blank(struct vc_data *c, int blank, int mode_switch) } /* interface routine */ -static int +static void sisusbcon_scrolldelta(struct vc_data *c, int lines) { struct sisusb_usb_data *sisusb; int margin = c->vc_size_row * 4; int ul, we, p, st; - /* The return value does not seem to be used */ - sisusb = sisusb_get_sisusb_lock_and_check(c->vc_num); if (!sisusb) - return 0; + return; /* sisusb->lock is down */ if (sisusb_is_inactive(c, sisusb)) { mutex_unlock(&sisusb->lock); - return 0; + return; } if (!lines) /* Turn scrollback off */ @@ -774,8 +772,6 @@ sisusbcon_scrolldelta(struct vc_data *c, int lines) sisusbcon_set_start_address(sisusb, c); mutex_unlock(&sisusb->lock); - - return 1; } /* Interface routine */ @@ -1433,7 +1429,6 @@ static const struct consw sisusb_dummy_con = { .con_font_default = SISUSBCONDUMMY, .con_font_copy = SISUSBCONDUMMY, .con_set_palette = SISUSBCONDUMMY, - .con_scrolldelta = SISUSBCONDUMMY, }; int diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index 0efc52f11ad0..9ce03b9aba88 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -72,6 +72,5 @@ const struct consw dummy_con = { .con_font_default = DUMMY, .con_font_copy = DUMMY, .con_set_palette = DUMMY, - .con_scrolldelta = DUMMY, }; EXPORT_SYMBOL_GPL(dummy_con); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index afd3301ac40c..eadc7bf62eb3 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -171,7 +171,6 @@ static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static int fbcon_set_palette(struct vc_data *vc, const unsigned char *table); -static int fbcon_scrolldelta(struct vc_data *vc, int lines); /* * Internal routines @@ -2765,7 +2764,7 @@ static void fbcon_invert_region(struct vc_data *vc, u16 * p, int cnt) } } -static int fbcon_scrolldelta(struct vc_data *vc, int lines) +static void fbcon_scrolldelta(struct vc_data *vc, int lines) { struct fb_info *info = registered_fb[con2fb_map[fg_console]]; struct fbcon_ops *ops = info->fbcon_par; @@ -2774,9 +2773,9 @@ static int fbcon_scrolldelta(struct vc_data *vc, int lines) if (softback_top) { if (vc->vc_num != fg_console) - return 0; + return; if (vc->vc_mode != KD_TEXT || !lines) - return 0; + return; if (logo_shown >= 0) { struct vc_data *conp2 = vc_cons[logo_shown].d; @@ -2809,11 +2808,11 @@ static int fbcon_scrolldelta(struct vc_data *vc, int lines) fbcon_cursor(vc, CM_ERASE | CM_SOFTBACK); fbcon_redraw_softback(vc, disp, lines); fbcon_cursor(vc, CM_DRAW | CM_SOFTBACK); - return 0; + return; } if (!scrollback_phys_max) - return -ENOSYS; + return; scrollback_old = scrollback_current; scrollback_current -= lines; @@ -2822,10 +2821,10 @@ static int fbcon_scrolldelta(struct vc_data *vc, int lines) else if (scrollback_current > scrollback_max) scrollback_current = scrollback_max; if (scrollback_current == scrollback_old) - return 0; + return; if (fbcon_is_inactive(vc, info)) - return 0; + return; fbcon_cursor(vc, CM_ERASE); @@ -2852,7 +2851,6 @@ static int fbcon_scrolldelta(struct vc_data *vc, int lines) if (!scrollback_current) fbcon_cursor(vc, CM_DRAW); - return 0; } static int fbcon_set_origin(struct vc_data *vc) diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index 8edc062536a8..234af26b4829 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -505,11 +505,6 @@ static int mdacon_blank(struct vc_data *c, int blank, int mode_switch) } } -static int mdacon_scrolldelta(struct vc_data *c, int lines) -{ - return 0; -} - static void mdacon_cursor(struct vc_data *c, int mode) { if (mode == CM_ERASE) { @@ -578,7 +573,6 @@ static const struct consw mda_con = { .con_switch = mdacon_switch, .con_blank = mdacon_blank, .con_set_palette = mdacon_set_palette, - .con_scrolldelta = mdacon_scrolldelta, .con_build_attr = mdacon_build_attr, .con_invert_region = mdacon_invert_region, }; diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 0553dfe684ef..eb3d4ce12cd5 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -579,12 +579,6 @@ static int newport_set_palette(struct vc_data *vc, const unsigned char *table) return -EINVAL; } -static int newport_scrolldelta(struct vc_data *vc, int lines) -{ - /* there is (nearly) no off-screen memory, so we can't scroll back */ - return 0; -} - static int newport_scroll(struct vc_data *vc, int t, int b, int dir, int lines) { @@ -735,7 +729,6 @@ const struct consw newport_con = { .con_font_set = newport_font_set, .con_font_default = newport_font_default, .con_set_palette = newport_set_palette, - .con_scrolldelta = newport_scrolldelta, .con_set_origin = DUMMY, .con_save_screen = DUMMY }; diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c index e440c2d9fe7c..20f6a2f5d4a7 100644 --- a/drivers/video/console/sticon.c +++ b/drivers/video/console/sticon.c @@ -256,11 +256,6 @@ static int sticon_blank(struct vc_data *c, int blank, int mode_switch) return 1; } -static int sticon_scrolldelta(struct vc_data *conp, int lines) -{ - return 0; -} - static u16 *sticon_screen_pos(struct vc_data *conp, int offset) { int line; @@ -359,7 +354,6 @@ static const struct consw sti_con = { .con_switch = sticon_switch, .con_blank = sticon_blank, .con_set_palette = sticon_set_palette, - .con_scrolldelta = sticon_scrolldelta, .con_set_origin = sticon_set_origin, .con_save_screen = sticon_save_screen, .con_build_attr = sticon_build_attr, diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index 8bf911002cba..f447d6916991 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -80,7 +80,7 @@ static void vgacon_deinit(struct vc_data *c); static void vgacon_cursor(struct vc_data *c, int mode); static int vgacon_switch(struct vc_data *c); static int vgacon_blank(struct vc_data *c, int blank, int mode_switch); -static int vgacon_scrolldelta(struct vc_data *c, int lines); +static void vgacon_scrolldelta(struct vc_data *c, int lines); static int vgacon_set_origin(struct vc_data *c); static void vgacon_save_screen(struct vc_data *c); static int vgacon_scroll(struct vc_data *c, int t, int b, int dir, @@ -248,18 +248,18 @@ static void vgacon_restore_screen(struct vc_data *c) } } -static int vgacon_scrolldelta(struct vc_data *c, int lines) +static void vgacon_scrolldelta(struct vc_data *c, int lines) { int start, end, count, soff; if (!lines) { c->vc_visible_origin = c->vc_origin; vga_set_mem_top(c); - return 1; + return; } if (!vgacon_scrollback) - return 1; + return; if (!vgacon_scrollback_save) { vgacon_cursor(c, CM_ERASE); @@ -320,8 +320,6 @@ static int vgacon_scrolldelta(struct vc_data *c, int lines) scr_memcpyw(d, s, diff * c->vc_size_row); } else vgacon_cursor(c, CM_MOVE); - - return 1; } #else #define vgacon_scrollback_startup(...) do { } while (0) @@ -334,7 +332,7 @@ static void vgacon_restore_screen(struct vc_data *c) vgacon_scrolldelta(c, 0); } -static int vgacon_scrolldelta(struct vc_data *c, int lines) +static void vgacon_scrolldelta(struct vc_data *c, int lines) { if (!lines) /* Turn scrollback off */ c->vc_visible_origin = c->vc_origin; @@ -362,7 +360,6 @@ static int vgacon_scrolldelta(struct vc_data *c, int lines) c->vc_visible_origin = vga_vram_base + (p + ul) % we; } vga_set_mem_top(c); - return 1; } #endif /* CONFIG_VGACON_SOFT_SCROLLBACK */ diff --git a/include/linux/console.h b/include/linux/console.h index 98c8615dc300..d175de8d7006 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -28,6 +28,12 @@ struct tty_struct; #define VT100ID "\033[?1;2c" #define VT102ID "\033[?6c" +/** + * struct consw - callbacks for consoles + * + * @con_scrolldelta: the contents of the console should be scrolled by @lines. + * Invoked by user. (optional) + */ struct consw { struct module *owner; const char *(*con_startup)(void); @@ -48,7 +54,7 @@ struct consw { int (*con_resize)(struct vc_data *, unsigned int, unsigned int, unsigned int); int (*con_set_palette)(struct vc_data *, const unsigned char *); - int (*con_scrolldelta)(struct vc_data *, int); + void (*con_scrolldelta)(struct vc_data *, int lines); int (*con_set_origin)(struct vc_data *); void (*con_save_screen)(struct vc_data *); u8 (*con_build_attr)(struct vc_data *, u8, u8, u8, u8, u8, u8); -- cgit v1.2.3 From 709280da6238629c3b488b7be87c6d9185f4d03e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:27 +0200 Subject: tty: vt, consw->con_set_palette cleanup * allow NULL consw->con_set_palette (some consoles define an empty hook) * => remove empty hooks now * return value of consw->con_set_palette is never checked => make the function void * document consw->con_set_palette a bit Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: linux-usb@vger.kernel.org Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 2 +- drivers/usb/misc/sisusbvga/sisusb_con.c | 11 ++++------- drivers/video/console/dummycon.c | 1 - drivers/video/console/fbcon.c | 10 +++++----- drivers/video/console/mdacon.c | 6 ------ drivers/video/console/newport_con.c | 6 ------ drivers/video/console/sticon.c | 6 ------ drivers/video/console/vgacon.c | 7 ++----- include/linux/console.h | 4 +++- 9 files changed, 15 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 365a91d01a0e..d5d906051613 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3978,7 +3978,7 @@ static void set_palette(struct vc_data *vc) { WARN_CONSOLE_UNLOCKED(); - if (vc->vc_mode != KD_GRAPHICS) + if (vc->vc_mode != KD_GRAPHICS && vc->vc_sw->con_set_palette) vc->vc_sw->con_set_palette(vc, color_table); } diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index a8244ebeb7a7..4112835f4aed 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -595,7 +595,7 @@ sisusbcon_save_screen(struct vc_data *c) } /* interface routine */ -static int +static void sisusbcon_set_palette(struct vc_data *c, const unsigned char *table) { struct sisusb_usb_data *sisusb; @@ -604,17 +604,17 @@ sisusbcon_set_palette(struct vc_data *c, const unsigned char *table) /* Return value not used by vt */ if (!CON_IS_VISIBLE(c)) - return -EINVAL; + return; sisusb = sisusb_get_sisusb_lock_and_check(c->vc_num); if (!sisusb) - return -EINVAL; + return; /* sisusb->lock is down */ if (sisusb_is_inactive(c, sisusb)) { mutex_unlock(&sisusb->lock); - return -EINVAL; + return; } for (i = j = 0; i < 16; i++) { @@ -629,8 +629,6 @@ sisusbcon_set_palette(struct vc_data *c, const unsigned char *table) } mutex_unlock(&sisusb->lock); - - return 0; } /* interface routine */ @@ -1428,7 +1426,6 @@ static const struct consw sisusb_dummy_con = { .con_font_get = SISUSBCONDUMMY, .con_font_default = SISUSBCONDUMMY, .con_font_copy = SISUSBCONDUMMY, - .con_set_palette = SISUSBCONDUMMY, }; int diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index 9ce03b9aba88..0ef544ef5634 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -71,6 +71,5 @@ const struct consw dummy_con = { .con_font_get = DUMMY, .con_font_default = DUMMY, .con_font_copy = DUMMY, - .con_set_palette = DUMMY, }; EXPORT_SYMBOL_GPL(dummy_con); diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index eadc7bf62eb3..9359b06377cf 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -170,7 +170,7 @@ static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, int height, int width); static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); -static int fbcon_set_palette(struct vc_data *vc, const unsigned char *table); +static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines @@ -2651,17 +2651,17 @@ static struct fb_cmap palette_cmap = { 0, 16, palette_red, palette_green, palette_blue, NULL }; -static int fbcon_set_palette(struct vc_data *vc, const unsigned char *table) +static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table) { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; int i, j, k, depth; u8 val; if (fbcon_is_inactive(vc, info)) - return -EINVAL; + return; if (!CON_IS_VISIBLE(vc)) - return 0; + return; depth = fb_get_color_depth(&info->var, &info->fix); if (depth > 3) { @@ -2683,7 +2683,7 @@ static int fbcon_set_palette(struct vc_data *vc, const unsigned char *table) } else fb_copy_cmap(fb_default_cmap(1 << depth), &palette_cmap); - return fb_set_cmap(&palette_cmap, info); + fb_set_cmap(&palette_cmap, info); } static u16 *fbcon_screen_pos(struct vc_data *vc, int offset) diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index 234af26b4829..1fe5245eb6dd 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -481,11 +481,6 @@ static int mdacon_switch(struct vc_data *c) return 1; /* redrawing needed */ } -static int mdacon_set_palette(struct vc_data *c, const unsigned char *table) -{ - return -EINVAL; -} - static int mdacon_blank(struct vc_data *c, int blank, int mode_switch) { if (mda_type == TYPE_MDA) { @@ -572,7 +567,6 @@ static const struct consw mda_con = { .con_bmove = mdacon_bmove, .con_switch = mdacon_switch, .con_blank = mdacon_blank, - .con_set_palette = mdacon_set_palette, .con_build_attr = mdacon_build_attr, .con_invert_region = mdacon_invert_region, }; diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index eb3d4ce12cd5..a436930f9e5d 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -574,11 +574,6 @@ static int newport_font_set(struct vc_data *vc, struct console_font *font, unsig return newport_set_font(vc->vc_num, font); } -static int newport_set_palette(struct vc_data *vc, const unsigned char *table) -{ - return -EINVAL; -} - static int newport_scroll(struct vc_data *vc, int t, int b, int dir, int lines) { @@ -728,7 +723,6 @@ const struct consw newport_con = { .con_blank = newport_blank, .con_font_set = newport_font_set, .con_font_default = newport_font_default, - .con_set_palette = newport_set_palette, .con_set_origin = DUMMY, .con_save_screen = DUMMY }; diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c index 20f6a2f5d4a7..fe7c4dbb676e 100644 --- a/drivers/video/console/sticon.c +++ b/drivers/video/console/sticon.c @@ -79,11 +79,6 @@ static const char *sticon_startup(void) return "STI console"; } -static int sticon_set_palette(struct vc_data *c, const unsigned char *table) -{ - return -EINVAL; -} - static void sticon_putc(struct vc_data *conp, int c, int ypos, int xpos) { int redraw_cursor = 0; @@ -353,7 +348,6 @@ static const struct consw sti_con = { .con_bmove = sticon_bmove, .con_switch = sticon_switch, .con_blank = sticon_blank, - .con_set_palette = sticon_set_palette, .con_set_origin = sticon_set_origin, .con_save_screen = sticon_save_screen, .con_build_attr = sticon_build_attr, diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index f447d6916991..aaae9bd23900 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -856,16 +856,13 @@ static void vga_set_palette(struct vc_data *vc, const unsigned char *table) } } -static int vgacon_set_palette(struct vc_data *vc, const unsigned char *table) +static void vgacon_set_palette(struct vc_data *vc, const unsigned char *table) { #ifdef CAN_LOAD_PALETTE if (vga_video_type != VIDEO_TYPE_VGAC || vga_palette_blanked || !CON_IS_VISIBLE(vc)) - return -EINVAL; + return; vga_set_palette(vc, table); - return 0; -#else - return -EINVAL; #endif } diff --git a/include/linux/console.h b/include/linux/console.h index d175de8d7006..382a527104c4 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -31,6 +31,7 @@ struct tty_struct; /** * struct consw - callbacks for consoles * + * @con_set_palette: sets the palette of the console to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) */ @@ -53,7 +54,8 @@ struct consw { int (*con_font_copy)(struct vc_data *, int); int (*con_resize)(struct vc_data *, unsigned int, unsigned int, unsigned int); - int (*con_set_palette)(struct vc_data *, const unsigned char *); + void (*con_set_palette)(struct vc_data *, + const unsigned char *table); void (*con_scrolldelta)(struct vc_data *, int lines); int (*con_set_origin)(struct vc_data *); void (*con_save_screen)(struct vc_data *); -- cgit v1.2.3 From 52ad1f38b4f6e2f2133668247036ad64ef7ae18a Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:28 +0200 Subject: tty: vt, remove consw->con_bmove It is never called since commit 81732c3b2fede (tty vt: Fix line garbage in virtual console on command line edition) in 3.7. So remove all the callbacks. Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: linux-usb@vger.kernel.org Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: linux-parisc@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/sisusbvga/sisusb_con.c | 35 --------------------------------- drivers/video/console/dummycon.c | 1 - drivers/video/console/fbcon.c | 1 - drivers/video/console/mdacon.c | 33 ------------------------------- drivers/video/console/newport_con.c | 29 --------------------------- drivers/video/console/sticon.c | 17 ---------------- drivers/video/console/vgacon.c | 1 - include/linux/console.h | 1 - 8 files changed, 118 deletions(-) (limited to 'include') diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index 4112835f4aed..52a6da991165 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -477,39 +477,6 @@ sisusbcon_clear(struct vc_data *c, int y, int x, int height, int width) mutex_unlock(&sisusb->lock); } -/* Interface routine */ -static void -sisusbcon_bmove(struct vc_data *c, int sy, int sx, - int dy, int dx, int height, int width) -{ - struct sisusb_usb_data *sisusb; - int cols, length; - - if (width <= 0 || height <= 0) - return; - - sisusb = sisusb_get_sisusb_lock_and_check(c->vc_num); - if (!sisusb) - return; - - /* sisusb->lock is down */ - - cols = sisusb->sisusb_num_columns; - - if (sisusb_is_inactive(c, sisusb)) { - mutex_unlock(&sisusb->lock); - return; - } - - length = ((height * cols) - dx - (cols - width - dx)) * 2; - - - sisusb_copy_memory(sisusb, (unsigned char *)SISUSB_VADDR(dx, dy), - (long)SISUSB_HADDR(dx, dy), length); - - mutex_unlock(&sisusb->lock); -} - /* interface routine */ static int sisusbcon_switch(struct vc_data *c) @@ -1371,7 +1338,6 @@ static const struct consw sisusb_con = { .con_putcs = sisusbcon_putcs, .con_cursor = sisusbcon_cursor, .con_scroll = sisusbcon_scroll, - .con_bmove = sisusbcon_bmove, .con_switch = sisusbcon_switch, .con_blank = sisusbcon_blank, .con_font_set = sisusbcon_font_set, @@ -1419,7 +1385,6 @@ static const struct consw sisusb_dummy_con = { .con_putcs = SISUSBCONDUMMY, .con_cursor = SISUSBCONDUMMY, .con_scroll = SISUSBCONDUMMY, - .con_bmove = SISUSBCONDUMMY, .con_switch = SISUSBCONDUMMY, .con_blank = SISUSBCONDUMMY, .con_font_set = SISUSBCONDUMMY, diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index 0ef544ef5634..9269d5685239 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -64,7 +64,6 @@ const struct consw dummy_con = { .con_putcs = DUMMY, .con_cursor = DUMMY, .con_scroll = DUMMY, - .con_bmove = DUMMY, .con_switch = DUMMY, .con_blank = DUMMY, .con_font_set = DUMMY, diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 9359b06377cf..eef8a8b7274f 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -3334,7 +3334,6 @@ static const struct consw fb_con = { .con_putcs = fbcon_putcs, .con_cursor = fbcon_cursor, .con_scroll = fbcon_scroll, - .con_bmove = fbcon_bmove, .con_switch = fbcon_switch, .con_blank = fbcon_blank, .con_font_set = fbcon_set_font, diff --git a/drivers/video/console/mdacon.c b/drivers/video/console/mdacon.c index 1fe5245eb6dd..bacbb044d77c 100644 --- a/drivers/video/console/mdacon.c +++ b/drivers/video/console/mdacon.c @@ -444,38 +444,6 @@ static void mdacon_clear(struct vc_data *c, int y, int x, } } -static void mdacon_bmove(struct vc_data *c, int sy, int sx, - int dy, int dx, int height, int width) -{ - u16 *src, *dest; - - if (width <= 0 || height <= 0) - return; - - if (sx==0 && dx==0 && width==mda_num_columns) { - scr_memmovew(MDA_ADDR(0,dy), MDA_ADDR(0,sy), height*width*2); - - } else if (dy < sy || (dy == sy && dx < sx)) { - src = MDA_ADDR(sx, sy); - dest = MDA_ADDR(dx, dy); - - for (; height > 0; height--) { - scr_memmovew(dest, src, width*2); - src += mda_num_columns; - dest += mda_num_columns; - } - } else { - src = MDA_ADDR(sx, sy+height-1); - dest = MDA_ADDR(dx, dy+height-1); - - for (; height > 0; height--) { - scr_memmovew(dest, src, width*2); - src -= mda_num_columns; - dest -= mda_num_columns; - } - } -} - static int mdacon_switch(struct vc_data *c) { return 1; /* redrawing needed */ @@ -564,7 +532,6 @@ static const struct consw mda_con = { .con_putcs = mdacon_putcs, .con_cursor = mdacon_cursor, .con_scroll = mdacon_scroll, - .con_bmove = mdacon_bmove, .con_switch = mdacon_switch, .con_blank = mdacon_blank, .con_build_attr = mdacon_build_attr, diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index a436930f9e5d..e3b9521e4ec3 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -673,34 +673,6 @@ static int newport_scroll(struct vc_data *vc, int t, int b, int dir, return 1; } -static void newport_bmove(struct vc_data *vc, int sy, int sx, int dy, - int dx, int h, int w) -{ - short xs, ys, xe, ye, xoffs, yoffs; - - xs = sx << 3; - xe = ((sx + w) << 3) - 1; - /* - * as bmove is only used to move stuff around in the same line - * (h == 1), we don't care about wrap arounds caused by topscan != 0 - */ - ys = ((sy << 4) + topscan) & 0x3ff; - ye = (((sy + h) << 4) - 1 + topscan) & 0x3ff; - xoffs = (dx - sx) << 3; - yoffs = (dy - sy) << 4; - if (xoffs > 0) { - /* move to the right, exchange starting points */ - swap(xe, xs); - } - newport_wait(npregs); - npregs->set.drawmode0 = (NPORT_DMODE0_S2S | NPORT_DMODE0_BLOCK | - NPORT_DMODE0_DOSETUP | NPORT_DMODE0_STOPX - | NPORT_DMODE0_STOPY); - npregs->set.xystarti = (xs << 16) | ys; - npregs->set.xyendi = (xe << 16) | ye; - npregs->go.xymove = (xoffs << 16) | yoffs; -} - static int newport_dummy(struct vc_data *c) { return 0; @@ -718,7 +690,6 @@ const struct consw newport_con = { .con_putcs = newport_putcs, .con_cursor = newport_cursor, .con_scroll = newport_scroll, - .con_bmove = newport_bmove, .con_switch = newport_switch, .con_blank = newport_blank, .con_font_set = newport_font_set, diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c index fe7c4dbb676e..3a10ac19598f 100644 --- a/drivers/video/console/sticon.c +++ b/drivers/video/console/sticon.c @@ -177,22 +177,6 @@ static int sticon_scroll(struct vc_data *conp, int t, int b, int dir, int count) return 0; } -static void sticon_bmove(struct vc_data *conp, int sy, int sx, - int dy, int dx, int height, int width) -{ - if (!width || !height) - return; -#if 0 - if (((sy <= p->cursor_y) && (p->cursor_y < sy+height) && - (sx <= p->cursor_x) && (p->cursor_x < sx+width)) || - ((dy <= p->cursor_y) && (p->cursor_y < dy+height) && - (dx <= p->cursor_x) && (p->cursor_x < dx+width))) - sticon_cursor(p, CM_ERASE /*|CM_SOFTBACK*/); -#endif - - sti_bmove(sticon_sti, sy, sx, dy, dx, height, width); -} - static void sticon_init(struct vc_data *c, int init) { struct sti_struct *sti = sticon_sti; @@ -345,7 +329,6 @@ static const struct consw sti_con = { .con_putcs = sticon_putcs, .con_cursor = sticon_cursor, .con_scroll = sticon_scroll, - .con_bmove = sticon_bmove, .con_switch = sticon_switch, .con_blank = sticon_blank, .con_set_origin = sticon_set_origin, diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index aaae9bd23900..e280b3ceebd9 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1421,7 +1421,6 @@ const struct consw vga_con = { .con_putcs = DUMMY, .con_cursor = vgacon_cursor, .con_scroll = vgacon_scroll, - .con_bmove = DUMMY, .con_switch = vgacon_switch, .con_blank = vgacon_blank, .con_font_set = vgacon_font_set, diff --git a/include/linux/console.h b/include/linux/console.h index 382a527104c4..d530c4627e54 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -45,7 +45,6 @@ struct consw { void (*con_putcs)(struct vc_data *, const unsigned short *, int, int, int); void (*con_cursor)(struct vc_data *, int); int (*con_scroll)(struct vc_data *, int, int, int, int); - void (*con_bmove)(struct vc_data *, int, int, int, int, int, int); int (*con_switch)(struct vc_data *); int (*con_blank)(struct vc_data *, int, int); int (*con_font_set)(struct vc_data *, struct console_font *, unsigned); -- cgit v1.2.3 From 6ca8dfd78187d8238abc5b2996848a0c8f07948d Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:35 +0200 Subject: tty: vt, convert more macros to functions Namely convert: * IS_FG -> con_is_fg * DO_UPDATE -> con_should_update * CON_IS_VISIBLE -> con_is_visible DO_UPDATE was a weird name for a yes/no answer, so the new name is con_should_update. Signed-off-by: Jiri Slaby Cc: Thomas Winischhofer Cc: Jean-Christophe Plagniol-Villard Cc: linux-usb@vger.kernel.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 62 ++++++++++++++++++--------------- drivers/usb/misc/sisusbvga/sisusb_con.c | 4 +-- drivers/video/console/fbcon.c | 26 +++++++------- drivers/video/console/vgacon.c | 8 ++--- include/linux/console_struct.h | 5 ++- 5 files changed, 57 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 8ceabfd20561..26de5c0fc056 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -277,8 +277,15 @@ static void notify_update(struct vc_data *vc) * Low-Level Functions */ -#define IS_FG(vc) ((vc)->vc_num == fg_console) -#define DO_UPDATE(vc) (CON_IS_VISIBLE(vc) && !console_blanked) +static inline bool con_is_fg(const struct vc_data *vc) +{ + return vc->vc_num == fg_console; +} + +static inline bool con_should_update(const struct vc_data *vc) +{ + return con_is_visible(vc) && !console_blanked; +} static inline unsigned short *screenpos(struct vc_data *vc, int offset, int viewed) { @@ -316,7 +323,7 @@ static void scrup(struct vc_data *vc, unsigned int t, unsigned int b, int nr) nr = b - t - 1; if (b > vc->vc_rows || t >= b || nr < 1) return; - if (CON_IS_VISIBLE(vc) && vc->vc_sw->con_scroll(vc, t, b, SM_UP, nr)) + if (con_is_visible(vc) && vc->vc_sw->con_scroll(vc, t, b, SM_UP, nr)) return; d = (unsigned short *)(vc->vc_origin + vc->vc_size_row * t); s = (unsigned short *)(vc->vc_origin + vc->vc_size_row * (t + nr)); @@ -334,7 +341,7 @@ static void scrdown(struct vc_data *vc, unsigned int t, unsigned int b, int nr) nr = b - t - 1; if (b > vc->vc_rows || t >= b || nr < 1) return; - if (CON_IS_VISIBLE(vc) && vc->vc_sw->con_scroll(vc, t, b, SM_DOWN, nr)) + if (con_is_visible(vc) && vc->vc_sw->con_scroll(vc, t, b, SM_DOWN, nr)) return; s = (unsigned short *)(vc->vc_origin + vc->vc_size_row * t); step = vc->vc_cols * nr; @@ -390,7 +397,7 @@ void update_region(struct vc_data *vc, unsigned long start, int count) { WARN_CONSOLE_UNLOCKED(); - if (DO_UPDATE(vc)) { + if (con_should_update(vc)) { hide_cursor(vc); do_update_region(vc, start, count); set_cursor(vc); @@ -490,7 +497,7 @@ void invert_screen(struct vc_data *vc, int offset, int count, int viewed) } } - if (DO_UPDATE(vc)) + if (con_should_update(vc)) do_update_region(vc, (unsigned long) p, count); notify_update(vc); } @@ -507,7 +514,7 @@ void complement_pos(struct vc_data *vc, int offset) if (old_offset != -1 && old_offset >= 0 && old_offset < vc->vc_screenbuf_size) { scr_writew(old, screenpos(vc, old_offset, 1)); - if (DO_UPDATE(vc)) + if (con_should_update(vc)) vc->vc_sw->con_putc(vc, old, oldy, oldx); notify_update(vc); } @@ -522,7 +529,7 @@ void complement_pos(struct vc_data *vc, int offset) old = scr_readw(p); new = old ^ vc->vc_complement_mask; scr_writew(new, p); - if (DO_UPDATE(vc)) { + if (con_should_update(vc)) { oldx = (offset >> 1) % vc->vc_cols; oldy = (offset >> 1) / vc->vc_cols; vc->vc_sw->con_putc(vc, new, oldy, oldx); @@ -538,7 +545,7 @@ static void insert_char(struct vc_data *vc, unsigned int nr) scr_memmovew(p + nr, p, (vc->vc_cols - vc->vc_x - nr) * 2); scr_memsetw(p, vc->vc_video_erase_char, nr * 2); vc->vc_need_wrap = 0; - if (DO_UPDATE(vc)) + if (con_should_update(vc)) do_update_region(vc, (unsigned long) p, vc->vc_cols - vc->vc_x); } @@ -551,7 +558,7 @@ static void delete_char(struct vc_data *vc, unsigned int nr) scr_memsetw(p + vc->vc_cols - vc->vc_x - nr, vc->vc_video_erase_char, nr * 2); vc->vc_need_wrap = 0; - if (DO_UPDATE(vc)) + if (con_should_update(vc)) do_update_region(vc, (unsigned long) p, vc->vc_cols - vc->vc_x); } @@ -571,7 +578,7 @@ static void add_softcursor(struct vc_data *vc) if ((type & 0x20) && ((softcursor_original & 0x7000) == (i & 0x7000))) i ^= 0x7000; if ((type & 0x40) && ((i & 0x700) == ((i & 0x7000) >> 4))) i ^= 0x0700; scr_writew(i, (u16 *) vc->vc_pos); - if (DO_UPDATE(vc)) + if (con_should_update(vc)) vc->vc_sw->con_putc(vc, i, vc->vc_y, vc->vc_x); } @@ -579,7 +586,7 @@ static void hide_softcursor(struct vc_data *vc) { if (softcursor_original != -1) { scr_writew(softcursor_original, (u16 *)vc->vc_pos); - if (DO_UPDATE(vc)) + if (con_should_update(vc)) vc->vc_sw->con_putc(vc, softcursor_original, vc->vc_y, vc->vc_x); softcursor_original = -1; @@ -596,8 +603,7 @@ static void hide_cursor(struct vc_data *vc) static void set_cursor(struct vc_data *vc) { - if (!IS_FG(vc) || console_blanked || - vc->vc_mode == KD_GRAPHICS) + if (!con_is_fg(vc) || console_blanked || vc->vc_mode == KD_GRAPHICS) return; if (vc->vc_deccm) { if (vc == sel_cons) @@ -613,7 +619,7 @@ static void set_origin(struct vc_data *vc) { WARN_CONSOLE_UNLOCKED(); - if (!CON_IS_VISIBLE(vc) || + if (!con_is_visible(vc) || !vc->vc_sw->con_set_origin || !vc->vc_sw->con_set_origin(vc)) vc->vc_origin = (unsigned long)vc->vc_screenbuf; @@ -661,12 +667,12 @@ void redraw_screen(struct vc_data *vc, int is_switch) struct vc_data *old_vc = vc_cons[fg_console].d; if (old_vc == vc) return; - if (!CON_IS_VISIBLE(vc)) + if (!con_is_visible(vc)) redraw = 1; *vc->vc_display_fg = vc; fg_console = vc->vc_num; hide_cursor(old_vc); - if (!CON_IS_VISIBLE(old_vc)) { + if (!con_is_visible(old_vc)) { save_screen(old_vc); set_origin(old_vc); } @@ -941,7 +947,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, tty_do_resize(tty, &ws); } - if (CON_IS_VISIBLE(vc)) + if (con_is_visible(vc)) update_screen(vc); vt_event_post(VT_EVENT_RESIZE, vc->vc_num, vc->vc_num); return err; @@ -1171,7 +1177,7 @@ static void csi_J(struct vc_data *vc, int vpar) scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char, vc->vc_screenbuf_size >> 1); set_origin(vc); - if (CON_IS_VISIBLE(vc)) + if (con_is_visible(vc)) update_screen(vc); /* fall through */ case 2: /* erase whole display */ @@ -1182,7 +1188,7 @@ static void csi_J(struct vc_data *vc, int vpar) return; } scr_memsetw(start, vc->vc_video_erase_char, 2 * count); - if (DO_UPDATE(vc)) + if (con_should_update(vc)) do_update_region(vc, (unsigned long) start, count); vc->vc_need_wrap = 0; } @@ -1210,7 +1216,7 @@ static void csi_K(struct vc_data *vc, int vpar) } scr_memsetw(start, vc->vc_video_erase_char, 2 * count); vc->vc_need_wrap = 0; - if (DO_UPDATE(vc)) + if (con_should_update(vc)) do_update_region(vc, (unsigned long) start, count); } @@ -1223,7 +1229,7 @@ static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar posi count = (vpar > vc->vc_cols - vc->vc_x) ? (vc->vc_cols - vc->vc_x) : vpar; scr_memsetw((unsigned short *)vc->vc_pos, vc->vc_video_erase_char, 2 * count); - if (DO_UPDATE(vc)) + if (con_should_update(vc)) vc->vc_sw->con_clear(vc, vc->vc_y, vc->vc_x, 1, count); vc->vc_need_wrap = 0; } @@ -2208,7 +2214,7 @@ static int do_con_write(struct tty_struct *tty, const unsigned char *buf, int co charmask = himask ? 0x1ff : 0xff; /* undraw cursor first */ - if (IS_FG(vc)) + if (con_is_fg(vc)) hide_cursor(vc); param.vc = vc; @@ -2380,7 +2386,7 @@ rescan_last_byte: ((vc_attr << 8) & ~himask) + ((tc & 0x100) ? himask : 0) + (tc & 0xff) : (vc_attr << 8) + tc, (u16 *) vc->vc_pos); - if (DO_UPDATE(vc) && draw_x < 0) { + if (con_should_update(vc) && draw_x < 0) { draw_x = vc->vc_x; draw_from = vc->vc_pos; } @@ -2564,7 +2570,7 @@ static void vt_console_print(struct console *co, const char *b, unsigned count) goto quit; /* undraw cursor first */ - if (IS_FG(vc)) + if (con_is_fg(vc)) hide_cursor(vc); start = (ushort *)vc->vc_pos; @@ -2575,7 +2581,7 @@ static void vt_console_print(struct console *co, const char *b, unsigned count) c = *b++; if (c == 10 || c == 13 || c == 8 || vc->vc_need_wrap) { if (cnt > 0) { - if (CON_IS_VISIBLE(vc)) + if (con_is_visible(vc)) vc->vc_sw->con_putcs(vc, start, cnt, vc->vc_y, vc->vc_x); vc->vc_x += cnt; if (vc->vc_need_wrap) @@ -2607,7 +2613,7 @@ static void vt_console_print(struct console *co, const char *b, unsigned count) myx++; } if (cnt > 0) { - if (CON_IS_VISIBLE(vc)) + if (con_is_visible(vc)) vc->vc_sw->con_putcs(vc, start, cnt, vc->vc_y, vc->vc_x); vc->vc_x += cnt; if (vc->vc_x == vc->vc_cols) { @@ -3154,7 +3160,7 @@ static int do_bind_con_driver(const struct consw *csw, int first, int last, j = i; - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { k = i; save_screen(vc); } diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index 52a6da991165..460cebf322e3 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -570,7 +570,7 @@ sisusbcon_set_palette(struct vc_data *c, const unsigned char *table) /* Return value not used by vt */ - if (!CON_IS_VISIBLE(c)) + if (!con_is_visible(c)) return; sisusb = sisusb_get_sisusb_lock_and_check(c->vc_num); @@ -1226,7 +1226,7 @@ sisusbcon_do_font_op(struct sisusb_usb_data *sisusb, int set, int slot, struct vc_data *vc = vc_cons[i].d; if (vc && vc->vc_sw == &sisusb_con) { - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { vc->vc_sw->con_cursor(vc, CM_DRAW); } vc->vc_font.height = fh; diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index eef8a8b7274f..b87f5cfdaea5 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -380,7 +380,7 @@ static void fb_flashcursor(struct work_struct *work) if (ops && ops->currcon != -1) vc = vc_cons[ops->currcon].d; - if (!vc || !CON_IS_VISIBLE(vc) || + if (!vc || !con_is_visible(vc) || registered_fb[con2fb_map[vc->vc_num]] != info || vc->vc_deccm != 1) { console_unlock(); @@ -618,7 +618,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, erase, vc->vc_size_row * logo_lines); - if (CON_IS_VISIBLE(vc) && vc->vc_mode == KD_TEXT) { + if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { fbcon_clear_margins(vc, 0); update_screen(vc); } @@ -1112,7 +1112,7 @@ static void fbcon_init(struct vc_data *vc, int init) * * We need to do it in fbcon_init() to prevent screen corruption. */ - if (CON_IS_VISIBLE(vc) && vc->vc_mode == KD_TEXT) { + if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { if (info->fbops->fb_set_par && !(ops->flags & FBCON_FLAGS_INIT)) { ret = info->fbops->fb_set_par(info); @@ -1192,7 +1192,7 @@ static void fbcon_deinit(struct vc_data *vc) if (!ops) goto finished; - if (CON_IS_VISIBLE(vc)) + if (con_is_visible(vc)) fbcon_del_cursor_timer(info); ops->flags &= ~FBCON_FLAGS_INIT; @@ -1397,7 +1397,7 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, rows /= vc->vc_font.height; vc_resize(vc, cols, rows); - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { update_screen(vc); if (softback_buf) fbcon_update_softback(vc); @@ -2145,7 +2145,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, return -EINVAL; DPRINTK("resize now %ix%i\n", var.xres, var.yres); - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; fb_set_var(info, &var); @@ -2448,7 +2448,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int cnt; char *old_data = NULL; - if (CON_IS_VISIBLE(vc) && softback_lines) + if (con_is_visible(vc) && softback_lines) fbcon_set_origin(vc); resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); @@ -2529,9 +2529,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, cols /= w; rows /= h; vc_resize(vc, cols, rows); - if (CON_IS_VISIBLE(vc) && softback_buf) + if (con_is_visible(vc) && softback_buf) fbcon_update_softback(vc); - } else if (CON_IS_VISIBLE(vc) + } else if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { fbcon_clear_margins(vc, 0); update_screen(vc); @@ -2660,7 +2660,7 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table) if (fbcon_is_inactive(vc, info)) return; - if (!CON_IS_VISIBLE(vc)) + if (!con_is_visible(vc)) return; depth = fb_get_color_depth(&info->var, &info->fix); @@ -2902,7 +2902,7 @@ static void fbcon_modechanged(struct fb_info *info) p = &fb_display[vc->vc_num]; set_blitting_type(vc, info); - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { var_to_display(p, &info->var, info); cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres); rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); @@ -2941,7 +2941,7 @@ static void fbcon_set_all_vcs(struct fb_info *info) registered_fb[con2fb_map[i]] != info) continue; - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { fg = i; continue; } @@ -3180,7 +3180,7 @@ static void fbcon_fb_blanked(struct fb_info *info, int blank) registered_fb[con2fb_map[ops->currcon]] != info) return; - if (CON_IS_VISIBLE(vc)) { + if (con_is_visible(vc)) { if (blank) do_blank_screen(0); else diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index e280b3ceebd9..11576611a974 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -589,7 +589,7 @@ static void vgacon_init(struct vc_data *c, int init) static void vgacon_deinit(struct vc_data *c) { /* When closing the active console, reset video origin */ - if (CON_IS_VISIBLE(c)) { + if (con_is_visible(c)) { c->vc_visible_origin = vga_vram_base; vga_set_mem_top(c); } @@ -860,7 +860,7 @@ static void vgacon_set_palette(struct vc_data *vc, const unsigned char *table) { #ifdef CAN_LOAD_PALETTE if (vga_video_type != VIDEO_TYPE_VGAC || vga_palette_blanked - || !CON_IS_VISIBLE(vc)) + || !con_is_visible(vc)) return; vga_set_palette(vc, table); #endif @@ -1248,7 +1248,7 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) struct vc_data *c = vc_cons[i].d; if (c && c->vc_sw == &vga_con) { - if (CON_IS_VISIBLE(c)) { + if (con_is_visible(c)) { /* void size to cause regs to be rewritten */ cursor_size_lastfrom = 0; cursor_size_lastto = 0; @@ -1312,7 +1312,7 @@ static int vgacon_resize(struct vc_data *c, unsigned int width, return success */ return (user) ? 0 : -EINVAL; - if (CON_IS_VISIBLE(c) && !vga_is_gfx) /* who knows */ + if (con_is_visible(c) && !vga_is_gfx) /* who knows */ vgacon_doresize(c, width, height); return 0; } diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 5fa605c93428..a12d3f2899a8 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -168,6 +168,9 @@ extern void vc_SAK(struct work_struct *work); #define CUR_DEFAULT CUR_UNDERLINE -#define CON_IS_VISIBLE(conp) (*conp->vc_display_fg == conp) +static inline bool con_is_visible(const struct vc_data *vc) +{ + return *vc->vc_display_fg == vc; +} #endif /* _LINUX_CONSOLE_STRUCT_H */ -- cgit v1.2.3 From f8b0c2e688f086d22157afc734755ed370e288dc Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:36 +0200 Subject: tty: vt, ignore PIO_UNIMAPCLR param We do not do hashtables for unicode fonts since 1995 (1.3.28). So it is time to remove the second parameter of con_clear_unimap and ignore the advice from userspace completely. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/consolemap.c | 13 ++++++------- drivers/tty/vt/vt_ioctl.c | 8 +------- include/linux/vt_kern.h | 5 ++--- 3 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/consolemap.c b/drivers/tty/vt/consolemap.c index c8c91f0476a2..9d7ab7b66a8a 100644 --- a/drivers/tty/vt/consolemap.c +++ b/drivers/tty/vt/consolemap.c @@ -499,9 +499,8 @@ con_insert_unipair(struct uni_pagedir *p, u_short unicode, u_short fontpos) return 0; } -/* ui is a leftover from using a hashtable, but might be used again - Caller must hold the lock */ -static int con_do_clear_unimap(struct vc_data *vc, struct unimapinit *ui) +/* Caller must hold the lock */ +static int con_do_clear_unimap(struct vc_data *vc) { struct uni_pagedir *p, *q; @@ -524,11 +523,11 @@ static int con_do_clear_unimap(struct vc_data *vc, struct unimapinit *ui) return 0; } -int con_clear_unimap(struct vc_data *vc, struct unimapinit *ui) +int con_clear_unimap(struct vc_data *vc) { int ret; console_lock(); - ret = con_do_clear_unimap(vc, ui); + ret = con_do_clear_unimap(vc); console_unlock(); return ret; } @@ -556,7 +555,7 @@ int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) int j, k; u16 **p1, *p2, l; - err1 = con_do_clear_unimap(vc, NULL); + err1 = con_do_clear_unimap(vc); if (err1) { console_unlock(); return err1; @@ -677,7 +676,7 @@ int con_set_default_unimap(struct vc_data *vc) /* The default font is always 256 characters */ - err = con_do_clear_unimap(vc, NULL); + err = con_do_clear_unimap(vc); if (err) return err; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 97d5a74558a3..f62c598810ff 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -1006,16 +1006,10 @@ int vt_ioctl(struct tty_struct *tty, break; case PIO_UNIMAPCLR: - { struct unimapinit ui; if (!perm) return -EPERM; - ret = copy_from_user(&ui, up, sizeof(struct unimapinit)); - if (ret) - ret = -EFAULT; - else - con_clear_unimap(vc, &ui); + con_clear_unimap(vc); break; - } case PIO_UNIMAP: case GIO_UNIMAP: diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 160f81fe3eb8..6abd24f258bc 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -59,14 +59,13 @@ int tioclinux(struct tty_struct *tty, unsigned long arg); #ifdef CONFIG_CONSOLE_TRANSLATIONS /* consolemap.c */ -struct unimapinit; struct unipair; int con_set_trans_old(unsigned char __user * table); int con_get_trans_old(unsigned char __user * table); int con_set_trans_new(unsigned short __user * table); int con_get_trans_new(unsigned short __user * table); -int con_clear_unimap(struct vc_data *vc, struct unimapinit *ui); +int con_clear_unimap(struct vc_data *vc); int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list); int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, struct unipair __user *list); int con_set_default_unimap(struct vc_data *vc); @@ -92,7 +91,7 @@ static inline int con_get_trans_new(unsigned short __user *table) { return -EINVAL; } -static inline int con_clear_unimap(struct vc_data *vc, struct unimapinit *ui) +static inline int con_clear_unimap(struct vc_data *vc) { return 0; } -- cgit v1.2.3 From abd530de2a55c1a74271e27d6e8c71c74c25e222 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 23 Jun 2016 13:34:37 +0200 Subject: tty: vt, remove unused vc_deccolm vc_deccolm is only set and never read, remove the member from vc_data. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 1 - include/linux/console_struct.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 26de5c0fc056..213ce24060b5 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1482,7 +1482,6 @@ static void set_mode(struct vc_data *vc, int on_off) clr_kbd(vc, decckm); break; case 3: /* 80/132 mode switch unimplemented */ - vc->vc_deccolm = on_off; #if 0 vc_resize(deccolm ? 132 : 80, vc->vc_rows); /* this alone does not suffice; some user mode diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index a12d3f2899a8..6fd3c908a340 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -106,7 +106,6 @@ struct vc_data { unsigned int vc_decawm : 1; /* Autowrap Mode */ unsigned int vc_deccm : 1; /* Cursor Visible */ unsigned int vc_decim : 1; /* Insert Mode */ - unsigned int vc_deccolm : 1; /* 80/132 Column Mode */ /* attribute flags */ unsigned int vc_intensity : 2; /* 0=half-bright, 1=normal, 2=bold */ unsigned int vc_italic:1; -- cgit v1.2.3 From c6f82787a5a193a5c4c49ddaeb362d320efa5fba Mon Sep 17 00:00:00 2001 From: "Chuah, Kim Tatt" Date: Wed, 15 Jun 2016 13:44:11 +0800 Subject: dmaengine: hsu: Export hsu_dma_get_status() To allow other code to safely read DMA Channel Status Register (where the register attribute for Channel Error, Descriptor Time Out & Descriptor Done fields are read-clear), export hsu_dma_get_status(). hsu_dma_irq() is renamed to hsu_dma_do_irq() and requires Status Register value to be passed in. Signed-off-by: Chuah, Kim Tatt Acked-by: Andy Shevchenko Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- drivers/dma/hsu/hsu.c | 90 +++++++++++++++++++++++++++++--------- drivers/dma/hsu/pci.c | 11 ++++- drivers/tty/serial/8250/8250_mid.c | 22 +++++++--- include/linux/dma/hsu.h | 14 ++++-- 4 files changed, 106 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c index f8c5cd53307c..c5f21efd6090 100644 --- a/drivers/dma/hsu/hsu.c +++ b/drivers/dma/hsu/hsu.c @@ -126,28 +126,33 @@ static void hsu_dma_start_transfer(struct hsu_dma_chan *hsuc) hsu_dma_start_channel(hsuc); } -static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc) -{ - unsigned long flags; - u32 sr; - - spin_lock_irqsave(&hsuc->vchan.lock, flags); - sr = hsu_chan_readl(hsuc, HSU_CH_SR); - spin_unlock_irqrestore(&hsuc->vchan.lock, flags); - - return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY); -} - -irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr) +/* + * hsu_dma_get_status() - get DMA channel status + * @chip: HSUART DMA chip + * @nr: DMA channel number + * @status: pointer for DMA Channel Status Register value + * + * Description: + * The function reads and clears the DMA Channel Status Register, checks + * if it was a timeout interrupt and returns a corresponding value. + * + * Caller should provide a valid pointer for the DMA Channel Status + * Register value that will be returned in @status. + * + * Return: + * 1 for DMA timeout status, 0 for other DMA status, or error code for + * invalid parameters or no interrupt pending. + */ +int hsu_dma_get_status(struct hsu_dma_chip *chip, unsigned short nr, + u32 *status) { struct hsu_dma_chan *hsuc; - struct hsu_dma_desc *desc; unsigned long flags; u32 sr; /* Sanity check */ if (nr >= chip->hsu->nr_channels) - return IRQ_NONE; + return -EINVAL; hsuc = &chip->hsu->chan[nr]; @@ -155,22 +160,65 @@ irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr) * No matter what situation, need read clear the IRQ status * There is a bug, see Errata 5, HSD 2900918 */ - sr = hsu_dma_chan_get_sr(hsuc); + spin_lock_irqsave(&hsuc->vchan.lock, flags); + sr = hsu_chan_readl(hsuc, HSU_CH_SR); + spin_unlock_irqrestore(&hsuc->vchan.lock, flags); + + /* Check if any interrupt is pending */ + sr &= ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY); if (!sr) - return IRQ_NONE; + return -EIO; /* Timeout IRQ, need wait some time, see Errata 2 */ if (sr & HSU_CH_SR_DESCTO_ANY) udelay(2); + /* + * At this point, at least one of Descriptor Time Out, Channel Error + * or Descriptor Done bits must be set. Clear the Descriptor Time Out + * bits and if sr is still non-zero, it must be channel error or + * descriptor done which are higher priority than timeout and handled + * in hsu_dma_do_irq(). Else, it must be a timeout. + */ sr &= ~HSU_CH_SR_DESCTO_ANY; - if (!sr) - return IRQ_HANDLED; + + *status = sr; + + return sr ? 0 : 1; +} +EXPORT_SYMBOL_GPL(hsu_dma_get_status); + +/* + * hsu_dma_do_irq() - DMA interrupt handler + * @chip: HSUART DMA chip + * @nr: DMA channel number + * @status: Channel Status Register value + * + * Description: + * This function handles Channel Error and Descriptor Done interrupts. + * This function should be called after determining that the DMA interrupt + * is not a normal timeout interrupt, ie. hsu_dma_get_status() returned 0. + * + * Return: + * IRQ_NONE for invalid channel number, IRQ_HANDLED otherwise. + */ +irqreturn_t hsu_dma_do_irq(struct hsu_dma_chip *chip, unsigned short nr, + u32 status) +{ + struct hsu_dma_chan *hsuc; + struct hsu_dma_desc *desc; + unsigned long flags; + + /* Sanity check */ + if (nr >= chip->hsu->nr_channels) + return IRQ_NONE; + + hsuc = &chip->hsu->chan[nr]; spin_lock_irqsave(&hsuc->vchan.lock, flags); desc = hsuc->desc; if (desc) { - if (sr & HSU_CH_SR_CHE) { + if (status & HSU_CH_SR_CHE) { desc->status = DMA_ERROR; } else if (desc->active < desc->nents) { hsu_dma_start_channel(hsuc); @@ -184,7 +232,7 @@ irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr) return IRQ_HANDLED; } -EXPORT_SYMBOL_GPL(hsu_dma_irq); +EXPORT_SYMBOL_GPL(hsu_dma_do_irq); static struct hsu_dma_desc *hsu_dma_alloc_desc(unsigned int nents) { diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c index e2db76bd56d8..9916058531d9 100644 --- a/drivers/dma/hsu/pci.c +++ b/drivers/dma/hsu/pci.c @@ -27,13 +27,20 @@ static irqreturn_t hsu_pci_irq(int irq, void *dev) { struct hsu_dma_chip *chip = dev; u32 dmaisr; + u32 status; unsigned short i; irqreturn_t ret = IRQ_NONE; + int err; dmaisr = readl(chip->regs + HSU_PCI_DMAISR); for (i = 0; i < chip->hsu->nr_channels; i++) { - if (dmaisr & 0x1) - ret |= hsu_dma_irq(chip, i); + if (dmaisr & 0x1) { + err = hsu_dma_get_status(chip, i, &status); + if (err > 0) + ret |= IRQ_HANDLED; + else if (err == 0) + ret |= hsu_dma_do_irq(chip, i, status); + } dmaisr >>= 1; } diff --git a/drivers/tty/serial/8250/8250_mid.c b/drivers/tty/serial/8250/8250_mid.c index 86379a79a6a3..b218ff528df7 100644 --- a/drivers/tty/serial/8250/8250_mid.c +++ b/drivers/tty/serial/8250/8250_mid.c @@ -97,12 +97,24 @@ static int dnv_handle_irq(struct uart_port *p) { struct mid8250 *mid = p->private_data; unsigned int fisr = serial_port_in(p, INTEL_MID_UART_DNV_FISR); + u32 status; int ret = IRQ_NONE; - - if (fisr & BIT(2)) - ret |= hsu_dma_irq(&mid->dma_chip, 1); - if (fisr & BIT(1)) - ret |= hsu_dma_irq(&mid->dma_chip, 0); + int err; + + if (fisr & BIT(2)) { + err = hsu_dma_get_status(&mid->dma_chip, 1, &status); + if (err > 0) + ret |= IRQ_HANDLED; + else if (err == 0) + ret |= hsu_dma_do_irq(&mid->dma_chip, 1, status); + } + if (fisr & BIT(1)) { + err = hsu_dma_get_status(&mid->dma_chip, 0, &status); + if (err > 0) + ret |= IRQ_HANDLED; + else if (err == 0) + ret |= hsu_dma_do_irq(&mid->dma_chip, 0, status); + } if (fisr & BIT(0)) ret |= serial8250_handle_irq(p, serial_port_in(p, UART_IIR)); return ret; diff --git a/include/linux/dma/hsu.h b/include/linux/dma/hsu.h index 79df69dc629c..aaff68efba5d 100644 --- a/include/linux/dma/hsu.h +++ b/include/linux/dma/hsu.h @@ -39,14 +39,22 @@ struct hsu_dma_chip { #if IS_ENABLED(CONFIG_HSU_DMA) /* Export to the internal users */ -irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr); +int hsu_dma_get_status(struct hsu_dma_chip *chip, unsigned short nr, + u32 *status); +irqreturn_t hsu_dma_do_irq(struct hsu_dma_chip *chip, unsigned short nr, + u32 status); /* Export to the platform drivers */ int hsu_dma_probe(struct hsu_dma_chip *chip); int hsu_dma_remove(struct hsu_dma_chip *chip); #else -static inline irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, - unsigned short nr) +static inline int hsu_dma_get_status(struct hsu_dma_chip *chip, + unsigned short nr, u32 *status) +{ + return 0; +} +static inline irqreturn_t hsu_dma_do_irq(struct hsu_dma_chip *chip, + unsigned short nr, u32 status) { return IRQ_NONE; } -- cgit v1.2.3 From 4ef03d328769eddbfeca1f1c958fdb181a69c341 Mon Sep 17 00:00:00 2001 From: Yegor Yefremov Date: Tue, 31 May 2016 10:59:18 +0200 Subject: tty/serial/8250: use mctrl_gpio helpers This patch permits the usage for GPIOs to control the CTS/RTS/DTR/DSR/DCD/RI signals. Signed-off-by: Yegor Yefremov Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/8250.txt | 19 ++++++++++++ drivers/tty/serial/8250/8250.h | 35 ++++++++++++++++++++++- drivers/tty/serial/8250/8250_core.c | 9 ++++++ drivers/tty/serial/8250/8250_omap.c | 31 +++++++++++--------- drivers/tty/serial/8250/8250_port.c | 7 ++++- drivers/tty/serial/8250/Kconfig | 1 + include/linux/serial_8250.h | 1 + 7 files changed, 88 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt index 936ab5b87324..f5561ac7e17e 100644 --- a/Documentation/devicetree/bindings/serial/8250.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt @@ -42,6 +42,9 @@ Optional properties: - auto-flow-control: one way to enable automatic flow control support. The driver is allowed to detect support for the capability even without this property. +- {rts,cts,dtr,dsr,rng,dcd}-gpios: specify a GPIO for RTS/CTS/DTR/DSR/RI/DCD + line respectively. It will use specified GPIO instead of the peripheral + function pin for the UART feature. If unsure, don't specify this property. Note: * fsl,ns16550: @@ -63,3 +66,19 @@ Example: interrupts = <10>; reg-shift = <2>; }; + +Example for OMAP UART using GPIO-based modem control signals: + + uart4: serial@49042000 { + compatible = "ti,omap3-uart"; + reg = <0x49042000 0x400>; + interrupts = <80>; + ti,hwmods = "uart4"; + clock-frequency = <48000000>; + cts-gpios = <&gpio3 5 GPIO_ACTIVE_LOW>; + rts-gpios = <&gpio3 6 GPIO_ACTIVE_LOW>; + dtr-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>; + dsr-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>; + dcd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; + rng-gpios = <&gpio1 15 GPIO_ACTIVE_LOW>; + }; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 1a16feac9a36..122e0e4029fe 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -15,6 +15,8 @@ #include #include +#include "../serial_mctrl_gpio.h" + struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); @@ -131,12 +133,43 @@ void serial8250_em485_destroy(struct uart_8250_port *p); static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { + int mctrl_gpio = 0; + serial_out(up, UART_MCR, value); + + if (value & UART_MCR_RTS) + mctrl_gpio |= TIOCM_RTS; + if (value & UART_MCR_DTR) + mctrl_gpio |= TIOCM_DTR; + + mctrl_gpio_set(up->gpios, mctrl_gpio); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { - return serial_in(up, UART_MCR); + int mctrl, mctrl_gpio = 0; + + mctrl = serial_in(up, UART_MCR); + + /* save current MCR values */ + if (mctrl & UART_MCR_RTS) + mctrl_gpio |= TIOCM_RTS; + if (mctrl & UART_MCR_DTR) + mctrl_gpio |= TIOCM_DTR; + + mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); + + if (mctrl_gpio & TIOCM_RTS) + mctrl |= UART_MCR_RTS; + else + mctrl &= ~UART_MCR_RTS; + + if (mctrl_gpio & TIOCM_DTR) + mctrl |= UART_MCR_DTR; + else + mctrl &= ~UART_MCR_DTR; + + return mctrl; } #if defined(__alpha__) && !defined(CONFIG_PCI) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index dcf43f66404f..13ad5c3d2e68 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -974,6 +974,8 @@ int serial8250_register_8250_port(struct uart_8250_port *up) uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { + struct mctrl_gpios *gpios; + if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); @@ -1011,6 +1013,13 @@ int serial8250_register_8250_port(struct uart_8250_port *up) if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; + gpios = mctrl_gpio_init(&uart->port, 0); + if (IS_ERR(gpios)) { + if (PTR_ERR(gpios) != -ENOSYS) + return PTR_ERR(gpios); + } else + uart->gpios = gpios; + serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 61ad6c3b20a0..e14982f36a04 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -134,18 +134,21 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) serial8250_do_set_mctrl(port, mctrl); - /* - * Turn off autoRTS if RTS is lowered and restore autoRTS setting - * if RTS is raised - */ - lcr = serial_in(up, UART_LCR); - serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) - priv->efr |= UART_EFR_RTS; - else - priv->efr &= ~UART_EFR_RTS; - serial_out(up, UART_EFR, priv->efr); - serial_out(up, UART_LCR, lcr); + if (IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, + UART_GPIO_RTS))) { + /* + * Turn off autoRTS if RTS is lowered and restore autoRTS + * setting if RTS is raised + */ + lcr = serial_in(up, UART_LCR); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) + priv->efr |= UART_EFR_RTS; + else + priv->efr &= ~UART_EFR_RTS; + serial_out(up, UART_EFR, priv->efr); + serial_out(up, UART_LCR, lcr); + } } /* @@ -446,7 +449,9 @@ static void omap_8250_set_termios(struct uart_port *port, priv->efr = 0; up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF); - if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW) { + if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW + && IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, + UART_GPIO_RTS))) { /* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */ up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS; priv->efr |= UART_EFR_CTS; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index bdfa659b9606..7481b95c6d84 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1618,6 +1618,8 @@ static void serial8250_disable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; + mctrl_gpio_disable_ms(up->gpios); + up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } @@ -1630,6 +1632,8 @@ static void serial8250_enable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; + mctrl_gpio_enable_ms(up->gpios); + up->ier |= UART_IER_MSI; serial8250_rpm_get(up); @@ -1913,7 +1917,8 @@ unsigned int serial8250_do_get_mctrl(struct uart_port *port) ret |= TIOCM_DSR; if (status & UART_MSR_CTS) ret |= TIOCM_CTS; - return ret; + + return mctrl_gpio_get(up->gpios, &ret); } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index b5a0f2e76f08..b1c73dec7eda 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -6,6 +6,7 @@ config SERIAL_8250 tristate "8250/16550 and compatible serial support" select SERIAL_CORE + select SERIAL_MCTRL_GPIO if GPIOLIB ---help--- This selects whether you want to include the driver for the standard serial ports. The standard answer is Y. People who might say N diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 48ec7651989b..923266cd294a 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -111,6 +111,7 @@ struct uart_8250_port { * if no_console_suspend */ unsigned char probe; + struct mctrl_gpios *gpios; #define UART_PROBE_RSA (1 << 0) /* -- cgit v1.2.3 From f8ba3647f30ab22daeb5110453e2dad8a2c1d841 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 6 Jun 2016 18:41:00 +0900 Subject: earlycon: mark earlycon code as __used iif the caller is built-in Keep earlycon related symbols only when CONFIG_SERIAL_EARLYCON is enabled and the driver is built-in. This will be helpful to clean up ifdefs surrounding earlycon code in serial drivers. Signed-off-by: Masahiro Yamada Acked-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index a3d7c0d4a03e..2f44e2013654 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -352,9 +352,15 @@ struct earlycon_id { extern const struct earlycon_id __earlycon_table[]; extern const struct earlycon_id __earlycon_table_end[]; +#if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) +#define EARLYCON_USED_OR_UNUSED __used +#else +#define EARLYCON_USED_OR_UNUSED __maybe_unused +#endif + #define OF_EARLYCON_DECLARE(_name, compat, fn) \ static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ - __used __section(__earlycon_table) \ + EARLYCON_USED_OR_UNUSED __section(__earlycon_table) \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn } -- cgit v1.2.3 From a3aef37930713447b45b1f0f9f8841be44f7db45 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Tue, 21 Jun 2016 10:58:10 +0300 Subject: xhci: get rid of platform data No more users for it. Signed-off-by: Heikki Krogerus Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-plat.c | 5 +---- include/linux/usb/xhci_pdriver.h | 27 --------------------------- 2 files changed, 1 insertion(+), 31 deletions(-) delete mode 100644 include/linux/usb/xhci_pdriver.h (limited to 'include') diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index d1db8bb10554..ed56bf9ed885 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include "xhci.h" @@ -138,7 +137,6 @@ MODULE_DEVICE_TABLE(of, usb_xhci_of_match); static int xhci_plat_probe(struct platform_device *pdev) { - struct usb_xhci_pdata *pdata = dev_get_platdata(&pdev->dev); const struct of_device_id *match; const struct hc_driver *driver; struct xhci_hcd *xhci; @@ -222,8 +220,7 @@ static int xhci_plat_probe(struct platform_device *pdev) goto disable_clk; } - if (device_property_read_bool(&pdev->dev, "usb3-lpm-capable") || - (pdata && pdata->usb3_lpm_capable)) + if (device_property_read_bool(&pdev->dev, "usb3-lpm-capable")) xhci->quirks |= XHCI_LPM_SUPPORT; if (HCC_MAX_PSA(xhci->hcc_params) >= 4) diff --git a/include/linux/usb/xhci_pdriver.h b/include/linux/usb/xhci_pdriver.h deleted file mode 100644 index 376654b5b0f7..000000000000 --- a/include/linux/usb/xhci_pdriver.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY - * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - * for more details. - * - */ - -#ifndef __USB_CORE_XHCI_PDRIVER_H -#define __USB_CORE_XHCI_PDRIVER_H - -/** - * struct usb_xhci_pdata - platform_data for generic xhci platform driver - * - * @usb3_lpm_capable: determines if this xhci platform supports USB3 - * LPM capability - * - */ -struct usb_xhci_pdata { - unsigned usb3_lpm_capable:1; -}; - -#endif /* __USB_CORE_XHCI_PDRIVER_H */ -- cgit v1.2.3 From 0afef45654ae908536278ecb143ded5bbc713391 Mon Sep 17 00:00:00 2001 From: Stuart Yoder Date: Wed, 22 Jun 2016 16:40:45 -0500 Subject: staging: fsl-mc: add support for device table matching Move the definition of fsl_mc_device_id to its proper location in mod_devicetable.h, and add fsl-mc bus support to devicetable-offsets.c and file2alias.c to enable device table matching. With this patch udev based module loading of fsl-mc drivers is supported. Signed-off-by: Stuart Yoder Signed-off-by: Greg Kroah-Hartman --- drivers/staging/fsl-mc/include/mc.h | 13 ------------- include/linux/mod_devicetable.h | 16 ++++++++++++++++ scripts/mod/devicetable-offsets.c | 4 ++++ scripts/mod/file2alias.c | 12 ++++++++++++ 4 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/staging/fsl-mc/include/mc.h b/drivers/staging/fsl-mc/include/mc.h index bc0d45cb9b65..a9a9d23f78d5 100644 --- a/drivers/staging/fsl-mc/include/mc.h +++ b/drivers/staging/fsl-mc/include/mc.h @@ -50,19 +50,6 @@ struct fsl_mc_driver { #define to_fsl_mc_driver(_drv) \ container_of(_drv, struct fsl_mc_driver, driver) -/** - * struct fsl_mc_device_id - MC object device Id entry for driver matching - * @vendor: vendor ID - * @obj_type: MC object type - * - * Type of entries in the "device Id" table for MC object devices supported by - * a MC object device driver. The last entry of the table has vendor set to 0x0 - */ -struct fsl_mc_device_id { - u16 vendor; - const char obj_type[16]; -}; - /** * enum fsl_mc_pool_type - Types of allocatable MC bus resources * diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 6e4c645e1c0d..ed84c07f6a51 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -657,4 +657,20 @@ struct ulpi_device_id { kernel_ulong_t driver_data; }; +/** + * struct fsl_mc_device_id - MC object device identifier + * @vendor: vendor ID + * @obj_type: MC object type + * @ver_major: MC object version major number + * @ver_minor: MC object version minor number + * + * Type of entries in the "device Id" table for MC object devices supported by + * a MC object device driver. The last entry of the table has vendor set to 0x0 + */ +struct fsl_mc_device_id { + __u16 vendor; + const char obj_type[16]; +}; + + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index 840b97328b39..e4d90e50f6fe 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -202,5 +202,9 @@ int main(void) DEVID_FIELD(hda_device_id, rev_id); DEVID_FIELD(hda_device_id, api_version); + DEVID(fsl_mc_device_id); + DEVID_FIELD(fsl_mc_device_id, vendor); + DEVID_FIELD(fsl_mc_device_id, obj_type); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index fec75786f75b..29d6699d5a06 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1289,6 +1289,18 @@ static int do_hda_entry(const char *filename, void *symval, char *alias) } ADD_TO_DEVTABLE("hdaudio", hda_device_id, do_hda_entry); +/* Looks like: fsl-mc:vNdN */ +static int do_fsl_mc_entry(const char *filename, void *symval, + char *alias) +{ + DEF_FIELD(symval, fsl_mc_device_id, vendor); + DEF_FIELD_ADDR(symval, fsl_mc_device_id, obj_type); + + sprintf(alias, "fsl-mc:v%08Xd%s", vendor, *obj_type); + return 1; +} +ADD_TO_DEVTABLE("fslmc", fsl_mc_device_id, do_fsl_mc_entry); + /* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) { -- cgit v1.2.3 From 7dc603c9028ea5d4354e0e317e8481df99b06d7e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 16 Jun 2016 13:29:28 +0200 Subject: sched/fair: Fix PELT integrity for new tasks Vincent and Yuyang found another few scenarios in which entity tracking goes wobbly. The scenarios are basically due to the fact that new tasks are not immediately attached and thereby differ from the normal situation -- a task is always attached to a cfs_rq load average (such that it includes its blocked contribution) and are explicitly detached/attached on migration to another cfs_rq. Scenario 1: switch to fair class p->sched_class = fair_class; if (queued) enqueue_task(p); ... enqueue_entity() enqueue_entity_load_avg() migrated = !sa->last_update_time (true) if (migrated) attach_entity_load_avg() check_class_changed() switched_from() (!fair) switched_to() (fair) switched_to_fair() attach_entity_load_avg() If @p is a new task that hasn't been fair before, it will have !last_update_time and, per the above, end up in attach_entity_load_avg() _twice_. Scenario 2: change between cgroups sched_move_group(p) if (queued) dequeue_task() task_move_group_fair() detach_task_cfs_rq() detach_entity_load_avg() set_task_rq() attach_task_cfs_rq() attach_entity_load_avg() if (queued) enqueue_task(); ... enqueue_entity() enqueue_entity_load_avg() migrated = !sa->last_update_time (true) if (migrated) attach_entity_load_avg() Similar as with scenario 1, if @p is a new task, it will have !load_update_time and we'll end up in attach_entity_load_avg() _twice_. Furthermore, notice how we do a detach_entity_load_avg() on something that wasn't attached to begin with. As stated above; the problem is that the new task isn't yet attached to the load tracking and thereby violates the invariant assumption. This patch remedies this by ensuring a new task is indeed properly attached to the load tracking on creation, through post_init_entity_util_avg(). Of course, this isn't entirely as straightforward as one might think, since the task is hashed before we call wake_up_new_task() and thus can be poked at. We avoid this by adding TASK_NEW and teaching cpu_cgroup_can_attach() to refuse such tasks. Reported-by: Yuyang Du Reported-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- kernel/sched/core.c | 28 +++++++++++++++++++++++----- kernel/sched/fair.c | 45 +++++++++++++++++++++++++++++++++++++-------- 3 files changed, 63 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index b45acfd18f4e..d99218a1e043 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -219,9 +219,10 @@ extern void proc_sched_set_task(struct task_struct *p); #define TASK_WAKING 256 #define TASK_PARKED 512 #define TASK_NOLOAD 1024 -#define TASK_STATE_MAX 2048 +#define TASK_NEW 2048 +#define TASK_STATE_MAX 4096 -#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN" +#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn" extern char ___assert_task_state[1 - 2*!!( sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)]; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3d856c46f6d8..14afa518948c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2342,11 +2342,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) __sched_fork(clone_flags, p); /* - * We mark the process as running here. This guarantees that + * We mark the process as NEW here. This guarantees that * nobody will actually run it, and a signal or other external * event cannot wake it up and insert it on the runqueue either. */ - p->state = TASK_RUNNING; + p->state = TASK_NEW; /* * Make sure we do not leak PI boosting priority to the child. @@ -2383,6 +2383,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->sched_class = &fair_sched_class; } + init_entity_runnable_average(&p->se); + /* * The child is not yet in the pid-hash so no cgroup attach races, * and the cgroup is pinned to this child due to cgroup_fork() @@ -2529,9 +2531,8 @@ void wake_up_new_task(struct task_struct *p) struct rq_flags rf; struct rq *rq; - /* Initialize new task's runnable average */ - init_entity_runnable_average(&p->se); raw_spin_lock_irqsave(&p->pi_lock, rf.flags); + p->state = TASK_RUNNING; #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: @@ -8237,6 +8238,7 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *css; + int ret = 0; cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED @@ -8247,8 +8249,24 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) if (task->sched_class != &fair_sched_class) return -EINVAL; #endif + /* + * Serialize against wake_up_new_task() such that if its + * running, we're sure to observe its full state. + */ + raw_spin_lock_irq(&task->pi_lock); + /* + * Avoid calling sched_move_task() before wake_up_new_task() + * has happened. This would lead to problems with PELT, due to + * move wanting to detach+attach while we're not attached yet. + */ + if (task->state == TASK_NEW) + ret = -EINVAL; + raw_spin_unlock_irq(&task->pi_lock); + + if (ret) + break; } - return 0; + return ret; } static void cpu_cgroup_attach(struct cgroup_taskset *tset) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 64f26bc436eb..0c21a12c0205 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -690,6 +690,10 @@ void init_entity_runnable_average(struct sched_entity *se) /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); +static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq); +static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se); + /* * With new tasks being created, their initial util_avgs are extrapolated * based on the cfs_rq's current util_avg: @@ -720,6 +724,7 @@ void post_init_entity_util_avg(struct sched_entity *se) struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + u64 now = cfs_rq_clock_task(cfs_rq); if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -733,16 +738,37 @@ void post_init_entity_util_avg(struct sched_entity *se) } sa->util_sum = sa->util_avg * LOAD_AVG_MAX; } + + if (entity_is_task(se)) { + struct task_struct *p = task_of(se); + if (p->sched_class != &fair_sched_class) { + /* + * For !fair tasks do: + * + update_cfs_rq_load_avg(now, cfs_rq, false); + attach_entity_load_avg(cfs_rq, se); + switched_from_fair(rq, p); + * + * such that the next switched_to_fair() has the + * expected state. + */ + se->avg.last_update_time = now; + return; + } + } + + update_cfs_rq_load_avg(now, cfs_rq, false); + attach_entity_load_avg(cfs_rq, se); } -#else +#else /* !CONFIG_SMP */ void init_entity_runnable_average(struct sched_entity *se) { } void post_init_entity_util_avg(struct sched_entity *se) { } -#endif +#endif /* CONFIG_SMP */ /* * Update the current task's runtime statistics. @@ -2840,8 +2866,6 @@ void set_task_rq_fair(struct sched_entity *se, static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} #endif /* CONFIG_FAIR_GROUP_SCHED */ -static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); - static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -2951,6 +2975,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* * If we got migrated (either between CPUs or between cgroups) we'll * have aged the average right before clearing @last_update_time. + * + * Or we're fresh through post_init_entity_util_avg(). */ if (se->avg.last_update_time) { __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), @@ -3056,11 +3082,14 @@ void remove_entity_load_avg(struct sched_entity *se) u64 last_update_time; /* - * Newly created task or never used group entity should not be removed - * from its (source) cfs_rq + * tasks cannot exit without having gone through wake_up_new_task() -> + * post_init_entity_util_avg() which will have added things to the + * cfs_rq, so we can remove unconditionally. + * + * Similarly for groups, they will have passed through + * post_init_entity_util_avg() before unregister_sched_fair_group() + * calls this. */ - if (se->avg.last_update_time == 0) - return; last_update_time = cfs_rq_last_update_time(cfs_rq); -- cgit v1.2.3 From 54fd11fee59e7d05287bc4eebccc8ec9742f2745 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Sat, 25 Jun 2016 08:20:25 +0100 Subject: efi: Document #define FOO_PROTOCOL_GUID layout Add a comment documenting why EFI GUIDs are laid out like they are. Ideally I'd like to change all the ", " to "," too, but right now the format is such that checkpatch won't complain with new ones, and staring at checkpatch didn't get me anywhere towards making that work. Signed-off-by: Peter Jones Signed-off-by: Matt Fleming Cc: Ard Biesheuvel Cc: Joe Perches Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1466839230-12781-3-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- include/linux/efi.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index f196dd0b0f2f..03009695760d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -536,7 +536,22 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes, void efi_native_runtime_setup(void); /* - * EFI Configuration Table and GUID definitions + * EFI Configuration Table and GUID definitions + * + * These should be formatted roughly like the ones in the UEFI SPEC has + * them. It makes them easier to grep for, and they look the same when + * you're staring at them. Here's the guide: + * + * GUID: 12345678-1234-1234-1234-123456789012 + * Spec: + * #define EFI_SOME_PROTOCOL_GUID \ + * {0x12345678,0x1234,0x1234,\ + * {0x12,0x34,0x12,0x34,0x56,0x78,0x90,0x12}} + * Here: + * #define SOME_PROTOCOL_GUID \ + * EFI_GUID(0x12345678, 0x1234, 0x1234, \ + * 0x12, 0x34, 0x12, 0x34, 0x56, 0x78, 0x90, 0x12) + * ^ tab ^tab ^ space */ #define NULL_GUID \ EFI_GUID(0x00000000, 0x0000, 0x0000, \ -- cgit v1.2.3 From 80e75596079f0a41f905836ad0ccaac68ba33612 Mon Sep 17 00:00:00 2001 From: Alex Thorlton Date: Sat, 25 Jun 2016 08:20:27 +0100 Subject: efi: Convert efi_call_virt() to efi_call_virt_pointer() This commit makes a few slight modifications to the efi_call_virt() macro to get it to work with function pointers that are stored in locations other than efi.systab->runtime, and renames the macro to efi_call_virt_pointer(). The majority of the changes here are to pull these macros up into header files so that they can be accessed from outside of drivers/firmware/efi/runtime-wrappers.c. The most significant change not directly related to the code move is to add an extra "p" argument into the appropriate efi_call macros, and use that new argument in place of the, formerly hard-coded, efi.systab->runtime pointer. The last piece of the puzzle was to add an efi_call_virt() macro back into drivers/firmware/efi/runtime-wrappers.c to wrap around the new efi_call_virt_pointer() macro - this was mainly to keep the code from looking too cluttered by adding a bunch of extra references to efi.systab->runtime everywhere. Note that I also broke up the code in the efi_call_virt_pointer() macro a bit in the process of moving it. Signed-off-by: Alex Thorlton Signed-off-by: Matt Fleming Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: Dimitri Sivanich Cc: Linus Torvalds Cc: Mark Rutland Cc: Peter Zijlstra Cc: Roy Franz Cc: Russ Anderson Cc: Russell King Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1466839230-12781-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- arch/arm/include/asm/efi.h | 4 +-- arch/arm64/include/asm/efi.h | 4 +-- arch/x86/include/asm/efi.h | 9 +++--- drivers/firmware/efi/runtime-wrappers.c | 53 +++++++-------------------------- include/linux/efi.h | 51 +++++++++++++++++++++++++++++++ 5 files changed, 69 insertions(+), 52 deletions(-) (limited to 'include') diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index a708fa1f0905..766bf9b78160 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -28,10 +28,10 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define arch_efi_call_virt_setup() efi_virtmap_load() #define arch_efi_call_virt_teardown() efi_virtmap_unload() -#define arch_efi_call_virt(f, args...) \ +#define arch_efi_call_virt(p, f, args...) \ ({ \ efi_##f##_t *__f; \ - __f = efi.systab->runtime->f; \ + __f = p->f; \ __f(args); \ }) diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 622db3c6474e..bd887663689b 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -23,10 +23,10 @@ int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); efi_virtmap_load(); \ }) -#define arch_efi_call_virt(f, args...) \ +#define arch_efi_call_virt(p, f, args...) \ ({ \ efi_##f##_t *__f; \ - __f = efi.systab->runtime->f; \ + __f = p->f; \ __f(args); \ }) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 78d1e7467eae..55b4596ef688 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -41,10 +41,9 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); /* * Wrap all the virtual calls in a way that forces the parameters on the stack. */ -#define arch_efi_call_virt(f, args...) \ +#define arch_efi_call_virt(p, f, args...) \ ({ \ - ((efi_##f##_t __attribute__((regparm(0)))*) \ - efi.systab->runtime->f)(args); \ + ((efi_##f##_t __attribute__((regparm(0)))*) p->f)(args); \ }) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) @@ -81,8 +80,8 @@ struct efi_scratch { } \ }) -#define arch_efi_call_virt(f, args...) \ - efi_call((void *)efi.systab->runtime->f, args) \ +#define arch_efi_call_virt(p, f, args...) \ + efi_call((void *)p->f, args) \ #define arch_efi_call_virt_teardown() \ ({ \ diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 23bef6bb73ee..41958774cde3 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -22,7 +22,16 @@ #include #include -static void efi_call_virt_check_flags(unsigned long flags, const char *call) +/* + * Wrap around the new efi_call_virt_generic() macros so that the + * code doesn't get too cluttered: + */ +#define efi_call_virt(f, args...) \ + efi_call_virt_pointer(efi.systab->runtime, f, args) +#define __efi_call_virt(f, args...) \ + __efi_call_virt_pointer(efi.systab->runtime, f, args) + +void efi_call_virt_check_flags(unsigned long flags, const char *call) { unsigned long cur_flags, mismatch; @@ -38,48 +47,6 @@ static void efi_call_virt_check_flags(unsigned long flags, const char *call) local_irq_restore(flags); } -/* - * Arch code can implement the following three template macros, avoiding - * reptition for the void/non-void return cases of {__,}efi_call_virt: - * - * * arch_efi_call_virt_setup - * - * Sets up the environment for the call (e.g. switching page tables, - * allowing kernel-mode use of floating point, if required). - * - * * arch_efi_call_virt - * - * Performs the call. The last expression in the macro must be the call - * itself, allowing the logic to be shared by the void and non-void - * cases. - * - * * arch_efi_call_virt_teardown - * - * Restores the usual kernel environment once the call has returned. - */ - -#define efi_call_virt(f, args...) \ -({ \ - efi_status_t __s; \ - unsigned long flags; \ - arch_efi_call_virt_setup(); \ - local_save_flags(flags); \ - __s = arch_efi_call_virt(f, args); \ - efi_call_virt_check_flags(flags, __stringify(f)); \ - arch_efi_call_virt_teardown(); \ - __s; \ -}) - -#define __efi_call_virt(f, args...) \ -({ \ - unsigned long flags; \ - arch_efi_call_virt_setup(); \ - local_save_flags(flags); \ - arch_efi_call_virt(f, args); \ - efi_call_virt_check_flags(flags, __stringify(f)); \ - arch_efi_call_virt_teardown(); \ -}) - /* * According to section 7.1 of the UEFI spec, Runtime Services are not fully * reentrant, and there are particular combinations of calls that need to be diff --git a/include/linux/efi.h b/include/linux/efi.h index 03009695760d..75d148dc9c3f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1480,4 +1480,55 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, unsigned long size); bool efi_runtime_disabled(void); +extern void efi_call_virt_check_flags(unsigned long flags, const char *call); + +/* + * Arch code can implement the following three template macros, avoiding + * reptition for the void/non-void return cases of {__,}efi_call_virt(): + * + * * arch_efi_call_virt_setup() + * + * Sets up the environment for the call (e.g. switching page tables, + * allowing kernel-mode use of floating point, if required). + * + * * arch_efi_call_virt() + * + * Performs the call. The last expression in the macro must be the call + * itself, allowing the logic to be shared by the void and non-void + * cases. + * + * * arch_efi_call_virt_teardown() + * + * Restores the usual kernel environment once the call has returned. + */ + +#define efi_call_virt_pointer(p, f, args...) \ +({ \ + efi_status_t __s; \ + unsigned long __flags; \ + \ + arch_efi_call_virt_setup(); \ + \ + local_save_flags(__flags); \ + __s = arch_efi_call_virt(p, f, args); \ + efi_call_virt_check_flags(__flags, __stringify(f)); \ + \ + arch_efi_call_virt_teardown(); \ + \ + __s; \ +}) + +#define __efi_call_virt_pointer(p, f, args...) \ +({ \ + unsigned long __flags; \ + \ + arch_efi_call_virt_setup(); \ + \ + local_save_flags(__flags); \ + arch_efi_call_virt(p, f, args); \ + efi_call_virt_check_flags(__flags, __stringify(f)); \ + \ + arch_efi_call_virt_teardown(); \ +}) + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From b684e9bc750b6349ff59f1b1ab4397cae255765f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 25 Jun 2016 08:20:30 +0100 Subject: x86/efi: Remove the unused efi_get_time() function Nothing calls the efi_get_time() function on x86, but it does suffer from the 32-bit time_t overflow in 2038. This removes the function, we can always put it back in case we need it later. Signed-off-by: Arnd Bergmann Signed-off-by: Matt Fleming Acked-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/1466839230-12781-8-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- arch/x86/platform/efi/efi.c | 15 --------------- include/linux/efi.h | 1 - 2 files changed, 16 deletions(-) (limited to 'include') diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f93545e7dc54..d898b334ff46 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -98,21 +98,6 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -void efi_get_time(struct timespec *now) -{ - efi_status_t status; - efi_time_t eft; - efi_time_cap_t cap; - - status = efi.get_time(&eft, &cap); - if (status != EFI_SUCCESS) - pr_err("Oops: efitime: can't read time!\n"); - - now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour, - eft.minute, eft.second); - now->tv_nsec = 0; -} - void __init efi_find_mirror(void) { efi_memory_desc_t *md; diff --git a/include/linux/efi.h b/include/linux/efi.h index 75d148dc9c3f..0174f28ce9b3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -990,7 +990,6 @@ extern u64 efi_mem_desc_end(efi_memory_desc_t *md); extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); -extern void efi_get_time(struct timespec *now); extern void efi_reserve_boot_services(void); extern int efi_get_fdt_params(struct efi_fdt_params *params); extern struct kobject *efi_kobj; -- cgit v1.2.3 From 20f7b53dfc24e0caa984087691af82e442229680 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 27 Jun 2016 19:17:06 +0900 Subject: extcon: Move struct extcon_cable from header file to core This patch moves the struct extcon_cable because that should be only handled by extcon core. There are no reason to publish the internal structure. Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon.c | 20 ++++++++++++++++++++ include/linux/extcon.h | 20 -------------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index b6408f015637..b5fdb5d9dbad 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -77,6 +77,26 @@ static const char *extcon_name[] = { NULL, }; +/** + * struct extcon_cable - An internal data for each cable of extcon device. + * @edev: The extcon device + * @cable_index: Index of this cable in the edev + * @attr_g: Attribute group for the cable + * @attr_name: "name" sysfs entry + * @attr_state: "state" sysfs entry + * @attrs: Array pointing to attr_name and attr_state for attr_g + */ +struct extcon_cable { + struct extcon_dev *edev; + int cable_index; + + struct attribute_group attr_g; + struct device_attribute attr_name; + struct device_attribute attr_state; + + struct attribute *attrs[3]; /* to be fed to attr_g.attrs */ +}; + static struct class *extcon_class; #if defined(CONFIG_ANDROID) static struct class_compat *switch_class; diff --git a/include/linux/extcon.h b/include/linux/extcon.h index cec5c543afc6..1b2c8b6809cc 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -126,26 +126,6 @@ struct extcon_dev { struct device_attribute *d_attrs_muex; }; -/** - * struct extcon_cable - An internal data for each cable of extcon device. - * @edev: The extcon device - * @cable_index: Index of this cable in the edev - * @attr_g: Attribute group for the cable - * @attr_name: "name" sysfs entry - * @attr_state: "state" sysfs entry - * @attrs: Array pointing to attr_name and attr_state for attr_g - */ -struct extcon_cable { - struct extcon_dev *edev; - int cable_index; - - struct attribute_group attr_g; - struct device_attribute attr_name; - struct device_attribute attr_state; - - struct attribute *attrs[3]; /* to be fed to attr_g.attrs */ -}; - #if IS_ENABLED(CONFIG_EXTCON) /* -- cgit v1.2.3 From 58f386560a68dd98bd6744a28fc853eef11faebe Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 27 Jun 2016 20:03:39 +0900 Subject: extcon: Add resource-managed functions to register extcon notifier This patch adds the resource-managed functions for register/unregister the extcon notifier with the id of each external connector. This function will make it easy to handle the extcon notifier. - int devm_extcon_register_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); - void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); Signed-off-by: Chanwoo Choi --- drivers/extcon/devres.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/extcon.h | 17 ++++++++++++ 2 files changed, 90 insertions(+) (limited to 'include') diff --git a/drivers/extcon/devres.c b/drivers/extcon/devres.c index 694ca85d5a70..e686acd1c459 100644 --- a/drivers/extcon/devres.c +++ b/drivers/extcon/devres.c @@ -37,6 +37,19 @@ static void devm_extcon_dev_unreg(struct device *dev, void *res) extcon_dev_unregister(*(struct extcon_dev **)res); } +struct extcon_dev_notifier_devres { + struct extcon_dev *edev; + unsigned int id; + struct notifier_block *nb; +}; + +static void devm_extcon_dev_notifier_unreg(struct device *dev, void *res) +{ + struct extcon_dev_notifier_devres *this = res; + + extcon_unregister_notifier(this->edev, this->id, this->nb); +} + /** * devm_extcon_dev_allocate - Allocate managed extcon device * @dev: device owning the extcon device being created @@ -141,3 +154,63 @@ void devm_extcon_dev_unregister(struct device *dev, struct extcon_dev *edev) devm_extcon_dev_match, edev)); } EXPORT_SYMBOL_GPL(devm_extcon_dev_unregister); + +/** + * devm_extcon_register_notifier() - Resource-managed extcon_register_notifier() + * @dev: device to allocate extcon device + * @edev: the extcon device that has the external connecotr. + * @id: the unique id of each external connector in extcon enumeration. + * @nb: a notifier block to be registered. + * + * This function manages automatically the notifier of extcon device using + * device resource management and simplify the control of unregistering + * the notifier of extcon device. + * + * Note that the second parameter given to the callback of nb (val) is + * "old_state", not the current state. The current state can be retrieved + * by looking at the third pameter (edev pointer)'s state value. + * + * Returns 0 if success or negaive error number if failure. + */ +int devm_extcon_register_notifier(struct device *dev, struct extcon_dev *edev, + unsigned int id, struct notifier_block *nb) +{ + struct extcon_dev_notifier_devres *ptr; + int ret; + + ptr = devres_alloc(devm_extcon_dev_notifier_unreg, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + ret = extcon_register_notifier(edev, id, nb); + if (ret) { + devres_free(ptr); + return ret; + } + + ptr->edev = edev; + ptr->id = id; + ptr->nb = nb; + devres_add(dev, ptr); + + return 0; +} +EXPORT_SYMBOL(devm_extcon_register_notifier); + +/** + * devm_extcon_unregister_notifier() + - Resource-managed extcon_unregister_notifier() + * @dev: device to allocate extcon device + * @edev: the extcon device that has the external connecotr. + * @id: the unique id of each external connector in extcon enumeration. + * @nb: a notifier block to be registered. + */ +void devm_extcon_unregister_notifier(struct device *dev, + struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb) +{ + WARN_ON(devres_release(dev, devm_extcon_dev_notifier_unreg, + devm_extcon_dev_match, edev)); +} +EXPORT_SYMBOL(devm_extcon_unregister_notifier); diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 1b2c8b6809cc..7bf530f3f4f5 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -182,6 +182,12 @@ extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); +extern int devm_extcon_register_notifier(struct device *dev, + struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb); +extern void devm_extcon_unregister_notifier(struct device *dev, + struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb); /* * Following API get the extcon device from devicetree. @@ -273,6 +279,17 @@ static inline int extcon_unregister_notifier(struct extcon_dev *edev, return 0; } +static inline int devm_extcon_register_notifier(struct device *dev, + struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb) +{ + return -ENOSYS; +} + +static inline void devm_extcon_unregister_notifier(struct device *dev, + struct extcon_dev *edev, unsigned int id, + struct notifier_block *nb) { } + static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index) { -- cgit v1.2.3 From b4bba38909c21689de21355e84259cb7b38f25ac Mon Sep 17 00:00:00 2001 From: Benjamin Marzinski Date: Mon, 27 Jun 2016 09:58:40 -0500 Subject: fs: export __block_write_full_page gfs2 needs to be able to skip the check to see if a page is outside of the file size when writing it out. gfs2 can get into a situation where it needs to flush its in-memory log to disk while a truncate is in progress. If the file being trucated has data journaling enabled, it is possible that there are data blocks in the log that are past the end of the file. gfs can't finish the log flush without either writing these blocks out or revoking them. Otherwise, if the node crashed, it could overwrite subsequent changes made by other nodes in the cluster when it's journal was replayed. Unfortunately, there is no way to add log entries to the log during a flush. So gfs2 simply writes out the page instead. This situation can only occur when the truncate code still has the file locked exclusively, and hasn't marked this block as free in the metadata (which happens later in truc_dealloc). After gfs2 writes this page out, the truncation code will shortly invalidate it and write out any revokes if necessary. In order to make this work, gfs2 needs to be able to skip the check for writes outside the file size. Since the check exists in block_write_full_page, this patch exports __block_write_full_page, which doesn't have the check. Signed-off-by: Benjamin Marzinski Signed-off-by: Bob Peterson --- fs/buffer.c | 3 ++- include/linux/buffer_head.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/buffer.c b/fs/buffer.c index 754813a6962b..6c15012a75d9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1687,7 +1687,7 @@ static struct buffer_head *create_page_buffers(struct page *page, struct inode * * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this * causes the writes to be flagged as synchronous writes. */ -static int __block_write_full_page(struct inode *inode, struct page *page, +int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler) { @@ -1848,6 +1848,7 @@ recover: unlock_page(page); goto done; } +EXPORT_SYMBOL(__block_write_full_page); /* * If a page has any new buffers, zero them out here, and mark them uptodate diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d48daa3f6f20..7e14e545c4b6 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -208,6 +208,9 @@ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); +int __block_write_full_page(struct inode *inode, struct page *page, + get_block_t *get_block, struct writeback_control *wbc, + bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); -- cgit v1.2.3 From 7c84f7f80d6fcea36246b793d06c3555ca53ddcd Mon Sep 17 00:00:00 2001 From: David Frey Date: Thu, 2 Jun 2016 09:59:11 +0200 Subject: hwmon: add support for Sensirion SHT3x sensors This driver implements support for the Sensirion SHT3x-DIS chip, a humidity and temperature sensor. Temperature is measured in degrees celsius, relative humidity is expressed as a percentage. In the sysfs interface, all values are scaled by 1000, i.e. the value for 31.5 degrees celsius is 31500. Signed-off-by: Pascal Sachs [groeck: Fixed 'Variable length array is used' gcc warning] Signed-off-by: Guenter Roeck --- Documentation/hwmon/sht3x | 72 ++++ drivers/hwmon/Kconfig | 11 + drivers/hwmon/Makefile | 1 + drivers/hwmon/sht3x.c | 725 ++++++++++++++++++++++++++++++++++++ include/linux/platform_data/sht3x.h | 25 ++ 5 files changed, 834 insertions(+) create mode 100644 Documentation/hwmon/sht3x create mode 100644 drivers/hwmon/sht3x.c create mode 100644 include/linux/platform_data/sht3x.h (limited to 'include') diff --git a/Documentation/hwmon/sht3x b/Documentation/hwmon/sht3x new file mode 100644 index 000000000000..f5aa633ed383 --- /dev/null +++ b/Documentation/hwmon/sht3x @@ -0,0 +1,72 @@ +Kernel driver sht3x +=================== + +Supported chips: + * Sensirion SHT3x-DIS + Prefix: 'sht3x' + Addresses scanned: none + Datasheet: http://www.sensirion.com/fileadmin/user_upload/customers/sensirion/Dokumente/Humidity/Sensirion_Humidity_Datasheet_SHT3x_DIS.pdf + +Author: + David Frey + Pascal Sachs + +Description +----------- + +This driver implements support for the Sensirion SHT3x-DIS chip, a humidity +and temperature sensor. Temperature is measured in degrees celsius, relative +humidity is expressed as a percentage. In the sysfs interface, all values are +scaled by 1000, i.e. the value for 31.5 degrees celsius is 31500. + +The device communicates with the I2C protocol. Sensors can have the I2C +addresses 0x44 or 0x45, depending on the wiring. See +Documentation/i2c/instantiating-devices for methods to instantiate the device. + +There are two options configurable by means of sht3x_platform_data: +1. blocking (pull the I2C clock line down while performing the measurement) or + non-blocking mode. Blocking mode will guarantee the fastest result but + the I2C bus will be busy during that time. By default, non-blocking mode + is used. Make sure clock-stretching works properly on your device if you + want to use blocking mode. +2. high or low accuracy. High accuracy is used by default and using it is + strongly recommended. + +The sht3x sensor supports a single shot mode as well as 5 periodic measure +modes, which can be controlled with the update_interval sysfs interface. +The allowed update_interval in milliseconds are as follows: + * 0 single shot mode + * 2000 0.5 Hz periodic measurement + * 1000 1 Hz periodic measurement + * 500 2 Hz periodic measurement + * 250 4 Hz periodic measurement + * 100 10 Hz periodic measurement + +In the periodic measure mode, the sensor automatically triggers a measurement +with the configured update interval on the chip. When a temperature or humidity +reading exceeds the configured limits, the alert attribute is set to 1 and +the alert pin on the sensor is set to high. +When the temperature and humidity readings move back between the hysteresis +values, the alert bit is set to 0 and the alert pin on the sensor is set to +low. + +sysfs-Interface +--------------- + +temp1_input: temperature input +humidity1_input: humidity input +temp1_max: temperature max value +temp1_max_hyst: temperature hysteresis value for max limit +humidity1_max: humidity max value +humidity1_max_hyst: humidity hysteresis value for max limit +temp1_min: temperature min value +temp1_min_hyst: temperature hysteresis value for min limit +humidity1_min: humidity min value +humidity1_min_hyst: humidity hysteresis value for min limit +temp1_alarm: alarm flag is set to 1 if the temperature is outside the + configured limits. Alarm only works in periodic measure mode +humidity1_alarm: alarm flag is set to 1 if the humidity is outside the + configured limits. Alarm only works in periodic measure mode +update_interval: update interval, 0 for single shot, interval in msec + for periodic measurement. If the interval is not supported + by the sensor, the next faster interval is chosen diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index ff940075bb90..e0be99a4615c 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1265,6 +1265,17 @@ config SENSORS_SHT21 This driver can also be built as a module. If so, the module will be called sht21. +config SENSORS_SHT3x + tristate "Sensiron humidity and temperature sensors. SHT3x and compat." + depends on I2C + select CRC8 + help + If you say yes here you get support for the Sensiron SHT30 and SHT31 + humidity and temperature sensors. + + This driver can also be built as a module. If so, the module + will be called sht3x. + config SENSORS_SHTC1 tristate "Sensiron humidity and temperature sensors. SHTC1 and compat." depends on I2C diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 2ef5b7c4c54f..406b18b995b3 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -138,6 +138,7 @@ obj-$(CONFIG_SENSORS_SCH5627) += sch5627.o obj-$(CONFIG_SENSORS_SCH5636) += sch5636.o obj-$(CONFIG_SENSORS_SHT15) += sht15.o obj-$(CONFIG_SENSORS_SHT21) += sht21.o +obj-$(CONFIG_SENSORS_SHT3x) += sht3x.o obj-$(CONFIG_SENSORS_SHTC1) += shtc1.o obj-$(CONFIG_SENSORS_SIS5595) += sis5595.o obj-$(CONFIG_SENSORS_SMM665) += smm665.o diff --git a/drivers/hwmon/sht3x.c b/drivers/hwmon/sht3x.c new file mode 100644 index 000000000000..707a3f85385b --- /dev/null +++ b/drivers/hwmon/sht3x.c @@ -0,0 +1,725 @@ +/* Sensirion SHT3x-DIS humidity and temperature sensor driver. + * The SHT3x comes in many different versions, this driver is for the + * I2C version only. + * + * Copyright (C) 2016 Sensirion AG, Switzerland + * Author: David Frey + * Author: Pascal Sachs + * + * 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. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* commands (high precision mode) */ +static const unsigned char sht3x_cmd_measure_blocking_hpm[] = { 0x2c, 0x06 }; +static const unsigned char sht3x_cmd_measure_nonblocking_hpm[] = { 0x24, 0x00 }; + +/* commands (low power mode) */ +static const unsigned char sht3x_cmd_measure_blocking_lpm[] = { 0x2c, 0x10 }; +static const unsigned char sht3x_cmd_measure_nonblocking_lpm[] = { 0x24, 0x16 }; + +/* commands for periodic mode */ +static const unsigned char sht3x_cmd_measure_periodic_mode[] = { 0xe0, 0x00 }; +static const unsigned char sht3x_cmd_break[] = { 0x30, 0x93 }; + +/* other commands */ +static const unsigned char sht3x_cmd_read_status_reg[] = { 0xf3, 0x2d }; +static const unsigned char sht3x_cmd_clear_status_reg[] = { 0x30, 0x41 }; + +/* delays for non-blocking i2c commands, both in us */ +#define SHT3X_NONBLOCKING_WAIT_TIME_HPM 15000 +#define SHT3X_NONBLOCKING_WAIT_TIME_LPM 4000 + +#define SHT3X_WORD_LEN 2 +#define SHT3X_CMD_LENGTH 2 +#define SHT3X_CRC8_LEN 1 +#define SHT3X_RESPONSE_LENGTH 6 +#define SHT3X_CRC8_POLYNOMIAL 0x31 +#define SHT3X_CRC8_INIT 0xFF +#define SHT3X_MIN_TEMPERATURE -45000 +#define SHT3X_MAX_TEMPERATURE 130000 +#define SHT3X_MIN_HUMIDITY 0 +#define SHT3X_MAX_HUMIDITY 100000 + +enum sht3x_chips { + sht3x, + sts3x, +}; + +enum sht3x_limits { + limit_max = 0, + limit_max_hyst, + limit_min, + limit_min_hyst, +}; + +DECLARE_CRC8_TABLE(sht3x_crc8_table); + +/* periodic measure commands (high precision mode) */ +static const char periodic_measure_commands_hpm[][SHT3X_CMD_LENGTH] = { + /* 0.5 measurements per second */ + {0x20, 0x32}, + /* 1 measurements per second */ + {0x21, 0x30}, + /* 2 measurements per second */ + {0x22, 0x36}, + /* 4 measurements per second */ + {0x23, 0x34}, + /* 10 measurements per second */ + {0x27, 0x37}, +}; + +/* periodic measure commands (low power mode) */ +static const char periodic_measure_commands_lpm[][SHT3X_CMD_LENGTH] = { + /* 0.5 measurements per second */ + {0x20, 0x2f}, + /* 1 measurements per second */ + {0x21, 0x2d}, + /* 2 measurements per second */ + {0x22, 0x2b}, + /* 4 measurements per second */ + {0x23, 0x29}, + /* 10 measurements per second */ + {0x27, 0x2a}, +}; + +struct sht3x_limit_commands { + const char read_command[SHT3X_CMD_LENGTH]; + const char write_command[SHT3X_CMD_LENGTH]; +}; + +static const struct sht3x_limit_commands limit_commands[] = { + /* temp1_max, humidity1_max */ + [limit_max] = { {0xe1, 0x1f}, {0x61, 0x1d} }, + /* temp_1_max_hyst, humidity1_max_hyst */ + [limit_max_hyst] = { {0xe1, 0x14}, {0x61, 0x16} }, + /* temp1_min, humidity1_min */ + [limit_min] = { {0xe1, 0x02}, {0x61, 0x00} }, + /* temp_1_min_hyst, humidity1_min_hyst */ + [limit_min_hyst] = { {0xe1, 0x09}, {0x61, 0x0B} }, +}; + +#define SHT3X_NUM_LIMIT_CMD ARRAY_SIZE(limit_commands) + +static const u16 mode_to_update_interval[] = { + 0, + 2000, + 1000, + 500, + 250, + 100, +}; + +struct sht3x_data { + struct i2c_client *client; + struct mutex i2c_lock; /* lock for sending i2c commands */ + struct mutex data_lock; /* lock for updating driver data */ + + u8 mode; + const unsigned char *command; + u32 wait_time; /* in us*/ + unsigned long last_update; /* last update in periodic mode*/ + + struct sht3x_platform_data setup; + + /* + * cached values for temperature and humidity and limits + * the limits arrays have the following order: + * max, max_hyst, min, min_hyst + */ + int temperature; + int temperature_limits[SHT3X_NUM_LIMIT_CMD]; + u32 humidity; + u32 humidity_limits[SHT3X_NUM_LIMIT_CMD]; +}; + +static u8 get_mode_from_update_interval(u16 value) +{ + size_t index; + u8 number_of_modes = ARRAY_SIZE(mode_to_update_interval); + + if (value == 0) + return 0; + + /* find next faster update interval */ + for (index = 1; index < number_of_modes; index++) { + if (mode_to_update_interval[index] <= value) + return index; + } + + return number_of_modes - 1; +} + +static int sht3x_read_from_command(struct i2c_client *client, + struct sht3x_data *data, + const char *command, + char *buf, int length, u32 wait_time) +{ + int ret; + + mutex_lock(&data->i2c_lock); + ret = i2c_master_send(client, command, SHT3X_CMD_LENGTH); + + if (ret != SHT3X_CMD_LENGTH) { + ret = ret < 0 ? ret : -EIO; + goto out; + } + + if (wait_time) + usleep_range(wait_time, wait_time + 1000); + + ret = i2c_master_recv(client, buf, length); + if (ret != length) { + ret = ret < 0 ? ret : -EIO; + goto out; + } + + ret = 0; +out: + mutex_unlock(&data->i2c_lock); + return ret; +} + +static int sht3x_extract_temperature(u16 raw) +{ + /* + * From datasheet: + * T = -45 + 175 * ST / 2^16 + * Adapted for integer fixed point (3 digit) arithmetic. + */ + return ((21875 * (int)raw) >> 13) - 45000; +} + +static u32 sht3x_extract_humidity(u16 raw) +{ + /* + * From datasheet: + * RH = 100 * SRH / 2^16 + * Adapted for integer fixed point (3 digit) arithmetic. + */ + return (12500 * (u32)raw) >> 13; +} + +static struct sht3x_data *sht3x_update_client(struct device *dev) +{ + struct sht3x_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + u16 interval_ms = mode_to_update_interval[data->mode]; + unsigned long interval_jiffies = msecs_to_jiffies(interval_ms); + unsigned char buf[SHT3X_RESPONSE_LENGTH]; + u16 val; + int ret = 0; + + mutex_lock(&data->data_lock); + /* + * Only update cached readings once per update interval in periodic + * mode. In single shot mode the sensor measures values on demand, so + * every time the sysfs interface is called, a measurement is triggered. + * In periodic mode however, the measurement process is handled + * internally by the sensor and reading out sensor values only makes + * sense if a new reading is available. + */ + if (time_after(jiffies, data->last_update + interval_jiffies)) { + ret = sht3x_read_from_command(client, data, data->command, buf, + sizeof(buf), data->wait_time); + if (ret) + goto out; + + val = be16_to_cpup((__be16 *)buf); + data->temperature = sht3x_extract_temperature(val); + val = be16_to_cpup((__be16 *)(buf + 3)); + data->humidity = sht3x_extract_humidity(val); + data->last_update = jiffies; + } + +out: + mutex_unlock(&data->data_lock); + if (ret) + return ERR_PTR(ret); + + return data; +} + +/* sysfs attributes */ +static ssize_t temp1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct sht3x_data *data = sht3x_update_client(dev); + + if (IS_ERR(data)) + return PTR_ERR(data); + + return sprintf(buf, "%d\n", data->temperature); +} + +static ssize_t humidity1_input_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct sht3x_data *data = sht3x_update_client(dev); + + if (IS_ERR(data)) + return PTR_ERR(data); + + return sprintf(buf, "%u\n", data->humidity); +} + +/* + * limits_update must only be called from probe or with data_lock held + */ +static int limits_update(struct sht3x_data *data) +{ + int ret; + u8 index; + int temperature; + u32 humidity; + u16 raw; + char buffer[SHT3X_RESPONSE_LENGTH]; + const struct sht3x_limit_commands *commands; + struct i2c_client *client = data->client; + + for (index = 0; index < SHT3X_NUM_LIMIT_CMD; index++) { + commands = &limit_commands[index]; + ret = sht3x_read_from_command(client, data, + commands->read_command, buffer, + SHT3X_RESPONSE_LENGTH, 0); + + if (ret) + return ret; + + raw = be16_to_cpup((__be16 *)buffer); + temperature = sht3x_extract_temperature((raw & 0x01ff) << 7); + humidity = sht3x_extract_humidity(raw & 0xfe00); + data->temperature_limits[index] = temperature; + data->humidity_limits[index] = humidity; + } + + return ret; +} + +static ssize_t temp1_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct sht3x_data *data = dev_get_drvdata(dev); + u8 index = to_sensor_dev_attr(attr)->index; + int temperature_limit = data->temperature_limits[index]; + + return scnprintf(buf, PAGE_SIZE, "%d\n", temperature_limit); +} + +static ssize_t humidity1_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct sht3x_data *data = dev_get_drvdata(dev); + u8 index = to_sensor_dev_attr(attr)->index; + u32 humidity_limit = data->humidity_limits[index]; + + return scnprintf(buf, PAGE_SIZE, "%u\n", humidity_limit); +} + +/* + * limit_store must only be called with data_lock held + */ +static size_t limit_store(struct device *dev, + size_t count, + u8 index, + int temperature, + u32 humidity) +{ + char buffer[SHT3X_CMD_LENGTH + SHT3X_WORD_LEN + SHT3X_CRC8_LEN]; + char *position = buffer; + int ret; + u16 raw; + struct sht3x_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + const struct sht3x_limit_commands *commands; + + commands = &limit_commands[index]; + + memcpy(position, commands->write_command, SHT3X_CMD_LENGTH); + position += SHT3X_CMD_LENGTH; + /* + * ST = (T + 45) / 175 * 2^16 + * SRH = RH / 100 * 2^16 + * adapted for fixed point arithmetic and packed the same as + * in limit_show() + */ + raw = ((u32)(temperature + 45000) * 24543) >> (16 + 7); + raw |= ((humidity * 42950) >> 16) & 0xfe00; + + *((__be16 *)position) = cpu_to_be16(raw); + position += SHT3X_WORD_LEN; + *position = crc8(sht3x_crc8_table, + position - SHT3X_WORD_LEN, + SHT3X_WORD_LEN, + SHT3X_CRC8_INIT); + + mutex_lock(&data->i2c_lock); + ret = i2c_master_send(client, buffer, sizeof(buffer)); + mutex_unlock(&data->i2c_lock); + + if (ret != sizeof(buffer)) + return ret < 0 ? ret : -EIO; + + data->temperature_limits[index] = temperature; + data->humidity_limits[index] = humidity; + return count; +} + +static ssize_t temp1_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + int temperature; + int ret; + struct sht3x_data *data = dev_get_drvdata(dev); + u8 index = to_sensor_dev_attr(attr)->index; + + ret = kstrtoint(buf, 0, &temperature); + if (ret) + return ret; + + temperature = clamp_val(temperature, SHT3X_MIN_TEMPERATURE, + SHT3X_MAX_TEMPERATURE); + mutex_lock(&data->data_lock); + ret = limit_store(dev, count, index, temperature, + data->humidity_limits[index]); + mutex_unlock(&data->data_lock); + + return ret; +} + +static ssize_t humidity1_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + u32 humidity; + int ret; + struct sht3x_data *data = dev_get_drvdata(dev); + u8 index = to_sensor_dev_attr(attr)->index; + + ret = kstrtou32(buf, 0, &humidity); + if (ret) + return ret; + + humidity = clamp_val(humidity, SHT3X_MIN_HUMIDITY, SHT3X_MAX_HUMIDITY); + mutex_lock(&data->data_lock); + ret = limit_store(dev, count, index, data->temperature_limits[index], + humidity); + mutex_unlock(&data->data_lock); + + return ret; +} + +static void sht3x_select_command(struct sht3x_data *data) +{ + /* + * In blocking mode (clock stretching mode) the I2C bus + * is blocked for other traffic, thus the call to i2c_master_recv() + * will wait until the data is ready. For non blocking mode, we + * have to wait ourselves. + */ + if (data->mode > 0) { + data->command = sht3x_cmd_measure_periodic_mode; + data->wait_time = 0; + } else if (data->setup.blocking_io) { + data->command = data->setup.high_precision ? + sht3x_cmd_measure_blocking_hpm : + sht3x_cmd_measure_blocking_lpm; + data->wait_time = 0; + } else { + if (data->setup.high_precision) { + data->command = sht3x_cmd_measure_nonblocking_hpm; + data->wait_time = SHT3X_NONBLOCKING_WAIT_TIME_HPM; + } else { + data->command = sht3x_cmd_measure_nonblocking_lpm; + data->wait_time = SHT3X_NONBLOCKING_WAIT_TIME_LPM; + } + } +} + +static int status_register_read(struct device *dev, + struct device_attribute *attr, + char *buffer, int length) +{ + int ret; + struct sht3x_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + + ret = sht3x_read_from_command(client, data, sht3x_cmd_read_status_reg, + buffer, length, 0); + + return ret; +} + +static ssize_t temp1_alarm_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + char buffer[SHT3X_WORD_LEN + SHT3X_CRC8_LEN]; + int ret; + + ret = status_register_read(dev, attr, buffer, + SHT3X_WORD_LEN + SHT3X_CRC8_LEN); + if (ret) + return ret; + + return scnprintf(buf, PAGE_SIZE, "%d\n", !!(buffer[0] & 0x04)); +} + +static ssize_t humidity1_alarm_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + char buffer[SHT3X_WORD_LEN + SHT3X_CRC8_LEN]; + int ret; + + ret = status_register_read(dev, attr, buffer, + SHT3X_WORD_LEN + SHT3X_CRC8_LEN); + if (ret) + return ret; + + return scnprintf(buf, PAGE_SIZE, "%d\n", !!(buffer[0] & 0x08)); +} + +static ssize_t update_interval_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct sht3x_data *data = dev_get_drvdata(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", + mode_to_update_interval[data->mode]); +} + +static ssize_t update_interval_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + u16 update_interval; + u8 mode; + int ret; + const char *command; + struct sht3x_data *data = dev_get_drvdata(dev); + struct i2c_client *client = data->client; + + ret = kstrtou16(buf, 0, &update_interval); + if (ret) + return ret; + + mode = get_mode_from_update_interval(update_interval); + + mutex_lock(&data->data_lock); + /* mode did not change */ + if (mode == data->mode) { + mutex_unlock(&data->data_lock); + return count; + } + + mutex_lock(&data->i2c_lock); + /* + * Abort periodic measure mode. + * To do any changes to the configuration while in periodic mode, we + * have to send a break command to the sensor, which then falls back + * to single shot (mode = 0). + */ + if (data->mode > 0) { + ret = i2c_master_send(client, sht3x_cmd_break, + SHT3X_CMD_LENGTH); + if (ret != SHT3X_CMD_LENGTH) + goto out; + data->mode = 0; + } + + if (mode > 0) { + if (data->setup.high_precision) + command = periodic_measure_commands_hpm[mode - 1]; + else + command = periodic_measure_commands_lpm[mode - 1]; + + /* select mode */ + ret = i2c_master_send(client, command, SHT3X_CMD_LENGTH); + if (ret != SHT3X_CMD_LENGTH) + goto out; + } + + /* select mode and command */ + data->mode = mode; + sht3x_select_command(data); + +out: + mutex_unlock(&data->i2c_lock); + mutex_unlock(&data->data_lock); + if (ret != SHT3X_CMD_LENGTH) + return ret < 0 ? ret : -EIO; + + return count; +} + +static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, temp1_input_show, NULL, 0); +static SENSOR_DEVICE_ATTR(humidity1_input, S_IRUGO, humidity1_input_show, + NULL, 0); +static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, + temp1_limit_show, temp1_limit_store, + limit_max); +static SENSOR_DEVICE_ATTR(humidity1_max, S_IRUGO | S_IWUSR, + humidity1_limit_show, humidity1_limit_store, + limit_max); +static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, + temp1_limit_show, temp1_limit_store, + limit_max_hyst); +static SENSOR_DEVICE_ATTR(humidity1_max_hyst, S_IRUGO | S_IWUSR, + humidity1_limit_show, humidity1_limit_store, + limit_max_hyst); +static SENSOR_DEVICE_ATTR(temp1_min, S_IRUGO | S_IWUSR, + temp1_limit_show, temp1_limit_store, + limit_min); +static SENSOR_DEVICE_ATTR(humidity1_min, S_IRUGO | S_IWUSR, + humidity1_limit_show, humidity1_limit_store, + limit_min); +static SENSOR_DEVICE_ATTR(temp1_min_hyst, S_IRUGO | S_IWUSR, + temp1_limit_show, temp1_limit_store, + limit_min_hyst); +static SENSOR_DEVICE_ATTR(humidity1_min_hyst, S_IRUGO | S_IWUSR, + humidity1_limit_show, humidity1_limit_store, + limit_min_hyst); +static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, temp1_alarm_show, NULL, 0); +static SENSOR_DEVICE_ATTR(humidity1_alarm, S_IRUGO, humidity1_alarm_show, + NULL, 0); +static SENSOR_DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, + update_interval_show, update_interval_store, 0); + +static struct attribute *sht3x_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_humidity1_input.dev_attr.attr, + &sensor_dev_attr_temp1_max.dev_attr.attr, + &sensor_dev_attr_temp1_max_hyst.dev_attr.attr, + &sensor_dev_attr_humidity1_max.dev_attr.attr, + &sensor_dev_attr_humidity1_max_hyst.dev_attr.attr, + &sensor_dev_attr_temp1_min.dev_attr.attr, + &sensor_dev_attr_temp1_min_hyst.dev_attr.attr, + &sensor_dev_attr_humidity1_min.dev_attr.attr, + &sensor_dev_attr_humidity1_min_hyst.dev_attr.attr, + &sensor_dev_attr_temp1_alarm.dev_attr.attr, + &sensor_dev_attr_humidity1_alarm.dev_attr.attr, + &sensor_dev_attr_update_interval.dev_attr.attr, + NULL +}; + +static struct attribute *sts3x_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + NULL +}; + +ATTRIBUTE_GROUPS(sht3x); +ATTRIBUTE_GROUPS(sts3x); + +static int sht3x_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + int ret; + struct sht3x_data *data; + struct device *hwmon_dev; + struct i2c_adapter *adap = client->adapter; + struct device *dev = &client->dev; + const struct attribute_group **attribute_groups; + + /* + * we require full i2c support since the sht3x uses multi-byte read and + * writes as well as multi-byte commands which are not supported by + * the smbus protocol + */ + if (!i2c_check_functionality(adap, I2C_FUNC_I2C)) + return -ENODEV; + + ret = i2c_master_send(client, sht3x_cmd_clear_status_reg, + SHT3X_CMD_LENGTH); + if (ret != SHT3X_CMD_LENGTH) + return ret < 0 ? ret : -ENODEV; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->setup.blocking_io = false; + data->setup.high_precision = true; + data->mode = 0; + data->last_update = 0; + data->client = client; + crc8_populate_msb(sht3x_crc8_table, SHT3X_CRC8_POLYNOMIAL); + + if (client->dev.platform_data) + data->setup = *(struct sht3x_platform_data *)dev->platform_data; + + sht3x_select_command(data); + + mutex_init(&data->i2c_lock); + mutex_init(&data->data_lock); + + ret = limits_update(data); + if (ret) + return ret; + + if (id->driver_data == sts3x) + attribute_groups = sts3x_groups; + else + attribute_groups = sht3x_groups; + + hwmon_dev = devm_hwmon_device_register_with_groups(dev, + client->name, + data, + attribute_groups); + + if (IS_ERR(hwmon_dev)) + dev_dbg(dev, "unable to register hwmon device\n"); + + return PTR_ERR_OR_ZERO(hwmon_dev); +} + +/* device ID table */ +static const struct i2c_device_id sht3x_ids[] = { + {"sht3x", sht3x}, + {"sts3x", sts3x}, + {} +}; + +MODULE_DEVICE_TABLE(i2c, sht3x_ids); + +static struct i2c_driver sht3x_i2c_driver = { + .driver.name = "sht3x", + .probe = sht3x_probe, + .id_table = sht3x_ids, +}; + +module_i2c_driver(sht3x_i2c_driver); + +MODULE_AUTHOR("David Frey "); +MODULE_AUTHOR("Pascal Sachs "); +MODULE_DESCRIPTION("Sensirion SHT3x humidity and temperature sensor driver"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/platform_data/sht3x.h b/include/linux/platform_data/sht3x.h new file mode 100644 index 000000000000..2e5eea358194 --- /dev/null +++ b/include/linux/platform_data/sht3x.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2016 Sensirion AG, Switzerland + * Author: David Frey + * Author: Pascal Sachs + * + * 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 __SHT3X_H_ +#define __SHT3X_H_ + +struct sht3x_platform_data { + bool blocking_io; + bool high_precision; +}; +#endif /* __SHT3X_H_ */ -- cgit v1.2.3 From c35d9292fee0474a1a037f75b0b85af32200c76f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 18 Apr 2016 23:06:48 +0200 Subject: of: Add a new macro to declare_of for one parameter function returning a value The macro OF_DECLARE_1 expect a void (*func)(struct device_node *) while the OF_DECLARE_2 expect a int (*func)(struct device_node *, struct device_node *). The second one allows to pass an init function returning a value, which make possible to call the functions in the table and check the return value in order to catch at a higher level the errors and handle them from there instead of doing a panic in each driver (well at least this is the case for the clkevt). Unfortunately the OF_DECLARE_1 does not allow that and that lead to some code duplication and crappyness in the drivers. The OF_DECLARE_1 is used by all the clk drivers and the clocksource/clockevent drivers. It is not possible to do the change in one shot as we have to change all the init functions. The OF_DECLARE_2 specifies an init function prototype with two parameters with the node and its parent. The latter won't be used, ever, in the timer drivers. Introduce a OF_DECLARE_1_RET macro to be used, and hopefully we can smoothly and iteratively change the users of OF_DECLARE_1 to use the new macro instead. Signed-off-by: Daniel Lezcano Acked-by: Rob Herring --- include/linux/of.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index c7292e8ea080..552943d37f40 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -1009,10 +1009,13 @@ static inline int of_get_available_child_count(const struct device_node *np) #endif typedef int (*of_init_fn_2)(struct device_node *, struct device_node *); +typedef int (*of_init_fn_1_ret)(struct device_node *); typedef void (*of_init_fn_1)(struct device_node *); #define OF_DECLARE_1(table, name, compat, fn) \ _OF_DECLARE(table, name, compat, fn, of_init_fn_1) +#define OF_DECLARE_1_RET(table, name, compat, fn) \ + _OF_DECLARE(table, name, compat, fn, of_init_fn_1_ret) #define OF_DECLARE_2(table, name, compat, fn) \ _OF_DECLARE(table, name, compat, fn, of_init_fn_2) -- cgit v1.2.3 From b7c4db861683af5fc50ac3cb3751cf847d765211 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 31 May 2016 16:25:59 +0200 Subject: clocksource/drivers/clksrc-probe: Introduce init functions with return code Currently, the clksrc-probe is not able to handle any error from the init functions. There are different issues with the current code: - the code is duplicated in the init functions by writing error - every driver tends to panic in its own init function - counting the number of clocksources is not reliable This patch adds another table to store the functions returning an error. The table is temporary while we convert all the drivers to return an error and will disappear. Signed-off-by: Daniel Lezcano --- drivers/clocksource/clksrc-probe.c | 22 ++++++++++++++++++++++ include/asm-generic/vmlinux.lds.h | 2 ++ include/linux/clocksource.h | 3 +++ 3 files changed, 27 insertions(+) (limited to 'include') diff --git a/drivers/clocksource/clksrc-probe.c b/drivers/clocksource/clksrc-probe.c index 7cb6c923a836..5fa6a555b35c 100644 --- a/drivers/clocksource/clksrc-probe.c +++ b/drivers/clocksource/clksrc-probe.c @@ -20,16 +20,22 @@ #include extern struct of_device_id __clksrc_of_table[]; +extern struct of_device_id __clksrc_ret_of_table[]; static const struct of_device_id __clksrc_of_table_sentinel __used __section(__clksrc_of_table_end); +static const struct of_device_id __clksrc_ret_of_table_sentinel + __used __section(__clksrc_ret_of_table_end); + void __init clocksource_probe(void) { struct device_node *np; const struct of_device_id *match; of_init_fn_1 init_func; + of_init_fn_1_ret init_func_ret; unsigned clocksources = 0; + int ret; for_each_matching_node_and_match(np, __clksrc_of_table, &match) { if (!of_device_is_available(np)) @@ -40,6 +46,22 @@ void __init clocksource_probe(void) clocksources++; } + for_each_matching_node_and_match(np, __clksrc_ret_of_table, &match) { + if (!of_device_is_available(np)) + continue; + + init_func_ret = match->data; + + ret = init_func_ret(np); + if (ret) { + pr_err("Failed to initialize '%s': %d", + of_node_full_name(np), ret); + continue; + } + + clocksources++; + } + clocksources += acpi_probe_device_table(clksrc); if (!clocksources) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab94b553..8c6c626285c0 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -173,6 +173,7 @@ *(__##name##_of_table_end) #define CLKSRC_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc) +#define CLKSRC_RET_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc_ret) #define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip) #define CLK_OF_TABLES() OF_TABLE(CONFIG_COMMON_CLK, clk) #define IOMMU_OF_TABLES() OF_TABLE(CONFIG_OF_IOMMU, iommu) @@ -531,6 +532,7 @@ CLK_OF_TABLES() \ RESERVEDMEM_OF_TABLES() \ CLKSRC_OF_TABLES() \ + CLKSRC_RET_OF_TABLES() \ IOMMU_OF_TABLES() \ CPU_METHOD_OF_TABLES() \ CPUIDLE_METHOD_OF_TABLES() \ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 44a1aff22566..15c3839850f4 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -246,6 +246,9 @@ extern int clocksource_i8253_init(void); #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ OF_DECLARE_1(clksrc, name, compat, fn) +#define CLOCKSOURCE_OF_DECLARE_RET(name, compat, fn) \ + OF_DECLARE_1_RET(clksrc_ret, name, compat, fn) + #ifdef CONFIG_CLKSRC_PROBE extern void clocksource_probe(void); #else -- cgit v1.2.3 From 2ef2538bc613af45baf9f2a032c9a8259c4c6672 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 6 Jun 2016 23:28:01 +0200 Subject: clocksource/drivers/sp804: Convert init function to return error The init functions do not return any error. They behave as the following: - panic, thus leading to a kernel crash while another timer may work and make the system boot up correctly or - print an error and let the caller unaware if the state of the system Change that by converting the init functions to return an error conforming to the CLOCKSOURCE_OF_RET prototype. Proper error handling (rollback, errno value) will be changed later case by case, thus this change just return back an error or success in the init function. Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-sp804.c | 90 +++++++++++++++++++++++++-------------- include/clocksource/timer-sp804.h | 8 ++-- 2 files changed, 63 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c index 5f45b9adef60..3dc47efc9298 100644 --- a/drivers/clocksource/timer-sp804.c +++ b/drivers/clocksource/timer-sp804.c @@ -77,7 +77,7 @@ void __init sp804_timer_disable(void __iomem *base) writel(0, base + TIMER_CTRL); } -void __init __sp804_clocksource_and_sched_clock_init(void __iomem *base, +int __init __sp804_clocksource_and_sched_clock_init(void __iomem *base, const char *name, struct clk *clk, int use_sched_clock) @@ -89,14 +89,13 @@ void __init __sp804_clocksource_and_sched_clock_init(void __iomem *base, if (IS_ERR(clk)) { pr_err("sp804: clock not found: %d\n", (int)PTR_ERR(clk)); - return; + return PTR_ERR(clk); } } rate = sp804_get_clock_rate(clk); - if (rate < 0) - return; + return -EINVAL; /* setup timer 0 as free-running clocksource */ writel(0, base + TIMER_CTRL); @@ -112,6 +111,8 @@ void __init __sp804_clocksource_and_sched_clock_init(void __iomem *base, sched_clock_base = base; sched_clock_register(sp804_read, 32, rate); } + + return 0; } @@ -186,7 +187,7 @@ static struct irqaction sp804_timer_irq = { .dev_id = &sp804_clockevent, }; -void __init __sp804_clockevents_init(void __iomem *base, unsigned int irq, struct clk *clk, const char *name) +int __init __sp804_clockevents_init(void __iomem *base, unsigned int irq, struct clk *clk, const char *name) { struct clock_event_device *evt = &sp804_clockevent; long rate; @@ -196,12 +197,12 @@ void __init __sp804_clockevents_init(void __iomem *base, unsigned int irq, struc if (IS_ERR(clk)) { pr_err("sp804: %s clock not found: %d\n", name, (int)PTR_ERR(clk)); - return; + return PTR_ERR(clk); } rate = sp804_get_clock_rate(clk); if (rate < 0) - return; + return -EINVAL; clkevt_base = base; clkevt_reload = DIV_ROUND_CLOSEST(rate, HZ); @@ -213,27 +214,31 @@ void __init __sp804_clockevents_init(void __iomem *base, unsigned int irq, struc setup_irq(irq, &sp804_timer_irq); clockevents_config_and_register(evt, rate, 0xf, 0xffffffff); + + return 0; } -static void __init sp804_of_init(struct device_node *np) +static int __init sp804_of_init(struct device_node *np) { static bool initialized = false; void __iomem *base; - int irq; + int irq, ret = -EINVAL; u32 irq_num = 0; struct clk *clk1, *clk2; const char *name = of_get_property(np, "compatible", NULL); base = of_iomap(np, 0); - if (WARN_ON(!base)) - return; + if (!base) + return -ENXIO; /* Ensure timers are disabled */ writel(0, base + TIMER_CTRL); writel(0, base + TIMER_2_BASE + TIMER_CTRL); - if (initialized || !of_device_is_available(np)) + if (initialized || !of_device_is_available(np)) { + ret = -EINVAL; goto err; + } clk1 = of_clk_get(np, 0); if (IS_ERR(clk1)) @@ -256,35 +261,53 @@ static void __init sp804_of_init(struct device_node *np) of_property_read_u32(np, "arm,sp804-has-irq", &irq_num); if (irq_num == 2) { - __sp804_clockevents_init(base + TIMER_2_BASE, irq, clk2, name); - __sp804_clocksource_and_sched_clock_init(base, name, clk1, 1); + + ret = __sp804_clockevents_init(base + TIMER_2_BASE, irq, clk2, name); + if (ret) + goto err; + + ret = __sp804_clocksource_and_sched_clock_init(base, name, clk1, 1); + if (ret) + goto err; } else { - __sp804_clockevents_init(base, irq, clk1 , name); - __sp804_clocksource_and_sched_clock_init(base + TIMER_2_BASE, - name, clk2, 1); + + ret = __sp804_clockevents_init(base, irq, clk1 , name); + if (ret) + goto err; + + ret =__sp804_clocksource_and_sched_clock_init(base + TIMER_2_BASE, + name, clk2, 1); + if (ret) + goto err; } initialized = true; - return; + return 0; err: iounmap(base); + return ret; } -CLOCKSOURCE_OF_DECLARE(sp804, "arm,sp804", sp804_of_init); +CLOCKSOURCE_OF_DECLARE_RET(sp804, "arm,sp804", sp804_of_init); -static void __init integrator_cp_of_init(struct device_node *np) +static int __init integrator_cp_of_init(struct device_node *np) { static int init_count = 0; void __iomem *base; - int irq; + int irq, ret = -EINVAL; const char *name = of_get_property(np, "compatible", NULL); struct clk *clk; base = of_iomap(np, 0); - if (WARN_ON(!base)) - return; + if (!base) { + pr_err("Failed to iomap"); + return -ENXIO; + } + clk = of_clk_get(np, 0); - if (WARN_ON(IS_ERR(clk))) - return; + if (IS_ERR(clk)) { + pr_err("Failed to get clock"); + return PTR_ERR(clk); + } /* Ensure timer is disabled */ writel(0, base + TIMER_CTRL); @@ -292,19 +315,24 @@ static void __init integrator_cp_of_init(struct device_node *np) if (init_count == 2 || !of_device_is_available(np)) goto err; - if (!init_count) - __sp804_clocksource_and_sched_clock_init(base, name, clk, 0); - else { + if (!init_count) { + ret = __sp804_clocksource_and_sched_clock_init(base, name, clk, 0); + if (ret) + goto err; + } else { irq = irq_of_parse_and_map(np, 0); if (irq <= 0) goto err; - __sp804_clockevents_init(base, irq, clk, name); + ret = __sp804_clockevents_init(base, irq, clk, name); + if (ret) + goto err; } init_count++; - return; + return 0; err: iounmap(base); + return ret; } -CLOCKSOURCE_OF_DECLARE(intcp, "arm,integrator-cp-timer", integrator_cp_of_init); +CLOCKSOURCE_OF_DECLARE_RET(intcp, "arm,integrator-cp-timer", integrator_cp_of_init); diff --git a/include/clocksource/timer-sp804.h b/include/clocksource/timer-sp804.h index 1f8a1caa7cb4..7654d71243dd 100644 --- a/include/clocksource/timer-sp804.h +++ b/include/clocksource/timer-sp804.h @@ -3,10 +3,10 @@ struct clk; -void __sp804_clocksource_and_sched_clock_init(void __iomem *, - const char *, struct clk *, int); -void __sp804_clockevents_init(void __iomem *, unsigned int, - struct clk *, const char *); +int __sp804_clocksource_and_sched_clock_init(void __iomem *, + const char *, struct clk *, int); +int __sp804_clockevents_init(void __iomem *, unsigned int, + struct clk *, const char *); void sp804_timer_disable(void __iomem *); static inline void sp804_clocksource_init(void __iomem *base, const char *name) -- cgit v1.2.3 From 177cf6e52b0a1a382b9892d3cc9aafd6e7c5943f Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 7 Jun 2016 00:27:44 +0200 Subject: clocksources: Switch back to the clksrc table All the clocksource drivers's init function are now converted to return an error code. CLOCKSOURCE_OF_DECLARE is no longer used as well as the clksrc-of table. Let's convert back the names: - CLOCKSOURCE_OF_DECLARE_RET => CLOCKSOURCE_OF_DECLARE - clksrc-of-ret => clksrc-of Signed-off-by: Daniel Lezcano For exynos_mct and samsung_pwm_timer: Acked-by: Krzysztof Kozlowski For arch/arc: Acked-by: Vineet Gupta For mediatek driver: Acked-by: Matthias Brugger For the Rockchip-part Acked-by: Heiko Stuebner For STi : Acked-by: Patrice Chotard For the mps2-timer.c and versatile.c changes: Acked-by: Liviu Dudau For the OXNAS part : Acked-by: Neil Armstrong For LPC32xx driver: Acked-by: Sylvain Lemieux For Broadcom Kona timer change: Acked-by: Ray Jui For Sun4i and Sun5i: Acked-by: Chen-Yu Tsai For Meson6: Acked-by: Carlo Caione For Keystone: Acked-by: Santosh Shilimkar For NPS: Acked-by: Noam Camus For bcm2835: Acked-by: Eric Anholt --- arch/arc/kernel/time.c | 6 +++--- arch/arm/kernel/smp_twd.c | 6 +++--- arch/microblaze/kernel/timer.c | 2 +- arch/mips/ralink/cevt-rt3352.c | 2 +- arch/nios2/kernel/time.c | 2 +- drivers/clocksource/arm_arch_timer.c | 6 +++--- drivers/clocksource/arm_global_timer.c | 2 +- drivers/clocksource/armv7m_systick.c | 2 +- drivers/clocksource/asm9260_timer.c | 2 +- drivers/clocksource/bcm2835_timer.c | 2 +- drivers/clocksource/bcm_kona_timer.c | 4 ++-- drivers/clocksource/cadence_ttc_timer.c | 2 +- drivers/clocksource/clksrc-dbx500-prcmu.c | 2 +- drivers/clocksource/clksrc-probe.c | 14 -------------- drivers/clocksource/clksrc_st_lpc.c | 2 +- drivers/clocksource/clps711x-timer.c | 2 +- drivers/clocksource/dw_apb_timer_of.c | 8 ++++---- drivers/clocksource/exynos_mct.c | 4 ++-- drivers/clocksource/fsl_ftm_timer.c | 2 +- drivers/clocksource/h8300_timer16.c | 2 +- drivers/clocksource/h8300_timer8.c | 2 +- drivers/clocksource/h8300_tpu.c | 2 +- drivers/clocksource/meson6_timer.c | 2 +- drivers/clocksource/mips-gic-timer.c | 2 +- drivers/clocksource/moxart_timer.c | 2 +- drivers/clocksource/mps2-timer.c | 2 +- drivers/clocksource/mtk_timer.c | 2 +- drivers/clocksource/mxs_timer.c | 2 +- drivers/clocksource/nomadik-mtu.c | 2 +- drivers/clocksource/pxa_timer.c | 2 +- drivers/clocksource/qcom-timer.c | 4 ++-- drivers/clocksource/rockchip_timer.c | 8 ++++---- drivers/clocksource/samsung_pwm_timer.c | 8 ++++---- drivers/clocksource/sun4i_timer.c | 2 +- drivers/clocksource/tango_xtal.c | 2 +- drivers/clocksource/tegra20_timer.c | 4 ++-- drivers/clocksource/time-armada-370-xp.c | 6 +++--- drivers/clocksource/time-efm32.c | 4 ++-- drivers/clocksource/time-lpc32xx.c | 2 +- drivers/clocksource/time-orion.c | 2 +- drivers/clocksource/time-pistachio.c | 2 +- drivers/clocksource/timer-atlas7.c | 2 +- drivers/clocksource/timer-atmel-pit.c | 2 +- drivers/clocksource/timer-atmel-st.c | 2 +- drivers/clocksource/timer-digicolor.c | 2 +- drivers/clocksource/timer-imx-gpt.c | 24 ++++++++++++------------ drivers/clocksource/timer-integrator-ap.c | 2 +- drivers/clocksource/timer-keystone.c | 2 +- drivers/clocksource/timer-nps.c | 4 ++-- drivers/clocksource/timer-oxnas-rps.c | 4 ++-- drivers/clocksource/timer-prima2.c | 2 +- drivers/clocksource/timer-sp804.c | 4 ++-- drivers/clocksource/timer-stm32.c | 2 +- drivers/clocksource/timer-sun5i.c | 4 ++-- drivers/clocksource/timer-ti-32k.c | 2 +- drivers/clocksource/timer-u300.c | 2 +- drivers/clocksource/versatile.c | 4 ++-- drivers/clocksource/vf_pit_timer.c | 2 +- drivers/clocksource/vt8500_timer.c | 2 +- drivers/clocksource/zevio-timer.c | 2 +- include/asm-generic/vmlinux.lds.h | 2 -- include/linux/clocksource.h | 5 +---- 62 files changed, 98 insertions(+), 117 deletions(-) (limited to 'include') diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c index 09de669f4ff0..98f22d2eb563 100644 --- a/arch/arc/kernel/time.c +++ b/arch/arc/kernel/time.c @@ -130,7 +130,7 @@ static int __init arc_cs_setup_gfrc(struct device_node *node) return clocksource_register_hz(&arc_counter_gfrc, arc_timer_freq); } -CLOCKSOURCE_OF_DECLARE_RET(arc_gfrc, "snps,archs-timer-gfrc", arc_cs_setup_gfrc); +CLOCKSOURCE_OF_DECLARE(arc_gfrc, "snps,archs-timer-gfrc", arc_cs_setup_gfrc); #endif @@ -192,7 +192,7 @@ static int __init arc_cs_setup_rtc(struct device_node *node) return clocksource_register_hz(&arc_counter_rtc, arc_timer_freq); } -CLOCKSOURCE_OF_DECLARE_RET(arc_rtc, "snps,archs-timer-rtc", arc_cs_setup_rtc); +CLOCKSOURCE_OF_DECLARE(arc_rtc, "snps,archs-timer-rtc", arc_cs_setup_rtc); #endif @@ -379,7 +379,7 @@ static int __init arc_of_timer_init(struct device_node *np) return ret; } -CLOCKSOURCE_OF_DECLARE_RET(arc_clkevt, "snps,arc-timer", arc_of_timer_init); +CLOCKSOURCE_OF_DECLARE(arc_clkevt, "snps,arc-timer", arc_of_timer_init); /* * Called from start_kernel() - boot CPU only diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 2b24be41d9cc..b6ec65e68009 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -412,7 +412,7 @@ out: WARN(err, "twd_local_timer_of_register failed (%d)\n", err); return err; } -CLOCKSOURCE_OF_DECLARE_RET(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register); -CLOCKSOURCE_OF_DECLARE_RET(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register); -CLOCKSOURCE_OF_DECLARE_RET(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register); +CLOCKSOURCE_OF_DECLARE(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register); +CLOCKSOURCE_OF_DECLARE(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register); +CLOCKSOURCE_OF_DECLARE(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register); #endif diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c index 7f35e7b50f1b..5bbf38b916ef 100644 --- a/arch/microblaze/kernel/timer.c +++ b/arch/microblaze/kernel/timer.c @@ -332,5 +332,5 @@ static int __init xilinx_timer_init(struct device_node *timer) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(xilinx_timer, "xlnx,xps-timer-1.00.a", +CLOCKSOURCE_OF_DECLARE(xilinx_timer, "xlnx,xps-timer-1.00.a", xilinx_timer_init); diff --git a/arch/mips/ralink/cevt-rt3352.c b/arch/mips/ralink/cevt-rt3352.c index f2d3c7908626..f24eee04e16a 100644 --- a/arch/mips/ralink/cevt-rt3352.c +++ b/arch/mips/ralink/cevt-rt3352.c @@ -150,4 +150,4 @@ static int __init ralink_systick_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(systick, "ralink,cevt-systick", ralink_systick_init); +CLOCKSOURCE_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init); diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c index b75e40e17963..d9563ddb337e 100644 --- a/arch/nios2/kernel/time.c +++ b/arch/nios2/kernel/time.c @@ -352,4 +352,4 @@ void __init time_init(void) clocksource_probe(); } -CLOCKSOURCE_OF_DECLARE_RET(nios2_timer, ALTR_TIMER_COMPATIBLE, nios2_time_init); +CLOCKSOURCE_OF_DECLARE(nios2_timer, ALTR_TIMER_COMPATIBLE, nios2_time_init); diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index d0cda68e2c41..9e33309ad2ea 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -784,8 +784,8 @@ static int __init arch_timer_of_init(struct device_node *np) return arch_timer_init(); } -CLOCKSOURCE_OF_DECLARE_RET(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init); -CLOCKSOURCE_OF_DECLARE_RET(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init); +CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init); +CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init); static int __init arch_timer_mem_init(struct device_node *np) { @@ -868,7 +868,7 @@ out: of_node_put(best_frame); return ret; } -CLOCKSOURCE_OF_DECLARE_RET(armv7_arch_timer_mem, "arm,armv7-timer-mem", +CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem", arch_timer_mem_init); #ifdef CONFIG_ACPI diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 40104fc93f24..2a9ceb6e93f9 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -358,5 +358,5 @@ out_unmap: } /* Only tested on r2p2 and r3p0 */ -CLOCKSOURCE_OF_DECLARE_RET(arm_gt, "arm,cortex-a9-global-timer", +CLOCKSOURCE_OF_DECLARE(arm_gt, "arm,cortex-a9-global-timer", global_timer_of_register); diff --git a/drivers/clocksource/armv7m_systick.c b/drivers/clocksource/armv7m_systick.c index 2b55410edaf6..e93af1f6a36c 100644 --- a/drivers/clocksource/armv7m_systick.c +++ b/drivers/clocksource/armv7m_systick.c @@ -81,5 +81,5 @@ out_unmap: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(arm_systick, "arm,armv7m-systick", +CLOCKSOURCE_OF_DECLARE(arm_systick, "arm,armv7m-systick", system_timer_of_register); diff --git a/drivers/clocksource/asm9260_timer.c b/drivers/clocksource/asm9260_timer.c index d113c0275d06..1ba871b7fe11 100644 --- a/drivers/clocksource/asm9260_timer.c +++ b/drivers/clocksource/asm9260_timer.c @@ -238,5 +238,5 @@ static int __init asm9260_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(asm9260_timer, "alphascale,asm9260-timer", +CLOCKSOURCE_OF_DECLARE(asm9260_timer, "alphascale,asm9260-timer", asm9260_timer_init); diff --git a/drivers/clocksource/bcm2835_timer.c b/drivers/clocksource/bcm2835_timer.c index 2dcf896b5381..e71acf231c89 100644 --- a/drivers/clocksource/bcm2835_timer.c +++ b/drivers/clocksource/bcm2835_timer.c @@ -142,5 +142,5 @@ static int __init bcm2835_timer_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(bcm2835, "brcm,bcm2835-system-timer", +CLOCKSOURCE_OF_DECLARE(bcm2835, "brcm,bcm2835-system-timer", bcm2835_timer_init); diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c index c251aa68993f..86f87be3d80f 100644 --- a/drivers/clocksource/bcm_kona_timer.c +++ b/drivers/clocksource/bcm_kona_timer.c @@ -195,9 +195,9 @@ static int __init kona_timer_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(brcm_kona, "brcm,kona-timer", kona_timer_init); +CLOCKSOURCE_OF_DECLARE(brcm_kona, "brcm,kona-timer", kona_timer_init); /* * bcm,kona-timer is deprecated by brcm,kona-timer * being kept here for driver compatibility */ -CLOCKSOURCE_OF_DECLARE_RET(bcm_kona, "bcm,kona-timer", kona_timer_init); +CLOCKSOURCE_OF_DECLARE(bcm_kona, "bcm,kona-timer", kona_timer_init); diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c index e2e76311dde2..388a77bdc39a 100644 --- a/drivers/clocksource/cadence_ttc_timer.c +++ b/drivers/clocksource/cadence_ttc_timer.c @@ -539,4 +539,4 @@ static int __init ttc_timer_init(struct device_node *timer) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(ttc, "cdns,ttc", ttc_timer_init); +CLOCKSOURCE_OF_DECLARE(ttc, "cdns,ttc", ttc_timer_init); diff --git a/drivers/clocksource/clksrc-dbx500-prcmu.c b/drivers/clocksource/clksrc-dbx500-prcmu.c index 5a59d2953388..77a365f573d7 100644 --- a/drivers/clocksource/clksrc-dbx500-prcmu.c +++ b/drivers/clocksource/clksrc-dbx500-prcmu.c @@ -86,5 +86,5 @@ static int __init clksrc_dbx500_prcmu_init(struct device_node *node) #endif return clocksource_register_hz(&clocksource_dbx500_prcmu, RATE_32K); } -CLOCKSOURCE_OF_DECLARE_RET(dbx500_prcmu, "stericsson,db8500-prcmu-timer-4", +CLOCKSOURCE_OF_DECLARE(dbx500_prcmu, "stericsson,db8500-prcmu-timer-4", clksrc_dbx500_prcmu_init); diff --git a/drivers/clocksource/clksrc-probe.c b/drivers/clocksource/clksrc-probe.c index 5fa6a555b35c..bc62be97f0a8 100644 --- a/drivers/clocksource/clksrc-probe.c +++ b/drivers/clocksource/clksrc-probe.c @@ -20,19 +20,14 @@ #include extern struct of_device_id __clksrc_of_table[]; -extern struct of_device_id __clksrc_ret_of_table[]; static const struct of_device_id __clksrc_of_table_sentinel __used __section(__clksrc_of_table_end); -static const struct of_device_id __clksrc_ret_of_table_sentinel - __used __section(__clksrc_ret_of_table_end); - void __init clocksource_probe(void) { struct device_node *np; const struct of_device_id *match; - of_init_fn_1 init_func; of_init_fn_1_ret init_func_ret; unsigned clocksources = 0; int ret; @@ -41,15 +36,6 @@ void __init clocksource_probe(void) if (!of_device_is_available(np)) continue; - init_func = match->data; - init_func(np); - clocksources++; - } - - for_each_matching_node_and_match(np, __clksrc_ret_of_table, &match) { - if (!of_device_is_available(np)) - continue; - init_func_ret = match->data; ret = init_func_ret(np); diff --git a/drivers/clocksource/clksrc_st_lpc.c b/drivers/clocksource/clksrc_st_lpc.c index c9022a9eb593..03cc49217bb4 100644 --- a/drivers/clocksource/clksrc_st_lpc.c +++ b/drivers/clocksource/clksrc_st_lpc.c @@ -132,4 +132,4 @@ static int __init st_clksrc_of_register(struct device_node *np) return ret; } -CLOCKSOURCE_OF_DECLARE_RET(ddata, "st,stih407-lpc", st_clksrc_of_register); +CLOCKSOURCE_OF_DECLARE(ddata, "st,stih407-lpc", st_clksrc_of_register); diff --git a/drivers/clocksource/clps711x-timer.c b/drivers/clocksource/clps711x-timer.c index 3b6619808442..84aed78261e4 100644 --- a/drivers/clocksource/clps711x-timer.c +++ b/drivers/clocksource/clps711x-timer.c @@ -119,5 +119,5 @@ static int __init clps711x_timer_init(struct device_node *np) return -EINVAL; } } -CLOCKSOURCE_OF_DECLARE_RET(clps711x, "cirrus,clps711x-timer", clps711x_timer_init); +CLOCKSOURCE_OF_DECLARE(clps711x, "cirrus,clps711x-timer", clps711x_timer_init); #endif diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index 4985a2cadad9..aee6c0d39a7c 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -167,7 +167,7 @@ static int __init dw_apb_timer_init(struct device_node *timer) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(pc3x2_timer, "picochip,pc3x2-timer", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer_osc, "snps,dw-apb-timer-osc", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer_sp, "snps,dw-apb-timer-sp", dw_apb_timer_init); +CLOCKSOURCE_OF_DECLARE(apb_timer, "snps,dw-apb-timer", dw_apb_timer_init); diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index f6caed0c36ae..0d18dd4b3bd2 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -627,5 +627,5 @@ static int __init mct_init_ppi(struct device_node *np) { return mct_init_dt(np, MCT_INT_PPI); } -CLOCKSOURCE_OF_DECLARE_RET(exynos4210, "samsung,exynos4210-mct", mct_init_spi); -CLOCKSOURCE_OF_DECLARE_RET(exynos4412, "samsung,exynos4412-mct", mct_init_ppi); +CLOCKSOURCE_OF_DECLARE(exynos4210, "samsung,exynos4210-mct", mct_init_spi); +CLOCKSOURCE_OF_DECLARE(exynos4412, "samsung,exynos4412-mct", mct_init_ppi); diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c index 9ad4ca32fb2d..738515b89073 100644 --- a/drivers/clocksource/fsl_ftm_timer.c +++ b/drivers/clocksource/fsl_ftm_timer.c @@ -369,4 +369,4 @@ err: kfree(priv); return ret; } -CLOCKSOURCE_OF_DECLARE_RET(flextimer, "fsl,ftm-timer", ftm_timer_init); +CLOCKSOURCE_OF_DECLARE(flextimer, "fsl,ftm-timer", ftm_timer_init); diff --git a/drivers/clocksource/h8300_timer16.c b/drivers/clocksource/h8300_timer16.c index 9d99fc85ffad..07d9d5be9054 100644 --- a/drivers/clocksource/h8300_timer16.c +++ b/drivers/clocksource/h8300_timer16.c @@ -187,5 +187,5 @@ free_clk: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(h8300_16bit, "renesas,16bit-timer", +CLOCKSOURCE_OF_DECLARE(h8300_16bit, "renesas,16bit-timer", h8300_16timer_init); diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c index 0292a1907619..546bb180f5a4 100644 --- a/drivers/clocksource/h8300_timer8.c +++ b/drivers/clocksource/h8300_timer8.c @@ -215,4 +215,4 @@ free_clk: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(h8300_8bit, "renesas,8bit-timer", h8300_8timer_init); +CLOCKSOURCE_OF_DECLARE(h8300_8bit, "renesas,8bit-timer", h8300_8timer_init); diff --git a/drivers/clocksource/h8300_tpu.c b/drivers/clocksource/h8300_tpu.c index 4faf718b30f3..7bdf1991c847 100644 --- a/drivers/clocksource/h8300_tpu.c +++ b/drivers/clocksource/h8300_tpu.c @@ -154,4 +154,4 @@ free_clk: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(h8300_tpu, "renesas,tpu", h8300_tpu_init); +CLOCKSOURCE_OF_DECLARE(h8300_tpu, "renesas,tpu", h8300_tpu_init); diff --git a/drivers/clocksource/meson6_timer.c b/drivers/clocksource/meson6_timer.c index 3a6e78f62b19..52af591a9fc7 100644 --- a/drivers/clocksource/meson6_timer.c +++ b/drivers/clocksource/meson6_timer.c @@ -174,5 +174,5 @@ static int __init meson6_timer_init(struct device_node *node) 1, 0xfffe); return 0; } -CLOCKSOURCE_OF_DECLARE_RET(meson6, "amlogic,meson6-timer", +CLOCKSOURCE_OF_DECLARE(meson6, "amlogic,meson6-timer", meson6_timer_init); diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index b164b8712f39..1572c7a778ab 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -222,5 +222,5 @@ static void __init gic_clocksource_of_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(mips_gic_timer, "mti,gic-timer", +CLOCKSOURCE_OF_DECLARE(mips_gic_timer, "mti,gic-timer", gic_clocksource_of_init); diff --git a/drivers/clocksource/moxart_timer.c b/drivers/clocksource/moxart_timer.c index b9c30cd035bf..841454417acd 100644 --- a/drivers/clocksource/moxart_timer.c +++ b/drivers/clocksource/moxart_timer.c @@ -178,4 +178,4 @@ static int __init moxart_timer_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(moxart, "moxa,moxart-timer", moxart_timer_init); +CLOCKSOURCE_OF_DECLARE(moxart, "moxa,moxart-timer", moxart_timer_init); diff --git a/drivers/clocksource/mps2-timer.c b/drivers/clocksource/mps2-timer.c index c303fa9ba87f..3e4431ed9aa9 100644 --- a/drivers/clocksource/mps2-timer.c +++ b/drivers/clocksource/mps2-timer.c @@ -274,4 +274,4 @@ static int __init mps2_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(mps2_timer, "arm,mps2-timer", mps2_timer_init); +CLOCKSOURCE_OF_DECLARE(mps2_timer, "arm,mps2-timer", mps2_timer_init); diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c index 432a2c0884a9..90659493c59c 100644 --- a/drivers/clocksource/mtk_timer.c +++ b/drivers/clocksource/mtk_timer.c @@ -265,4 +265,4 @@ err_kzalloc: return -EINVAL; } -CLOCKSOURCE_OF_DECLARE_RET(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init); +CLOCKSOURCE_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init); diff --git a/drivers/clocksource/mxs_timer.c b/drivers/clocksource/mxs_timer.c index 17b9d1991178..630a8d3904bb 100644 --- a/drivers/clocksource/mxs_timer.c +++ b/drivers/clocksource/mxs_timer.c @@ -295,4 +295,4 @@ static int __init mxs_timer_init(struct device_node *np) return setup_irq(irq, &mxs_timer_irq); } -CLOCKSOURCE_OF_DECLARE_RET(mxs, "fsl,timrot", mxs_timer_init); +CLOCKSOURCE_OF_DECLARE(mxs, "fsl,timrot", mxs_timer_init); diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c index d2be5b3e0318..3c124d1ca600 100644 --- a/drivers/clocksource/nomadik-mtu.c +++ b/drivers/clocksource/nomadik-mtu.c @@ -284,5 +284,5 @@ static int __init nmdk_timer_of_init(struct device_node *node) return nmdk_timer_init(base, irq, pclk, clk); } -CLOCKSOURCE_OF_DECLARE_RET(nomadik_mtu, "st,nomadik-mtu", +CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "st,nomadik-mtu", nmdk_timer_of_init); diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c index 59af75cc4c74..937e10b84d58 100644 --- a/drivers/clocksource/pxa_timer.c +++ b/drivers/clocksource/pxa_timer.c @@ -213,7 +213,7 @@ static int __init pxa_timer_dt_init(struct device_node *np) return pxa_timer_common_init(irq, clk_get_rate(clk)); } -CLOCKSOURCE_OF_DECLARE_RET(pxa_timer, "marvell,pxa-timer", pxa_timer_dt_init); +CLOCKSOURCE_OF_DECLARE(pxa_timer, "marvell,pxa-timer", pxa_timer_dt_init); /* * Legacy timer init for non device-tree boards. diff --git a/drivers/clocksource/qcom-timer.c b/drivers/clocksource/qcom-timer.c index 79f73bddc5f4..662576339049 100644 --- a/drivers/clocksource/qcom-timer.c +++ b/drivers/clocksource/qcom-timer.c @@ -273,5 +273,5 @@ static int __init msm_dt_timer_init(struct device_node *np) return msm_timer_init(freq, 32, irq, !!percpu_offset); } -CLOCKSOURCE_OF_DECLARE_RET(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(scss_timer, "qcom,scss-timer", msm_dt_timer_init); +CLOCKSOURCE_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init); +CLOCKSOURCE_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init); diff --git a/drivers/clocksource/rockchip_timer.c b/drivers/clocksource/rockchip_timer.c index 85aee6953944..23e267acba25 100644 --- a/drivers/clocksource/rockchip_timer.c +++ b/drivers/clocksource/rockchip_timer.c @@ -205,7 +205,7 @@ static int __init rk3399_timer_init(struct device_node *np) return rk_timer_init(np, TIMER_CONTROL_REG3399); } -CLOCKSOURCE_OF_DECLARE_RET(rk3288_timer, "rockchip,rk3288-timer", - rk3288_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(rk3399_timer, "rockchip,rk3399-timer", - rk3399_timer_init); +CLOCKSOURCE_OF_DECLARE(rk3288_timer, "rockchip,rk3288-timer", + rk3288_timer_init); +CLOCKSOURCE_OF_DECLARE(rk3399_timer, "rockchip,rk3399-timer", + rk3399_timer_init); diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c index 27a9797e8187..54565bd0093b 100644 --- a/drivers/clocksource/samsung_pwm_timer.c +++ b/drivers/clocksource/samsung_pwm_timer.c @@ -466,7 +466,7 @@ static int __init s3c2410_pwm_clocksource_init(struct device_node *np) { return samsung_pwm_alloc(np, &s3c24xx_variant); } -CLOCKSOURCE_OF_DECLARE_RET(s3c2410_pwm, "samsung,s3c2410-pwm", s3c2410_pwm_clocksource_init); +CLOCKSOURCE_OF_DECLARE(s3c2410_pwm, "samsung,s3c2410-pwm", s3c2410_pwm_clocksource_init); static const struct samsung_pwm_variant s3c64xx_variant = { .bits = 32, @@ -479,7 +479,7 @@ static int __init s3c64xx_pwm_clocksource_init(struct device_node *np) { return samsung_pwm_alloc(np, &s3c64xx_variant); } -CLOCKSOURCE_OF_DECLARE_RET(s3c6400_pwm, "samsung,s3c6400-pwm", s3c64xx_pwm_clocksource_init); +CLOCKSOURCE_OF_DECLARE(s3c6400_pwm, "samsung,s3c6400-pwm", s3c64xx_pwm_clocksource_init); static const struct samsung_pwm_variant s5p64x0_variant = { .bits = 32, @@ -492,7 +492,7 @@ static int __init s5p64x0_pwm_clocksource_init(struct device_node *np) { return samsung_pwm_alloc(np, &s5p64x0_variant); } -CLOCKSOURCE_OF_DECLARE_RET(s5p6440_pwm, "samsung,s5p6440-pwm", s5p64x0_pwm_clocksource_init); +CLOCKSOURCE_OF_DECLARE(s5p6440_pwm, "samsung,s5p6440-pwm", s5p64x0_pwm_clocksource_init); static const struct samsung_pwm_variant s5p_variant = { .bits = 32, @@ -505,5 +505,5 @@ static int __init s5p_pwm_clocksource_init(struct device_node *np) { return samsung_pwm_alloc(np, &s5p_variant); } -CLOCKSOURCE_OF_DECLARE_RET(s5pc100_pwm, "samsung,s5pc100-pwm", s5p_pwm_clocksource_init); +CLOCKSOURCE_OF_DECLARE(s5pc100_pwm, "samsung,s5pc100-pwm", s5p_pwm_clocksource_init); #endif diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index 445373091fe8..97669ee4df2a 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -226,5 +226,5 @@ static int __init sun4i_timer_init(struct device_node *node) return ret; } -CLOCKSOURCE_OF_DECLARE_RET(sun4i, "allwinner,sun4i-a10-timer", +CLOCKSOURCE_OF_DECLARE(sun4i, "allwinner,sun4i-a10-timer", sun4i_timer_init); diff --git a/drivers/clocksource/tango_xtal.c b/drivers/clocksource/tango_xtal.c index 7dc716cc976f..12fcef8cf2d3 100644 --- a/drivers/clocksource/tango_xtal.c +++ b/drivers/clocksource/tango_xtal.c @@ -53,4 +53,4 @@ static int __init tango_clocksource_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(tango, "sigma,tick-counter", tango_clocksource_init); +CLOCKSOURCE_OF_DECLARE(tango, "sigma,tick-counter", tango_clocksource_init); diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c index 543c37e3a62c..f960891aa04e 100644 --- a/drivers/clocksource/tegra20_timer.c +++ b/drivers/clocksource/tegra20_timer.c @@ -237,7 +237,7 @@ static int __init tegra20_init_timer(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(tegra20_timer, "nvidia,tegra20-timer", tegra20_init_timer); +CLOCKSOURCE_OF_DECLARE(tegra20_timer, "nvidia,tegra20-timer", tegra20_init_timer); static int __init tegra20_init_rtc(struct device_node *np) { @@ -261,4 +261,4 @@ static int __init tegra20_init_rtc(struct device_node *np) return register_persistent_clock(NULL, tegra_read_persistent_clock64); } -CLOCKSOURCE_OF_DECLARE_RET(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc); +CLOCKSOURCE_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc); diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c index bc4ab48d4048..a4e59239f28e 100644 --- a/drivers/clocksource/time-armada-370-xp.c +++ b/drivers/clocksource/time-armada-370-xp.c @@ -371,7 +371,7 @@ static int __init armada_xp_timer_init(struct device_node *np) return armada_370_xp_timer_common_init(np); } -CLOCKSOURCE_OF_DECLARE_RET(armada_xp, "marvell,armada-xp-timer", +CLOCKSOURCE_OF_DECLARE(armada_xp, "marvell,armada-xp-timer", armada_xp_timer_init); static int __init armada_375_timer_init(struct device_node *np) @@ -409,7 +409,7 @@ static int __init armada_375_timer_init(struct device_node *np) return armada_370_xp_timer_common_init(np); } -CLOCKSOURCE_OF_DECLARE_RET(armada_375, "marvell,armada-375-timer", +CLOCKSOURCE_OF_DECLARE(armada_375, "marvell,armada-375-timer", armada_375_timer_init); static int __init armada_370_timer_init(struct device_node *np) @@ -432,5 +432,5 @@ static int __init armada_370_timer_init(struct device_node *np) return armada_370_xp_timer_common_init(np); } -CLOCKSOURCE_OF_DECLARE_RET(armada_370, "marvell,armada-370-timer", +CLOCKSOURCE_OF_DECLARE(armada_370, "marvell,armada-370-timer", armada_370_timer_init); diff --git a/drivers/clocksource/time-efm32.c b/drivers/clocksource/time-efm32.c index 6e2f79fd6ad0..5ac344b383e1 100644 --- a/drivers/clocksource/time-efm32.c +++ b/drivers/clocksource/time-efm32.c @@ -283,5 +283,5 @@ static int __init efm32_timer_init(struct device_node *np) return ret; } -CLOCKSOURCE_OF_DECLARE_RET(efm32compat, "efm32,timer", efm32_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(efm32, "energymicro,efm32-timer", efm32_timer_init); +CLOCKSOURCE_OF_DECLARE(efm32compat, "efm32,timer", efm32_timer_init); +CLOCKSOURCE_OF_DECLARE(efm32, "energymicro,efm32-timer", efm32_timer_init); diff --git a/drivers/clocksource/time-lpc32xx.c b/drivers/clocksource/time-lpc32xx.c index cb5b8665ff82..9649cfdb9213 100644 --- a/drivers/clocksource/time-lpc32xx.c +++ b/drivers/clocksource/time-lpc32xx.c @@ -311,4 +311,4 @@ static int __init lpc32xx_timer_init(struct device_node *np) return ret; } -CLOCKSOURCE_OF_DECLARE_RET(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init); +CLOCKSOURCE_OF_DECLARE(lpc32xx_timer, "nxp,lpc3220-timer", lpc32xx_timer_init); diff --git a/drivers/clocksource/time-orion.c b/drivers/clocksource/time-orion.c index 5fdeb5dcc4cf..a28f496e97cf 100644 --- a/drivers/clocksource/time-orion.c +++ b/drivers/clocksource/time-orion.c @@ -167,4 +167,4 @@ static int __init orion_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(orion_timer, "marvell,orion-timer", orion_timer_init); +CLOCKSOURCE_OF_DECLARE(orion_timer, "marvell,orion-timer", orion_timer_init); diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c index adaaec5e9abd..a7d9a08e4b0e 100644 --- a/drivers/clocksource/time-pistachio.c +++ b/drivers/clocksource/time-pistachio.c @@ -214,5 +214,5 @@ static int __init pistachio_clksrc_of_init(struct device_node *node) sched_clock_register(pistachio_read_sched_clock, 32, rate); return clocksource_register_hz(&pcs_gpt.cs, rate); } -CLOCKSOURCE_OF_DECLARE_RET(pistachio_gptimer, "img,pistachio-gptimer", +CLOCKSOURCE_OF_DECLARE(pistachio_gptimer, "img,pistachio-gptimer", pistachio_clksrc_of_init); diff --git a/drivers/clocksource/timer-atlas7.c b/drivers/clocksource/timer-atlas7.c index 7b1a0071a211..90f8fbc154a4 100644 --- a/drivers/clocksource/timer-atlas7.c +++ b/drivers/clocksource/timer-atlas7.c @@ -304,4 +304,4 @@ static int __init sirfsoc_of_timer_init(struct device_node *np) return sirfsoc_atlas7_timer_init(np); } -CLOCKSOURCE_OF_DECLARE_RET(sirfsoc_atlas7_timer, "sirf,atlas7-tick", sirfsoc_of_timer_init); +CLOCKSOURCE_OF_DECLARE(sirfsoc_atlas7_timer, "sirf,atlas7-tick", sirfsoc_of_timer_init); diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index ffaca7c2c996..1ffac0cb0cb7 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -270,5 +270,5 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) return at91sam926x_pit_common_init(data); } -CLOCKSOURCE_OF_DECLARE_RET(at91sam926x_pit, "atmel,at91sam9260-pit", +CLOCKSOURCE_OF_DECLARE(at91sam926x_pit, "atmel,at91sam9260-pit", at91sam926x_pit_dt_init); diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c index e9331d36965b..e90ab5b63a90 100644 --- a/drivers/clocksource/timer-atmel-st.c +++ b/drivers/clocksource/timer-atmel-st.c @@ -260,5 +260,5 @@ static int __init atmel_st_timer_init(struct device_node *node) /* register clocksource */ return clocksource_register_hz(&clk32k, sclk_rate); } -CLOCKSOURCE_OF_DECLARE_RET(atmel_st_timer, "atmel,at91rm9200-st", +CLOCKSOURCE_OF_DECLARE(atmel_st_timer, "atmel,at91rm9200-st", atmel_st_timer_init); diff --git a/drivers/clocksource/timer-digicolor.c b/drivers/clocksource/timer-digicolor.c index b929061ebe56..10318cc99c0e 100644 --- a/drivers/clocksource/timer-digicolor.c +++ b/drivers/clocksource/timer-digicolor.c @@ -202,5 +202,5 @@ static int __init digicolor_timer_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(conexant_digicolor, "cnxt,cx92755-timer", +CLOCKSOURCE_OF_DECLARE(conexant_digicolor, "cnxt,cx92755-timer", digicolor_timer_init); diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index d5640a747078..f595460bfc58 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -545,15 +545,15 @@ static int __init imx6dl_timer_init_dt(struct device_node *np) return mxc_timer_init_dt(np, GPT_TYPE_IMX6DL); } -CLOCKSOURCE_OF_DECLARE_RET(imx1_timer, "fsl,imx1-gpt", imx1_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx21_timer, "fsl,imx21-gpt", imx21_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx27_timer, "fsl,imx27-gpt", imx21_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx31_timer, "fsl,imx31-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx25_timer, "fsl,imx25-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx50_timer, "fsl,imx50-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx51_timer, "fsl,imx51-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx53_timer, "fsl,imx53-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx6q_timer, "fsl,imx6q-gpt", imx31_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx6dl_timer, "fsl,imx6dl-gpt", imx6dl_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx6sl_timer, "fsl,imx6sl-gpt", imx6dl_timer_init_dt); -CLOCKSOURCE_OF_DECLARE_RET(imx6sx_timer, "fsl,imx6sx-gpt", imx6dl_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx1_timer, "fsl,imx1-gpt", imx1_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx21_timer, "fsl,imx21-gpt", imx21_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx27_timer, "fsl,imx27-gpt", imx21_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx31_timer, "fsl,imx31-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx25_timer, "fsl,imx25-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx50_timer, "fsl,imx50-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx51_timer, "fsl,imx51-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx53_timer, "fsl,imx53-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx6q_timer, "fsl,imx6q-gpt", imx31_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx6dl_timer, "fsl,imx6dl-gpt", imx6dl_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx6sl_timer, "fsl,imx6sl-gpt", imx6dl_timer_init_dt); +CLOCKSOURCE_OF_DECLARE(imx6sx_timer, "fsl,imx6sx-gpt", imx6dl_timer_init_dt); diff --git a/drivers/clocksource/timer-integrator-ap.c b/drivers/clocksource/timer-integrator-ap.c index 675faceab5d6..df6e672afc04 100644 --- a/drivers/clocksource/timer-integrator-ap.c +++ b/drivers/clocksource/timer-integrator-ap.c @@ -232,5 +232,5 @@ static int __init integrator_ap_timer_init_of(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(integrator_ap_timer, "arm,integrator-timer", +CLOCKSOURCE_OF_DECLARE(integrator_ap_timer, "arm,integrator-timer", integrator_ap_timer_init_of); diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c index 4199823b2ec9..ab68a47ab3b4 100644 --- a/drivers/clocksource/timer-keystone.c +++ b/drivers/clocksource/timer-keystone.c @@ -226,5 +226,5 @@ err: return error; } -CLOCKSOURCE_OF_DECLARE_RET(keystone_timer, "ti,keystone-timer", +CLOCKSOURCE_OF_DECLARE(keystone_timer, "ti,keystone-timer", keystone_timer_init); diff --git a/drivers/clocksource/timer-nps.c b/drivers/clocksource/timer-nps.c index b5c7b2bd77bd..70c149af8ee0 100644 --- a/drivers/clocksource/timer-nps.c +++ b/drivers/clocksource/timer-nps.c @@ -96,5 +96,5 @@ static int __init nps_timer_init(struct device_node *node) return nps_setup_clocksource(node, clk); } -CLOCKSOURCE_OF_DECLARE_RET(ezchip_nps400_clksrc, "ezchip,nps400-timer", - nps_timer_init); +CLOCKSOURCE_OF_DECLARE(ezchip_nps400_clksrc, "ezchip,nps400-timer", + nps_timer_init); diff --git a/drivers/clocksource/timer-oxnas-rps.c b/drivers/clocksource/timer-oxnas-rps.c index 0d99f40ee757..bd887e2a8cf8 100644 --- a/drivers/clocksource/timer-oxnas-rps.c +++ b/drivers/clocksource/timer-oxnas-rps.c @@ -293,5 +293,5 @@ err_alloc: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(ox810se_rps, - "oxsemi,ox810se-rps-timer", oxnas_rps_timer_init); +CLOCKSOURCE_OF_DECLARE(ox810se_rps, + "oxsemi,ox810se-rps-timer", oxnas_rps_timer_init); diff --git a/drivers/clocksource/timer-prima2.c b/drivers/clocksource/timer-prima2.c index 7b1084d0b45e..dae8a66301d7 100644 --- a/drivers/clocksource/timer-prima2.c +++ b/drivers/clocksource/timer-prima2.c @@ -246,5 +246,5 @@ static int __init sirfsoc_prima2_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(sirfsoc_prima2_timer, +CLOCKSOURCE_OF_DECLARE(sirfsoc_prima2_timer, "sirf,prima2-tick", sirfsoc_prima2_timer_init); diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c index 3dc47efc9298..d07863388e05 100644 --- a/drivers/clocksource/timer-sp804.c +++ b/drivers/clocksource/timer-sp804.c @@ -287,7 +287,7 @@ err: iounmap(base); return ret; } -CLOCKSOURCE_OF_DECLARE_RET(sp804, "arm,sp804", sp804_of_init); +CLOCKSOURCE_OF_DECLARE(sp804, "arm,sp804", sp804_of_init); static int __init integrator_cp_of_init(struct device_node *np) { @@ -335,4 +335,4 @@ err: iounmap(base); return ret; } -CLOCKSOURCE_OF_DECLARE_RET(intcp, "arm,integrator-cp-timer", integrator_cp_of_init); +CLOCKSOURCE_OF_DECLARE(intcp, "arm,integrator-cp-timer", integrator_cp_of_init); diff --git a/drivers/clocksource/timer-stm32.c b/drivers/clocksource/timer-stm32.c index d5bf352905c8..1b2574c4fb97 100644 --- a/drivers/clocksource/timer-stm32.c +++ b/drivers/clocksource/timer-stm32.c @@ -187,4 +187,4 @@ err_clk_get: return ret; } -CLOCKSOURCE_OF_DECLARE_RET(stm32, "st,stm32-timer", stm32_clockevent_init); +CLOCKSOURCE_OF_DECLARE(stm32, "st,stm32-timer", stm32_clockevent_init); diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c index f0a3ffbab431..c184eb84101e 100644 --- a/drivers/clocksource/timer-sun5i.c +++ b/drivers/clocksource/timer-sun5i.c @@ -346,7 +346,7 @@ static int __init sun5i_timer_init(struct device_node *node) return sun5i_setup_clockevent(node, timer_base, clk, irq); } -CLOCKSOURCE_OF_DECLARE_RET(sun5i_a13, "allwinner,sun5i-a13-hstimer", +CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer", sun5i_timer_init); -CLOCKSOURCE_OF_DECLARE_RET(sun7i_a20, "allwinner,sun7i-a20-hstimer", +CLOCKSOURCE_OF_DECLARE(sun7i_a20, "allwinner,sun7i-a20-hstimer", sun5i_timer_init); diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c index e4ad3c6e03f9..92b7e390f6c8 100644 --- a/drivers/clocksource/timer-ti-32k.c +++ b/drivers/clocksource/timer-ti-32k.c @@ -124,5 +124,5 @@ static int __init ti_32k_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(ti_32k_timer, "ti,omap-counter32k", +CLOCKSOURCE_OF_DECLARE(ti_32k_timer, "ti,omap-counter32k", ti_32k_timer_init); diff --git a/drivers/clocksource/timer-u300.c b/drivers/clocksource/timer-u300.c index a6a0dec41faa..704e40c6f151 100644 --- a/drivers/clocksource/timer-u300.c +++ b/drivers/clocksource/timer-u300.c @@ -458,5 +458,5 @@ static int __init u300_timer_init_of(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(u300_timer, "stericsson,u300-apptimer", +CLOCKSOURCE_OF_DECLARE(u300_timer, "stericsson,u300-apptimer", u300_timer_init_of); diff --git a/drivers/clocksource/versatile.c b/drivers/clocksource/versatile.c index 8daeffac300b..220b490a8142 100644 --- a/drivers/clocksource/versatile.c +++ b/drivers/clocksource/versatile.c @@ -38,7 +38,7 @@ static int __init versatile_sched_clock_init(struct device_node *node) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(vexpress, "arm,vexpress-sysreg", +CLOCKSOURCE_OF_DECLARE(vexpress, "arm,vexpress-sysreg", versatile_sched_clock_init); -CLOCKSOURCE_OF_DECLARE_RET(versatile, "arm,versatile-sysreg", +CLOCKSOURCE_OF_DECLARE(versatile, "arm,versatile-sysreg", versatile_sched_clock_init); diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c index ca4dff4d5684..55d8d8402d90 100644 --- a/drivers/clocksource/vf_pit_timer.c +++ b/drivers/clocksource/vf_pit_timer.c @@ -201,4 +201,4 @@ static int __init pit_timer_init(struct device_node *np) return pit_clockevent_init(clk_rate, irq); } -CLOCKSOURCE_OF_DECLARE_RET(vf610, "fsl,vf610-pit", pit_timer_init); +CLOCKSOURCE_OF_DECLARE(vf610, "fsl,vf610-pit", pit_timer_init); diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c index 1bc8707b4f9d..b15069483fbd 100644 --- a/drivers/clocksource/vt8500_timer.c +++ b/drivers/clocksource/vt8500_timer.c @@ -165,4 +165,4 @@ static int __init vt8500_timer_init(struct device_node *np) return 0; } -CLOCKSOURCE_OF_DECLARE_RET(vt8500, "via,vt8500-timer", vt8500_timer_init); +CLOCKSOURCE_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init); diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c index cb4cf056d56d..9a53f5ef6157 100644 --- a/drivers/clocksource/zevio-timer.c +++ b/drivers/clocksource/zevio-timer.c @@ -215,4 +215,4 @@ static int __init zevio_timer_init(struct device_node *node) return zevio_timer_add(node); } -CLOCKSOURCE_OF_DECLARE_RET(zevio_timer, "lsi,zevio-timer", zevio_timer_init); +CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_init); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8c6c626285c0..6a67ab94b553 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -173,7 +173,6 @@ *(__##name##_of_table_end) #define CLKSRC_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc) -#define CLKSRC_RET_OF_TABLES() OF_TABLE(CONFIG_CLKSRC_OF, clksrc_ret) #define IRQCHIP_OF_MATCH_TABLE() OF_TABLE(CONFIG_IRQCHIP, irqchip) #define CLK_OF_TABLES() OF_TABLE(CONFIG_COMMON_CLK, clk) #define IOMMU_OF_TABLES() OF_TABLE(CONFIG_OF_IOMMU, iommu) @@ -532,7 +531,6 @@ CLK_OF_TABLES() \ RESERVEDMEM_OF_TABLES() \ CLKSRC_OF_TABLES() \ - CLKSRC_RET_OF_TABLES() \ IOMMU_OF_TABLES() \ CPU_METHOD_OF_TABLES() \ CPUIDLE_METHOD_OF_TABLES() \ diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 15c3839850f4..08398182f56e 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -244,10 +244,7 @@ extern int clocksource_mmio_init(void __iomem *, const char *, extern int clocksource_i8253_init(void); #define CLOCKSOURCE_OF_DECLARE(name, compat, fn) \ - OF_DECLARE_1(clksrc, name, compat, fn) - -#define CLOCKSOURCE_OF_DECLARE_RET(name, compat, fn) \ - OF_DECLARE_1_RET(clksrc_ret, name, compat, fn) + OF_DECLARE_1_RET(clksrc, name, compat, fn) #ifdef CONFIG_CLKSRC_PROBE extern void clocksource_probe(void); -- cgit v1.2.3 From b81ea968706bdb5c2f2af62c5700573a32ab310a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 2 Jun 2016 22:44:49 +0200 Subject: clk: Add missing clk_get_sys() stub When compiling with the COMPILE_TEST option set, the clps711x does not compile because of the clk_get_sys() noop stub missing. Signed-off-by: Daniel Lezcano Reviewed-by: Michael Turquette --- include/linux/clk.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/clk.h b/include/linux/clk.h index 0df4a51e1a78..834179f3fa72 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -461,6 +461,10 @@ static inline struct clk *clk_get_parent(struct clk *clk) return NULL; } +static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) +{ + return NULL; +} #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ -- cgit v1.2.3 From bc92126012c8c84988eebbbf9c8a246949b07462 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 27 Jun 2016 21:09:04 +0900 Subject: extcon: Fix the wrong description about extcon_set/get_cable_state_() This patch fixes the wrong description about extcon_set/get_cable_state_() because they use the unique id of external connector instead of legacy name. Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 7bf530f3f4f5..61004413dc64 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -165,7 +165,7 @@ extern int extcon_update_state(struct extcon_dev *edev, u32 mask, u32 state); /* * get/set_cable_state access each bit of the 32b encoded state value. - * They are used to access the status of each cable based on the cable_name. + * They are used to access the status of each cable based on the cable id. */ extern int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id); extern int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, -- cgit v1.2.3 From 9a9b6aa6a8759c83024627d681eff982d6ee03b7 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Tue, 28 Jun 2016 10:32:00 -0700 Subject: Input: add SW_PEN_INSERTED define Some devices with a pen may have a switch that can be used to detect when the pen is inserted or removed to a slot on the device. Let's add a define to the input event codes so that everyone can be on the same page for what event we should generate when the pen is inserted or removed. In general the pen switch could be used by the software on the device to kick off any number of actions when the pen is inserted or removed. Signed-off-by: Douglas Anderson Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 737fa32faad4..d6d071fc3c56 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -780,6 +780,7 @@ #define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ #define SW_LINEIN_INSERT 0x0d /* set = inserted */ #define SW_MUTE_DEVICE 0x0e /* set = device disabled */ +#define SW_PEN_INSERTED 0x0f /* set = pen inserted */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) -- cgit v1.2.3 From fedbb6b4ff341c1e2120f4ffbf367fd78ac3e8f3 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Wed, 29 Jun 2016 21:47:03 +0300 Subject: ipv4: Fix ip_skb_dst_mtu to use the sk passed by ip_finish_output ip_skb_dst_mtu uses skb->sk, assuming it is an AF_INET socket (e.g. it calls ip_sk_use_pmtu which casts sk as an inet_sk). However, in the case of UDP tunneling, the skb->sk is not necessarily an inet socket (could be AF_PACKET socket, or AF_UNSPEC if arriving from tun/tap). OTOH, the sk passed as an argument throughout IP stack's output path is the one which is of PMTU interest: - In case of local sockets, sk is same as skb->sk; - In case of a udp tunnel, sk is the tunneling socket. Fix, by passing ip_finish_output's sk to ip_skb_dst_mtu. This augments 7026b1ddb6 'netfilter: Pass socket pointer down through okfn().' Signed-off-by: Shmulik Ladkani Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 5 ++--- net/bridge/br_netfilter_hooks.c | 2 +- net/ipv4/ip_output.c | 4 ++-- 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 37165fba3741..08f36cd2b874 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -313,10 +313,9 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, return min(dst->dev->mtu, IP_MAX_MTU); } -static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb) +static inline unsigned int ip_skb_dst_mtu(struct sock *sk, + const struct sk_buff *skb) { - struct sock *sk = skb->sk; - if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 2d25979273a6..77e7f69bf80d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -700,7 +700,7 @@ static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { - unsigned int mtu = ip_skb_dst_mtu(skb); + unsigned int mtu = ip_skb_dst_mtu(sk, skb); struct iphdr *iph = ip_hdr(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 124bf0a66328..4bd4921639c3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk return dst_output(net, sk, skb); } #endif - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); @@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; -- cgit v1.2.3 From bc2b7dab629a51e8beb5fda4222c62a23b729f26 Mon Sep 17 00:00:00 2001 From: Gregor Boirie Date: Wed, 9 Mar 2016 19:05:49 +0100 Subject: iio:core: timestamping clock selection support Adds a new per-device sysfs attribute "current_timestamp_clock" to allow userspace to select a particular POSIX clock for buffered samples and events timestamping. Following clocks, as listed in clock_gettime(2), are supported: CLOCK_REALTIME, CLOCK_MONOTONIC, CLOCK_MONOTONIC_RAW, CLOCK_REALTIME_COARSE, CLOCK_MONOTONIC_COARSE, CLOCK_BOOTTIME and CLOCK_TAI. Signed-off-by: Gregor Boirie Acked-by: Sanchayan Maity Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 7 + Documentation/DocBook/iio.tmpl | 2 +- drivers/iio/accel/bma180.c | 2 +- drivers/iio/accel/bmc150-accel-core.c | 4 +- drivers/iio/accel/kxcjk-1013.c | 2 +- drivers/iio/accel/mma7455_core.c | 3 +- drivers/iio/accel/mma8452.c | 4 +- drivers/iio/accel/mma9551.c | 2 +- drivers/iio/accel/mma9553.c | 2 +- drivers/iio/adc/ad7291.c | 2 +- drivers/iio/adc/ad7298.c | 2 +- drivers/iio/adc/ad7476.c | 2 +- drivers/iio/adc/ad7887.c | 2 +- drivers/iio/adc/ad7923.c | 2 +- drivers/iio/adc/ad799x.c | 4 +- drivers/iio/adc/cc10001_adc.c | 2 +- drivers/iio/adc/hi8435.c | 2 +- drivers/iio/adc/ina2xx-adc.c | 6 +- drivers/iio/adc/max1363.c | 5 +- drivers/iio/adc/ti-adc081c.c | 3 +- drivers/iio/adc/ti-ads1015.c | 3 +- drivers/iio/adc/vf610_adc.c | 3 +- drivers/iio/adc/xilinx-xadc-events.c | 4 +- drivers/iio/chemical/atlas-ph-sensor.c | 2 +- drivers/iio/common/st_sensors/st_sensors_buffer.c | 2 +- drivers/iio/common/st_sensors/st_sensors_trigger.c | 2 +- drivers/iio/dac/ad5421.c | 6 +- drivers/iio/dac/ad5504.c | 2 +- drivers/iio/dummy/iio_simple_dummy_buffer.c | 3 +- drivers/iio/dummy/iio_simple_dummy_events.c | 2 +- drivers/iio/gyro/bmg160_core.c | 30 ++-- drivers/iio/iio_core.h | 3 + drivers/iio/imu/bmi160/bmi160_core.c | 3 +- drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c | 2 +- drivers/iio/industrialio-core.c | 179 ++++++++++++++++++++- drivers/iio/industrialio-event.c | 19 ++- drivers/iio/industrialio-trigger.c | 2 +- drivers/iio/light/acpi-als.c | 2 +- drivers/iio/light/adjd_s311.c | 2 +- drivers/iio/light/apds9300.c | 2 +- drivers/iio/light/apds9960.c | 4 +- drivers/iio/light/cm36651.c | 2 +- drivers/iio/light/gp2ap020a00f.c | 8 +- drivers/iio/light/isl29125.c | 2 +- drivers/iio/light/lm3533-als.c | 2 +- drivers/iio/light/ltr501.c | 7 +- drivers/iio/light/max44000.c | 3 +- drivers/iio/light/opt3001.c | 4 +- drivers/iio/light/stk3310.c | 2 +- drivers/iio/light/tcs3414.c | 2 +- drivers/iio/light/tcs3472.c | 2 +- drivers/iio/light/tsl2563.c | 2 +- drivers/iio/light/us5182d.c | 2 +- drivers/iio/magnetometer/ak8975.c | 3 +- drivers/iio/magnetometer/hmc5843_core.c | 2 +- drivers/iio/magnetometer/mag3110.c | 2 +- drivers/iio/pressure/mpl3115.c | 2 +- drivers/iio/pressure/ms5611_core.c | 3 +- drivers/iio/proximity/pulsedlight-lidar-lite-v2.c | 2 +- drivers/iio/proximity/sx9500.c | 4 +- drivers/staging/iio/accel/lis3l02dq_core.c | 2 +- drivers/staging/iio/accel/sca3000_core.c | 2 +- drivers/staging/iio/adc/ad7280a.c | 8 +- drivers/staging/iio/adc/ad7606_ring.c | 3 +- drivers/staging/iio/adc/ad7816.c | 3 +- drivers/staging/iio/addac/adt7316.c | 4 +- drivers/staging/iio/cdc/ad7150.c | 2 +- drivers/staging/iio/light/tsl2x7x_core.c | 2 +- include/linux/iio/iio.h | 22 ++- 69 files changed, 327 insertions(+), 114 deletions(-) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index e7f590c6ef8e..fee35c00cc4e 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -32,6 +32,13 @@ Description: Description of the physical chip / device for device X. Typically a part number. +What: /sys/bus/iio/devices/iio:deviceX/timestamp_clock +KernelVersion: 4.5 +Contact: linux-iio@vger.kernel.org +Description: + String identifying current posix clock used to timestamp + buffered samples and events for device X. + What: /sys/bus/iio/devices/iio:deviceX/sampling_frequency What: /sys/bus/iio/devices/iio:deviceX/buffer/sampling_frequency What: /sys/bus/iio/devices/triggerX/sampling_frequency diff --git a/Documentation/DocBook/iio.tmpl b/Documentation/DocBook/iio.tmpl index f525bf56d1dd..e2ab6a1f223e 100644 --- a/Documentation/DocBook/iio.tmpl +++ b/Documentation/DocBook/iio.tmpl @@ -594,7 +594,7 @@ irqreturn_t sensor_iio_pollfunc(int irq, void *p) { - pf->timestamp = iio_get_time_ns(); + pf->timestamp = iio_get_time_ns((struct indio_dev *)p); return IRQ_WAKE_THREAD; } diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index f04b88406995..e3f88ba5faf3 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -654,7 +654,7 @@ static irqreturn_t bma180_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct bma180_data *data = iio_priv(indio_dev); - int64_t time_ns = iio_get_time_ns(); + s64 time_ns = iio_get_time_ns(indio_dev); int bit, ret, i = 0; mutex_lock(&data->mutex); diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index 197e693e7e7b..bf17aae66145 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -901,7 +901,7 @@ static int __bmc150_accel_fifo_flush(struct iio_dev *indio_dev, */ if (!irq) { data->old_timestamp = data->timestamp; - data->timestamp = iio_get_time_ns(); + data->timestamp = iio_get_time_ns(indio_dev); } /* @@ -1303,7 +1303,7 @@ static irqreturn_t bmc150_accel_irq_handler(int irq, void *private) int i; data->old_timestamp = data->timestamp; - data->timestamp = iio_get_time_ns(); + data->timestamp = iio_get_time_ns(indio_dev); for (i = 0; i < BMC150_ACCEL_TRIGGERS; i++) { if (data->triggers[i].enabled) { diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index bfe219a8bea2..765a72362dc6 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1129,7 +1129,7 @@ static irqreturn_t kxcjk1013_data_rdy_trig_poll(int irq, void *private) struct iio_dev *indio_dev = private; struct kxcjk1013_data *data = iio_priv(indio_dev); - data->timestamp = iio_get_time_ns(); + data->timestamp = iio_get_time_ns(indio_dev); if (data->dready_trigger_on) iio_trigger_poll(data->dready_trig); diff --git a/drivers/iio/accel/mma7455_core.c b/drivers/iio/accel/mma7455_core.c index c902f54c23f5..6551085bedd7 100644 --- a/drivers/iio/accel/mma7455_core.c +++ b/drivers/iio/accel/mma7455_core.c @@ -97,7 +97,8 @@ static irqreturn_t mma7455_trigger_handler(int irq, void *p) if (ret) goto done; - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index 799fe64fc286..c0df28328368 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -917,7 +917,7 @@ static int mma8452_write_event_config(struct iio_dev *indio_dev, static void mma8452_transient_interrupt(struct iio_dev *indio_dev) { struct mma8452_data *data = iio_priv(indio_dev); - s64 ts = iio_get_time_ns(); + s64 ts = iio_get_time_ns(indio_dev); int src; src = i2c_smbus_read_byte_data(data->client, data->chip_info->ev_src); @@ -997,7 +997,7 @@ static irqreturn_t mma8452_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/accel/mma9551.c b/drivers/iio/accel/mma9551.c index d899a4d4307f..bf2704435629 100644 --- a/drivers/iio/accel/mma9551.c +++ b/drivers/iio/accel/mma9551.c @@ -391,7 +391,7 @@ static irqreturn_t mma9551_event_handler(int irq, void *private) iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_INCLI, 0, (mma_axis + 1), IIO_EV_TYPE_ROC, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); out: mutex_unlock(&data->mutex); diff --git a/drivers/iio/accel/mma9553.c b/drivers/iio/accel/mma9553.c index bb05f3efddca..36bf19733be0 100644 --- a/drivers/iio/accel/mma9553.c +++ b/drivers/iio/accel/mma9553.c @@ -1001,7 +1001,7 @@ static irqreturn_t mma9553_irq_handler(int irq, void *private) struct iio_dev *indio_dev = private; struct mma9553_data *data = iio_priv(indio_dev); - data->timestamp = iio_get_time_ns(); + data->timestamp = iio_get_time_ns(indio_dev); /* * Since we only configure the interrupt pin when an * event is enabled, we are sure we have at least diff --git a/drivers/iio/adc/ad7291.c b/drivers/iio/adc/ad7291.c index c0eabf156702..037630932749 100644 --- a/drivers/iio/adc/ad7291.c +++ b/drivers/iio/adc/ad7291.c @@ -115,7 +115,7 @@ static irqreturn_t ad7291_event_handler(int irq, void *private) u16 t_status, v_status; u16 command; int i; - s64 timestamp = iio_get_time_ns(); + s64 timestamp = iio_get_time_ns(indio_dev); if (ad7291_i2c_read(chip, AD7291_T_ALERT_STATUS, &t_status)) return IRQ_HANDLED; diff --git a/drivers/iio/adc/ad7298.c b/drivers/iio/adc/ad7298.c index 62bb8f7ce4a0..5dd0742da75a 100644 --- a/drivers/iio/adc/ad7298.c +++ b/drivers/iio/adc/ad7298.c @@ -163,7 +163,7 @@ static irqreturn_t ad7298_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, st->rx_buf, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad7476.c b/drivers/iio/adc/ad7476.c index 810c9a9fa62f..a819be288577 100644 --- a/drivers/iio/adc/ad7476.c +++ b/drivers/iio/adc/ad7476.c @@ -70,7 +70,7 @@ static irqreturn_t ad7476_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, st->data, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c index ee2ccc19fab6..1bc363b0a4c1 100644 --- a/drivers/iio/adc/ad7887.c +++ b/drivers/iio/adc/ad7887.c @@ -122,7 +122,7 @@ static irqreturn_t ad7887_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, st->data, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index ff444c19d749..133711680e55 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -181,7 +181,7 @@ static irqreturn_t ad7923_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, st->rx_buf, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c index ec0200dd52cb..54284766d2ef 100644 --- a/drivers/iio/adc/ad799x.c +++ b/drivers/iio/adc/ad799x.c @@ -212,7 +212,7 @@ static irqreturn_t ad799x_trigger_handler(int irq, void *p) goto out; iio_push_to_buffers_with_timestamp(indio_dev, st->rx_buf, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); out: iio_trigger_notify_done(indio_dev->trig); @@ -502,7 +502,7 @@ static irqreturn_t ad799x_event_handler(int irq, void *private) (i >> 1), IIO_EV_TYPE_THRESH, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } done: diff --git a/drivers/iio/adc/cc10001_adc.c b/drivers/iio/adc/cc10001_adc.c index 8254f529b2a9..91636c0ba5b5 100644 --- a/drivers/iio/adc/cc10001_adc.c +++ b/drivers/iio/adc/cc10001_adc.c @@ -186,7 +186,7 @@ done: if (!sample_invalid) iio_push_to_buffers_with_timestamp(indio_dev, data, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/adc/hi8435.c b/drivers/iio/adc/hi8435.c index c73c6c62a6ac..c62bdb0a809e 100644 --- a/drivers/iio/adc/hi8435.c +++ b/drivers/iio/adc/hi8435.c @@ -400,7 +400,7 @@ static void hi8435_iio_push_event(struct iio_dev *idev, unsigned int val) iio_push_event(idev, IIO_UNMOD_EVENT_CODE(IIO_VOLTAGE, i, IIO_EV_TYPE_THRESH, dir), - iio_get_time_ns()); + iio_get_time_ns(idev)); } } diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 502f2fbe8aef..b95ce5d7ee2c 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -465,7 +465,7 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev) s64 time_a, time_b; unsigned int alert; - time_a = iio_get_time_ns(); + time_a = iio_get_time_ns(indio_dev); /* * Because the timer thread and the chip conversion clock @@ -504,7 +504,7 @@ static int ina2xx_work_buffer(struct iio_dev *indio_dev) data[i++] = val; } - time_b = iio_get_time_ns(); + time_b = iio_get_time_ns(indio_dev); iio_push_to_buffers_with_timestamp(indio_dev, (unsigned int *)data, time_a); @@ -554,7 +554,7 @@ static int ina2xx_buffer_enable(struct iio_dev *indio_dev) dev_dbg(&indio_dev->dev, "Async readout mode: %d\n", chip->allow_async_readout); - chip->prev_ns = iio_get_time_ns(); + chip->prev_ns = iio_get_time_ns(indio_dev); chip->task = kthread_run(ina2xx_capture_thread, (void *)indio_dev, "%s:%d-%uus", indio_dev->name, indio_dev->id, diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index 998dc3caad4c..73af30684657 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -788,7 +788,7 @@ static irqreturn_t max1363_event_handler(int irq, void *private) { struct iio_dev *indio_dev = private; struct max1363_state *st = iio_priv(indio_dev); - s64 timestamp = iio_get_time_ns(); + s64 timestamp = iio_get_time_ns(indio_dev); unsigned long mask, loc; u8 rx; u8 tx[2] = { st->setupbyte, @@ -1506,7 +1506,8 @@ static irqreturn_t max1363_trigger_handler(int irq, void *p) if (b_sent < 0) goto done_free; - iio_push_to_buffers_with_timestamp(indio_dev, rxbuf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, rxbuf, + iio_get_time_ns(indio_dev)); done_free: kfree(rxbuf); diff --git a/drivers/iio/adc/ti-adc081c.c b/drivers/iio/adc/ti-adc081c.c index f8807adc08c4..283d2a12b6da 100644 --- a/drivers/iio/adc/ti-adc081c.c +++ b/drivers/iio/adc/ti-adc081c.c @@ -139,7 +139,8 @@ static irqreturn_t adc081c_trigger_handler(int irq, void *p) if (ret < 0) goto out; buf[0] = ret; - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); out: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/adc/ti-ads1015.c b/drivers/iio/adc/ti-ads1015.c index 8be192a84893..c9574af09882 100644 --- a/drivers/iio/adc/ti-ads1015.c +++ b/drivers/iio/adc/ti-ads1015.c @@ -288,7 +288,8 @@ static irqreturn_t ads1015_trigger_handler(int irq, void *p) buf[0] = res; mutex_unlock(&data->lock); - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); err: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c index 653bf1379d2e..228a003adeed 100644 --- a/drivers/iio/adc/vf610_adc.c +++ b/drivers/iio/adc/vf610_adc.c @@ -594,7 +594,8 @@ static irqreturn_t vf610_adc_isr(int irq, void *dev_id) if (iio_buffer_enabled(indio_dev)) { info->buffer[0] = info->value; iio_push_to_buffers_with_timestamp(indio_dev, - info->buffer, iio_get_time_ns()); + info->buffer, + iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); } else complete(&info->completion); diff --git a/drivers/iio/adc/xilinx-xadc-events.c b/drivers/iio/adc/xilinx-xadc-events.c index edcf3aabd70d..6d5c2a6f4e6e 100644 --- a/drivers/iio/adc/xilinx-xadc-events.c +++ b/drivers/iio/adc/xilinx-xadc-events.c @@ -46,7 +46,7 @@ static void xadc_handle_event(struct iio_dev *indio_dev, unsigned int event) iio_push_event(indio_dev, IIO_UNMOD_EVENT_CODE(chan->type, chan->channel, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } else { /* * For other channels we don't know whether it is a upper or @@ -56,7 +56,7 @@ static void xadc_handle_event(struct iio_dev *indio_dev, unsigned int event) iio_push_event(indio_dev, IIO_UNMOD_EVENT_CODE(chan->type, chan->channel, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } } diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c index 02e85db5d31f..ae038a59d256 100644 --- a/drivers/iio/chemical/atlas-ph-sensor.c +++ b/drivers/iio/chemical/atlas-ph-sensor.c @@ -343,7 +343,7 @@ static irqreturn_t atlas_trigger_handler(int irq, void *private) if (!ret) iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 50afc0f8f16b..7c84e90d8ce8 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -62,7 +62,7 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p) if (sdata->hw_irq_trigger) timestamp = sdata->hw_timestamp; else - timestamp = iio_get_time_ns(); + timestamp = iio_get_time_ns(indio_dev); len = st_sensors_get_buffer_element(indio_dev, sdata->buffer_data); if (len < 0) diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 296e4ff19ae8..fab494d71951 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -29,7 +29,7 @@ irqreturn_t st_sensors_irq_handler(int irq, void *p) struct st_sensor_data *sdata = iio_priv(indio_dev); /* Get the time stamp as close in time as possible */ - sdata->hw_timestamp = iio_get_time_ns(); + sdata->hw_timestamp = iio_get_time_ns(indio_dev); return IRQ_WAKE_THREAD; } diff --git a/drivers/iio/dac/ad5421.c b/drivers/iio/dac/ad5421.c index 968712be967f..559061ab1982 100644 --- a/drivers/iio/dac/ad5421.c +++ b/drivers/iio/dac/ad5421.c @@ -242,7 +242,7 @@ static irqreturn_t ad5421_fault_handler(int irq, void *data) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } if (events & AD5421_FAULT_UNDER_CURRENT) { @@ -251,7 +251,7 @@ static irqreturn_t ad5421_fault_handler(int irq, void *data) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } if (events & AD5421_FAULT_TEMP_OVER_140) { @@ -260,7 +260,7 @@ static irqreturn_t ad5421_fault_handler(int irq, void *data) 0, IIO_EV_TYPE_MAG, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } old_fault = fault; diff --git a/drivers/iio/dac/ad5504.c b/drivers/iio/dac/ad5504.c index 4e4c20d6d8b5..788b3d6fd1cc 100644 --- a/drivers/iio/dac/ad5504.c +++ b/drivers/iio/dac/ad5504.c @@ -223,7 +223,7 @@ static irqreturn_t ad5504_event_handler(int irq, void *private) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns((struct iio_dev *)private)); return IRQ_HANDLED; } diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c index cf44a6f79431..b383892a5193 100644 --- a/drivers/iio/dummy/iio_simple_dummy_buffer.c +++ b/drivers/iio/dummy/iio_simple_dummy_buffer.c @@ -85,7 +85,8 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p) } } - iio_push_to_buffers_with_timestamp(indio_dev, data, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, data, + iio_get_time_ns(indio_dev)); kfree(data); diff --git a/drivers/iio/dummy/iio_simple_dummy_events.c b/drivers/iio/dummy/iio_simple_dummy_events.c index 6eb600ff7056..ed63ffd849f8 100644 --- a/drivers/iio/dummy/iio_simple_dummy_events.c +++ b/drivers/iio/dummy/iio_simple_dummy_events.c @@ -158,7 +158,7 @@ static irqreturn_t iio_simple_dummy_get_timestamp(int irq, void *private) struct iio_dev *indio_dev = private; struct iio_dummy_state *st = iio_priv(indio_dev); - st->event_timestamp = iio_get_time_ns(); + st->event_timestamp = iio_get_time_ns(indio_dev); return IRQ_WAKE_THREAD; } diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 7ccc044063f6..8155251d9984 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -885,25 +885,25 @@ static irqreturn_t bmg160_event_handler(int irq, void *private) if (val & BMG160_ANY_MOTION_BIT_X) iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ANGL_VEL, - 0, - IIO_MOD_X, - IIO_EV_TYPE_ROC, - dir), - iio_get_time_ns()); + 0, + IIO_MOD_X, + IIO_EV_TYPE_ROC, + dir), + iio_get_time_ns(indio_dev)); if (val & BMG160_ANY_MOTION_BIT_Y) iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ANGL_VEL, - 0, - IIO_MOD_Y, - IIO_EV_TYPE_ROC, - dir), - iio_get_time_ns()); + 0, + IIO_MOD_Y, + IIO_EV_TYPE_ROC, + dir), + iio_get_time_ns(indio_dev)); if (val & BMG160_ANY_MOTION_BIT_Z) iio_push_event(indio_dev, IIO_MOD_EVENT_CODE(IIO_ANGL_VEL, - 0, - IIO_MOD_Z, - IIO_EV_TYPE_ROC, - dir), - iio_get_time_ns()); + 0, + IIO_MOD_Z, + IIO_EV_TYPE_ROC, + dir), + iio_get_time_ns(indio_dev)); ack_intr_status: if (!data->dready_trigger_on) { diff --git a/drivers/iio/iio_core.h b/drivers/iio/iio_core.h index 359883525ab7..4c45488e3a7f 100644 --- a/drivers/iio/iio_core.h +++ b/drivers/iio/iio_core.h @@ -79,4 +79,7 @@ void iio_device_unregister_eventset(struct iio_dev *indio_dev); void iio_device_wakeup_eventset(struct iio_dev *indio_dev); int iio_event_getfd(struct iio_dev *indio_dev); +struct iio_event_interface; +bool iio_event_enabled(const struct iio_event_interface *ev_int); + #endif diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c index 97928d558a15..e0251b8c1a52 100644 --- a/drivers/iio/imu/bmi160/bmi160_core.c +++ b/drivers/iio/imu/bmi160/bmi160_core.c @@ -411,7 +411,8 @@ static irqreturn_t bmi160_trigger_handler(int irq, void *p) buf[j++] = sample; } - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index d0700628ee6d..3a9f3eac91ab 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -107,7 +107,7 @@ irqreturn_t inv_mpu6050_irq_handler(int irq, void *p) struct inv_mpu6050_state *st = iio_priv(indio_dev); s64 timestamp; - timestamp = iio_get_time_ns(); + timestamp = iio_get_time_ns(indio_dev); kfifo_in_spinlocked(&st->timestamps, ×tamp, 1, &st->time_stamp_lock); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 2a85bd888619..f914d5d140e4 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -178,6 +178,86 @@ ssize_t iio_read_const_attr(struct device *dev, } EXPORT_SYMBOL(iio_read_const_attr); +static int iio_device_set_clock(struct iio_dev *indio_dev, clockid_t clock_id) +{ + int ret; + const struct iio_event_interface *ev_int = indio_dev->event_interface; + + ret = mutex_lock_interruptible(&indio_dev->mlock); + if (ret) + return ret; + if ((ev_int && iio_event_enabled(ev_int)) || + iio_buffer_enabled(indio_dev)) { + mutex_unlock(&indio_dev->mlock); + return -EBUSY; + } + indio_dev->clock_id = clock_id; + mutex_unlock(&indio_dev->mlock); + + return 0; +} + +/** + * iio_get_time_ns() - utility function to get a time stamp for events etc + * @indio_dev: device + */ +s64 iio_get_time_ns(const struct iio_dev *indio_dev) +{ + struct timespec tp; + + switch (iio_device_get_clock(indio_dev)) { + case CLOCK_REALTIME: + ktime_get_real_ts(&tp); + break; + case CLOCK_MONOTONIC: + ktime_get_ts(&tp); + break; + case CLOCK_MONOTONIC_RAW: + getrawmonotonic(&tp); + break; + case CLOCK_REALTIME_COARSE: + tp = current_kernel_time(); + break; + case CLOCK_MONOTONIC_COARSE: + tp = get_monotonic_coarse(); + break; + case CLOCK_BOOTTIME: + get_monotonic_boottime(&tp); + break; + case CLOCK_TAI: + timekeeping_clocktai(&tp); + break; + default: + BUG(); + } + + return timespec_to_ns(&tp); +} +EXPORT_SYMBOL(iio_get_time_ns); + +/** + * iio_get_time_res() - utility function to get time stamp clock resolution in + * nano seconds. + * @indio_dev: device + */ +unsigned int iio_get_time_res(const struct iio_dev *indio_dev) +{ + switch (iio_device_get_clock(indio_dev)) { + case CLOCK_REALTIME: + case CLOCK_MONOTONIC: + case CLOCK_MONOTONIC_RAW: + case CLOCK_BOOTTIME: + case CLOCK_TAI: + return hrtimer_resolution; + case CLOCK_REALTIME_COARSE: + case CLOCK_MONOTONIC_COARSE: + return LOW_RES_NSEC; + default: + BUG(); + } +} +EXPORT_SYMBOL(iio_get_time_res); + static int __init iio_init(void) { int ret; @@ -990,11 +1070,91 @@ static ssize_t iio_show_dev_name(struct device *dev, static DEVICE_ATTR(name, S_IRUGO, iio_show_dev_name, NULL); +static ssize_t iio_show_timestamp_clock(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + const struct iio_dev *indio_dev = dev_to_iio_dev(dev); + const clockid_t clk = iio_device_get_clock(indio_dev); + const char *name; + ssize_t sz; + + switch (clk) { + case CLOCK_REALTIME: + name = "realtime\n"; + sz = sizeof("realtime\n"); + break; + case CLOCK_MONOTONIC: + name = "monotonic\n"; + sz = sizeof("monotonic\n"); + break; + case CLOCK_MONOTONIC_RAW: + name = "monotonic_raw\n"; + sz = sizeof("monotonic_raw\n"); + break; + case CLOCK_REALTIME_COARSE: + name = "realtime_coarse\n"; + sz = sizeof("realtime_coarse\n"); + break; + case CLOCK_MONOTONIC_COARSE: + name = "monotonic_coarse\n"; + sz = sizeof("monotonic_coarse\n"); + break; + case CLOCK_BOOTTIME: + name = "boottime\n"; + sz = sizeof("boottime\n"); + break; + case CLOCK_TAI: + name = "tai\n"; + sz = sizeof("tai\n"); + break; + default: + BUG(); + } + + memcpy(buf, name, sz); + return sz; +} + +static ssize_t iio_store_timestamp_clock(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + clockid_t clk; + int ret; + + if (sysfs_streq(buf, "realtime")) + clk = CLOCK_REALTIME; + else if (sysfs_streq(buf, "monotonic")) + clk = CLOCK_MONOTONIC; + else if (sysfs_streq(buf, "monotonic_raw")) + clk = CLOCK_MONOTONIC_RAW; + else if (sysfs_streq(buf, "realtime_coarse")) + clk = CLOCK_REALTIME_COARSE; + else if (sysfs_streq(buf, "monotonic_coarse")) + clk = CLOCK_MONOTONIC_COARSE; + else if (sysfs_streq(buf, "boottime")) + clk = CLOCK_BOOTTIME; + else if (sysfs_streq(buf, "tai")) + clk = CLOCK_TAI; + else + return -EINVAL; + + ret = iio_device_set_clock(dev_to_iio_dev(dev), clk); + if (ret) + return ret; + + return len; +} + +static DEVICE_ATTR(current_timestamp_clock, S_IRUGO | S_IWUSR, + iio_show_timestamp_clock, iio_store_timestamp_clock); + static int iio_device_register_sysfs(struct iio_dev *indio_dev) { int i, ret = 0, attrcount, attrn, attrcount_orig = 0; struct iio_dev_attr *p; - struct attribute **attr; + struct attribute **attr, *clk = NULL; /* First count elements in any existing group */ if (indio_dev->info->attrs) { @@ -1009,16 +1169,25 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) */ if (indio_dev->channels) for (i = 0; i < indio_dev->num_channels; i++) { - ret = iio_device_add_channel_sysfs(indio_dev, - &indio_dev - ->channels[i]); + const struct iio_chan_spec *chan = + &indio_dev->channels[i]; + + if (chan->type == IIO_TIMESTAMP) + clk = &dev_attr_current_timestamp_clock.attr; + + ret = iio_device_add_channel_sysfs(indio_dev, chan); if (ret < 0) goto error_clear_attrs; attrcount += ret; } + if (indio_dev->event_interface) + clk = &dev_attr_current_timestamp_clock.attr; + if (indio_dev->name) attrcount++; + if (clk) + attrcount++; indio_dev->chan_attr_group.attrs = kcalloc(attrcount + 1, sizeof(indio_dev->chan_attr_group.attrs[0]), @@ -1039,6 +1208,8 @@ static int iio_device_register_sysfs(struct iio_dev *indio_dev) indio_dev->chan_attr_group.attrs[attrn++] = &p->dev_attr.attr; if (indio_dev->name) indio_dev->chan_attr_group.attrs[attrn++] = &dev_attr_name.attr; + if (clk) + indio_dev->chan_attr_group.attrs[attrn++] = clk; indio_dev->groups[indio_dev->groupcounter++] = &indio_dev->chan_attr_group; diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c index cae332b1d7ea..0ebfc923a997 100644 --- a/drivers/iio/industrialio-event.c +++ b/drivers/iio/industrialio-event.c @@ -44,6 +44,11 @@ struct iio_event_interface { struct mutex read_lock; }; +bool iio_event_enabled(const struct iio_event_interface *ev_int) +{ + return !!test_bit(IIO_BUSY_BIT_POS, &ev_int->flags); +} + /** * iio_push_event() - try to add event to the list for userspace reading * @indio_dev: IIO device structure @@ -60,7 +65,7 @@ int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp) int copied; /* Does anyone care? */ - if (test_bit(IIO_BUSY_BIT_POS, &ev_int->flags)) { + if (iio_event_enabled(ev_int)) { ev.id = ev_code; ev.timestamp = timestamp; @@ -180,8 +185,14 @@ int iio_event_getfd(struct iio_dev *indio_dev) if (ev_int == NULL) return -ENODEV; - if (test_and_set_bit(IIO_BUSY_BIT_POS, &ev_int->flags)) - return -EBUSY; + fd = mutex_lock_interruptible(&indio_dev->mlock); + if (fd) + return fd; + + if (test_and_set_bit(IIO_BUSY_BIT_POS, &ev_int->flags)) { + fd = -EBUSY; + goto unlock; + } iio_device_get(indio_dev); @@ -194,6 +205,8 @@ int iio_event_getfd(struct iio_dev *indio_dev) kfifo_reset_out(&ev_int->det_events); } +unlock: + mutex_unlock(&indio_dev->mlock); return fd; } diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index 98457f044aa5..7ad82fdd3e5b 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -289,7 +289,7 @@ static int iio_trigger_detach_poll_func(struct iio_trigger *trig, irqreturn_t iio_pollfunc_store_time(int irq, void *p) { struct iio_poll_func *pf = p; - pf->timestamp = iio_get_time_ns(); + pf->timestamp = iio_get_time_ns(pf->indio_dev); return IRQ_WAKE_THREAD; } EXPORT_SYMBOL(iio_pollfunc_store_time); diff --git a/drivers/iio/light/acpi-als.c b/drivers/iio/light/acpi-als.c index 53201d99a16c..f0b47c501f4e 100644 --- a/drivers/iio/light/acpi-als.c +++ b/drivers/iio/light/acpi-als.c @@ -118,7 +118,7 @@ static void acpi_als_notify(struct acpi_device *device, u32 event) struct iio_dev *indio_dev = acpi_driver_data(device); struct acpi_als *als = iio_priv(indio_dev); s32 *buffer = als->evt_buffer; - s64 time_ns = iio_get_time_ns(); + s64 time_ns = iio_get_time_ns(indio_dev); s32 val; int ret; diff --git a/drivers/iio/light/adjd_s311.c b/drivers/iio/light/adjd_s311.c index 09ad5f1ce539..0113fc843a81 100644 --- a/drivers/iio/light/adjd_s311.c +++ b/drivers/iio/light/adjd_s311.c @@ -118,7 +118,7 @@ static irqreturn_t adjd_s311_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; struct adjd_s311_data *data = iio_priv(indio_dev); - s64 time_ns = iio_get_time_ns(); + s64 time_ns = iio_get_time_ns(indio_dev); int i, j = 0; int ret = adjd_s311_req_data(indio_dev); diff --git a/drivers/iio/light/apds9300.c b/drivers/iio/light/apds9300.c index e1b9fa5a7e91..649b26f67813 100644 --- a/drivers/iio/light/apds9300.c +++ b/drivers/iio/light/apds9300.c @@ -396,7 +396,7 @@ static irqreturn_t apds9300_interrupt_handler(int irq, void *private) IIO_UNMOD_EVENT_CODE(IIO_INTENSITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(dev_info)); apds9300_clear_intr(data); diff --git a/drivers/iio/light/apds9960.c b/drivers/iio/light/apds9960.c index 651d57b8abbf..a4304edc3e0f 100644 --- a/drivers/iio/light/apds9960.c +++ b/drivers/iio/light/apds9960.c @@ -807,7 +807,7 @@ static irqreturn_t apds9960_interrupt_handler(int irq, void *private) IIO_UNMOD_EVENT_CODE(IIO_INTENSITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); regmap_write(data->regmap, APDS9960_REG_CICLEAR, 1); } @@ -816,7 +816,7 @@ static irqreturn_t apds9960_interrupt_handler(int irq, void *private) IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); regmap_write(data->regmap, APDS9960_REG_PICLEAR, 1); } diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c index c8d7b5ea7e78..9d66e89c57ef 100644 --- a/drivers/iio/light/cm36651.c +++ b/drivers/iio/light/cm36651.c @@ -268,7 +268,7 @@ static irqreturn_t cm36651_irq_handler(int irq, void *data) CM36651_CMD_READ_RAW_PROXIMITY, IIO_EV_TYPE_THRESH, ev_dir); - iio_push_event(indio_dev, ev_code, iio_get_time_ns()); + iio_push_event(indio_dev, ev_code, iio_get_time_ns(indio_dev)); return IRQ_HANDLED; } diff --git a/drivers/iio/light/gp2ap020a00f.c b/drivers/iio/light/gp2ap020a00f.c index af73af3586a9..6ada9149f142 100644 --- a/drivers/iio/light/gp2ap020a00f.c +++ b/drivers/iio/light/gp2ap020a00f.c @@ -851,7 +851,7 @@ static irqreturn_t gp2ap020a00f_prox_sensing_handler(int irq, void *data) GP2AP020A00F_SCAN_MODE_PROXIMITY, IIO_EV_TYPE_ROC, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } else { iio_push_event(indio_dev, IIO_UNMOD_EVENT_CODE( @@ -859,7 +859,7 @@ static irqreturn_t gp2ap020a00f_prox_sensing_handler(int irq, void *data) GP2AP020A00F_SCAN_MODE_PROXIMITY, IIO_EV_TYPE_ROC, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } } @@ -925,7 +925,7 @@ static irqreturn_t gp2ap020a00f_thresh_event_handler(int irq, void *data) IIO_MOD_LIGHT_CLEAR, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } if (test_bit(GP2AP020A00F_FLAG_ALS_FALLING_EV, &priv->flags)) { @@ -939,7 +939,7 @@ static irqreturn_t gp2ap020a00f_thresh_event_handler(int irq, void *data) IIO_MOD_LIGHT_CLEAR, IIO_EV_TYPE_THRESH, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } } diff --git a/drivers/iio/light/isl29125.c b/drivers/iio/light/isl29125.c index a6b9d66233d5..f48b9e5bdb0e 100644 --- a/drivers/iio/light/isl29125.c +++ b/drivers/iio/light/isl29125.c @@ -188,7 +188,7 @@ static irqreturn_t isl29125_trigger_handler(int irq, void *p) } iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/light/lm3533-als.c b/drivers/iio/light/lm3533-als.c index e56937c40a18..f409c2047c05 100644 --- a/drivers/iio/light/lm3533-als.c +++ b/drivers/iio/light/lm3533-als.c @@ -267,7 +267,7 @@ static irqreturn_t lm3533_als_isr(int irq, void *dev_id) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); out: return IRQ_HANDLED; } diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 6bf89d8f3741..3afc53a3d0b6 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -1256,7 +1256,8 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p) buf[j++] = psdata & LTR501_PS_DATA_MASK; } - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); @@ -1282,14 +1283,14 @@ static irqreturn_t ltr501_interrupt_handler(int irq, void *private) IIO_UNMOD_EVENT_CODE(IIO_INTENSITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); if (status & LTR501_STATUS_PS_INTR) iio_push_event(indio_dev, IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); return IRQ_HANDLED; } diff --git a/drivers/iio/light/max44000.c b/drivers/iio/light/max44000.c index f17cb2ea18f5..6511b20a2a29 100644 --- a/drivers/iio/light/max44000.c +++ b/drivers/iio/light/max44000.c @@ -511,7 +511,8 @@ static irqreturn_t max44000_trigger_handler(int irq, void *p) } mutex_unlock(&data->lock); - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c index b776c8ed4387..78c9b3a6453a 100644 --- a/drivers/iio/light/opt3001.c +++ b/drivers/iio/light/opt3001.c @@ -713,13 +713,13 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) IIO_UNMOD_EVENT_CODE(IIO_LIGHT, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(iio)); if (ret & OPT3001_CONFIGURATION_FL) iio_push_event(iio, IIO_UNMOD_EVENT_CODE(IIO_LIGHT, 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(iio)); } else if (ret & OPT3001_CONFIGURATION_CRF) { ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_RESULT); if (ret < 0) { diff --git a/drivers/iio/light/stk3310.c b/drivers/iio/light/stk3310.c index 9e847f8f4f0c..45cf8b0a4363 100644 --- a/drivers/iio/light/stk3310.c +++ b/drivers/iio/light/stk3310.c @@ -528,7 +528,7 @@ static irqreturn_t stk3310_irq_handler(int irq, void *private) struct iio_dev *indio_dev = private; struct stk3310_data *data = iio_priv(indio_dev); - data->timestamp = iio_get_time_ns(); + data->timestamp = iio_get_time_ns(indio_dev); return IRQ_WAKE_THREAD; } diff --git a/drivers/iio/light/tcs3414.c b/drivers/iio/light/tcs3414.c index 8a15fb541dc3..a795afb7667b 100644 --- a/drivers/iio/light/tcs3414.c +++ b/drivers/iio/light/tcs3414.c @@ -216,7 +216,7 @@ static irqreturn_t tcs3414_trigger_handler(int irq, void *p) } iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/light/tcs3472.c b/drivers/iio/light/tcs3472.c index b29312f99077..3aa71e34ae28 100644 --- a/drivers/iio/light/tcs3472.c +++ b/drivers/iio/light/tcs3472.c @@ -202,7 +202,7 @@ static irqreturn_t tcs3472_trigger_handler(int irq, void *p) } iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c index 57b108c30e98..04598ae993d4 100644 --- a/drivers/iio/light/tsl2563.c +++ b/drivers/iio/light/tsl2563.c @@ -630,7 +630,7 @@ static irqreturn_t tsl2563_event_handler(int irq, void *private) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), - iio_get_time_ns()); + iio_get_time_ns(dev_info)); /* clear the interrupt and push the event */ i2c_smbus_write_byte(chip->client, TSL2563_CMD | TSL2563_CLEARINT); diff --git a/drivers/iio/light/us5182d.c b/drivers/iio/light/us5182d.c index 45bc2f742f46..20c40f780964 100644 --- a/drivers/iio/light/us5182d.c +++ b/drivers/iio/light/us5182d.c @@ -833,7 +833,7 @@ static irqreturn_t us5182d_irq_thread_handler(int irq, void *private) dir = ret & US5182D_CFG0_PROX ? IIO_EV_DIR_RISING : IIO_EV_DIR_FALLING; ev = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 1, IIO_EV_TYPE_THRESH, dir); - iio_push_event(indio_dev, ev, iio_get_time_ns()); + iio_push_event(indio_dev, ev, iio_get_time_ns(indio_dev)); ret = i2c_smbus_write_byte_data(data->client, US5182D_REG_CFG0, ret & ~US5182D_CFG0_PX_IRQ); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 57d3654d7caf..2121b50ab9b3 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -829,7 +829,8 @@ static void ak8975_fill_buffer(struct iio_dev *indio_dev) buff[1] = clamp_t(s16, le16_to_cpu(buff[1]), -def->range, def->range); buff[2] = clamp_t(s16, le16_to_cpu(buff[2]), -def->range, def->range); - iio_push_to_buffers_with_timestamp(indio_dev, buff, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buff, + iio_get_time_ns(indio_dev)); return; unlock: diff --git a/drivers/iio/magnetometer/hmc5843_core.c b/drivers/iio/magnetometer/hmc5843_core.c index 77882b466e0f..ba3e2a374ee5 100644 --- a/drivers/iio/magnetometer/hmc5843_core.c +++ b/drivers/iio/magnetometer/hmc5843_core.c @@ -451,7 +451,7 @@ static irqreturn_t hmc5843_trigger_handler(int irq, void *p) goto done; iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c index 261d517428e4..f2be4a049056 100644 --- a/drivers/iio/magnetometer/mag3110.c +++ b/drivers/iio/magnetometer/mag3110.c @@ -261,7 +261,7 @@ static irqreturn_t mag3110_trigger_handler(int irq, void *p) } iio_push_to_buffers_with_timestamp(indio_dev, buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c index 01b2e0b18878..6392d7b62841 100644 --- a/drivers/iio/pressure/mpl3115.c +++ b/drivers/iio/pressure/mpl3115.c @@ -171,7 +171,7 @@ static irqreturn_t mpl3115_trigger_handler(int irq, void *p) mutex_unlock(&data->lock); iio_push_to_buffers_with_timestamp(indio_dev, buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); done: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c index 76578b07bb6e..feb41f82c64a 100644 --- a/drivers/iio/pressure/ms5611_core.c +++ b/drivers/iio/pressure/ms5611_core.c @@ -224,7 +224,8 @@ static irqreturn_t ms5611_trigger_handler(int irq, void *p) if (ret < 0) goto err; - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); err: iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c index c0b0e82abf94..3141c3c161bb 100644 --- a/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c +++ b/drivers/iio/proximity/pulsedlight-lidar-lite-v2.c @@ -238,7 +238,7 @@ static irqreturn_t lidar_trigger_handler(int irq, void *private) ret = lidar_get_measurement(data, data->buffer); if (!ret) { iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } else if (ret != -EINVAL) { dev_err(&data->client->dev, "cannot read LIDAR measurement"); } diff --git a/drivers/iio/proximity/sx9500.c b/drivers/iio/proximity/sx9500.c index 66cd09a18786..1d74b3aafeed 100644 --- a/drivers/iio/proximity/sx9500.c +++ b/drivers/iio/proximity/sx9500.c @@ -492,7 +492,7 @@ static void sx9500_push_events(struct iio_dev *indio_dev) dir = new_prox ? IIO_EV_DIR_FALLING : IIO_EV_DIR_RISING; ev = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, chan, IIO_EV_TYPE_THRESH, dir); - iio_push_event(indio_dev, ev, iio_get_time_ns()); + iio_push_event(indio_dev, ev, iio_get_time_ns(indio_dev)); data->prox_stat[chan] = new_prox; } } @@ -669,7 +669,7 @@ static irqreturn_t sx9500_trigger_handler(int irq, void *private) } iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); out: mutex_unlock(&data->mutex); diff --git a/drivers/staging/iio/accel/lis3l02dq_core.c b/drivers/staging/iio/accel/lis3l02dq_core.c index 7a6fed3f2d3f..5c3410a74fdb 100644 --- a/drivers/staging/iio/accel/lis3l02dq_core.c +++ b/drivers/staging/iio/accel/lis3l02dq_core.c @@ -451,7 +451,7 @@ static irqreturn_t lis3l02dq_event_handler(int irq, void *private) struct iio_dev *indio_dev = private; u8 t; - s64 timestamp = iio_get_time_ns(); + s64 timestamp = iio_get_time_ns(indio_dev); lis3l02dq_spi_read_reg_8(indio_dev, LIS3L02DQ_REG_WAKE_UP_SRC_ADDR, diff --git a/drivers/staging/iio/accel/sca3000_core.c b/drivers/staging/iio/accel/sca3000_core.c index 53c5425d02b3..aacf643e87d3 100644 --- a/drivers/staging/iio/accel/sca3000_core.c +++ b/drivers/staging/iio/accel/sca3000_core.c @@ -774,7 +774,7 @@ static irqreturn_t sca3000_event_handler(int irq, void *private) struct iio_dev *indio_dev = private; struct sca3000_state *st = iio_priv(indio_dev); int ret, val; - s64 last_timestamp = iio_get_time_ns(); + s64 last_timestamp = iio_get_time_ns(indio_dev); /* * Could lead if badly timed to an extra read of status reg, diff --git a/drivers/staging/iio/adc/ad7280a.c b/drivers/staging/iio/adc/ad7280a.c index a06b46cb81ca..2177f1dd2b5d 100644 --- a/drivers/staging/iio/adc/ad7280a.c +++ b/drivers/staging/iio/adc/ad7280a.c @@ -705,7 +705,7 @@ static irqreturn_t ad7280_event_handler(int irq, void *private) IIO_EV_DIR_RISING, IIO_EV_TYPE_THRESH, 0, 0, 0), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); else if (((channels[i] >> 11) & 0xFFF) <= st->cell_threshlow) iio_push_event(indio_dev, @@ -715,7 +715,7 @@ static irqreturn_t ad7280_event_handler(int irq, void *private) IIO_EV_DIR_FALLING, IIO_EV_TYPE_THRESH, 0, 0, 0), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } else { if (((channels[i] >> 11) & 0xFFF) >= st->aux_threshhigh) iio_push_event(indio_dev, @@ -724,7 +724,7 @@ static irqreturn_t ad7280_event_handler(int irq, void *private) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); else if (((channels[i] >> 11) & 0xFFF) <= st->aux_threshlow) iio_push_event(indio_dev, @@ -733,7 +733,7 @@ static irqreturn_t ad7280_event_handler(int irq, void *private) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_FALLING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } } diff --git a/drivers/staging/iio/adc/ad7606_ring.c b/drivers/staging/iio/adc/ad7606_ring.c index a6f8eb11242c..0572df9aad85 100644 --- a/drivers/staging/iio/adc/ad7606_ring.c +++ b/drivers/staging/iio/adc/ad7606_ring.c @@ -77,7 +77,8 @@ static void ad7606_poll_bh_to_ring(struct work_struct *work_s) goto done; } - iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns()); + iio_push_to_buffers_with_timestamp(indio_dev, buf, + iio_get_time_ns(indio_dev)); done: gpio_set_value(st->pdata->gpio_convst, 0); iio_trigger_notify_done(indio_dev->trig); diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c index ac3735c7f4a9..5e8115b01011 100644 --- a/drivers/staging/iio/adc/ad7816.c +++ b/drivers/staging/iio/adc/ad7816.c @@ -253,7 +253,8 @@ static const struct attribute_group ad7816_attribute_group = { static irqreturn_t ad7816_event_handler(int irq, void *private) { - iio_push_event(private, IIO_EVENT_CODE_AD7816_OTI, iio_get_time_ns()); + iio_push_event(private, IIO_EVENT_CODE_AD7816_OTI, + iio_get_time_ns((struct iio_dev *)private)); return IRQ_HANDLED; } diff --git a/drivers/staging/iio/addac/adt7316.c b/drivers/staging/iio/addac/adt7316.c index a10e7d8e6002..3faffe59c933 100644 --- a/drivers/staging/iio/addac/adt7316.c +++ b/drivers/staging/iio/addac/adt7316.c @@ -1752,7 +1752,7 @@ static irqreturn_t adt7316_event_handler(int irq, void *private) if ((chip->id & ID_FAMILY_MASK) != ID_ADT75XX) stat1 &= 0x1F; - time = iio_get_time_ns(); + time = iio_get_time_ns(indio_dev); if (stat1 & BIT(0)) iio_push_event(indio_dev, IIO_UNMOD_EVENT_CODE(IIO_TEMP, 0, @@ -1804,7 +1804,7 @@ static irqreturn_t adt7316_event_handler(int irq, void *private) 0, IIO_EV_TYPE_THRESH, IIO_EV_DIR_RISING), - iio_get_time_ns()); + iio_get_time_ns(indio_dev)); } return IRQ_HANDLED; diff --git a/drivers/staging/iio/cdc/ad7150.c b/drivers/staging/iio/cdc/ad7150.c index f6b9a10326ea..5578a077fcfb 100644 --- a/drivers/staging/iio/cdc/ad7150.c +++ b/drivers/staging/iio/cdc/ad7150.c @@ -493,7 +493,7 @@ static irqreturn_t ad7150_event_handler(int irq, void *private) struct iio_dev *indio_dev = private; struct ad7150_chip_info *chip = iio_priv(indio_dev); u8 int_status; - s64 timestamp = iio_get_time_ns(); + s64 timestamp = iio_get_time_ns(indio_dev); int ret; ret = i2c_smbus_read_byte_data(chip->client, AD7150_STATUS); diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c index d553c8e18fcc..ea15bc1c300c 100644 --- a/drivers/staging/iio/light/tsl2x7x_core.c +++ b/drivers/staging/iio/light/tsl2x7x_core.c @@ -1554,7 +1554,7 @@ static irqreturn_t tsl2x7x_event_handler(int irq, void *private) { struct iio_dev *indio_dev = private; struct tsl2X7X_chip *chip = iio_priv(indio_dev); - s64 timestamp = iio_get_time_ns(); + s64 timestamp = iio_get_time_ns(indio_dev); int ret; u8 value; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 7c29cb0124ae..854e2dad1e0d 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -312,13 +312,8 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan, }, \ } -/** - * iio_get_time_ns() - utility function to get a time stamp for events etc - **/ -static inline s64 iio_get_time_ns(void) -{ - return ktime_get_real_ns(); -} +s64 iio_get_time_ns(const struct iio_dev *indio_dev); +unsigned int iio_get_time_res(const struct iio_dev *indio_dev); /* Device operating modes */ #define INDIO_DIRECT_MODE 0x01 @@ -497,6 +492,7 @@ struct iio_buffer_setup_ops { * @chan_attr_group: [INTERN] group for all attrs in base directory * @name: [DRIVER] name of the device. * @info: [DRIVER] callbacks and constant info from driver + * @clock_id: [INTERN] timestamping clock posix identifier * @info_exist_lock: [INTERN] lock to prevent use during removal * @setup_ops: [DRIVER] callbacks to call before and after buffer * enable/disable @@ -537,6 +533,7 @@ struct iio_dev { struct attribute_group chan_attr_group; const char *name; const struct iio_info *info; + clockid_t clock_id; struct mutex info_exist_lock; const struct iio_buffer_setup_ops *setup_ops; struct cdev chrdev; @@ -565,7 +562,7 @@ extern struct bus_type iio_bus_type; /** * iio_device_put() - reference counted deallocation of struct device - * @indio_dev: IIO device structure containing the device + * @indio_dev: IIO device structure containing the device **/ static inline void iio_device_put(struct iio_dev *indio_dev) { @@ -573,6 +570,15 @@ static inline void iio_device_put(struct iio_dev *indio_dev) put_device(&indio_dev->dev); } +/** + * iio_device_get_clock() - Retrieve current timestamping clock for the device + * @indio_dev: IIO device structure containing the device + */ +static inline clockid_t iio_device_get_clock(const struct iio_dev *indio_dev) +{ + return indio_dev->clock_id; +} + /** * dev_to_iio_dev() - Get IIO device struct from a device struct * @dev: The device embedded in the IIO device -- cgit v1.2.3 From f87fda00b6ed232a817c655b8d179b48bde8fdbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 30 Jun 2016 16:13:41 +0200 Subject: bonding: prevent out of bound accesses ether_addr_equal_64bits() requires some care about its arguments, namely that 8 bytes might be read, even if last 2 byte values are not used. KASan detected a violation with null_mac_addr and lacpdu_mcast_addr in bond_3ad.c Same problem with mac_bcast[] and mac_v6_allmcast[] in bond_alb.c : Although the 8-byte alignment was there, KASan would detect out of bound accesses. Fixes: 815117adaf5b ("bonding: use ether_addr_equal_unaligned for bond addr compare") Fixes: bb54e58929f3 ("bonding: Verify RX LACPDU has proper dest mac-addr") Fixes: 885a136c52a8 ("bonding: use compare_ether_addr_64bits() in ALB") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Acked-by: Dmitry Vyukov Acked-by: Nikolay Aleksandrov Acked-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/bonding/bond_3ad.c | 11 +++++++---- drivers/net/bonding/bond_alb.c | 7 ++----- include/net/bonding.h | 7 ++++++- 3 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index ca81f46ea1aa..edc70ffad660 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -101,11 +101,14 @@ enum ad_link_speed_type { #define MAC_ADDRESS_EQUAL(A, B) \ ether_addr_equal_64bits((const u8 *)A, (const u8 *)B) -static struct mac_addr null_mac_addr = { { 0, 0, 0, 0, 0, 0 } }; +static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = { + 0, 0, 0, 0, 0, 0 +}; static u16 ad_ticks_per_sec; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; -static const u8 lacpdu_mcast_addr[ETH_ALEN] = MULTICAST_LACPDU_ADDR; +static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = + MULTICAST_LACPDU_ADDR; /* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); @@ -1739,7 +1742,7 @@ static void ad_clear_agg(struct aggregator *aggregator) aggregator->is_individual = false; aggregator->actor_admin_aggregator_key = 0; aggregator->actor_oper_aggregator_key = 0; - aggregator->partner_system = null_mac_addr; + eth_zero_addr(aggregator->partner_system.mac_addr_value); aggregator->partner_system_priority = 0; aggregator->partner_oper_aggregator_key = 0; aggregator->receive_state = 0; @@ -1761,7 +1764,7 @@ static void ad_initialize_agg(struct aggregator *aggregator) if (aggregator) { ad_clear_agg(aggregator); - aggregator->aggregator_mac_address = null_mac_addr; + eth_zero_addr(aggregator->aggregator_mac_address.mac_addr_value); aggregator->aggregator_identifier = 0; aggregator->slave = NULL; } diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index c5ac160a8ae9..551f0f8dead3 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -42,13 +42,10 @@ -#ifndef __long_aligned -#define __long_aligned __attribute__((aligned((sizeof(long))))) -#endif -static const u8 mac_bcast[ETH_ALEN] __long_aligned = { +static const u8 mac_bcast[ETH_ALEN + 2] __long_aligned = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; -static const u8 mac_v6_allmcast[ETH_ALEN] __long_aligned = { +static const u8 mac_v6_allmcast[ETH_ALEN + 2] __long_aligned = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x01 }; static const int alb_delta_in_ticks = HZ / ALB_TIMER_TICKS_PER_SEC; diff --git a/include/net/bonding.h b/include/net/bonding.h index 791800ddd6d9..6360c259da6d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -34,6 +34,9 @@ #define BOND_DEFAULT_MIIMON 100 +#ifndef __long_aligned +#define __long_aligned __attribute__((aligned((sizeof(long))))) +#endif /* * Less bad way to call ioctl from within the kernel; this needs to be * done some other way to get the call out of interrupt context. @@ -138,7 +141,9 @@ struct bond_params { struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; - u8 ad_actor_system[ETH_ALEN]; + + /* 2 bytes of padding : see ether_addr_equal_64bits() */ + u8 ad_actor_system[ETH_ALEN + 2]; }; struct bond_parm_tbl { -- cgit v1.2.3 From 65ee67084589c1783a74b4a4a5db38d7264ec8b5 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 30 Jun 2016 17:34:43 +0300 Subject: net/mlx5: Add timeout handle to commands with callback The current implementation does not handle timeout in case of command with callback request, and this can lead to deadlock if the command doesn't get fw response. Add delayed callback timeout work before posting the command to fw. In case of real fw command completion we will cancel the delayed work. In case of fw command timeout the callback timeout handler will be called and it will simulate fw completion with timeout error. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 38 ++++++++++++++++++++++----- include/linux/mlx5/driver.h | 1 + 2 files changed, 32 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 74067f547aa6..d6e2a1cae19a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -606,11 +606,36 @@ static void dump_command(struct mlx5_core_dev *dev, pr_debug("\n"); } +static u16 msg_to_opcode(struct mlx5_cmd_msg *in) +{ + struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data); + + return be16_to_cpu(hdr->opcode); +} + +static void cb_timeout_handler(struct work_struct *work) +{ + struct delayed_work *dwork = container_of(work, struct delayed_work, + work); + struct mlx5_cmd_work_ent *ent = container_of(dwork, + struct mlx5_cmd_work_ent, + cb_timeout_work); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, + cmd); + + ent->ret = -ETIMEDOUT; + mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", + mlx5_command_str(msg_to_opcode(ent->in)), + msg_to_opcode(ent->in)); + mlx5_cmd_comp_handler(dev, 1UL << ent->idx); +} + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); + unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); struct mlx5_cmd_layout *lay; struct semaphore *sem; unsigned long flags; @@ -651,6 +676,9 @@ static void cmd_work_handler(struct work_struct *work) dump_command(dev, ent, 1); ent->ts1 = ktime_get_ns(); + if (ent->callback) + schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -695,13 +723,6 @@ static const char *deliv_status_to_str(u8 status) } } -static u16 msg_to_opcode(struct mlx5_cmd_msg *in) -{ - struct mlx5_inbox_hdr *hdr = (struct mlx5_inbox_hdr *)(in->first.data); - - return be16_to_cpu(hdr->opcode); -} - static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); @@ -765,6 +786,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (!callback) init_completion(&ent->done); + INIT_DELAYED_WORK(&ent->cb_timeout_work, cb_timeout_handler); INIT_WORK(&ent->work, cmd_work_handler); if (page_queue) { cmd_work_handler(&ent->work); @@ -1242,6 +1264,8 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec) struct semaphore *sem; ent = cmd->ent_arr[i]; + if (ent->callback) + cancel_delayed_work(&ent->cb_timeout_work); if (ent->page_queue) sem = &cmd->pages_sem; else diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80776d0c52dc..fd72ecf0ce9f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -629,6 +629,7 @@ struct mlx5_cmd_work_ent { void *uout; int uout_size; mlx5_cmd_cbk_t callback; + struct delayed_work cb_timeout_work; void *context; int idx; struct completion done; -- cgit v1.2.3 From 94477bff390aa4612d2332c8abafaae0a13d6923 Mon Sep 17 00:00:00 2001 From: Sinclair Yeh Date: Wed, 29 Jun 2016 12:58:49 -0700 Subject: drm/ttm: Make ttm_bo_mem_compat available There are cases where it is desired to see if a proposed placement is compatible with a buffer object before calling ttm_bo_validate(). Signed-off-by: Sinclair Yeh Reviewed-by: Thomas Hellstrom Cc: --- This is the first of a 3-patch series to fix a black screen issue observed on Ubuntu 16.04 server. --- drivers/gpu/drm/ttm/ttm_bo.c | 7 ++++--- include/drm/ttm/ttm_bo_api.h | 14 ++++++++++++++ 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 39386f50af87..a71cf98c655f 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1034,9 +1034,9 @@ out_unlock: return ret; } -static bool ttm_bo_mem_compat(struct ttm_placement *placement, - struct ttm_mem_reg *mem, - uint32_t *new_flags) +bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags) { int i; @@ -1068,6 +1068,7 @@ static bool ttm_bo_mem_compat(struct ttm_placement *placement, return false; } +EXPORT_SYMBOL(ttm_bo_mem_compat); int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index c801d9028e37..4cecb0b75b9c 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -316,6 +316,20 @@ ttm_bo_reference(struct ttm_buffer_object *bo) */ extern int ttm_bo_wait(struct ttm_buffer_object *bo, bool interruptible, bool no_wait); + +/** + * ttm_bo_mem_compat - Check if proposed placement is compatible with a bo + * + * @placement: Return immediately if buffer is busy. + * @mem: The struct ttm_mem_reg indicating the region where the bo resides + * @new_flags: Describes compatible placement found + * + * Returns true if the placement is compatible + */ +extern bool ttm_bo_mem_compat(struct ttm_placement *placement, + struct ttm_mem_reg *mem, + uint32_t *new_flags); + /** * ttm_bo_validate * -- cgit v1.2.3 From eb70db8756717b90c01ccc765fdefc4dd969fc74 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 1 Jul 2016 16:07:50 -0400 Subject: packet: Use symmetric hash for PACKET_FANOUT_HASH. People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that they want packets going in both directions on a flow to hash to the same bucket. The core kernel SKB hash became non-symmetric when the ipv6 flow label and other entities were incorporated into the standard flow hash order to increase entropy. But there are no users of PACKET_FANOUT_HASH who want an assymetric hash, they all want a symmetric one. Therefore, use the flow dissector to compute a flat symmetric hash over only the protocol, addresses and ports. This hash does not get installed into and override the normal skb hash, so this change has no effect whatsoever on the rest of the stack. Reported-by: Eric Leblond Tested-by: Eric Leblond Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++ net/packet/af_packet.c | 2 +- 3 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ee38a4127475..24859d40acde 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) } void __skb_get_hash(struct sk_buff *skb); +u32 __skb_get_hash_symmetric(struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a669dea146c6..61ad43f61c5e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9bff6ef16fa7..9f0983fa4d52 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_scale(skb_get_hash(skb), num); + return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, -- cgit v1.2.3 From 82a31b9231f02d9c1b7b290a46999d517b0d312a Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 30 Jun 2016 10:15:22 -0700 Subject: net_sched: fix mirrored packets checksum Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation") we need to fixup the checksum for CHECKSUM_COMPLETE when pushing skb on RX path. Otherwise we get similar splats. Cc: Jamal Hadi Salim Cc: Tom Herbert Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 +++++++++++++++++++ net/core/skbuff.c | 18 ------------------ net/sched/act_mirred.c | 2 +- 3 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24859d40acde..f39b37180c41 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2870,6 +2870,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_partial(start, len, skb->csum); } +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, + unsigned int len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e549c03..eb12d2161fb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3015,24 +3015,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); -/** - * skb_push_rcsum - push skb and update receive checksum - * @skb: buffer to update - * @len: length of data pulled - * - * This function performs an skb_push on the packet and updates - * the CHECKSUM_COMPLETE checksum. It should be used on - * receive path processing instead of skb_push unless you know - * that the checksum difference is zero (e.g., a valid IP header) - * or you are setting ip_summed to CHECKSUM_NONE. - */ -static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) -{ - skb_push(skb, len); - skb_postpush_rcsum(skb, skb->data, len); - return skb->data; -} - /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942bc9e42..1f5bd6ccbd2c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb->mac_len); + skb_push_rcsum(skb2, skb->mac_len); } /* mirror is always swallowed */ -- cgit v1.2.3 From 487cf917ed0d12afaf403d9d77684bf44b8c13be Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Wed, 29 Jun 2016 04:27:36 -0400 Subject: Revert "ACPI, PCI, IRQ: remove redundant code in acpi_irq_penalty_init()" Trying to make the ISA and PCI init functionality common turned out to be a bad idea, because the ISA path depends on external functionality. Restore the previous behavior and limit the refactoring to PCI interrupts only. Fixes: 1fcb6a813c4f "ACPI,PCI,IRQ: remove redundant code in acpi_irq_penalty_init()" Signed-off-by: Sinan Kaya Tested-by: Wim Osterholt Signed-off-by: Rafael J. Wysocki --- arch/x86/pci/acpi.c | 1 + drivers/acpi/pci_link.c | 36 ++++++++++++++++++++++++++++++++++++ include/acpi/acpi_drivers.h | 1 + 3 files changed, 38 insertions(+) (limited to 'include') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a61f6b..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index db7be62a8222..606083bb3f00 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -517,6 +517,42 @@ static int acpi_irq_get_penalty(int irq) return penalty; } +int __init acpi_irq_penalty_init(void) +{ + struct acpi_pci_link *link; + int i; + + /* + * Update penalties to facilitate IRQ balancing. + */ + list_for_each_entry(link, &acpi_link_list, list) { + + /* + * reflect the possible and active irqs in the penalty table -- + * useful for breaking ties. + */ + if (link->irq.possible_count) { + int penalty = + PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; + + for (i = 0; i < link->irq.possible_count; i++) { + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS) + acpi_isa_irq_penalty[link->irq. + possible[i]] += + penalty; + } + + } else if (link->irq.active && + (link->irq.active < ACPI_MAX_ISA_IRQS)) { + acpi_isa_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; + } + } + + return 0; +} + static int acpi_irq_balance = -1; /* 0: static, 1: balance */ static int acpi_pci_link_allocate(struct acpi_pci_link *link) diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h index 797ae2ec8eee..29c691265b49 100644 --- a/include/acpi/acpi_drivers.h +++ b/include/acpi/acpi_drivers.h @@ -78,6 +78,7 @@ /* ACPI PCI Interrupt Link (pci_link.c) */ +int acpi_irq_penalty_init(void); int acpi_pci_link_allocate_irq(acpi_handle handle, int index, int *triggering, int *polarity, char **name); int acpi_pci_link_free_irq(acpi_handle handle); -- cgit v1.2.3 From 1b6cf310103799f371066453f55755088b008be0 Mon Sep 17 00:00:00 2001 From: Venkat Reddy Talla Date: Thu, 30 Jun 2016 17:54:00 +0900 Subject: extcon: adc-jack: add suspend/resume support adding suspend and resume funtionality for extcon-adc-jack driver to configure system wake up for extcon events, also adding support to enable/disable system wakeup through flag wakeup_source based on platform requirement. Signed-off-by: Venkat Reddy Talla Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon-adc-jack.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/extcon/extcon-adc-jack.h | 2 ++ 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c index 7fc0ae1912f8..44e48aa78a84 100644 --- a/drivers/extcon/extcon-adc-jack.c +++ b/drivers/extcon/extcon-adc-jack.c @@ -38,6 +38,7 @@ * @chan: iio channel being queried. */ struct adc_jack_data { + struct device *dev; struct extcon_dev *edev; const unsigned int **cable_names; @@ -49,6 +50,7 @@ struct adc_jack_data { struct delayed_work handler; struct iio_channel *chan; + bool wakeup_source; }; static void adc_jack_handler(struct work_struct *work) @@ -105,6 +107,7 @@ static int adc_jack_probe(struct platform_device *pdev) return -EINVAL; } + data->dev = &pdev->dev; data->edev = devm_extcon_dev_allocate(&pdev->dev, pdata->cable_names); if (IS_ERR(data->edev)) { dev_err(&pdev->dev, "failed to allocate extcon device\n"); @@ -128,6 +131,7 @@ static int adc_jack_probe(struct platform_device *pdev) return PTR_ERR(data->chan); data->handling_delay = msecs_to_jiffies(pdata->handling_delay_ms); + data->wakeup_source = pdata->wakeup_source; INIT_DEFERRABLE_WORK(&data->handler, adc_jack_handler); @@ -151,6 +155,9 @@ static int adc_jack_probe(struct platform_device *pdev) return err; } + if (data->wakeup_source) + device_init_wakeup(&pdev->dev, 1); + return 0; } @@ -165,11 +172,38 @@ static int adc_jack_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int adc_jack_suspend(struct device *dev) +{ + struct adc_jack_data *data = dev_get_drvdata(dev); + + cancel_delayed_work_sync(&data->handler); + if (device_may_wakeup(data->dev)) + enable_irq_wake(data->irq); + + return 0; +} + +static int adc_jack_resume(struct device *dev) +{ + struct adc_jack_data *data = dev_get_drvdata(dev); + + if (device_may_wakeup(data->dev)) + disable_irq_wake(data->irq); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +static SIMPLE_DEV_PM_OPS(adc_jack_pm_ops, + adc_jack_suspend, adc_jack_resume); + static struct platform_driver adc_jack_driver = { .probe = adc_jack_probe, .remove = adc_jack_remove, .driver = { .name = "adc-jack", + .pm = &adc_jack_pm_ops, }, }; diff --git a/include/linux/extcon/extcon-adc-jack.h b/include/linux/extcon/extcon-adc-jack.h index 53c60806bcfb..ac85f2061351 100644 --- a/include/linux/extcon/extcon-adc-jack.h +++ b/include/linux/extcon/extcon-adc-jack.h @@ -53,6 +53,7 @@ struct adc_jack_cond { * milli-seconds after the interrupt occurs. You may * describe such delays with @handling_delay_ms, which * is rounded-off by jiffies. + * @wakeup_source: flag to wake up the system for extcon events. */ struct adc_jack_pdata { const char *name; @@ -65,6 +66,7 @@ struct adc_jack_pdata { unsigned long irq_flags; unsigned long handling_delay_ms; /* in ms */ + bool wakeup_source; }; #endif /* _EXTCON_ADC_JACK_H */ -- cgit v1.2.3 From 90efe05562921768d34e44c0292703ea3168ba8d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Jun 2016 15:14:42 +0200 Subject: iio: st_sensors: harden interrupt handling Leonard Crestez observed the following phenomenon: when using hard interrupt triggers (the DRDY line coming out of an ST sensor) sometimes a new value would arrive while reading the previous value, due to latencies in the system. We discovered that the ST hardware as far as can be observed is designed for level interrupts: the DRDY line will be held asserted as long as there are new values coming. The interrupt handler should be re-entered until we're out of values to handle from the sensor. If interrupts were handled as occurring on the edges (usually low-to-high) new values could appear and the line be held asserted after that, and these values would be missed, the interrupt handler would also lock up as new data was available, but as no new edges occurs on the DRDY signal, nothing happens: the edge detector only detects edges. To counter this, do the following: - Accept interrupt lines to be flagged as level interrupts using IRQF_TRIGGER_HIGH and IRQF_TRIGGER_LOW. If the line is marked like this (in the device tree node or ACPI table or similar) it will be utilized as a level IRQ. We mark the line with IRQF_ONESHOT and mask the IRQ while processing a sample, then the top half will be entered again if new values are available. - If we are flagged as using edge interrupts with IRQF_TRIGGER_RISING or IRQF_TRIGGER_FALLING: remove IRQF_ONESHOT so that the interrupt line is not masked while running the thread part of the interrupt. This way we will never miss an interrupt, then introduce a loop that polls the data ready registers repeatedly until no new samples are available, then exit the interrupt handler. This way we know no new values are available when the interrupt handler exits and new (edge) interrupts will be triggered when data arrives. Take some extra care to update the timestamp in the poll loop if this happens. The timestamp will not be 100% perfect, but it will at least be closer to the actual events. Usually the extra poll loop will handle the new samples, but once in a blue moon, we get a new IRQ while exiting the loop, before returning from the thread IRQ bottom half with IRQ_HANDLED. On these rare occasions, the removal of IRQF_ONESHOT means the interrupt will immediately fire again. - If no interrupt type is indicated from the DT/ACPI, choose IRQF_TRIGGER_RISING as default, as this is necessary for legacy boards. Tested successfully on the LIS331DL and L3G4200D by setting sampling frequency to 400Hz/800Hz and stressing the system: extra reads in the threaded interrupt handler occurs. Cc: Giuseppe Barba Cc: Denis Ciocca Tested-by: Crestez Dan Leonard Reported-by: Crestez Dan Leonard Signed-off-by: Linus Walleij Signed-off-by: Jonathan Cameron --- drivers/iio/common/st_sensors/st_sensors_buffer.c | 7 +- drivers/iio/common/st_sensors/st_sensors_trigger.c | 154 +++++++++++++++------ include/linux/iio/common/st_sensors.h | 2 + 3 files changed, 117 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/iio/common/st_sensors/st_sensors_buffer.c b/drivers/iio/common/st_sensors/st_sensors_buffer.c index 7c84e90d8ce8..2371fc875d2d 100644 --- a/drivers/iio/common/st_sensors/st_sensors_buffer.c +++ b/drivers/iio/common/st_sensors/st_sensors_buffer.c @@ -58,7 +58,12 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p) struct st_sensor_data *sdata = iio_priv(indio_dev); s64 timestamp; - /* If we do timetamping here, do it before reading the values */ + /* + * If we do timetamping here, do it before reading the values, because + * once we've read the values, new interrupts can occur (when using + * the hardware trigger) and the hw_timestamp may get updated. + * By storing it in a local variable first, we are safe. + */ if (sdata->hw_irq_trigger) timestamp = sdata->hw_timestamp; else diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index fab494d71951..e66f12ee8a55 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -17,6 +17,50 @@ #include #include "st_sensors_core.h" +/** + * st_sensors_new_samples_available() - check if more samples came in + * returns: + * 0 - no new samples available + * 1 - new samples available + * negative - error or unknown + */ +static int st_sensors_new_samples_available(struct iio_dev *indio_dev, + struct st_sensor_data *sdata) +{ + u8 status; + int ret; + + /* How would I know if I can't check it? */ + if (!sdata->sensor_settings->drdy_irq.addr_stat_drdy) + return -EINVAL; + + /* No scan mask, no interrupt */ + if (!indio_dev->active_scan_mask) + return 0; + + ret = sdata->tf->read_byte(&sdata->tb, sdata->dev, + sdata->sensor_settings->drdy_irq.addr_stat_drdy, + &status); + if (ret < 0) { + dev_err(sdata->dev, + "error checking samples available\n"); + return ret; + } + /* + * the lower bits of .active_scan_mask[0] is directly mapped + * to the channels on the sensor: either bit 0 for + * one-dimensional sensors, or e.g. x,y,z for accelerometers, + * gyroscopes or magnetometers. No sensor use more than 3 + * channels, so cut the other status bits here. + */ + status &= 0x07; + + if (status & (u8)indio_dev->active_scan_mask[0]) + return 1; + + return 0; +} + /** * st_sensors_irq_handler() - top half of the IRQ-based triggers * @irq: irq number @@ -43,44 +87,43 @@ irqreturn_t st_sensors_irq_thread(int irq, void *p) struct iio_trigger *trig = p; struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); struct st_sensor_data *sdata = iio_priv(indio_dev); - int ret; /* * If this trigger is backed by a hardware interrupt and we have a - * status register, check if this IRQ came from us + * status register, check if this IRQ came from us. Notice that + * we will process also if st_sensors_new_samples_available() + * returns negative: if we can't check status, then poll + * unconditionally. */ - if (sdata->sensor_settings->drdy_irq.addr_stat_drdy) { - u8 status; - - ret = sdata->tf->read_byte(&sdata->tb, sdata->dev, - sdata->sensor_settings->drdy_irq.addr_stat_drdy, - &status); - if (ret < 0) { - dev_err(sdata->dev, "could not read channel status\n"); - goto out_poll; - } - /* - * the lower bits of .active_scan_mask[0] is directly mapped - * to the channels on the sensor: either bit 0 for - * one-dimensional sensors, or e.g. x,y,z for accelerometers, - * gyroscopes or magnetometers. No sensor use more than 3 - * channels, so cut the other status bits here. - */ - status &= 0x07; + if (sdata->hw_irq_trigger && + st_sensors_new_samples_available(indio_dev, sdata)) { + iio_trigger_poll_chained(p); + } else { + dev_dbg(sdata->dev, "spurious IRQ\n"); + return IRQ_NONE; + } - /* - * If this was not caused by any channels on this sensor, - * return IRQ_NONE - */ - if (!indio_dev->active_scan_mask) - return IRQ_NONE; - if (!(status & (u8)indio_dev->active_scan_mask[0])) - return IRQ_NONE; + /* + * If we have proper level IRQs the handler will be re-entered if + * the line is still active, so return here and come back in through + * the top half if need be. + */ + if (!sdata->edge_irq) + return IRQ_HANDLED; + + /* + * If we are using egde IRQs, new samples arrived while processing + * the IRQ and those may be missed unless we pick them here, so poll + * again. If the sensor delivery frequency is very high, this thread + * turns into a polled loop handler. + */ + while (sdata->hw_irq_trigger && + st_sensors_new_samples_available(indio_dev, sdata)) { + dev_dbg(sdata->dev, "more samples came in during polling\n"); + sdata->hw_timestamp = iio_get_time_ns(indio_dev); + iio_trigger_poll_chained(p); } -out_poll: - /* It's our IRQ: proceed to handle the register polling */ - iio_trigger_poll_chained(p); return IRQ_HANDLED; } @@ -107,13 +150,18 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, * If the IRQ is triggered on falling edge, we need to mark the * interrupt as active low, if the hardware supports this. */ - if (irq_trig == IRQF_TRIGGER_FALLING) { + switch(irq_trig) { + case IRQF_TRIGGER_FALLING: + case IRQF_TRIGGER_LOW: if (!sdata->sensor_settings->drdy_irq.addr_ihl) { dev_err(&indio_dev->dev, - "falling edge specified for IRQ but hardware " - "only support rising edge, will request " - "rising edge\n"); - irq_trig = IRQF_TRIGGER_RISING; + "falling/low specified for IRQ " + "but hardware only support rising/high: " + "will request rising/high\n"); + if (irq_trig == IRQF_TRIGGER_FALLING) + irq_trig = IRQF_TRIGGER_RISING; + if (irq_trig == IRQF_TRIGGER_LOW) + irq_trig = IRQF_TRIGGER_HIGH; } else { /* Set up INT active low i.e. falling edge */ err = st_sensors_write_data_with_mask(indio_dev, @@ -122,20 +170,39 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, if (err < 0) goto iio_trigger_free; dev_info(&indio_dev->dev, - "interrupts on the falling edge\n"); + "interrupts on the falling edge or " + "active low level\n"); } - } else if (irq_trig == IRQF_TRIGGER_RISING) { + break; + case IRQF_TRIGGER_RISING: dev_info(&indio_dev->dev, "interrupts on the rising edge\n"); - - } else { + break; + case IRQF_TRIGGER_HIGH: + dev_info(&indio_dev->dev, + "interrupts active high level\n"); + break; + default: + /* This is the most preferred mode, if possible */ dev_err(&indio_dev->dev, - "unsupported IRQ trigger specified (%lx), only " - "rising and falling edges supported, enforce " + "unsupported IRQ trigger specified (%lx), enforce " "rising edge\n", irq_trig); irq_trig = IRQF_TRIGGER_RISING; } + /* Tell the interrupt handler that we're dealing with edges */ + if (irq_trig == IRQF_TRIGGER_FALLING || + irq_trig == IRQF_TRIGGER_RISING) + sdata->edge_irq = true; + else + /* + * If we're not using edges (i.e. level interrupts) we + * just mask off the IRQ, handle one interrupt, then + * if the line is still low, we return to the + * interrupt handler top half again and start over. + */ + irq_trig |= IRQF_ONESHOT; + /* * If the interrupt pin is Open Drain, by definition this * means that the interrupt line may be shared with other @@ -148,9 +215,6 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.addr_stat_drdy) irq_trig |= IRQF_SHARED; - /* Let's create an interrupt thread masking the hard IRQ here */ - irq_trig |= IRQF_ONESHOT; - err = request_threaded_irq(sdata->get_irq_data_ready(indio_dev), st_sensors_irq_handler, st_sensors_irq_thread, diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 28052cddaa03..228bd44efa4c 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -223,6 +223,7 @@ struct st_sensor_settings { * @get_irq_data_ready: Function to get the IRQ used for data ready signal. * @tf: Transfer function structure used by I/O operations. * @tb: Transfer buffers and mutex used by I/O operations. + * @edge_irq: the IRQ triggers on edges and need special handling. * @hw_irq_trigger: if we're using the hardware interrupt on the sensor. * @hw_timestamp: Latest timestamp from the interrupt handler, when in use. */ @@ -250,6 +251,7 @@ struct st_sensor_data { const struct st_sensor_transfer_function *tf; struct st_sensor_transfer_buffer tb; + bool edge_irq; bool hw_irq_trigger; s64 hw_timestamp; }; -- cgit v1.2.3 From b6140914fd079e43ea75a53429b47128584f033a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 17:39:22 +0900 Subject: genirq/msi: Remove unused MSI_FLAG_IDENTITY_MAP No user and we definitely don't want to grow one. Signed-off-by: Thomas Gleixner Reviewed-by: Bart Van Assche Cc: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-2-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/msi.h | 6 ++---- kernel/irq/msi.c | 8 ++------ 2 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index 8b425c66305a..c33abfa0f5a7 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -264,12 +264,10 @@ enum { * callbacks. */ MSI_FLAG_USE_DEF_CHIP_OPS = (1 << 1), - /* Build identity map between hwirq and irq */ - MSI_FLAG_IDENTITY_MAP = (1 << 2), /* Support multiple PCI MSI interrupts */ - MSI_FLAG_MULTI_PCI_MSI = (1 << 3), + MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ - MSI_FLAG_PCI_MSIX = (1 << 4), + MSI_FLAG_PCI_MSIX = (1 << 3), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 38e89ce7b071..eb5bf2b50b07 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -324,7 +324,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct msi_domain_ops *ops = info->ops; msi_alloc_info_t arg; struct msi_desc *desc; - int i, ret, virq = -1; + int i, ret, virq; ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg); if (ret) @@ -332,12 +332,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, for_each_msi_entry(desc, dev) { ops->set_desc(&arg, desc); - if (info->flags & MSI_FLAG_IDENTITY_MAP) - virq = (int)ops->get_hwirq(info, &arg); - else - virq = -1; - virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used, + virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, dev_to_node(dev), &arg, false); if (virq < 0) { ret = -ENOSPC; -- cgit v1.2.3 From 9c2555835bb3d34dfac52a0be943dcc4bedd650f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 17:39:23 +0900 Subject: genirq: Introduce IRQD_AFFINITY_MANAGED flag Interupts marked with this flag are excluded from user space interrupt affinity changes. Contrary to the IRQ_NO_BALANCING flag, the kernel internal affinity mechanism is not blocked. This flag will be used for multi-queue device interrupts. Signed-off-by: Thomas Gleixner Cc: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-3-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/irq.h | 7 +++++++ kernel/irq/internals.h | 2 ++ kernel/irq/manage.c | 21 ++++++++++++++++++--- kernel/irq/proc.c | 2 +- 4 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/irq.h b/include/linux/irq.h index 4d758a7c604a..f6074813688d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -197,6 +197,7 @@ struct irq_data { * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU + * IRQD_AFFINITY_MANAGED - Affinity is auto-managed by the kernel */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -212,6 +213,7 @@ enum { IRQD_IRQ_INPROGRESS = (1 << 18), IRQD_WAKEUP_ARMED = (1 << 19), IRQD_FORWARDED_TO_VCPU = (1 << 20), + IRQD_AFFINITY_MANAGED = (1 << 21), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -305,6 +307,11 @@ static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; } +static inline bool irqd_affinity_is_managed(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 09be2c903c6d..b15aa3b617a2 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -105,6 +105,8 @@ static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif +extern bool irq_can_set_affinity_usr(unsigned int irq); + extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask); extern void irq_set_thread_affinity(struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ef0bc02c3a70..30658e9827f0 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -115,12 +115,12 @@ EXPORT_SYMBOL(synchronize_irq); #ifdef CONFIG_SMP cpumask_var_t irq_default_affinity; -static int __irq_can_set_affinity(struct irq_desc *desc) +static bool __irq_can_set_affinity(struct irq_desc *desc) { if (!desc || !irqd_can_balance(&desc->irq_data) || !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity) - return 0; - return 1; + return false; + return true; } /** @@ -133,6 +133,21 @@ int irq_can_set_affinity(unsigned int irq) return __irq_can_set_affinity(irq_to_desc(irq)); } +/** + * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space + * @irq: Interrupt to check + * + * Like irq_can_set_affinity() above, but additionally checks for the + * AFFINITY_MANAGED flag. + */ +bool irq_can_set_affinity_usr(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + return __irq_can_set_affinity(desc) && + !irqd_affinity_is_managed(&desc->irq_data); +} + /** * irq_set_thread_affinity - Notify irq threads to adjust affinity * @desc: irq descriptor which has affitnity changed diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 4e1b94726818..40bdcdc1f700 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -96,7 +96,7 @@ static ssize_t write_irq_affinity(int type, struct file *file, cpumask_var_t new_value; int err; - if (!irq_can_set_affinity(irq) || no_irq_affinity) + if (!irq_can_set_affinity_usr(irq) || no_irq_affinity) return -EIO; if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) -- cgit v1.2.3 From 06ee6d571f0e350253a8fc3492316b2be007fae2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 17:39:24 +0900 Subject: genirq: Add affinity hint to irq allocation Add an extra argument to the irq(domain) allocation functions, so we can hand down affinity hints to the allocator. Thats necessary to implement proper support for multiqueue devices. Signed-off-by: Thomas Gleixner Cc: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-4-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- arch/sparc/kernel/irq_64.c | 2 +- arch/x86/kernel/apic/io_apic.c | 5 +++-- include/linux/irq.h | 4 ++-- include/linux/irqdomain.h | 9 ++++++--- kernel/irq/ipi.c | 2 +- kernel/irq/irqdesc.c | 12 ++++++++---- kernel/irq/irqdomain.c | 22 ++++++++++++++-------- kernel/irq/manage.c | 7 ++++--- kernel/irq/msi.c | 3 ++- 9 files changed, 41 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index e22416ce56ea..34a7930b76ef 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -242,7 +242,7 @@ unsigned int irq_alloc(unsigned int dev_handle, unsigned int dev_ino) { int irq; - irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL); + irq = __irq_alloc_descs(-1, 1, 1, numa_node_id(), NULL, NULL); if (irq <= 0) goto out; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 446702ed99dc..7c4f90dd4c2a 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -981,7 +981,7 @@ static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, return __irq_domain_alloc_irqs(domain, irq, 1, ioapic_alloc_attr_node(info), - info, legacy); + info, legacy, NULL); } /* @@ -1014,7 +1014,8 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, info->ioapic_pin)) return -ENOMEM; } else { - irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true); + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true, + NULL); if (irq >= 0) { irq_data = irq_domain_get_irq_data(domain, irq); data = irq_data->chip_data; diff --git a/include/linux/irq.h b/include/linux/irq.h index f6074813688d..39ce46ac5c18 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -708,11 +708,11 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) unsigned int arch_dynirq_lower_bound(unsigned int from); int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, - struct module *owner); + struct module *owner, const struct cpumask *affinity); /* use macros to avoid needing export.h for THIS_MODULE */ #define irq_alloc_descs(irq, from, cnt, node) \ - __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE) + __irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL) #define irq_alloc_desc(node) \ irq_alloc_descs(-1, 0, 1, node) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index f1f36e04d885..1aee0fbe900e 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -39,6 +39,7 @@ struct irq_domain; struct of_device_id; struct irq_chip; struct irq_data; +struct cpumask; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 @@ -217,7 +218,8 @@ extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); extern void irq_set_default_host(struct irq_domain *host); extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, - irq_hw_number_t hwirq, int node); + irq_hw_number_t hwirq, int node, + const struct cpumask *affinity); static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) { @@ -389,7 +391,7 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, - bool realloc); + bool realloc, const struct cpumask *affinity); extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); extern void irq_domain_activate_irq(struct irq_data *irq_data); extern void irq_domain_deactivate_irq(struct irq_data *irq_data); @@ -397,7 +399,8 @@ extern void irq_domain_deactivate_irq(struct irq_data *irq_data); static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs, int node, void *arg) { - return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false); + return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false, + NULL); } extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index 89b49f6773f0..4fd23510d5f2 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -76,7 +76,7 @@ int irq_reserve_ipi(struct irq_domain *domain, } } - virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE); + virq = irq_domain_alloc_descs(-1, nr_irqs, 0, NUMA_NO_NODE, NULL); if (virq <= 0) { pr_warn("Can't reserve IPI, failed to alloc descs\n"); return -ENOMEM; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8731e1c5d1e7..b8df4fcdbb5f 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -223,7 +223,7 @@ static void free_desc(unsigned int irq) } static int alloc_descs(unsigned int start, unsigned int cnt, int node, - struct module *owner) + const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int i; @@ -333,6 +333,7 @@ static void free_desc(unsigned int irq) } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, + const struct cpumask *affinity, struct module *owner) { u32 i; @@ -453,12 +454,15 @@ EXPORT_SYMBOL_GPL(irq_free_descs); * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) + * @affinity: Optional pointer to an affinity mask which hints where the + * irq descriptors should be allocated and which default + * affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, - struct module *owner) + struct module *owner, const struct cpumask *affinity) { int start, ret; @@ -494,7 +498,7 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, bitmap_set(allocated_irqs, start, cnt); mutex_unlock(&sparse_irq_lock); - return alloc_descs(start, cnt, node, owner); + return alloc_descs(start, cnt, node, affinity, owner); err: mutex_unlock(&sparse_irq_lock); @@ -512,7 +516,7 @@ EXPORT_SYMBOL_GPL(__irq_alloc_descs); */ unsigned int irq_alloc_hwirqs(int cnt, int node) { - int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL); + int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL); if (irq < 0) return 0; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8798b6c9e945..79459b732dc9 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -481,7 +481,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node)); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), NULL); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -835,19 +835,23 @@ const struct irq_domain_ops irq_domain_simple_ops = { EXPORT_SYMBOL_GPL(irq_domain_simple_ops); int irq_domain_alloc_descs(int virq, unsigned int cnt, irq_hw_number_t hwirq, - int node) + int node, const struct cpumask *affinity) { unsigned int hint; if (virq >= 0) { - virq = irq_alloc_descs(virq, virq, cnt, node); + virq = __irq_alloc_descs(virq, virq, cnt, node, THIS_MODULE, + affinity); } else { hint = hwirq % nr_irqs; if (hint == 0) hint++; - virq = irq_alloc_descs_from(hint, cnt, node); - if (virq <= 0 && hint > 1) - virq = irq_alloc_descs_from(1, cnt, node); + virq = __irq_alloc_descs(-1, hint, cnt, node, THIS_MODULE, + affinity); + if (virq <= 0 && hint > 1) { + virq = __irq_alloc_descs(-1, 1, cnt, node, THIS_MODULE, + affinity); + } } return virq; @@ -1160,6 +1164,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, * @node: NUMA node id for memory allocation * @arg: domain specific argument * @realloc: IRQ descriptors have already been allocated if true + * @affinity: Optional irq affinity mask for multiqueue devices * * Allocate IRQ numbers and initialized all data structures to support * hierarchy IRQ domains. @@ -1175,7 +1180,7 @@ int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, */ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, - bool realloc) + bool realloc, const struct cpumask *affinity) { int i, ret, virq; @@ -1193,7 +1198,8 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, if (realloc && irq_base >= 0) { virq = irq_base; } else { - virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node); + virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node, + affinity); if (virq < 0) { pr_debug("cannot allocate IRQ(base %d, count %d)\n", irq_base, nr_irqs); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 30658e9827f0..ad0aac6d1248 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -353,10 +353,11 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) return 0; /* - * Preserve an userspace affinity setup, but make sure that - * one of the targets is online. + * Preserve the managed affinity setting and an userspace affinity + * setup, but make sure that one of the targets is online. */ - if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { + if (irqd_affinity_is_managed(&desc->irq_data) || + irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { if (cpumask_intersects(desc->irq_common_data.affinity, cpu_online_mask)) set = desc->irq_common_data.affinity; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index eb5bf2b50b07..58dbbacc6fbb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -334,7 +334,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, ops->set_desc(&arg, desc); virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, - dev_to_node(dev), &arg, false); + dev_to_node(dev), &arg, false, + NULL); if (virq < 0) { ret = -ENOSPC; if (ops->handle_error) -- cgit v1.2.3 From 0972fa57f53525ffa6ced12d703750fc2791e3ce Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 17:39:26 +0900 Subject: genirq/msi: Make use of affinity aware allocations Allow the MSI code to provide affinity hints per MSI descriptor. Signed-off-by: Thomas Gleixner Cc: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-6-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/msi.h | 2 ++ kernel/irq/msi.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index c33abfa0f5a7..4f0bfe5912b2 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -47,6 +47,7 @@ struct fsl_mc_msi_desc { * @nvec_used: The number of vectors used * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse + * @affinity: Optional pointer to a cpu affinity mask for this descriptor * * @masked: [PCI MSI/X] Mask bits * @is_msix: [PCI MSI/X] True if MSI-X @@ -67,6 +68,7 @@ struct msi_desc { unsigned int nvec_used; struct device *dev; struct msi_msg msg; + const struct cpumask *affinity; union { /* PCI MSI/X specific data */ diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 58dbbacc6fbb..0e2a736b14a7 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -335,7 +335,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, dev_to_node(dev), &arg, false, - NULL); + desc->affinity); if (virq < 0) { ret = -ENOSPC; if (ops->handle_error) -- cgit v1.2.3 From 5e385a6ef31fbbf2acbda770aecc2bc2ff933d17 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 4 Jul 2016 17:39:27 +0900 Subject: genirq: Add a helper to spread an affinity mask for MSI/MSI-X vectors This is lifted from the blk-mq code and adopted to use the affinity mask concept just introduced in the irq handling code. It tries to keep the algorithm the same as the one current used by blk-mq, but improvements like assining vectors on a per-node basis instead of just per sibling are possible with this simple move and refactoring. Signed-off-by: Christoph Hellwig Cc: linux-block@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: linux-nvme@lists.infradead.org Cc: axboe@fb.com Cc: agordeev@redhat.com Link: http://lkml.kernel.org/r/1467621574-8277-7-git-send-email-hch@lst.de Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 8 +++++++ kernel/irq/Makefile | 1 + kernel/irq/affinity.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 70 insertions(+) create mode 100644 kernel/irq/affinity.c (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9fcabeb07787..b6683f0ffc9f 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -278,6 +278,8 @@ extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); +struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs); + #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) @@ -308,6 +310,12 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { return 0; } + +static inline struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) +{ + *nr_vecs = 1; + return NULL; +} #endif /* CONFIG_SMP */ /* diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 2ee42e95a3ce..1d3ee3169202 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -9,3 +9,4 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o +obj-$(CONFIG_SMP) += affinity.o diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c new file mode 100644 index 000000000000..f68959341c0f --- /dev/null +++ b/kernel/irq/affinity.c @@ -0,0 +1,61 @@ + +#include +#include +#include +#include + +static int get_first_sibling(unsigned int cpu) +{ + unsigned int ret; + + ret = cpumask_first(topology_sibling_cpumask(cpu)); + if (ret < nr_cpu_ids) + return ret; + return cpu; +} + +/* + * Take a map of online CPUs and the number of available interrupt vectors + * and generate an output cpumask suitable for spreading MSI/MSI-X vectors + * so that they are distributed as good as possible around the CPUs. If + * more vectors than CPUs are available we'll map one to each CPU, + * otherwise we map one to the first sibling of each socket. + * + * If there are more vectors than CPUs we will still only have one bit + * set per CPU, but interrupt code will keep on assigning the vectors from + * the start of the bitmap until we run out of vectors. + */ +struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) +{ + struct cpumask *affinity_mask; + unsigned int max_vecs = *nr_vecs; + + if (max_vecs == 1) + return NULL; + + affinity_mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!affinity_mask) { + *nr_vecs = 1; + return NULL; + } + + if (max_vecs >= num_online_cpus()) { + cpumask_copy(affinity_mask, cpu_online_mask); + *nr_vecs = num_online_cpus(); + } else { + unsigned int vecs = 0, cpu; + + for_each_online_cpu(cpu) { + if (cpu == get_first_sibling(cpu)) { + cpumask_set_cpu(cpu, affinity_mask); + vecs++; + } + + if (--max_vecs == 0) + break; + } + *nr_vecs = vecs; + } + + return affinity_mask; +} -- cgit v1.2.3 From 300eb0139cf27044c67f6005ff17b8434c7843f0 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Mon, 9 May 2016 18:39:59 -0500 Subject: phy: Add set_mode callback The initial use for this is for PHYs that have a mode related to USB OTG. There are several SoCs (e.g. TI OMAP and DA8xx) that have a mode setting in the USB PHY to override OTG VBUS and ID signals. Of course, the enum can be expaned in the future to include modes for other types of PHYs as well. Suggested-by: Kishon Vijay Abraham I Signed-off-by: David Lechner --- drivers/phy/phy-core.c | 15 +++++++++++++++ include/linux/phy/phy.h | 17 +++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index b72e9a3b6429..8eca906b6e70 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -342,6 +342,21 @@ int phy_power_off(struct phy *phy) } EXPORT_SYMBOL_GPL(phy_power_off); +int phy_set_mode(struct phy *phy, enum phy_mode mode) +{ + int ret; + + if (!phy || !phy->ops->set_mode) + return 0; + + mutex_lock(&phy->mutex); + ret = phy->ops->set_mode(phy, mode); + mutex_unlock(&phy->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_set_mode); + /** * _of_phy_get() - lookup and obtain a reference to a phy by phandle * @np: device_node for which to get the phy diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index a810f2a18842..f08b67238b58 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -22,12 +22,20 @@ struct phy; +enum phy_mode { + PHY_MODE_INVALID, + PHY_MODE_USB_HOST, + PHY_MODE_USB_DEVICE, + PHY_MODE_USB_OTG, +}; + /** * struct phy_ops - set of function pointers for performing phy operations * @init: operation to be performed for initializing phy * @exit: operation to be performed while exiting * @power_on: powering on the phy * @power_off: powering off the phy + * @set_mode: set the mode of the phy * @owner: the module owner containing the ops */ struct phy_ops { @@ -35,6 +43,7 @@ struct phy_ops { int (*exit)(struct phy *phy); int (*power_on)(struct phy *phy); int (*power_off)(struct phy *phy); + int (*set_mode)(struct phy *phy, enum phy_mode mode); struct module *owner; }; @@ -126,6 +135,7 @@ int phy_init(struct phy *phy); int phy_exit(struct phy *phy); int phy_power_on(struct phy *phy); int phy_power_off(struct phy *phy); +int phy_set_mode(struct phy *phy, enum phy_mode mode); static inline int phy_get_bus_width(struct phy *phy) { return phy->attrs.bus_width; @@ -233,6 +243,13 @@ static inline int phy_power_off(struct phy *phy) return -ENOSYS; } +static inline int phy_set_mode(struct phy *phy, enum phy_mode mode) +{ + if (!phy) + return 0; + return -ENOSYS; +} + static inline int phy_get_bus_width(struct phy *phy) { return -ENOSYS; -- cgit v1.2.3 From f06628638cf6e75f179742b6c1b35076965b9fdd Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 28 Jun 2016 14:56:51 -0700 Subject: locking/atomic: Introduce inc/dec variants for the atomic_fetch_$op() API With the inclusion of atomic FETCH-OP variants, many places in the kernel can make use of atomic_fetch_$op() to avoid the callers that need to compute the value/state _before_ the operation. Peter Zijlstra laid out the machinery but we are still missing the simpler dec,inc() calls (which future patches will make use of). This patch only deals with the generic code, as at least right now no arch actually implement them -- which is similar to what the OP-RETURN primitives currently do. Signed-off-by: Davidlohr Bueso Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: James.Bottomley@HansenPartnership.com Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: awalls@md.metrocast.net Cc: bp@alien8.de Cc: cw00.choi@samsung.com Cc: davem@davemloft.net Cc: dledford@redhat.com Cc: dougthompson@xmission.com Cc: gregkh@linuxfoundation.org Cc: hans.verkuil@cisco.com Cc: heiko.carstens@de.ibm.com Cc: jikos@kernel.org Cc: kys@microsoft.com Cc: mchehab@osg.samsung.com Cc: pfg@sgi.com Cc: schwidefsky@de.ibm.com Cc: sean.hefty@intel.com Cc: sumit.semwal@linaro.org Link: http://lkml.kernel.org/r/20160628215651.GA20048@linux-80c1.suse Signed-off-by: Ingo Molnar --- include/asm-generic/atomic-long.h | 22 +++++++ include/linux/atomic.h | 128 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 150 insertions(+) (limited to 'include') diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h index 2d0d3cf791ab..288cc9e96395 100644 --- a/include/asm-generic/atomic-long.h +++ b/include/asm-generic/atomic-long.h @@ -146,6 +146,28 @@ ATOMIC_LONG_FETCH_OP(xor, _relaxed) ATOMIC_LONG_FETCH_OP(xor, _acquire) ATOMIC_LONG_FETCH_OP(xor, _release) +#undef ATOMIC_LONG_FETCH_OP + +#define ATOMIC_LONG_FETCH_INC_DEC_OP(op, mo) \ +static inline long \ +atomic_long_fetch_##op##mo(atomic_long_t *l) \ +{ \ + ATOMIC_LONG_PFX(_t) *v = (ATOMIC_LONG_PFX(_t) *)l; \ + \ + return (long)ATOMIC_LONG_PFX(_fetch_##op##mo)(v); \ +} + +ATOMIC_LONG_FETCH_INC_DEC_OP(inc,) +ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _relaxed) +ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _acquire) +ATOMIC_LONG_FETCH_INC_DEC_OP(inc, _release) +ATOMIC_LONG_FETCH_INC_DEC_OP(dec,) +ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _relaxed) +ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _acquire) +ATOMIC_LONG_FETCH_INC_DEC_OP(dec, _release) + +#undef ATOMIC_LONG_FETCH_INC_DEC_OP + #define ATOMIC_LONG_OP(op) \ static __always_inline void \ atomic_long_##op(long i, atomic_long_t *l) \ diff --git a/include/linux/atomic.h b/include/linux/atomic.h index 12d910d61b83..e71835bf60a9 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -188,6 +188,38 @@ #endif #endif /* atomic_fetch_add_relaxed */ +/* atomic_fetch_inc_relaxed */ +#ifndef atomic_fetch_inc_relaxed + +#ifndef atomic_fetch_inc +#define atomic_fetch_inc(v) atomic_fetch_add(1, (v)) +#define atomic_fetch_inc_relaxed(v) atomic_fetch_add_relaxed(1, (v)) +#define atomic_fetch_inc_acquire(v) atomic_fetch_add_acquire(1, (v)) +#define atomic_fetch_inc_release(v) atomic_fetch_add_release(1, (v)) +#else /* atomic_fetch_inc */ +#define atomic_fetch_inc_relaxed atomic_fetch_inc +#define atomic_fetch_inc_acquire atomic_fetch_inc +#define atomic_fetch_inc_release atomic_fetch_inc +#endif /* atomic_fetch_inc */ + +#else /* atomic_fetch_inc_relaxed */ + +#ifndef atomic_fetch_inc_acquire +#define atomic_fetch_inc_acquire(...) \ + __atomic_op_acquire(atomic_fetch_inc, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_inc_release +#define atomic_fetch_inc_release(...) \ + __atomic_op_release(atomic_fetch_inc, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_inc +#define atomic_fetch_inc(...) \ + __atomic_op_fence(atomic_fetch_inc, __VA_ARGS__) +#endif +#endif /* atomic_fetch_inc_relaxed */ + /* atomic_fetch_sub_relaxed */ #ifndef atomic_fetch_sub_relaxed #define atomic_fetch_sub_relaxed atomic_fetch_sub @@ -212,6 +244,38 @@ #endif #endif /* atomic_fetch_sub_relaxed */ +/* atomic_fetch_dec_relaxed */ +#ifndef atomic_fetch_dec_relaxed + +#ifndef atomic_fetch_dec +#define atomic_fetch_dec(v) atomic_fetch_sub(1, (v)) +#define atomic_fetch_dec_relaxed(v) atomic_fetch_sub_relaxed(1, (v)) +#define atomic_fetch_dec_acquire(v) atomic_fetch_sub_acquire(1, (v)) +#define atomic_fetch_dec_release(v) atomic_fetch_sub_release(1, (v)) +#else /* atomic_fetch_dec */ +#define atomic_fetch_dec_relaxed atomic_fetch_dec +#define atomic_fetch_dec_acquire atomic_fetch_dec +#define atomic_fetch_dec_release atomic_fetch_dec +#endif /* atomic_fetch_dec */ + +#else /* atomic_fetch_dec_relaxed */ + +#ifndef atomic_fetch_dec_acquire +#define atomic_fetch_dec_acquire(...) \ + __atomic_op_acquire(atomic_fetch_dec, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_dec_release +#define atomic_fetch_dec_release(...) \ + __atomic_op_release(atomic_fetch_dec, __VA_ARGS__) +#endif + +#ifndef atomic_fetch_dec +#define atomic_fetch_dec(...) \ + __atomic_op_fence(atomic_fetch_dec, __VA_ARGS__) +#endif +#endif /* atomic_fetch_dec_relaxed */ + /* atomic_fetch_or_relaxed */ #ifndef atomic_fetch_or_relaxed #define atomic_fetch_or_relaxed atomic_fetch_or @@ -697,6 +761,38 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_add_relaxed */ +/* atomic64_fetch_inc_relaxed */ +#ifndef atomic64_fetch_inc_relaxed + +#ifndef atomic64_fetch_inc +#define atomic64_fetch_inc(v) atomic64_fetch_add(1, (v)) +#define atomic64_fetch_inc_relaxed(v) atomic64_fetch_add_relaxed(1, (v)) +#define atomic64_fetch_inc_acquire(v) atomic64_fetch_add_acquire(1, (v)) +#define atomic64_fetch_inc_release(v) atomic64_fetch_add_release(1, (v)) +#else /* atomic64_fetch_inc */ +#define atomic64_fetch_inc_relaxed atomic64_fetch_inc +#define atomic64_fetch_inc_acquire atomic64_fetch_inc +#define atomic64_fetch_inc_release atomic64_fetch_inc +#endif /* atomic64_fetch_inc */ + +#else /* atomic64_fetch_inc_relaxed */ + +#ifndef atomic64_fetch_inc_acquire +#define atomic64_fetch_inc_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_inc, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_inc_release +#define atomic64_fetch_inc_release(...) \ + __atomic_op_release(atomic64_fetch_inc, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_inc +#define atomic64_fetch_inc(...) \ + __atomic_op_fence(atomic64_fetch_inc, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_inc_relaxed */ + /* atomic64_fetch_sub_relaxed */ #ifndef atomic64_fetch_sub_relaxed #define atomic64_fetch_sub_relaxed atomic64_fetch_sub @@ -721,6 +817,38 @@ static inline int atomic_dec_if_positive(atomic_t *v) #endif #endif /* atomic64_fetch_sub_relaxed */ +/* atomic64_fetch_dec_relaxed */ +#ifndef atomic64_fetch_dec_relaxed + +#ifndef atomic64_fetch_dec +#define atomic64_fetch_dec(v) atomic64_fetch_sub(1, (v)) +#define atomic64_fetch_dec_relaxed(v) atomic64_fetch_sub_relaxed(1, (v)) +#define atomic64_fetch_dec_acquire(v) atomic64_fetch_sub_acquire(1, (v)) +#define atomic64_fetch_dec_release(v) atomic64_fetch_sub_release(1, (v)) +#else /* atomic64_fetch_dec */ +#define atomic64_fetch_dec_relaxed atomic64_fetch_dec +#define atomic64_fetch_dec_acquire atomic64_fetch_dec +#define atomic64_fetch_dec_release atomic64_fetch_dec +#endif /* atomic64_fetch_dec */ + +#else /* atomic64_fetch_dec_relaxed */ + +#ifndef atomic64_fetch_dec_acquire +#define atomic64_fetch_dec_acquire(...) \ + __atomic_op_acquire(atomic64_fetch_dec, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_dec_release +#define atomic64_fetch_dec_release(...) \ + __atomic_op_release(atomic64_fetch_dec, __VA_ARGS__) +#endif + +#ifndef atomic64_fetch_dec +#define atomic64_fetch_dec(...) \ + __atomic_op_fence(atomic64_fetch_dec, __VA_ARGS__) +#endif +#endif /* atomic64_fetch_dec_relaxed */ + /* atomic64_fetch_or_relaxed */ #ifndef atomic64_fetch_or_relaxed #define atomic64_fetch_or_relaxed atomic64_fetch_or -- cgit v1.2.3 From e675447bda51c1ea72d1ac9132ce3bed974f1da3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:15 +0000 Subject: timers: Make 'pinned' a timer property We want to move the timer migration logic from a 'push' to a 'pull' model. Under the current 'push' model pinned timers are handled via a runtime API variant: mod_timer_pinned(). The 'pull' model requires us to store the pinned attribute of a timer in the timer_list structure itself, as a new TIMER_PINNED bit in timer->flags. This flag must be set at initialization time and the timer APIs recognize the flag. This patch: - Implements the new flag and associated new-style initialization methods - makes mod_timer() recognize new-style pinned timers, - and adds some migration helper facility to allow step by step conversion of old-style to new-style pinned timers. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Chris Mason Cc: Eric Dumazet Cc: George Spelvin Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094341.049338558@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/timer.h | 25 ++++++++++++++++++++++--- kernel/time/timer.c | 10 +++++----- 2 files changed, 27 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 20ac746f3eb3..046d6cf26498 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -62,7 +62,8 @@ struct timer_list { #define TIMER_MIGRATING 0x00080000 #define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) #define TIMER_DEFERRABLE 0x00100000 -#define TIMER_IRQSAFE 0x00200000 +#define TIMER_PINNED 0x00200000 +#define TIMER_IRQSAFE 0x00400000 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ @@ -78,9 +79,15 @@ struct timer_list { #define TIMER_INITIALIZER(_function, _expires, _data) \ __TIMER_INITIALIZER((_function), (_expires), (_data), 0) +#define TIMER_PINNED_INITIALIZER(_function, _expires, _data) \ + __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_PINNED) + #define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) \ __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE) +#define TIMER_PINNED_DEFERRED_INITIALIZER(_function, _expires, _data) \ + __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE | TIMER_PINNED) + #define DEFINE_TIMER(_name, _function, _expires, _data) \ struct timer_list _name = \ TIMER_INITIALIZER(_function, _expires, _data) @@ -124,8 +131,12 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define init_timer(timer) \ __init_timer((timer), 0) +#define init_timer_pinned(timer) \ + __init_timer((timer), TIMER_PINNED) #define init_timer_deferrable(timer) \ __init_timer((timer), TIMER_DEFERRABLE) +#define init_timer_pinned_deferrable(timer) \ + __init_timer((timer), TIMER_DEFERRABLE | TIMER_PINNED) #define init_timer_on_stack(timer) \ __init_timer_on_stack((timer), 0) @@ -145,12 +156,20 @@ static inline void init_timer_on_stack_key(struct timer_list *timer, #define setup_timer(timer, fn, data) \ __setup_timer((timer), (fn), (data), 0) +#define setup_pinned_timer(timer, fn, data) \ + __setup_timer((timer), (fn), (data), TIMER_PINNED) #define setup_deferrable_timer(timer, fn, data) \ __setup_timer((timer), (fn), (data), TIMER_DEFERRABLE) +#define setup_pinned_deferrable_timer(timer, fn, data) \ + __setup_timer((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) #define setup_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), 0) +#define setup_pinned_timer_on_stack(timer, fn, data) \ + __setup_timer_on_stack((timer), (fn), (data), TIMER_PINNED) #define setup_deferrable_timer_on_stack(timer, fn, data) \ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE) +#define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \ + __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED) /** * timer_pending - is a timer pending? @@ -175,8 +194,8 @@ extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires); extern void set_timer_slack(struct timer_list *time, int slack_hz); -#define TIMER_NOT_PINNED 0 -#define TIMER_PINNED 1 +#define MOD_TIMER_NOT_PINNED 0 +#define MOD_TIMER_PINNED 1 /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 3a95f9728778..693f6d14058e 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -782,7 +782,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - new_base = get_target_base(base, pinned); + new_base = get_target_base(base, pinned || timer->flags & TIMER_PINNED); if (base != new_base) { /* @@ -825,7 +825,7 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, true, MOD_TIMER_NOT_PINNED); } EXPORT_SYMBOL(mod_timer_pending); @@ -900,7 +900,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires) if (timer_pending(timer) && timer->expires == expires) return 1; - return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, false, MOD_TIMER_NOT_PINNED); } EXPORT_SYMBOL(mod_timer); @@ -928,7 +928,7 @@ int mod_timer_pinned(struct timer_list *timer, unsigned long expires) if (timer->expires == expires && timer_pending(timer)) return 1; - return __mod_timer(timer, expires, false, TIMER_PINNED); + return __mod_timer(timer, expires, false, MOD_TIMER_PINNED); } EXPORT_SYMBOL(mod_timer_pinned); @@ -1512,7 +1512,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); + __mod_timer(&timer, expire, false, MOD_TIMER_NOT_PINNED); schedule(); del_singleshot_timer_sync(&timer); -- cgit v1.2.3 From 177ec0a0a531695210b277d734b2f92ee5796303 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:24 +0000 Subject: timers: Remove the deprecated mod_timer_pinned() API We switched all users to initialize the timers as pinned and call mod_timer(). Remove the now unused timer API function. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Chris Mason Cc: Eric Dumazet Cc: George Spelvin Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094341.706205231@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/timer.h | 3 --- kernel/time/timer.c | 39 +++++---------------------------------- 2 files changed, 5 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 046d6cf26498..a8f6c70eb414 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -190,12 +190,9 @@ extern void add_timer_on(struct timer_list *timer, int cpu); extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); -extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires); extern void set_timer_slack(struct timer_list *time, int slack_hz); -#define MOD_TIMER_NOT_PINNED 0 -#define MOD_TIMER_PINNED 1 /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 693f6d14058e..ba49c1cf80f5 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -764,8 +764,7 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, } static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, - bool pending_only, int pinned) +__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) { struct tvec_base *base, *new_base; unsigned long flags; @@ -782,7 +781,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - new_base = get_target_base(base, pinned || timer->flags & TIMER_PINNED); + new_base = get_target_base(base, timer->flags & TIMER_PINNED); if (base != new_base) { /* @@ -825,7 +824,7 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true, MOD_TIMER_NOT_PINNED); + return __mod_timer(timer, expires, true); } EXPORT_SYMBOL(mod_timer_pending); @@ -900,38 +899,10 @@ int mod_timer(struct timer_list *timer, unsigned long expires) if (timer_pending(timer) && timer->expires == expires) return 1; - return __mod_timer(timer, expires, false, MOD_TIMER_NOT_PINNED); + return __mod_timer(timer, expires, false); } EXPORT_SYMBOL(mod_timer); -/** - * mod_timer_pinned - modify a timer's timeout - * @timer: the timer to be modified - * @expires: new timeout in jiffies - * - * mod_timer_pinned() is a way to update the expire field of an - * active timer (if the timer is inactive it will be activated) - * and to ensure that the timer is scheduled on the current CPU. - * - * Note that this does not prevent the timer from being migrated - * when the current CPU goes offline. If this is a problem for - * you, use CPU-hotplug notifiers to handle it correctly, for - * example, cancelling the timer when the corresponding CPU goes - * offline. - * - * mod_timer_pinned(timer, expires) is equivalent to: - * - * del_timer(timer); timer->expires = expires; add_timer(timer); - */ -int mod_timer_pinned(struct timer_list *timer, unsigned long expires) -{ - if (timer->expires == expires && timer_pending(timer)) - return 1; - - return __mod_timer(timer, expires, false, MOD_TIMER_PINNED); -} -EXPORT_SYMBOL(mod_timer_pinned); - /** * add_timer - start a timer * @timer: the timer to be added @@ -1512,7 +1483,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies; setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false, MOD_TIMER_NOT_PINNED); + __mod_timer(&timer, expire, false); schedule(); del_singleshot_timer_sync(&timer); -- cgit v1.2.3 From 15dba1e37b5cfd7fab9bc84e0f05f35c918f4eef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:27 +0000 Subject: hlist: Add hlist_is_singular_node() helper Required to figure out whether the entry is the only one in the hlist. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Chris Mason Cc: Eric Dumazet Cc: George Spelvin Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094341.867631372@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/list.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/list.h b/include/linux/list.h index 5356f4d661a7..5183138aa932 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -678,6 +678,16 @@ static inline bool hlist_fake(struct hlist_node *h) return h->pprev == &h->next; } +/* + * Check whether the node is the only node of the head without + * accessing head: + */ +static inline bool +hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) +{ + return !n->next && n->pprev == &h->first; +} + /* * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. -- cgit v1.2.3 From b0d6e2dcb284f1f4dcb4b92760f49eeaf5fc0bc7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:29 +0000 Subject: timers: Reduce the CPU index space to 256k We want to store the array index in the flags space. 256k CPUs should be enough for a while. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Chris Mason Cc: George Spelvin Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Paul McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094342.030144293@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/timer.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index a8f6c70eb414..989f33d16ebf 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -58,12 +58,12 @@ struct timer_list { * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! */ -#define TIMER_CPUMASK 0x0007FFFF -#define TIMER_MIGRATING 0x00080000 +#define TIMER_CPUMASK 0x0003FFFF +#define TIMER_MIGRATING 0x00040000 #define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) -#define TIMER_DEFERRABLE 0x00100000 -#define TIMER_PINNED 0x00200000 -#define TIMER_IRQSAFE 0x00400000 +#define TIMER_DEFERRABLE 0x00080000 +#define TIMER_PINNED 0x00100000 +#define TIMER_IRQSAFE 0x00200000 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ -- cgit v1.2.3 From 500462a9de657f86edaa102f8ab6bff7f7e43fc2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:30 +0000 Subject: timers: Switch to a non-cascading wheel The current timer wheel has some drawbacks: 1) Cascading: Cascading can be an unbound operation and is completely pointless in most cases because the vast majority of the timer wheel timers are canceled or rearmed before expiration. (They are used as timeout safeguards, not as real timers to measure time.) 2) No fast lookup of the next expiring timer: In NOHZ scenarios the first timer soft interrupt after a long NOHZ period must fast forward the base time to the current value of jiffies. As we have no way to find the next expiring timer fast, the code loops linearly and increments the base time one by one and checks for expired timers in each step. This causes unbound overhead spikes exactly in the moment when we should wake up as fast as possible. After a thorough analysis of real world data gathered on laptops, workstations, webservers and other machines (thanks Chris!) I came to the conclusion that the current 'classic' timer wheel implementation can be modified to address the above issues. The vast majority of timer wheel timers is canceled or rearmed before expiry. Most of them are timeouts for networking and other I/O tasks. The nature of timeouts is to catch the exception from normal operation (TCP ack timed out, disk does not respond, etc.). For these kinds of timeouts the accuracy of the timeout is not really a concern. Timeouts are very often approximate worst-case values and in case the timeout fires, we already waited for a long time and performance is down the drain already. The few timers which actually expire can be split into two categories: 1) Short expiry times which expect halfways accurate expiry 2) Long term expiry times are inaccurate today already due to the batching which is done for NOHZ automatically and also via the set_timer_slack() API. So for long term expiry timers we can avoid the cascading property and just leave them in the less granular outer wheels until expiry or cancelation. Timers which are armed with a timeout larger than the wheel capacity are no longer cascaded. We expire them with the longest possible timeout (6+ days). We have not observed such timeouts in our data collection, but at least we handle them, applying the rule of the least surprise. To avoid extending the wheel levels for HZ=1000 so we can accomodate the longest observed timeouts (5 days in the network conntrack code) we reduce the first level granularity on HZ=1000 to 4ms, which effectively is the same as the HZ=250 behaviour. From our data analysis there is nothing which relies on that 1ms granularity and as a side effect we get better batching and timer locality for the networking code as well. Contrary to the classic wheel the granularity of the next wheel is not the capacity of the first wheel. The granularities of the wheels are in the currently chosen setting 8 times the granularity of the previous wheel. So for HZ=250 we end up with the following granularity levels: Level Offset Granularity Range 0 0 4 ms 0 ms - 252 ms 1 64 32 ms 256 ms - 2044 ms (256ms - ~2s) 2 128 256 ms 2048 ms - 16380 ms (~2s - ~16s) 3 192 2048 ms (~2s) 16384 ms - 131068 ms (~16s - ~2m) 4 256 16384 ms (~16s) 131072 ms - 1048572 ms (~2m - ~17m) 5 320 131072 ms (~2m) 1048576 ms - 8388604 ms (~17m - ~2h) 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) That's a worst case inaccuracy of 12.5% for the timers which are queued at the beginning of a level. So the new wheel concept addresses the old issues: 1) Cascading is avoided completely 2) By keeping the timers in the bucket until expiry/cancelation we can track the buckets which have timers enqueued in a bucket bitmap and therefore can look up the next expiring timer very fast and O(1). A further benefit of the concept is that the slack calculation which is done on every timer start is no longer necessary because the granularity levels provide natural batching already. Our extensive testing with various loads did not show any performance degradation vs. the current wheel implementation. This patch does not address the 'fast lookup' issue as we wanted to make sure that there is no regression introduced by the wheel redesign. The optimizations are in follow up patches. This patch contains fixes from Anna-Maria Gleixner and Richard Cochran. Signed-off-by: Thomas Gleixner Cc: Arjan van de Ven Cc: Chris Mason Cc: Eric Dumazet Cc: Frederic Weisbecker Cc: George Spelvin Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094342.108621834@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/timer.h | 2 + kernel/time/timer.c | 829 ++++++++++++++++++++++++++++---------------------- 2 files changed, 469 insertions(+), 362 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 989f33d16ebf..5869ab9848fe 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -64,6 +64,8 @@ struct timer_list { #define TIMER_DEFERRABLE 0x00080000 #define TIMER_PINNED 0x00100000 #define TIMER_IRQSAFE 0x00200000 +#define TIMER_ARRAYSHIFT 22 +#define TIMER_ARRAYMASK 0xFFC00000 #define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index f259a3ef4577..86e95b72665d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -59,43 +59,151 @@ __visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); /* - * per-CPU timer vector definitions: + * The timer wheel has LVL_DEPTH array levels. Each level provides an array of + * LVL_SIZE buckets. Each level is driven by its own clock and therefor each + * level has a different granularity. + * + * The level granularity is: LVL_CLK_DIV ^ lvl + * The level clock frequency is: HZ / (LVL_CLK_DIV ^ level) + * + * The array level of a newly armed timer depends on the relative expiry + * time. The farther the expiry time is away the higher the array level and + * therefor the granularity becomes. + * + * Contrary to the original timer wheel implementation, which aims for 'exact' + * expiry of the timers, this implementation removes the need for recascading + * the timers into the lower array levels. The previous 'classic' timer wheel + * implementation of the kernel already violated the 'exact' expiry by adding + * slack to the expiry time to provide batched expiration. The granularity + * levels provide implicit batching. + * + * This is an optimization of the original timer wheel implementation for the + * majority of the timer wheel use cases: timeouts. The vast majority of + * timeout timers (networking, disk I/O ...) are canceled before expiry. If + * the timeout expires it indicates that normal operation is disturbed, so it + * does not matter much whether the timeout comes with a slight delay. + * + * The only exception to this are networking timers with a small expiry + * time. They rely on the granularity. Those fit into the first wheel level, + * which has HZ granularity. + * + * We don't have cascading anymore. timers with a expiry time above the + * capacity of the last wheel level are force expired at the maximum timeout + * value of the last wheel level. From data sampling we know that the maximum + * value observed is 5 days (network connection tracking), so this should not + * be an issue. + * + * The currently chosen array constants values are a good compromise between + * array size and granularity. + * + * This results in the following granularity and range levels: + * + * HZ 1000 steps + * Level Offset Granularity Range + * 0 0 1 ms 0 ms - 63 ms + * 1 64 8 ms 64 ms - 511 ms + * 2 128 64 ms 512 ms - 4095 ms (512ms - ~4s) + * 3 192 512 ms 4096 ms - 32767 ms (~4s - ~32s) + * 4 256 4096 ms (~4s) 32768 ms - 262143 ms (~32s - ~4m) + * 5 320 32768 ms (~32s) 262144 ms - 2097151 ms (~4m - ~34m) + * 6 384 262144 ms (~4m) 2097152 ms - 16777215 ms (~34m - ~4h) + * 7 448 2097152 ms (~34m) 16777216 ms - 134217727 ms (~4h - ~1d) + * 8 512 16777216 ms (~4h) 134217728 ms - 1073741822 ms (~1d - ~12d) + * + * HZ 300 + * Level Offset Granularity Range + * 0 0 3 ms 0 ms - 210 ms + * 1 64 26 ms 213 ms - 1703 ms (213ms - ~1s) + * 2 128 213 ms 1706 ms - 13650 ms (~1s - ~13s) + * 3 192 1706 ms (~1s) 13653 ms - 109223 ms (~13s - ~1m) + * 4 256 13653 ms (~13s) 109226 ms - 873810 ms (~1m - ~14m) + * 5 320 109226 ms (~1m) 873813 ms - 6990503 ms (~14m - ~1h) + * 6 384 873813 ms (~14m) 6990506 ms - 55924050 ms (~1h - ~15h) + * 7 448 6990506 ms (~1h) 55924053 ms - 447392423 ms (~15h - ~5d) + * 8 512 55924053 ms (~15h) 447392426 ms - 3579139406 ms (~5d - ~41d) + * + * HZ 250 + * Level Offset Granularity Range + * 0 0 4 ms 0 ms - 255 ms + * 1 64 32 ms 256 ms - 2047 ms (256ms - ~2s) + * 2 128 256 ms 2048 ms - 16383 ms (~2s - ~16s) + * 3 192 2048 ms (~2s) 16384 ms - 131071 ms (~16s - ~2m) + * 4 256 16384 ms (~16s) 131072 ms - 1048575 ms (~2m - ~17m) + * 5 320 131072 ms (~2m) 1048576 ms - 8388607 ms (~17m - ~2h) + * 6 384 1048576 ms (~17m) 8388608 ms - 67108863 ms (~2h - ~18h) + * 7 448 8388608 ms (~2h) 67108864 ms - 536870911 ms (~18h - ~6d) + * 8 512 67108864 ms (~18h) 536870912 ms - 4294967288 ms (~6d - ~49d) + * + * HZ 100 + * Level Offset Granularity Range + * 0 0 10 ms 0 ms - 630 ms + * 1 64 80 ms 640 ms - 5110 ms (640ms - ~5s) + * 2 128 640 ms 5120 ms - 40950 ms (~5s - ~40s) + * 3 192 5120 ms (~5s) 40960 ms - 327670 ms (~40s - ~5m) + * 4 256 40960 ms (~40s) 327680 ms - 2621430 ms (~5m - ~43m) + * 5 320 327680 ms (~5m) 2621440 ms - 20971510 ms (~43m - ~5h) + * 6 384 2621440 ms (~43m) 20971520 ms - 167772150 ms (~5h - ~1d) + * 7 448 20971520 ms (~5h) 167772160 ms - 1342177270 ms (~1d - ~15d) */ -#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6) -#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8) -#define TVN_SIZE (1 << TVN_BITS) -#define TVR_SIZE (1 << TVR_BITS) -#define TVN_MASK (TVN_SIZE - 1) -#define TVR_MASK (TVR_SIZE - 1) -#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) - -struct tvec { - struct hlist_head vec[TVN_SIZE]; -}; -struct tvec_root { - struct hlist_head vec[TVR_SIZE]; -}; +/* Clock divisor for the next level */ +#define LVL_CLK_SHIFT 3 +#define LVL_CLK_DIV (1UL << LVL_CLK_SHIFT) +#define LVL_CLK_MASK (LVL_CLK_DIV - 1) +#define LVL_SHIFT(n) ((n) * LVL_CLK_SHIFT) +#define LVL_GRAN(n) (1UL << LVL_SHIFT(n)) + +/* + * The time start value for each level to select the bucket at enqueue + * time. + */ +#define LVL_START(n) ((LVL_SIZE - 1) << (((n) - 1) * LVL_CLK_SHIFT)) + +/* Size of each clock level */ +#define LVL_BITS 6 +#define LVL_SIZE (1UL << LVL_BITS) +#define LVL_MASK (LVL_SIZE - 1) +#define LVL_OFFS(n) ((n) * LVL_SIZE) + +/* Level depth */ +#if HZ > 100 +# define LVL_DEPTH 9 +# else +# define LVL_DEPTH 8 +#endif + +/* The cutoff (max. capacity of the wheel) */ +#define WHEEL_TIMEOUT_CUTOFF (LVL_START(LVL_DEPTH)) +#define WHEEL_TIMEOUT_MAX (WHEEL_TIMEOUT_CUTOFF - LVL_GRAN(LVL_DEPTH - 1)) + +/* + * The resulting wheel size. If NOHZ is configured we allocate two + * wheels so we have a separate storage for the deferrable timers. + */ +#define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) + +#ifdef CONFIG_NO_HZ_COMMON +# define NR_BASES 2 +# define BASE_STD 0 +# define BASE_DEF 1 +#else +# define NR_BASES 1 +# define BASE_STD 0 +# define BASE_DEF 0 +#endif struct timer_base { - spinlock_t lock; - struct timer_list *running_timer; - unsigned long clk; - unsigned long next_timer; - unsigned long active_timers; - unsigned long all_timers; - int cpu; - bool migration_enabled; - bool nohz_active; - struct tvec_root tv1; - struct tvec tv2; - struct tvec tv3; - struct tvec tv4; - struct tvec tv5; + spinlock_t lock; + struct timer_list *running_timer; + unsigned long clk; + unsigned int cpu; + bool migration_enabled; + bool nohz_active; + DECLARE_BITMAP(pending_map, WHEEL_SIZE); + struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; - -static DEFINE_PER_CPU(struct timer_base, timer_bases); +static DEFINE_PER_CPU(struct timer_base, timer_bases[NR_BASES]); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) unsigned int sysctl_timer_migration = 1; @@ -106,15 +214,17 @@ void timers_update_migration(bool update_nohz) unsigned int cpu; /* Avoid the loop, if nothing to update */ - if (this_cpu_read(timer_bases.migration_enabled) == on) + if (this_cpu_read(timer_bases[BASE_STD].migration_enabled) == on) return; for_each_possible_cpu(cpu) { - per_cpu(timer_bases.migration_enabled, cpu) = on; + per_cpu(timer_bases[BASE_STD].migration_enabled, cpu) = on; + per_cpu(timer_bases[BASE_DEF].migration_enabled, cpu) = on; per_cpu(hrtimer_bases.migration_enabled, cpu) = on; if (!update_nohz) continue; - per_cpu(timer_bases.nohz_active, cpu) = true; + per_cpu(timer_bases[BASE_STD].nohz_active, cpu) = true; + per_cpu(timer_bases[BASE_DEF].nohz_active, cpu) = true; per_cpu(hrtimer_bases.nohz_active, cpu) = true; } } @@ -133,20 +243,6 @@ int timer_migration_handler(struct ctl_table *table, int write, mutex_unlock(&mutex); return ret; } - -static inline struct timer_base *get_target_base(struct timer_base *base, - int pinned) -{ - if (pinned || !base->migration_enabled) - return this_cpu_ptr(&timer_bases); - return per_cpu_ptr(&timer_bases, get_nohz_timer_target()); -} -#else -static inline struct timer_base *get_target_base(struct timer_base *base, - int pinned) -{ - return this_cpu_ptr(&timer_bases); -} #endif static unsigned long round_jiffies_common(unsigned long j, int cpu, @@ -370,78 +466,91 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); +static inline unsigned int timer_get_idx(struct timer_list *timer) +{ + return (timer->flags & TIMER_ARRAYMASK) >> TIMER_ARRAYSHIFT; +} + +static inline void timer_set_idx(struct timer_list *timer, unsigned int idx) +{ + timer->flags = (timer->flags & ~TIMER_ARRAYMASK) | + idx << TIMER_ARRAYSHIFT; +} + +/* + * Helper function to calculate the array index for a given expiry + * time. + */ +static inline unsigned calc_index(unsigned expires, unsigned lvl) +{ + expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl); + return LVL_OFFS(lvl) + (expires & LVL_MASK); +} + static void __internal_add_timer(struct timer_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; - unsigned long idx = expires - base->clk; + unsigned long delta = expires - base->clk; struct hlist_head *vec; - - if (idx < TVR_SIZE) { - int i = expires & TVR_MASK; - vec = base->tv1.vec + i; - } else if (idx < 1 << (TVR_BITS + TVN_BITS)) { - int i = (expires >> TVR_BITS) & TVN_MASK; - vec = base->tv2.vec + i; - } else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK; - vec = base->tv3.vec + i; - } else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) { - int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK; - vec = base->tv4.vec + i; - } else if ((signed long) idx < 0) { - /* - * Can happen if you add a timer with expires == jiffies, - * or you set a timer to go off in the past - */ - vec = base->tv1.vec + (base->clk & TVR_MASK); + unsigned int idx; + + if (delta < LVL_START(1)) { + idx = calc_index(expires, 0); + } else if (delta < LVL_START(2)) { + idx = calc_index(expires, 1); + } else if (delta < LVL_START(3)) { + idx = calc_index(expires, 2); + } else if (delta < LVL_START(4)) { + idx = calc_index(expires, 3); + } else if (delta < LVL_START(5)) { + idx = calc_index(expires, 4); + } else if (delta < LVL_START(6)) { + idx = calc_index(expires, 5); + } else if (delta < LVL_START(7)) { + idx = calc_index(expires, 6); + } else if (LVL_DEPTH > 8 && delta < LVL_START(8)) { + idx = calc_index(expires, 7); + } else if ((long) delta < 0) { + idx = base->clk & LVL_MASK; } else { - int i; - /* If the timeout is larger than MAX_TVAL (on 64-bit - * architectures or with CONFIG_BASE_SMALL=1) then we - * use the maximum timeout. + /* + * Force expire obscene large timeouts to expire at the + * capacity limit of the wheel. */ - if (idx > MAX_TVAL) { - idx = MAX_TVAL; - expires = idx + base->clk; - } - i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; - vec = base->tv5.vec + i; - } + if (expires >= WHEEL_TIMEOUT_CUTOFF) + expires = WHEEL_TIMEOUT_MAX; + idx = calc_index(expires, LVL_DEPTH - 1); + } + /* + * Enqueue the timer into the array bucket, mark it pending in + * the bitmap and store the index in the timer flags. + */ + vec = base->vectors + idx; hlist_add_head(&timer->entry, vec); + __set_bit(idx, base->pending_map); + timer_set_idx(timer, idx); } static void internal_add_timer(struct timer_base *base, struct timer_list *timer) { - /* Advance base->jiffies, if the base is empty */ - if (!base->all_timers++) - base->clk = jiffies; - __internal_add_timer(base, timer); - /* - * Update base->active_timers and base->next_timer - */ - if (!(timer->flags & TIMER_DEFERRABLE)) { - if (!base->active_timers++ || - time_before(timer->expires, base->next_timer)) - base->next_timer = timer->expires; - } /* * Check whether the other CPU is in dynticks mode and needs - * to be triggered to reevaluate the timer wheel. - * We are protected against the other CPU fiddling - * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to stop its tick can not - * evaluate the timer wheel. + * to be triggered to reevaluate the timer wheel. We are + * protected against the other CPU fiddling with the timer by + * holding the timer base lock. This also makes sure that a + * CPU on the way to stop its tick can not evaluate the timer + * wheel. * * Spare the IPI for deferrable timers on idle targets though. * The next busy ticks will take care of it. Except full dynticks * require special care against races with idle_cpu(), lets deal * with that later. */ - if (base->nohz_active) { + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) { if (!(timer->flags & TIMER_DEFERRABLE) || tick_nohz_full_cpu(base->cpu)) wake_up_nohz_cpu(base->cpu); @@ -706,54 +815,87 @@ static inline void detach_timer(struct timer_list *timer, bool clear_pending) entry->next = LIST_POISON2; } -static inline void -detach_expired_timer(struct timer_list *timer, struct timer_base *base) -{ - detach_timer(timer, true); - if (!(timer->flags & TIMER_DEFERRABLE)) - base->active_timers--; - base->all_timers--; -} - static int detach_if_pending(struct timer_list *timer, struct timer_base *base, bool clear_pending) { + unsigned idx = timer_get_idx(timer); + if (!timer_pending(timer)) return 0; + if (hlist_is_singular_node(&timer->entry, base->vectors + idx)) + __clear_bit(idx, base->pending_map); + detach_timer(timer, clear_pending); - if (!(timer->flags & TIMER_DEFERRABLE)) { - base->active_timers--; - if (timer->expires == base->next_timer) - base->next_timer = base->clk; - } - /* If this was the last timer, advance base->jiffies */ - if (!--base->all_timers) - base->clk = jiffies; return 1; } +static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) +{ + struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); + + /* + * If the timer is deferrable and nohz is active then we need to use + * the deferrable base. + */ + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && + (tflags & TIMER_DEFERRABLE)) + base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); + return base; +} + +static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) +{ + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + + /* + * If the timer is deferrable and nohz is active then we need to use + * the deferrable base. + */ + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && + (tflags & TIMER_DEFERRABLE)) + base = this_cpu_ptr(&timer_bases[BASE_DEF]); + return base; +} + +static inline struct timer_base *get_timer_base(u32 tflags) +{ + return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); +} + +static inline struct timer_base *get_target_base(struct timer_base *base, + unsigned tflags) +{ +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) + if ((tflags & TIMER_PINNED) || !base->migration_enabled) + return get_timer_this_cpu_base(tflags); + return get_timer_cpu_base(tflags, get_nohz_timer_target()); +#else + return get_timer_this_cpu_base(tflags); +#endif +} + /* - * We are using hashed locking: holding per_cpu(timer_bases).lock - * means that all timers which are tied to this base via timer->base are - * locked, and the base itself is locked too. + * We are using hashed locking: Holding per_cpu(timer_bases[x]).lock means + * that all timers which are tied to this base are locked, and the base itself + * is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could - * be found on ->tvX lists. + * be found in the base->vectors array. * - * When the timer's base is locked and removed from the list, the - * TIMER_MIGRATING flag is set, FIXME + * When a timer is migrating then the TIMER_MIGRATING flag is set and we need + * to wait until the migration is done. */ static struct timer_base *lock_timer_base(struct timer_list *timer, - unsigned long *flags) + unsigned long *flags) __acquires(timer->base->lock) { for (;;) { - u32 tf = timer->flags; struct timer_base *base; + u32 tf = timer->flags; if (!(tf & TIMER_MIGRATING)) { - base = per_cpu_ptr(&timer_bases, tf & TIMER_CPUMASK); + base = get_timer_base(tf); spin_lock_irqsave(&base->lock, *flags); if (timer->flags == tf) return base; @@ -770,6 +912,27 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) unsigned long flags; int ret = 0; + /* + * TODO: Calculate the array bucket of the timer right here w/o + * holding the base lock. This allows to check not only + * timer->expires == expires below, but also whether the timer + * ends up in the same bucket. If we really need to requeue + * the timer then we check whether base->clk have + * advanced between here and locking the timer base. If + * jiffies advanced we have to recalc the array bucket with the + * lock held. + */ + + /* + * This is a common optimization triggered by the + * networking code - if the timer is re-modified + * to be the same thing then just return: + */ + if (timer_pending(timer)) { + if (timer->expires == expires) + return 1; + } + timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); @@ -781,15 +944,15 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) debug_activate(timer, expires); - new_base = get_target_base(base, timer->flags & TIMER_PINNED); + new_base = get_target_base(base, timer->flags); if (base != new_base) { /* - * We are trying to schedule the timer on the local CPU. + * We are trying to schedule the timer on the new base. * However we can't change timer's base while it is running, * otherwise del_timer_sync() can't detect that the timer's - * handler yet has not finished. This also guarantees that - * the timer is serialized wrt itself. + * handler yet has not finished. This also guarantees that the + * timer is serialized wrt itself. */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ @@ -828,45 +991,6 @@ int mod_timer_pending(struct timer_list *timer, unsigned long expires) } EXPORT_SYMBOL(mod_timer_pending); -/* - * Decide where to put the timer while taking the slack into account - * - * Algorithm: - * 1) calculate the maximum (absolute) time - * 2) calculate the highest bit where the expires and new max are different - * 3) use this bit to make a mask - * 4) use the bitmask to round down the maximum time, so that all last - * bits are zeros - */ -static inline -unsigned long apply_slack(struct timer_list *timer, unsigned long expires) -{ - unsigned long expires_limit, mask; - int bit; - - if (timer->slack >= 0) { - expires_limit = expires + timer->slack; - } else { - long delta = expires - jiffies; - - if (delta < 256) - return expires; - - expires_limit = expires + delta / 256; - } - mask = expires ^ expires_limit; - if (mask == 0) - return expires; - - bit = __fls(mask); - - mask = (1UL << bit) - 1; - - expires_limit = expires_limit & ~(mask); - - return expires_limit; -} - /** * mod_timer - modify a timer's timeout * @timer: the timer to be modified @@ -889,16 +1013,6 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) */ int mod_timer(struct timer_list *timer, unsigned long expires) { - expires = apply_slack(timer, expires); - - /* - * This is a common optimization triggered by the - * networking code - if the timer is re-modified - * to be the same thing then just return: - */ - if (timer_pending(timer) && timer->expires == expires) - return 1; - return __mod_timer(timer, expires, false); } EXPORT_SYMBOL(mod_timer); @@ -933,13 +1047,14 @@ EXPORT_SYMBOL(add_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - struct timer_base *new_base = per_cpu_ptr(&timer_bases, cpu); - struct timer_base *base; + struct timer_base *new_base, *base; unsigned long flags; timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); + new_base = get_timer_cpu_base(timer->flags, cpu); + /* * If @timer was on a different CPU, it should be migrated with the * old base locked to prevent other operations proceeding with the @@ -1085,27 +1200,6 @@ int del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(del_timer_sync); #endif -static int cascade(struct timer_base *base, struct tvec *tv, int index) -{ - /* cascade all the timers from tv up one level */ - struct timer_list *timer; - struct hlist_node *tmp; - struct hlist_head tv_list; - - hlist_move_list(tv->vec + index, &tv_list); - - /* - * We are removing _all_ timers from the list, so we - * don't have to detach them individually. - */ - hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) { - /* No accounting, while moving them */ - __internal_add_timer(base, timer); - } - - return index; -} - static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), unsigned long data) { @@ -1149,68 +1243,80 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), } } -#define INDEX(N) ((base->clk >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) +static void expire_timers(struct timer_base *base, struct hlist_head *head) +{ + while (!hlist_empty(head)) { + struct timer_list *timer; + void (*fn)(unsigned long); + unsigned long data; + + timer = hlist_entry(head->first, struct timer_list, entry); + timer_stats_account_timer(timer); + + base->running_timer = timer; + detach_timer(timer, true); + + fn = timer->function; + data = timer->data; + + if (timer->flags & TIMER_IRQSAFE) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock_irq(&base->lock); + } + } +} + +static int collect_expired_timers(struct timer_base *base, + struct hlist_head *heads) +{ + unsigned long clk = base->clk; + struct hlist_head *vec; + int i, levels = 0; + unsigned int idx; + + for (i = 0; i < LVL_DEPTH; i++) { + idx = (clk & LVL_MASK) + i * LVL_SIZE; + + if (__test_and_clear_bit(idx, base->pending_map)) { + vec = base->vectors + idx; + hlist_move_list(vec, heads++); + levels++; + } + /* Is it time to look at the next level? */ + if (clk & LVL_CLK_MASK) + break; + /* Shift clock for the next level granularity */ + clk >>= LVL_CLK_SHIFT; + } + return levels; +} /** * __run_timers - run all expired timers (if any) on this CPU. * @base: the timer vector to be processed. - * - * This function cascades all vectors and executes all expired timer - * vectors. */ static inline void __run_timers(struct timer_base *base) { - struct timer_list *timer; + struct hlist_head heads[LVL_DEPTH]; + int levels; + + if (!time_after_eq(jiffies, base->clk)) + return; spin_lock_irq(&base->lock); while (time_after_eq(jiffies, base->clk)) { - struct hlist_head work_list; - struct hlist_head *head = &work_list; - int index; - if (!base->all_timers) { - base->clk = jiffies; - break; - } - - index = base->clk & TVR_MASK; + levels = collect_expired_timers(base, heads); + base->clk++; - /* - * Cascade timers: - */ - if (!index && - (!cascade(base, &base->tv2, INDEX(0))) && - (!cascade(base, &base->tv3, INDEX(1))) && - !cascade(base, &base->tv4, INDEX(2))) - cascade(base, &base->tv5, INDEX(3)); - ++base->clk; - hlist_move_list(base->tv1.vec + index, head); - while (!hlist_empty(head)) { - void (*fn)(unsigned long); - unsigned long data; - bool irqsafe; - - timer = hlist_entry(head->first, struct timer_list, entry); - fn = timer->function; - data = timer->data; - irqsafe = timer->flags & TIMER_IRQSAFE; - - timer_stats_account_timer(timer); - - base->running_timer = timer; - detach_expired_timer(timer, base); - - if (irqsafe) { - spin_unlock(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock(&base->lock); - } else { - spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock_irq(&base->lock); - } - } + while (levels--) + expire_timers(base, heads + levels); } base->running_timer = NULL; spin_unlock_irq(&base->lock); @@ -1218,78 +1324,87 @@ static inline void __run_timers(struct timer_base *base) #ifdef CONFIG_NO_HZ_COMMON /* - * Find out when the next timer event is due to happen. This - * is used on S/390 to stop all activity when a CPU is idle. - * This function needs to be called with interrupts disabled. + * Find the next pending bucket of a level. Search from @offset + @clk upwards + * and if nothing there, search from start of the level (@offset) up to + * @offset + clk. + */ +static int next_pending_bucket(struct timer_base *base, unsigned offset, + unsigned clk) +{ + unsigned pos, start = offset + clk; + unsigned end = offset + LVL_SIZE; + + pos = find_next_bit(base->pending_map, end, start); + if (pos < end) + return pos - start; + + pos = find_next_bit(base->pending_map, start, offset); + return pos < start ? pos + LVL_SIZE - start : -1; +} + +/* + * Search the first expiring timer in the various clock levels. */ static unsigned long __next_timer_interrupt(struct timer_base *base) { - unsigned long clk = base->clk; - unsigned long expires = clk + NEXT_TIMER_MAX_DELTA; - int index, slot, array, found = 0; - struct timer_list *nte; - struct tvec *varray[4]; - - /* Look for timer events in tv1. */ - index = slot = clk & TVR_MASK; - do { - hlist_for_each_entry(nte, base->tv1.vec + slot, entry) { - if (nte->flags & TIMER_DEFERRABLE) - continue; - - found = 1; - expires = nte->expires; - /* Look at the cascade bucket(s)? */ - if (!index || slot < index) - goto cascade; - return expires; + unsigned long clk, next, adj; + unsigned lvl, offset = 0; + + spin_lock(&base->lock); + next = base->clk + NEXT_TIMER_MAX_DELTA; + clk = base->clk; + for (lvl = 0; lvl < LVL_DEPTH; lvl++, offset += LVL_SIZE) { + int pos = next_pending_bucket(base, offset, clk & LVL_MASK); + + if (pos >= 0) { + unsigned long tmp = clk + (unsigned long) pos; + + tmp <<= LVL_SHIFT(lvl); + if (time_before(tmp, next)) + next = tmp; } - slot = (slot + 1) & TVR_MASK; - } while (slot != index); - -cascade: - /* Calculate the next cascade event */ - if (index) - clk += TVR_SIZE - index; - clk >>= TVR_BITS; - - /* Check tv2-tv5. */ - varray[0] = &base->tv2; - varray[1] = &base->tv3; - varray[2] = &base->tv4; - varray[3] = &base->tv5; - - for (array = 0; array < 4; array++) { - struct tvec *varp = varray[array]; - - index = slot = clk & TVN_MASK; - do { - hlist_for_each_entry(nte, varp->vec + slot, entry) { - if (nte->flags & TIMER_DEFERRABLE) - continue; - - found = 1; - if (time_before(nte->expires, expires)) - expires = nte->expires; - } - /* - * Do we still search for the first timer or are - * we looking up the cascade buckets ? - */ - if (found) { - /* Look at the cascade bucket(s)? */ - if (!index || slot < index) - break; - return expires; - } - slot = (slot + 1) & TVN_MASK; - } while (slot != index); - - if (index) - clk += TVN_SIZE - index; - clk >>= TVN_BITS; + /* + * Clock for the next level. If the current level clock lower + * bits are zero, we look at the next level as is. If not we + * need to advance it by one because that's going to be the + * next expiring bucket in that level. base->clk is the next + * expiring jiffie. So in case of: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 0 0 + * + * we have to look at all levels @index 0. With + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 0 2 + * + * LVL0 has the next expiring bucket @index 2. The upper + * levels have the next expiring bucket @index 1. + * + * In case that the propagation wraps the next level the same + * rules apply: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 + * 0 0 0 0 F 2 + * + * So after looking at LVL0 we get: + * + * LVL5 LVL4 LVL3 LVL2 LVL1 + * 0 0 0 1 0 + * + * So no propagation from LVL1 to LVL2 because that happened + * with the add already, but then we need to propagate further + * from LVL2 to LVL3. + * + * So the simple check whether the lower bits of the current + * level are 0 or not is sufficient for all cases. + */ + adj = clk & LVL_CLK_MASK ? 1 : 0; + clk >>= LVL_CLK_SHIFT; + clk += adj; } - return expires; + spin_unlock(&base->lock); + return next; } /* @@ -1335,7 +1450,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) */ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { - struct timer_base *base = this_cpu_ptr(&timer_bases); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; @@ -1346,17 +1461,11 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (cpu_is_offline(smp_processor_id())) return expires; - spin_lock(&base->lock); - if (base->active_timers) { - if (time_before_eq(base->next_timer, base->clk)) - base->next_timer = __next_timer_interrupt(base); - nextevt = base->next_timer; - if (time_before_eq(nextevt, basej)) - expires = basem; - else - expires = basem + (nextevt - basej) * TICK_NSEC; - } - spin_unlock(&base->lock); + nextevt = __next_timer_interrupt(base); + if (time_before_eq(nextevt, basej)) + expires = basem; + else + expires = basem + (nextevt - basej) * TICK_NSEC; return cmp_next_hrtimer_event(basem, expires); } @@ -1387,10 +1496,11 @@ void update_process_times(int user_tick) */ static void run_timer_softirq(struct softirq_action *h) { - struct timer_base *base = this_cpu_ptr(&timer_bases); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - if (time_after_eq(jiffies, base->clk)) - __run_timers(base); + __run_timers(base); + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) + __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } /* @@ -1541,7 +1651,6 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h while (!hlist_empty(head)) { timer = hlist_entry(head->first, struct timer_list, entry); - /* We ignore the accounting on the dying cpu */ detach_timer(timer, false); timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); @@ -1552,35 +1661,29 @@ static void migrate_timers(int cpu) { struct timer_base *old_base; struct timer_base *new_base; - int i; + int b, i; BUG_ON(cpu_online(cpu)); - old_base = per_cpu_ptr(&timer_bases, cpu); - new_base = get_cpu_ptr(&timer_bases); - /* - * The caller is globally serialized and nobody else - * takes two locks at once, deadlock is not possible. - */ - spin_lock_irq(&new_base->lock); - spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); - - BUG_ON(old_base->running_timer); - - for (i = 0; i < TVR_SIZE; i++) - migrate_timer_list(new_base, old_base->tv1.vec + i); - for (i = 0; i < TVN_SIZE; i++) { - migrate_timer_list(new_base, old_base->tv2.vec + i); - migrate_timer_list(new_base, old_base->tv3.vec + i); - migrate_timer_list(new_base, old_base->tv4.vec + i); - migrate_timer_list(new_base, old_base->tv5.vec + i); - } - old_base->active_timers = 0; - old_base->all_timers = 0; + for (b = 0; b < NR_BASES; b++) { + old_base = per_cpu_ptr(&timer_bases[b], cpu); + new_base = get_cpu_ptr(&timer_bases[b]); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); + spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + + BUG_ON(old_base->running_timer); + + for (i = 0; i < WHEEL_SIZE; i++) + migrate_timer_list(new_base, old_base->vectors + i); - spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); - put_cpu_ptr(&timer_bases); + spin_unlock(&old_base->lock); + spin_unlock_irq(&new_base->lock); + put_cpu_ptr(&timer_bases); + } } static int timer_cpu_notify(struct notifier_block *self, @@ -1608,13 +1711,15 @@ static inline void timer_register_cpu_notifier(void) { } static void __init init_timer_cpu(int cpu) { - struct timer_base *base = per_cpu_ptr(&timer_bases, cpu); - - base->cpu = cpu; - spin_lock_init(&base->lock); + struct timer_base *base; + int i; - base->clk = jiffies; - base->next_timer = base->clk; + for (i = 0; i < NR_BASES; i++) { + base = per_cpu_ptr(&timer_bases[i], cpu); + base->cpu = cpu; + spin_lock_init(&base->lock); + base->clk = jiffies; + } } static void __init init_timer_cpus(void) -- cgit v1.2.3 From 53bf837b78d155b8e1110b3c25b4d0d6391b8ff3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 4 Jul 2016 09:50:31 +0000 Subject: timers: Remove set_timer_slack() leftovers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We now have implicit batching in the timer wheel. The slack API is no longer used, so remove it. Signed-off-by: Thomas Gleixner Cc: Alan Stern Cc: Andrew F. Davis Cc: Arjan van de Ven Cc: Chris Mason Cc: David S. Miller Cc: David Woodhouse Cc: Dmitry Eremin-Solenikov Cc: Eric Dumazet Cc: Frederic Weisbecker Cc: George Spelvin Cc: Greg Kroah-Hartman Cc: Jaehoon Chung Cc: Jens Axboe Cc: John Stultz Cc: Josh Triplett Cc: Len Brown Cc: Linus Torvalds Cc: Mathias Nyman Cc: Pali Rohár Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Sebastian Reichel Cc: Ulf Hansson Cc: linux-block@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mmc@vger.kernel.org Cc: linux-pm@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: netdev@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160704094342.189813118@linutronix.de Signed-off-by: Ingo Molnar --- block/genhd.c | 5 ----- drivers/mmc/host/jz4740_mmc.c | 2 -- drivers/power/bq27xxx_battery.c | 5 +---- drivers/usb/host/ohci-hcd.c | 1 - drivers/usb/host/xhci.c | 2 -- include/linux/timer.h | 4 ---- kernel/time/timer.c | 19 ------------------- lib/random32.c | 1 - 8 files changed, 1 insertion(+), 38 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index 9f42526b4d62..f06d7f3b075b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1523,12 +1523,7 @@ static void __disk_unblock_events(struct gendisk *disk, bool check_now) if (--ev->block) goto out_unlock; - /* - * Not exactly a latency critical operation, set poll timer - * slack to 25% and kick event check. - */ intv = disk_events_poll_jiffies(disk); - set_timer_slack(&ev->dwork.timer, intv / 4); if (check_now) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 03ddf0ecf402..684087db170b 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1068,8 +1068,6 @@ static int jz4740_mmc_probe(struct platform_device* pdev) jz4740_mmc_clock_disable(host); setup_timer(&host->timeout_timer, jz4740_mmc_timeout, (unsigned long)host); - /* It is not important when it times out, it just needs to timeout. */ - set_timer_slack(&host->timeout_timer, HZ); host->use_dma = true; if (host->use_dma && jz4740_mmc_acquire_dma_channels(host) != 0) diff --git a/drivers/power/bq27xxx_battery.c b/drivers/power/bq27xxx_battery.c index 45f6ebf88df6..e90b3f307e0f 100644 --- a/drivers/power/bq27xxx_battery.c +++ b/drivers/power/bq27xxx_battery.c @@ -735,11 +735,8 @@ static void bq27xxx_battery_poll(struct work_struct *work) bq27xxx_battery_update(di); - if (poll_interval > 0) { - /* The timer does not have to be accurate. */ - set_timer_slack(&di->work.timer, poll_interval * HZ / 4); + if (poll_interval > 0) schedule_delayed_work(&di->work, poll_interval * HZ); - } } /* diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 0449235d4f22..1700908b84ef 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -500,7 +500,6 @@ static int ohci_init (struct ohci_hcd *ohci) setup_timer(&ohci->io_watchdog, io_watchdog_func, (unsigned long) ohci); - set_timer_slack(&ohci->io_watchdog, msecs_to_jiffies(20)); ohci->hcca = dma_alloc_coherent (hcd->self.controller, sizeof(*ohci->hcca), &ohci->hcca_dma, GFP_KERNEL); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index f2f9518c53ab..a986fe763d87 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -490,8 +490,6 @@ static void compliance_mode_recovery_timer_init(struct xhci_hcd *xhci) xhci->comp_mode_recovery_timer.expires = jiffies + msecs_to_jiffies(COMP_MODE_RCVRY_MSECS); - set_timer_slack(&xhci->comp_mode_recovery_timer, - msecs_to_jiffies(COMP_MODE_RCVRY_MSECS)); add_timer(&xhci->comp_mode_recovery_timer); xhci_dbg_trace(xhci, trace_xhci_dbg_quirks, "Compliance mode recovery timer initialized"); diff --git a/include/linux/timer.h b/include/linux/timer.h index 5869ab9848fe..4419506b564e 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -19,7 +19,6 @@ struct timer_list { void (*function)(unsigned long); unsigned long data; u32 flags; - int slack; #ifdef CONFIG_TIMER_STATS int start_pid; @@ -73,7 +72,6 @@ struct timer_list { .expires = (_expires), \ .data = (_data), \ .flags = (_flags), \ - .slack = -1, \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ } @@ -193,8 +191,6 @@ extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); -extern void set_timer_slack(struct timer_list *time, int slack_hz); - /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 86e95b72665d..a83e23d0bc25 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -447,24 +447,6 @@ unsigned long round_jiffies_up_relative(unsigned long j) } EXPORT_SYMBOL_GPL(round_jiffies_up_relative); -/** - * set_timer_slack - set the allowed slack for a timer - * @timer: the timer to be modified - * @slack_hz: the amount of time (in jiffies) allowed for rounding - * - * Set the amount of time, in jiffies, that a certain timer has - * in terms of slack. By setting this value, the timer subsystem - * will schedule the actual timer somewhere between - * the time mod_timer() asks for, and that time plus the slack. - * - * By setting the slack to -1, a percentage of the delay is used - * instead. - */ -void set_timer_slack(struct timer_list *timer, int slack_hz) -{ - timer->slack = slack_hz; -} -EXPORT_SYMBOL_GPL(set_timer_slack); static inline unsigned int timer_get_idx(struct timer_list *timer) { @@ -775,7 +757,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags, { timer->entry.pprev = NULL; timer->flags = flags | raw_smp_processor_id(); - timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; timer->start_pid = -1; diff --git a/lib/random32.c b/lib/random32.c index 510d1ce7d4d2..69ed593aab07 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -233,7 +233,6 @@ static void __prandom_timer(unsigned long dontcare) static void __init __prandom_start_seed_timer(void) { - set_timer_slack(&seed_timer, HZ); seed_timer.expires = jiffies + msecs_to_jiffies(40 * MSEC_PER_SEC); add_timer(&seed_timer); } -- cgit v1.2.3 From 069f0cd00df0abfb9252e0dbdc355e40e6ab75fc Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 5 Jul 2016 00:31:26 +0200 Subject: printk: Make the printk*once() variants return a value Have printk*once() return a bool which denotes whether the string was printed or not so that calling code can react accordingly. Signed-off-by: Borislav Petkov Cc: Andrew Morton Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1467671487-10344-3-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar --- include/linux/printk.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index f4da695fd615..f136b22c7772 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -108,11 +108,14 @@ struct va_format { * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format checking. */ -#define no_printk(fmt, ...) \ -do { \ - if (0) \ - printk(fmt, ##__VA_ARGS__); \ -} while (0) +#define no_printk(fmt, ...) \ +({ \ + do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ + } while (0); \ + 0; \ +}) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) @@ -309,20 +312,24 @@ extern asmlinkage void dump_stack(void) __cold; #define printk_once(fmt, ...) \ ({ \ static bool __print_once __read_mostly; \ + bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk(fmt, ##__VA_ARGS__); \ } \ + unlikely(__ret_print_once); \ }) #define printk_deferred_once(fmt, ...) \ ({ \ static bool __print_once __read_mostly; \ + bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk_deferred(fmt, ##__VA_ARGS__); \ } \ + unlikely(__ret_print_once); \ }) #else #define printk_once(fmt, ...) \ -- cgit v1.2.3 From b059a453b1cf1c8453c2b2ed373d3147d6264ebd Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Tue, 28 Jun 2016 14:35:38 +0300 Subject: x86/vdso: Add mremap hook to vm_special_mapping Add possibility for 32-bit user-space applications to move the vDSO mapping. Previously, when a user-space app called mremap() for the vDSO address, in the syscall return path it would land on the previous address of the vDSOpage, resulting in segmentation violation. Now it lands fine and returns to userspace with a remapped vDSO. This will also fix the context.vdso pointer for 64-bit, which does not affect the user of vDSO after mremap() currently, but this may change in the future. As suggested by Andy, return -EINVAL for mremap() that would split the vDSO image: that operation cannot possibly result in a working system so reject it. Renamed and moved the text_mapping structure declaration inside map_vdso(), as it used only there and now it complements the vvar_mapping variable. There is still a problem for remapping the vDSO in glibc applications: the linker relocates addresses for syscalls on the vDSO page, so you need to relink with the new addresses. Without that the next syscall through glibc may fail: Program received signal SIGSEGV, Segmentation fault. #0 0xf7fd9b80 in __kernel_vsyscall () #1 0xf7ec8238 in _exit () from /usr/lib32/libc.so.6 Signed-off-by: Dmitry Safonov Acked-by: Andy Lutomirski Cc: 0x7f454c46@gmail.com Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160628113539.13606-2-dsafonov@virtuozzo.com Signed-off-by: Ingo Molnar --- arch/x86/entry/vdso/vma.c | 47 ++++++++++++++++++++++++++++++++++++++++++----- include/linux/mm_types.h | 3 +++ mm/mmap.c | 10 ++++++++++ 3 files changed, 55 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index ab220ac9b3b9..3329844e3c43 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -97,10 +98,40 @@ static int vdso_fault(const struct vm_special_mapping *sm, return 0; } -static const struct vm_special_mapping text_mapping = { - .name = "[vdso]", - .fault = vdso_fault, -}; +static void vdso_fix_landing(const struct vdso_image *image, + struct vm_area_struct *new_vma) +{ +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + if (in_ia32_syscall() && image == &vdso_image_32) { + struct pt_regs *regs = current_pt_regs(); + unsigned long vdso_land = image->sym_int80_landing_pad; + unsigned long old_land_addr = vdso_land + + (unsigned long)current->mm->context.vdso; + + /* Fixing userspace landing - look at do_fast_syscall_32 */ + if (regs->ip == old_land_addr) + regs->ip = new_vma->vm_start + vdso_land; + } +#endif +} + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + unsigned long new_size = new_vma->vm_end - new_vma->vm_start; + const struct vdso_image *image = current->mm->context.vdso_image; + + if (image->size != new_size) + return -EINVAL; + + if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) + return -EFAULT; + + vdso_fix_landing(image, new_vma); + current->mm->context.vdso = (void __user *)new_vma->vm_start; + + return 0; +} static int vvar_fault(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf) @@ -151,6 +182,12 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) struct vm_area_struct *vma; unsigned long addr, text_start; int ret = 0; + + static const struct vm_special_mapping vdso_mapping = { + .name = "[vdso]", + .fault = vdso_fault, + .mremap = vdso_mremap, + }; static const struct vm_special_mapping vvar_mapping = { .name = "[vvar]", .fault = vvar_fault, @@ -185,7 +222,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) image->size, VM_READ|VM_EXEC| VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - &text_mapping); + &vdso_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ca3e517980a0..917f2b6a0cde 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -594,6 +594,9 @@ struct vm_special_mapping { int (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); + + int (*mremap)(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma); }; enum tlb_flush_reason { diff --git a/mm/mmap.c b/mm/mmap.c index de2c1769cc68..234edffec1d0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2943,9 +2943,19 @@ static const char *special_mapping_name(struct vm_area_struct *vma) return ((struct vm_special_mapping *)vma->vm_private_data)->name; } +static int special_mapping_mremap(struct vm_area_struct *new_vma) +{ + struct vm_special_mapping *sm = new_vma->vm_private_data; + + if (sm->mremap) + return sm->mremap(sm, new_vma); + return 0; +} + static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, + .mremap = special_mapping_mremap, .name = special_mapping_name, }; -- cgit v1.2.3 From c8607e020014cf11a61601a0005270bad81cabdf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 6 Jul 2016 14:53:06 +0200 Subject: netfilter: nft_ct: fix expiration getter We need to compute timeout.expires - jiffies, not the other way around. Add a helper, another patch can then later change more places in conntrack code where we currently open-code this. Will allow us to only change one place later when we remove per-ct timer. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 8 ++++++++ net/netfilter/nft_ct.c | 6 +----- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dd78bea227c8..b6083c34ef0d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -284,6 +284,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK; } +/* jiffies until ct expires, 0 if already expired */ +static inline unsigned long nf_ct_expires(const struct nf_conn *ct) +{ + long timeout = (long)ct->timeout.expires - (long)jiffies; + + return timeout > 0 ? timeout : 0; +} + struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 137e308d5b24..81fbb450783e 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -54,7 +54,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, const struct nf_conn_help *help; const struct nf_conntrack_tuple *tuple; const struct nf_conntrack_helper *helper; - long diff; unsigned int state; ct = nf_ct_get(pkt->skb, &ctinfo); @@ -94,10 +93,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #endif case NFT_CT_EXPIRATION: - diff = (long)jiffies - (long)ct->timeout.expires; - if (diff < 0) - diff = 0; - *dest = jiffies_to_msecs(diff); + *dest = jiffies_to_msecs(nf_ct_expires(ct)); return; case NFT_CT_HELPER: if (ct->master == NULL) -- cgit v1.2.3 From 7fb2b43c3252c9177825a0a49138cd16144b6b5e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 27 Jun 2016 12:49:20 +0200 Subject: efi: Reorganize the GUID table to make it easier to read Re-organize the GUID table so that every GUID takes a single line. This makes each line super long, but if you have a large enough terminal (or zoom out of a small terminal) then you can see the structure at a glance - which is more readable than it was the case with the multi-line layout. Acked-by: Matt Fleming Cc: Ard Biesheuvel Cc: Joe Perches Cc: Linus Torvalds Cc: Peter Jones Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20160627104920.GA9099@gmail.com Signed-off-by: Ingo Molnar --- include/linux/efi.h | 145 +++++++++++++--------------------------------------- 1 file changed, 36 insertions(+), 109 deletions(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index 0174f28ce9b3..7f80a75ee9e3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -538,9 +538,11 @@ void efi_native_runtime_setup(void); /* * EFI Configuration Table and GUID definitions * - * These should be formatted roughly like the ones in the UEFI SPEC has - * them. It makes them easier to grep for, and they look the same when - * you're staring at them. Here's the guide: + * These are all defined in a single line to make them easier to + * grep for and to see them at a glance - while still having a + * similar structure to the definitions in the spec. + * + * Here's how they are structured: * * GUID: 12345678-1234-1234-1234-123456789012 * Spec: @@ -548,119 +550,44 @@ void efi_native_runtime_setup(void); * {0x12345678,0x1234,0x1234,\ * {0x12,0x34,0x12,0x34,0x56,0x78,0x90,0x12}} * Here: - * #define SOME_PROTOCOL_GUID \ - * EFI_GUID(0x12345678, 0x1234, 0x1234, \ - * 0x12, 0x34, 0x12, 0x34, 0x56, 0x78, 0x90, 0x12) - * ^ tab ^tab ^ space + * #define SOME_PROTOCOL_GUID EFI_GUID(0x12345678, 0x1234, 0x1234, 0x12, 0x34, 0x12, 0x34, 0x56, 0x78, 0x90, 0x12) + * ^ tabs ^extra space + * + * Note that the 'extra space' separates the values at the same place + * where the UEFI SPEC breaks the line. */ -#define NULL_GUID \ - EFI_GUID(0x00000000, 0x0000, 0x0000, \ - 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00) - -#define MPS_TABLE_GUID \ - EFI_GUID(0xeb9d2d2f, 0x2d88, 0x11d3, \ - 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) - -#define ACPI_TABLE_GUID \ - EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, \ - 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) - -#define ACPI_20_TABLE_GUID \ - EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, \ - 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) - -#define SMBIOS_TABLE_GUID \ - EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, \ - 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) - -#define SMBIOS3_TABLE_GUID \ - EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, \ - 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94) - -#define SAL_SYSTEM_TABLE_GUID \ - EFI_GUID(0xeb9d2d32, 0x2d88, 0x11d3, \ - 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) - -#define HCDP_TABLE_GUID \ - EFI_GUID(0xf951938d, 0x620b, 0x42ef, \ - 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98) - -#define UGA_IO_PROTOCOL_GUID \ - EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, \ - 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2) - -#define EFI_GLOBAL_VARIABLE_GUID \ - EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, \ - 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c) - -#define UV_SYSTEM_TABLE_GUID \ - EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, \ - 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) - -#define LINUX_EFI_CRASH_GUID \ - EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, \ - 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) - -#define LOADED_IMAGE_PROTOCOL_GUID \ - EFI_GUID(0x5b1b31a1, 0x9562, 0x11d2, \ - 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) - -#define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID \ - EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, \ - 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) - -#define EFI_UGA_PROTOCOL_GUID \ - EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, \ - 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) - -#define EFI_PCI_IO_PROTOCOL_GUID \ - EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, \ - 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) - -#define EFI_FILE_INFO_ID \ - EFI_GUID(0x9576e92, 0x6d3f, 0x11d2, \ - 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) - -#define EFI_SYSTEM_RESOURCE_TABLE_GUID \ - EFI_GUID(0xb122a263, 0x3661, 0x4f68, \ - 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80) - -#define EFI_FILE_SYSTEM_GUID \ - EFI_GUID(0x964e5b22, 0x6459, 0x11d2, \ - 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) - -#define DEVICE_TREE_GUID \ - EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, \ - 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0) - -#define EFI_PROPERTIES_TABLE_GUID \ - EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, \ - 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5) - -#define EFI_RNG_PROTOCOL_GUID \ - EFI_GUID(0x3152bca5, 0xeade, 0x433d, \ - 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) - -#define EFI_MEMORY_ATTRIBUTES_TABLE_GUID \ - EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, \ - 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) - -#define EFI_CONSOLE_OUT_DEVICE_GUID \ - EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, \ - 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define NULL_GUID EFI_GUID(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00) +#define MPS_TABLE_GUID EFI_GUID(0xeb9d2d2f, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define ACPI_TABLE_GUID EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define ACPI_20_TABLE_GUID EFI_GUID(0x8868e871, 0xe4f1, 0x11d3, 0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81) +#define SMBIOS_TABLE_GUID EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define SMBIOS3_TABLE_GUID EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c, 0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94) +#define SAL_SYSTEM_TABLE_GUID EFI_GUID(0xeb9d2d32, 0x2d88, 0x11d3, 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) +#define HCDP_TABLE_GUID EFI_GUID(0xf951938d, 0x620b, 0x42ef, 0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98) +#define UGA_IO_PROTOCOL_GUID EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b, 0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2) +#define EFI_GLOBAL_VARIABLE_GUID EFI_GUID(0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c) +#define UV_SYSTEM_TABLE_GUID EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93) +#define LINUX_EFI_CRASH_GUID EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc, 0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0) +#define LOADED_IMAGE_PROTOCOL_GUID EFI_GUID(0x5b1b31a1, 0x9562, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) +#define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID EFI_GUID(0x9042a9de, 0x23dc, 0x4a38, 0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a) +#define EFI_UGA_PROTOCOL_GUID EFI_GUID(0x982c298b, 0xf4fa, 0x41cb, 0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39) +#define EFI_PCI_IO_PROTOCOL_GUID EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5, 0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a) +#define EFI_FILE_INFO_ID EFI_GUID(0x09576e92, 0x6d3f, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) +#define EFI_SYSTEM_RESOURCE_TABLE_GUID EFI_GUID(0xb122a263, 0x3661, 0x4f68, 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80) +#define EFI_FILE_SYSTEM_GUID EFI_GUID(0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) +#define DEVICE_TREE_GUID EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0) +#define EFI_PROPERTIES_TABLE_GUID EFI_GUID(0x880aaca3, 0x4adc, 0x4a04, 0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5) +#define EFI_RNG_PROTOCOL_GUID EFI_GUID(0x3152bca5, 0xeade, 0x433d, 0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44) +#define EFI_MEMORY_ATTRIBUTES_TABLE_GUID EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) +#define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance * associated with ConOut */ -#define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID \ - EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, \ - 0xb9, 0xe, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) - -#define LINUX_EFI_LOADER_ENTRY_GUID \ - EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, \ - 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) +#define LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID EFI_GUID(0xe03fc20a, 0x85dc, 0x406e, 0xb9, 0x0e, 0x4a, 0xb5, 0x02, 0x37, 0x1d, 0x95) +#define LINUX_EFI_LOADER_ENTRY_GUID EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf, 0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f) typedef struct { efi_guid_t guid; -- cgit v1.2.3 From 2e9d1e150abf88cb63e5d34ca286edbb95b4c53d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 20 Jun 2016 16:58:29 +0200 Subject: x86/entry: Avoid interrupt flag save and restore Thanks to all the work that was done by Andy Lutomirski and others, enter_from_user_mode() and prepare_exit_to_usermode() are now called only with interrupts disabled. Let's provide them a version of user_enter()/user_exit() that skips saving and restoring the interrupt flag. On an AMD-based machine I tested this patch on, with force-enabled context tracking, the speed-up in system calls was 90 clock cycles or 6%, measured with the following simple benchmark: #include #include #include #include unsigned long rdtsc() { unsigned long result; asm volatile("rdtsc; shl $32, %%rdx; mov %%eax, %%eax\n" "or %%rdx, %%rax" : "=a" (result) : : "rdx"); return result; } int main() { unsigned long tsc1, tsc2; int pid = getpid(); int i; tsc1 = rdtsc(); for (i = 0; i < 100000000; i++) kill(pid, SIGWINCH); tsc2 = rdtsc(); printf("%ld\n", tsc2 - tsc1); } Signed-off-by: Paolo Bonzini Reviewed-by: Rik van Riel Reviewed-by: Andy Lutomirski Acked-by: Paolo Bonzini Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Link: http://lkml.kernel.org/r/1466434712-31440-2-git-send-email-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/entry/common.c | 4 ++-- include/linux/context_tracking.h | 15 +++++++++++++++ 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index ec138e538c44..618bc61d35b7 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -43,7 +43,7 @@ static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) __visible void enter_from_user_mode(void) { CT_WARN_ON(ct_state() != CONTEXT_USER); - user_exit(); + user_exit_irqoff(); } #else static inline void enter_from_user_mode(void) {} @@ -274,7 +274,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) ti->status &= ~TS_COMPAT; #endif - user_enter(); + user_enter_irqoff(); } #define SYSCALL_EXIT_WORK_FLAGS \ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d259274238db..d9aef2a0ec8e 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -31,6 +31,19 @@ static inline void user_exit(void) context_tracking_exit(CONTEXT_USER); } +/* Called with interrupts disabled. */ +static inline void user_enter_irqoff(void) +{ + if (context_tracking_is_enabled()) + __context_tracking_enter(CONTEXT_USER); + +} +static inline void user_exit_irqoff(void) +{ + if (context_tracking_is_enabled()) + __context_tracking_exit(CONTEXT_USER); +} + static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; @@ -69,6 +82,8 @@ static inline enum ctx_state ct_state(void) #else static inline void user_enter(void) { } static inline void user_exit(void) { } +static inline void user_enter_irqoff(void) { } +static inline void user_exit_irqoff(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } -- cgit v1.2.3 From abb2bafd295fe962bbadc329dbfb2146457283ac Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sun, 12 Jun 2016 12:31:53 +0200 Subject: x86/quirks: Add early quirk to reset Apple AirPort card MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The EFI firmware on Macs contains a full-fledged network stack for downloading OS X images from osrecovery.apple.com. Unfortunately on Macs introduced 2011 and 2012, EFI brings up the Broadcom 4331 wireless card on every boot and leaves it enabled even after ExitBootServices has been called. The card continues to assert its IRQ line, causing spurious interrupts if the IRQ is shared. It also corrupts memory by DMAing received packets, allowing for remote code execution over the air. This only stops when a driver is loaded for the wireless card, which may be never if the driver is not installed or blacklisted. The issue seems to be constrained to the Broadcom 4331. Chris Milsted has verified that the newer Broadcom 4360 built into the MacBookPro11,3 (2013/2014) does not exhibit this behaviour. The chances that Apple will ever supply a firmware fix for the older machines appear to be zero. The solution is to reset the card on boot by writing to a reset bit in its mmio space. This must be done as an early quirk and not as a plain vanilla PCI quirk to successfully combat memory corruption by DMAed packets: Matthew Garrett found out in 2012 that the packets are written to EfiBootServicesData memory (http://mjg59.dreamwidth.org/11235.html). This type of memory is made available to the page allocator by efi_free_boot_services(). Plain vanilla PCI quirks run much later, in subsys initcall level. In-between a time window would be open for memory corruption. Random crashes occurring in this time window and attributed to DMAed packets have indeed been observed in the wild by Chris Bainbridge. When Matthew Garrett analyzed the memory corruption issue in 2012, he sought to fix it with a grub quirk which transitions the card to D3hot: http://git.savannah.gnu.org/cgit/grub.git/commit/?id=9d34bb85da56 This approach does not help users with other bootloaders and while it may prevent DMAed packets, it does not cure the spurious interrupts emanating from the card. Unfortunately the card's mmio space is inaccessible in D3hot, so to reset it, we have to undo the effect of Matthew's grub patch and transition the card back to D0. Note that the quirk takes a few shortcuts to reduce the amount of code: The size of BAR 0 and the location of the PM capability is identical on all affected machines and therefore hardcoded. Only the address of BAR 0 differs between models. Also, it is assumed that the BCMA core currently mapped is the 802.11 core. The EFI driver seems to always take care of this. Michael Büsch, Bjorn Helgaas and Matt Fleming contributed feedback towards finding the best solution to this problem. The following should be a comprehensive list of affected models: iMac13,1 2012 21.5" [Root Port 00:1c.3 = 8086:1e16] iMac13,2 2012 27" [Root Port 00:1c.3 = 8086:1e16] Macmini5,1 2011 i5 2.3 GHz [Root Port 00:1c.1 = 8086:1c12] Macmini5,2 2011 i5 2.5 GHz [Root Port 00:1c.1 = 8086:1c12] Macmini5,3 2011 i7 2.0 GHz [Root Port 00:1c.1 = 8086:1c12] Macmini6,1 2012 i5 2.5 GHz [Root Port 00:1c.1 = 8086:1e12] Macmini6,2 2012 i7 2.3 GHz [Root Port 00:1c.1 = 8086:1e12] MacBookPro8,1 2011 13" [Root Port 00:1c.1 = 8086:1c12] MacBookPro8,2 2011 15" [Root Port 00:1c.1 = 8086:1c12] MacBookPro8,3 2011 17" [Root Port 00:1c.1 = 8086:1c12] MacBookPro9,1 2012 15" [Root Port 00:1c.1 = 8086:1e12] MacBookPro9,2 2012 13" [Root Port 00:1c.1 = 8086:1e12] MacBookPro10,1 2012 15" [Root Port 00:1c.1 = 8086:1e12] MacBookPro10,2 2012 13" [Root Port 00:1c.1 = 8086:1e12] For posterity, spurious interrupts caused by the Broadcom 4331 wireless card resulted in splats like this (stacktrace omitted): irq 17: nobody cared (try booting with the "irqpoll" option) handlers: [] pcie_isr [] sdhci_irq [sdhci] threaded [] sdhci_thread_irq [sdhci] [] azx_interrupt [snd_hda_codec] Disabling IRQ #17 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=79301 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111781 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=728916 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=895951#c16 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1009819 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1098621 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1149632#c5 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1279130 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1332732 Tested-by: Konstantin Simanov # [MacBookPro8,1] Tested-by: Lukas Wunner # [MacBookPro9,1] Tested-by: Bryan Paradis # [MacBookPro9,2] Tested-by: Andrew Worsley # [MacBookPro10,1] Tested-by: Chris Bainbridge # [MacBookPro10,2] Signed-off-by: Lukas Wunner Acked-by: RafaÅ‚ MiÅ‚ecki Acked-by: Matt Fleming Cc: Andy Lutomirski Cc: Bjorn Helgaas Cc: Borislav Petkov Cc: Brian Gerst Cc: Chris Milsted Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Matthew Garrett Cc: Michael Buesch Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yinghai Lu Cc: b43-dev@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: stable@vger.kernel.org Cc: stable@vger.kernel.org # 123456789abc: x86/quirks: Apply nvidia_bugs quirk only on root bus Cc: stable@vger.kernel.org # 123456789abc: x86/quirks: Reintroduce scanning of secondary buses Link: http://lkml.kernel.org/r/48d0972ac82a53d460e5fce77a07b2560db95203.1465690253.git.lukas@wunner.de [ Did minor readability edits. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/early-quirks.c | 64 ++++++++++++++++++++++++++++++++++++++++++ drivers/bcma/bcma_private.h | 2 -- include/linux/bcma/bcma.h | 1 + 3 files changed, 65 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index ea60c05c2487..57b71373bae3 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include #include +#include +#include #include +#include +#include #include #include #include @@ -21,6 +25,9 @@ #include #include #include +#include + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -597,6 +604,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -639,6 +701,8 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index eda09090cb52..f642c4264c27 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -8,8 +8,6 @@ #include #include -#define BCMA_CORE_SIZE 0x1000 - #define bcma_err(bus, fmt, ...) \ pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index e6b41f42602b..3db25df396cb 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -159,6 +159,7 @@ struct bcma_host_ops { #define BCMA_CORE_DEFAULT 0xFFF #define BCMA_MAX_NR_CORES 16 +#define BCMA_CORE_SIZE 0x1000 /* Chip IDs of PCIe devices */ #define BCMA_CHIP_ID_BCM4313 0x4313 -- cgit v1.2.3 From 44530d588e142a96cf0cd345a7cb8911c4f88720 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 10 Jul 2016 20:58:36 +0200 Subject: Revert "perf/x86/intel, watchdog: Switch NMI watchdog to ref cycles on x86" This reverts commit 2c95afc1e83d93fac3be6923465e1753c2c53b0a. Stephane reported the following regression: > Since Andi added: > > commit 2c95afc1e83d93fac3be6923465e1753c2c53b0a > Author: Andi Kleen > Date: Thu Jun 9 06:14:38 2016 -0700 > > perf/x86/intel, watchdog: Switch NMI watchdog to ref cycles on x86 > > $ perf stat -e ref-cycles ls > .... > > fails systematically because the ref-cycles is now used by the > watchdog and given this is a system-wide pinned event, it monopolizes > the fixed counter 2 which is the only counter able to measure this event. Since the next merge window is near, fix the regression for now by reverting the commit. Reported-by: Stephane Eranian Cc: Andi Kleen Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Vince Weaver Cc: Alexander Shishkin Cc: Linus Torvalds Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/hw_nmi.c | 8 -------- include/linux/nmi.h | 1 - kernel/watchdog.c | 7 ------- 3 files changed, 16 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 016f4263fad4..7788ce643bf4 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -18,16 +18,8 @@ #include #include #include -#include #ifdef CONFIG_HARDLOCKUP_DETECTOR -int hw_nmi_get_event(void) -{ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) - return PERF_COUNT_HW_REF_CPU_CYCLES; - return PERF_COUNT_HW_CPU_CYCLES; -} - u64 hw_nmi_get_sample_period(int watchdog_thresh) { return (u64)(cpu_khz) * 1000 * watchdog_thresh; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 79858af27209..4630eeae18e0 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -66,7 +66,6 @@ static inline bool trigger_allbutself_cpu_backtrace(void) #ifdef CONFIG_LOCKUP_DETECTOR u64 hw_nmi_get_sample_period(int watchdog_thresh); -int hw_nmi_get_event(void); extern int nmi_watchdog_enabled; extern int soft_watchdog_enabled; extern int watchdog_user_enabled; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 8dd30fcd91be..9acb29f280ec 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -315,12 +315,6 @@ static int is_softlockup(unsigned long touch_ts) #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* Can be overriden by architecture */ -__weak int hw_nmi_get_event(void) -{ - return PERF_COUNT_HW_CPU_CYCLES; -} - static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -610,7 +604,6 @@ static int watchdog_nmi_enable(unsigned int cpu) wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); - wd_attr->config = hw_nmi_get_event(); /* Try to register using hardware perf events */ event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); -- cgit v1.2.3 From 00c611def8748a0a1cf1d31842e49b42dfdb3de1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 11 Jul 2016 16:21:08 +0200 Subject: Revert "ACPI 2.0 / AML: Improve module level execution by moving the If/Else/While execution to per-table basis" Revert commit 3d4b7ae96d81 (ACPI 2.0 / AML: Improve module level execution by moving the If/Else/While execution to per-table basis) that enabled the execution of module-level AML after loading each table (rather than after all AML tables have been loaded), but overlooked locking issues resulting from that change. Fixes: 3d4b7ae96d81 (ACPI 2.0 / AML: Improve module level execution by moving the If/Else/While execution to per-table basis) Reported-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 4e4c21491c41..1ff3a76c265d 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -192,7 +192,7 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_do_not_use_xsdt, FALSE); /* * Optionally support group module level code. */ -ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, FALSE); +ACPI_INIT_GLOBAL(u8, acpi_gbl_group_module_level_code, TRUE); /* * Optionally use 32-bit FADT addresses if and when there is a conflict -- cgit v1.2.3 From 6d4e56ce977864b0fcd28c61555060e6010aa89b Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 11 Jul 2016 09:10:06 -0400 Subject: posix_acl: de-union a_refcount and a_rcu Currently the two are unioned together, but I don't think that's safe. It looks like get_cached_acl could race with the last put in posix_acl_release. get_cached_acl calls atomic_inc_not_zero on a_refcount, but that field could have already been clobbered by call_rcu, and may no longer be zero. Fix this by de-unioning the two fields. Fixes: b8a7a3a66747 (posix_acl: Inode acl caching fixes) Signed-off-by: Jeff Layton Signed-off-by: Al Viro --- include/linux/posix_acl.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 5b5a80cc5926..c818772d9f9d 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -43,10 +43,8 @@ struct posix_acl_entry { }; struct posix_acl { - union { - atomic_t a_refcount; - struct rcu_head a_rcu; - }; + atomic_t a_refcount; + struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[0]; }; -- cgit v1.2.3 From 05f310e26fe9d97fec0ce1752edc16bf1ea55a2d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 12 Jul 2016 14:16:32 +0300 Subject: x86/sfi: Enable enumeration of SD devices SFI specification v0.8.2 defines type of devices which are connected to SD bus. In particularly WiFi dongle is a such. Add a callback to enumerate the devices connected to SD bus. Signed-off-by: Andy Shevchenko Cc: Bjorn Helgaas Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1468322192-62080-1-git-send-email-andriy.shevchenko@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/intel-mid.h | 15 +++++++++++++++ arch/x86/platform/intel-mid/sfi.c | 29 +++++++++++++++++++++++++++++ include/linux/sfi.h | 1 + 3 files changed, 45 insertions(+) (limited to 'include') diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 59013a2ac713..9d6b097aa73d 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -49,6 +49,21 @@ struct devs_id { static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \ __attribute__((__section__(".x86_intel_mid_dev.init"))) = &i +/** +* struct mid_sd_board_info - template for SD device creation +* @name: identifies the driver +* @bus_num: board-specific identifier for a given SD controller +* @max_clk: the maximum frequency device supports +* @platform_data: the particular data stored there is driver-specific +*/ +struct mid_sd_board_info { + char name[SFI_NAME_LEN]; + int bus_num; + unsigned short addr; + u32 max_clk; + void *platform_data; +}; + /* * Medfield is the follow-up of Moorestown, it combines two chip solution into * one. Other than that it also added always-on and constant tsc and lapic diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index 5ee360a951ce..1555672d436f 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -407,6 +407,32 @@ static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry, i2c_register_board_info(pentry->host_num, &i2c_info, 1); } +static void __init sfi_handle_sd_dev(struct sfi_device_table_entry *pentry, + struct devs_id *dev) +{ + struct mid_sd_board_info sd_info; + void *pdata; + + memset(&sd_info, 0, sizeof(sd_info)); + strncpy(sd_info.name, pentry->name, SFI_NAME_LEN); + sd_info.bus_num = pentry->host_num; + sd_info.max_clk = pentry->max_freq; + sd_info.addr = pentry->addr; + pr_debug("SD bus = %d, name = %16.16s, max_clk = %d, addr = 0x%x\n", + sd_info.bus_num, + sd_info.name, + sd_info.max_clk, + sd_info.addr); + pdata = intel_mid_sfi_get_pdata(dev, &sd_info); + if (IS_ERR(pdata)) + return; + + /* Nothing we can do with this for now */ + sd_info.platform_data = pdata; + + pr_debug("Successfully registered %16.16s", sd_info.name); +} + extern struct devs_id *const __x86_intel_mid_dev_start[], *const __x86_intel_mid_dev_end[]; @@ -490,6 +516,9 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) case SFI_DEV_TYPE_I2C: sfi_handle_i2c_dev(pentry, dev); break; + case SFI_DEV_TYPE_SD: + sfi_handle_sd_dev(pentry, dev); + break; case SFI_DEV_TYPE_UART: case SFI_DEV_TYPE_HSI: default: diff --git a/include/linux/sfi.h b/include/linux/sfi.h index d9b436f09925..e0e1597ef9e6 100644 --- a/include/linux/sfi.h +++ b/include/linux/sfi.h @@ -156,6 +156,7 @@ struct sfi_device_table_entry { #define SFI_DEV_TYPE_UART 2 #define SFI_DEV_TYPE_HSI 3 #define SFI_DEV_TYPE_IPC 4 +#define SFI_DEV_TYPE_SD 5 u8 host_num; /* attached to host 0, 1...*/ u16 addr; -- cgit v1.2.3 From f4979fcea7fd36d8e2f556abef86f80e0d5af1ba Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 12 Jul 2016 18:18:56 -0400 Subject: rose: limit sk_filter trim to payload Sockets can have a filter program attached that drops or trims incoming packets based on the filter program return value. Rose requires data packets to have at least ROSE_MIN_LEN bytes. It verifies this on arrival in rose_route_frame and unconditionally pulls the bytes in rose_recvmsg. The filter can trim packets to below this value in-between, causing pull to fail, leaving the partial header at the time of skb_copy_datagram_msg. Place a lower bound on the size to which sk_filter may trim packets by introducing sk_filter_trim_cap and call this for rose packets. Signed-off-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 6 +++++- net/core/filter.c | 10 +++++----- net/rose/rose_in.c | 3 ++- 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fc31ef1da2d..8f74f3d61894 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -467,7 +467,11 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) } #endif /* CONFIG_DEBUG_SET_MODULE_RONX */ -int sk_filter(struct sock *sk, struct sk_buff *skb); +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); +static inline int sk_filter(struct sock *sk, struct sk_buff *skb) +{ + return sk_filter_trim_cap(sk, skb, 1); +} struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); diff --git a/net/core/filter.c b/net/core/filter.c index c4b330c85c02..e759d90e8cef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -53,9 +53,10 @@ #include /** - * sk_filter - run a packet through a socket filter + * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter + * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -64,7 +65,7 @@ * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter(struct sock *sk, struct sk_buff *skb) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; @@ -85,14 +86,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); - - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } -EXPORT_SYMBOL(sk_filter); +EXPORT_SYMBOL(sk_filter_trim_cap); static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 79c4abcfa6b4..0a6394754e81 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -164,7 +164,8 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety rose_frames_acked(sk, nr); if (ns == rose->vr) { rose_start_idletimer(sk); - if (sock_queue_rcv_skb(sk, skb) == 0) { + if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 && + __sock_queue_rcv_skb(sk, skb) == 0) { rose->vr = (rose->vr + 1) % ROSE_MODULUS; queued = 1; } else { -- cgit v1.2.3 From 4f0c40d94461cfd23893a17335b2ab78ecb333c8 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 12 Jul 2016 18:18:57 -0400 Subject: dccp: limit sk_filter trim to payload Dccp verifies packet integrity, including length, at initial rcv in dccp_invalid_packet, later pulls headers in dccp_enqueue_skb. A call to sk_filter in-between can cause __skb_pull to wrap skb->len. skb_copy_datagram_msg interprets this as a negative value, so (correctly) fails with EFAULT. The negative length is reported in ioctl SIOCINQ or possibly in a DCCP_WARN in dccp_close. Introduce an sk_receive_skb variant that caps how small a filter program can trim packets, and call this in dccp with the header length. Excessively trimmed packets are now processed normally and queued for reception as 0B payloads. Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Signed-off-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/sock.h | 8 +++++++- net/core/sock.c | 7 ++++--- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- 4 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 649d2a8c17fc..ff5be7e8ddea 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1576,7 +1576,13 @@ static inline void sock_put(struct sock *sk) */ void sock_gen_put(struct sock *sk); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested); +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, + unsigned int trim_cap); +static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested) +{ + return __sk_receive_skb(sk, skb, nested, 1); +} static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { diff --git a/net/core/sock.c b/net/core/sock.c index b7f12639c26a..25dab8b60223 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -452,11 +452,12 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sock_queue_rcv_skb); -int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) +int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, + const int nested, unsigned int trim_cap) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb)) + if (sk_filter_trim_cap(sk, skb, trim_cap)) goto discard_and_relse; skb->dev = NULL; @@ -492,7 +493,7 @@ discard_and_relse: kfree_skb(skb); goto out; } -EXPORT_SYMBOL(sk_receive_skb); +EXPORT_SYMBOL(__sk_receive_skb); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 25dd25b47d41..345a3aeb8c7e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -868,7 +868,7 @@ lookup: goto discard_and_relse; nf_reset(skb); - return sk_receive_skb(sk, skb, 1); + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d176f4e66369..3ff137d9471d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -732,7 +732,7 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - return sk_receive_skb(sk, skb, 1) ? -1 : 0; + return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4) ? -1 : 0; no_dccp_socket: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) -- cgit v1.2.3 From 57430218317e5b280a80582a139b26029c25de6c Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 13 Jul 2016 16:50:01 +0200 Subject: sched/cputime: Count actually elapsed irq & softirq time Currently, if there was any irq or softirq time during 'ticks' jiffies, the entire period will be accounted as irq or softirq time. This is inaccurate if only a subset of the time was actually spent handling irqs, and could conceivably mis-count all of the ticks during a period as irq time, when there was some irq and some softirq time. This can actually happen when irqtime_account_process_tick is called from account_idle_ticks, which can pass a larger number of ticks down all at once. Fix this by changing irqtime_account_hi_update(), irqtime_account_si_update(), and steal_account_process_ticks() to work with cputime_t time units, and return the amount of time spent in each mode. Rename steal_account_process_ticks() to steal_account_process_time(), to reflect that time is now accounted in cputime_t, instead of ticks. Additionally, have irqtime_account_process_tick() take into account how much time was spent in each of steal, irq, and softirq time. The latter could help improve the accuracy of cputime accounting when returning from idle on a NO_HZ_IDLE CPU. Properly accounting how much time was spent in hardirq and softirq time will also allow the NO_HZ_FULL code to re-use these same functions for hardirq and softirq accounting. Signed-off-by: Rik van Riel [ Make nsecs_to_cputime64() actually return cputime64_t. ] Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1468421405-20056-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/asm-generic/cputime_nsecs.h | 2 + kernel/sched/cputime.c | 124 ++++++++++++++++++++++-------------- 2 files changed, 79 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h index 0f1c6f315cdc..a84e28e0c634 100644 --- a/include/asm-generic/cputime_nsecs.h +++ b/include/asm-generic/cputime_nsecs.h @@ -50,6 +50,8 @@ typedef u64 __nocast cputime64_t; (__force u64)(__ct) #define nsecs_to_cputime(__nsecs) \ (__force cputime_t)(__nsecs) +#define nsecs_to_cputime64(__nsecs) \ + (__force cputime64_t)(__nsecs) /* diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 3d60e5d76fdb..db82ae12cf01 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -79,40 +79,50 @@ void irqtime_account_irq(struct task_struct *curr) } EXPORT_SYMBOL_GPL(irqtime_account_irq); -static int irqtime_account_hi_update(void) +static cputime_t irqtime_account_hi_update(cputime_t maxtime) { u64 *cpustat = kcpustat_this_cpu->cpustat; unsigned long flags; - u64 latest_ns; - int ret = 0; + cputime_t irq_cputime; local_irq_save(flags); - latest_ns = this_cpu_read(cpu_hardirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) - ret = 1; + irq_cputime = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time)) - + cpustat[CPUTIME_IRQ]; + irq_cputime = min(irq_cputime, maxtime); + cpustat[CPUTIME_IRQ] += irq_cputime; local_irq_restore(flags); - return ret; + return irq_cputime; } -static int irqtime_account_si_update(void) +static cputime_t irqtime_account_si_update(cputime_t maxtime) { u64 *cpustat = kcpustat_this_cpu->cpustat; unsigned long flags; - u64 latest_ns; - int ret = 0; + cputime_t softirq_cputime; local_irq_save(flags); - latest_ns = this_cpu_read(cpu_softirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) - ret = 1; + softirq_cputime = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time)) - + cpustat[CPUTIME_SOFTIRQ]; + softirq_cputime = min(softirq_cputime, maxtime); + cpustat[CPUTIME_SOFTIRQ] += softirq_cputime; local_irq_restore(flags); - return ret; + return softirq_cputime; } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ #define sched_clock_irqtime (0) +static cputime_t irqtime_account_hi_update(cputime_t dummy) +{ + return 0; +} + +static cputime_t irqtime_account_si_update(cputime_t dummy) +{ + return 0; +} + #endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ static inline void task_group_account_field(struct task_struct *p, int index, @@ -257,31 +267,44 @@ void account_idle_time(cputime_t cputime) cpustat[CPUTIME_IDLE] += (__force u64) cputime; } -static __always_inline unsigned long steal_account_process_tick(unsigned long max_jiffies) +static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) { #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { + cputime_t steal_cputime; u64 steal; - unsigned long steal_jiffies; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; - /* - * steal is in nsecs but our caller is expecting steal - * time in jiffies. Lets cast the result to jiffies - * granularity and account the rest on the next rounds. - */ - steal_jiffies = min(nsecs_to_jiffies(steal), max_jiffies); - this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies); + steal_cputime = min(nsecs_to_cputime(steal), maxtime); + account_steal_time(steal_cputime); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime); - account_steal_time(jiffies_to_cputime(steal_jiffies)); - return steal_jiffies; + return steal_cputime; } #endif return 0; } +/* + * Account how much elapsed time was spent in steal, irq, or softirq time. + */ +static inline cputime_t account_other_time(cputime_t max) +{ + cputime_t accounted; + + accounted = steal_account_process_time(max); + + if (accounted < max) + accounted += irqtime_account_hi_update(max - accounted); + + if (accounted < max) + accounted += irqtime_account_si_update(max - accounted); + + return accounted; +} + /* * Accumulate raw cputime values of dead tasks (sig->[us]time) and live * tasks (sum on group iteration) belonging to @tsk's group. @@ -342,21 +365,23 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) static void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq, int ticks) { - cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); - u64 cputime = (__force u64) cputime_one_jiffy; - u64 *cpustat = kcpustat_this_cpu->cpustat; + u64 cputime = (__force u64) cputime_one_jiffy * ticks; + cputime_t scaled, other; - if (steal_account_process_tick(ULONG_MAX)) + /* + * When returning from idle, many ticks can get accounted at + * once, including some ticks of steal, irq, and softirq time. + * Subtract those ticks from the amount of time accounted to + * idle, or potentially user or system time. Due to rounding, + * other time can exceed ticks occasionally. + */ + other = account_other_time(cputime); + if (other >= cputime) return; + cputime -= other; + scaled = cputime_to_scaled(cputime); - cputime *= ticks; - scaled *= ticks; - - if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += cputime; - } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += cputime; - } else if (this_cpu_ksoftirqd() == p) { + if (this_cpu_ksoftirqd() == p) { /* * ksoftirqd time do not get accounted in cpu_softirq_time. * So, we have to handle it separately here. @@ -466,7 +491,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime */ void account_process_tick(struct task_struct *p, int user_tick) { - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime_t cputime, scaled, steal; struct rq *rq = this_rq(); if (vtime_accounting_cpu_enabled()) @@ -477,16 +502,21 @@ void account_process_tick(struct task_struct *p, int user_tick) return; } - if (steal_account_process_tick(ULONG_MAX)) + cputime = cputime_one_jiffy; + steal = steal_account_process_time(cputime); + + if (steal >= cputime) return; + cputime -= steal; + scaled = cputime_to_scaled(cputime); + if (user_tick) - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime, scaled); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, - one_jiffy_scaled); + account_system_time(p, HARDIRQ_OFFSET, cputime, scaled); else - account_idle_time(cputime_one_jiffy); + account_idle_time(cputime); } /* @@ -681,14 +711,14 @@ static cputime_t vtime_delta(struct task_struct *tsk) static cputime_t get_vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); - unsigned long delta_jiffies, steal_jiffies; + cputime_t delta, steal; - delta_jiffies = now - tsk->vtime_snap; - steal_jiffies = steal_account_process_tick(delta_jiffies); + delta = jiffies_to_cputime(now - tsk->vtime_snap); + steal = steal_account_process_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap = now; - return jiffies_to_cputime(delta_jiffies - steal_jiffies); + return delta - steal; } static void __vtime_account_system(struct task_struct *tsk) -- cgit v1.2.3 From b58c35840521bb02b150e1d0d34ca9197f8b7145 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 13 Jul 2016 16:50:02 +0200 Subject: sched/cputime: Replace VTIME_GEN irq time code with IRQ_TIME_ACCOUNTING code The CONFIG_VIRT_CPU_ACCOUNTING_GEN irq time tracking code does not appear to currently work right. On CPUs without nohz_full=, only tick based irq time sampling is done, which breaks down when dealing with a nohz_idle CPU. On firewalls and similar systems, no ticks may happen on a CPU for a while, and the irq time spent may never get accounted properly. This can cause issues with capacity planning and power saving, which use the CPU statistics as inputs in decision making. Remove the VTIME_GEN vtime irq time code, and replace it with the IRQ_TIME_ACCOUNTING code, when selected as a config option by the user. Signed-off-by: Rik van Riel Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1468421405-20056-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 32 ++++++++++++++------------------ init/Kconfig | 6 +++--- kernel/sched/cputime.c | 16 +++------------- 3 files changed, 20 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index fa2196990f84..d1977d84ebdf 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -14,6 +14,18 @@ struct task_struct; */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline bool vtime_accounting_cpu_enabled(void) { return true; } + +#ifdef __ARCH_HAS_VTIME_ACCOUNT +extern void vtime_account_irq_enter(struct task_struct *tsk); +#else +extern void vtime_common_account_irq_enter(struct task_struct *tsk); +static inline void vtime_account_irq_enter(struct task_struct *tsk) +{ + if (vtime_accounting_cpu_enabled()) + vtime_common_account_irq_enter(tsk); +} +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ + #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -64,17 +76,6 @@ extern void vtime_account_system(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); extern void vtime_account_user(struct task_struct *tsk); -#ifdef __ARCH_HAS_VTIME_ACCOUNT -extern void vtime_account_irq_enter(struct task_struct *tsk); -#else -extern void vtime_common_account_irq_enter(struct task_struct *tsk); -static inline void vtime_account_irq_enter(struct task_struct *tsk) -{ - if (vtime_accounting_cpu_enabled()) - vtime_common_account_irq_enter(tsk); -} -#endif /* __ARCH_HAS_VTIME_ACCOUNT */ - #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline void vtime_task_switch(struct task_struct *prev) { } @@ -85,13 +86,8 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -extern void vtime_gen_account_irq_exit(struct task_struct *tsk); - -static inline void vtime_account_irq_exit(struct task_struct *tsk) -{ - if (vtime_accounting_cpu_enabled()) - vtime_gen_account_irq_exit(tsk); -} +static inline void vtime_account_irq_enter(struct task_struct *tsk) { } +static inline void vtime_account_irq_exit(struct task_struct *tsk) { } extern void vtime_user_enter(struct task_struct *tsk); diff --git a/init/Kconfig b/init/Kconfig index c02d89777713..787dd76acf29 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -375,9 +375,11 @@ config VIRT_CPU_ACCOUNTING_GEN If unsure, say N. +endchoice + config IRQ_TIME_ACCOUNTING bool "Fine granularity task level IRQ time accounting" - depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL + depends on HAVE_IRQ_TIME_ACCOUNTING && !VIRT_CPU_ACCOUNTING_NATIVE help Select this option to enable fine granularity task irq time accounting. This is done by reading a timestamp on each @@ -386,8 +388,6 @@ config IRQ_TIME_ACCOUNTING If in doubt, say N here. -endchoice - config BSD_PROCESS_ACCT bool "BSD Process Accounting" depends on MULTIUSER diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index db82ae12cf01..ca7e33cb0967 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -711,14 +711,14 @@ static cputime_t vtime_delta(struct task_struct *tsk) static cputime_t get_vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); - cputime_t delta, steal; + cputime_t delta, other; delta = jiffies_to_cputime(now - tsk->vtime_snap); - steal = steal_account_process_time(delta); + other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap = now; - return delta - steal; + return delta - other; } static void __vtime_account_system(struct task_struct *tsk) @@ -738,16 +738,6 @@ void vtime_account_system(struct task_struct *tsk) write_seqcount_end(&tsk->vtime_seqcount); } -void vtime_gen_account_irq_exit(struct task_struct *tsk) -{ - write_seqcount_begin(&tsk->vtime_seqcount); - if (vtime_delta(tsk)) - __vtime_account_system(tsk); - if (context_tracking_in_user()) - tsk->vtime_snap_whence = VTIME_USER; - write_seqcount_end(&tsk->vtime_seqcount); -} - void vtime_account_user(struct task_struct *tsk) { cputime_t delta_cpu; -- cgit v1.2.3 From 0cfdf9a198b0d4f5ad6c87d894db7830b796b2cc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 13 Jul 2016 16:50:03 +0200 Subject: sched/cputime: Clean up the old vtime gen irqtime accounting completely Vtime generic irqtime accounting has been removed but there are a few remnants to clean up: * The vtime_accounting_cpu_enabled() check in irq entry was only used by CONFIG_VIRT_CPU_ACCOUNTING_GEN. We can safely remove it. * Without the vtime_accounting_cpu_enabled(), we no longer need to have a vtime_common_account_irq_enter() indirect function. * Move vtime_account_irq_enter() implementation under CONFIG_VIRT_CPU_ACCOUNTING_NATIVE which is the last user. * The vtime_account_user() call was only used on irq entry for CONFIG_VIRT_CPU_ACCOUNTING_GEN. We can remove that too. Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1468421405-20056-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 11 ----------- kernel/sched/cputime.c | 33 ++++++++++----------------------- 2 files changed, 10 insertions(+), 34 deletions(-) (limited to 'include') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index d1977d84ebdf..65aef5e9d04e 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -14,18 +14,7 @@ struct task_struct; */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline bool vtime_accounting_cpu_enabled(void) { return true; } - -#ifdef __ARCH_HAS_VTIME_ACCOUNT extern void vtime_account_irq_enter(struct task_struct *tsk); -#else -extern void vtime_common_account_irq_enter(struct task_struct *tsk); -static inline void vtime_account_irq_enter(struct task_struct *tsk) -{ - if (vtime_accounting_cpu_enabled()) - vtime_common_account_irq_enter(tsk); -} -#endif /* __ARCH_HAS_VTIME_ACCOUNT */ - #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ca7e33cb0967..16a873c203b1 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -431,6 +431,10 @@ void vtime_common_task_switch(struct task_struct *prev) } #endif +#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ + + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE /* * Archs that account the whole time spent in the idle task * (outside irq) as idle time can rely on this and just implement @@ -440,33 +444,16 @@ void vtime_common_task_switch(struct task_struct *prev) * vtime_account(). */ #ifndef __ARCH_HAS_VTIME_ACCOUNT -void vtime_common_account_irq_enter(struct task_struct *tsk) +void vtime_account_irq_enter(struct task_struct *tsk) { - if (!in_interrupt()) { - /* - * If we interrupted user, context_tracking_in_user() - * is 1 because the context tracking don't hook - * on irq entry/exit. This way we know if - * we need to flush user time on kernel entry. - */ - if (context_tracking_in_user()) { - vtime_account_user(tsk); - return; - } - - if (is_idle_task(tsk)) { - vtime_account_idle(tsk); - return; - } - } - vtime_account_system(tsk); + if (!in_interrupt() && is_idle_task(tsk)) + vtime_account_idle(tsk); + else + vtime_account_system(tsk); } -EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter); +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ -#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { *ut = p->utime; -- cgit v1.2.3 From 8612f17ab99c1f0770792bc875f5f039212a2a85 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 13 Jul 2016 16:50:04 +0200 Subject: sched/cputime: Reorganize vtime native irqtime accounting headers The vtime irqtime accounting headers are very scattered and convoluted right now. Reorganize them such that it is obvious that only CONFIG_VIRT_CPU_ACCOUNTING_NATIVE does use it. Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Rik van Riel Cc: Thomas Gleixner Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1468421405-20056-5-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 35 +++++++++++++++++------------------ 1 file changed, 17 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 65aef5e9d04e..aa9bfea8804a 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -12,12 +12,9 @@ struct task_struct; /* * vtime_accounting_cpu_enabled() definitions/declarations */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) static inline bool vtime_accounting_cpu_enabled(void) { return true; } -extern void vtime_account_irq_enter(struct task_struct *tsk); -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +#elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. @@ -38,11 +35,9 @@ static inline bool vtime_accounting_cpu_enabled(void) return false; } -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING +#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline bool vtime_accounting_cpu_enabled(void) { return false; } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* @@ -70,14 +65,10 @@ extern void vtime_account_user(struct task_struct *tsk); static inline void vtime_task_switch(struct task_struct *prev) { } static inline void vtime_account_system(struct task_struct *tsk) { } static inline void vtime_account_user(struct task_struct *tsk) { } -static inline void vtime_account_irq_enter(struct task_struct *tsk) { } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void arch_vtime_task_switch(struct task_struct *tsk); -static inline void vtime_account_irq_enter(struct task_struct *tsk) { } -static inline void vtime_account_irq_exit(struct task_struct *tsk) { } - extern void vtime_user_enter(struct task_struct *tsk); static inline void vtime_user_exit(struct task_struct *tsk) @@ -88,11 +79,6 @@ extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ -static inline void vtime_account_irq_exit(struct task_struct *tsk) -{ - /* On hard|softirq exit we always account to hard|softirq cputime */ - vtime_account_system(tsk); -} static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } @@ -100,6 +86,19 @@ static inline void vtime_guest_exit(struct task_struct *tsk) { } static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +extern void vtime_account_irq_enter(struct task_struct *tsk); +static inline void vtime_account_irq_exit(struct task_struct *tsk) +{ + /* On hard|softirq exit we always account to hard|softirq cputime */ + vtime_account_system(tsk); +} +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ +static inline void vtime_account_irq_enter(struct task_struct *tsk) { } +static inline void vtime_account_irq_exit(struct task_struct *tsk) { } +#endif + + #ifdef CONFIG_IRQ_TIME_ACCOUNTING extern void irqtime_account_irq(struct task_struct *tsk); #else -- cgit v1.2.3 From 12cb22bb8ae9aff9d72a9c0a234f26d641b20eb6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 14 Jul 2016 12:07:15 -0700 Subject: uapi: export lirc.h header This header contains the userspace API for lirc. This is a fixup for commit b7be755733dc ("[media] bz#75751: Move internal header file lirc.h to uapi/"). It moved the header to the right place, but it forgot to add it at Kbuild. So, despite being at uapi, it is not copied to the right place. Fixes: b7be755733dc44c72 ("[media] bz#75751: Move internal header file lirc.h to uapi/") Link: http://lkml.kernel.org/r/320c765d32bfc82c582e336d52ffe1026c73c644.1468439021.git.mchehab@s-opensource.com Signed-off-by: Mauro Carvalho Chehab Cc: Alec Leamas Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 8bdae34d1f9a..ec10cfef166a 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -245,6 +245,7 @@ endif header-y += hw_breakpoint.h header-y += l2tp.h header-y += libc-compat.h +header-y += lirc.h header-y += limits.h header-y += llc.h header-y += loop.h -- cgit v1.2.3 From e41f501d391265ff568f3e49d6128cc30856a36f Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Thu, 14 Jul 2016 12:07:29 -0700 Subject: vmlinux.lds: account for destructor sections If CONFIG_KASAN is enabled and gcc is configured with --disable-initfini-array and/or gold linker is used, gcc emits .ctors/.dtors and .text.startup/.text.exit sections instead of .init_array/.fini_array. .dtors section is not explicitly accounted in the linker script and messes vvar/percpu layout. We want: ffffffff822bfd80 D _edata ffffffff822c0000 D __vvar_beginning_hack ffffffff822c0000 A __vvar_page ffffffff822c0080 0000000000000098 D vsyscall_gtod_data ffffffff822c1000 A __init_begin ffffffff822c1000 D init_per_cpu__irq_stack_union ffffffff822c1000 A __per_cpu_load ffffffff822d3000 D init_per_cpu__gdt_page We got: ffffffff8279a600 D _edata ffffffff8279b000 A __vvar_page ffffffff8279c000 A __init_begin ffffffff8279c000 D init_per_cpu__irq_stack_union ffffffff8279c000 A __per_cpu_load ffffffff8279e000 D __vvar_beginning_hack ffffffff8279e080 0000000000000098 D vsyscall_gtod_data ffffffff827ae000 D init_per_cpu__gdt_page This happens because __vvar_page and .vvar get different addresses in arch/x86/kernel/vmlinux.lds.S: . = ALIGN(PAGE_SIZE); __vvar_page = .; .vvar : AT(ADDR(.vvar) - LOAD_OFFSET) { /* work around gold bug 13023 */ __vvar_beginning_hack = .; Discard .dtors/.fini_array/.text.exit, since we don't call dtors. Merge .text.startup into init text. Link: http://lkml.kernel.org/r/1467386363-120030-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov Reviewed-by: Andrey Ryabinin Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab94b553..081d0f258d4c 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -542,15 +542,19 @@ #define INIT_TEXT \ *(.init.text) \ + *(.text.startup) \ MEM_DISCARD(init.text) #define EXIT_DATA \ *(.exit.data) \ + *(.fini_array) \ + *(.dtors) \ MEM_DISCARD(exit.data) \ MEM_DISCARD(exit.rodata) #define EXIT_TEXT \ *(.exit.text) \ + *(.text.exit) \ MEM_DISCARD(exit.text) #define EXIT_CALL \ -- cgit v1.2.3 From 33f4751e99601b7bfd1d66aedabd3ee9140922de Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 14 Jul 2016 12:07:32 -0700 Subject: mm: thp: move pmd check inside ptl for freeze_page() I found a race condition triggering VM_BUG_ON() in freeze_page(), when running a testcase with 3 processes: - process 1: keep writing thp, - process 2: keep clearing soft-dirty bits from virtual address of process 1 - process 3: call migratepages for process 1, The kernel message is like this: kernel BUG at /src/linux-dev/mm/huge_memory.c:3096! invalid opcode: 0000 [#1] SMP Modules linked in: cfg80211 rfkill crc32c_intel ppdev serio_raw pcspkr virtio_balloon virtio_console parport_pc parport pvpanic acpi_cpufreq tpm_tis tpm i2c_piix4 virtio_blk virtio_net ata_generic pata_acpi floppy virtio_pci virtio_ring virtio CPU: 0 PID: 28863 Comm: migratepages Not tainted 4.6.0-v4.6-160602-0827-+ #2 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff880037320000 ti: ffff88007cdd0000 task.ti: ffff88007cdd0000 RIP: 0010:[] [] split_huge_page_to_list+0x496/0x590 RSP: 0018:ffff88007cdd3b70 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffff88007c7b88c0 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000700000200 RDI: ffffea0003188000 RBP: ffff88007cdd3bb8 R08: 0000000000000001 R09: 00003ffffffff000 R10: ffff880000000000 R11: ffffc000001fffff R12: ffffea0003188000 R13: ffffea0003188000 R14: 0000000000000000 R15: 0400000000000080 FS: 00007f8ec241d740(0000) GS:ffff88007dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f8ec1f3ed20 CR3: 000000003707b000 CR4: 00000000000006f0 Call Trace: ? list_del+0xd/0x30 queue_pages_pte_range+0x4d1/0x590 __walk_page_range+0x204/0x4e0 walk_page_range+0x71/0xf0 queue_pages_range+0x75/0x90 ? queue_pages_hugetlb+0x190/0x190 ? new_node_page+0xc0/0xc0 ? change_prot_numa+0x40/0x40 migrate_to_node+0x71/0xd0 do_migrate_pages+0x1c3/0x210 SyS_migrate_pages+0x261/0x290 entry_SYSCALL_64_fastpath+0x1a/0xa4 Code: e8 b0 87 fb ff 0f 0b 48 c7 c6 30 32 9f 81 e8 a2 87 fb ff 0f 0b 48 c7 c6 b8 46 9f 81 e8 94 87 fb ff 0f 0b 85 c0 0f 84 3e fd ff ff <0f> 0b 85 c0 0f 85 a6 00 00 00 48 8b 75 c0 4c 89 f7 41 be f0 ff RIP split_huge_page_to_list+0x496/0x590 I'm not sure of the full scenario of the reproduction, but my debug showed that split_huge_pmd_address(freeze=true) returned without running main code of pmd splitting because pmd_present(*pmd) in precheck somehow returned 0. If this happens, the subsequent try_to_unmap() fails and returns non-zero (because page_mapcount() still > 0), and finally VM_BUG_ON() fires. This patch tries to fix it by prechecking pmd state inside ptl. Link: http://lkml.kernel.org/r/1466990929-7452-1-git-send-email-n-horiguchi@ah.jp.nec.com Signed-off-by: Naoya Horiguchi Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 4 ++-- mm/huge_memory.c | 31 ++++++++++++------------------- 2 files changed, 14 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 419fb9e03447..f0a7a0320300 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -94,7 +94,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze); + unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -102,7 +102,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ - false); \ + false, NULL); \ } while (0) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 55940d173318..343a2b7e57aa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2984,7 +2984,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze) + unsigned long address, bool freeze, struct page *page) { spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; @@ -2992,8 +2992,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); + + /* + * If caller asks to setup a migration entries, we need a page to check + * pmd against. Otherwise we can end up replacing wrong page. + */ + VM_BUG_ON(freeze && !page); + if (page && page != pmd_page(*pmd)) + goto out; + if (pmd_trans_huge(*pmd)) { - struct page *page = pmd_page(*pmd); + page = pmd_page(*pmd); if (PageMlocked(page)) clear_page_mlock(page); } else if (!pmd_devmap(*pmd)) @@ -3020,24 +3029,8 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) - return; - /* - * If caller asks to setup a migration entries, we need a page to check - * pmd against. Otherwise we can end up replacing wrong page. - */ - VM_BUG_ON(freeze && !page); - if (page && page != pmd_page(*pmd)) - return; - - /* - * Caller holds the mmap_sem write mode or the anon_vma lock, - * so a huge pmd cannot materialize from under us (khugepaged - * holds both the mmap_sem write mode and the anon_vma lock - * write mode). - */ - __split_huge_pmd(vma, pmd, address, freeze); + __split_huge_pmd(vma, pmd, address, freeze, page); } void vma_adjust_trans_huge(struct vm_area_struct *vma, -- cgit v1.2.3 From 5a49973d7143ebbabd76e1dcd69ee42e349bb7b9 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 14 Jul 2016 12:07:38 -0700 Subject: mm: thp: refix false positive BUG in page_move_anon_rmap() The VM_BUG_ON_PAGE in page_move_anon_rmap() is more trouble than it's worth: the syzkaller fuzzer hit it again. It's still wrong for some THP cases, because linear_page_index() was never intended to apply to addresses before the start of a vma. That's easily fixed with a signed long cast inside linear_page_index(); and Dmitry has tested such a patch, to verify the false positive. But why extend linear_page_index() just for this case? when the avoidance in page_move_anon_rmap() has already grown ugly, and there's no reason for the check at all (nothing else there is using address or index). Remove address arg from page_move_anon_rmap(), remove VM_BUG_ON_PAGE, remove CONFIG_DEBUG_VM PageTransHuge adjustment. And one more thing: should the compound_head(page) be done inside or outside page_move_anon_rmap()? It's usually pushed down to the lowest level nowadays (and mm/memory.c shows no other explicit use of it), so I think it's better done in page_move_anon_rmap() than by caller. Fixes: 0798d3c022dc ("mm: thp: avoid false positive VM_BUG_ON_PAGE in page_move_anon_rmap()") Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1607120444540.12528@eggly.anvils Signed-off-by: Hugh Dickins Reported-by: Dmitry Vyukov Acked-by: Kirill A. Shutemov Cc: Mika Westerberg Cc: Andrea Arcangeli Cc: Rik van Riel Cc: [4.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 2 +- mm/hugetlb.c | 2 +- mm/memory.c | 3 +-- mm/rmap.c | 9 +++------ 4 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 49eb4f8ebac9..2b0fad83683f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -158,7 +158,7 @@ struct anon_vma *page_get_anon_vma(struct page *page); /* * rmap interfaces called when adding or removing pte of page */ -void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c1f3c0be150a..addfe4accc07 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3383,7 +3383,7 @@ retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma, address); + page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, address, ptep); return 0; } diff --git a/mm/memory.c b/mm/memory.c index cd1f29e4897e..9e046819e619 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2399,8 +2399,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, * Protected against the rmap code by * the page lock. */ - page_move_anon_rmap(compound_head(old_page), - vma, address); + page_move_anon_rmap(old_page, vma); } unlock_page(old_page); return wp_page_reuse(mm, vma, address, page_table, ptl, diff --git a/mm/rmap.c b/mm/rmap.c index e4b713a6ed7e..701b93fea2a0 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1084,23 +1084,20 @@ EXPORT_SYMBOL_GPL(page_mkclean); * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to - * @address: the user virtual address mapped * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ -void page_move_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + page = compound_head(page); + VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); - if (IS_ENABLED(CONFIG_DEBUG_VM) && PageTransHuge(page)) - address &= HPAGE_PMD_MASK; - VM_BUG_ON_PAGE(page->index != linear_page_index(vma, address), page); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* -- cgit v1.2.3 From 18d3df3eab23796d7f852f9c6bb60962b8372ced Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 14 Jul 2016 18:00:10 +0200 Subject: vlan: use a valid default mtu value for vlan over macsec macsec can't cope with mtu frames which need vlan tag insertion, and vlan device set the default mtu equal to the underlying dev's one. By default vlan over macsec devices use invalid mtu, dropping all the large packets. This patch adds a netif helper to check if an upper vlan device needs mtu reduction. The helper is used during vlan devices initialization to set a valid default and during mtu updating to forbid invalid, too bit, mtu values. The helper currently only check if the lower dev is a macsec device, if we get more users, we need to update only the helper (possibly reserving an additional IFF bit). Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ net/8021q/vlan_dev.c | 10 ++++++---- net/8021q/vlan_netlink.c | 7 +++++-- 3 files changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f45929ce8157..da4b33bea982 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4145,6 +4145,13 @@ static inline void netif_keep_dst(struct net_device *dev) dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } +/* return true if dev can't cope with mtu frames that need vlan tag insertion */ +static inline bool netif_reduces_vlan_mtu(struct net_device *dev) +{ + /* TODO: reserve and use an additional IFF bit, if we get more users */ + return dev->priv_flags & IFF_MACSEC; +} + extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 86ae75b77390..516b0e73263c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -146,10 +146,12 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu) { - /* TODO: gotta make sure the underlying layer can handle it, - * maybe an IFF_VLAN_CAPABLE flag for devices? - */ - if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu) + struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + unsigned int max_mtu = real_dev->mtu; + + if (netif_reduces_vlan_mtu(real_dev)) + max_mtu -= VLAN_HLEN; + if (max_mtu < new_mtu) return -ERANGE; dev->mtu = new_mtu; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c92b52f37d38..1270207f3d7c 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,6 +118,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; + unsigned int max_mtu; __be16 proto; int err; @@ -144,9 +145,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; + max_mtu = netif_reduces_vlan_mtu(real_dev) ? real_dev->mtu - VLAN_HLEN : + real_dev->mtu; if (!tb[IFLA_MTU]) - dev->mtu = real_dev->mtu; - else if (dev->mtu > real_dev->mtu) + dev->mtu = max_mtu; + else if (dev->mtu > max_mtu) return -EINVAL; err = vlan_changelink(dev, tb, data); -- cgit v1.2.3 From eabfdda93477f6ee5e153f560560e9cb1c617fd7 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 18 Jul 2016 15:02:06 -0400 Subject: net: switchdev: change ageing_time type to clock_t The switchdev value for the SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME attribute is a clock_t and requires to use helpers such as clock_t_to_jiffies() to convert to milliseconds. Change ageing_time type from u32 to clock_t to make it explicit. Fixes: f55ac58ae64c ("switchdev: add bridge ageing_time attribute") Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 985619a59323..1d8e158241da 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -60,7 +60,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ - u32 ageing_time; /* BRIDGE_AGEING_TIME */ + clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ } u; }; -- cgit v1.2.3 From 73f576c04b9410ed19660f74f97521bee6e1c546 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 20 Jul 2016 15:44:57 -0700 Subject: mm: memcontrol: fix cgroup creation failure after many small jobs The memory controller has quite a bit of state that usually outlives the cgroup and pins its CSS until said state disappears. At the same time it imposes a 16-bit limit on the CSS ID space to economically store IDs in the wild. Consequently, when we use cgroups to contain frequent but small and short-lived jobs that leave behind some page cache, we quickly run into the 64k limitations of outstanding CSSs. Creating a new cgroup fails with -ENOSPC while there are only a few, or even no user-visible cgroups in existence. Although pinning CSSs past cgroup removal is common, there are only two instances that actually need an ID after a cgroup is deleted: cache shadow entries and swapout records. Cache shadow entries reference the ID weakly and can deal with the CSS having disappeared when it's looked up later. They pose no hurdle. Swap-out records do need to pin the css to hierarchically attribute swapins after the cgroup has been deleted; though the only pages that remain swapped out after offlining are tmpfs/shmem pages. And those references are under the user's control, so they are manageable. This patch introduces a private 16-bit memcg ID and switches swap and cache shadow entries over to using that. This ID can then be recycled after offlining when the CSS remains pinned only by objects that don't specifically need it. This script demonstrates the problem by faulting one cache page in a new cgroup and deleting it again: set -e mkdir -p pages for x in `seq 128000`; do [ $((x % 1000)) -eq 0 ] && echo $x mkdir /cgroup/foo echo $$ >/cgroup/foo/cgroup.procs echo trex >pages/$x echo $$ >/cgroup/cgroup.procs rmdir /cgroup/foo done When run on an unpatched kernel, we eventually run out of possible IDs even though there are no visible cgroups: [root@ham ~]# ./cssidstress.sh [...] 65000 mkdir: cannot create directory '/cgroup/foo': No space left on device After this patch, the IDs get released upon cgroup destruction and the cache and css objects get released once memory reclaim kicks in. [hannes@cmpxchg.org: init the IDR] Link: http://lkml.kernel.org/r/20160621154601.GA22431@cmpxchg.org Fixes: b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined groups") Link: http://lkml.kernel.org/r/20160617162516.GD19084@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: John Garcia Reviewed-by: Vladimir Davydov Acked-by: Tejun Heo Cc: Nikolay Borisov Cc: [3.19+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 25 ++++++-------- mm/memcontrol.c | 82 ++++++++++++++++++++++++++++++++++++++++++---- mm/slab_common.c | 4 +-- 3 files changed, 87 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a805474df4ab..56e6069d2452 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,11 @@ enum mem_cgroup_events_target { #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX +struct mem_cgroup_id { + int id; + atomic_t ref; +}; + struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; unsigned long events[MEMCG_NR_EVENTS]; @@ -172,6 +177,9 @@ enum memcg_kmem_state { struct mem_cgroup { struct cgroup_subsys_state css; + /* Private memcg ID. Used to ID objects that outlive the cgroup */ + struct mem_cgroup_id id; + /* Accounted resources */ struct page_counter memory; struct page_counter swap; @@ -330,22 +338,9 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) if (mem_cgroup_disabled()) return 0; - return memcg->css.id; -} - -/** - * mem_cgroup_from_id - look up a memcg from an id - * @id: the id to look up - * - * Caller must hold rcu_read_lock() and use css_tryget() as necessary. - */ -static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) -{ - struct cgroup_subsys_state *css; - - css = css_from_id(id, &memory_cgrp_subsys); - return mem_cgroup_from_css(css); + return memcg->id.id; } +struct mem_cgroup *mem_cgroup_from_id(unsigned short id); /** * parent_mem_cgroup - find the accounting parent of a memcg diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac8664db3823..5339c89dff63 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4057,6 +4057,60 @@ static struct cftype mem_cgroup_legacy_files[] = { { }, /* terminate */ }; +/* + * Private memory cgroup IDR + * + * Swap-out records and page cache shadow entries need to store memcg + * references in constrained space, so we maintain an ID space that is + * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of + * memory-controlled cgroups to 64k. + * + * However, there usually are many references to the oflline CSS after + * the cgroup has been destroyed, such as page cache or reclaimable + * slab objects, that don't need to hang on to the ID. We want to keep + * those dead CSS from occupying IDs, or we might quickly exhaust the + * relatively small ID space and prevent the creation of new cgroups + * even when there are much fewer than 64k cgroups - possibly none. + * + * Maintain a private 16-bit ID space for memcg, and allow the ID to + * be freed and recycled when it's no longer needed, which is usually + * when the CSS is offlined. + * + * The only exception to that are records of swapped out tmpfs/shmem + * pages that need to be attributed to live ancestors on swapin. But + * those references are manageable from userspace. + */ + +static DEFINE_IDR(mem_cgroup_idr); + +static void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + atomic_inc(&memcg->id.ref); +} + +static void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + if (atomic_dec_and_test(&memcg->id.ref)) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + + /* Memcg ID pins CSS */ + css_put(&memcg->css); + } +} + +/** + * mem_cgroup_from_id - look up a memcg from a memcg id + * @id: the memcg id to look up + * + * Caller must hold rcu_read_lock(). + */ +struct mem_cgroup *mem_cgroup_from_id(unsigned short id) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return idr_find(&mem_cgroup_idr, id); +} + static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -4116,6 +4170,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (!memcg) return NULL; + memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, + 1, MEM_CGROUP_ID_MAX, + GFP_KERNEL); + if (memcg->id.id < 0) + goto fail; + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); if (!memcg->stat) goto fail; @@ -4142,8 +4202,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void) #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif + idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: + if (memcg->id.id > 0) + idr_remove(&mem_cgroup_idr, memcg->id.id); mem_cgroup_free(memcg); return NULL; } @@ -4206,12 +4269,11 @@ fail: return ERR_PTR(-ENOMEM); } -static int -mem_cgroup_css_online(struct cgroup_subsys_state *css) +static int mem_cgroup_css_online(struct cgroup_subsys_state *css) { - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; - + /* Online state pins memcg ID, memcg ID pins CSS */ + mem_cgroup_id_get(mem_cgroup_from_css(css)); + css_get(css); return 0; } @@ -4234,6 +4296,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + + mem_cgroup_id_put(memcg); } static void mem_cgroup_css_released(struct cgroup_subsys_state *css) @@ -5756,6 +5820,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); @@ -5774,6 +5839,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put(&memcg->css); } /* @@ -5804,11 +5872,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) !page_counter_try_charge(&memcg->swap, 1, &counter)) return -ENOMEM; + mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); - css_get(&memcg->css); return 0; } @@ -5837,7 +5905,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry) page_counter_uncharge(&memcg->memsw, 1); } mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + mem_cgroup_id_put(memcg); } rcu_read_unlock(); } diff --git a/mm/slab_common.c b/mm/slab_common.c index a65dad7fdcd1..82317abb03ed 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -526,8 +526,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, goto out_unlock; cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); - cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - css->id, memcg_name_buf); + cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, + css->serial_nr, memcg_name_buf); if (!cache_name) goto out_unlock; -- cgit v1.2.3 From 3cb9185c67304b2a7ea9be73e7d13df6fb2793a1 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Wed, 20 Jul 2016 15:45:00 -0700 Subject: radix-tree: fix radix_tree_iter_retry() for tagged iterators. radix_tree_iter_retry() resets slot to NULL, but it doesn't reset tags. Then NULL slot and non-zero iter.tags passed to radix_tree_next_slot() leading to crash: RIP: radix_tree_next_slot include/linux/radix-tree.h:473 find_get_pages_tag+0x334/0x930 mm/filemap.c:1452 .... Call Trace: pagevec_lookup_tag+0x3a/0x80 mm/swap.c:960 mpage_prepare_extent_to_map+0x321/0xa90 fs/ext4/inode.c:2516 ext4_writepages+0x10be/0x2b20 fs/ext4/inode.c:2736 do_writepages+0x97/0x100 mm/page-writeback.c:2364 __filemap_fdatawrite_range+0x248/0x2e0 mm/filemap.c:300 filemap_write_and_wait_range+0x121/0x1b0 mm/filemap.c:490 ext4_sync_file+0x34d/0xdb0 fs/ext4/fsync.c:115 vfs_fsync_range+0x10a/0x250 fs/sync.c:195 vfs_fsync fs/sync.c:209 do_fsync+0x42/0x70 fs/sync.c:219 SYSC_fdatasync fs/sync.c:232 SyS_fdatasync+0x19/0x20 fs/sync.c:230 entry_SYSCALL_64_fastpath+0x23/0xc1 arch/x86/entry/entry_64.S:207 We must reset iterator's tags to bail out from radix_tree_next_slot() and go to the slow-path in radix_tree_next_chunk(). Fixes: 46437f9a554f ("radix-tree: fix race in gang lookup") Link: http://lkml.kernel.org/r/1468495196-10604-1-git-send-email-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reported-by: Dmitry Vyukov Acked-by: Konstantin Khlebnikov Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Ross Zwisler Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cb4b7e8cee81..eca6f626c16e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -407,6 +407,7 @@ static inline __must_check void **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; + iter->tags = 0; return NULL; } -- cgit v1.2.3