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 --- include/linux/iio/common/st_sensors.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') 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 --- include/linux/iio/common/st_sensors.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') 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 2853908a59603118f854b813da055c26257dfa4f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 May 2016 13:49:56 -0400 Subject: undo "fs: allow d_instantiate to be called with negative parent dentry" Background: spufs used to mangle the order in which it had been building dentry trees. It was broken in a lot of ways, but most of them required the right timing to trigger until an fsnotify change had added one more - the one that was always triggered. Unfortunately, insteading of fixing their long-standing bug the spufs folks had chosen to paper over the fsnotify trigger. Eventually said bug had been spotted and killed off, but the pointless check in fsnotify has remained, complete with the implication that one *could* do that kind of crap. Again, a parent of any dentry should always be positive. Any code can rely upon that and anything violating that assert is a bug, *not* something to be accomodated. Signed-off-by: Al Viro --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 29f917517299..d188a107c562 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -281,7 +281,7 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) * us with the new state. */ parent = dentry->d_parent; - if (parent->d_inode && fsnotify_inode_watches_children(parent->d_inode)) + if (fsnotify_inode_watches_children(parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; -- 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 --- include/uapi/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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 affda48410a5bbfd516def60bbc97f2683cd9f7b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 May 2016 18:35:12 -0400 Subject: trim fsnotify hooks a bit fsnotify_d_move()/__fsnotify_d_instantiate()/__fsnotify_update_dcache_flags() are identical to each other, regardless of the config. Signed-off-by: Al Viro --- include/linux/fsnotify.h | 12 ------------ include/linux/fsnotify_backend.h | 20 +++----------------- 2 files changed, 3 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 0141f257d67b..eed9e853a06f 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -51,18 +51,6 @@ static inline int fsnotify_perm(struct file *file, int mask) return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -/* - * fsnotify_d_move - dentry has been moved - */ -static inline void fsnotify_d_move(struct dentry *dentry) -{ - /* - * On move we need to update dentry->d_flags to indicate if the new parent - * cares about events from this dentry. - */ - __fsnotify_update_dcache_flags(dentry); -} - /* * fsnotify_link_count - inode's link count changed */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index d188a107c562..58205f33af02 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -267,10 +267,8 @@ static inline int fsnotify_inode_watches_children(struct inode *inode) * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ -static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) +static inline void fsnotify_update_flags(struct dentry *dentry) { - struct dentry *parent; - assert_spin_locked(&dentry->d_lock); /* @@ -280,21 +278,12 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) * find our entry, so it will spin until we complete here, and update * us with the new state. */ - parent = dentry->d_parent; - if (fsnotify_inode_watches_children(parent->d_inode)) + if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } -/* - * fsnotify_d_instantiate - instantiate a dentry for inode - */ -static inline void __fsnotify_d_instantiate(struct dentry *dentry) -{ - __fsnotify_update_dcache_flags(dentry); -} - /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ @@ -386,10 +375,7 @@ static inline void __fsnotify_inode_delete(struct inode *inode) static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} -static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) -{} - -static inline void __fsnotify_d_instantiate(struct dentry *dentry) +static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) -- cgit v1.2.3 From 79c530ed4dd374e51f3c8ff75134a1da201952b7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 19 May 2016 19:45:59 +0200 Subject: ARM: dts: r8a7794: Remove nonexistent thermal sensor clock According to the latest information, there is no thermal IP block present on the r8a7794 SoC. Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/dt-bindings/clock/r8a7794-clock.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/r8a7794-clock.h b/include/dt-bindings/clock/r8a7794-clock.h index 4d3ecd626c1f..a3491ba2f6ec 100644 --- a/include/dt-bindings/clock/r8a7794-clock.h +++ b/include/dt-bindings/clock/r8a7794-clock.h @@ -67,7 +67,6 @@ #define R8A7794_CLK_IRQC 7 /* MSTP5 */ -#define R8A7794_CLK_THERMAL 22 #define R8A7794_CLK_PWM 23 /* MSTP7 */ -- cgit v1.2.3 From 8d5b5d5ce58ee1b90110f4e358eefe3c3a6b08a2 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 1 May 2016 19:36:57 +0900 Subject: reset: add devm_reset_controller_register API Add a device managed API for reset_controller_register(). This helps in reducing code in .remove callbacks and sometimes dropping .remove callbacks entirely. Signed-off-by: Masahiro Yamada Acked-by: Laxman Dewangan Signed-off-by: Philipp Zabel --- include/linux/reset-controller.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index b91ba932bbd4..db1fe6772ad5 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -53,4 +53,8 @@ struct reset_controller_dev { int reset_controller_register(struct reset_controller_dev *rcdev); void reset_controller_unregister(struct reset_controller_dev *rcdev); +struct device; +int devm_reset_controller_register(struct device *dev, + struct reset_controller_dev *rcdev); + #endif -- cgit v1.2.3 From 312521d0543513f37f0badb4efc7bfed2d99672e Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Tue, 24 May 2016 15:35:34 -0700 Subject: ACPI / NUMA: Move acpi_numa_arch_fixup() to ia64 only Since acpi_numa_arch_fixup() is only used in arch ia64, move it there to make a generic interface easier. This avoids empty function stubs or some complex kconfig options for x86 and arm64. Signed-off-by: Robert Richter Reviewed-by: Hanjun Guo Signed-off-by: David Daney Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..8010b266e856 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -237,7 +237,6 @@ void acpi_numa_slit_init (struct acpi_table_slit *slit); void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); -void acpi_numa_arch_fixup(void); #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; -- cgit v1.2.3 From e84025e274e66986277e11f0dda03373e246ffad Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 24 May 2016 15:35:39 -0700 Subject: ACPI / NUMA: move bad_srat() and srat_disabled() to drivers/acpi/numa.c bad_srat() and srat_disabled() are shared by x86 and follow-on arm64 patches. Move them to drivers/acpi/numa.c in preparation for arm64 support. Signed-off-by: Hanjun Guo Signed-off-by: Robert Richter [david.daney@cavium.com moved definitions to drivers/acpi/numa.c] Signed-off-by: David Daney Signed-off-by: Rafael J. Wysocki --- include/acpi/acpi_numa.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index 94a37cd7fbda..d4b72944ccda 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -15,6 +15,10 @@ extern int pxm_to_node(int); extern int node_to_pxm(int); extern int acpi_map_pxm_to_node(int); extern unsigned char acpi_srat_revision; +extern int acpi_numa __initdata; + +extern void bad_srat(void); +extern int srat_disabled(void); #endif /* CONFIG_ACPI_NUMA */ #endif /* __ACP_NUMA_H */ -- cgit v1.2.3 From fb7c2bae8a479e388a1f664e32d6ddca55c7a249 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 24 May 2016 15:35:43 -0700 Subject: ACPI / processor: Add acpi_map_madt_entry() Follow-on arm64 ACPI/NUMA patches need to map MADT entries very early (before kmalloc is usable). Add acpi_map_madt_entry() which, indirectly, uses early_memremap()/early_memunmap() to access the table and parse out the mpidr. The existing implementation of map_madt_entry() is modified to take a pointer to the MADT as a parameter and the callers adjusted. Signed-off-by: David Daney Acked-by: Catalin Marinas Signed-off-by: Rafael J. Wysocki --- include/acpi/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 6f1805dd5d3c..f473e6618339 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -309,6 +309,7 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) /* in processor_core.c */ phys_cpuid_t acpi_get_phys_id(acpi_handle, int type, u32 acpi_id); +phys_cpuid_t acpi_map_madt_entry(u32 acpi_id); int acpi_map_cpuid(phys_cpuid_t phys_id, u32 acpi_id); int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id); -- cgit v1.2.3 From 4c5773f9f5462dcb372857813918bbfe8c0cdcdd Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 28 May 2016 11:54:12 +0200 Subject: dt-bindings: clock: Add license and reformat Exynos5410 clock IDs Add license and copyrights (file introduced in 2014) to header with Exynos5410 clock IDs. Additionally reformat it to improve readability. Signed-off-by: Krzysztof Kozlowski Acked-by: Stephen Boyd Reviewed-by: Javier Martinez Canillas Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5410.h | 54 ++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h index 9b180f032e2d..213f19e02870 100644 --- a/include/dt-bindings/clock/exynos5410.h +++ b/include/dt-bindings/clock/exynos5410.h @@ -1,33 +1,43 @@ +/* + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Device Tree binding constants for Exynos5421 clock controller. +*/ + #ifndef _DT_BINDINGS_CLOCK_EXYNOS_5410_H #define _DT_BINDINGS_CLOCK_EXYNOS_5410_H /* core clocks */ -#define CLK_FIN_PLL 1 -#define CLK_FOUT_APLL 2 -#define CLK_FOUT_CPLL 3 -#define CLK_FOUT_MPLL 4 -#define CLK_FOUT_BPLL 5 -#define CLK_FOUT_KPLL 6 +#define CLK_FIN_PLL 1 +#define CLK_FOUT_APLL 2 +#define CLK_FOUT_CPLL 3 +#define CLK_FOUT_MPLL 4 +#define CLK_FOUT_BPLL 5 +#define CLK_FOUT_KPLL 6 /* gate for special clocks (sclk) */ -#define CLK_SCLK_UART0 128 -#define CLK_SCLK_UART1 129 -#define CLK_SCLK_UART2 130 -#define CLK_SCLK_UART3 131 -#define CLK_SCLK_MMC0 132 -#define CLK_SCLK_MMC1 133 -#define CLK_SCLK_MMC2 134 +#define CLK_SCLK_UART0 128 +#define CLK_SCLK_UART1 129 +#define CLK_SCLK_UART2 130 +#define CLK_SCLK_UART3 131 +#define CLK_SCLK_MMC0 132 +#define CLK_SCLK_MMC1 133 +#define CLK_SCLK_MMC2 134 /* gate clocks */ -#define CLK_UART0 257 -#define CLK_UART1 258 -#define CLK_UART2 259 -#define CLK_UART3 260 -#define CLK_MCT 315 -#define CLK_MMC0 351 -#define CLK_MMC1 352 -#define CLK_MMC2 353 +#define CLK_UART0 257 +#define CLK_UART1 258 +#define CLK_UART2 259 +#define CLK_UART3 260 +#define CLK_MCT 315 +#define CLK_MMC0 351 +#define CLK_MMC1 352 +#define CLK_MMC2 353 -#define CLK_NR_CLKS 512 +#define CLK_NR_CLKS 512 #endif /* _DT_BINDINGS_CLOCK_EXYNOS_5410_H */ -- cgit v1.2.3 From 5cd3535a27a7cf8fc4070b499d66e419e7e72b61 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 28 May 2016 11:54:13 +0200 Subject: dt-bindings: clock: Add PWM and USB clock IDs to Exynos5410 Add IDs for PWM and USB clocks to Exynos5410. Use the same number as for Exynos5420 just in case in future these drivers were merged. Signed-off-by: Krzysztof Kozlowski Acked-by: Stephen Boyd Reviewed-by: Javier Martinez Canillas Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5410.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h index 213f19e02870..34c8e96987a1 100644 --- a/include/dt-bindings/clock/exynos5410.h +++ b/include/dt-bindings/clock/exynos5410.h @@ -1,5 +1,6 @@ /* * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Copyright (c) 2016 Krzysztof Kozlowski * * 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 @@ -27,16 +28,25 @@ #define CLK_SCLK_MMC0 132 #define CLK_SCLK_MMC1 133 #define CLK_SCLK_MMC2 134 +#define CLK_SCLK_USBD300 150 +#define CLK_SCLK_USBD301 151 +#define CLK_SCLK_USBPHY300 152 +#define CLK_SCLK_USBPHY301 153 +#define CLK_SCLK_PWM 155 /* gate clocks */ #define CLK_UART0 257 #define CLK_UART1 258 #define CLK_UART2 259 #define CLK_UART3 260 +#define CLK_PWM 279 #define CLK_MCT 315 #define CLK_MMC0 351 #define CLK_MMC1 352 #define CLK_MMC2 353 +#define CLK_USBH20 365 +#define CLK_USBD300 366 +#define CLK_USBD301 367 #define CLK_NR_CLKS 512 -- cgit v1.2.3 From ed1e1505db0c116affdfab01e650c44a9c459c65 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 28 May 2016 11:54:29 +0200 Subject: dt-bindings: clock: Add I2C, HSI2C and RTC clock IDs to Exynos5410 Add IDs for I2C, USI (HSI2C) and RTC clocks to Exynos5410. Use the same number as for Exynos5420 just in case in future these drivers are merged. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Javier Martinez Canillas Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5410.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h index 34c8e96987a1..e94b7bbfd6af 100644 --- a/include/dt-bindings/clock/exynos5410.h +++ b/include/dt-bindings/clock/exynos5410.h @@ -38,9 +38,18 @@ #define CLK_UART0 257 #define CLK_UART1 258 #define CLK_UART2 259 +#define CLK_I2C0 261 +#define CLK_I2C1 262 +#define CLK_I2C2 263 +#define CLK_I2C3 264 +#define CLK_USI0 265 +#define CLK_USI1 266 +#define CLK_USI2 267 +#define CLK_USI3 268 #define CLK_UART3 260 #define CLK_PWM 279 #define CLK_MCT 315 +#define CLK_RTC 317 #define CLK_MMC0 351 #define CLK_MMC1 352 #define CLK_MMC2 353 -- cgit v1.2.3 From 2230c49f09b552454eac51b81e9e4e41060b5e70 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 13 May 2016 16:45:18 +0100 Subject: ASoC: arizona: Add a notifier chain for CODEC events Add a notifier chain that can be used from the machine driver to catch events generated by the CODEC. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- include/linux/mfd/arizona/core.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/arizona/core.h b/include/linux/mfd/arizona/core.h index d55a42297d49..58ab4c0fe761 100644 --- a/include/linux/mfd/arizona/core.h +++ b/include/linux/mfd/arizona/core.h @@ -14,6 +14,7 @@ #define _WM_ARIZONA_CORE_H #include +#include #include #include #include @@ -148,8 +149,17 @@ struct arizona { uint16_t dac_comp_coeff; uint8_t dac_comp_enabled; struct mutex dac_comp_lock; + + struct blocking_notifier_head notifier; }; +static inline int arizona_call_notifiers(struct arizona *arizona, + unsigned long event, + void *data) +{ + return blocking_notifier_call_chain(&arizona->notifier, event, data); +} + int arizona_clk32k_enable(struct arizona *arizona); int arizona_clk32k_disable(struct arizona *arizona); -- cgit v1.2.3 From 6742064aef7f1fba8e68d30b2e726918a5d66790 Mon Sep 17 00:00:00 2001 From: Piotr Stankiewicz Date: Fri, 13 May 2016 17:03:55 +0100 Subject: ASoC: dapm: support user-defined stop condition in dai_get_connected_widgets Certain situations may warrant examining DAPM paths only to a certain arbitrary point, as opposed to always following them to the end. For instance, when establishing a connection between a front-end DAI link and a back-end DAI link in a DPCM path, it does not make sense to walk the DAPM graph beyond the first widget associated with a back-end link. This patch introduces a mechanism which lets a user of dai_get_connected_widgets supply a function which will be called for every node during the graph walk. When invoked, this function can execute arbitrary logic to decide whether the walk, given a DAPM widget and walk direction, should be terminated at that point or continued as normal. Signed-off-by: Piotr Stankiewicz Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 3101d53468aa..ca77db443499 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -358,6 +358,7 @@ struct snd_soc_dapm_context; struct regulator; struct snd_soc_dapm_widget_list; struct snd_soc_dapm_update; +enum snd_soc_dapm_direction; int dapm_regulator_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event); @@ -451,7 +452,9 @@ void dapm_mark_endpoints_dirty(struct snd_soc_card *card); /* dapm path query */ int snd_soc_dapm_dai_get_connected_widgets(struct snd_soc_dai *dai, int stream, - struct snd_soc_dapm_widget_list **list); + struct snd_soc_dapm_widget_list **list, + bool (*custom_stop_condition)(struct snd_soc_dapm_widget *, + enum snd_soc_dapm_direction)); struct snd_soc_dapm_context *snd_soc_dapm_kcontrol_dapm( struct snd_kcontrol *kcontrol); -- cgit v1.2.3 From dcc0799bf75c43f3d4e65716c88f35933da186cf Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 27 May 2016 14:45:45 +0100 Subject: ASoC: Introduce SOC_SINGLE_S8_TLV() macro This patch introduces SOC_SINGLE_S8_TLV() macro for volume control on chips which supports both negative and positive gains with sign bit on a 8 bit register, Gain ranges from -128 to +127 with a predefined step size. Currently we only have support to DOUBLE_S8_TLV() which does not fit for cases where we just have separate gain control register for each channel. One of the Qualcomm SOC msm8916 has such gain control register whose gain range is from -38.4dB to +38.4dB with step size of 0.3dB. Signed-off-by: Srinivas Kandagatla Signed-off-by: Mark Brown --- include/sound/soc.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index fd7b58a58d6f..6144882cc96a 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -179,6 +179,17 @@ .get = snd_soc_get_volsw, .put = snd_soc_put_volsw, \ .private_value = SOC_DOUBLE_R_S_VALUE(reg_left, reg_right, xshift, \ xmin, xmax, xsign_bit, xinvert) } +#define SOC_SINGLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \ +{ .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ + .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ + SNDRV_CTL_ELEM_ACCESS_READWRITE, \ + .tlv.p = (tlv_array), \ + .info = snd_soc_info_volsw, .get = snd_soc_get_volsw,\ + .put = snd_soc_put_volsw, \ + .private_value = (unsigned long)&(struct soc_mixer_control) \ + {.reg = xreg, .rreg = xreg, \ + .min = xmin, .max = xmax, .platform_max = xmax, \ + .sign_bit = 7,} } #define SOC_DOUBLE_S8_TLV(xname, xreg, xmin, xmax, tlv_array) \ { .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = (xname), \ .access = SNDRV_CTL_ELEM_ACCESS_TLV_READ | \ -- 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 +++++- 2 files changed, 6 insertions(+), 2 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)) -- cgit v1.2.3 From 7a1aedba7061948eee4d188740e24ffb20ff7ab7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Horia=20Geant=C4=83?= Date: Thu, 19 May 2016 18:10:43 +0300 Subject: asm-generic/io.h: allow barriers in io{read,write}{16,32}be MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While reviewing the addition of io{read,write}64be accessors, Arnd -finds a potential problem: "If an architecture overrides readq/writeq to have barriers but does not override ioread64be/iowrite64be, this will lack the barriers and behave differently from the little-endian version. I think the only affected architecture is ARC, since ARM and ARM64 both override the big-endian accessors to have the correct barriers, and all others don't use barriers at all." -suggests a fix for the same problem in existing code (16/32-bit accessors); the fix leads "to a double-swap on architectures that don't override the io{read,write}{16,32}be accessors, but it will work correctly on all architectures without them having to override these accessors." Suggested-by: Arnd Bergmann Acked-by: Arnd Bergmann Signed-off-by: Horia Geantă Signed-off-by: Herbert Xu --- include/asm-generic/io.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 002b81f6f2bc..325c8908f6de 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -613,7 +613,7 @@ static inline void iowrite32(u32 value, volatile void __iomem *addr) #define ioread16be ioread16be static inline u16 ioread16be(const volatile void __iomem *addr) { - return __be16_to_cpu(__raw_readw(addr)); + return swab16(readw(addr)); } #endif @@ -621,7 +621,7 @@ static inline u16 ioread16be(const volatile void __iomem *addr) #define ioread32be ioread32be static inline u32 ioread32be(const volatile void __iomem *addr) { - return __be32_to_cpu(__raw_readl(addr)); + return swab32(readl(addr)); } #endif @@ -629,7 +629,7 @@ static inline u32 ioread32be(const volatile void __iomem *addr) #define iowrite16be iowrite16be static inline void iowrite16be(u16 value, void volatile __iomem *addr) { - __raw_writew(__cpu_to_be16(value), addr); + writew(swab16(value), addr); } #endif @@ -637,7 +637,7 @@ static inline void iowrite16be(u16 value, void volatile __iomem *addr) #define iowrite32be iowrite32be static inline void iowrite32be(u32 value, volatile void __iomem *addr) { - __raw_writel(__cpu_to_be32(value), addr); + writel(swab32(value), addr); } #endif -- cgit v1.2.3 From 9e44fb1816dba8f283809a25c29ff7969a3acb99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Horia=20Geant=C4=83?= Date: Thu, 19 May 2016 18:10:56 +0300 Subject: asm-generic/io.h: add io{read,write}64 accessors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This will allow device drivers to consistently use io{read,write}XX also for 64-bit accesses. Acked-by: Arnd Bergmann Signed-off-by: Horia Geantă Signed-off-by: Herbert Xu --- include/asm-generic/io.h | 63 +++++++++++++++++++++++++++++++++++++++++++++ include/asm-generic/iomap.h | 8 ++++++ 2 files changed, 71 insertions(+) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 325c8908f6de..7ef015eb3403 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -585,6 +585,16 @@ static inline u32 ioread32(const volatile void __iomem *addr) } #endif +#ifdef CONFIG_64BIT +#ifndef ioread64 +#define ioread64 ioread64 +static inline u64 ioread64(const volatile void __iomem *addr) +{ + return readq(addr); +} +#endif +#endif /* CONFIG_64BIT */ + #ifndef iowrite8 #define iowrite8 iowrite8 static inline void iowrite8(u8 value, volatile void __iomem *addr) @@ -609,6 +619,16 @@ static inline void iowrite32(u32 value, volatile void __iomem *addr) } #endif +#ifdef CONFIG_64BIT +#ifndef iowrite64 +#define iowrite64 iowrite64 +static inline void iowrite64(u64 value, volatile void __iomem *addr) +{ + writeq(value, addr); +} +#endif +#endif /* CONFIG_64BIT */ + #ifndef ioread16be #define ioread16be ioread16be static inline u16 ioread16be(const volatile void __iomem *addr) @@ -625,6 +645,16 @@ static inline u32 ioread32be(const volatile void __iomem *addr) } #endif +#ifdef CONFIG_64BIT +#ifndef ioread64be +#define ioread64be ioread64be +static inline u64 ioread64be(const volatile void __iomem *addr) +{ + return swab64(readq(addr)); +} +#endif +#endif /* CONFIG_64BIT */ + #ifndef iowrite16be #define iowrite16be iowrite16be static inline void iowrite16be(u16 value, void volatile __iomem *addr) @@ -641,6 +671,16 @@ static inline void iowrite32be(u32 value, volatile void __iomem *addr) } #endif +#ifdef CONFIG_64BIT +#ifndef iowrite64be +#define iowrite64be iowrite64be +static inline void iowrite64be(u64 value, volatile void __iomem *addr) +{ + writeq(swab64(value), addr); +} +#endif +#endif /* CONFIG_64BIT */ + #ifndef ioread8_rep #define ioread8_rep ioread8_rep static inline void ioread8_rep(const volatile void __iomem *addr, void *buffer, @@ -668,6 +708,17 @@ static inline void ioread32_rep(const volatile void __iomem *addr, } #endif +#ifdef CONFIG_64BIT +#ifndef ioread64_rep +#define ioread64_rep ioread64_rep +static inline void ioread64_rep(const volatile void __iomem *addr, + void *buffer, unsigned int count) +{ + readsq(addr, buffer, count); +} +#endif +#endif /* CONFIG_64BIT */ + #ifndef iowrite8_rep #define iowrite8_rep iowrite8_rep static inline void iowrite8_rep(volatile void __iomem *addr, @@ -697,6 +748,18 @@ static inline void iowrite32_rep(volatile void __iomem *addr, writesl(addr, buffer, count); } #endif + +#ifdef CONFIG_64BIT +#ifndef iowrite64_rep +#define iowrite64_rep iowrite64_rep +static inline void iowrite64_rep(volatile void __iomem *addr, + const void *buffer, + unsigned int count) +{ + writesq(addr, buffer, count); +} +#endif +#endif /* CONFIG_64BIT */ #endif /* CONFIG_GENERIC_IOMAP */ #ifdef __KERNEL__ diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index d8f8622fa044..650fede33c25 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -30,12 +30,20 @@ extern unsigned int ioread16(void __iomem *); extern unsigned int ioread16be(void __iomem *); extern unsigned int ioread32(void __iomem *); extern unsigned int ioread32be(void __iomem *); +#ifdef CONFIG_64BIT +extern u64 ioread64(void __iomem *); +extern u64 ioread64be(void __iomem *); +#endif extern void iowrite8(u8, void __iomem *); extern void iowrite16(u16, void __iomem *); extern void iowrite16be(u16, void __iomem *); extern void iowrite32(u32, void __iomem *); extern void iowrite32be(u32, void __iomem *); +#ifdef CONFIG_64BIT +extern void iowrite64(u64, void __iomem *); +extern void iowrite64be(u64, void __iomem *); +#endif /* * "string" versions of the above. Note that they -- cgit v1.2.3 From 4bdf1cfca5d46294142cdf49cd997b8b83491adf Mon Sep 17 00:00:00 2001 From: Nicolai Stange Date: Thu, 26 May 2016 12:57:50 +0200 Subject: lib/mpi: purge mpi_set_buffer() mpi_set_buffer() has no in-tree users and similar functionality is provided by mpi_read_raw_data(). Remove mpi_set_buffer(). Signed-off-by: Nicolai Stange Signed-off-by: Herbert Xu --- include/linux/mpi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 3a5abe95affd..f219559e5e80 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -80,7 +80,6 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign); -int mpi_set_buffer(MPI a, const void *buffer, unsigned nbytes, int sign); int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned *nbytes, int *sign); -- cgit v1.2.3 From bf1ecd210541ef5f3a110e88e8ca5d33b4aa5c23 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Tue, 31 May 2016 00:16:50 +0300 Subject: cfg80211: Allow cfg80211_connect_result() errors to be distinguished Previously, the status parameter to cfg80211_connect_result() was documented as using WLAN_STATUS_UNSPECIFIED_FAILURE (1) when the real status code for the failure is not known. This value can be used by an AP (and often is) and as such, user space cannot distinguish between explicitly rejected authentication/association and not being able to even try to associate or not receiving a response from the AP. Add a new inline function, cfg80211_connect_timeout(), to be used when the driver knows that the connection attempt failed due to a reason where connection could not be attempt or no response was received from the AP. The internal functions now allow a negative status value (-1) to be used as an indication of this special case. This results in the NL80211_ATTR_TIMED_OUT to be added to the NL80211_CMD_CONNECT event to allow user space to determine this case was hit. For backwards compatibility, NL80211_STATUS_CODE with the value WLAN_STATUS_UNSPECIFIED_FAILURE is still indicated in the event in such a case. Signed-off-by: Jouni Malinen [johannes: fix cfg80211_connect_bss() prototype to use int for status, add cfg80211_connect_timeout() to docbook, fix docbook] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 53 +++++++++++++++++++++++++++++++++----------- include/uapi/linux/nl80211.h | 7 +++++- 2 files changed, 46 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 63921672bed0..537f010cf5e1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2367,19 +2367,23 @@ struct cfg80211_qos_map { * (invoked with the wireless_dev mutex held) * * @connect: Connect to the ESS with the specified parameters. When connected, - * call cfg80211_connect_result() with status code %WLAN_STATUS_SUCCESS. - * If the connection fails for some reason, call cfg80211_connect_result() - * with the status from the AP. The driver is allowed to roam to other - * BSSes within the ESS when the other BSS matches the connect parameters. - * When such roaming is initiated by the driver, the driver is expected to - * verify that the target matches the configured security parameters and - * to use Reassociation Request frame instead of Association Request frame. - * The connect function can also be used to request the driver to perform - * a specific roam when connected to an ESS. In that case, the prev_bssid + * call cfg80211_connect_result()/cfg80211_connect_bss() with status code + * %WLAN_STATUS_SUCCESS. If the connection fails for some reason, call + * cfg80211_connect_result()/cfg80211_connect_bss() with the status code + * from the AP or cfg80211_connect_timeout() if no frame with status code + * was received. + * The driver is allowed to roam to other BSSes within the ESS when the + * other BSS matches the connect parameters. When such roaming is initiated + * by the driver, the driver is expected to verify that the target matches + * the configured security parameters and to use Reassociation Request + * frame instead of Association Request frame. + * The connect function can also be used to request the driver to perform a + * specific roam when connected to an ESS. In that case, the prev_bssid * parameter is set to the BSSID of the currently associated BSS as an - * indication of requesting reassociation. In both the driver-initiated and - * new connect() call initiated roaming cases, the result of roaming is - * indicated with a call to cfg80211_roamed() or cfg80211_roamed_bss(). + * indication of requesting reassociation. + * In both the driver-initiated and new connect() call initiated roaming + * cases, the result of roaming is indicated with a call to + * cfg80211_roamed() or cfg80211_roamed_bss(). * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS. * (invoked with the wireless_dev mutex held) @@ -4680,7 +4684,7 @@ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, - size_t resp_ie_len, u16 status, gfp_t gfp); + size_t resp_ie_len, int status, gfp_t gfp); /** * cfg80211_connect_result - notify cfg80211 of connection result @@ -4709,6 +4713,29 @@ cfg80211_connect_result(struct net_device *dev, const u8 *bssid, resp_ie_len, status, gfp); } +/** + * cfg80211_connect_timeout - notify cfg80211 of connection timeout + * + * @dev: network device + * @bssid: the BSSID of the AP + * @req_ie: association request IEs (maybe be %NULL) + * @req_ie_len: association request IEs length + * @gfp: allocation flags + * + * It should be called by the underlying driver whenever connect() has failed + * in a sequence where no explicit authentication/association rejection was + * received from the AP. This could happen, e.g., due to not being able to send + * out the Authentication or Association Request frame or timing out while + * waiting for the response. + */ +static inline void +cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, + const u8 *req_ie, size_t req_ie_len, gfp_t gfp) +{ + cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1, + gfp); +} + /** * cfg80211_roamed - notify cfg80211 of roaming * diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e23d78685a01..8d995316aadb 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -493,7 +493,12 @@ * This attribute is ignored if driver does not support roam scan. * It is also sent as an event, with the BSSID and response IEs when the * connection is established or failed to be established. This can be - * determined by the STATUS_CODE attribute. + * determined by the %NL80211_ATTR_STATUS_CODE attribute (0 = success, + * non-zero = failure). If %NL80211_ATTR_TIMED_OUT is included in the + * event, the connection attempt failed due to not being able to initiate + * authentication/association or not receiving a response from the AP. + * Non-zero %NL80211_ATTR_STATUS_CODE value is indicated in that case as + * well to remain backwards compatible. * @NL80211_CMD_ROAM: request that the card roam (currently not implemented), * sent as an event when the card/driver roamed by itself. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify -- cgit v1.2.3 From 019ae3a918811715192b22c400ac78d54acc26a9 Mon Sep 17 00:00:00 2001 From: "Kanchanapally, Vidyullatha" Date: Mon, 16 May 2016 10:41:04 +0530 Subject: cfg80211: Advertise extended capabilities per interface type to userspace The driver extended capabilities may differ for different interface types which the userspace needs to know (for example the fine timing measurement initiator and responder bits might differ for a station and AP). Add a new nl80211 attribute to provide extended capabilities per interface type to userspace. Signed-off-by: Vidyullatha Kanchanapally Reviewed-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 28 +++++++++++++++++++++++++++- include/uapi/linux/nl80211.h | 7 +++++++ 2 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 537f010cf5e1..7bbb00d8b2cd 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3083,6 +3083,24 @@ struct wiphy_vendor_command { unsigned long *storage); }; +/** + * struct wiphy_iftype_ext_capab - extended capabilities per interface type + * @iftype: interface type + * @extended_capabilities: extended capabilities supported by the driver, + * additional capabilities might be supported by userspace; these are the + * 802.11 extended capabilities ("Extended Capabilities element") and are + * in the same format as in the information element. See IEEE Std + * 802.11-2012 8.4.2.29 for the defined fields. + * @extended_capabilities_mask: mask of the valid values + * @extended_capabilities_len: length of the extended capabilities + */ +struct wiphy_iftype_ext_capab { + enum nl80211_iftype iftype; + const u8 *extended_capabilities; + const u8 *extended_capabilities_mask; + u8 extended_capabilities_len; +}; + /** * struct wiphy - wireless hardware description * @reg_notifier: the driver's regulatory notification callback, @@ -3203,9 +3221,14 @@ struct wiphy_vendor_command { * additional capabilities might be supported by userspace; these are * the 802.11 extended capabilities ("Extended Capabilities element") * and are in the same format as in the information element. See - * 802.11-2012 8.4.2.29 for the defined fields. + * 802.11-2012 8.4.2.29 for the defined fields. These are the default + * extended capabilities to be used if the capabilities are not specified + * for a specific interface type in iftype_ext_capab. * @extended_capabilities_mask: mask of the valid values * @extended_capabilities_len: length of the extended capabilities + * @iftype_ext_capab: array of extended capabilities per interface type + * @num_iftype_ext_capab: number of interface types for which extended + * capabilities are specified separately. * @coalesce: packet coalescing support information * * @vendor_commands: array of vendor commands supported by the hardware @@ -3305,6 +3328,9 @@ struct wiphy { const u8 *extended_capabilities, *extended_capabilities_mask; u8 extended_capabilities_len; + const struct wiphy_iftype_ext_capab *iftype_ext_capab; + unsigned int num_iftype_ext_capab; + /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't * know whether it points to a wiphy your driver has registered diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 8d995316aadb..53c8278827a0 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1824,6 +1824,11 @@ enum nl80211_commands { * * @NL80211_ATTR_PAD: attribute used for padding for 64-bit alignment * + * @NL80211_ATTR_IFTYPE_EXT_CAPA: Nested attribute of the following attributes: + * %NL80211_ATTR_IFTYPE, %NL80211_ATTR_EXT_CAPA, + * %NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities per + * interface type. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2206,6 +2211,8 @@ enum nl80211_attrs { NL80211_ATTR_PAD, + NL80211_ATTR_IFTYPE_EXT_CAPA, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 168d7c4e8bb25c076ed8be67fcca84f5dcd0b2c6 Mon Sep 17 00:00:00 2001 From: John Youn Date: Tue, 31 May 2016 16:55:01 -0700 Subject: reset: Return -ENOTSUPP when not configured Prior to commit 6c96f05c8bb8 ("reset: Make [of_]reset_control_get[_foo] functions wrappers"), the "optional" functions returned -ENOTSUPP when CONFIG_RESET_CONTROLLER was not set. Revert back to the old behavior by changing the new __devm_reset_control_get() and __of_reset_control_get() functions to return ERR_PTR(-ENOTSUPP) when compiled without CONFIG_RESET_CONTROLLER. Otherwise they will return -EINVAL causing users to think that an error occurred when CONFIG_RESET_CONTROLLER is not set. Fixes: 6c96f05c8bb8 ("reset: Make [of_]reset_control_get[_foo] functions wrappers") Signed-off-by: John Youn Signed-off-by: Philipp Zabel --- include/linux/reset.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/reset.h b/include/linux/reset.h index ec0306ce7b92..067db57c81dc 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -71,14 +71,14 @@ static inline struct reset_control *__of_reset_control_get( struct device_node *node, const char *id, int index, int shared) { - return ERR_PTR(-EINVAL); + return ERR_PTR(-ENOTSUPP); } static inline struct reset_control *__devm_reset_control_get( struct device *dev, const char *id, int index, int shared) { - return ERR_PTR(-EINVAL); + return ERR_PTR(-ENOTSUPP); } #endif /* CONFIG_RESET_CONTROLLER */ -- cgit v1.2.3 From 79795e20a184ebabf4ae743d1506cc39783caa46 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Mon, 30 May 2016 15:27:16 +0200 Subject: dt-bindings: reset: Add bindings for the Meson SoC Reset Controller Add DT bindings for the Meson SoC Reset Controller documentation and the associated include file. Acked-by: Rob Herring Signed-off-by: Neil Armstrong Signed-off-by: Philipp Zabel --- .../dt-bindings/reset/amlogic,meson-gxbb-reset.h | 210 +++++++++++++++++++++ include/dt-bindings/reset/amlogic,meson8b-reset.h | 175 +++++++++++++++++ 2 files changed, 385 insertions(+) create mode 100644 include/dt-bindings/reset/amlogic,meson-gxbb-reset.h create mode 100644 include/dt-bindings/reset/amlogic,meson8b-reset.h (limited to 'include') diff --git a/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h b/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h new file mode 100644 index 000000000000..524d6077ac1b --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson-gxbb-reset.h @@ -0,0 +1,210 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright (c) 2016 BayLibre, SAS. + * Author: Neil Armstrong + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public 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 . + * The full GNU General Public License is included in this distribution + * in the file called COPYING. + * + * BSD LICENSE + * + * Copyright (c) 2016 BayLibre, SAS. + * Author: Neil Armstrong + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _DT_BINDINGS_AMLOGIC_MESON_GXBB_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON_GXBB_RESET_H + +/* RESET0 */ +#define RESET_HIU 0 +/* 1 */ +#define RESET_DOS_RESET 2 +#define RESET_DDR_TOP 3 +#define RESET_DCU_RESET 4 +#define RESET_VIU 5 +#define RESET_AIU 6 +#define RESET_VID_PLL_DIV 7 +/* 8 */ +#define RESET_PMUX 9 +#define RESET_VENC 10 +#define RESET_ASSIST 11 +#define RESET_AFIFO2 12 +#define RESET_VCBUS 13 +/* 14 */ +/* 15 */ +#define RESET_GIC 16 +#define RESET_CAPB3_DECODE 17 +#define RESET_NAND_CAPB3 18 +#define RESET_HDMITX_CAPB3 19 +#define RESET_MALI_CAPB3 20 +#define RESET_DOS_CAPB3 21 +#define RESET_SYS_CPU_CAPB3 22 +#define RESET_CBUS_CAPB3 23 +#define RESET_AHB_CNTL 24 +#define RESET_AHB_DATA 25 +#define RESET_VCBUS_CLK81 26 +#define RESET_MMC 27 +#define RESET_MIPI_0 28 +#define RESET_MIPI_1 29 +#define RESET_MIPI_2 30 +#define RESET_MIPI_3 31 +/* RESET1 */ +#define RESET_CPPM 32 +#define RESET_DEMUX 33 +#define RESET_USB_OTG 34 +#define RESET_DDR 35 +#define RESET_AO_RESET 36 +#define RESET_BT656 37 +#define RESET_AHB_SRAM 38 +/* 39 */ +#define RESET_PARSER 40 +#define RESET_BLKMV 41 +#define RESET_ISA 42 +#define RESET_ETHERNET 43 +#define RESET_SD_EMMC_A 44 +#define RESET_SD_EMMC_B 45 +#define RESET_SD_EMMC_C 46 +#define RESET_ROM_BOOT 47 +#define RESET_SYS_CPU_0 48 +#define RESET_SYS_CPU_1 49 +#define RESET_SYS_CPU_2 50 +#define RESET_SYS_CPU_3 51 +#define RESET_SYS_CPU_CORE_0 52 +#define RESET_SYS_CPU_CORE_1 53 +#define RESET_SYS_CPU_CORE_2 54 +#define RESET_SYS_CPU_CORE_3 55 +#define RESET_SYS_PLL_DIV 56 +#define RESET_SYS_CPU_AXI 57 +#define RESET_SYS_CPU_L2 58 +#define RESET_SYS_CPU_P 59 +#define RESET_SYS_CPU_MBIST 60 +/* 61 */ +/* 62 */ +/* 63 */ +/* RESET2 */ +#define RESET_VD_RMEM 64 +#define RESET_AUDIN 65 +#define RESET_HDMI_TX 66 +/* 67 */ +/* 68 */ +/* 69 */ +#define RESET_GE2D 70 +#define RESET_PARSER_REG 71 +#define RESET_PARSER_FETCH 72 +#define RESET_PARSER_CTL 73 +#define RESET_PARSER_TOP 74 +/* 75 */ +/* 76 */ +#define RESET_AO_CPU_RESET 77 +#define RESET_MALI 78 +#define RESET_HDMI_SYSTEM_RESET 79 +/* 80-95 */ +/* RESET3 */ +#define RESET_RING_OSCILLATOR 96 +#define RESET_SYS_CPU 97 +#define RESET_EFUSE 98 +#define RESET_SYS_CPU_BVCI 99 +#define RESET_AIFIFO 100 +#define RESET_TVFE 101 +#define RESET_AHB_BRIDGE_CNTL 102 +/* 103 */ +#define RESET_AUDIO_DAC 104 +#define RESET_DEMUX_TOP 105 +#define RESET_DEMUX_DES 106 +#define RESET_DEMUX_S2P_0 107 +#define RESET_DEMUX_S2P_1 108 +#define RESET_DEMUX_RESET_0 109 +#define RESET_DEMUX_RESET_1 110 +#define RESET_DEMUX_RESET_2 111 +/* 112-127 */ +/* RESET4 */ +/* 128 */ +/* 129 */ +/* 130 */ +/* 131 */ +#define RESET_DVIN_RESET 132 +#define RESET_RDMA 133 +#define RESET_VENCI 134 +#define RESET_VENCP 135 +/* 136 */ +#define RESET_VDAC 137 +#define RESET_RTC 138 +/* 139 */ +#define RESET_VDI6 140 +#define RESET_VENCL 141 +#define RESET_I2C_MASTER_2 142 +#define RESET_I2C_MASTER_1 143 +/* 144-159 */ +/* RESET5 */ +/* 160-191 */ +/* RESET6 */ +#define RESET_PERIPHS_GENERAL 192 +#define RESET_PERIPHS_SPICC 193 +#define RESET_PERIPHS_SMART_CARD 194 +#define RESET_PERIPHS_SAR_ADC 195 +#define RESET_PERIPHS_I2C_MASTER_0 196 +#define RESET_SANA 197 +/* 198 */ +#define RESET_PERIPHS_STREAM_INTERFACE 199 +#define RESET_PERIPHS_SDIO 200 +#define RESET_PERIPHS_UART_0 201 +#define RESET_PERIPHS_UART_1_2 202 +#define RESET_PERIPHS_ASYNC_0 203 +#define RESET_PERIPHS_ASYNC_1 204 +#define RESET_PERIPHS_SPI_0 205 +#define RESET_PERIPHS_SDHC 206 +#define RESET_UART_SLIP 207 +/* 208-223 */ +/* RESET7 */ +#define RESET_USB_DDR_0 224 +#define RESET_USB_DDR_1 225 +#define RESET_USB_DDR_2 226 +#define RESET_USB_DDR_3 227 +/* 228 */ +#define RESET_DEVICE_MMC_ARB 229 +/* 230 */ +#define RESET_VID_LOCK 231 +#define RESET_A9_DMC_PIPEL 232 +/* 233-255 */ + +#endif diff --git a/include/dt-bindings/reset/amlogic,meson8b-reset.h b/include/dt-bindings/reset/amlogic,meson8b-reset.h new file mode 100644 index 000000000000..614aff2c7aff --- /dev/null +++ b/include/dt-bindings/reset/amlogic,meson8b-reset.h @@ -0,0 +1,175 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright (c) 2016 BayLibre, SAS. + * Author: Neil Armstrong + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public 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 . + * The full GNU General Public License is included in this distribution + * in the file called COPYING. + * + * BSD LICENSE + * + * Copyright (c) 2016 BayLibre, SAS. + * Author: Neil Armstrong + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _DT_BINDINGS_AMLOGIC_MESON8B_RESET_H +#define _DT_BINDINGS_AMLOGIC_MESON8B_RESET_H + +/* RESET0 */ +#define RESET_HIU 0 +#define RESET_VLD 1 +#define RESET_IQIDCT 2 +#define RESET_MC 3 +/* 8 */ +#define RESET_VIU 5 +#define RESET_AIU 6 +#define RESET_MCPU 7 +#define RESET_CCPU 8 +#define RESET_PMUX 9 +#define RESET_VENC 10 +#define RESET_ASSIST 11 +#define RESET_AFIFO2 12 +#define RESET_MDEC 13 +#define RESET_VLD_PART 14 +#define RESET_VIFIFO 15 +/* 16-31 */ +/* RESET1 */ +/* 32 */ +#define RESET_DEMUX 33 +#define RESET_USB_OTG 34 +#define RESET_DDR 35 +#define RESET_VDAC_1 36 +#define RESET_BT656 37 +#define RESET_AHB_SRAM 38 +#define RESET_AHB_BRIDGE 39 +#define RESET_PARSER 40 +#define RESET_BLKMV 41 +#define RESET_ISA 42 +#define RESET_ETHERNET 43 +#define RESET_ABUF 44 +#define RESET_AHB_DATA 45 +#define RESET_AHB_CNTL 46 +#define RESET_ROM_BOOT 47 +/* 48-63 */ +/* RESET2 */ +#define RESET_VD_RMEM 64 +#define RESET_AUDIN 65 +#define RESET_DBLK 66 +#define RESET_PIC_DC 66 +#define RESET_PSC 66 +#define RESET_NAND 66 +#define RESET_GE2D 70 +#define RESET_PARSER_REG 71 +#define RESET_PARSER_FETCH 72 +#define RESET_PARSER_CTL 73 +#define RESET_PARSER_TOP 74 +#define RESET_HDMI_APB 75 +#define RESET_AUDIO_APB 76 +#define RESET_MEDIA_CPU 77 +#define RESET_MALI 78 +#define RESET_HDMI_SYSTEM_RESET 79 +/* 80-95 */ +/* RESET3 */ +#define RESET_RING_OSCILLATOR 96 +#define RESET_SYS_CPU_0 97 +#define RESET_EFUSE 98 +#define RESET_SYS_CPU_BVCI 99 +#define RESET_AIFIFO 100 +#define RESET_AUDIO_PLL_MODULATOR 101 +#define RESET_AHB_BRIDGE_CNTL 102 +#define RESET_SYS_CPU_1 103 +#define RESET_AUDIO_DAC 104 +#define RESET_DEMUX_TOP 105 +#define RESET_DEMUX_DES 106 +#define RESET_DEMUX_S2P_0 107 +#define RESET_DEMUX_S2P_1 108 +#define RESET_DEMUX_RESET_0 109 +#define RESET_DEMUX_RESET_1 110 +#define RESET_DEMUX_RESET_2 111 +/* 112-127 */ +/* RESET4 */ +#define RESET_PL310 128 +#define RESET_A5_APB 129 +#define RESET_A5_AXI 130 +#define RESET_A5 131 +#define RESET_DVIN 132 +#define RESET_RDMA 133 +#define RESET_VENCI 134 +#define RESET_VENCP 135 +#define RESET_VENCT 136 +#define RESET_VDAC_4 137 +#define RESET_RTC 138 +#define RESET_A5_DEBUG 139 +#define RESET_VDI6 140 +#define RESET_VENCL 141 +/* 142-159 */ +/* RESET5 */ +#define RESET_DDR_PLL 160 +#define RESET_MISC_PLL 161 +#define RESET_SYS_PLL 162 +#define RESET_HPLL_PLL 163 +#define RESET_AUDIO_PLL 164 +#define RESET_VID2_PLL 165 +/* 166-191 */ +/* RESET6 */ +#define RESET_PERIPHS_GENERAL 192 +#define RESET_PERIPHS_IR_REMOTE 193 +#define RESET_PERIPHS_SMART_CARD 194 +#define RESET_PERIPHS_SAR_ADC 195 +#define RESET_PERIPHS_I2C_MASTER_0 196 +#define RESET_PERIPHS_I2C_MASTER_1 197 +#define RESET_PERIPHS_I2C_SLAVE 198 +#define RESET_PERIPHS_STREAM_INTERFACE 199 +#define RESET_PERIPHS_SDIO 200 +#define RESET_PERIPHS_UART_0 201 +#define RESET_PERIPHS_UART_1 202 +#define RESET_PERIPHS_ASYNC_0 203 +#define RESET_PERIPHS_ASYNC_1 204 +#define RESET_PERIPHS_SPI_0 205 +#define RESET_PERIPHS_SPI_1 206 +#define RESET_PERIPHS_LED_PWM 207 +/* 208-223 */ +/* RESET7 */ +/* 224-255 */ + +#endif -- cgit v1.2.3 From 109869f522852094393b829918b56327c0feb360 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 31 May 2016 20:39:00 +0200 Subject: dt-bindings: clock: Add TMU clock ID to Exynos5410 Add ID for TMU clock to Exynos5410. Use the same number as for Exynos5420 just in case in future these drivers were merged. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Javier Martinez Canillas Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5410.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h index e94b7bbfd6af..705b2aa84317 100644 --- a/include/dt-bindings/clock/exynos5410.h +++ b/include/dt-bindings/clock/exynos5410.h @@ -50,6 +50,7 @@ #define CLK_PWM 279 #define CLK_MCT 315 #define CLK_RTC 317 +#define CLK_TMU 318 #define CLK_MMC0 351 #define CLK_MMC1 352 #define CLK_MMC2 353 -- cgit v1.2.3 From 59451e1233bd315c5379a631838a03d80e689581 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Thu, 5 May 2016 17:31:47 -0700 Subject: mtd: spi-nor: change return value of read/write Change the return value of spi-nor device read and write methods to allow returning amount of data transferred and errors as read(2)/write(2) does. Also, start handling positive returns in spi_nor_read(), since we want to convert drivers to start returning the read-length both via *retlen and the return code. (We don't need to do the same transition process for spi_nor_write(), since ->write() didn't used to have a return code at all.) Signed-off-by: Michal Suchanek Signed-off-by: Brian Norris Tested-by Cyrille Pitchen Acked-by: Michal Suchanek Tested-by: Michal Suchanek --- include/linux/mtd/spi-nor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 7f041bd88b82..34680a493156 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -173,9 +173,9 @@ struct spi_nor { int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - int (*read)(struct spi_nor *nor, loff_t from, + ssize_t (*read)(struct spi_nor *nor, loff_t from, size_t len, size_t *retlen, u_char *read_buf); - void (*write)(struct spi_nor *nor, loff_t to, + ssize_t (*write)(struct spi_nor *nor, loff_t to, size_t len, size_t *retlen, const u_char *write_buf); int (*erase)(struct spi_nor *nor, loff_t offs); -- cgit v1.2.3 From 2dd087b16946cf168f401526adf26afa771bb740 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Thu, 5 May 2016 17:31:53 -0700 Subject: mtd: spi-nor: stop passing around retlen Do not pass retlen to hardware driver read/write functions. Update it in spi-nor generic driver instead. Signed-off-by: Michal Suchanek Signed-off-by: Brian Norris Tested-by Cyrille Pitchen Acked-by: Michal Suchanek Tested-by: Michal Suchanek --- include/linux/mtd/spi-nor.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 34680a493156..c425c7b4c2a0 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -174,9 +174,9 @@ struct spi_nor { int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); ssize_t (*read)(struct spi_nor *nor, loff_t from, - size_t len, size_t *retlen, u_char *read_buf); + size_t len, u_char *read_buf); ssize_t (*write)(struct spi_nor *nor, loff_t to, - size_t len, size_t *retlen, const u_char *write_buf); + size_t len, const u_char *write_buf); int (*erase)(struct spi_nor *nor, loff_t offs); int (*flash_lock)(struct spi_nor *nor, loff_t ofs, uint64_t len); -- cgit v1.2.3 From 595d0b29463343c3be995d3948930b8231e5b8cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 31 May 2016 15:22:41 -0700 Subject: udp: avoid csum_partial() for validated skb In commit e6afc8ace6dd5 ("udp: remove headers from UDP packets before queueing"), udp_csum_pull_header() helper was added but missed fact that CHECKSUM_UNNECESSARY packets were now converted to CHECKSUM_NONE and skb->csum_valid was set to 1 for them. Since csum_partial() is quite expensive, even for 8-byte area, it is worth adding a test. We also can use skb->data instead of udp_hdr() as we are pulling UDP headers, as it is sightly faster. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/udp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/udp.h b/include/net/udp.h index ae07f375370d..8894d7144189 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -160,8 +160,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, static inline void udp_csum_pull_header(struct sk_buff *skb) { - if (skb->ip_summed == CHECKSUM_NONE) - skb->csum = csum_partial(udp_hdr(skb), sizeof(struct udphdr), + if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE) + skb->csum = csum_partial(skb->data, sizeof(struct udphdr), skb->csum); skb_pull_rcsum(skb, sizeof(struct udphdr)); UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); -- cgit v1.2.3 From 4528dd8ed477bf202bd33ee48d38d656672d37f8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 1 Jun 2016 11:45:49 +0200 Subject: dt-bindings: clock: Add watchdog and SSS clock IDs to Exynos5410 Add IDs for watchdog and Security SubSystem to Exynos5410. Use the same number as for Exynos5420 just in case in future these drivers were merged. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Javier Martinez Canillas Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5410.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5410.h b/include/dt-bindings/clock/exynos5410.h index 705b2aa84317..85b467b3a207 100644 --- a/include/dt-bindings/clock/exynos5410.h +++ b/include/dt-bindings/clock/exynos5410.h @@ -49,6 +49,7 @@ #define CLK_UART3 260 #define CLK_PWM 279 #define CLK_MCT 315 +#define CLK_WDT 316 #define CLK_RTC 317 #define CLK_TMU 318 #define CLK_MMC0 351 @@ -57,6 +58,7 @@ #define CLK_USBH20 365 #define CLK_USBD300 366 #define CLK_USBD301 367 +#define CLK_SSS 471 #define CLK_NR_CLKS 512 -- cgit v1.2.3 From 8cfc8ddc99df9509a46043b14af81f5c6a223eab Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 18 Feb 2016 22:04:22 +0800 Subject: pstore: add lzo/lz4 compression support Like zlib compression in pstore, this patch added lzo and lz4 compression support so that users can have more options and better compression ratio. The original code treats the compressed data together with the uncompressed ECC correction notice by using zlib decompress. The ECC correction notice is missing in the decompression process. The treatment also makes lzo and lz4 not working. So I treat them separately by using pstore_decompress() to treat the compressed data, and memcpy() to treat the uncompressed ECC correction notice. Signed-off-by: Geliang Tang Signed-off-by: Kees Cook --- include/linux/pstore.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index 831479f8df8f..899e95e84400 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -58,7 +58,8 @@ struct pstore_info { int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - bool *compressed, struct pstore_info *psi); + bool *compressed, ssize_t *ecc_notice_size, + struct pstore_info *psi); int (*write)(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, bool compressed, -- cgit v1.2.3 From e788892ba3cc71d385b75895f7a375fbc659ce86 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 2 Jun 2016 23:24:15 +0200 Subject: cpufreq: governor: Get rid of governor events The design of the cpufreq governor API is not very straightforward, as struct cpufreq_governor provides only one callback to be invoked from different code paths for different purposes. The purpose it is invoked for is determined by its second "event" argument, causing it to act as a "callback multiplexer" of sorts. Unfortunately, that leads to extra complexity in governors, some of which implement the ->governor() callback as a switch statement that simply checks the event argument and invokes a separate function to handle that specific event. That extra complexity can be eliminated by replacing the all-purpose ->governor() callback with a family of callbacks to carry out specific governor operations: initialization and exit, start and stop and policy limits updates. That also turns out to reduce the code size too, so do it. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 4e81e08db752..5bcda3e6aa9e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -455,18 +455,14 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, #define MIN_LATENCY_MULTIPLIER (20) #define TRANSITION_LATENCY_LIMIT (10 * 1000 * 1000) -/* Governor Events */ -#define CPUFREQ_GOV_START 1 -#define CPUFREQ_GOV_STOP 2 -#define CPUFREQ_GOV_LIMITS 3 -#define CPUFREQ_GOV_POLICY_INIT 4 -#define CPUFREQ_GOV_POLICY_EXIT 5 - struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; int initialized; - int (*governor) (struct cpufreq_policy *policy, - unsigned int event); + int (*init)(struct cpufreq_policy *policy); + void (*exit)(struct cpufreq_policy *policy); + int (*start)(struct cpufreq_policy *policy); + void (*stop)(struct cpufreq_policy *policy); + void (*limits)(struct cpufreq_policy *policy); ssize_t (*show_setspeed) (struct cpufreq_policy *policy, char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, -- cgit v1.2.3 From bf2be2de8493dd5f86d6e0f0d4eecb5810ad035b Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 18 May 2016 17:55:31 +0530 Subject: cpufreq: governor: Create cpufreq_policy_apply_limits() Create a new helper to avoid code duplication across governors. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 5bcda3e6aa9e..3be54a0b4373 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -489,6 +489,14 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor); struct cpufreq_governor *cpufreq_default_governor(void); struct cpufreq_governor *cpufreq_fallback_governor(void); +static inline void cpufreq_policy_apply_limits(struct cpufreq_policy *policy) +{ + if (policy->max < policy->cur) + __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); + else if (policy->min > policy->cur) + __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); +} + /* Governor attribute set */ struct gov_attr_set { struct kobject kobj; -- cgit v1.2.3 From 9a15fb2c797a15524e63eacb10bd6cd68a99e830 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 18 May 2016 22:59:49 +0200 Subject: cpufreq: Drop the 'initialized' field from struct cpufreq_governor The 'initialized' field in struct cpufreq_governor is only used by the conservative governor (as a usage counter) and the way that happens is far from straightforward and arguably incorrect. Namely, the value of 'initialized' is checked by cpufreq_dbs_governor_init() and cpufreq_dbs_governor_exit() and the results of those checks are passed (as the second argument) to the ->init() and ->exit() callbacks in struct dbs_governor. Those callbacks are only implemented by the ondemand and conservative governors and ondemand doesn't use their second argument at all. In turn, the conservative governor uses it to decide whether or not to either register or unregister a transition notifier. That whole mechanism is not only unnecessarily convoluted, but also racy, because the 'initialized' field of struct cpufreq_governor is updated in cpufreq_init_governor() and cpufreq_exit_governor() under policy->rwsem which doesn't help if one of these functions is run twice in parallel for different policies (which isn't impossible in principle), for example. Instead of it, add a proper usage counter to the conservative governor and update it from cs_init() and cs_exit() which is guaranteed to be non-racy, as those functions are only called under gov_dbs_data_mutex which is global. With that in place, drop the 'initialized' field from struct cpufreq_governor as it is not used any more. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 3be54a0b4373..fbd696edf5bd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -457,7 +457,6 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; - int initialized; int (*init)(struct cpufreq_policy *policy); void (*exit)(struct cpufreq_policy *policy); int (*start)(struct cpufreq_policy *policy); -- cgit v1.2.3 From 1aefc75b2449eb68a6fc3ca932e2a4ee353b748d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 31 May 2016 22:14:44 +0200 Subject: cpufreq: stats: Make the stats code non-modular The modularity of cpufreq_stats is quite problematic. First off, the usage of policy notifiers for the initialization and cleanup in the cpufreq_stats module is inherently racy with respect to CPU offline/online and the initialization and cleanup of the cpufreq driver. Second, fast frequency switching (used by the schedutil governor) cannot be enabled if any transition notifiers are registered, so if the cpufreq_stats module (that registers a transition notifier for updating transition statistics) is loaded, the schedutil governor cannot use fast frequency switching. On the other hand, allowing cpufreq_stats to be built as a module doesn't really add much value. Arguably, there's not much reason for that code to be modular at all. For the above reasons, make the cpufreq stats code non-modular, modify the core to invoke functions provided by that code directly and drop the notifiers from it. Make the stats sysfs attributes appear empty if fast frequency switching is enabled as the statistics will not be updated in that case anyway (and returning -EBUSY from those attributes breaks powertop). While at it, clean up Kconfig help for the CPU_FREQ_STAT and CPU_FREQ_STAT_DETAILS options. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index fbd696edf5bd..7ed93c310c08 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -185,6 +185,18 @@ static inline unsigned int cpufreq_quick_get_max(unsigned int cpu) static inline void disable_cpufreq(void) { } #endif +#ifdef CONFIG_CPU_FREQ_STAT +void cpufreq_stats_create_table(struct cpufreq_policy *policy); +void cpufreq_stats_free_table(struct cpufreq_policy *policy); +void cpufreq_stats_record_transition(struct cpufreq_policy *policy, + unsigned int new_freq); +#else +static inline void cpufreq_stats_create_table(struct cpufreq_policy *policy) { } +static inline void cpufreq_stats_free_table(struct cpufreq_policy *policy) { } +static inline void cpufreq_stats_record_transition(struct cpufreq_policy *policy, + unsigned int new_freq) { } +#endif /* CONFIG_CPU_FREQ_STAT */ + /********************************************************************* * CPUFREQ DRIVER INTERFACE * *********************************************************************/ -- cgit v1.2.3 From ccc12561926c0bef9a40865db93b926a0927e93f Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Fri, 20 May 2016 20:40:26 +0530 Subject: regmap: irq: Add support to call client specific pre/post interrupt service Regmap irq implements the generic interrupt service routine which is common for most of devices. Some devices, like MAX77620, MAX20024 needs the special handling before and after servicing the interrupt as generic. For the example, MAX77620 programming guidelines for interrupt servicing says: 1. When interrupt occurs from PMIC, mask the PMIC interrupt by setting GLBLM. 2. Read IRQTOP and service the interrupt accordingly. 3. Once all interrupts has been checked and serviced, the interrupt service routine un-masks the hardware interrupt line by clearing GLBLM. The step (2) is implemented in regmap irq as generic routine. For step (1) and (3), add callbacks from regmap irq to client driver to handle chip specific configurations. Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 3dc08ce15426..a0bfe481f9ab 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -851,6 +851,12 @@ struct regmap_irq { * @num_type_reg: Number of type registers. * @type_reg_stride: Stride to use for chips where type registers are not * contiguous. + * @handle_pre_irq: Driver specific callback to handle interrupt from device + * before regmap_irq_handler process the interrupts. + * @handle_post_irq: Driver specific callback to handle interrupt from device + * after handling the interrupts in regmap_irq_handler(). + * @irq_drv_data: Driver specific IRQ data which is passed as parameter when + * driver specific pre/post interrupt handler is called. */ struct regmap_irq_chip { const char *name; @@ -877,6 +883,10 @@ struct regmap_irq_chip { int num_type_reg; unsigned int type_reg_stride; + + int (*handle_pre_irq)(void *irq_drv_data); + int (*handle_post_irq)(void *irq_drv_data); + void *irq_drv_data; }; struct regmap_irq_chip_data; -- cgit v1.2.3 From 351a4dedb34cbeb9f747f0e2309e891b6fb906cb Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Thu, 2 Jun 2016 10:23:29 +0300 Subject: qed: Utilize FW 8.10.3.0 The New QED firmware contains several fixes, including: - Wrong classification of packets in 4-port devices. - Anti-spoof interoperability with encapsulated packets. - Tx-switching of encapsulated packets. It also slightly improves Tx performance of the device. In addition, this firmware contains the necessary logic for supporting iscsi & rdma, for which we plan on pushing protocol drivers in the imminent future. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 205 +++++++++++++++++++++++++++++------------ include/linux/qed/eth_common.h | 124 +++++++++++++++---------- include/linux/qed/qed_eth_if.h | 1 + 3 files changed, 222 insertions(+), 108 deletions(-) (limited to 'include') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 3f14c7efe68f..285189a5ea6d 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -13,9 +13,19 @@ #define X_FINAL_CLEANUP_AGG_INT 1 +/* Queue Zone sizes in bytes */ +#define TSTORM_QZONE_SIZE 8 +#define MSTORM_QZONE_SIZE 0 +#define USTORM_QZONE_SIZE 8 +#define XSTORM_QZONE_SIZE 8 +#define YSTORM_QZONE_SIZE 0 +#define PSTORM_QZONE_SIZE 0 + +#define ETH_MAX_NUM_RX_QUEUES_PER_VF 16 + #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 7 -#define FW_REVISION_VERSION 3 +#define FW_MINOR_VERSION 10 +#define FW_REVISION_VERSION 5 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -97,45 +107,86 @@ #define DQ_XCM_AGG_VAL_SEL_REG6 7 /* XCM agg val selection */ -#define DQ_XCM_ETH_EDPM_NUM_BDS_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD2 -#define DQ_XCM_ETH_TX_BD_CONS_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD3 -#define DQ_XCM_CORE_TX_BD_CONS_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD3 -#define DQ_XCM_ETH_TX_BD_PROD_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD4 -#define DQ_XCM_CORE_TX_BD_PROD_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD4 -#define DQ_XCM_CORE_SPQ_PROD_CMD \ - DQ_XCM_AGG_VAL_SEL_WORD4 -#define DQ_XCM_ETH_GO_TO_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD5 +#define DQ_XCM_CORE_TX_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_CORE_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_CORE_SPQ_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_ETH_EDPM_NUM_BDS_CMD DQ_XCM_AGG_VAL_SEL_WORD2 +#define DQ_XCM_ETH_TX_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD3 +#define DQ_XCM_ETH_TX_BD_PROD_CMD DQ_XCM_AGG_VAL_SEL_WORD4 +#define DQ_XCM_ETH_GO_TO_BD_CONS_CMD DQ_XCM_AGG_VAL_SEL_WORD5 + +/* UCM agg val selection (HW) */ +#define DQ_UCM_AGG_VAL_SEL_WORD0 0 +#define DQ_UCM_AGG_VAL_SEL_WORD1 1 +#define DQ_UCM_AGG_VAL_SEL_WORD2 2 +#define DQ_UCM_AGG_VAL_SEL_WORD3 3 +#define DQ_UCM_AGG_VAL_SEL_REG0 4 +#define DQ_UCM_AGG_VAL_SEL_REG1 5 +#define DQ_UCM_AGG_VAL_SEL_REG2 6 +#define DQ_UCM_AGG_VAL_SEL_REG3 7 + +/* UCM agg val selection (FW) */ +#define DQ_UCM_ETH_PMD_TX_CONS_CMD DQ_UCM_AGG_VAL_SEL_WORD2 +#define DQ_UCM_ETH_PMD_RX_CONS_CMD DQ_UCM_AGG_VAL_SEL_WORD3 +#define DQ_UCM_ROCE_CQ_CONS_CMD DQ_UCM_AGG_VAL_SEL_REG0 +#define DQ_UCM_ROCE_CQ_PROD_CMD DQ_UCM_AGG_VAL_SEL_REG2 + +/* TCM agg val selection (HW) */ +#define DQ_TCM_AGG_VAL_SEL_WORD0 0 +#define DQ_TCM_AGG_VAL_SEL_WORD1 1 +#define DQ_TCM_AGG_VAL_SEL_WORD2 2 +#define DQ_TCM_AGG_VAL_SEL_WORD3 3 +#define DQ_TCM_AGG_VAL_SEL_REG1 4 +#define DQ_TCM_AGG_VAL_SEL_REG2 5 +#define DQ_TCM_AGG_VAL_SEL_REG6 6 +#define DQ_TCM_AGG_VAL_SEL_REG9 7 + +/* TCM agg val selection (FW) */ +#define DQ_TCM_L2B_BD_PROD_CMD \ + DQ_TCM_AGG_VAL_SEL_WORD1 +#define DQ_TCM_ROCE_RQ_PROD_CMD \ + DQ_TCM_AGG_VAL_SEL_WORD0 /* XCM agg counter flag selection */ -#define DQ_XCM_AGG_FLG_SHIFT_BIT14 0 -#define DQ_XCM_AGG_FLG_SHIFT_BIT15 1 -#define DQ_XCM_AGG_FLG_SHIFT_CF12 2 -#define DQ_XCM_AGG_FLG_SHIFT_CF13 3 -#define DQ_XCM_AGG_FLG_SHIFT_CF18 4 -#define DQ_XCM_AGG_FLG_SHIFT_CF19 5 -#define DQ_XCM_AGG_FLG_SHIFT_CF22 6 -#define DQ_XCM_AGG_FLG_SHIFT_CF23 7 +#define DQ_XCM_AGG_FLG_SHIFT_BIT14 0 +#define DQ_XCM_AGG_FLG_SHIFT_BIT15 1 +#define DQ_XCM_AGG_FLG_SHIFT_CF12 2 +#define DQ_XCM_AGG_FLG_SHIFT_CF13 3 +#define DQ_XCM_AGG_FLG_SHIFT_CF18 4 +#define DQ_XCM_AGG_FLG_SHIFT_CF19 5 +#define DQ_XCM_AGG_FLG_SHIFT_CF22 6 +#define DQ_XCM_AGG_FLG_SHIFT_CF23 7 /* XCM agg counter flag selection */ -#define DQ_XCM_ETH_DQ_CF_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF18) -#define DQ_XCM_CORE_DQ_CF_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF18) -#define DQ_XCM_ETH_TERMINATE_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF19) -#define DQ_XCM_CORE_TERMINATE_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF19) -#define DQ_XCM_ETH_SLOW_PATH_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF22) -#define DQ_XCM_CORE_SLOW_PATH_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF22) -#define DQ_XCM_ETH_TPH_EN_CMD (1 << \ - DQ_XCM_AGG_FLG_SHIFT_CF23) +#define DQ_XCM_CORE_DQ_CF_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_CORE_TERMINATE_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_CORE_SLOW_PATH_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_ETH_DQ_CF_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF18) +#define DQ_XCM_ETH_TERMINATE_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF19) +#define DQ_XCM_ETH_SLOW_PATH_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF22) +#define DQ_XCM_ETH_TPH_EN_CMD (1 << DQ_XCM_AGG_FLG_SHIFT_CF23) + +/* UCM agg counter flag selection (HW) */ +#define DQ_UCM_AGG_FLG_SHIFT_CF0 0 +#define DQ_UCM_AGG_FLG_SHIFT_CF1 1 +#define DQ_UCM_AGG_FLG_SHIFT_CF3 2 +#define DQ_UCM_AGG_FLG_SHIFT_CF4 3 +#define DQ_UCM_AGG_FLG_SHIFT_CF5 4 +#define DQ_UCM_AGG_FLG_SHIFT_CF6 5 +#define DQ_UCM_AGG_FLG_SHIFT_RULE0EN 6 +#define DQ_UCM_AGG_FLG_SHIFT_RULE1EN 7 + +/* UCM agg counter flag selection (FW) */ +#define DQ_UCM_ETH_PMD_TX_ARM_CMD (1 << DQ_UCM_AGG_FLG_SHIFT_CF4) +#define DQ_UCM_ETH_PMD_RX_ARM_CMD (1 << DQ_UCM_AGG_FLG_SHIFT_CF5) + +#define DQ_REGION_SHIFT (12) + +/* DPM */ +#define DQ_DPM_WQE_BUFF_SIZE (320) + +/* Conn type ranges */ +#define DQ_CONN_TYPE_RANGE_SHIFT (4) /*****************/ /* QM CONSTANTS */ @@ -282,8 +333,6 @@ (PXP_EXTERNAL_BAR_GLOBAL_WINDOW_START + \ PXP_EXTERNAL_BAR_GLOBAL_WINDOW_LENGTH - 1) -#define PXP_ILT_PAGE_SIZE_NUM_BITS_MIN 12 -#define PXP_ILT_BLOCK_FACTOR_MULTIPLIER 1024 #define PXP_VF_BAR0_START_IGU 0 #define PXP_VF_BAR0_IGU_LENGTH 0x3000 @@ -342,6 +391,9 @@ #define PXP_VF_BAR0_GRC_WINDOW_LENGTH 32 +#define PXP_ILT_PAGE_SIZE_NUM_BITS_MIN 12 +#define PXP_ILT_BLOCK_FACTOR_MULTIPLIER 1024 + /* ILT Records */ #define PXP_NUM_ILT_RECORDS_BB 7600 #define PXP_NUM_ILT_RECORDS_K2 11000 @@ -379,6 +431,38 @@ struct async_data { u8 fw_debug_param; }; +struct coalescing_timeset { + u8 value; +#define COALESCING_TIMESET_TIMESET_MASK 0x7F +#define COALESCING_TIMESET_TIMESET_SHIFT 0 +#define COALESCING_TIMESET_VALID_MASK 0x1 +#define COALESCING_TIMESET_VALID_SHIFT 7 +}; + +struct common_prs_pf_msg_info { + __le32 value; +#define COMMON_PRS_PF_MSG_INFO_NPAR_DEFAULT_PF_MASK 0x1 +#define COMMON_PRS_PF_MSG_INFO_NPAR_DEFAULT_PF_SHIFT 0 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_1_MASK 0x1 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_1_SHIFT 1 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_2_MASK 0x1 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_2_SHIFT 2 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_3_MASK 0x1 +#define COMMON_PRS_PF_MSG_INFO_FW_DEBUG_3_SHIFT 3 +#define COMMON_PRS_PF_MSG_INFO_RESERVED_MASK 0xFFFFFFF +#define COMMON_PRS_PF_MSG_INFO_RESERVED_SHIFT 4 +}; + +struct common_queue_zone { + __le16 ring_drv_data_consumer; + __le16 reserved; +}; + +struct eth_rx_prod_data { + __le16 bd_prod; + __le16 cqe_prod; +}; + struct regpair { __le32 lo; __le32 hi; @@ -388,11 +472,23 @@ struct vf_pf_channel_eqe_data { struct regpair msg_addr; }; +struct malicious_vf_eqe_data { + u8 vf_id; + u8 err_id; + __le16 reserved[3]; +}; + +struct initial_cleanup_eqe_data { + u8 vf_id; + u8 reserved[7]; +}; + /* Event Data Union */ union event_ring_data { - u8 bytes[8]; - struct vf_pf_channel_eqe_data vf_pf_channel; - struct async_data async_info; + u8 bytes[8]; + struct vf_pf_channel_eqe_data vf_pf_channel; + struct malicious_vf_eqe_data malicious_vf; + struct initial_cleanup_eqe_data vf_init_cleanup; }; /* Event Ring Entry */ @@ -433,6 +529,16 @@ enum protocol_type { MAX_PROTOCOL_TYPE }; +struct ustorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + u8 reserved[3]; +}; + +struct ustorm_queue_zone { + struct ustorm_eth_queue_zone eth; + struct common_queue_zone common; +}; + /* status block structure */ struct cau_pi_entry { u32 prod; @@ -683,19 +789,4 @@ struct status_block { #define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 }; -struct tunnel_parsing_flags { - u8 flags; -#define TUNNEL_PARSING_FLAGS_TYPE_MASK 0x3 -#define TUNNEL_PARSING_FLAGS_TYPE_SHIFT 0 -#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_MASK 0x1 -#define TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_SHIFT 2 -#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_MASK 0x3 -#define TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_SHIFT 3 -#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_MASK 0x1 -#define TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_SHIFT 5 -#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK 0x1 -#define TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT 6 -#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_MASK 0x1 -#define TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_SHIFT 7 -}; #endif /* __COMMON_HSI__ */ diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index 092cb0c1afcb..b5ebc697d05f 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -12,6 +12,8 @@ /********************/ /* ETH FW CONSTANTS */ /********************/ +#define ETH_HSI_VER_MAJOR 3 +#define ETH_HSI_VER_MINOR 0 #define ETH_CACHE_LINE_SIZE 64 #define ETH_MAX_RAMROD_PER_CON 8 @@ -57,19 +59,6 @@ #define ETH_TPA_CQE_CONT_LEN_LIST_SIZE 6 #define ETH_TPA_CQE_END_LEN_LIST_SIZE 4 -/* Queue Zone sizes */ -#define TSTORM_QZONE_SIZE 0 -#define MSTORM_QZONE_SIZE sizeof(struct mstorm_eth_queue_zone) -#define USTORM_QZONE_SIZE sizeof(struct ustorm_eth_queue_zone) -#define XSTORM_QZONE_SIZE 0 -#define YSTORM_QZONE_SIZE sizeof(struct ystorm_eth_queue_zone) -#define PSTORM_QZONE_SIZE 0 - -/* Interrupt coalescing TimeSet */ -struct coalescing_timeset { - u8 timeset; - u8 valid; -}; struct eth_tx_1st_bd_flags { u8 bitfields; @@ -97,12 +86,12 @@ struct eth_tx_data_1st_bd { u8 nbds; struct eth_tx_1st_bd_flags bd_flags; __le16 bitfields; -#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_MASK 0x1 -#define ETH_TX_DATA_1ST_BD_TUNN_CFG_OVERRIDE_SHIFT 0 +#define ETH_TX_DATA_1ST_BD_TUNN_FLAG_MASK 0x1 +#define ETH_TX_DATA_1ST_BD_TUNN_FLAG_SHIFT 0 #define ETH_TX_DATA_1ST_BD_RESERVED0_MASK 0x1 #define ETH_TX_DATA_1ST_BD_RESERVED0_SHIFT 1 -#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_MASK 0x3FFF -#define ETH_TX_DATA_1ST_BD_FW_USE_ONLY_SHIFT 2 +#define ETH_TX_DATA_1ST_BD_PKT_LEN_MASK 0x3FFF +#define ETH_TX_DATA_1ST_BD_PKT_LEN_SHIFT 2 }; /* The parsing information data for the second tx bd of a given packet. */ @@ -136,28 +125,51 @@ struct eth_tx_data_2nd_bd { #define ETH_TX_DATA_2ND_BD_RESERVED0_SHIFT 13 }; +struct eth_fast_path_cqe_fw_debug { + u8 reserved0; + u8 reserved1; + __le16 reserved2; +}; + +/* tunneling parsing flags */ +struct eth_tunnel_parsing_flags { + u8 flags; +#define ETH_TUNNEL_PARSING_FLAGS_TYPE_MASK 0x3 +#define ETH_TUNNEL_PARSING_FLAGS_TYPE_SHIFT 0 +#define ETH_TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_MASK 0x1 +#define ETH_TUNNEL_PARSING_FLAGS_TENNANT_ID_EXIST_SHIFT 2 +#define ETH_TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_MASK 0x3 +#define ETH_TUNNEL_PARSING_FLAGS_NEXT_PROTOCOL_SHIFT 3 +#define ETH_TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_MASK 0x1 +#define ETH_TUNNEL_PARSING_FLAGS_FIRSTHDRIPMATCH_SHIFT 5 +#define ETH_TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_MASK 0x1 +#define ETH_TUNNEL_PARSING_FLAGS_IPV4_FRAGMENT_SHIFT 6 +#define ETH_TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_MASK 0x1 +#define ETH_TUNNEL_PARSING_FLAGS_IPV4_OPTIONS_SHIFT 7 +}; + /* Regular ETH Rx FP CQE. */ struct eth_fast_path_rx_reg_cqe { - u8 type; - u8 bitfields; + u8 type; + u8 bitfields; #define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_MASK 0x7 #define ETH_FAST_PATH_RX_REG_CQE_RSS_HASH_TYPE_SHIFT 0 #define ETH_FAST_PATH_RX_REG_CQE_TC_MASK 0xF #define ETH_FAST_PATH_RX_REG_CQE_TC_SHIFT 3 #define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_MASK 0x1 #define ETH_FAST_PATH_RX_REG_CQE_RESERVED0_SHIFT 7 - __le16 pkt_len; - struct parsing_and_err_flags pars_flags; - __le16 vlan_tag; - __le32 rss_hash; - __le16 len_on_first_bd; - u8 placement_offset; - struct tunnel_parsing_flags tunnel_pars_flags; - u8 bd_num; - u8 reserved[7]; - u32 fw_debug; - u8 reserved1[3]; - u8 flags; + __le16 pkt_len; + struct parsing_and_err_flags pars_flags; + __le16 vlan_tag; + __le32 rss_hash; + __le16 len_on_first_bd; + u8 placement_offset; + struct eth_tunnel_parsing_flags tunnel_pars_flags; + u8 bd_num; + u8 reserved[7]; + struct eth_fast_path_cqe_fw_debug fw_debug; + u8 reserved1[3]; + u8 flags; #define ETH_FAST_PATH_RX_REG_CQE_VALID_MASK 0x1 #define ETH_FAST_PATH_RX_REG_CQE_VALID_SHIFT 0 #define ETH_FAST_PATH_RX_REG_CQE_VALID_TOGGLE_MASK 0x1 @@ -207,11 +219,11 @@ struct eth_fast_path_rx_tpa_start_cqe { __le32 rss_hash; __le16 len_on_first_bd; u8 placement_offset; - struct tunnel_parsing_flags tunnel_pars_flags; + struct eth_tunnel_parsing_flags tunnel_pars_flags; u8 tpa_agg_index; u8 header_len; __le16 ext_bd_len_list[ETH_TPA_CQE_START_LEN_LIST_SIZE]; - u32 fw_debug; + struct eth_fast_path_cqe_fw_debug fw_debug; }; /* The L4 pseudo checksum mode for Ethernet */ @@ -264,12 +276,25 @@ enum eth_rx_cqe_type { MAX_ETH_RX_CQE_TYPE }; -/* ETH Rx producers data */ -struct eth_rx_prod_data { - __le16 bd_prod; - __le16 cqe_prod; - __le16 reserved; - __le16 reserved1; +enum eth_rx_tunn_type { + ETH_RX_NO_TUNN, + ETH_RX_TUNN_GENEVE, + ETH_RX_TUNN_GRE, + ETH_RX_TUNN_VXLAN, + MAX_ETH_RX_TUNN_TYPE +}; + +/* Aggregation end reason. */ +enum eth_tpa_end_reason { + ETH_AGG_END_UNUSED, + ETH_AGG_END_SP_UPDATE, + ETH_AGG_END_MAX_LEN, + ETH_AGG_END_LAST_SEG, + ETH_AGG_END_TIMEOUT, + ETH_AGG_END_NOT_CONSISTENT, + ETH_AGG_END_OUT_OF_ORDER, + ETH_AGG_END_NON_TPA_SEG, + MAX_ETH_TPA_END_REASON }; /* The first tx bd of a given packet */ @@ -337,21 +362,18 @@ union eth_tx_bd_types { }; /* Mstorm Queue Zone */ -struct mstorm_eth_queue_zone { - struct eth_rx_prod_data rx_producers; - __le32 reserved[2]; -}; - -/* Ustorm Queue Zone */ -struct ustorm_eth_queue_zone { - struct coalescing_timeset int_coalescing_timeset; - __le16 reserved[3]; +enum eth_tx_tunn_type { + ETH_TX_TUNN_GENEVE, + ETH_TX_TUNN_TTAG, + ETH_TX_TUNN_GRE, + ETH_TX_TUNN_VXLAN, + MAX_ETH_TX_TUNN_TYPE }; /* Ystorm Queue Zone */ -struct ystorm_eth_queue_zone { - struct coalescing_timeset int_coalescing_timeset; - __le16 reserved[3]; +struct xstorm_eth_queue_zone { + struct coalescing_timeset int_coalescing_timeset; + u8 reserved[7]; }; /* ETH doorbell data */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 6ae8cb4a61d3..f8ff71126d9e 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -113,6 +113,7 @@ struct qed_queue_start_common_params { u8 vport_id; u16 sb; u16 sb_idx; + u16 vf_qid; }; struct qed_tunn_params { -- 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 +++ 1 file changed, 3 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); -- 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 ++++++ 1 file changed, 6 insertions(+) (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 */ }; -- 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 --- include/linux/perf_event.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') 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 3f03396918962b2f8b888d02b23cd1e0c88bf5e5 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 24 May 2016 09:16:06 +0200 Subject: media: vb2-dma-contig: add helper for setting dma max seg size Add a helper function for device drivers to set DMA's max_seg_size. Setting it to largest possible value lets DMA-mapping API always create contiguous mappings in DMA address space. This is essential for all devices, which use dma-contig videobuf2 memory allocator and shared buffers. Till now, the only case when vb2-dma-contig really 'worked' was a case where userspace provided USERPTR buffer, which was in fact mmaped contiguous buffer from the other v4l2/drm device. Also DMABUF made of contiguous buffer worked only when its exporter did not split it into several chunks in the scatter-list. Any other buffer failed, regardless of the arch/platform used and the presence of the IOMMU of the device bus. This patch provides interface to fix this issue. Signed-off-by: Marek Szyprowski Signed-off-by: Sylwester Nawrocki --- include/media/videobuf2-dma-contig.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/videobuf2-dma-contig.h b/include/media/videobuf2-dma-contig.h index 2087c9a68be3..f7dc8401817e 100644 --- a/include/media/videobuf2-dma-contig.h +++ b/include/media/videobuf2-dma-contig.h @@ -35,6 +35,8 @@ static inline void *vb2_dma_contig_init_ctx(struct device *dev) } void vb2_dma_contig_cleanup_ctx(void *alloc_ctx); +int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size); +void vb2_dma_contig_clear_max_seg_size(struct device *dev); extern const struct vb2_mem_ops vb2_dma_contig_memops; -- cgit v1.2.3 From 59ce4039727ef408769ab0e1263ece893abe22bb Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 24 May 2016 15:31:24 +0200 Subject: of: reserved_mem: add support for using more than one region for given device This patch allows device drivers to initialize more than one reserved memory region assigned to given device. When driver needs to use more than one reserved memory region, it should allocate child devices and initialize regions by index for each of its child devices. Signed-off-by: Marek Szyprowski Acked-by: Rob Herring Signed-off-by: Sylwester Nawrocki --- include/linux/of_reserved_mem.h | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index ad2f67054372..1779cda99ef7 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -1,7 +1,8 @@ #ifndef __OF_RESERVED_MEM_H #define __OF_RESERVED_MEM_H -struct device; +#include + struct of_phandle_args; struct reserved_mem_ops; @@ -28,14 +29,17 @@ typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem); _OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn) #ifdef CONFIG_OF_RESERVED_MEM -int of_reserved_mem_device_init(struct device *dev); + +int of_reserved_mem_device_init_by_idx(struct device *dev, + struct device_node *np, int idx); void of_reserved_mem_device_release(struct device *dev); void fdt_init_reserved_mem(void); void fdt_reserved_mem_save_node(unsigned long node, const char *uname, phys_addr_t base, phys_addr_t size); #else -static inline int of_reserved_mem_device_init(struct device *dev) +static inline int of_reserved_mem_device_init_by_idx(struct device *dev, + struct device_node *np, int idx) { return -ENOSYS; } @@ -46,4 +50,19 @@ static inline void fdt_reserved_mem_save_node(unsigned long node, const char *uname, phys_addr_t base, phys_addr_t size) { } #endif +/** + * of_reserved_mem_device_init() - assign reserved memory region to given device + * @dev: Pointer to the device to configure + * + * This function assigns respective DMA-mapping operations based on the first + * reserved memory region specified by 'memory-region' property in device tree + * node of the given device. + * + * Returns error code or zero on success. + */ +static inline int of_reserved_mem_device_init(struct device *dev) +{ + return of_reserved_mem_device_init_by_idx(dev, dev->of_node, 0); +} + #endif /* __OF_RESERVED_MEM_H */ -- 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 5ab788d7383289bfc141ab357767bc6c11bbf77f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 May 2016 20:57:50 +0200 Subject: rtc: cmos: move mc146818rtc code out of asm-generic/rtc.h Drivers should not really include stuff from asm-generic directly, and the PC-style cmos rtc driver does this in order to reuse the mc146818 implementation of get_rtc_time/set_rtc_time rather than the architecture specific one for the architecture it gets built for. To make it more obvious what is going on, this moves and renames the two functions into include/linux/mc146818rtc.h, which holds the other mc146818 specific code. Ideally it would be in a .c file, but that would require extra infrastructure as the functions are called by multiple drivers with conflicting dependencies. With this change, the asm-generic/rtc.h header also becomes much more generic, so it can be reused more easily across any architecture that still relies on the genrtc driver. The only caller of the internal __get_rtc_time/__set_rtc_time functions is in arch/alpha/kernel/rtc.c, and we just change those over to the new naming. Signed-off-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Alexandre Belloni --- include/asm-generic/rtc.h | 206 ++------------------------------------------ include/linux/mc146818rtc.h | 194 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 199 insertions(+), 201 deletions(-) (limited to 'include') diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h index 4e3b6558331e..4fcff22cd707 100644 --- a/include/asm-generic/rtc.h +++ b/include/asm-generic/rtc.h @@ -12,12 +12,12 @@ #ifndef __ASM_RTC_H__ #define __ASM_RTC_H__ -#include #include -#include -#include -#ifdef CONFIG_ACPI -#include + +#ifndef get_rtc_time +#include +#define get_rtc_time mc146818_get_time +#define set_rtc_time mc146818_set_time #endif #define RTC_PIE 0x40 /* periodic interrupt enable */ @@ -31,202 +31,6 @@ #define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ #define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ -/* - * Returns true if a clock update is in progress - */ -static inline unsigned char rtc_is_updating(void) -{ - unsigned char uip; - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); - spin_unlock_irqrestore(&rtc_lock, flags); - return uip; -} - -static inline unsigned int __get_rtc_time(struct rtc_time *time) -{ - unsigned char ctrl; - unsigned long flags; - unsigned char century = 0; - -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_year; -#endif - - /* - * read RTC once any update in progress is done. The update - * can take just over 2ms. We wait 20ms. There is no need to - * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. - * If you need to know *exactly* when a second has started, enable - * periodic update complete interrupts, (via ioctl) and then - * immediately read /dev/rtc which will block until you get the IRQ. - * Once the read clears, read the RTC time (again via ioctl). Easy. - */ - if (rtc_is_updating()) - mdelay(20); - - /* - * Only the values that we read from the RTC are set. We leave - * tm_wday, tm_yday and tm_isdst untouched. Even though the - * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated - * by the RTC when initially set to a non-zero value. - */ - spin_lock_irqsave(&rtc_lock, flags); - time->tm_sec = CMOS_READ(RTC_SECONDS); - time->tm_min = CMOS_READ(RTC_MINUTES); - time->tm_hour = CMOS_READ(RTC_HOURS); - time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); - time->tm_mon = CMOS_READ(RTC_MONTH); - time->tm_year = CMOS_READ(RTC_YEAR); -#ifdef CONFIG_MACH_DECSTATION - real_year = CMOS_READ(RTC_DEC_YEAR); -#endif -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - ctrl = CMOS_READ(RTC_CONTROL); - spin_unlock_irqrestore(&rtc_lock, flags); - - if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - time->tm_sec = bcd2bin(time->tm_sec); - time->tm_min = bcd2bin(time->tm_min); - time->tm_hour = bcd2bin(time->tm_hour); - time->tm_mday = bcd2bin(time->tm_mday); - time->tm_mon = bcd2bin(time->tm_mon); - time->tm_year = bcd2bin(time->tm_year); - century = bcd2bin(century); - } - -#ifdef CONFIG_MACH_DECSTATION - time->tm_year += real_year - 72; -#endif - - if (century) - time->tm_year += (century - 19) * 100; - - /* - * Account for differences between how the RTC uses the values - * and how they are defined in a struct rtc_time; - */ - if (time->tm_year <= 69) - time->tm_year += 100; - - time->tm_mon--; - - return RTC_24H; -} - -#ifndef get_rtc_time -#define get_rtc_time __get_rtc_time -#endif - -/* Set the current date and time in the real time clock. */ -static inline int __set_rtc_time(struct rtc_time *time) -{ - unsigned long flags; - unsigned char mon, day, hrs, min, sec; - unsigned char save_control, save_freq_select; - unsigned int yrs; -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_yrs, leap_yr; -#endif - unsigned char century = 0; - - yrs = time->tm_year; - mon = time->tm_mon + 1; /* tm_mon starts at zero */ - day = time->tm_mday; - hrs = time->tm_hour; - min = time->tm_min; - sec = time->tm_sec; - - if (yrs > 255) /* They are unsigned */ - return -EINVAL; - - spin_lock_irqsave(&rtc_lock, flags); -#ifdef CONFIG_MACH_DECSTATION - real_yrs = yrs; - leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || - !((yrs + 1900) % 400)); - yrs = 72; - - /* - * We want to keep the year set to 73 until March - * for non-leap years, so that Feb, 29th is handled - * correctly. - */ - if (!leap_yr && mon < 3) { - real_yrs--; - yrs = 73; - } -#endif - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) { - century = (yrs + 1900) / 100; - yrs %= 100; - } -#endif - - /* These limits and adjustments are independent of - * whether the chip is in binary mode or not. - */ - if (yrs > 169) { - spin_unlock_irqrestore(&rtc_lock, flags); - return -EINVAL; - } - - if (yrs >= 100) - yrs -= 100; - - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) - || RTC_ALWAYS_BCD) { - sec = bin2bcd(sec); - min = bin2bcd(min); - hrs = bin2bcd(hrs); - day = bin2bcd(day); - mon = bin2bcd(mon); - yrs = bin2bcd(yrs); - century = bin2bcd(century); - } - - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - -#ifdef CONFIG_MACH_DECSTATION - CMOS_WRITE(real_yrs, RTC_DEC_YEAR); -#endif - CMOS_WRITE(yrs, RTC_YEAR); - CMOS_WRITE(mon, RTC_MONTH); - CMOS_WRITE(day, RTC_DAY_OF_MONTH); - CMOS_WRITE(hrs, RTC_HOURS); - CMOS_WRITE(min, RTC_MINUTES); - CMOS_WRITE(sec, RTC_SECONDS); -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - CMOS_WRITE(century, acpi_gbl_FADT.century); -#endif - - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - spin_unlock_irqrestore(&rtc_lock, flags); - - return 0; -} - -#ifndef set_rtc_time -#define set_rtc_time __set_rtc_time -#endif - static inline unsigned int get_rtc_ss(void) { struct rtc_time h; diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 433e0c74d643..e9e346b37846 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -14,6 +14,12 @@ #include #include /* get the user-level API */ #include /* register access macros */ +#include +#include + +#ifdef CONFIG_ACPI +#include +#endif #ifdef __KERNEL__ #include /* spinlock_t */ @@ -120,4 +126,192 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ +/* + * Returns true if a clock update is in progress + */ +static inline unsigned char mc146818_is_updating(void) +{ + unsigned char uip; + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); + uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); + spin_unlock_irqrestore(&rtc_lock, flags); + return uip; +} + +static inline unsigned int mc146818_get_time(struct rtc_time *time) +{ + unsigned char ctrl; + unsigned long flags; + unsigned char century = 0; + +#ifdef CONFIG_MACH_DECSTATION + unsigned int real_year; +#endif + + /* + * read RTC once any update in progress is done. The update + * can take just over 2ms. We wait 20ms. There is no need to + * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. + * If you need to know *exactly* when a second has started, enable + * periodic update complete interrupts, (via ioctl) and then + * immediately read /dev/rtc which will block until you get the IRQ. + * Once the read clears, read the RTC time (again via ioctl). Easy. + */ + if (mc146818_is_updating()) + mdelay(20); + + /* + * Only the values that we read from the RTC are set. We leave + * tm_wday, tm_yday and tm_isdst untouched. Even though the + * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated + * by the RTC when initially set to a non-zero value. + */ + spin_lock_irqsave(&rtc_lock, flags); + time->tm_sec = CMOS_READ(RTC_SECONDS); + time->tm_min = CMOS_READ(RTC_MINUTES); + time->tm_hour = CMOS_READ(RTC_HOURS); + time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); + time->tm_mon = CMOS_READ(RTC_MONTH); + time->tm_year = CMOS_READ(RTC_YEAR); +#ifdef CONFIG_MACH_DECSTATION + real_year = CMOS_READ(RTC_DEC_YEAR); +#endif +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) + century = CMOS_READ(acpi_gbl_FADT.century); +#endif + ctrl = CMOS_READ(RTC_CONTROL); + spin_unlock_irqrestore(&rtc_lock, flags); + + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + { + time->tm_sec = bcd2bin(time->tm_sec); + time->tm_min = bcd2bin(time->tm_min); + time->tm_hour = bcd2bin(time->tm_hour); + time->tm_mday = bcd2bin(time->tm_mday); + time->tm_mon = bcd2bin(time->tm_mon); + time->tm_year = bcd2bin(time->tm_year); + century = bcd2bin(century); + } + +#ifdef CONFIG_MACH_DECSTATION + time->tm_year += real_year - 72; +#endif + + if (century) + time->tm_year += (century - 19) * 100; + + /* + * Account for differences between how the RTC uses the values + * and how they are defined in a struct rtc_time; + */ + if (time->tm_year <= 69) + time->tm_year += 100; + + time->tm_mon--; + + return RTC_24H; +} + +/* Set the current date and time in the real time clock. */ +static inline int mc146818_set_time(struct rtc_time *time) +{ + unsigned long flags; + unsigned char mon, day, hrs, min, sec; + unsigned char save_control, save_freq_select; + unsigned int yrs; +#ifdef CONFIG_MACH_DECSTATION + unsigned int real_yrs, leap_yr; +#endif + unsigned char century = 0; + + yrs = time->tm_year; + mon = time->tm_mon + 1; /* tm_mon starts at zero */ + day = time->tm_mday; + hrs = time->tm_hour; + min = time->tm_min; + sec = time->tm_sec; + + if (yrs > 255) /* They are unsigned */ + return -EINVAL; + + spin_lock_irqsave(&rtc_lock, flags); +#ifdef CONFIG_MACH_DECSTATION + real_yrs = yrs; + leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || + !((yrs + 1900) % 400)); + yrs = 72; + + /* + * We want to keep the year set to 73 until March + * for non-leap years, so that Feb, 29th is handled + * correctly. + */ + if (!leap_yr && mon < 3) { + real_yrs--; + yrs = 73; + } +#endif + +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) { + century = (yrs + 1900) / 100; + yrs %= 100; + } +#endif + + /* These limits and adjustments are independent of + * whether the chip is in binary mode or not. + */ + if (yrs > 169) { + spin_unlock_irqrestore(&rtc_lock, flags); + return -EINVAL; + } + + if (yrs >= 100) + yrs -= 100; + + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) + || RTC_ALWAYS_BCD) { + sec = bin2bcd(sec); + min = bin2bcd(min); + hrs = bin2bcd(hrs); + day = bin2bcd(day); + mon = bin2bcd(mon); + yrs = bin2bcd(yrs); + century = bin2bcd(century); + } + + save_control = CMOS_READ(RTC_CONTROL); + CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + +#ifdef CONFIG_MACH_DECSTATION + CMOS_WRITE(real_yrs, RTC_DEC_YEAR); +#endif + CMOS_WRITE(yrs, RTC_YEAR); + CMOS_WRITE(mon, RTC_MONTH); + CMOS_WRITE(day, RTC_DAY_OF_MONTH); + CMOS_WRITE(hrs, RTC_HOURS); + CMOS_WRITE(min, RTC_MINUTES); + CMOS_WRITE(sec, RTC_SECONDS); +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) + CMOS_WRITE(century, acpi_gbl_FADT.century); +#endif + + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + + spin_unlock_irqrestore(&rtc_lock, flags); + + return 0; +} + #endif /* _MC146818RTC_H */ -- cgit v1.2.3 From 6705fdb34c7ddc2154f616aba42bc84d4e4a05a2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 May 2016 20:58:04 +0200 Subject: char/genrtc: remove the rest of the driver No architecture uses the genrtc driver any more, so let's kill it off for good. This now also includes asm-generic/rtc.h, which is otherwise completely unused. Signed-off-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Alexandre Belloni --- include/asm-generic/rtc.h | 51 ----------------------------------------------- 1 file changed, 51 deletions(-) delete mode 100644 include/asm-generic/rtc.h (limited to 'include') diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h deleted file mode 100644 index 4fcff22cd707..000000000000 --- a/include/asm-generic/rtc.h +++ /dev/null @@ -1,51 +0,0 @@ -/* - * include/asm-generic/rtc.h - * - * Author: Tom Rini - * - * Based on: - * drivers/char/rtc.c - * - * Please read the COPYING file for all license details. - */ - -#ifndef __ASM_RTC_H__ -#define __ASM_RTC_H__ - -#include - -#ifndef get_rtc_time -#include -#define get_rtc_time mc146818_get_time -#define set_rtc_time mc146818_set_time -#endif - -#define RTC_PIE 0x40 /* periodic interrupt enable */ -#define RTC_AIE 0x20 /* alarm interrupt enable */ -#define RTC_UIE 0x10 /* update-finished interrupt enable */ - -/* some dummy definitions */ -#define RTC_BATT_BAD 0x100 /* battery bad */ -#define RTC_SQWE 0x08 /* enable square-wave output */ -#define RTC_DM_BINARY 0x04 /* all time/date values are BCD if clear */ -#define RTC_24H 0x02 /* 24 hour mode - else hours bit 7 means pm */ -#define RTC_DST_EN 0x01 /* auto switch DST - works f. USA only */ - -static inline unsigned int get_rtc_ss(void) -{ - struct rtc_time h; - - get_rtc_time(&h); - return h.tm_sec; -} - -static inline int get_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} -static inline int set_rtc_pll(struct rtc_pll_info *pll) -{ - return -EINVAL; -} - -#endif /* __ASM_RTC_H__ */ -- cgit v1.2.3 From 3953c46c3ac7eef31a9935427371c6f54a22f1ba Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Thu, 2 Jun 2016 15:05:40 -0300 Subject: sk_buff: allow segmenting based on frag sizes This patch allows segmenting a skb based on its frags sizes instead of based on a fixed value. Signed-off-by: Marcelo Ricardo Leitner Tested-by: Xin Long Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ee38a4127475..329a0a9ef671 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -301,6 +301,11 @@ struct sk_buff; #endif extern int sysctl_max_skb_frags; +/* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to + * segment using its current segmentation instead. + */ +#define GSO_BY_FRAGS 0xFFFF + typedef struct skb_frag_struct skb_frag_t; struct skb_frag_struct { -- cgit v1.2.3 From ae7ef81ef000adeee7a87585b9135ff8a8064acc Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Thu, 2 Jun 2016 15:05:41 -0300 Subject: skbuff: introduce skb_gso_validate_mtu skb_gso_network_seglen is not enough for checking fragment sizes if skb is using GSO_BY_FRAGS as we have to check frag per frag. This patch introduces skb_gso_validate_mtu, based on the former, which will wrap the use case inside it as all calls to skb_gso_network_seglen were to validate if it fits on a given TMU, and improve the check. Signed-off-by: Marcelo Ricardo Leitner Tested-by: Xin Long Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 329a0a9ef671..aa3f9d7e8d5c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2992,6 +2992,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); +bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, int write_len); -- cgit v1.2.3 From 90017accff61ae89283ad9a51f9ac46ca01633fb Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Thu, 2 Jun 2016 15:05:43 -0300 Subject: sctp: Add GSO support SCTP has this pecualiarity that its packets cannot be just segmented to (P)MTU. Its chunks must be contained in IP segments, padding respected. So we can't just generate a big skb, set gso_size to the fragmentation point and deliver it to IP layer. This patch takes a different approach. SCTP will now build a skb as it would be if it was received using GRO. That is, there will be a cover skb with protocol headers and children ones containing the actual segments, already segmented to a way that respects SCTP RFCs. With that, we can tell skb_segment() to just split based on frag_list, trusting its sizes are already in accordance. This way SCTP can benefit from GSO and instead of passing several packets through the stack, it can pass a single large packet. v2: - Added support for receiving GSO frames, as requested by Dave Miller. - Clear skb->cb if packet is GSO (otherwise it's not used by SCTP) - Added heuristics similar to what we have in TCP for not generating single GSO packets that fills cwnd. v3: - consider sctphdr size in skb_gso_transport_seglen() - rebased due to 5c7cdf339af5 ("gso: Remove arbitrary checks for unsupported GSO") Signed-off-by: Marcelo Ricardo Leitner Tested-by: Xin Long Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 7 +++++-- include/linux/netdevice.h | 1 + include/linux/skbuff.h | 2 ++ include/net/sctp/sctp.h | 4 ++++ include/net/sctp/structs.h | 5 +++++ 5 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index aa7b2400f98c..9c6c8ef2e9e7 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -53,8 +53,9 @@ enum { * headers in software. */ NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */ + NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_TUNNEL_REMCSUM_BIT, + NETIF_F_GSO_SCTP_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -128,6 +129,7 @@ enum { #define NETIF_F_TSO_MANGLEID __NETIF_F(TSO_MANGLEID) #define NETIF_F_GSO_PARTIAL __NETIF_F(GSO_PARTIAL) #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM) +#define NETIF_F_GSO_SCTP __NETIF_F(GSO_SCTP) #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER) #define NETIF_F_HW_VLAN_STAG_RX __NETIF_F(HW_VLAN_STAG_RX) #define NETIF_F_HW_VLAN_STAG_TX __NETIF_F(HW_VLAN_STAG_TX) @@ -166,7 +168,8 @@ enum { NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO) +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO | \ + NETIF_F_GSO_SCTP) /* * If one device supports one of these features, then enable them diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f45929ce8157..fa6df2699532 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4012,6 +4012,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index aa3f9d7e8d5c..dc0fca747c5e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -487,6 +487,8 @@ enum { SKB_GSO_PARTIAL = 1 << 13, SKB_GSO_TUNNEL_REMCSUM = 1 << 14, + + SKB_GSO_SCTP = 1 << 15, }; #if BITS_PER_LONG > 32 diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index b392ac8382f2..632e205ca54b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -186,6 +186,10 @@ void sctp_assocs_proc_exit(struct net *net); int sctp_remaddr_proc_init(struct net *net); void sctp_remaddr_proc_exit(struct net *net); +/* + * sctp/offload.c + */ +int sctp_offload_init(void); /* * Module global variables diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 16b013a6191c..83c5ec58b93a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -566,6 +566,9 @@ struct sctp_chunk { /* This points to the sk_buff containing the actual data. */ struct sk_buff *skb; + /* In case of GSO packets, this will store the head one */ + struct sk_buff *head_skb; + /* These are the SCTP headers by reverse order in a packet. * Note that some of these may happen more than once. In that * case, we point at the "current" one, whatever that means @@ -696,6 +699,8 @@ struct sctp_packet { size_t overhead; /* This is the total size of all chunks INCLUDING padding. */ size_t size; + /* This is the maximum size this packet may have */ + size_t max_size; /* The packet is destined for this transport address. * The function we finally use to pass down to the next lower -- cgit v1.2.3 From a91eb52abb504a1dd3248a5d07b54e7f95d5fcf1 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 3 Jun 2016 14:35:32 +0300 Subject: qed: Revisit chain implementation RoCE driver is going to need a 32-bit chain [current chain implementation for qed* currently supports only 16-bit producer/consumer chains]. This patch adds said support, as well as doing other slight tweaks and modifications to qed's chain API. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 553 +++++++++++++++++++++++++----------------- include/linux/qed/qed_if.h | 3 +- 2 files changed, 336 insertions(+), 220 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 5f8fcaaa6504..eceaa9ed2ae9 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -47,16 +47,56 @@ enum qed_chain_use_mode { QED_CHAIN_USE_TO_CONSUME_PRODUCE, /* Chain starts empty */ }; +enum qed_chain_cnt_type { + /* The chain's size/prod/cons are kept in 16-bit variables */ + QED_CHAIN_CNT_TYPE_U16, + + /* The chain's size/prod/cons are kept in 32-bit variables */ + QED_CHAIN_CNT_TYPE_U32, +}; + struct qed_chain_next { struct regpair next_phys; void *next_virt; }; +struct qed_chain_pbl_u16 { + u16 prod_page_idx; + u16 cons_page_idx; +}; + +struct qed_chain_pbl_u32 { + u32 prod_page_idx; + u32 cons_page_idx; +}; + struct qed_chain_pbl { + /* Base address of a pre-allocated buffer for pbl */ dma_addr_t p_phys_table; void *p_virt_table; - u16 prod_page_idx; - u16 cons_page_idx; + + /* Table for keeping the virtual addresses of the chain pages, + * respectively to the physical addresses in the pbl table. + */ + void **pp_virt_addr_tbl; + + /* Index to current used page by producer/consumer */ + union { + struct qed_chain_pbl_u16 pbl16; + struct qed_chain_pbl_u32 pbl32; + } u; +}; + +struct qed_chain_u16 { + /* Cyclic index of next element to produce/consme */ + u16 prod_idx; + u16 cons_idx; +}; + +struct qed_chain_u32 { + /* Cyclic index of next element to produce/consme */ + u32 prod_idx; + u32 cons_idx; }; struct qed_chain { @@ -64,13 +104,25 @@ struct qed_chain { dma_addr_t p_phys_addr; void *p_prod_elem; void *p_cons_elem; - u16 page_cnt; + enum qed_chain_mode mode; enum qed_chain_use_mode intended_use; /* used to produce/consume */ - u16 capacity; /*< number of _usable_ elements */ - u16 size; /* number of elements */ - u16 prod_idx; - u16 cons_idx; + enum qed_chain_cnt_type cnt_type; + + union { + struct qed_chain_u16 chain16; + struct qed_chain_u32 chain32; + } u; + + u32 page_cnt; + + /* Number of elements - capacity is for usable elements only, + * while size will contain total number of elements [for entire chain]. + */ + u32 capacity; + u32 size; + + /* Elements information for fast calculations */ u16 elem_per_page; u16 elem_per_page_mask; u16 elem_unusable; @@ -96,66 +148,69 @@ struct qed_chain { #define QED_CHAIN_PAGE_CNT(elem_cnt, elem_size, mode) \ DIV_ROUND_UP(elem_cnt, USABLE_ELEMS_PER_PAGE(elem_size, mode)) +#define is_chain_u16(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U16) +#define is_chain_u32(p) ((p)->cnt_type == QED_CHAIN_CNT_TYPE_U32) + /* Accessors */ static inline u16 qed_chain_get_prod_idx(struct qed_chain *p_chain) { - return p_chain->prod_idx; + return p_chain->u.chain16.prod_idx; } static inline u16 qed_chain_get_cons_idx(struct qed_chain *p_chain) { - return p_chain->cons_idx; + return p_chain->u.chain16.cons_idx; +} + +static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) +{ + return p_chain->u.chain32.cons_idx; } static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) { u16 used; - /* we don't need to trancate upon assignmet, as we assign u32->u16 */ - used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - - (u32)p_chain->cons_idx; + used = (u16) (((u32)0x10000 + + (u32)p_chain->u.chain16.prod_idx) - + (u32)p_chain->u.chain16.cons_idx); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->prod_idx / p_chain->elem_per_page - - p_chain->cons_idx / p_chain->elem_per_page; + used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page - + p_chain->u.chain16.cons_idx / p_chain->elem_per_page; - return p_chain->capacity - used; + return (u16)(p_chain->capacity - used); } -static inline u8 qed_chain_is_full(struct qed_chain *p_chain) +static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) { - return qed_chain_get_elem_left(p_chain) == p_chain->capacity; -} + u32 used; -static inline u8 qed_chain_is_empty(struct qed_chain *p_chain) -{ - return qed_chain_get_elem_left(p_chain) == 0; -} + used = (u32) (((u64)0x100000000ULL + + (u64)p_chain->u.chain32.prod_idx) - + (u64)p_chain->u.chain32.cons_idx); + if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) + used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page - + p_chain->u.chain32.cons_idx / p_chain->elem_per_page; -static inline u16 qed_chain_get_elem_per_page( - struct qed_chain *p_chain) -{ - return p_chain->elem_per_page; + return p_chain->capacity - used; } -static inline u16 qed_chain_get_usable_per_page( - struct qed_chain *p_chain) +static inline u16 qed_chain_get_usable_per_page(struct qed_chain *p_chain) { return p_chain->usable_per_page; } -static inline u16 qed_chain_get_unusable_per_page( - struct qed_chain *p_chain) +static inline u16 qed_chain_get_unusable_per_page(struct qed_chain *p_chain) { return p_chain->elem_unusable; } -static inline u16 qed_chain_get_size(struct qed_chain *p_chain) +static inline u32 qed_chain_get_page_cnt(struct qed_chain *p_chain) { - return p_chain->size; + return p_chain->page_cnt; } -static inline dma_addr_t -qed_chain_get_pbl_phys(struct qed_chain *p_chain) +static inline dma_addr_t qed_chain_get_pbl_phys(struct qed_chain *p_chain) { return p_chain->pbl.p_phys_table; } @@ -172,64 +227,62 @@ qed_chain_get_pbl_phys(struct qed_chain *p_chain) */ static inline void qed_chain_advance_page(struct qed_chain *p_chain, - void **p_next_elem, - u16 *idx_to_inc, - u16 *page_to_inc) + void **p_next_elem, void *idx_to_inc, void *page_to_inc) { + struct qed_chain_next *p_next = NULL; + u32 page_index = 0; switch (p_chain->mode) { case QED_CHAIN_MODE_NEXT_PTR: - { - struct qed_chain_next *p_next = *p_next_elem; + p_next = *p_next_elem; *p_next_elem = p_next->next_virt; - *idx_to_inc += p_chain->elem_unusable; + if (is_chain_u16(p_chain)) + *(u16 *)idx_to_inc += p_chain->elem_unusable; + else + *(u32 *)idx_to_inc += p_chain->elem_unusable; break; - } case QED_CHAIN_MODE_SINGLE: *p_next_elem = p_chain->p_virt_addr; break; case QED_CHAIN_MODE_PBL: - /* It is assumed pages are sequential, next element needs - * to change only when passing going back to first from last. - */ - if (++(*page_to_inc) == p_chain->page_cnt) { - *page_to_inc = 0; - *p_next_elem = p_chain->p_virt_addr; + if (is_chain_u16(p_chain)) { + if (++(*(u16 *)page_to_inc) == p_chain->page_cnt) + *(u16 *)page_to_inc = 0; + page_index = *(u16 *)page_to_inc; + } else { + if (++(*(u32 *)page_to_inc) == p_chain->page_cnt) + *(u32 *)page_to_inc = 0; + page_index = *(u32 *)page_to_inc; } + *p_next_elem = p_chain->pbl.pp_virt_addr_tbl[page_index]; } } #define is_unusable_idx(p, idx) \ - (((p)->idx & (p)->elem_per_page_mask) == (p)->usable_per_page) + (((p)->u.chain16.idx & (p)->elem_per_page_mask) == (p)->usable_per_page) + +#define is_unusable_idx_u32(p, idx) \ + (((p)->u.chain32.idx & (p)->elem_per_page_mask) == (p)->usable_per_page) +#define is_unusable_next_idx(p, idx) \ + ((((p)->u.chain16.idx + 1) & (p)->elem_per_page_mask) == \ + (p)->usable_per_page) -#define is_unusable_next_idx(p, idx) \ - ((((p)->idx + 1) & (p)->elem_per_page_mask) == (p)->usable_per_page) +#define is_unusable_next_idx_u32(p, idx) \ + ((((p)->u.chain32.idx + 1) & (p)->elem_per_page_mask) == \ + (p)->usable_per_page) -#define test_ans_skip(p, idx) \ +#define test_and_skip(p, idx) \ do { \ - if (is_unusable_idx(p, idx)) { \ - (p)->idx += (p)->elem_unusable; \ + if (is_chain_u16(p)) { \ + if (is_unusable_idx(p, idx)) \ + (p)->u.chain16.idx += (p)->elem_unusable; \ + } else { \ + if (is_unusable_idx_u32(p, idx)) \ + (p)->u.chain32.idx += (p)->elem_unusable; \ } \ } while (0) -/** - * @brief qed_chain_return_multi_produced - - * - * A chain in which the driver "Produces" elements should use this API - * to indicate previous produced elements are now consumed. - * - * @param p_chain - * @param num - */ -static inline void -qed_chain_return_multi_produced(struct qed_chain *p_chain, - u16 num) -{ - p_chain->cons_idx += num; - test_ans_skip(p_chain, cons_idx); -} - /** * @brief qed_chain_return_produced - * @@ -240,8 +293,11 @@ qed_chain_return_multi_produced(struct qed_chain *p_chain, */ static inline void qed_chain_return_produced(struct qed_chain *p_chain) { - p_chain->cons_idx++; - test_ans_skip(p_chain, cons_idx); + if (is_chain_u16(p_chain)) + p_chain->u.chain16.cons_idx++; + else + p_chain->u.chain32.cons_idx++; + test_and_skip(p_chain, cons_idx); } /** @@ -257,21 +313,33 @@ static inline void qed_chain_return_produced(struct qed_chain *p_chain) */ static inline void *qed_chain_produce(struct qed_chain *p_chain) { - void *ret = NULL; - - if ((p_chain->prod_idx & p_chain->elem_per_page_mask) == - p_chain->next_page_mask) { - qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, - &p_chain->prod_idx, - &p_chain->pbl.prod_page_idx); + void *p_ret = NULL, *p_prod_idx, *p_prod_page_idx; + + if (is_chain_u16(p_chain)) { + if ((p_chain->u.chain16.prod_idx & + p_chain->elem_per_page_mask) == p_chain->next_page_mask) { + p_prod_idx = &p_chain->u.chain16.prod_idx; + p_prod_page_idx = &p_chain->pbl.u.pbl16.prod_page_idx; + qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, + p_prod_idx, p_prod_page_idx); + } + p_chain->u.chain16.prod_idx++; + } else { + if ((p_chain->u.chain32.prod_idx & + p_chain->elem_per_page_mask) == p_chain->next_page_mask) { + p_prod_idx = &p_chain->u.chain32.prod_idx; + p_prod_page_idx = &p_chain->pbl.u.pbl32.prod_page_idx; + qed_chain_advance_page(p_chain, &p_chain->p_prod_elem, + p_prod_idx, p_prod_page_idx); + } + p_chain->u.chain32.prod_idx++; } - ret = p_chain->p_prod_elem; - p_chain->prod_idx++; + p_ret = p_chain->p_prod_elem; p_chain->p_prod_elem = (void *)(((u8 *)p_chain->p_prod_elem) + p_chain->elem_size); - return ret; + return p_ret; } /** @@ -282,9 +350,9 @@ static inline void *qed_chain_produce(struct qed_chain *p_chain) * @param p_chain * @param num * - * @return u16, number of unusable BDs + * @return number of unusable BDs */ -static inline u16 qed_chain_get_capacity(struct qed_chain *p_chain) +static inline u32 qed_chain_get_capacity(struct qed_chain *p_chain) { return p_chain->capacity; } @@ -297,11 +365,13 @@ static inline u16 qed_chain_get_capacity(struct qed_chain *p_chain) * * @param p_chain */ -static inline void -qed_chain_recycle_consumed(struct qed_chain *p_chain) +static inline void qed_chain_recycle_consumed(struct qed_chain *p_chain) { - test_ans_skip(p_chain, prod_idx); - p_chain->prod_idx++; + test_and_skip(p_chain, prod_idx); + if (is_chain_u16(p_chain)) + p_chain->u.chain16.prod_idx++; + else + p_chain->u.chain32.prod_idx++; } /** @@ -316,21 +386,33 @@ qed_chain_recycle_consumed(struct qed_chain *p_chain) */ static inline void *qed_chain_consume(struct qed_chain *p_chain) { - void *ret = NULL; - - if ((p_chain->cons_idx & p_chain->elem_per_page_mask) == - p_chain->next_page_mask) { + void *p_ret = NULL, *p_cons_idx, *p_cons_page_idx; + + if (is_chain_u16(p_chain)) { + if ((p_chain->u.chain16.cons_idx & + p_chain->elem_per_page_mask) == p_chain->next_page_mask) { + p_cons_idx = &p_chain->u.chain16.cons_idx; + p_cons_page_idx = &p_chain->pbl.u.pbl16.cons_page_idx; + qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, + p_cons_idx, p_cons_page_idx); + } + p_chain->u.chain16.cons_idx++; + } else { + if ((p_chain->u.chain32.cons_idx & + p_chain->elem_per_page_mask) == p_chain->next_page_mask) { + p_cons_idx = &p_chain->u.chain32.cons_idx; + p_cons_page_idx = &p_chain->pbl.u.pbl32.cons_page_idx; qed_chain_advance_page(p_chain, &p_chain->p_cons_elem, - &p_chain->cons_idx, - &p_chain->pbl.cons_page_idx); + p_cons_idx, p_cons_page_idx); + } + p_chain->u.chain32.cons_idx++; } - ret = p_chain->p_cons_elem; - p_chain->cons_idx++; + p_ret = p_chain->p_cons_elem; p_chain->p_cons_elem = (void *)(((u8 *)p_chain->p_cons_elem) + p_chain->elem_size); - return ret; + return p_ret; } /** @@ -340,16 +422,33 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) */ static inline void qed_chain_reset(struct qed_chain *p_chain) { - int i; - - p_chain->prod_idx = 0; - p_chain->cons_idx = 0; - p_chain->p_cons_elem = p_chain->p_virt_addr; - p_chain->p_prod_elem = p_chain->p_virt_addr; + u32 i; + + if (is_chain_u16(p_chain)) { + p_chain->u.chain16.prod_idx = 0; + p_chain->u.chain16.cons_idx = 0; + } else { + p_chain->u.chain32.prod_idx = 0; + p_chain->u.chain32.cons_idx = 0; + } + p_chain->p_cons_elem = p_chain->p_virt_addr; + p_chain->p_prod_elem = p_chain->p_virt_addr; if (p_chain->mode == QED_CHAIN_MODE_PBL) { - p_chain->pbl.prod_page_idx = p_chain->page_cnt - 1; - p_chain->pbl.cons_page_idx = p_chain->page_cnt - 1; + /* Use (page_cnt - 1) as a reset value for the prod/cons page's + * indices, to avoid unnecessary page advancing on the first + * call to qed_chain_produce/consume. Instead, the indices + * will be advanced to page_cnt and then will be wrapped to 0. + */ + u32 reset_val = p_chain->page_cnt - 1; + + if (is_chain_u16(p_chain)) { + p_chain->pbl.u.pbl16.prod_page_idx = (u16)reset_val; + p_chain->pbl.u.pbl16.cons_page_idx = (u16)reset_val; + } else { + p_chain->pbl.u.pbl32.prod_page_idx = reset_val; + p_chain->pbl.u.pbl32.cons_page_idx = reset_val; + } } switch (p_chain->intended_use) { @@ -377,168 +476,184 @@ static inline void qed_chain_reset(struct qed_chain *p_chain) * @param intended_use * @param mode */ -static inline void qed_chain_init(struct qed_chain *p_chain, - void *p_virt_addr, - dma_addr_t p_phys_addr, - u16 page_cnt, - u8 elem_size, - enum qed_chain_use_mode intended_use, - enum qed_chain_mode mode) +static inline void qed_chain_init_params(struct qed_chain *p_chain, + u32 page_cnt, + u8 elem_size, + enum qed_chain_use_mode intended_use, + enum qed_chain_mode mode, + enum qed_chain_cnt_type cnt_type) { /* chain fixed parameters */ - p_chain->p_virt_addr = p_virt_addr; - p_chain->p_phys_addr = p_phys_addr; + p_chain->p_virt_addr = NULL; + p_chain->p_phys_addr = 0; p_chain->elem_size = elem_size; - p_chain->page_cnt = page_cnt; + p_chain->intended_use = intended_use; p_chain->mode = mode; + p_chain->cnt_type = cnt_type; - p_chain->intended_use = intended_use; p_chain->elem_per_page = ELEMS_PER_PAGE(elem_size); - p_chain->usable_per_page = - USABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->capacity = p_chain->usable_per_page * page_cnt; - p_chain->size = p_chain->elem_per_page * page_cnt; + p_chain->usable_per_page = USABLE_ELEMS_PER_PAGE(elem_size, mode); p_chain->elem_per_page_mask = p_chain->elem_per_page - 1; - p_chain->elem_unusable = UNUSABLE_ELEMS_PER_PAGE(elem_size, mode); - p_chain->next_page_mask = (p_chain->usable_per_page & p_chain->elem_per_page_mask); - if (mode == QED_CHAIN_MODE_NEXT_PTR) { - struct qed_chain_next *p_next; - u16 i; - - for (i = 0; i < page_cnt - 1; i++) { - /* Increment mem_phy to the next page. */ - p_phys_addr += QED_CHAIN_PAGE_SIZE; - - /* Initialize the physical address of the next page. */ - p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + - elem_size * - p_chain-> - usable_per_page); - - p_next->next_phys.lo = DMA_LO_LE(p_phys_addr); - p_next->next_phys.hi = DMA_HI_LE(p_phys_addr); - - /* Initialize the virtual address of the next page. */ - p_next->next_virt = (void *)((u8 *)p_virt_addr + - QED_CHAIN_PAGE_SIZE); - - /* Move to the next page. */ - p_virt_addr = p_next->next_virt; - } - - /* Last page's next should point to beginning of the chain */ - p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + - elem_size * - p_chain->usable_per_page); + p_chain->page_cnt = page_cnt; + p_chain->capacity = p_chain->usable_per_page * page_cnt; + p_chain->size = p_chain->elem_per_page * page_cnt; - p_next->next_phys.lo = DMA_LO_LE(p_chain->p_phys_addr); - p_next->next_phys.hi = DMA_HI_LE(p_chain->p_phys_addr); - p_next->next_virt = p_chain->p_virt_addr; - } - qed_chain_reset(p_chain); + p_chain->pbl.p_phys_table = 0; + p_chain->pbl.p_virt_table = NULL; + p_chain->pbl.pp_virt_addr_tbl = NULL; } /** - * @brief qed_chain_pbl_init - Initalizes a basic pbl chain - * struct + * @brief qed_chain_init_mem - + * + * Initalizes a basic chain struct with its chain buffers + * * @param p_chain * @param p_virt_addr virtual address of allocated buffer's beginning * @param p_phys_addr physical address of allocated buffer's beginning - * @param page_cnt number of pages in the allocated buffer - * @param elem_size size of each element in the chain - * @param use_mode - * @param p_phys_pbl pointer to a pre-allocated side table - * which will hold physical page addresses. - * @param p_virt_pbl pointer to a pre allocated side table - * which will hold virtual page addresses. + * */ -static inline void -qed_chain_pbl_init(struct qed_chain *p_chain, - void *p_virt_addr, - dma_addr_t p_phys_addr, - u16 page_cnt, - u8 elem_size, - enum qed_chain_use_mode use_mode, - dma_addr_t p_phys_pbl, - dma_addr_t *p_virt_pbl) +static inline void qed_chain_init_mem(struct qed_chain *p_chain, + void *p_virt_addr, dma_addr_t p_phys_addr) { - dma_addr_t *p_pbl_dma = p_virt_pbl; - int i; - - qed_chain_init(p_chain, p_virt_addr, p_phys_addr, page_cnt, - elem_size, use_mode, QED_CHAIN_MODE_PBL); + p_chain->p_virt_addr = p_virt_addr; + p_chain->p_phys_addr = p_phys_addr; +} +/** + * @brief qed_chain_init_pbl_mem - + * + * Initalizes a basic chain struct with its pbl buffers + * + * @param p_chain + * @param p_virt_pbl pointer to a pre allocated side table which will hold + * virtual page addresses. + * @param p_phys_pbl pointer to a pre-allocated side table which will hold + * physical page addresses. + * @param pp_virt_addr_tbl + * pointer to a pre-allocated side table which will hold + * the virtual addresses of the chain pages. + * + */ +static inline void qed_chain_init_pbl_mem(struct qed_chain *p_chain, + void *p_virt_pbl, + dma_addr_t p_phys_pbl, + void **pp_virt_addr_tbl) +{ p_chain->pbl.p_phys_table = p_phys_pbl; p_chain->pbl.p_virt_table = p_virt_pbl; - - /* Fill the PBL with physical addresses*/ - for (i = 0; i < page_cnt; i++) { - *p_pbl_dma = p_phys_addr; - p_phys_addr += QED_CHAIN_PAGE_SIZE; - p_pbl_dma++; - } + p_chain->pbl.pp_virt_addr_tbl = pp_virt_addr_tbl; } /** - * @brief qed_chain_set_prod - sets the prod to the given - * value + * @brief qed_chain_init_next_ptr_elem - + * + * Initalizes a next pointer element + * + * @param p_chain + * @param p_virt_curr virtual address of a chain page of which the next + * pointer element is initialized + * @param p_virt_next virtual address of the next chain page + * @param p_phys_next physical address of the next chain page * - * @param prod_idx - * @param p_prod_elem */ -static inline void qed_chain_set_prod(struct qed_chain *p_chain, - u16 prod_idx, - void *p_prod_elem) +static inline void +qed_chain_init_next_ptr_elem(struct qed_chain *p_chain, + void *p_virt_curr, + void *p_virt_next, dma_addr_t p_phys_next) { - p_chain->prod_idx = prod_idx; - p_chain->p_prod_elem = p_prod_elem; + struct qed_chain_next *p_next; + u32 size; + + size = p_chain->elem_size * p_chain->usable_per_page; + p_next = (struct qed_chain_next *)((u8 *)p_virt_curr + size); + + DMA_REGPAIR_LE(p_next->next_phys, p_phys_next); + + p_next->next_virt = p_virt_next; } /** - * @brief qed_chain_get_elem - + * @brief qed_chain_get_last_elem - * - * get a pointer to an element represented by absolute idx + * Returns a pointer to the last element of the chain * * @param p_chain - * @assumption p_chain->size is a power of 2 * - * @return void*, a pointer to next element + * @return void* */ -static inline void *qed_chain_sge_get_elem(struct qed_chain *p_chain, - u16 idx) +static inline void *qed_chain_get_last_elem(struct qed_chain *p_chain) { - void *ret = NULL; - - if (idx >= p_chain->size) - return NULL; + struct qed_chain_next *p_next = NULL; + void *p_virt_addr = NULL; + u32 size, last_page_idx; - ret = (u8 *)p_chain->p_virt_addr + p_chain->elem_size * idx; + if (!p_chain->p_virt_addr) + goto out; - return ret; + switch (p_chain->mode) { + case QED_CHAIN_MODE_NEXT_PTR: + size = p_chain->elem_size * p_chain->usable_per_page; + p_virt_addr = p_chain->p_virt_addr; + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + size); + while (p_next->next_virt != p_chain->p_virt_addr) { + p_virt_addr = p_next->next_virt; + p_next = (struct qed_chain_next *)((u8 *)p_virt_addr + + size); + } + break; + case QED_CHAIN_MODE_SINGLE: + p_virt_addr = p_chain->p_virt_addr; + break; + case QED_CHAIN_MODE_PBL: + last_page_idx = p_chain->page_cnt - 1; + p_virt_addr = p_chain->pbl.pp_virt_addr_tbl[last_page_idx]; + break; + } + /* p_virt_addr points at this stage to the last page of the chain */ + size = p_chain->elem_size * (p_chain->usable_per_page - 1); + p_virt_addr = (u8 *)p_virt_addr + size; +out: + return p_virt_addr; } /** - * @brief qed_chain_sge_inc_cons_prod + * @brief qed_chain_set_prod - sets the prod to the given value * - * for sge chains, producer isn't increased serially, the ring - * is expected to be full at all times. Once elements are - * consumed, they are immediately produced. + * @param prod_idx + * @param p_prod_elem + */ +static inline void qed_chain_set_prod(struct qed_chain *p_chain, + u32 prod_idx, void *p_prod_elem) +{ + if (is_chain_u16(p_chain)) + p_chain->u.chain16.prod_idx = (u16) prod_idx; + else + p_chain->u.chain32.prod_idx = prod_idx; + p_chain->p_prod_elem = p_prod_elem; +} + +/** + * @brief qed_chain_pbl_zero_mem - set chain memory to 0 * * @param p_chain - * @param cnt - * - * @return inline void */ -static inline void -qed_chain_sge_inc_cons_prod(struct qed_chain *p_chain, - u16 cnt) +static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain) { - p_chain->prod_idx += cnt; - p_chain->cons_idx += cnt; + u32 i, page_cnt; + + if (p_chain->mode != QED_CHAIN_MODE_PBL) + return; + + page_cnt = qed_chain_get_page_cnt(p_chain); + + for (i = 0; i < page_cnt; i++) + memset(p_chain->pbl.pp_virt_addr_tbl[i], 0, + QED_CHAIN_PAGE_SIZE); } #endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4c29439f54bf..15efccfdc46e 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -325,7 +325,8 @@ struct qed_common_ops { int (*chain_alloc)(struct qed_dev *cdev, enum qed_chain_use_mode intended_use, enum qed_chain_mode mode, - u16 num_elems, + enum qed_chain_cnt_type cnt_type, + u32 num_elems, size_t elem_size, struct qed_chain *p_chain); -- cgit v1.2.3 From 7a9b6b8f6e4c52b31830d32570c2a226e27651f9 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 3 Jun 2016 14:35:33 +0300 Subject: qed: Add common HSI for new protocols This adds the qed portion of the RoCE & iSCSI firmware HSI, as well as adding several new common HSI files which would be required by both qed and qed* protocols. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 190 ++++- include/linux/qed/iscsi_common.h | 1439 ++++++++++++++++++++++++++++++++++++ include/linux/qed/rdma_common.h | 44 ++ include/linux/qed/roce_common.h | 17 + include/linux/qed/storage_common.h | 91 +++ include/linux/qed/tcp_common.h | 226 ++++++ 6 files changed, 2006 insertions(+), 1 deletion(-) create mode 100644 include/linux/qed/iscsi_common.h create mode 100644 include/linux/qed/rdma_common.h create mode 100644 include/linux/qed/roce_common.h create mode 100644 include/linux/qed/storage_common.h create mode 100644 include/linux/qed/tcp_common.h (limited to 'include') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 285189a5ea6d..077a3b6cc80f 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -12,6 +12,7 @@ #define CORE_SPQE_PAGE_SIZE_BYTES 4096 #define X_FINAL_CLEANUP_AGG_INT 1 +#define NUM_OF_GLOBAL_QUEUES 128 /* Queue Zone sizes in bytes */ #define TSTORM_QZONE_SIZE 8 @@ -694,7 +695,10 @@ struct parsing_and_err_flags { #define PARSING_AND_ERR_FLAGS_TUNNELL4CHKSMERROR_SHIFT 15 }; -/* Concrete Function ID. */ +struct pb_context { + __le32 crc[4]; +}; + struct pxp_concrete_fid { __le16 fid; #define PXP_CONCRETE_FID_PFID_MASK 0xF @@ -761,6 +765,72 @@ struct pxp_ptt_entry { }; /* RSS hash type */ +struct rdif_task_context { + __le32 initial_ref_tag; + __le16 app_tag_value; + __le16 app_tag_mask; + u8 flags0; +#define RDIF_TASK_CONTEXT_IGNOREAPPTAG_MASK 0x1 +#define RDIF_TASK_CONTEXT_IGNOREAPPTAG_SHIFT 0 +#define RDIF_TASK_CONTEXT_INITIALREFTAGVALID_MASK 0x1 +#define RDIF_TASK_CONTEXT_INITIALREFTAGVALID_SHIFT 1 +#define RDIF_TASK_CONTEXT_HOSTGUARDTYPE_MASK 0x1 +#define RDIF_TASK_CONTEXT_HOSTGUARDTYPE_SHIFT 2 +#define RDIF_TASK_CONTEXT_SETERRORWITHEOP_MASK 0x1 +#define RDIF_TASK_CONTEXT_SETERRORWITHEOP_SHIFT 3 +#define RDIF_TASK_CONTEXT_PROTECTIONTYPE_MASK 0x3 +#define RDIF_TASK_CONTEXT_PROTECTIONTYPE_SHIFT 4 +#define RDIF_TASK_CONTEXT_CRC_SEED_MASK 0x1 +#define RDIF_TASK_CONTEXT_CRC_SEED_SHIFT 6 +#define RDIF_TASK_CONTEXT_KEEPREFTAGCONST_MASK 0x1 +#define RDIF_TASK_CONTEXT_KEEPREFTAGCONST_SHIFT 7 + u8 partial_dif_data[7]; + __le16 partial_crc_value; + __le16 partial_checksum_value; + __le32 offset_in_io; + __le16 flags1; +#define RDIF_TASK_CONTEXT_VALIDATEGUARD_MASK 0x1 +#define RDIF_TASK_CONTEXT_VALIDATEGUARD_SHIFT 0 +#define RDIF_TASK_CONTEXT_VALIDATEAPPTAG_MASK 0x1 +#define RDIF_TASK_CONTEXT_VALIDATEAPPTAG_SHIFT 1 +#define RDIF_TASK_CONTEXT_VALIDATEREFTAG_MASK 0x1 +#define RDIF_TASK_CONTEXT_VALIDATEREFTAG_SHIFT 2 +#define RDIF_TASK_CONTEXT_FORWARDGUARD_MASK 0x1 +#define RDIF_TASK_CONTEXT_FORWARDGUARD_SHIFT 3 +#define RDIF_TASK_CONTEXT_FORWARDAPPTAG_MASK 0x1 +#define RDIF_TASK_CONTEXT_FORWARDAPPTAG_SHIFT 4 +#define RDIF_TASK_CONTEXT_FORWARDREFTAG_MASK 0x1 +#define RDIF_TASK_CONTEXT_FORWARDREFTAG_SHIFT 5 +#define RDIF_TASK_CONTEXT_INTERVALSIZE_MASK 0x7 +#define RDIF_TASK_CONTEXT_INTERVALSIZE_SHIFT 6 +#define RDIF_TASK_CONTEXT_HOSTINTERFACE_MASK 0x3 +#define RDIF_TASK_CONTEXT_HOSTINTERFACE_SHIFT 9 +#define RDIF_TASK_CONTEXT_DIFBEFOREDATA_MASK 0x1 +#define RDIF_TASK_CONTEXT_DIFBEFOREDATA_SHIFT 11 +#define RDIF_TASK_CONTEXT_RESERVED0_MASK 0x1 +#define RDIF_TASK_CONTEXT_RESERVED0_SHIFT 12 +#define RDIF_TASK_CONTEXT_NETWORKINTERFACE_MASK 0x1 +#define RDIF_TASK_CONTEXT_NETWORKINTERFACE_SHIFT 13 +#define RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK_MASK 0x1 +#define RDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK_SHIFT 14 +#define RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK_MASK 0x1 +#define RDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK_SHIFT 15 + __le16 state; +#define RDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFT_MASK 0xF +#define RDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFT_SHIFT 0 +#define RDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFT_MASK 0xF +#define RDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFT_SHIFT 4 +#define RDIF_TASK_CONTEXT_ERRORINIO_MASK 0x1 +#define RDIF_TASK_CONTEXT_ERRORINIO_SHIFT 8 +#define RDIF_TASK_CONTEXT_CHECKSUMOVERFLOW_MASK 0x1 +#define RDIF_TASK_CONTEXT_CHECKSUMOVERFLOW_SHIFT 9 +#define RDIF_TASK_CONTEXT_REFTAGMASK_MASK 0xF +#define RDIF_TASK_CONTEXT_REFTAGMASK_SHIFT 10 +#define RDIF_TASK_CONTEXT_RESERVED1_MASK 0x3 +#define RDIF_TASK_CONTEXT_RESERVED1_SHIFT 14 + __le32 reserved2; +}; + enum rss_hash_type { RSS_HASH_TYPE_DEFAULT = 0, RSS_HASH_TYPE_IPV4 = 1, @@ -789,4 +859,122 @@ struct status_block { #define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 }; +struct tdif_task_context { + __le32 initial_ref_tag; + __le16 app_tag_value; + __le16 app_tag_mask; + __le16 partial_crc_valueB; + __le16 partial_checksum_valueB; + __le16 stateB; +#define TDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFTB_MASK 0xF +#define TDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFTB_SHIFT 0 +#define TDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFTB_MASK 0xF +#define TDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFTB_SHIFT 4 +#define TDIF_TASK_CONTEXT_ERRORINIOB_MASK 0x1 +#define TDIF_TASK_CONTEXT_ERRORINIOB_SHIFT 8 +#define TDIF_TASK_CONTEXT_CHECKSUMOVERFLOW_MASK 0x1 +#define TDIF_TASK_CONTEXT_CHECKSUMOVERFLOW_SHIFT 9 +#define TDIF_TASK_CONTEXT_RESERVED0_MASK 0x3F +#define TDIF_TASK_CONTEXT_RESERVED0_SHIFT 10 + u8 reserved1; + u8 flags0; +#define TDIF_TASK_CONTEXT_IGNOREAPPTAG_MASK 0x1 +#define TDIF_TASK_CONTEXT_IGNOREAPPTAG_SHIFT 0 +#define TDIF_TASK_CONTEXT_INITIALREFTAGVALID_MASK 0x1 +#define TDIF_TASK_CONTEXT_INITIALREFTAGVALID_SHIFT 1 +#define TDIF_TASK_CONTEXT_HOSTGUARDTYPE_MASK 0x1 +#define TDIF_TASK_CONTEXT_HOSTGUARDTYPE_SHIFT 2 +#define TDIF_TASK_CONTEXT_SETERRORWITHEOP_MASK 0x1 +#define TDIF_TASK_CONTEXT_SETERRORWITHEOP_SHIFT 3 +#define TDIF_TASK_CONTEXT_PROTECTIONTYPE_MASK 0x3 +#define TDIF_TASK_CONTEXT_PROTECTIONTYPE_SHIFT 4 +#define TDIF_TASK_CONTEXT_CRC_SEED_MASK 0x1 +#define TDIF_TASK_CONTEXT_CRC_SEED_SHIFT 6 +#define TDIF_TASK_CONTEXT_RESERVED2_MASK 0x1 +#define TDIF_TASK_CONTEXT_RESERVED2_SHIFT 7 + __le32 flags1; +#define TDIF_TASK_CONTEXT_VALIDATEGUARD_MASK 0x1 +#define TDIF_TASK_CONTEXT_VALIDATEGUARD_SHIFT 0 +#define TDIF_TASK_CONTEXT_VALIDATEAPPTAG_MASK 0x1 +#define TDIF_TASK_CONTEXT_VALIDATEAPPTAG_SHIFT 1 +#define TDIF_TASK_CONTEXT_VALIDATEREFTAG_MASK 0x1 +#define TDIF_TASK_CONTEXT_VALIDATEREFTAG_SHIFT 2 +#define TDIF_TASK_CONTEXT_FORWARDGUARD_MASK 0x1 +#define TDIF_TASK_CONTEXT_FORWARDGUARD_SHIFT 3 +#define TDIF_TASK_CONTEXT_FORWARDAPPTAG_MASK 0x1 +#define TDIF_TASK_CONTEXT_FORWARDAPPTAG_SHIFT 4 +#define TDIF_TASK_CONTEXT_FORWARDREFTAG_MASK 0x1 +#define TDIF_TASK_CONTEXT_FORWARDREFTAG_SHIFT 5 +#define TDIF_TASK_CONTEXT_INTERVALSIZE_MASK 0x7 +#define TDIF_TASK_CONTEXT_INTERVALSIZE_SHIFT 6 +#define TDIF_TASK_CONTEXT_HOSTINTERFACE_MASK 0x3 +#define TDIF_TASK_CONTEXT_HOSTINTERFACE_SHIFT 9 +#define TDIF_TASK_CONTEXT_DIFBEFOREDATA_MASK 0x1 +#define TDIF_TASK_CONTEXT_DIFBEFOREDATA_SHIFT 11 +#define TDIF_TASK_CONTEXT_RESERVED3_MASK 0x1 +#define TDIF_TASK_CONTEXT_RESERVED3_SHIFT 12 +#define TDIF_TASK_CONTEXT_NETWORKINTERFACE_MASK 0x1 +#define TDIF_TASK_CONTEXT_NETWORKINTERFACE_SHIFT 13 +#define TDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFTA_MASK 0xF +#define TDIF_TASK_CONTEXT_RECEIVEDDIFBYTESLEFTA_SHIFT 14 +#define TDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFTA_MASK 0xF +#define TDIF_TASK_CONTEXT_TRANSMITEDDIFBYTESLEFTA_SHIFT 18 +#define TDIF_TASK_CONTEXT_ERRORINIOA_MASK 0x1 +#define TDIF_TASK_CONTEXT_ERRORINIOA_SHIFT 22 +#define TDIF_TASK_CONTEXT_CHECKSUMOVERFLOWA_MASK 0x1 +#define TDIF_TASK_CONTEXT_CHECKSUMOVERFLOWA_SHIFT 23 +#define TDIF_TASK_CONTEXT_REFTAGMASK_MASK 0xF +#define TDIF_TASK_CONTEXT_REFTAGMASK_SHIFT 24 +#define TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK_MASK 0x1 +#define TDIF_TASK_CONTEXT_FORWARDAPPTAGWITHMASK_SHIFT 28 +#define TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK_MASK 0x1 +#define TDIF_TASK_CONTEXT_FORWARDREFTAGWITHMASK_SHIFT 29 +#define TDIF_TASK_CONTEXT_KEEPREFTAGCONST_MASK 0x1 +#define TDIF_TASK_CONTEXT_KEEPREFTAGCONST_SHIFT 30 +#define TDIF_TASK_CONTEXT_RESERVED4_MASK 0x1 +#define TDIF_TASK_CONTEXT_RESERVED4_SHIFT 31 + __le32 offset_in_iob; + __le16 partial_crc_value_a; + __le16 partial_checksum_valuea_; + __le32 offset_in_ioa; + u8 partial_dif_data_a[8]; + u8 partial_dif_data_b[8]; +}; + +struct timers_context { + __le32 logical_client0; +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_MASK 0xFFFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC0_SHIFT 0 +#define TIMERS_CONTEXT_VALIDLC0_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC0_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC0_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC0_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED0_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED0_SHIFT 30 + __le32 logical_client1; +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_MASK 0xFFFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC1_SHIFT 0 +#define TIMERS_CONTEXT_VALIDLC1_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC1_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC1_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC1_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED1_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED1_SHIFT 30 + __le32 logical_client2; +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_MASK 0xFFFFFFF +#define TIMERS_CONTEXT_EXPIRATIONTIMELC2_SHIFT 0 +#define TIMERS_CONTEXT_VALIDLC2_MASK 0x1 +#define TIMERS_CONTEXT_VALIDLC2_SHIFT 28 +#define TIMERS_CONTEXT_ACTIVELC2_MASK 0x1 +#define TIMERS_CONTEXT_ACTIVELC2_SHIFT 29 +#define TIMERS_CONTEXT_RESERVED2_MASK 0x3 +#define TIMERS_CONTEXT_RESERVED2_SHIFT 30 + __le32 host_expiration_fields; +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_MASK 0xFFFFFFF +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALUE_SHIFT 0 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_MASK 0x1 +#define TIMERS_CONTEXT_HOSTEXPRIRATIONVALID_SHIFT 28 +#define TIMERS_CONTEXT_RESERVED3_MASK 0x7 +#define TIMERS_CONTEXT_RESERVED3_SHIFT 29 +}; #endif /* __COMMON_HSI__ */ diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h new file mode 100644 index 000000000000..b3c0feb15ae9 --- /dev/null +++ b/include/linux/qed/iscsi_common.h @@ -0,0 +1,1439 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __ISCSI_COMMON__ +#define __ISCSI_COMMON__ +/**********************/ +/* ISCSI FW CONSTANTS */ +/**********************/ + +/* iSCSI HSI constants */ +#define ISCSI_DEFAULT_MTU (1500) + +/* Current iSCSI HSI version number composed of two fields (16 bit) */ +#define ISCSI_HSI_MAJOR_VERSION (0) +#define ISCSI_HSI_MINOR_VERSION (0) + +/* KWQ (kernel work queue) layer codes */ +#define ISCSI_SLOW_PATH_LAYER_CODE (6) + +/* CQE completion status */ +#define ISCSI_EQE_COMPLETION_SUCCESS (0x0) +#define ISCSI_EQE_RST_CONN_RCVD (0x1) + +/* iSCSI parameter defaults */ +#define ISCSI_DEFAULT_HEADER_DIGEST (0) +#define ISCSI_DEFAULT_DATA_DIGEST (0) +#define ISCSI_DEFAULT_INITIAL_R2T (1) +#define ISCSI_DEFAULT_IMMEDIATE_DATA (1) +#define ISCSI_DEFAULT_MAX_PDU_LENGTH (0x2000) +#define ISCSI_DEFAULT_FIRST_BURST_LENGTH (0x10000) +#define ISCSI_DEFAULT_MAX_BURST_LENGTH (0x40000) +#define ISCSI_DEFAULT_MAX_OUTSTANDING_R2T (1) + +/* iSCSI parameter limits */ +#define ISCSI_MIN_VAL_MAX_PDU_LENGTH (0x200) +#define ISCSI_MAX_VAL_MAX_PDU_LENGTH (0xffffff) +#define ISCSI_MIN_VAL_BURST_LENGTH (0x200) +#define ISCSI_MAX_VAL_BURST_LENGTH (0xffffff) +#define ISCSI_MIN_VAL_MAX_OUTSTANDING_R2T (1) +#define ISCSI_MAX_VAL_MAX_OUTSTANDING_R2T (0xff) + +/* iSCSI reserved params */ +#define ISCSI_ITT_ALL_ONES (0xffffffff) +#define ISCSI_TTT_ALL_ONES (0xffffffff) + +#define ISCSI_OPTION_1_OFF_CHIP_TCP 1 +#define ISCSI_OPTION_2_ON_CHIP_TCP 2 + +#define ISCSI_INITIATOR_MODE 0 +#define ISCSI_TARGET_MODE 1 + +/* iSCSI request op codes */ +#define ISCSI_OPCODE_NOP_OUT_NO_IMM (0) +#define ISCSI_OPCODE_NOP_OUT ( \ + ISCSI_OPCODE_NOP_OUT_NO_IMM | 0x40) +#define ISCSI_OPCODE_SCSI_CMD_NO_IMM (1) +#define ISCSI_OPCODE_SCSI_CMD ( \ + ISCSI_OPCODE_SCSI_CMD_NO_IMM | 0x40) +#define ISCSI_OPCODE_TMF_REQUEST_NO_IMM (2) +#define ISCSI_OPCODE_TMF_REQUEST ( \ + ISCSI_OPCODE_TMF_REQUEST_NO_IMM | 0x40) +#define ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM (3) +#define ISCSI_OPCODE_LOGIN_REQUEST ( \ + ISCSI_OPCODE_LOGIN_REQUEST_NO_IMM | 0x40) +#define ISCSI_OPCODE_TEXT_REQUEST_NO_IMM (4) +#define ISCSI_OPCODE_TEXT_REQUEST ( \ + ISCSI_OPCODE_TEXT_REQUEST_NO_IMM | 0x40) +#define ISCSI_OPCODE_DATA_OUT (5) +#define ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM (6) +#define ISCSI_OPCODE_LOGOUT_REQUEST ( \ + ISCSI_OPCODE_LOGOUT_REQUEST_NO_IMM | 0x40) + +/* iSCSI response/messages op codes */ +#define ISCSI_OPCODE_NOP_IN (0x20) +#define ISCSI_OPCODE_SCSI_RESPONSE (0x21) +#define ISCSI_OPCODE_TMF_RESPONSE (0x22) +#define ISCSI_OPCODE_LOGIN_RESPONSE (0x23) +#define ISCSI_OPCODE_TEXT_RESPONSE (0x24) +#define ISCSI_OPCODE_DATA_IN (0x25) +#define ISCSI_OPCODE_LOGOUT_RESPONSE (0x26) +#define ISCSI_OPCODE_R2T (0x31) +#define ISCSI_OPCODE_ASYNC_MSG (0x32) +#define ISCSI_OPCODE_REJECT (0x3f) + +/* iSCSI stages */ +#define ISCSI_STAGE_SECURITY_NEGOTIATION (0) +#define ISCSI_STAGE_LOGIN_OPERATIONAL_NEGOTIATION (1) +#define ISCSI_STAGE_FULL_FEATURE_PHASE (3) + +/* iSCSI CQE errors */ +#define CQE_ERROR_BITMAP_DATA_DIGEST (0x08) +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN (0x10) +#define CQE_ERROR_BITMAP_DATA_TRUNCATED (0x20) + +struct cqe_error_bitmap { + u8 cqe_error_status_bits; +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7 +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4 +#define CQE_ERROR_BITMAP_DATA_TRUNCATED_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_TRUNCATED_ERR_SHIFT 5 +#define CQE_ERROR_BITMAP_UNDER_RUN_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_UNDER_RUN_ERR_SHIFT 6 +#define CQE_ERROR_BITMAP_RESERVED2_MASK 0x1 +#define CQE_ERROR_BITMAP_RESERVED2_SHIFT 7 +}; + +union cqe_error_status { + u8 error_status; + struct cqe_error_bitmap error_bits; +}; + +struct data_hdr { + __le32 data[12]; +}; + +struct iscsi_async_msg_hdr { + __le16 reserved0; + u8 flags_attr; +#define ISCSI_ASYNC_MSG_HDR_RSRV_MASK 0x7F +#define ISCSI_ASYNC_MSG_HDR_RSRV_SHIFT 0 +#define ISCSI_ASYNC_MSG_HDR_CONST1_MASK 0x1 +#define ISCSI_ASYNC_MSG_HDR_CONST1_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_ASYNC_MSG_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_ASYNC_MSG_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_ASYNC_MSG_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_ASYNC_MSG_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 all_ones; + __le32 reserved1; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le16 param1_rsrv; + u8 async_vcode; + u8 async_event; + __le16 param3_rsrv; + __le16 param2_rsrv; + __le32 reserved7; +}; + +struct iscsi_sge { + struct regpair sge_addr; + __le16 sge_len; + __le16 reserved0; + __le32 reserved1; +}; + +struct iscsi_cached_sge_ctx { + struct iscsi_sge sge; + struct regpair reserved; + __le32 dsgl_curr_offset[2]; +}; + +struct iscsi_cmd_hdr { + __le16 reserved1; + u8 flags_attr; +#define ISCSI_CMD_HDR_ATTR_MASK 0x7 +#define ISCSI_CMD_HDR_ATTR_SHIFT 0 +#define ISCSI_CMD_HDR_RSRV_MASK 0x3 +#define ISCSI_CMD_HDR_RSRV_SHIFT 3 +#define ISCSI_CMD_HDR_WRITE_MASK 0x1 +#define ISCSI_CMD_HDR_WRITE_SHIFT 5 +#define ISCSI_CMD_HDR_READ_MASK 0x1 +#define ISCSI_CMD_HDR_READ_SHIFT 6 +#define ISCSI_CMD_HDR_FINAL_MASK 0x1 +#define ISCSI_CMD_HDR_FINAL_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_CMD_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_CMD_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_CMD_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_CMD_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 expected_transfer_length; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 cdb[4]; +}; + +struct iscsi_common_hdr { + u8 hdr_status; + u8 hdr_response; + u8 hdr_flags; + u8 hdr_first_byte; +#define ISCSI_COMMON_HDR_OPCODE_MASK 0x3F +#define ISCSI_COMMON_HDR_OPCODE_SHIFT 0 +#define ISCSI_COMMON_HDR_IMM_MASK 0x1 +#define ISCSI_COMMON_HDR_IMM_SHIFT 6 +#define ISCSI_COMMON_HDR_RSRV_MASK 0x1 +#define ISCSI_COMMON_HDR_RSRV_SHIFT 7 + __le32 hdr_second_dword; +#define ISCSI_COMMON_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_COMMON_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_COMMON_HDR_TOTAL_AHS_LEN_SHIFT 24 + __le32 lun_reserved[4]; + __le32 data[6]; +}; + +struct iscsi_conn_offload_params { + struct regpair sq_pbl_addr; + struct regpair r2tq_pbl_addr; + struct regpair xhq_pbl_addr; + struct regpair uhq_pbl_addr; + __le32 initial_ack; + __le16 physical_q0; + __le16 physical_q1; + u8 flags; +#define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1 +#define ISCSI_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 +#define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 +#define ISCSI_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0x3F +#define ISCSI_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 2 + u8 pbl_page_size_log; + u8 pbe_page_size_log; + u8 default_cq; + __le32 stat_sn; +}; + +struct iscsi_slow_path_hdr { + u8 op_code; + u8 flags; +#define ISCSI_SLOW_PATH_HDR_RESERVED0_MASK 0xF +#define ISCSI_SLOW_PATH_HDR_RESERVED0_SHIFT 0 +#define ISCSI_SLOW_PATH_HDR_LAYER_CODE_MASK 0x7 +#define ISCSI_SLOW_PATH_HDR_LAYER_CODE_SHIFT 4 +#define ISCSI_SLOW_PATH_HDR_RESERVED1_MASK 0x1 +#define ISCSI_SLOW_PATH_HDR_RESERVED1_SHIFT 7 +}; + +struct iscsi_conn_update_ramrod_params { + struct iscsi_slow_path_hdr hdr; + __le16 conn_id; + __le32 fw_cid; + u8 flags; +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T_SHIFT 2 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_MASK 0x1 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA_SHIFT 3 +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0xF +#define ISCSI_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_SHIFT 4 + u8 reserved0[3]; + __le32 max_seq_size; + __le32 max_send_pdu_length; + __le32 max_recv_pdu_length; + __le32 first_seq_length; + __le32 exp_stat_sn; +}; + +struct iscsi_ext_cdb_cmd_hdr { + __le16 reserved1; + u8 flags_attr; +#define ISCSI_EXT_CDB_CMD_HDR_ATTR_MASK 0x7 +#define ISCSI_EXT_CDB_CMD_HDR_ATTR_SHIFT 0 +#define ISCSI_EXT_CDB_CMD_HDR_RSRV_MASK 0x3 +#define ISCSI_EXT_CDB_CMD_HDR_RSRV_SHIFT 3 +#define ISCSI_EXT_CDB_CMD_HDR_WRITE_MASK 0x1 +#define ISCSI_EXT_CDB_CMD_HDR_WRITE_SHIFT 5 +#define ISCSI_EXT_CDB_CMD_HDR_READ_MASK 0x1 +#define ISCSI_EXT_CDB_CMD_HDR_READ_SHIFT 6 +#define ISCSI_EXT_CDB_CMD_HDR_FINAL_MASK 0x1 +#define ISCSI_EXT_CDB_CMD_HDR_FINAL_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_EXT_CDB_CMD_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_EXT_CDB_CMD_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE_MASK 0xFF +#define ISCSI_EXT_CDB_CMD_HDR_CDB_SIZE_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 expected_transfer_length; + __le32 cmd_sn; + __le32 exp_stat_sn; + struct iscsi_sge cdb_sge; +}; + +struct iscsi_login_req_hdr { + u8 version_min; + u8 version_max; + u8 flags_attr; +#define ISCSI_LOGIN_REQ_HDR_NSG_MASK 0x3 +#define ISCSI_LOGIN_REQ_HDR_NSG_SHIFT 0 +#define ISCSI_LOGIN_REQ_HDR_CSG_MASK 0x3 +#define ISCSI_LOGIN_REQ_HDR_CSG_SHIFT 2 +#define ISCSI_LOGIN_REQ_HDR_RSRV_MASK 0x3 +#define ISCSI_LOGIN_REQ_HDR_RSRV_SHIFT 4 +#define ISCSI_LOGIN_REQ_HDR_C_MASK 0x1 +#define ISCSI_LOGIN_REQ_HDR_C_SHIFT 6 +#define ISCSI_LOGIN_REQ_HDR_T_MASK 0x1 +#define ISCSI_LOGIN_REQ_HDR_T_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_LOGIN_REQ_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_LOGIN_REQ_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_LOGIN_REQ_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_LOGIN_REQ_HDR_TOTAL_AHS_LEN_SHIFT 24 + __le32 isid_TABC; + __le16 tsih; + __le16 isid_d; + __le32 itt; + __le16 reserved1; + __le16 cid; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 reserved2[4]; +}; + +struct iscsi_logout_req_hdr { + __le16 reserved0; + u8 reason_code; + u8 opcode; + __le32 reserved1; + __le32 reserved2[2]; + __le32 itt; + __le16 reserved3; + __le16 cid; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 reserved4[4]; +}; + +struct iscsi_data_out_hdr { + __le16 reserved1; + u8 flags_attr; +#define ISCSI_DATA_OUT_HDR_RSRV_MASK 0x7F +#define ISCSI_DATA_OUT_HDR_RSRV_SHIFT 0 +#define ISCSI_DATA_OUT_HDR_FINAL_MASK 0x1 +#define ISCSI_DATA_OUT_HDR_FINAL_SHIFT 7 + u8 opcode; + __le32 reserved2; + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 reserved3; + __le32 exp_stat_sn; + __le32 reserved4; + __le32 data_sn; + __le32 buffer_offset; + __le32 reserved5; +}; + +struct iscsi_data_in_hdr { + u8 status_rsvd; + u8 reserved1; + u8 flags; +#define ISCSI_DATA_IN_HDR_STATUS_MASK 0x1 +#define ISCSI_DATA_IN_HDR_STATUS_SHIFT 0 +#define ISCSI_DATA_IN_HDR_UNDERFLOW_MASK 0x1 +#define ISCSI_DATA_IN_HDR_UNDERFLOW_SHIFT 1 +#define ISCSI_DATA_IN_HDR_OVERFLOW_MASK 0x1 +#define ISCSI_DATA_IN_HDR_OVERFLOW_SHIFT 2 +#define ISCSI_DATA_IN_HDR_RSRV_MASK 0x7 +#define ISCSI_DATA_IN_HDR_RSRV_SHIFT 3 +#define ISCSI_DATA_IN_HDR_ACK_MASK 0x1 +#define ISCSI_DATA_IN_HDR_ACK_SHIFT 6 +#define ISCSI_DATA_IN_HDR_FINAL_MASK 0x1 +#define ISCSI_DATA_IN_HDR_FINAL_SHIFT 7 + u8 opcode; + __le32 reserved2; + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 data_sn; + __le32 buffer_offset; + __le32 residual_count; +}; + +struct iscsi_r2t_hdr { + u8 reserved0[3]; + u8 opcode; + __le32 reserved2; + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 r2t_sn; + __le32 buffer_offset; + __le32 desired_data_trns_len; +}; + +struct iscsi_nop_out_hdr { + __le16 reserved1; + u8 flags_attr; +#define ISCSI_NOP_OUT_HDR_RSRV_MASK 0x7F +#define ISCSI_NOP_OUT_HDR_RSRV_SHIFT 0 +#define ISCSI_NOP_OUT_HDR_CONST1_MASK 0x1 +#define ISCSI_NOP_OUT_HDR_CONST1_SHIFT 7 + u8 opcode; + __le32 reserved2; + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 reserved3; + __le32 reserved4; + __le32 reserved5; + __le32 reserved6; +}; + +struct iscsi_nop_in_hdr { + __le16 reserved0; + u8 flags_attr; +#define ISCSI_NOP_IN_HDR_RSRV_MASK 0x7F +#define ISCSI_NOP_IN_HDR_RSRV_SHIFT 0 +#define ISCSI_NOP_IN_HDR_CONST1_MASK 0x1 +#define ISCSI_NOP_IN_HDR_CONST1_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_NOP_IN_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_NOP_IN_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_NOP_IN_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_NOP_IN_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 reserved5; + __le32 reserved6; + __le32 reserved7; +}; + +struct iscsi_login_response_hdr { + u8 version_active; + u8 version_max; + u8 flags_attr; +#define ISCSI_LOGIN_RESPONSE_HDR_NSG_MASK 0x3 +#define ISCSI_LOGIN_RESPONSE_HDR_NSG_SHIFT 0 +#define ISCSI_LOGIN_RESPONSE_HDR_CSG_MASK 0x3 +#define ISCSI_LOGIN_RESPONSE_HDR_CSG_SHIFT 2 +#define ISCSI_LOGIN_RESPONSE_HDR_RSRV_MASK 0x3 +#define ISCSI_LOGIN_RESPONSE_HDR_RSRV_SHIFT 4 +#define ISCSI_LOGIN_RESPONSE_HDR_C_MASK 0x1 +#define ISCSI_LOGIN_RESPONSE_HDR_C_SHIFT 6 +#define ISCSI_LOGIN_RESPONSE_HDR_T_MASK 0x1 +#define ISCSI_LOGIN_RESPONSE_HDR_T_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_LOGIN_RESPONSE_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_LOGIN_RESPONSE_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_LOGIN_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 + __le32 isid_TABC; + __le16 tsih; + __le16 isid_d; + __le32 itt; + __le32 reserved1; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le16 reserved2; + u8 status_detail; + u8 status_class; + __le32 reserved4[2]; +}; + +struct iscsi_logout_response_hdr { + u8 reserved1; + u8 response; + u8 flags; + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_LOGOUT_RESPONSE_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_LOGOUT_RESPONSE_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_LOGOUT_RESPONSE_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_LOGOUT_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 + __le32 reserved2[2]; + __le32 itt; + __le32 reserved3; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 reserved4; + __le16 time2retain; + __le16 time2wait; + __le32 reserved5[1]; +}; + +struct iscsi_text_request_hdr { + __le16 reserved0; + u8 flags_attr; +#define ISCSI_TEXT_REQUEST_HDR_RSRV_MASK 0x3F +#define ISCSI_TEXT_REQUEST_HDR_RSRV_SHIFT 0 +#define ISCSI_TEXT_REQUEST_HDR_C_MASK 0x1 +#define ISCSI_TEXT_REQUEST_HDR_C_SHIFT 6 +#define ISCSI_TEXT_REQUEST_HDR_F_MASK 0x1 +#define ISCSI_TEXT_REQUEST_HDR_F_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_TEXT_REQUEST_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_TEXT_REQUEST_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_TEXT_REQUEST_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_TEXT_REQUEST_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 reserved4[4]; +}; + +struct iscsi_text_response_hdr { + __le16 reserved1; + u8 flags; +#define ISCSI_TEXT_RESPONSE_HDR_RSRV_MASK 0x3F +#define ISCSI_TEXT_RESPONSE_HDR_RSRV_SHIFT 0 +#define ISCSI_TEXT_RESPONSE_HDR_C_MASK 0x1 +#define ISCSI_TEXT_RESPONSE_HDR_C_SHIFT 6 +#define ISCSI_TEXT_RESPONSE_HDR_F_MASK 0x1 +#define ISCSI_TEXT_RESPONSE_HDR_F_SHIFT 7 + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_TEXT_RESPONSE_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_TEXT_RESPONSE_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_TEXT_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 ttt; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 reserved4[3]; +}; + +struct iscsi_tmf_request_hdr { + __le16 reserved0; + u8 function; + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_TMF_REQUEST_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_TMF_REQUEST_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_TMF_REQUEST_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_TMF_REQUEST_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 rtt; + __le32 cmd_sn; + __le32 exp_stat_sn; + __le32 ref_cmd_sn; + __le32 exp_data_sn; + __le32 reserved4[2]; +}; + +struct iscsi_tmf_response_hdr { + u8 reserved2; + u8 hdr_response; + u8 hdr_flags; + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_TMF_RESPONSE_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_TMF_RESPONSE_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_TMF_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair reserved0; + __le32 itt; + __le32 rtt; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 reserved4[3]; +}; + +struct iscsi_response_hdr { + u8 hdr_status; + u8 hdr_response; + u8 hdr_flags; + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_RESPONSE_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_RESPONSE_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_RESPONSE_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_RESPONSE_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair lun; + __le32 itt; + __le32 snack_tag; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 exp_data_sn; + __le32 bi_residual_count; + __le32 residual_count; +}; + +struct iscsi_reject_hdr { + u8 reserved4; + u8 hdr_reason; + u8 hdr_flags; + u8 opcode; + __le32 hdr_second_dword; +#define ISCSI_REJECT_HDR_DATA_SEG_LEN_MASK 0xFFFFFF +#define ISCSI_REJECT_HDR_DATA_SEG_LEN_SHIFT 0 +#define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_MASK 0xFF +#define ISCSI_REJECT_HDR_TOTAL_AHS_LEN_SHIFT 24 + struct regpair reserved0; + __le32 reserved1; + __le32 reserved2; + __le32 stat_sn; + __le32 exp_cmd_sn; + __le32 max_cmd_sn; + __le32 data_sn; + __le32 reserved3[2]; +}; + +union iscsi_task_hdr { + struct iscsi_common_hdr common; + struct data_hdr data; + struct iscsi_cmd_hdr cmd; + struct iscsi_ext_cdb_cmd_hdr ext_cdb_cmd; + struct iscsi_login_req_hdr login_req; + struct iscsi_logout_req_hdr logout_req; + struct iscsi_data_out_hdr data_out; + struct iscsi_data_in_hdr data_in; + struct iscsi_r2t_hdr r2t; + struct iscsi_nop_out_hdr nop_out; + struct iscsi_nop_in_hdr nop_in; + struct iscsi_login_response_hdr login_response; + struct iscsi_logout_response_hdr logout_response; + struct iscsi_text_request_hdr text_request; + struct iscsi_text_response_hdr text_response; + struct iscsi_tmf_request_hdr tmf_request; + struct iscsi_tmf_response_hdr tmf_response; + struct iscsi_response_hdr response; + struct iscsi_reject_hdr reject; + struct iscsi_async_msg_hdr async_msg; +}; + +struct iscsi_cqe_common { + __le16 conn_id; + u8 cqe_type; + union cqe_error_status error_bitmap; + __le32 reserved[3]; + union iscsi_task_hdr iscsi_hdr; +}; + +struct iscsi_cqe_solicited { + __le16 conn_id; + u8 cqe_type; + union cqe_error_status error_bitmap; + __le16 itid; + u8 task_type; + u8 fw_dbg_field; + __le32 reserved1[2]; + union iscsi_task_hdr iscsi_hdr; +}; + +struct iscsi_cqe_unsolicited { + __le16 conn_id; + u8 cqe_type; + union cqe_error_status error_bitmap; + __le16 reserved0; + u8 reserved1; + u8 unsol_cqe_type; + struct regpair rqe_opaque; + union iscsi_task_hdr iscsi_hdr; +}; + +union iscsi_cqe { + struct iscsi_cqe_common cqe_common; + struct iscsi_cqe_solicited cqe_solicited; + struct iscsi_cqe_unsolicited cqe_unsolicited; +}; + +enum iscsi_cqes_type { + ISCSI_CQE_TYPE_SOLICITED = 1, + ISCSI_CQE_TYPE_UNSOLICITED, + ISCSI_CQE_TYPE_SOLICITED_WITH_SENSE + , + ISCSI_CQE_TYPE_TASK_CLEANUP, + ISCSI_CQE_TYPE_DUMMY, + MAX_ISCSI_CQES_TYPE +}; + +enum iscsi_cqe_unsolicited_type { + ISCSI_CQE_UNSOLICITED_NONE, + ISCSI_CQE_UNSOLICITED_SINGLE, + ISCSI_CQE_UNSOLICITED_FIRST, + ISCSI_CQE_UNSOLICITED_MIDDLE, + ISCSI_CQE_UNSOLICITED_LAST, + MAX_ISCSI_CQE_UNSOLICITED_TYPE +}; + +struct iscsi_virt_sgl_ctx { + struct regpair sgl_base; + struct regpair dsgl_base; + __le32 sgl_initial_offset; + __le32 dsgl_initial_offset; + __le32 dsgl_curr_offset[2]; +}; + +struct iscsi_sgl_var_params { + u8 sgl_ptr; + u8 dsgl_ptr; + __le16 sge_offset; + __le16 dsge_offset; +}; + +struct iscsi_phys_sgl_ctx { + struct regpair sgl_base; + struct regpair dsgl_base; + u8 sgl_size; + u8 dsgl_size; + __le16 reserved; + struct iscsi_sgl_var_params var_params[2]; +}; + +union iscsi_data_desc_ctx { + struct iscsi_virt_sgl_ctx virt_sgl; + struct iscsi_phys_sgl_ctx phys_sgl; + struct iscsi_cached_sge_ctx cached_sge; +}; + +struct iscsi_debug_modes { + u8 flags; +#define ISCSI_DEBUG_MODES_ASSERT_IF_RX_CONN_ERROR_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RX_CONN_ERROR_SHIFT 0 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_RESET_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_RESET_SHIFT 1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_FIN_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_FIN_SHIFT 2 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_CLEANUP_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_CLEANUP_SHIFT 3 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_REJECT_OR_ASYNC_SHIFT 4 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_MASK 0x1 +#define ISCSI_DEBUG_MODES_ASSERT_IF_RECV_NOP_SHIFT 5 +#define ISCSI_DEBUG_MODES_RESERVED0_MASK 0x3 +#define ISCSI_DEBUG_MODES_RESERVED0_SHIFT 6 +}; + +struct iscsi_dif_flags { + u8 flags; +#define ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG_MASK 0xF +#define ISCSI_DIF_FLAGS_PROT_INTERVAL_SIZE_LOG_SHIFT 0 +#define ISCSI_DIF_FLAGS_DIF_TO_PEER_MASK 0x1 +#define ISCSI_DIF_FLAGS_DIF_TO_PEER_SHIFT 4 +#define ISCSI_DIF_FLAGS_HOST_INTERFACE_MASK 0x7 +#define ISCSI_DIF_FLAGS_HOST_INTERFACE_SHIFT 5 +}; + +enum iscsi_eqe_opcode { + ISCSI_EVENT_TYPE_INIT_FUNC = 0, + ISCSI_EVENT_TYPE_DESTROY_FUNC, + ISCSI_EVENT_TYPE_OFFLOAD_CONN, + ISCSI_EVENT_TYPE_UPDATE_CONN, + ISCSI_EVENT_TYPE_CLEAR_SQ, + ISCSI_EVENT_TYPE_TERMINATE_CONN, + ISCSI_EVENT_TYPE_ASYN_CONNECT_COMPLETE, + ISCSI_EVENT_TYPE_ASYN_TERMINATE_DONE, + RESERVED8, + RESERVED9, + ISCSI_EVENT_TYPE_START_OF_ERROR_TYPES = 10, + ISCSI_EVENT_TYPE_ASYN_ABORT_RCVD, + ISCSI_EVENT_TYPE_ASYN_CLOSE_RCVD, + ISCSI_EVENT_TYPE_ASYN_SYN_RCVD, + ISCSI_EVENT_TYPE_ASYN_MAX_RT_TIME, + ISCSI_EVENT_TYPE_ASYN_MAX_RT_CNT, + ISCSI_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, + ISCSI_EVENT_TYPE_ASYN_FIN_WAIT2, + ISCSI_EVENT_TYPE_ISCSI_CONN_ERROR, + ISCSI_EVENT_TYPE_TCP_CONN_ERROR, + ISCSI_EVENT_TYPE_ASYN_DELETE_OOO_ISLES, + MAX_ISCSI_EQE_OPCODE +}; + +enum iscsi_error_types { + ISCSI_STATUS_NONE = 0, + ISCSI_CQE_ERROR_UNSOLICITED_RCV_ON_INVALID_CONN = 1, + ISCSI_CONN_ERROR_TASK_CID_MISMATCH, + ISCSI_CONN_ERROR_TASK_NOT_VALID, + ISCSI_CONN_ERROR_RQ_RING_IS_FULL, + ISCSI_CONN_ERROR_CMDQ_RING_IS_FULL, + ISCSI_CONN_ERROR_HQE_CACHING_FAILED, + ISCSI_CONN_ERROR_HEADER_DIGEST_ERROR, + ISCSI_CONN_ERROR_LOCAL_COMPLETION_ERROR, + ISCSI_CONN_ERROR_DATA_OVERRUN, + ISCSI_CONN_ERROR_OUT_OF_SGES_ERROR, + ISCSI_CONN_ERROR_TCP_SEG_PROC_URG_ERROR, + ISCSI_CONN_ERROR_TCP_SEG_PROC_IP_OPTIONS_ERROR, + ISCSI_CONN_ERROR_TCP_SEG_PROC_CONNECT_INVALID_WS_OPTION, + ISCSI_CONN_ERROR_TCP_IP_FRAGMENT_ERROR, + ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_LEN, + ISCSI_CONN_ERROR_PROTOCOL_ERR_AHS_TYPE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_ITT_OUT_OF_RANGE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_TTT_OUT_OF_RANGE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_EXCEEDS_PDU_SIZE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_OPCODE_BEFORE_UPDATE, + ISCSI_CONN_ERROR_UNVALID_NOPIN_DSL, + ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_CARRIES_NO_DATA, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SN, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_IN_TTT, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_OUT_ITT, + ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_TTT, + ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_BUFFER_OFFSET, + ISCSI_CONN_ERROR_PROTOCOL_ERR_BUFFER_OFFSET_OOO, + ISCSI_CONN_ERROR_PROTOCOL_ERR_R2T_SN, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_0, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_1, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DESIRED_DATA_TRNS_LEN_2, + ISCSI_CONN_ERROR_PROTOCOL_ERR_LUN, + ISCSI_CONN_ERROR_PROTOCOL_ERR_F_BIT_ZERO, + ISCSI_CONN_ERROR_PROTOCOL_ERR_F_BIT_ZERO_S_BIT_ONE, + ISCSI_CONN_ERROR_PROTOCOL_ERR_EXP_STAT_SN, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DSL_NOT_ZERO, + ISCSI_CONN_ERROR_PROTOCOL_ERR_INVALID_DSL, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DATA_SEG_LEN_TOO_BIG, + ISCSI_CONN_ERROR_PROTOCOL_ERR_OUTSTANDING_R2T_COUNT, + ISCSI_CONN_ERROR_PROTOCOL_ERR_DIF_TX, + ISCSI_CONN_ERROR_SENSE_DATA_LENGTH, + ISCSI_CONN_ERROR_DATA_PLACEMENT_ERROR, + ISCSI_ERROR_UNKNOWN, + MAX_ISCSI_ERROR_TYPES +}; + +struct iscsi_mflags { + u8 mflags; +#define ISCSI_MFLAGS_SLOW_IO_MASK 0x1 +#define ISCSI_MFLAGS_SLOW_IO_SHIFT 0 +#define ISCSI_MFLAGS_SINGLE_SGE_MASK 0x1 +#define ISCSI_MFLAGS_SINGLE_SGE_SHIFT 1 +#define ISCSI_MFLAGS_RESERVED_MASK 0x3F +#define ISCSI_MFLAGS_RESERVED_SHIFT 2 +}; + +struct iscsi_sgl { + struct regpair sgl_addr; + __le16 updated_sge_size; + __le16 updated_sge_offset; + __le32 byte_offset; +}; + +union iscsi_mstorm_sgl { + struct iscsi_sgl sgl_struct; + struct iscsi_sge single_sge; +}; + +enum iscsi_ramrod_cmd_id { + ISCSI_RAMROD_CMD_ID_UNUSED = 0, + ISCSI_RAMROD_CMD_ID_INIT_FUNC = 1, + ISCSI_RAMROD_CMD_ID_DESTROY_FUNC = 2, + ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN = 3, + ISCSI_RAMROD_CMD_ID_UPDATE_CONN = 4, + ISCSI_RAMROD_CMD_ID_TERMINATION_CONN = 5, + ISCSI_RAMROD_CMD_ID_CLEAR_SQ = 6, + MAX_ISCSI_RAMROD_CMD_ID +}; + +struct iscsi_reg1 { + __le32 reg1_map; +#define ISCSI_REG1_NUM_FAST_SGES_MASK 0x7 +#define ISCSI_REG1_NUM_FAST_SGES_SHIFT 0 +#define ISCSI_REG1_RESERVED1_MASK 0x1FFFFFFF +#define ISCSI_REG1_RESERVED1_SHIFT 3 +}; + +union iscsi_seq_num { + __le16 data_sn; + __le16 r2t_sn; +}; + +struct iscsi_spe_conn_offload { + struct iscsi_slow_path_hdr hdr; + __le16 conn_id; + __le32 fw_cid; + struct iscsi_conn_offload_params iscsi; + struct tcp_offload_params tcp; +}; + +struct iscsi_spe_conn_offload_option2 { + struct iscsi_slow_path_hdr hdr; + __le16 conn_id; + __le32 fw_cid; + struct iscsi_conn_offload_params iscsi; + struct tcp_offload_params_opt2 tcp; +}; + +struct iscsi_spe_conn_termination { + struct iscsi_slow_path_hdr hdr; + __le16 conn_id; + __le32 fw_cid; + u8 abortive; + u8 reserved0[7]; + struct regpair queue_cnts_addr; + struct regpair query_params_addr; +}; + +struct iscsi_spe_func_dstry { + struct iscsi_slow_path_hdr hdr; + __le16 reserved0; + __le32 reserved1; +}; + +struct iscsi_spe_func_init { + struct iscsi_slow_path_hdr hdr; + __le16 half_way_close_timeout; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 ll2_rx_queue_id; + u8 ooo_enable; + struct iscsi_debug_modes debug_mode; + __le16 reserved1; + __le32 reserved2; + __le32 reserved3; + __le32 reserved4; + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; +}; + +struct ystorm_iscsi_task_state { + union iscsi_data_desc_ctx sgl_ctx_union; + __le32 buffer_offset[2]; + __le16 bytes_nxt_dif; + __le16 rxmit_bytes_nxt_dif; + union iscsi_seq_num seq_num_union; + u8 dif_bytes_leftover; + u8 rxmit_dif_bytes_leftover; + __le16 reuse_count; + struct iscsi_dif_flags dif_flags; + u8 local_comp; + __le32 exp_r2t_sn; + __le32 sgl_offset[2]; +}; + +struct ystorm_iscsi_task_st_ctx { + struct ystorm_iscsi_task_state state; + union iscsi_task_hdr pdu_hdr; +}; + +struct ystorm_iscsi_task_ag_ctx { + u8 reserved; + u8 byte1; + __le16 word0; + u8 flags0; +#define YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define YSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT3_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT3_SHIFT 7 + u8 flags1; +#define YSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 +#define YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; +#define YSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 + u8 byte2; + __le32 TTT; + u8 byte3; + u8 byte4; + __le16 word1; +}; + +struct mstorm_iscsi_task_ag_ctx { + u8 cdu_validation; + u8 byte1; + __le16 task_cid; + u8 flags0; +#define MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define MSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 + u8 flags1; +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; +#define MSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 + u8 byte2; + __le32 reg0; + u8 byte3; + u8 byte4; + __le16 word1; +}; + +struct ustorm_iscsi_task_ag_ctx { + u8 reserved; + u8 state; + __le16 icid; + u8 flags0; +#define USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 + u8 flags1; +#define USTORM_ISCSI_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define USTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 + u8 flags3; +#define USTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 rcv_cont_len; + __le32 exp_cont_len; + __le32 total_data_acked; + __le32 exp_data_acked; + u8 next_tid_valid; + u8 byte3; + __le16 word1; + __le16 next_tid; + __le16 word3; + __le32 hdr_residual_count; + __le32 exp_r2t_sn; +}; + +struct mstorm_iscsi_task_st_ctx { + union iscsi_mstorm_sgl sgl_union; + struct iscsi_dif_flags dif_flags; + struct iscsi_mflags flags; + u8 sgl_size; + u8 host_sge_index; + __le16 dix_cur_sge_offset; + __le16 dix_cur_sge_size; + __le32 data_offset_rtid; + u8 dif_offset; + u8 dix_sgl_size; + u8 dix_sge_index; + u8 task_type; + struct regpair sense_db; + struct regpair dix_sgl_cur_sge; + __le32 rem_task_size; + __le16 reuse_count; + __le16 dif_data_residue; + u8 reserved0[4]; + __le32 reserved1[1]; +}; + +struct ustorm_iscsi_task_st_ctx { + __le32 rem_rcv_len; + __le32 exp_data_transfer_len; + __le32 exp_data_sn; + struct regpair lun; + struct iscsi_reg1 reg1; + u8 flags2; +#define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_AHS_EXIST_SHIFT 0 +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_MASK 0x7F +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED1_SHIFT 1 + u8 reserved2; + __le16 reserved3; + __le32 reserved4; + __le32 reserved5; + __le32 reserved6; + __le32 reserved7; + u8 task_type; + u8 error_flags; +#define USTORM_ISCSI_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0 +#define USTORM_ISCSI_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1 +#define USTORM_ISCSI_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2 +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED8_MASK 0x1F +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED8_SHIFT 3 + u8 flags; +#define USTORM_ISCSI_TASK_ST_CTX_CQE_WRITE_MASK 0x3 +#define USTORM_ISCSI_TASK_ST_CTX_CQE_WRITE_SHIFT 0 +#define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 +#define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 +#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_TOTALDATAACKED_DONE_SHIFT 4 +#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_HQSCANNED_DONE_SHIFT 5 +#define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_MASK 0x1 +#define USTORM_ISCSI_TASK_ST_CTX_RESERVED0_SHIFT 7 + u8 cq_rss_number; +}; + +struct iscsi_task_context { + struct ystorm_iscsi_task_st_ctx ystorm_st_context; + struct regpair ystorm_st_padding[2]; + struct ystorm_iscsi_task_ag_ctx ystorm_ag_context; + struct regpair ystorm_ag_padding[2]; + struct tdif_task_context tdif_context; + struct mstorm_iscsi_task_ag_ctx mstorm_ag_context; + struct regpair mstorm_ag_padding[2]; + struct ustorm_iscsi_task_ag_ctx ustorm_ag_context; + struct mstorm_iscsi_task_st_ctx mstorm_st_context; + struct ustorm_iscsi_task_st_ctx ustorm_st_context; + struct rdif_task_context rdif_context; +}; + +enum iscsi_task_type { + ISCSI_TASK_TYPE_INITIATOR_WRITE, + ISCSI_TASK_TYPE_INITIATOR_READ, + ISCSI_TASK_TYPE_MIDPATH, + ISCSI_TASK_TYPE_UNSOLIC, + ISCSI_TASK_TYPE_EXCHCLEANUP, + ISCSI_TASK_TYPE_IRRELEVANT, + ISCSI_TASK_TYPE_TARGET_WRITE, + ISCSI_TASK_TYPE_TARGET_READ, + ISCSI_TASK_TYPE_TARGET_RESPONSE, + ISCSI_TASK_TYPE_LOGIN_RESPONSE, + MAX_ISCSI_TASK_TYPE +}; + +union iscsi_ttt_txlen_union { + __le32 desired_tx_len; + __le32 ttt; +}; + +struct iscsi_uhqe { + __le32 reg1; +#define ISCSI_UHQE_PDU_PAYLOAD_LEN_MASK 0xFFFFF +#define ISCSI_UHQE_PDU_PAYLOAD_LEN_SHIFT 0 +#define ISCSI_UHQE_LOCAL_COMP_MASK 0x1 +#define ISCSI_UHQE_LOCAL_COMP_SHIFT 20 +#define ISCSI_UHQE_TOGGLE_BIT_MASK 0x1 +#define ISCSI_UHQE_TOGGLE_BIT_SHIFT 21 +#define ISCSI_UHQE_PURE_PAYLOAD_MASK 0x1 +#define ISCSI_UHQE_PURE_PAYLOAD_SHIFT 22 +#define ISCSI_UHQE_LOGIN_RESPONSE_PDU_MASK 0x1 +#define ISCSI_UHQE_LOGIN_RESPONSE_PDU_SHIFT 23 +#define ISCSI_UHQE_TASK_ID_HI_MASK 0xFF +#define ISCSI_UHQE_TASK_ID_HI_SHIFT 24 + __le32 reg2; +#define ISCSI_UHQE_BUFFER_OFFSET_MASK 0xFFFFFF +#define ISCSI_UHQE_BUFFER_OFFSET_SHIFT 0 +#define ISCSI_UHQE_TASK_ID_LO_MASK 0xFF +#define ISCSI_UHQE_TASK_ID_LO_SHIFT 24 +}; + +struct iscsi_wqe_field { + __le32 contlen_cdbsize_field; +#define ISCSI_WQE_FIELD_CONT_LEN_MASK 0xFFFFFF +#define ISCSI_WQE_FIELD_CONT_LEN_SHIFT 0 +#define ISCSI_WQE_FIELD_CDB_SIZE_MASK 0xFF +#define ISCSI_WQE_FIELD_CDB_SIZE_SHIFT 24 +}; + +union iscsi_wqe_field_union { + struct iscsi_wqe_field cont_field; + __le32 prev_tid; +}; + +struct iscsi_wqe { + __le16 task_id; + u8 flags; +#define ISCSI_WQE_WQE_TYPE_MASK 0x7 +#define ISCSI_WQE_WQE_TYPE_SHIFT 0 +#define ISCSI_WQE_NUM_FAST_SGES_MASK 0x7 +#define ISCSI_WQE_NUM_FAST_SGES_SHIFT 3 +#define ISCSI_WQE_PTU_INVALIDATE_MASK 0x1 +#define ISCSI_WQE_PTU_INVALIDATE_SHIFT 6 +#define ISCSI_WQE_RESPONSE_MASK 0x1 +#define ISCSI_WQE_RESPONSE_SHIFT 7 + struct iscsi_dif_flags prot_flags; + union iscsi_wqe_field_union cont_prevtid_union; +}; + +enum iscsi_wqe_type { + ISCSI_WQE_TYPE_NORMAL, + ISCSI_WQE_TYPE_TASK_CLEANUP, + ISCSI_WQE_TYPE_MIDDLE_PATH, + ISCSI_WQE_TYPE_LOGIN, + ISCSI_WQE_TYPE_FIRST_R2T_CONT, + ISCSI_WQE_TYPE_NONFIRST_R2T_CONT, + ISCSI_WQE_TYPE_RESPONSE, + MAX_ISCSI_WQE_TYPE +}; + +struct iscsi_xhqe { + union iscsi_ttt_txlen_union ttt_or_txlen; + __le32 exp_stat_sn; + struct iscsi_dif_flags prot_flags; + u8 total_ahs_length; + u8 opcode; + u8 flags; +#define ISCSI_XHQE_NUM_FAST_SGES_MASK 0x7 +#define ISCSI_XHQE_NUM_FAST_SGES_SHIFT 0 +#define ISCSI_XHQE_FINAL_MASK 0x1 +#define ISCSI_XHQE_FINAL_SHIFT 3 +#define ISCSI_XHQE_SUPER_IO_MASK 0x1 +#define ISCSI_XHQE_SUPER_IO_SHIFT 4 +#define ISCSI_XHQE_STATUS_BIT_MASK 0x1 +#define ISCSI_XHQE_STATUS_BIT_SHIFT 5 +#define ISCSI_XHQE_RESERVED_MASK 0x3 +#define ISCSI_XHQE_RESERVED_SHIFT 6 + union iscsi_seq_num seq_num_union; + __le16 reserved1; +}; + +struct mstorm_iscsi_stats_drv { + struct regpair iscsi_rx_dropped_pdus_task_not_valid; +}; + +struct ooo_opaque { + __le32 cid; + u8 drop_isle; + u8 drop_size; + u8 ooo_opcode; + u8 ooo_isle; +}; + +struct pstorm_iscsi_stats_drv { + struct regpair iscsi_tx_bytes_cnt; + struct regpair iscsi_tx_packet_cnt; +}; + +struct tstorm_iscsi_stats_drv { + struct regpair iscsi_rx_bytes_cnt; + struct regpair iscsi_rx_packet_cnt; + struct regpair iscsi_rx_new_ooo_isle_events_cnt; + __le32 iscsi_cmdq_threshold_cnt; + __le32 iscsi_rq_threshold_cnt; + __le32 iscsi_immq_threshold_cnt; +}; + +struct ustorm_iscsi_stats_drv { + struct regpair iscsi_rx_data_pdu_cnt; + struct regpair iscsi_rx_r2t_pdu_cnt; + struct regpair iscsi_rx_total_pdu_cnt; +}; + +struct xstorm_iscsi_stats_drv { + struct regpair iscsi_tx_go_to_slow_start_event_cnt; + struct regpair iscsi_tx_fast_retransmit_event_cnt; +}; + +struct ystorm_iscsi_stats_drv { + struct regpair iscsi_tx_data_pdu_cnt; + struct regpair iscsi_tx_r2t_pdu_cnt; + struct regpair iscsi_tx_total_pdu_cnt; +}; + +struct iscsi_db_data { + u8 params; +#define ISCSI_DB_DATA_DEST_MASK 0x3 +#define ISCSI_DB_DATA_DEST_SHIFT 0 +#define ISCSI_DB_DATA_AGG_CMD_MASK 0x3 +#define ISCSI_DB_DATA_AGG_CMD_SHIFT 2 +#define ISCSI_DB_DATA_BYPASS_EN_MASK 0x1 +#define ISCSI_DB_DATA_BYPASS_EN_SHIFT 4 +#define ISCSI_DB_DATA_RESERVED_MASK 0x1 +#define ISCSI_DB_DATA_RESERVED_SHIFT 5 +#define ISCSI_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 sq_prod; +}; + +struct tstorm_iscsi_task_ag_ctx { + u8 byte0; + u8 byte1; + __le16 word0; + u8 flags0; +#define TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT2_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT3_SHIFT 7 + u8 flags1; +#define TSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT5_SHIFT 1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 6 + u8 flags2; +#define TSTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6_SHIFT 6 + u8 flags3; +#define TSTORM_ISCSI_TASK_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4EN_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5EN_SHIFT 7 + u8 flags4; +#define TSTORM_ISCSI_TASK_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6EN_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7EN_SHIFT 1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 3 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 7 + u8 byte2; + __le16 word1; + __le32 reg0; + u8 byte3; + u8 byte4; + __le16 word2; + __le16 word3; + __le16 word4; + __le32 reg1; + __le32 reg2; +}; + +#endif /* __ISCSI_COMMON__ */ diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h new file mode 100644 index 000000000000..187991c1f439 --- /dev/null +++ b/include/linux/qed/rdma_common.h @@ -0,0 +1,44 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __RDMA_COMMON__ +#define __RDMA_COMMON__ +/************************/ +/* RDMA FW CONSTANTS */ +/************************/ + +#define RDMA_RESERVED_LKEY (0) +#define RDMA_RING_PAGE_SIZE (0x1000) + +#define RDMA_MAX_SGE_PER_SQ_WQE (4) +#define RDMA_MAX_SGE_PER_RQ_WQE (4) + +#define RDMA_MAX_DATA_SIZE_IN_WQE (0x7FFFFFFF) + +#define RDMA_REQ_RD_ATOMIC_ELM_SIZE (0x50) +#define RDMA_RESP_RD_ATOMIC_ELM_SIZE (0x20) + +#define RDMA_MAX_CQS (64 * 1024) +#define RDMA_MAX_TIDS (128 * 1024 - 1) +#define RDMA_MAX_PDS (64 * 1024) + +#define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS + +#define RDMA_TASK_TYPE (PROTOCOLID_ROCE) + +struct rdma_srq_id { + __le16 srq_idx; + __le16 opaque_fid; +}; + +struct rdma_srq_producers { + __le32 sge_prod; + __le32 wqe_prod; +}; + +#endif /* __RDMA_COMMON__ */ diff --git a/include/linux/qed/roce_common.h b/include/linux/qed/roce_common.h new file mode 100644 index 000000000000..2eeaf3dc6646 --- /dev/null +++ b/include/linux/qed/roce_common.h @@ -0,0 +1,17 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __ROCE_COMMON__ +#define __ROCE_COMMON__ + +#define ROCE_REQ_MAX_INLINE_DATA_SIZE (256) +#define ROCE_REQ_MAX_SINGLE_SQ_WQE_SIZE (288) + +#define ROCE_MAX_QPS (32 * 1024) + +#endif /* __ROCE_COMMON__ */ diff --git a/include/linux/qed/storage_common.h b/include/linux/qed/storage_common.h new file mode 100644 index 000000000000..3b8e1efd9bc2 --- /dev/null +++ b/include/linux/qed/storage_common.h @@ -0,0 +1,91 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __STORAGE_COMMON__ +#define __STORAGE_COMMON__ + +#define NUM_OF_CMDQS_CQS (NUM_OF_GLOBAL_QUEUES / 2) +#define BDQ_NUM_RESOURCES (4) + +#define BDQ_ID_RQ (0) +#define BDQ_ID_IMM_DATA (1) +#define BDQ_NUM_IDS (2) + +#define BDQ_MAX_EXTERNAL_RING_SIZE (1 << 15) + +struct scsi_bd { + struct regpair address; + struct regpair opaque; +}; + +struct scsi_bdq_ram_drv_data { + __le16 external_producer; + __le16 reserved0[3]; +}; + +struct scsi_drv_cmdq { + __le16 cmdq_cons; + __le16 reserved0; + __le32 reserved1; +}; + +struct scsi_init_func_params { + __le16 num_tasks; + u8 log_page_size; + u8 debug_mode; + u8 reserved2[12]; +}; + +struct scsi_init_func_queues { + struct regpair glbl_q_params_addr; + __le16 rq_buffer_size; + __le16 cq_num_entries; + __le16 cmdq_num_entries; + u8 bdq_resource_id; + u8 q_validity; +#define SCSI_INIT_FUNC_QUEUES_RQ_VALID_MASK 0x1 +#define SCSI_INIT_FUNC_QUEUES_RQ_VALID_SHIFT 0 +#define SCSI_INIT_FUNC_QUEUES_IMM_DATA_VALID_MASK 0x1 +#define SCSI_INIT_FUNC_QUEUES_IMM_DATA_VALID_SHIFT 1 +#define SCSI_INIT_FUNC_QUEUES_CMD_VALID_MASK 0x1 +#define SCSI_INIT_FUNC_QUEUES_CMD_VALID_SHIFT 2 +#define SCSI_INIT_FUNC_QUEUES_RESERVED_VALID_MASK 0x1F +#define SCSI_INIT_FUNC_QUEUES_RESERVED_VALID_SHIFT 3 + u8 num_queues; + u8 queue_relative_offset; + u8 cq_sb_pi; + u8 cmdq_sb_pi; + __le16 cq_cmdq_sb_num_arr[NUM_OF_CMDQS_CQS]; + __le16 reserved0; + u8 bdq_pbl_num_entries[BDQ_NUM_IDS]; + struct regpair bdq_pbl_base_address[BDQ_NUM_IDS]; + __le16 bdq_xoff_threshold[BDQ_NUM_IDS]; + __le16 bdq_xon_threshold[BDQ_NUM_IDS]; + __le16 cmdq_xoff_threshold; + __le16 cmdq_xon_threshold; + __le32 reserved1; +}; + +struct scsi_ram_per_bdq_resource_drv_data { + struct scsi_bdq_ram_drv_data drv_data_per_bdq_id[BDQ_NUM_IDS]; +}; + +struct scsi_sge { + struct regpair sge_addr; + __le16 sge_len; + __le16 reserved0; + __le32 reserved1; +}; + +struct scsi_terminate_extra_params { + __le16 unsolicited_cq_count; + __le16 cmdq_count; + u8 reserved[4]; +}; + +#endif /* __STORAGE_COMMON__ */ diff --git a/include/linux/qed/tcp_common.h b/include/linux/qed/tcp_common.h new file mode 100644 index 000000000000..accba0e6b704 --- /dev/null +++ b/include/linux/qed/tcp_common.h @@ -0,0 +1,226 @@ +/* QLogic qed NIC Driver + * Copyright (c) 2015 QLogic Corporation + * + * This software is available under the terms of the GNU General Public License + * (GPL) Version 2, available from the file COPYING in the main directory of + * this source tree. + */ + +#ifndef __TCP_COMMON__ +#define __TCP_COMMON__ + +#define TCP_INVALID_TIMEOUT_VAL -1 + +enum tcp_connect_mode { + TCP_CONNECT_ACTIVE, + TCP_CONNECT_PASSIVE, + MAX_TCP_CONNECT_MODE +}; + +struct tcp_init_params { + __le32 max_cwnd; + __le16 dup_ack_threshold; + __le16 tx_sws_timer; + __le16 min_rto; + __le16 min_rto_rt; + __le16 max_rto; + u8 maxfinrt; + u8 reserved[1]; +}; + +enum tcp_ip_version { + TCP_IPV4, + TCP_IPV6, + MAX_TCP_IP_VERSION +}; + +struct tcp_offload_params { + __le16 local_mac_addr_lo; + __le16 local_mac_addr_mid; + __le16 local_mac_addr_hi; + __le16 remote_mac_addr_lo; + __le16 remote_mac_addr_mid; + __le16 remote_mac_addr_hi; + __le16 vlan_id; + u8 flags; +#define TCP_OFFLOAD_PARAMS_TS_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_TS_EN_SHIFT 0 +#define TCP_OFFLOAD_PARAMS_DA_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_DA_EN_SHIFT 1 +#define TCP_OFFLOAD_PARAMS_KA_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_KA_EN_SHIFT 2 +#define TCP_OFFLOAD_PARAMS_NAGLE_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_NAGLE_EN_SHIFT 3 +#define TCP_OFFLOAD_PARAMS_DA_CNT_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_DA_CNT_EN_SHIFT 4 +#define TCP_OFFLOAD_PARAMS_FIN_SENT_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_FIN_SENT_SHIFT 5 +#define TCP_OFFLOAD_PARAMS_FIN_RECEIVED_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_FIN_RECEIVED_SHIFT 6 +#define TCP_OFFLOAD_PARAMS_RESERVED0_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_RESERVED0_SHIFT 7 + u8 ip_version; + __le32 remote_ip[4]; + __le32 local_ip[4]; + __le32 flow_label; + u8 ttl; + u8 tos_or_tc; + __le16 remote_port; + __le16 local_port; + __le16 mss; + u8 rcv_wnd_scale; + u8 connect_mode; + __le16 srtt; + __le32 cwnd; + __le32 ss_thresh; + __le16 reserved1; + u8 ka_max_probe_cnt; + u8 dup_ack_theshold; + __le32 rcv_next; + __le32 snd_una; + __le32 snd_next; + __le32 snd_max; + __le32 snd_wnd; + __le32 rcv_wnd; + __le32 snd_wl1; + __le32 ts_time; + __le32 ts_recent; + __le32 ts_recent_age; + __le32 total_rt; + __le32 ka_timeout_delta; + __le32 rt_timeout_delta; + u8 dup_ack_cnt; + u8 snd_wnd_probe_cnt; + u8 ka_probe_cnt; + u8 rt_cnt; + __le16 rtt_var; + __le16 reserved2; + __le32 ka_timeout; + __le32 ka_interval; + __le32 max_rt_time; + __le32 initial_rcv_wnd; + u8 snd_wnd_scale; + u8 ack_frequency; + __le16 da_timeout_value; + __le32 ts_ticks_per_second; +}; + +struct tcp_offload_params_opt2 { + __le16 local_mac_addr_lo; + __le16 local_mac_addr_mid; + __le16 local_mac_addr_hi; + __le16 remote_mac_addr_lo; + __le16 remote_mac_addr_mid; + __le16 remote_mac_addr_hi; + __le16 vlan_id; + u8 flags; +#define TCP_OFFLOAD_PARAMS_OPT2_TS_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_OPT2_TS_EN_SHIFT 0 +#define TCP_OFFLOAD_PARAMS_OPT2_DA_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_OPT2_DA_EN_SHIFT 1 +#define TCP_OFFLOAD_PARAMS_OPT2_KA_EN_MASK 0x1 +#define TCP_OFFLOAD_PARAMS_OPT2_KA_EN_SHIFT 2 +#define TCP_OFFLOAD_PARAMS_OPT2_RESERVED0_MASK 0x1F +#define TCP_OFFLOAD_PARAMS_OPT2_RESERVED0_SHIFT 3 + u8 ip_version; + __le32 remote_ip[4]; + __le32 local_ip[4]; + __le32 flow_label; + u8 ttl; + u8 tos_or_tc; + __le16 remote_port; + __le16 local_port; + __le16 mss; + u8 rcv_wnd_scale; + u8 connect_mode; + __le16 syn_ip_payload_length; + __le32 syn_phy_addr_lo; + __le32 syn_phy_addr_hi; + __le32 reserved1[22]; +}; + +enum tcp_seg_placement_event { + TCP_EVENT_ADD_PEN, + TCP_EVENT_ADD_NEW_ISLE, + TCP_EVENT_ADD_ISLE_RIGHT, + TCP_EVENT_ADD_ISLE_LEFT, + TCP_EVENT_JOIN, + TCP_EVENT_NOP, + MAX_TCP_SEG_PLACEMENT_EVENT +}; + +struct tcp_update_params { + __le16 flags; +#define TCP_UPDATE_PARAMS_REMOTE_MAC_ADDR_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_REMOTE_MAC_ADDR_CHANGED_SHIFT 0 +#define TCP_UPDATE_PARAMS_MSS_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_MSS_CHANGED_SHIFT 1 +#define TCP_UPDATE_PARAMS_TTL_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_TTL_CHANGED_SHIFT 2 +#define TCP_UPDATE_PARAMS_TOS_OR_TC_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_TOS_OR_TC_CHANGED_SHIFT 3 +#define TCP_UPDATE_PARAMS_KA_TIMEOUT_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_TIMEOUT_CHANGED_SHIFT 4 +#define TCP_UPDATE_PARAMS_KA_INTERVAL_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_INTERVAL_CHANGED_SHIFT 5 +#define TCP_UPDATE_PARAMS_MAX_RT_TIME_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_MAX_RT_TIME_CHANGED_SHIFT 6 +#define TCP_UPDATE_PARAMS_FLOW_LABEL_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_FLOW_LABEL_CHANGED_SHIFT 7 +#define TCP_UPDATE_PARAMS_INITIAL_RCV_WND_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_INITIAL_RCV_WND_CHANGED_SHIFT 8 +#define TCP_UPDATE_PARAMS_KA_MAX_PROBE_CNT_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_MAX_PROBE_CNT_CHANGED_SHIFT 9 +#define TCP_UPDATE_PARAMS_KA_EN_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_EN_CHANGED_SHIFT 10 +#define TCP_UPDATE_PARAMS_NAGLE_EN_CHANGED_MASK 0x1 +#define TCP_UPDATE_PARAMS_NAGLE_EN_CHANGED_SHIFT 11 +#define TCP_UPDATE_PARAMS_KA_EN_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_EN_SHIFT 12 +#define TCP_UPDATE_PARAMS_NAGLE_EN_MASK 0x1 +#define TCP_UPDATE_PARAMS_NAGLE_EN_SHIFT 13 +#define TCP_UPDATE_PARAMS_KA_RESTART_MASK 0x1 +#define TCP_UPDATE_PARAMS_KA_RESTART_SHIFT 14 +#define TCP_UPDATE_PARAMS_RETRANSMIT_RESTART_MASK 0x1 +#define TCP_UPDATE_PARAMS_RETRANSMIT_RESTART_SHIFT 15 + __le16 remote_mac_addr_lo; + __le16 remote_mac_addr_mid; + __le16 remote_mac_addr_hi; + __le16 mss; + u8 ttl; + u8 tos_or_tc; + __le32 ka_timeout; + __le32 ka_interval; + __le32 max_rt_time; + __le32 flow_label; + __le32 initial_rcv_wnd; + u8 ka_max_probe_cnt; + u8 reserved1[7]; +}; + +struct tcp_upload_params { + __le32 rcv_next; + __le32 snd_una; + __le32 snd_next; + __le32 snd_max; + __le32 snd_wnd; + __le32 rcv_wnd; + __le32 snd_wl1; + __le32 cwnd; + __le32 ss_thresh; + __le16 srtt; + __le16 rtt_var; + __le32 ts_time; + __le32 ts_recent; + __le32 ts_recent_age; + __le32 total_rt; + __le32 ka_timeout_delta; + __le32 rt_timeout_delta; + u8 dup_ack_cnt; + u8 snd_wnd_probe_cnt; + u8 ka_probe_cnt; + u8 rt_cnt; + __le32 reserved; +}; + +#endif /* __TCP_COMMON__ */ -- cgit v1.2.3 From c5ac93191d7e6977c5c3465ac94c73ebb8a8ecba Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Fri, 3 Jun 2016 14:35:34 +0300 Subject: qed: Add iscsi/rdma personalities This patch adds in the ecore 2 new personalities in addition to QED_PCI_ETH - QED_PCI_ISCSI and QED_PCI_ETH_ROCE. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/common_hsi.h | 4 +-- include/linux/qed/qed_if.h | 65 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 077a3b6cc80f..40c0ada01806 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -517,9 +517,9 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { - PROTOCOLID_RESERVED1, + PROTOCOLID_ISCSI, PROTOCOLID_RESERVED2, - PROTOCOLID_RESERVED3, + PROTOCOLID_ROCE, PROTOCOLID_CORE, PROTOCOLID_ETH, PROTOCOLID_RESERVED4, diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 15efccfdc46e..e8cc49f9688a 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -58,8 +58,70 @@ struct qed_eth_pf_params { u16 num_cons; }; +/* Most of the the parameters below are described in the FW iSCSI / TCP HSI */ +struct qed_iscsi_pf_params { + u64 glbl_q_params_addr; + u64 bdq_pbl_base_addr[2]; + u32 max_cwnd; + u16 cq_num_entries; + u16 cmdq_num_entries; + u16 dup_ack_threshold; + u16 tx_sws_timer; + u16 min_rto; + u16 min_rto_rt; + u16 max_rto; + + /* The following parameters are used during HW-init + * and these parameters need to be passed as arguments + * to update_pf_params routine invoked before slowpath start + */ + u16 num_cons; + u16 num_tasks; + + /* The following parameters are used during protocol-init */ + u16 half_way_close_timeout; + u16 bdq_xoff_threshold[2]; + u16 bdq_xon_threshold[2]; + u16 cmdq_xoff_threshold; + u16 cmdq_xon_threshold; + u16 rq_buffer_size; + + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 num_queues; + u8 log_page_size; + u8 rqe_log_size; + u8 max_fin_rt; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 ll2_ooo_queue_id; + u8 ooo_enable; + + u8 is_target; + u8 bdq_pbl_num_entries[2]; +}; + +struct qed_rdma_pf_params { + /* Supplied to QED during resource allocation (may affect the ILT and + * the doorbell BAR). + */ + u32 min_dpis; /* number of requested DPIs */ + u32 num_mrs; /* number of requested memory regions */ + u32 num_qps; /* number of requested Queue Pairs */ + u32 num_srqs; /* number of requested SRQ */ + u8 roce_edpm_mode; /* see QED_ROCE_EDPM_MODE_ENABLE */ + u8 gl_pi; /* protocol index */ + + /* Will allocate rate limiters to be used with QPs */ + u8 enable_dcqcn; +}; + struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; + struct qed_iscsi_pf_params iscsi_pf_params; + struct qed_rdma_pf_params rdma_pf_params; }; enum qed_int_mode { @@ -100,6 +162,8 @@ struct qed_dev_info { /* MFW version */ u32 mfw_rev; + bool rdma_supported; + u32 flash_size; u8 mf_mode; bool tx_switching; @@ -111,6 +175,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, + QED_PROTOCOL_ISCSI, }; struct qed_link_params { -- cgit v1.2.3 From 81b1251d3b761b303955408dd6a49618b5683c2b Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sat, 4 Jun 2016 08:20:16 +0300 Subject: qed: Fix next-ptr chains for BE / 32-bit Commit a91eb52abb50 ("qed: Revisit chain implementation") contains an incorrect implementation for BE platforms, as device's regpairs containing addresses are LE and they're not converted correctly when read back. In addition, it raises a compilation warning for 32-bit platforms where dma_addr_t is a 32-bit variable. Reported-by: kbuild test robot Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index eceaa9ed2ae9..7e441bdeabdc 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -25,10 +25,9 @@ } while (0) #define HILO_GEN(hi, lo, type) ((((type)(hi)) << 32) + (lo)) -#define HILO_DMA(hi, lo) HILO_GEN(hi, lo, dma_addr_t) #define HILO_64(hi, lo) HILO_GEN((le32_to_cpu(hi)), (le32_to_cpu(lo)), u64) -#define HILO_DMA_REGPAIR(regpair) (HILO_DMA(regpair.hi, regpair.lo)) #define HILO_64_REGPAIR(regpair) (HILO_64(regpair.hi, regpair.lo)) +#define HILO_DMA_REGPAIR(regpair) ((dma_addr_t)HILO_64_REGPAIR(regpair)) enum qed_chain_mode { /* Each Page contains a next pointer at its end */ -- cgit v1.2.3 From c8b098086b4c744084350d2757a637ad756adf34 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:16:57 +0200 Subject: net: dsa: Add a ports structure and use it in the switch structure There are going to be more per-port members added to the switch structure. So add a port structure and move the netdev into it. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 17c3d37b6779..9aed8572037c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -119,6 +119,10 @@ struct dsa_switch_tree { struct dsa_switch *ds[DSA_MAX_SWITCHES]; }; +struct dsa_port { + struct net_device *netdev; +}; + struct dsa_switch { struct device *dev; @@ -158,8 +162,8 @@ struct dsa_switch { u32 dsa_port_mask; u32 enabled_port_mask; u32 phys_mii_mask; + struct dsa_port ports[DSA_MAX_PORTS]; struct mii_bus *slave_mii_bus; - struct net_device *ports[DSA_MAX_PORTS]; }; static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) @@ -174,7 +178,7 @@ static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) { - return ds->enabled_port_mask & (1 << p) && ds->ports[p]; + return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; } static inline u8 dsa_upstream_port(struct dsa_switch *ds) -- cgit v1.2.3 From 189b0d93ec61e1f991e96d7bc03b03cf929d164c Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:16:58 +0200 Subject: net: dsa: Move port device node into port structure Move the port device node structure into the port structure, from the chip data. This information is needed in the next step of implementing the new binding. The chip data structure is used while parsing the whole old binding, before the individual switch structures exist. With the new bindings, this is reversed, the switches exist first, and the interconnections between the switches is derived from the individual switch bindings. Thus this chip data structure becomes unneeded. Signed-off-by: Andrew Lunn eviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 9aed8572037c..8314197d028f 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -121,6 +121,7 @@ struct dsa_switch_tree { struct dsa_port { struct net_device *netdev; + struct device_node *dn; }; struct dsa_switch { -- cgit v1.2.3 From 4a7704ffa86705b0580b6473c407b7b7618e072d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:16:59 +0200 Subject: net: dsa: Remove dynamic allocate of routing table With a maximum of four switches, the size of the routing table is the same as the pointer to it. Removing it makes the code simpler. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 8314197d028f..4e3afa9648ca 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -58,12 +58,11 @@ struct dsa_chip_data { struct device_node *port_dn[DSA_MAX_PORTS]; /* - * An array (with nr_chips elements) of which element [a] - * indicates which port on this switch should be used to - * send packets to that are destined for switch a. Can be - * NULL if there is only one switch chip. + * An array of which element [a] indicates which port on this + * switch should be used to send packets to that are destined + * for switch a. Can be NULL if there is only one switch chip. */ - s8 *rtable; + s8 rtable[DSA_MAX_SWITCHES]; }; struct dsa_platform_data { -- cgit v1.2.3 From 66472fc04e8be62858f29c7798ed17e984c1ab3b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:17:00 +0200 Subject: net: dsa: Copy the routing table into the switch structure The new binding will not have a chip data structure, it will place the routing directly into the switch structure. To enable backwards compatibility, copy the routing from the chip data into the switch structure. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 4e3afa9648ca..b666f27b3daa 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -148,6 +148,13 @@ struct dsa_switch { */ struct dsa_switch_driver *drv; + /* + * An array of which element [a] indicates which port on this + * switch should be used to send packets to that are destined + * for switch a. Can be NULL if there is only one switch chip. + */ + s8 rtable[DSA_MAX_SWITCHES]; + #ifdef CONFIG_NET_DSA_HWMON /* * Hardware monitoring information @@ -194,7 +201,7 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) if (dst->cpu_switch == ds->index) return dst->cpu_port; else - return ds->cd->rtable[dst->cpu_switch]; + return ds->rtable[dst->cpu_switch]; } struct switchdev_trans; -- cgit v1.2.3 From 39a7f2a4eb496c0c68cc93fcb403190b48605168 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:17:03 +0200 Subject: net: dsa: Refactor selection of tag ops into a function Replace the two switch statements with an array lookup, and store the result in the dsa tree structure. The drivers no longer need to know the selected tag protocol, so remove it from the dsa switch structure. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index b666f27b3daa..bd6ecaa0de96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -26,6 +26,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_TRAILER, DSA_TAG_PROTO_EDSA, DSA_TAG_PROTO_BRCM, + DSA_TAG_LAST, /* MUST BE LAST */ }; #define DSA_MAX_SWITCHES 4 @@ -99,7 +100,6 @@ struct dsa_switch_tree { struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); - enum dsa_tag_protocol tag_protocol; /* * Original copy of the master netdev ethtool_ops @@ -116,6 +116,12 @@ struct dsa_switch_tree { * Data for the individual switch chips. */ struct dsa_switch *ds[DSA_MAX_SWITCHES]; + + /* + * Tagging protocol operations for adding and removing an + * encapsulation tag. + */ + const struct dsa_device_ops *tag_ops; }; struct dsa_port { -- cgit v1.2.3 From 83c0afaec7b730b16c518aecc8e6246ec91b265e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sat, 4 Jun 2016 21:17:07 +0200 Subject: net: dsa: Add new binding implementation The existing DSA binding has a number of limitations and problems. The main problem is that it cannot represent a switch as a linux device, hanging off some bus. It is limited to one CPU port. The DSA platform device is artificial, and does not really represent hardware. Implement a new binding which can be embedded into any type of node on a bus to represent one switch device, and its links to other switches. Signed-off-by: Andrew Lunn Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index bd6ecaa0de96..cca7ef230742 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -85,6 +85,17 @@ struct dsa_platform_data { struct packet_type; struct dsa_switch_tree { + struct list_head list; + + /* Tree identifier */ + u32 tree; + + /* Number of switches attached to this tree */ + struct kref refcount; + + /* Has this tree been applied to the hardware? */ + bool applied; + /* * Configuration data for the platform device that owns * this dsa switch tree instance. @@ -169,10 +180,16 @@ struct dsa_switch { struct device *hwmon_dev; #endif + /* + * The lower device this switch uses to talk to the host + */ + struct net_device *master_netdev; + /* * Slave mii_bus and devices for the individual ports. */ u32 dsa_port_mask; + u32 cpu_port_mask; u32 enabled_port_mask; u32 phys_mii_mask; struct dsa_port ports[DSA_MAX_PORTS]; @@ -361,4 +378,7 @@ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { return dst->rcv != NULL; } + +void dsa_unregister_switch(struct dsa_switch *ds); +int dsa_register_switch(struct dsa_switch *ds, struct device_node *np); #endif -- cgit v1.2.3 From 6eb17e0df74c036eba7548915b37f009403fe09e Mon Sep 17 00:00:00 2001 From: Kejian Yan Date: Fri, 3 Jun 2016 10:55:09 +0800 Subject: ACPI: bus: add stub acpi_dev_found() to linux/acpi.h acpi_dev_found() will be used to detect if a given ACPI device is in the system. It will be compiled in non-ACPI case, but the function is in acpi_bus.h and acpi_bus.h can only be used in ACPI case, so this patch add the stub function to linux/acpi.h to make compiled successfully in non-ACPI cases. Cc: Rafael J. Wysocki Signed-off-by: Kejian Yan Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..3025d1930f6e 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -543,6 +543,11 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *); struct fwnode_handle; +static inline bool acpi_dev_found(const char *hid) +{ + return false; +} + static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return false; -- cgit v1.2.3 From 4ae399241adba66ad72e5973a1004f37ffbe67cd Mon Sep 17 00:00:00 2001 From: Kejian Yan Date: Fri, 3 Jun 2016 10:55:10 +0800 Subject: ACPI: bus: add stub acpi_evaluate_dsm() to linux/acpi.h acpi_evaluate_dsm() will be used to handle the _DSM method in ACPI case. It will be compiled in non-ACPI case, but the function is in acpi_bus.h and acpi_bus.h can only be used in ACPI case, so this patch add the stub function to linux/acpi.h to make compiled successfully in non-ACPI cases. Cc: Rafael J. Wysocki Signed-off-by: Kejian Yan Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- include/linux/acpi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3025d1930f6e..4d4bb4955682 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -659,6 +659,14 @@ static inline bool acpi_driver_match_device(struct device *dev, return false; } +static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, + const u8 *uuid, + int rev, int func, + union acpi_object *argv4) +{ + return NULL; +} + static inline int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { -- cgit v1.2.3 From 74699228b99d293ec52682eed356f7b39ec644e4 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 30 May 2016 19:05:10 +0200 Subject: soc: renesas: Add r8a7796 SYSC PM Domain Binding Definitions Signed-off-by: Geert Uytterhoeven Acked-by: Laurent Pinchart Signed-off-by: Simon Horman --- include/dt-bindings/power/r8a7796-sysc.h | 36 ++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/dt-bindings/power/r8a7796-sysc.h (limited to 'include') diff --git a/include/dt-bindings/power/r8a7796-sysc.h b/include/dt-bindings/power/r8a7796-sysc.h new file mode 100644 index 000000000000..5b4daab44daa --- /dev/null +++ b/include/dt-bindings/power/r8a7796-sysc.h @@ -0,0 +1,36 @@ +/* + * Copyright (C) 2016 Glider bvba + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ +#ifndef __DT_BINDINGS_POWER_R8A7796_SYSC_H__ +#define __DT_BINDINGS_POWER_R8A7796_SYSC_H__ + +/* + * These power domain indices match the numbers of the interrupt bits + * representing the power areas in the various Interrupt Registers + * (e.g. SYSCISR, Interrupt Status Register) + */ + +#define R8A7796_PD_CA57_CPU0 0 +#define R8A7796_PD_CA57_CPU1 1 +#define R8A7796_PD_CA53_CPU0 5 +#define R8A7796_PD_CA53_CPU1 6 +#define R8A7796_PD_CA53_CPU2 7 +#define R8A7796_PD_CA53_CPU3 8 +#define R8A7796_PD_CA57_SCU 12 +#define R8A7796_PD_CR7 13 +#define R8A7796_PD_A3VC 14 +#define R8A7796_PD_3DG_A 17 +#define R8A7796_PD_3DG_B 18 +#define R8A7796_PD_CA53_SCU 21 +#define R8A7796_PD_A3IR 24 +#define R8A7796_PD_A2VC0 25 +#define R8A7796_PD_A2VC1 26 + +/* Always-on power area */ +#define R8A7796_PD_ALWAYS_ON 32 + +#endif /* __DT_BINDINGS_POWER_R8A7796_SYSC_H__ */ -- cgit v1.2.3 From 972610fb23b08dd54879102a9d5be695d53b728b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 2 May 2016 14:36:32 +0200 Subject: clk: renesas: Add r8a7796 CPG Core Clock Definitions Add all R-Car M3-W Clock Pulse Generator Core Clock Outputs, as listed in Table 8.2b ("List of Clocks [R-Car M3-W]") of the R-Car Gen3 datasheet (rev. 0.51 + Errata for Rev051 Mar 31 2016). Note that internal CPG clocks (S0, S1, S2, S3, SDSRC, and SSPSRC) are not included, as they are used as internal clock sources only, and never referenced from DT. Signed-off-by: Geert Uytterhoeven Tested-by: Simon Horman --- include/dt-bindings/clock/r8a7796-cpg-mssr.h | 69 ++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 include/dt-bindings/clock/r8a7796-cpg-mssr.h (limited to 'include') diff --git a/include/dt-bindings/clock/r8a7796-cpg-mssr.h b/include/dt-bindings/clock/r8a7796-cpg-mssr.h new file mode 100644 index 000000000000..1e5942695f0d --- /dev/null +++ b/include/dt-bindings/clock/r8a7796-cpg-mssr.h @@ -0,0 +1,69 @@ +/* + * Copyright (C) 2016 Renesas Electronics Corp. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__ +#define __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__ + +#include + +/* r8a7796 CPG Core Clocks */ +#define R8A7796_CLK_Z 0 +#define R8A7796_CLK_Z2 1 +#define R8A7796_CLK_ZR 2 +#define R8A7796_CLK_ZG 3 +#define R8A7796_CLK_ZTR 4 +#define R8A7796_CLK_ZTRD2 5 +#define R8A7796_CLK_ZT 6 +#define R8A7796_CLK_ZX 7 +#define R8A7796_CLK_S0D1 8 +#define R8A7796_CLK_S0D2 9 +#define R8A7796_CLK_S0D3 10 +#define R8A7796_CLK_S0D4 11 +#define R8A7796_CLK_S0D6 12 +#define R8A7796_CLK_S0D8 13 +#define R8A7796_CLK_S0D12 14 +#define R8A7796_CLK_S1D1 15 +#define R8A7796_CLK_S1D2 16 +#define R8A7796_CLK_S1D4 17 +#define R8A7796_CLK_S2D1 18 +#define R8A7796_CLK_S2D2 19 +#define R8A7796_CLK_S2D4 20 +#define R8A7796_CLK_S3D1 21 +#define R8A7796_CLK_S3D2 22 +#define R8A7796_CLK_S3D4 23 +#define R8A7796_CLK_LB 24 +#define R8A7796_CLK_CL 25 +#define R8A7796_CLK_ZB3 26 +#define R8A7796_CLK_ZB3D2 27 +#define R8A7796_CLK_ZB3D4 28 +#define R8A7796_CLK_CR 29 +#define R8A7796_CLK_CRD2 30 +#define R8A7796_CLK_SD0H 31 +#define R8A7796_CLK_SD0 32 +#define R8A7796_CLK_SD1H 33 +#define R8A7796_CLK_SD1 34 +#define R8A7796_CLK_SD2H 35 +#define R8A7796_CLK_SD2 36 +#define R8A7796_CLK_SD3H 37 +#define R8A7796_CLK_SD3 38 +#define R8A7796_CLK_SSP2 39 +#define R8A7796_CLK_SSP1 40 +#define R8A7796_CLK_SSPRS 41 +#define R8A7796_CLK_RPC 42 +#define R8A7796_CLK_RPCD2 43 +#define R8A7796_CLK_MSO 44 +#define R8A7796_CLK_CANFD 45 +#define R8A7796_CLK_HDMI 46 +#define R8A7796_CLK_CSI0 47 +#define R8A7796_CLK_CSIREF 48 +#define R8A7796_CLK_CP 49 +#define R8A7796_CLK_CPEX 50 +#define R8A7796_CLK_R 51 +#define R8A7796_CLK_OSC 52 + +#endif /* __DT_BINDINGS_CLOCK_R8A7796_CPG_MSSR_H__ */ -- cgit v1.2.3 From 98f368e9e2630a3ce3e80fb10fb2e02038cf9578 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Thu, 2 Jun 2016 23:43:21 -0500 Subject: kernel: Add noaudit variant of ns_capable() When checking the current cred for a capability in a specific user namespace, it isn't always desirable to have the LSMs audit the check. This patch adds a noaudit variant of ns_capable() for when those situations arise. The common logic between ns_capable() and the new ns_capable_noaudit() is moved into a single, shared function to keep duplicated code to a minimum and ease maintainability. Signed-off-by: Tyler Hicks Acked-by: Serge E. Hallyn Signed-off-by: James Morris --- include/linux/capability.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index 00690ff92edf..5f3c63dde2d5 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -206,6 +206,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap); extern bool capable(int cap); extern bool ns_capable(struct user_namespace *ns, int cap); +extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); #else static inline bool has_capability(struct task_struct *t, int cap) { @@ -233,6 +234,10 @@ static inline bool ns_capable(struct user_namespace *ns, int cap) { return true; } +static inline bool ns_capable_noaudit(struct user_namespace *ns, int cap) +{ + return true; +} #endif /* CONFIG_MULTIUSER */ extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap); extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap); -- cgit v1.2.3 From 950334bcf17a6ab55ce13d3bdf050f7b429320d5 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Sat, 28 May 2016 18:09:16 -0500 Subject: PCI: Add devm_request_pci_bus_resources() Several host bridge drivers iterate through the list of bridge windows to request resources. Several others don't request the window resources at all. Add a devm_request_pci_bus_resources() interface to make it easier for drivers to request all the window resources. Export to GPL modules (from Arnd Bergmann ). Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..6ac83606cb0d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1143,9 +1143,12 @@ void pci_add_resource(struct list_head *resources, struct resource *res); void pci_add_resource_offset(struct list_head *resources, struct resource *res, resource_size_t offset); void pci_free_resource_list(struct list_head *resources); -void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); +void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, + unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +int devm_request_pci_bus_resources(struct device *dev, + struct list_head *resources); #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ -- cgit v1.2.3 From 14de9d114a82a564b94388c95af79a701dc93134 Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Fri, 3 Jun 2016 16:57:12 -0400 Subject: virtio-net: Add initial MTU advice feature This commit adds the feature bit and associated mtu device entry for the virtio network device. When a virtio device comes up, it checks the feature bit for the VIRTIO_NET_F_MTU feature. If such feature bit is enabled, the driver will read the advised MTU and use it as the initial value. Signed-off-by: Aaron Conole Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index ec32293a00db..1ab4ea6ec847 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -55,6 +55,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ +#define VIRTIO_NET_F_MTU 25 /* Initial MTU advice */ #ifndef VIRTIO_NET_NO_LEGACY #define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */ @@ -73,6 +74,8 @@ struct virtio_net_config { * Legal values are between 1 and 0x8000 */ __u16 max_virtqueue_pairs; + /* Default maximum transmit unit advice */ + __u16 mtu; } __attribute__((packed)); /* -- cgit v1.2.3 From 63044c4fd49f9e2ce8ee9c5ca24afe6ebbb9fb46 Mon Sep 17 00:00:00 2001 From: Giovanni Cabiddu Date: Thu, 2 Jun 2016 13:28:55 +0100 Subject: crypto: hash - shrink hash down to two types Move hash to 0xe to free up the space for acomp/scomp Signed-off-by: Giovanni Cabiddu Signed-off-by: Herbert Xu --- include/linux/crypto.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 6e28c895c376..d844cbc365f7 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -48,15 +48,15 @@ #define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 -#define CRYPTO_ALG_TYPE_DIGEST 0x00000008 -#define CRYPTO_ALG_TYPE_HASH 0x00000008 -#define CRYPTO_ALG_TYPE_SHASH 0x00000009 -#define CRYPTO_ALG_TYPE_AHASH 0x0000000a #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d +#define CRYPTO_ALG_TYPE_DIGEST 0x0000000e +#define CRYPTO_ALG_TYPE_HASH 0x0000000e +#define CRYPTO_ALG_TYPE_SHASH 0x0000000e +#define CRYPTO_ALG_TYPE_AHASH 0x0000000f #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e -#define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000c +#define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_BLKCIPHER_MASK 0x0000000c #define CRYPTO_ALG_LARVAL 0x00000010 -- cgit v1.2.3 From 4e49ea4a3d276365bf7396c9b77b4d1d5923835a Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:41 -0500 Subject: block/fs/drivers: remove rw argument from submit_bio This has callers of submit_bio/submit_bio_wait set the bio->bi_rw instead of passing it in. This makes that use the same as generic_make_request and how we set the other bio fields. Signed-off-by: Mike Christie Fixed up fs/ext4/crypto.c Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9faebf7f9a33..3bde94234eea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -473,7 +473,7 @@ static inline void bio_io_error(struct bio *bio) struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); -extern int submit_bio_wait(int rw, struct bio *bio); +extern int submit_bio_wait(struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *); diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..65e4c51ecb3d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2747,7 +2747,7 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); #ifdef CONFIG_BLOCK -extern blk_qc_t submit_bio(int, struct bio *); +extern blk_qc_t submit_bio(struct bio *); extern int bdev_read_only(struct block_device *); #endif extern int set_blocksize(struct block_device *, int); -- cgit v1.2.3 From f21508211d2b16e65821abd171378fa6ece126fe Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:42 -0500 Subject: block: add REQ_OP definitions and helpers The following patches separate the operation (WRITE, READ, DISCARD, etc) from the rq_flag_bits flags. This patch adds definitions for request/bio operations (REQ_OPs) and adds request/bio accessors to get/set the op. In this patch the REQ_OPs match the REQ rq_flag_bits ones for compat reasons while all the code is converted to use the op accessors in the set. In the last patches the op will become a number and the accessors and helpers in this patch will be dropped or updated. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ include/linux/blk_types.h | 24 ++++++++++++++++++++++++ include/linux/blkdev.h | 10 +++++++++- include/linux/fs.h | 26 ++++++++++++++++++++++++-- 4 files changed, 60 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 3bde94234eea..09c5308494a6 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,6 +44,9 @@ #define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) +#define bio_op(bio) (op_from_rq_bits((bio)->bi_rw)) +#define bio_set_op_attrs(bio, op, flags) ((bio)->bi_rw |= (op | flags)) + /* * upper 16 bits of bi_rw define the io priority of this bio */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 77e5d81f07aa..6e60baa583da 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -242,6 +242,30 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE = REQ_WRITE, + REQ_OP_DISCARD = REQ_DISCARD, + REQ_OP_WRITE_SAME = REQ_WRITE_SAME, +}; + +/* + * tmp cpmpat. Users used to set the write bit for all non reads, but + * we will be dropping the bitmap use for ops. Support both until + * the end of the patchset. + */ +static inline int op_from_rq_bits(u64 flags) +{ + if (flags & REQ_OP_DISCARD) + return REQ_OP_DISCARD; + else if (flags & REQ_OP_WRITE_SAME) + return REQ_OP_WRITE_SAME; + else if (flags & REQ_OP_WRITE) + return REQ_OP_WRITE; + else + return REQ_OP_READ; +} + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3d9cf326574f..49c2dbcad583 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,6 +200,13 @@ struct request { struct request *next_rq; }; +#define req_op(req) (op_from_rq_bits((req)->cmd_flags)) +#define req_set_op(req, op) ((req)->cmd_flags |= op) +#define req_set_op_attrs(req, op, flags) do { \ + req_set_op(req, op); \ + (req)->cmd_flags |= flags; \ +} while (0) + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -597,7 +604,8 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1)) +#define rq_data_dir(rq) \ + (op_is_write(op_from_rq_bits(rq->cmd_flags)) ? WRITE : READ) /* * Driver can handle struct request, if it either has an old style diff --git a/include/linux/fs.h b/include/linux/fs.h index 65e4c51ecb3d..62ca2f9cad95 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2464,15 +2464,37 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK +/* + * tmp cpmpat. Users used to set the write bit for all non reads, but + * we will be dropping the bitmap use for ops. Support both until + * the end of the patchset. + */ +static inline bool op_is_write(unsigned long flags) +{ + if (flags & (REQ_OP_WRITE | REQ_OP_WRITE_SAME | REQ_OP_DISCARD)) + return true; + else + return false; +} + /* * return READ, READA, or WRITE */ -#define bio_rw(bio) ((bio)->bi_rw & (RW_MASK | RWA_MASK)) +static inline int bio_rw(struct bio *bio) +{ + if (op_is_write(op_from_rq_bits(bio->bi_rw))) + return WRITE; + + return bio->bi_rw & RWA_MASK; +} /* * return data direction, READ or WRITE */ -#define bio_data_dir(bio) ((bio)->bi_rw & 1) +static inline int bio_data_dir(struct bio *bio) +{ + return op_is_write(op_from_rq_bits(bio->bi_rw)) ? WRITE : READ; +} extern void check_disk_size_change(struct gendisk *disk, struct block_device *bdev); -- cgit v1.2.3 From 2a222ca992c35aee1e83af428f3dd26a3f5d5d94 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:43 -0500 Subject: fs: have submit_bh users pass in op and flags separately This has submit_bh users pass in the operation and flags separately, so submit_bh_wbc can setup the bio op and bi_rw flags on the bio that is submitted. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d48daa3f6f20..bc9a45d1e3af 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -189,10 +189,11 @@ void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); -int __sync_dirty_buffer(struct buffer_head *bh, int rw); -void write_dirty_buffer(struct buffer_head *bh, int rw); -int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags); -int submit_bh(int, struct buffer_head *); +int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); +void write_dirty_buffer(struct buffer_head *bh, int op_flags); +int _submit_bh(int op, int op_flags, struct buffer_head *bh, + unsigned long bio_flags); +int submit_bh(int, int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); -- cgit v1.2.3 From dfec8a14fc9043039e3c04807caf39dc71102816 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:44 -0500 Subject: fs: have ll_rw_block users pass in op and flags separately This has ll_rw_block users pass in the operation and flags separately, so ll_rw_block can setup the bio op and bi_rw flags on the bio that is submitted. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/buffer_head.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index bc9a45d1e3af..d1dd29338ba0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -187,7 +187,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); -void ll_rw_block(int, int, struct buffer_head * bh[]); +void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); void write_dirty_buffer(struct buffer_head *bh, int op_flags); -- cgit v1.2.3 From a8ebb056a8aeb58aafef0af241a6b3ac34ac86bd Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:45 -0500 Subject: block, drivers, cgroup: use op_is_write helper instead of checking for REQ_WRITE We currently set REQ_WRITE/WRITE for all non READ IOs like discard, flush, writesame, etc. In the next patches where we no longer set up the op as a bitmap, we will not be able to detect a operation direction like writesame by testing if REQ_WRITE is set. This patch converts the drivers and cgroup to use the op_is_write helper. This should just cover the simple cases. I did dm, md and bcache in their own patches because they were more involved. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index c02e669945e9..04f9c8d64060 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -601,7 +601,7 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, { struct percpu_counter *cnt; - if (rw & REQ_WRITE) + if (op_is_write(rw)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; -- cgit v1.2.3 From 95fe6c1a209ef89d9f94dd04a0ad72be1487d5d5 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:48 -0500 Subject: block, fs, mm, drivers: use bio set/get op accessors This patch converts the simple bi_rw use cases in the block, drivers, mm and fs code to set/get the bio operation using bio_set_op_attrs/bio_op These should be simple one or two liner cases, so I just did them in one patch. The next patches handle the more complicated cases in a module per patch. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 09c5308494a6..4568647269a7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -109,18 +109,23 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - !(bio->bi_rw & REQ_DISCARD)) + bio_op(bio) != REQ_OP_DISCARD) return true; return false; } +static inline bool bio_no_advance_iter(struct bio *bio) +{ + return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; +} + static inline bool bio_is_rw(struct bio *bio) { if (!bio_has_data(bio)) return false; - if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK) + if (bio_no_advance_iter(bio)) return false; return true; @@ -228,7 +233,7 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK) + if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); @@ -256,10 +261,10 @@ static inline unsigned bio_segments(struct bio *bio) * differently: */ - if (bio->bi_rw & REQ_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD) return 1; - if (bio->bi_rw & REQ_WRITE_SAME) + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; bio_for_each_segment(bv, bio, iter) -- cgit v1.2.3 From 469e3216e20a3946a292ff0414ab86de408d465e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:49 -0500 Subject: block discard: use bio set op accessor This converts the block issue discard helper and users to use the bio_set_op_attrs accessor and only pass in the operation flags like REQ_SEQURE. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49c2dbcad583..8c78aca080af 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1149,7 +1149,8 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop); + sector_t nr_sects, gfp_t gfp_mask, int op_flags, + struct bio **biop); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, -- cgit v1.2.3 From 8a4c1e42e0eb7189296ac140761370e2549cffe7 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:50 -0500 Subject: direct-io: use bio set/get op accessors This patch has the dio code use a REQ_OP for the op and rq_flag_bits for bi_rw flags. To set/get the op it uses the bio_set_op_attrs/bio_op accssors. It also begins to convert btrfs's dio_submit_t because of the dio submit_io callout use. The next patches will completely convert this code and the reset of the btrfs code paths. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 62ca2f9cad95..af6f3c7e4822 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2824,7 +2824,7 @@ extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK -typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, +typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { -- cgit v1.2.3 From 04d328defd06257bf386d58f359013e0ef329226 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:31:55 -0500 Subject: f2fs: use bio op accessors Separate the op from the rq_flag_bits and have f2fs set/get the bio using bio_set_op_attrs/bio_op. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/trace/events/f2fs.h | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 3a09bb4dc3b2..733b896fd44f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -56,17 +56,21 @@ TRACE_DEFINE_ENUM(CP_DISCARD); { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) -#define F2FS_BIO_MASK(t) (t & (READA | WRITE_FLUSH_FUA)) +#define F2FS_BIO_FLAG_MASK(t) (t & (READA | WRITE_FLUSH_FUA)) #define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO)) -#define show_bio_type(type) show_bio_base(type), show_bio_extra(type) +#define show_bio_type(op, op_flags) show_bio_op(op), \ + show_bio_op_flags(op_flags), show_bio_extra(op_flags) -#define show_bio_base(type) \ - __print_symbolic(F2FS_BIO_MASK(type), \ +#define show_bio_op(op) \ + __print_symbolic(op, \ { READ, "READ" }, \ + { WRITE, "WRITE" }) + +#define show_bio_op_flags(flags) \ + __print_symbolic(F2FS_BIO_FLAG_MASK(flags), \ { READA, "READAHEAD" }, \ { READ_SYNC, "READ_SYNC" }, \ - { WRITE, "WRITE" }, \ { WRITE_SYNC, "WRITE_SYNC" }, \ { WRITE_FLUSH, "WRITE_FLUSH" }, \ { WRITE_FUA, "WRITE_FUA" }, \ @@ -734,7 +738,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, __field(pgoff_t, index) __field(block_t, old_blkaddr) __field(block_t, new_blkaddr) - __field(int, rw) + __field(int, op) + __field(int, op_flags) __field(int, type) ), @@ -744,17 +749,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio, __entry->index = page->index; __entry->old_blkaddr = fio->old_blkaddr; __entry->new_blkaddr = fio->new_blkaddr; - __entry->rw = fio->rw; + __entry->op = fio->op; + __entry->op_flags = fio->op_flags; __entry->type = fio->type; ), TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, " - "oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s", + "oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%si%s, type = %s", show_dev_ino(__entry), (unsigned long)__entry->index, (unsigned long long)__entry->old_blkaddr, (unsigned long long)__entry->new_blkaddr, - show_bio_type(__entry->rw), + show_bio_type(__entry->op, __entry->op_flags), show_block_type(__entry->type)) ); @@ -785,7 +791,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio, TP_STRUCT__entry( __field(dev_t, dev) - __field(int, rw) + __field(int, op) + __field(int, op_flags) __field(int, type) __field(sector_t, sector) __field(unsigned int, size) @@ -793,15 +800,16 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio, TP_fast_assign( __entry->dev = sb->s_dev; - __entry->rw = fio->rw; + __entry->op = fio->op; + __entry->op_flags = fio->op_flags; __entry->type = fio->type; __entry->sector = bio->bi_iter.bi_sector; __entry->size = bio->bi_iter.bi_size; ), - TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u", + TP_printk("dev = (%d,%d), %s%s%s, %s, sector = %lld, size = %u", show_dev(__entry), - show_bio_type(__entry->rw), + show_bio_type(__entry->op, __entry->op_flags), show_block_type(__entry->type), (unsigned long long)__entry->sector, __entry->size) -- cgit v1.2.3 From e6047149db702374f240dc18bab665479e25a8cc Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:04 -0500 Subject: dm: use bio op accessors Separate the op from the rq_flag_bits and have dm set/get the bio using bio_set_op_attrs/bio_op. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/dm-io.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index a68cbe59e6ad..b91b023deffb 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -57,7 +57,8 @@ struct dm_io_notify { */ struct dm_io_client; struct dm_io_request { - int bi_rw; /* READ|WRITE - not READA */ + int bi_op; /* REQ_OP */ + int bi_op_flags; /* rq_flag_bits */ struct dm_io_memory mem; /* Memory to use for io */ struct dm_io_notify notify; /* Synchronous if notify.fn is NULL */ struct dm_io_client *client; /* Client memory handler */ -- cgit v1.2.3 From ba568ea0a2ef9a193ca24874228474ec7ae2ff98 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:13 -0500 Subject: block: prepare elevator to use REQ_OPs. This patch converts the elevator code to use separate variables for the operation and flags, and to check req_op for the REQ_OP. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/elevator.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 638b324f0291..953d28647435 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -26,7 +26,7 @@ typedef int (elevator_dispatch_fn) (struct request_queue *, int); typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_may_queue_fn) (struct request_queue *, int); +typedef int (elevator_may_queue_fn) (struct request_queue *, int, int); typedef void (elevator_init_icq_fn) (struct io_cq *); typedef void (elevator_exit_icq_fn) (struct io_cq *); @@ -134,7 +134,7 @@ extern struct request *elv_former_request(struct request_queue *, struct request extern struct request *elv_latter_request(struct request_queue *, struct request *); extern int elv_register_queue(struct request_queue *q); extern void elv_unregister_queue(struct request_queue *q); -extern int elv_may_queue(struct request_queue *, int); +extern int elv_may_queue(struct request_queue *, int, int); extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *q, struct request *rq, struct bio *bio, gfp_t gfp_mask); -- cgit v1.2.3 From 63a4cc24867de73626e16767ce616c50dc5438d3 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:14 -0500 Subject: blkg_rwstat: separate op from flags The bio and request operation and flags are going to be separate definitions, so we cannot pass them in as a bitmap. This patch converts the blkg_rwstat code and its caller, cfq, to pass in the values separately. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 04f9c8d64060..f77150a4a96a 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -590,25 +590,26 @@ static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) /** * blkg_rwstat_add - add a value to a blkg_rwstat * @rwstat: target blkg_rwstat - * @rw: mask of REQ_{WRITE|SYNC} + * @op: REQ_OP + * @op_flags: rq_flag_bits * @val: value to add * * Add @val to @rwstat. The counters are chosen according to @rw. The * caller is responsible for synchronizing calls to this function. */ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - int rw, uint64_t val) + int op, int op_flags, uint64_t val) { struct percpu_counter *cnt; - if (op_is_write(rw)) + if (op_is_write(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); - if (rw & REQ_SYNC) + if (op_flags & REQ_SYNC) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; @@ -713,9 +714,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_rw, + blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_rw, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_rw, 1); + blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_rw, 1); } rcu_read_unlock(); -- cgit v1.2.3 From 8fe0d473f5477e9916d3ac581a226acfe83142be Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:15 -0500 Subject: block: convert merge/insert code to check for REQ_OPs. This patch converts the block layer merging code to use separate variables for the operation and flags, and to check req_op for the REQ_OP. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8c78aca080af..25f01ff19780 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -666,16 +666,16 @@ static inline bool rq_mergeable(struct request *rq) return true; } -static inline bool blk_check_merge_flags(unsigned int flags1, - unsigned int flags2) +static inline bool blk_check_merge_flags(unsigned int flags1, unsigned int op1, + unsigned int flags2, unsigned int op2) { - if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD)) + if ((op1 == REQ_OP_DISCARD) != (op2 == REQ_OP_DISCARD)) return false; if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE)) return false; - if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME)) + if ((op1 == REQ_OP_WRITE_SAME) != (op2 == REQ_OP_WRITE_SAME)) return false; return true; @@ -887,12 +887,12 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) } static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, - unsigned int cmd_flags) + int op) { - if (unlikely(cmd_flags & REQ_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); - if (unlikely(cmd_flags & REQ_WRITE_SAME)) + if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; return q->limits.max_sectors; @@ -919,11 +919,11 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (rq->cmd_flags & REQ_DISCARD)) - return blk_queue_get_max_sectors(q, rq->cmd_flags); + if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, blk_rq_pos(rq)), - blk_queue_get_max_sectors(q, rq->cmd_flags)); + blk_queue_get_max_sectors(q, req_op(rq))); } static inline unsigned int blk_rq_count_bios(struct request *rq) -- cgit v1.2.3 From d9d8c5c489f4969667a05727e9c2c4f78cffef1a Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:16 -0500 Subject: block: convert is_sync helpers to use REQ_OPs. This patch converts the is_sync helpers to use separate variables for the operation and flags. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25f01ff19780..4937c056fcbd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -624,14 +624,14 @@ static inline unsigned int blk_queue_cluster(struct request_queue *q) /* * We regard a request as sync, if either a read or a sync write */ -static inline bool rw_is_sync(unsigned int rw_flags) +static inline bool rw_is_sync(int op, unsigned int rw_flags) { - return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC); + return op == REQ_OP_READ || (rw_flags & REQ_SYNC); } static inline bool rq_is_sync(struct request *rq) { - return rw_is_sync(rq->cmd_flags); + return rw_is_sync(req_op(rq), rq->cmd_flags); } static inline bool blk_rl_full(struct request_list *rl, bool sync) -- cgit v1.2.3 From 1b9a9ab78b0ab79dc1f0ddd5fbed7833ec7de3a4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:18 -0500 Subject: blktrace: use op accessors Have blktrace use the req/bio op accessor to get the REQ_OP. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 2 +- include/trace/events/bcache.h | 12 ++++++++---- include/trace/events/block.h | 31 ++++++++++++++++++++----------- 3 files changed, 29 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 0f3172b8b225..cceb72f9e29f 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -118,7 +118,7 @@ static inline int blk_cmd_buf_len(struct request *rq) } extern void blk_dump_cmd(char *buf, struct request *rq); -extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes); +extern void blk_fill_rwbs(char *rwbs, int op, u32 rw, int bytes); #endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */ diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index 981acf74b14f..65673d8b81ac 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -27,7 +27,8 @@ DECLARE_EVENT_CLASS(bcache_request, __entry->sector = bio->bi_iter.bi_sector; __entry->orig_sector = bio->bi_iter.bi_sector - 16; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u (from %d,%d @ %llu)", @@ -101,7 +102,8 @@ DECLARE_EVENT_CLASS(bcache_bio, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u", @@ -136,7 +138,8 @@ TRACE_EVENT(bcache_read, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); __entry->cache_hit = hit; __entry->bypass = bypass; ), @@ -167,7 +170,8 @@ TRACE_EVENT(bcache_write, __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); __entry->writeback = writeback; __entry->bypass = bypass; ), diff --git a/include/trace/events/block.h b/include/trace/events/block.h index e8a5eca1dbe5..5a2a7592068f 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -84,7 +84,8 @@ DECLARE_EVENT_CLASS(block_rq_with_error, 0 : blk_rq_sectors(rq); __entry->errors = rq->errors; - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, + blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); ), @@ -162,7 +163,7 @@ TRACE_EVENT(block_rq_complete, __entry->nr_sector = nr_bytes >> 9; __entry->errors = rq->errors; - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes); + blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, nr_bytes); blk_dump_cmd(__get_str(cmd), rq); ), @@ -198,7 +199,8 @@ DECLARE_EVENT_CLASS(block_rq, __entry->bytes = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? blk_rq_bytes(rq) : 0; - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, + blk_rq_bytes(rq)); blk_dump_cmd(__get_str(cmd), rq); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -272,7 +274,8 @@ TRACE_EVENT(block_bio_bounce, bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -310,7 +313,8 @@ TRACE_EVENT(block_bio_complete, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = error; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u [%d]", @@ -337,7 +341,8 @@ DECLARE_EVENT_CLASS(block_bio_merge, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -404,7 +409,8 @@ TRACE_EVENT(block_bio_queue, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -432,7 +438,7 @@ DECLARE_EVENT_CLASS(block_get_rq, __entry->dev = bio ? bio->bi_bdev->bd_dev : 0; __entry->sector = bio ? bio->bi_iter.bi_sector : 0; __entry->nr_sector = bio ? bio_sectors(bio) : 0; - blk_fill_rwbs(__entry->rwbs, + blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0, bio ? bio->bi_rw : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -567,7 +573,8 @@ TRACE_EVENT(block_split, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -610,7 +617,8 @@ TRACE_EVENT(block_bio_remap, __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_iter.bi_size); + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", @@ -656,7 +664,8 @@ TRACE_EVENT(block_rq_remap, __entry->old_dev = dev; __entry->old_sector = from; __entry->nr_bios = blk_rq_count_bios(rq); - blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); + blk_fill_rwbs(__entry->rwbs, req_op(rq), rq->cmd_flags, + blk_rq_bytes(rq)); ), TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", -- cgit v1.2.3 From 43b62ce3ff0ac1f13b732cb1bd130f522af1dba4 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:20 -0500 Subject: block: move bio io prio to a new field In the next patch, we move drop the compat code and make the op a separate value that is hidden in bi_rw. To give the op and rq bits flags room to grow this moves prio to its own field. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 14 ++------------ include/linux/blk_types.h | 5 ++--- 2 files changed, 4 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 4568647269a7..35108c2f8ea9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -47,18 +47,8 @@ #define bio_op(bio) (op_from_rq_bits((bio)->bi_rw)) #define bio_set_op_attrs(bio, op, flags) ((bio)->bi_rw |= (op | flags)) -/* - * upper 16 bits of bi_rw define the io priority of this bio - */ -#define BIO_PRIO_SHIFT (8 * sizeof(unsigned long) - IOPRIO_BITS) -#define bio_prio(bio) ((bio)->bi_rw >> BIO_PRIO_SHIFT) -#define bio_prio_valid(bio) ioprio_valid(bio_prio(bio)) - -#define bio_set_prio(bio, prio) do { \ - WARN_ON(prio >= (1 << IOPRIO_BITS)); \ - (bio)->bi_rw &= ((1UL << BIO_PRIO_SHIFT) - 1); \ - (bio)->bi_rw |= ((unsigned long) (prio) << BIO_PRIO_SHIFT); \ -} while (0) +#define bio_prio(bio) (bio)->bi_ioprio +#define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) /* * various member access, note that bio_data should of course not be used diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6e60baa583da..27384134f8a0 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -48,9 +48,8 @@ struct bio { struct block_device *bi_bdev; unsigned int bi_flags; /* status, command, etc */ int bi_error; - unsigned long bi_rw; /* bottom bits READ/WRITE, - * top bits priority - */ + unsigned long bi_rw; /* READ/WRITE */ + unsigned short bi_ioprio; struct bvec_iter bi_iter; -- cgit v1.2.3 From 6296b9604fcebc2dd8d6ec396de80b2da84d9700 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:21 -0500 Subject: block, drivers, fs: shrink bi_rw from long to int We don't need bi_rw to be so large on 64 bit archs, so reduce it to unsigned int. Signed-off-by: Mike Christie Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 27384134f8a0..5efb6f12d2f5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -48,7 +48,7 @@ struct bio { struct block_device *bi_bdev; unsigned int bi_flags; /* status, command, etc */ int bi_error; - unsigned long bi_rw; /* READ/WRITE */ + unsigned int bi_rw; /* READ/WRITE */ unsigned short bi_ioprio; struct bvec_iter bi_iter; -- cgit v1.2.3 From 4e1b2d52a80d79296a5d899d73249748dea71a53 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:22 -0500 Subject: block, fs, drivers: remove REQ_OP compat defs and related code This patch drops the compat definition of req_op where it matches the rq_flag_bits definitions, and drops the related old and compat code that allowed users to set either the op or flags for the operation. We also then store the operation in the bi_rw/cmd_flags field similar to how we used to store the bio ioprio where it sat in the upper bits of the field. Signed-off-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 --- include/linux/blk_types.h | 52 +++++++++++++++++---------------------------- include/linux/blkdev.h | 14 ++++++++---- include/linux/fs.h | 37 +++++++++++++------------------- include/trace/events/f2fs.h | 1 - 5 files changed, 45 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 35108c2f8ea9..0bbb2e332410 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,9 +44,6 @@ #define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) #define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) -#define bio_op(bio) (op_from_rq_bits((bio)->bi_rw)) -#define bio_set_op_attrs(bio, op, flags) ((bio)->bi_rw |= (op | flags)) - #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5efb6f12d2f5..23c1ab2a9475 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -48,7 +48,9 @@ struct bio { struct block_device *bi_bdev; unsigned int bi_flags; /* status, command, etc */ int bi_error; - unsigned int bi_rw; /* READ/WRITE */ + unsigned int bi_rw; /* bottom bits req flags, + * top bits REQ_OP + */ unsigned short bi_ioprio; struct bvec_iter bi_iter; @@ -106,6 +108,16 @@ struct bio { struct bio_vec bi_inline_vecs[0]; }; +#define BIO_OP_SHIFT (8 * sizeof(unsigned int) - REQ_OP_BITS) +#define bio_op(bio) ((bio)->bi_rw >> BIO_OP_SHIFT) + +#define bio_set_op_attrs(bio, op, op_flags) do { \ + WARN_ON(op >= (1 << REQ_OP_BITS)); \ + (bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1); \ + (bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT); \ + (bio)->bi_rw |= op_flags; \ +} while (0) + #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) /* @@ -144,7 +156,6 @@ struct bio { */ enum rq_flag_bits { /* common flags */ - __REQ_WRITE, /* not set, read. set, write */ __REQ_FAILFAST_DEV, /* no driver retries of device errors */ __REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */ __REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */ @@ -152,9 +163,7 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ - __REQ_DISCARD, /* request to discard sectors */ - __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ - __REQ_WRITE_SAME, /* write same block many times */ + __REQ_SECURE, /* secure discard (used with REQ_OP_DISCARD) */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ @@ -190,28 +199,22 @@ enum rq_flag_bits { __REQ_NR_BITS, /* stops here */ }; -#define REQ_WRITE (1ULL << __REQ_WRITE) #define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV) #define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT) #define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1ULL << __REQ_SYNC) #define REQ_META (1ULL << __REQ_META) #define REQ_PRIO (1ULL << __REQ_PRIO) -#define REQ_DISCARD (1ULL << __REQ_DISCARD) -#define REQ_WRITE_SAME (1ULL << __REQ_WRITE_SAME) #define REQ_NOIDLE (1ULL << __REQ_NOIDLE) #define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \ - REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \ - REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) + (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ + REQ_FLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) #define REQ_CLONE_MASK REQ_COMMON_MASK -#define BIO_NO_ADVANCE_ITER_MASK (REQ_DISCARD|REQ_WRITE_SAME) - /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ) @@ -243,27 +246,12 @@ enum rq_flag_bits { enum req_op { REQ_OP_READ, - REQ_OP_WRITE = REQ_WRITE, - REQ_OP_DISCARD = REQ_DISCARD, - REQ_OP_WRITE_SAME = REQ_WRITE_SAME, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ }; -/* - * tmp cpmpat. Users used to set the write bit for all non reads, but - * we will be dropping the bitmap use for ops. Support both until - * the end of the patchset. - */ -static inline int op_from_rq_bits(u64 flags) -{ - if (flags & REQ_OP_DISCARD) - return REQ_OP_DISCARD; - else if (flags & REQ_OP_WRITE_SAME) - return REQ_OP_WRITE_SAME; - else if (flags & REQ_OP_WRITE) - return REQ_OP_WRITE; - else - return REQ_OP_READ; -} +#define REQ_OP_BITS 2 typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4937c056fcbd..78ae3dbf2de1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,8 +200,15 @@ struct request { struct request *next_rq; }; -#define req_op(req) (op_from_rq_bits((req)->cmd_flags)) -#define req_set_op(req, op) ((req)->cmd_flags |= op) +#define REQ_OP_SHIFT (8 * sizeof(u64) - REQ_OP_BITS) +#define req_op(req) ((req)->cmd_flags >> REQ_OP_SHIFT) + +#define req_set_op(req, op) do { \ + WARN_ON(op >= (1 << REQ_OP_BITS)); \ + (req)->cmd_flags &= ((1ULL << REQ_OP_SHIFT) - 1); \ + (req)->cmd_flags |= ((u64) (op) << REQ_OP_SHIFT); \ +} while (0) + #define req_set_op_attrs(req, op, flags) do { \ req_set_op(req, op); \ (req)->cmd_flags |= flags; \ @@ -604,8 +611,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) \ - (op_is_write(op_from_rq_bits(rq->cmd_flags)) ? WRITE : READ) +#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) /* * Driver can handle struct request, if it either has an old style diff --git a/include/linux/fs.h b/include/linux/fs.h index af6f3c7e4822..ccd166477487 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -152,9 +152,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define CHECK_IOVEC_ONLY -1 /* - * The below are the various read and write types that we support. Some of + * The below are the various read and write flags that we support. Some of * them include behavioral modifiers that send information down to the - * block layer and IO scheduler. Terminology: + * block layer and IO scheduler. They should be used along with a req_op. + * Terminology: * * The block layer uses device plugging to defer IO a little bit, in * the hope that we will see more IO very shortly. This increases @@ -193,19 +194,19 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * non-volatile media on completion. * */ -#define RW_MASK REQ_WRITE +#define RW_MASK REQ_OP_WRITE #define RWA_MASK REQ_RAHEAD -#define READ 0 +#define READ REQ_OP_READ #define WRITE RW_MASK #define READA RWA_MASK -#define READ_SYNC (READ | REQ_SYNC) -#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) -#define WRITE_ODIRECT (WRITE | REQ_SYNC) -#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) -#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) +#define READ_SYNC REQ_SYNC +#define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) +#define WRITE_ODIRECT REQ_SYNC +#define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) +#define WRITE_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FUA) +#define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) /* * Attribute flags. These should be or-ed together to figure out what @@ -2464,17 +2465,9 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -/* - * tmp cpmpat. Users used to set the write bit for all non reads, but - * we will be dropping the bitmap use for ops. Support both until - * the end of the patchset. - */ -static inline bool op_is_write(unsigned long flags) +static inline bool op_is_write(unsigned int op) { - if (flags & (REQ_OP_WRITE | REQ_OP_WRITE_SAME | REQ_OP_DISCARD)) - return true; - else - return false; + return op == REQ_OP_READ ? false : true; } /* @@ -2482,7 +2475,7 @@ static inline bool op_is_write(unsigned long flags) */ static inline int bio_rw(struct bio *bio) { - if (op_is_write(op_from_rq_bits(bio->bi_rw))) + if (op_is_write(bio_op(bio))) return WRITE; return bio->bi_rw & RWA_MASK; @@ -2493,7 +2486,7 @@ static inline int bio_rw(struct bio *bio) */ static inline int bio_data_dir(struct bio *bio) { - return op_is_write(op_from_rq_bits(bio->bi_rw)) ? WRITE : READ; + return op_is_write(bio_op(bio)) ? WRITE : READ; } extern void check_disk_size_change(struct gendisk *disk, diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 733b896fd44f..30efa44a473c 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -31,7 +31,6 @@ TRACE_DEFINE_ENUM(BG_GC); TRACE_DEFINE_ENUM(LFS); TRACE_DEFINE_ENUM(SSR); TRACE_DEFINE_ENUM(__REQ_RAHEAD); -TRACE_DEFINE_ENUM(__REQ_WRITE); TRACE_DEFINE_ENUM(__REQ_SYNC); TRACE_DEFINE_ENUM(__REQ_NOIDLE); TRACE_DEFINE_ENUM(__REQ_FLUSH); -- cgit v1.2.3 From 3a5e02ced11e22ecd9da3d6710afe15bcfee1d10 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:23 -0500 Subject: block, drivers: add REQ_OP_FLUSH operation This adds a REQ_OP_FLUSH operation that is sent to request_fn based drivers by the block layer's flush code, instead of sending requests with the request->cmd_flags REQ_FLUSH bit set. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 3 ++- include/linux/blkdev.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 23c1ab2a9475..32d87522f349 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -249,9 +249,10 @@ enum req_op { REQ_OP_WRITE, REQ_OP_DISCARD, /* request to discard sectors */ REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ }; -#define REQ_OP_BITS 2 +#define REQ_OP_BITS 3 typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78ae3dbf2de1..0c9f8793c87e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -666,6 +666,9 @@ static inline bool rq_mergeable(struct request *rq) if (rq->cmd_type != REQ_TYPE_FS) return false; + if (req_op(rq) == REQ_OP_FLUSH) + return false; + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; -- cgit v1.2.3 From 28a8f0d317bf225ff15008f5dd66ae16242dd843 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 5 Jun 2016 14:32:25 -0500 Subject: block, drivers, fs: rename REQ_FLUSH to REQ_PREFLUSH To avoid confusion between REQ_OP_FLUSH, which is handled by request_fn drivers, and upper layers requesting the block layer perform a flush sequence along with possibly a WRITE, this patch renames REQ_FLUSH to REQ_PREFLUSH. Signed-off-by: Mike Christie Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 ++++---- include/linux/fs.h | 4 ++-- include/trace/events/f2fs.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 32d87522f349..562ab8301217 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -168,7 +168,7 @@ enum rq_flag_bits { __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ __REQ_FUA, /* forced unit access */ - __REQ_FLUSH, /* request for cache flush */ + __REQ_PREFLUSH, /* request for cache flush */ /* bio only flags */ __REQ_RAHEAD, /* read ahead, can fail anytime */ @@ -212,12 +212,12 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_FLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) + REQ_PREFLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) #define REQ_CLONE_MASK REQ_COMMON_MASK /* This mask is used for both bio and request merge checking */ #define REQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_FLUSH_SEQ) + (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_PREFLUSH | REQ_FUA | REQ_FLUSH_SEQ) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_THROTTLED (1ULL << __REQ_THROTTLED) @@ -235,7 +235,7 @@ enum rq_flag_bits { #define REQ_PREEMPT (1ULL << __REQ_PREEMPT) #define REQ_ALLOCED (1ULL << __REQ_ALLOCED) #define REQ_COPY_USER (1ULL << __REQ_COPY_USER) -#define REQ_FLUSH (1ULL << __REQ_FLUSH) +#define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) #define REQ_IO_STAT (1ULL << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) diff --git a/include/linux/fs.h b/include/linux/fs.h index ccd166477487..183024525d40 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -204,9 +204,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define READ_SYNC REQ_SYNC #define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) #define WRITE_ODIRECT REQ_SYNC -#define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) +#define WRITE_FLUSH (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH) #define WRITE_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FUA) -#define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) +#define WRITE_FLUSH_FUA (REQ_SYNC | REQ_NOIDLE | REQ_PREFLUSH | REQ_FUA) /* * Attribute flags. These should be or-ed together to figure out what diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 30efa44a473c..878963a1f058 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -33,7 +33,7 @@ TRACE_DEFINE_ENUM(SSR); TRACE_DEFINE_ENUM(__REQ_RAHEAD); TRACE_DEFINE_ENUM(__REQ_SYNC); TRACE_DEFINE_ENUM(__REQ_NOIDLE); -TRACE_DEFINE_ENUM(__REQ_FLUSH); +TRACE_DEFINE_ENUM(__REQ_PREFLUSH); TRACE_DEFINE_ENUM(__REQ_FUA); TRACE_DEFINE_ENUM(__REQ_PRIO); TRACE_DEFINE_ENUM(__REQ_META); -- cgit v1.2.3 From 53eb440f4ada034ea43b295891feec3df0fa7a29 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 6 Jun 2016 06:32:54 -0400 Subject: net sched actions: introduce timestamp for firsttime use Useful to know when the action was first used for accounting (and debugging) Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 2 ++ include/uapi/linux/pkt_cls.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 9a9a8edc138f..8389c007076f 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -76,6 +76,8 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) if (tm->lastuse != now) tm->lastuse = now; + if (unlikely(!tm->firstuse)) + tm->firstuse = now; } struct tc_action { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index f4297c8a42fe..9ba1410bd21d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -124,6 +124,7 @@ struct tcf_t { __u64 install; __u64 lastuse; __u64 expires; + __u64 firstuse; }; struct tc_cnt { -- cgit v1.2.3 From 48d8ee1694dd1ab25614b58f968123a4598f887e Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 6 Jun 2016 06:32:55 -0400 Subject: net sched actions: aggregate dumping of actions timeinfo Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 8389c007076f..a891978310e9 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -80,6 +80,14 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) tm->firstuse = now; } +static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) +{ + dtm->install = jiffies_to_clock_t(jiffies - stm->install); + dtm->lastuse = jiffies_to_clock_t(jiffies - stm->lastuse); + dtm->firstuse = jiffies_to_clock_t(jiffies - stm->firstuse); + dtm->expires = jiffies_to_clock_t(stm->expires); +} + struct tc_action { void *priv; const struct tc_action_ops *ops; -- cgit v1.2.3 From 0b0f43fe2e7291aa97b1febeaa5a0de453d007ca Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 5 Jun 2016 10:41:32 -0400 Subject: net sched: indentation and other OCD stylistic fixes Signed-off-by: Jamal Hadi Salim Acked-by: Cong Wang --- include/net/act_api.h | 14 ++++++++------ include/net/tc_act/tc_defact.h | 4 ++-- include/uapi/linux/pkt_cls.h | 6 +++--- 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index a891978310e9..db218a12efb5 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -2,8 +2,8 @@ #define __NET_ACT_API_H /* - * Public police action API for classifiers/qdiscs - */ + * Public action API for classifiers/qdiscs +*/ #include #include @@ -107,7 +107,8 @@ struct tc_action_ops { char kind[IFNAMSIZ]; __u32 type; /* TBD to match kind */ struct module *owner; - int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); + int (*act)(struct sk_buff *, const struct tc_action *, + struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *, int bind); int (*lookup)(struct net *, struct tc_action *, u32); @@ -125,8 +126,8 @@ struct tc_action_net { }; static inline -int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops, - unsigned int mask) +int tc_action_net_init(struct tc_action_net *tn, + const struct tc_action_ops *ops, unsigned int mask) { int err = 0; @@ -169,7 +170,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind) } int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); -int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); +int tcf_unregister_action(struct tc_action_ops *a, + struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res); diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h index 9763dcbb9bc3..ab9b5d6be67b 100644 --- a/include/net/tc_act/tc_defact.h +++ b/include/net/tc_act/tc_defact.h @@ -5,8 +5,8 @@ struct tcf_defact { struct tcf_common common; - u32 tcfd_datalen; - void *tcfd_defdata; + u32 tcfd_datalen; + void *tcfd_defdata; }; #define to_defact(a) \ container_of(a->priv, struct tcf_defact, common) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 9ba1410bd21d..5702e933dc07 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -115,8 +115,8 @@ struct tc_police { __u32 mtu; struct tc_ratespec rate; struct tc_ratespec peakrate; - int refcnt; - int bindcnt; + int refcnt; + int bindcnt; __u32 capab; }; @@ -128,7 +128,7 @@ struct tcf_t { }; struct tc_cnt { - int refcnt; + int refcnt; int bindcnt; }; -- cgit v1.2.3 From 68f047e3d62ebfac24ff9be551476cf30eafb00e Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 6 Jun 2016 14:29:58 +0800 Subject: fsl/qe: add rx_sync and tx_sync for TDM mode Rx_sync and tx_sync are used by QE-TDM mode, add them to struct ucc_fast_info. Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- include/soc/fsl/qe/qe.h | 2 ++ include/soc/fsl/qe/ucc_fast.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 33b29ead3d55..f91874582ab3 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -80,6 +80,8 @@ enum qe_clock { QE_CLK22, /* Clock 22 */ QE_CLK23, /* Clock 23 */ QE_CLK24, /* Clock 24 */ + QE_RSYNC_PIN, /* RSYNC from pin */ + QE_TSYNC_PIN, /* TSYNC from pin */ QE_CLK_DUMMY }; diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index df8ea7958c63..31548b7aa50e 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -120,6 +120,8 @@ struct ucc_fast_info { int ucc_num; enum qe_clock rx_clock; enum qe_clock tx_clock; + enum qe_clock rx_sync; + enum qe_clock tx_sync; u32 regs; int irq; u32 uccm_mask; -- cgit v1.2.3 From bb8b2062aff321af1fc58781cc07fbbea01cceb3 Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 6 Jun 2016 14:29:59 +0800 Subject: fsl/qe: setup clock source for TDM mode Add tdm clock configuration in both qe clock system and ucc fast controller. Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- include/soc/fsl/qe/qe.h | 16 ++++++++++++++++ include/soc/fsl/qe/ucc.h | 4 ++++ include/soc/fsl/qe/ucc_fast.h | 1 + 3 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index f91874582ab3..c3b1dc8a21a7 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -244,6 +244,22 @@ static inline int qe_alive_during_sleep(void) #define qe_muram_addr cpm_muram_addr #define qe_muram_offset cpm_muram_offset +#define qe_setbits32(_addr, _v) iowrite32be(ioread32be(_addr) | (_v), (_addr)) +#define qe_clrbits32(_addr, _v) iowrite32be(ioread32be(_addr) & ~(_v), (_addr)) + +#define qe_setbits16(_addr, _v) iowrite16be(ioread16be(_addr) | (_v), (_addr)) +#define qe_clrbits16(_addr, _v) iowrite16be(ioread16be(_addr) & ~(_v), (_addr)) + +#define qe_setbits8(_addr, _v) iowrite8(ioread8(_addr) | (_v), (_addr)) +#define qe_clrbits8(_addr, _v) iowrite8(ioread8(_addr) & ~(_v), (_addr)) + +#define qe_clrsetbits32(addr, clear, set) \ + iowrite32be((ioread32be(addr) & ~(clear)) | (set), (addr)) +#define qe_clrsetbits16(addr, clear, set) \ + iowrite16be((ioread16be(addr) & ~(clear)) | (set), (addr)) +#define qe_clrsetbits8(addr, clear, set) \ + iowrite8((ioread8(addr) & ~(clear)) | (set), (addr)) + /* Structure that defines QE firmware binary files. * * See Documentation/powerpc/qe_firmware.txt for a description of these diff --git a/include/soc/fsl/qe/ucc.h b/include/soc/fsl/qe/ucc.h index 894f14cbb044..6bbbb597f2af 100644 --- a/include/soc/fsl/qe/ucc.h +++ b/include/soc/fsl/qe/ucc.h @@ -41,6 +41,10 @@ int ucc_set_qe_mux_mii_mng(unsigned int ucc_num); int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock, enum comm_dir mode); +int ucc_set_tdm_rxtx_clk(unsigned int tdm_num, enum qe_clock clock, + enum comm_dir mode); +int ucc_set_tdm_rxtx_sync(unsigned int tdm_num, enum qe_clock clock, + enum comm_dir mode); int ucc_mux_set_grant_tsa_bkpt(unsigned int ucc_num, int set, u32 mask); diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index 31548b7aa50e..b2633b7dcc00 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -118,6 +118,7 @@ enum ucc_fast_transparent_tcrc { /* Fast UCC initialization structure */ struct ucc_fast_info { int ucc_num; + int tdm_num; enum qe_clock rx_clock; enum qe_clock tx_clock; enum qe_clock rx_sync; -- cgit v1.2.3 From 19163ac3123e7fef8b1ecb2f1d4223f58ed5e884 Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 6 Jun 2016 14:30:00 +0800 Subject: fsl/qe: Make regs resouce_size_t Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- include/soc/fsl/qe/ucc_fast.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index b2633b7dcc00..e898895223f9 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -123,7 +123,7 @@ struct ucc_fast_info { enum qe_clock tx_clock; enum qe_clock rx_sync; enum qe_clock tx_sync; - u32 regs; + resource_size_t regs; int irq; u32 uccm_mask; int bd_mem_part; -- cgit v1.2.3 From 35ef1c20fdb26779b6c3c4fd74bbdd5028e70005 Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 6 Jun 2016 14:30:01 +0800 Subject: fsl/qe: Add QE TDM lib QE has module to support TDM, some other protocols supported by QE are based on TDM. add a qe-tdm lib, this lib provides functions to the protocols using TDM to configurate QE-TDM. Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- include/soc/fsl/qe/immap_qe.h | 5 +-- include/soc/fsl/qe/qe_tdm.h | 94 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+), 4 deletions(-) create mode 100644 include/soc/fsl/qe/qe_tdm.h (limited to 'include') diff --git a/include/soc/fsl/qe/immap_qe.h b/include/soc/fsl/qe/immap_qe.h index bedbff891423..c76ef30b05ba 100644 --- a/include/soc/fsl/qe/immap_qe.h +++ b/include/soc/fsl/qe/immap_qe.h @@ -159,10 +159,7 @@ struct spi { /* SI */ struct si1 { - __be16 siamr1; /* SI1 TDMA mode register */ - __be16 sibmr1; /* SI1 TDMB mode register */ - __be16 sicmr1; /* SI1 TDMC mode register */ - __be16 sidmr1; /* SI1 TDMD mode register */ + __be16 sixmr1[4]; /* SI1 TDMx (x = A B C D) mode register */ u8 siglmr1_h; /* SI1 global mode register high */ u8 res0[0x1]; u8 sicmdr1_h; /* SI1 command register high */ diff --git a/include/soc/fsl/qe/qe_tdm.h b/include/soc/fsl/qe/qe_tdm.h new file mode 100644 index 000000000000..4c91498ab117 --- /dev/null +++ b/include/soc/fsl/qe/qe_tdm.h @@ -0,0 +1,94 @@ +/* + * Internal header file for QE TDM mode routines. + * + * Copyright (C) 2016 Freescale Semiconductor, Inc. All rights reserved. + * + * Authors: Zhao Qiang + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version + */ + +#ifndef CONFIG_QE_TDM_H +#define CONFIG_QE_TDM_H + +#include +#include + +#include +#include + +#include +#include + +/* SI RAM entries */ +#define SIR_LAST 0x0001 +#define SIR_BYTE 0x0002 +#define SIR_CNT(x) ((x) << 2) +#define SIR_CSEL(x) ((x) << 5) +#define SIR_SGS 0x0200 +#define SIR_SWTR 0x4000 +#define SIR_MCC 0x8000 +#define SIR_IDLE 0 + +/* SIxMR fields */ +#define SIMR_SAD(x) ((x) << 12) +#define SIMR_SDM_NORMAL 0x0000 +#define SIMR_SDM_INTERNAL_LOOPBACK 0x0800 +#define SIMR_SDM_MASK 0x0c00 +#define SIMR_CRT 0x0040 +#define SIMR_SL 0x0020 +#define SIMR_CE 0x0010 +#define SIMR_FE 0x0008 +#define SIMR_GM 0x0004 +#define SIMR_TFSD(n) (n) +#define SIMR_RFSD(n) ((n) << 8) + +enum tdm_ts_t { + TDM_TX_TS, + TDM_RX_TS +}; + +enum tdm_framer_t { + TDM_FRAMER_T1, + TDM_FRAMER_E1 +}; + +enum tdm_mode_t { + TDM_INTERNAL_LOOPBACK, + TDM_NORMAL +}; + +struct si_mode_info { + u8 simr_rfsd; + u8 simr_tfsd; + u8 simr_crt; + u8 simr_sl; + u8 simr_ce; + u8 simr_fe; + u8 simr_gm; +}; + +struct ucc_tdm_info { + struct ucc_fast_info uf_info; + struct si_mode_info si_info; +}; + +struct ucc_tdm { + u16 tdm_port; /* port for this tdm:TDMA,TDMB */ + u32 siram_entry_id; + u16 __iomem *siram; + struct si1 __iomem *si_regs; + enum tdm_framer_t tdm_framer_type; + enum tdm_mode_t tdm_mode; + u8 num_of_ts; /* the number of timeslots in this tdm frame */ + u32 tx_ts_mask; /* tx time slot mask */ + u32 rx_ts_mask; /* rx time slot mask */ +}; + +int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm, + struct ucc_tdm_info *ut_info); +void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info); +#endif -- cgit v1.2.3 From c19b6d246a35627c3a69b2fa6bdece212b48214b Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 6 Jun 2016 14:30:02 +0800 Subject: drivers/net: support hdlc function for QE-UCC The driver add hdlc support for Freescale QUICC Engine. It support NMSI and TSA mode. Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- include/soc/fsl/qe/qe.h | 1 + include/soc/fsl/qe/ucc_fast.h | 22 ++++++++++++++++++++-- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index c3b1dc8a21a7..70339d7958c0 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -657,6 +657,7 @@ struct ucc_slow_pram { #define UCC_SLOW_GUMR_L_MODE_QMC 0x00000002 /* General UCC FAST Mode Register */ +#define UCC_FAST_GUMR_LOOPBACK 0x40000000 #define UCC_FAST_GUMR_TCI 0x20000000 #define UCC_FAST_GUMR_TRX 0x10000000 #define UCC_FAST_GUMR_TTX 0x08000000 diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index e898895223f9..3ee9e7c1a7d7 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -21,19 +21,37 @@ #include -/* Receive BD's status */ +/* Receive BD's status and length*/ #define R_E 0x80000000 /* buffer empty */ #define R_W 0x20000000 /* wrap bit */ #define R_I 0x10000000 /* interrupt on reception */ #define R_L 0x08000000 /* last */ #define R_F 0x04000000 /* first */ -/* transmit BD's status */ +/* transmit BD's status and length*/ #define T_R 0x80000000 /* ready bit */ #define T_W 0x20000000 /* wrap bit */ #define T_I 0x10000000 /* interrupt on completion */ #define T_L 0x08000000 /* last */ +/* Receive BD's status */ +#define R_E_S 0x8000 /* buffer empty */ +#define R_W_S 0x2000 /* wrap bit */ +#define R_I_S 0x1000 /* interrupt on reception */ +#define R_L_S 0x0800 /* last */ +#define R_F_S 0x0400 /* first */ +#define R_CM_S 0x0200 /* continuous mode */ +#define R_CR_S 0x0004 /* crc */ +#define R_OV_S 0x0002 /* crc */ + +/* transmit BD's status */ +#define T_R_S 0x8000 /* ready bit */ +#define T_W_S 0x2000 /* wrap bit */ +#define T_I_S 0x1000 /* interrupt on completion */ +#define T_L_S 0x0800 /* last */ +#define T_TC_S 0x0400 /* crc */ +#define T_TM_S 0x0200 /* continuous mode */ + /* Rx Data buffer must be 4 bytes aligned in most cases */ #define UCC_FAST_RX_ALIGN 4 #define UCC_FAST_MRBLR_ALIGNMENT 4 -- cgit v1.2.3 From f9eb8aea2a1e12fc2f584d1627deeb957435a801 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jun 2016 09:37:15 -0700 Subject: net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet Cc: Cong Wang Cc: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/sch_generic.h | 15 ++++----------- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fa6df2699532..59d7e06d88d5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1862,6 +1862,7 @@ struct net_device { #endif struct phy_device *phydev; struct lock_class_key *qdisc_tx_busylock; + struct lock_class_key *qdisc_running_key; bool proto_down; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a1fd76c22a59..bff8d895ef8a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -29,13 +29,6 @@ enum qdisc_state_t { __QDISC_STATE_THROTTLED, }; -/* - * following bits are only changed while qdisc lock is held - */ -enum qdisc___state_t { - __QDISC___STATE_RUNNING = 1, -}; - struct qdisc_size_table { struct rcu_head rcu; struct list_head list; @@ -93,7 +86,7 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned int __state; + seqcount_t running; struct gnet_stats_queue qstats; struct rcu_head rcu_head; int padded; @@ -104,20 +97,20 @@ struct Qdisc { static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; + return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc_is_running(qdisc)) return false; - qdisc->__state |= __QDISC___STATE_RUNNING; + write_seqcount_begin(&qdisc->running); return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - qdisc->__state &= ~__QDISC___STATE_RUNNING; + write_seqcount_end(&qdisc->running); } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) -- cgit v1.2.3 From edb09eb17ed89eaa82a52dd306beac93e292b485 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jun 2016 09:37:16 -0700 Subject: net: sched: do not acquire qdisc spinlock in qdisc/class stats dump Large tc dumps (tc -s {qdisc|class} sh dev ethX) done by Google BwE host agent [1] are problematic at scale : For each qdisc/class found in the dump, we currently lock the root qdisc spinlock in order to get stats. Sampling stats every 5 seconds from thousands of HTB classes is a challenge when the root qdisc spinlock is under high pressure. Not only the dumps take time, they also slow down the fast path (queue/dequeue packets) by 10 % to 20 % in some cases. An audit of existing qdiscs showed that sch_fq_codel is the only qdisc that might need the qdisc lock in fq_codel_dump_stats() and fq_codel_dump_class_stats() In v2 of this patch, I now use the Qdisc running seqcount to provide consistent reads of packets/bytes counters, regardless of 32/64 bit arches. I also changed rate estimators to use the same infrastructure so that they no longer need to lock root qdisc lock. [1] http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/43838.pdf Signed-off-by: Eric Dumazet Cc: Cong Wang Cc: Jamal Hadi Salim Cc: John Fastabend Cc: Kevin Athey Cc: Xiaotian Pei Signed-off-by: David S. Miller --- include/net/gen_stats.h | 12 ++++++++---- include/net/sch_generic.h | 8 ++++++++ 2 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 610cd397890e..231e121cc7d9 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -33,10 +33,12 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(struct gnet_dump *d, +int gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats, +void __gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b); int gnet_stats_copy_rate_est(struct gnet_dump *d, @@ -52,13 +54,15 @@ int gnet_stats_finish_copy(struct gnet_dump *d); int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, - spinlock_t *stats_lock, struct nlattr *opt); + spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt); void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est64 *rate_est); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, - spinlock_t *stats_lock, struct nlattr *opt); + spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt); bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, const struct gnet_stats_rate_est64 *rate_est); #endif diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index bff8d895ef8a..c4f5749342ec 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -314,6 +314,14 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } +static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) +{ + struct Qdisc *root = qdisc_root_sleeping(qdisc); + + ASSERT_RTNL(); + return &root->running; +} + static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; -- 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 --- include/soc/at91/at91_sfr.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/soc/at91/at91_sfr.h (limited to 'include') 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 f4502dd1da9b060a49d539eb754ff86cb97b89f0 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 8 Jun 2016 12:18:31 +0530 Subject: spi: Add DMA support for spi_flash_read() Few SPI devices provide accelerated read interfaces to read from SPI-NOR flash devices. These hardwares also support DMA to transfer data from flash to memory either via mem-to-mem DMA or dedicated slave DMA channels. Hence, add support for DMA in order to improve throughput and reduce CPU load. Use spi_map_buf() to get sg table for the buffer and pass it to SPI driver. Signed-off-by: Vignesh R Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 1f03483f61e5..7b53af4ba5f8 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1143,6 +1143,8 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd) * @opcode_nbits: number of lines to send opcode * @addr_nbits: number of lines to send address * @data_nbits: number of lines for data + * @rx_sg: Scatterlist for receive data read from flash + * @cur_msg_mapped: message has been mapped for DMA */ struct spi_flash_read_message { void *buf; @@ -1155,6 +1157,8 @@ struct spi_flash_read_message { u8 opcode_nbits; u8 addr_nbits; u8 data_nbits; + struct sg_table rx_sg; + bool cur_msg_mapped; }; /* SPI core interface for flash read support */ -- 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 --- include/asm-generic/rwsem.h | 6 +++--- include/linux/rwsem.h | 8 +++++--- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include') 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) \ -- 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 --- include/asm-generic/rwsem.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') 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 --- include/asm-generic/mutex-dec.h | 2 +- include/asm-generic/mutex-xchg.h | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') 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 -- 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 6f23d96cfa4fb68c4c9683f161f831057a5a134f Mon Sep 17 00:00:00 2001 From: Andreas Ziegler Date: Wed, 8 Jun 2016 11:36:56 +0200 Subject: fsl/qe: Do not prefix header guard with CONFIG_ The CONFIG_ prefix should only be used for options which can be configured through Kconfig and not for guarding headers. Signed-off-by: Andreas Ziegler Signed-off-by: David S. Miller --- include/soc/fsl/qe/qe_tdm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/fsl/qe/qe_tdm.h b/include/soc/fsl/qe/qe_tdm.h index 4c91498ab117..a1664b635f1a 100644 --- a/include/soc/fsl/qe/qe_tdm.h +++ b/include/soc/fsl/qe/qe_tdm.h @@ -11,8 +11,8 @@ * option) any later version */ -#ifndef CONFIG_QE_TDM_H -#define CONFIG_QE_TDM_H +#ifndef _QE_TDM_H_ +#define _QE_TDM_H_ #include #include -- cgit v1.2.3 From 6ad8c632ee48ae099aa13704ef18a641220fe211 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 8 Jun 2016 06:22:10 -0400 Subject: qed: Add support for query/config dcbx. Query API reads the dcbx data from the device shared memory and return it to the caller. The config API configures the user provided dcbx values on the device, and initiates the dcbx negotiation with the peer. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 90 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 90 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e8cc49f9688a..e1d5122e8a96 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -34,6 +34,96 @@ enum dcbx_protocol_type { DCBX_MAX_PROTOCOL_TYPE }; +#ifdef CONFIG_DCB +#define QED_LLDP_CHASSIS_ID_STAT_LEN 4 +#define QED_LLDP_PORT_ID_STAT_LEN 4 +#define QED_DCBX_MAX_APP_PROTOCOL 32 +#define QED_MAX_PFC_PRIORITIES 8 +#define QED_DCBX_DSCP_SIZE 64 + +struct qed_dcbx_lldp_remote { + u32 peer_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN]; + u32 peer_port_id[QED_LLDP_PORT_ID_STAT_LEN]; + bool enable_rx; + bool enable_tx; + u32 tx_interval; + u32 max_credit; +}; + +struct qed_dcbx_lldp_local { + u32 local_chassis_id[QED_LLDP_CHASSIS_ID_STAT_LEN]; + u32 local_port_id[QED_LLDP_PORT_ID_STAT_LEN]; +}; + +struct qed_dcbx_app_prio { + u8 roce; + u8 roce_v2; + u8 fcoe; + u8 iscsi; + u8 eth; +}; + +struct qed_dbcx_pfc_params { + bool willing; + bool enabled; + u8 prio[QED_MAX_PFC_PRIORITIES]; + u8 max_tc; +}; + +struct qed_app_entry { + bool ethtype; + bool enabled; + u8 prio; + u16 proto_id; + enum dcbx_protocol_type proto_type; +}; + +struct qed_dcbx_params { + struct qed_app_entry app_entry[QED_DCBX_MAX_APP_PROTOCOL]; + u16 num_app_entries; + bool app_willing; + bool app_valid; + bool app_error; + bool ets_willing; + bool ets_enabled; + bool ets_cbs; + bool valid; + u8 ets_pri_tc_tbl[QED_MAX_PFC_PRIORITIES]; + u8 ets_tc_bw_tbl[QED_MAX_PFC_PRIORITIES]; + u8 ets_tc_tsa_tbl[QED_MAX_PFC_PRIORITIES]; + struct qed_dbcx_pfc_params pfc; + u8 max_ets_tc; +}; + +struct qed_dcbx_admin_params { + struct qed_dcbx_params params; + bool valid; +}; + +struct qed_dcbx_remote_params { + struct qed_dcbx_params params; + bool valid; +}; + +struct qed_dcbx_operational_params { + struct qed_dcbx_app_prio app_prio; + struct qed_dcbx_params params; + bool valid; + bool enabled; + bool ieee; + bool cee; + u32 err; +}; + +struct qed_dcbx_get { + struct qed_dcbx_operational_params operational; + struct qed_dcbx_lldp_remote lldp_remote; + struct qed_dcbx_lldp_local lldp_local; + struct qed_dcbx_remote_params remote; + struct qed_dcbx_admin_params local; +}; +#endif + enum qed_led_mode { QED_LED_MODE_OFF, QED_LED_MODE_ON, -- cgit v1.2.3 From a1d8d8a51e8317269dd127d94b9de14f67d9563f Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 8 Jun 2016 06:22:11 -0400 Subject: qed: Add dcbnl support. This patch adds the implementation for both cee/ieee dcbnl callbacks by using the qed query/config APIs. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 62 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index f8ff71126d9e..71d523b4bc54 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -128,11 +128,73 @@ struct qed_eth_cb_ops { void (*force_mac) (void *dev, u8 *mac); }; +#ifdef CONFIG_DCB +/* Prototype declaration of qed_eth_dcbnl_ops should match with the declaration + * of dcbnl_rtnl_ops structure. + */ +struct qed_eth_dcbnl_ops { + /* IEEE 802.1Qaz std */ + int (*ieee_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc); + int (*ieee_setpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc); + int (*ieee_getets)(struct qed_dev *cdev, struct ieee_ets *ets); + int (*ieee_setets)(struct qed_dev *cdev, struct ieee_ets *ets); + int (*ieee_peer_getets)(struct qed_dev *cdev, struct ieee_ets *ets); + int (*ieee_peer_getpfc)(struct qed_dev *cdev, struct ieee_pfc *pfc); + int (*ieee_getapp)(struct qed_dev *cdev, struct dcb_app *app); + int (*ieee_setapp)(struct qed_dev *cdev, struct dcb_app *app); + + /* CEE std */ + u8 (*getstate)(struct qed_dev *cdev); + u8 (*setstate)(struct qed_dev *cdev, u8 state); + void (*getpgtccfgtx)(struct qed_dev *cdev, int prio, u8 *prio_type, + u8 *pgid, u8 *bw_pct, u8 *up_map); + void (*getpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 *bw_pct); + void (*getpgtccfgrx)(struct qed_dev *cdev, int prio, u8 *prio_type, + u8 *pgid, u8 *bw_pct, u8 *up_map); + void (*getpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 *bw_pct); + void (*getpfccfg)(struct qed_dev *cdev, int prio, u8 *setting); + void (*setpfccfg)(struct qed_dev *cdev, int prio, u8 setting); + u8 (*getcap)(struct qed_dev *cdev, int capid, u8 *cap); + int (*getnumtcs)(struct qed_dev *cdev, int tcid, u8 *num); + u8 (*getpfcstate)(struct qed_dev *cdev); + int (*getapp)(struct qed_dev *cdev, u8 idtype, u16 id); + u8 (*getfeatcfg)(struct qed_dev *cdev, int featid, u8 *flags); + + /* DCBX configuration */ + u8 (*getdcbx)(struct qed_dev *cdev); + void (*setpgtccfgtx)(struct qed_dev *cdev, int prio, + u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map); + void (*setpgtccfgrx)(struct qed_dev *cdev, int prio, + u8 pri_type, u8 pgid, u8 bw_pct, u8 up_map); + void (*setpgbwgcfgtx)(struct qed_dev *cdev, int pgid, u8 bw_pct); + void (*setpgbwgcfgrx)(struct qed_dev *cdev, int pgid, u8 bw_pct); + u8 (*setall)(struct qed_dev *cdev); + int (*setnumtcs)(struct qed_dev *cdev, int tcid, u8 num); + void (*setpfcstate)(struct qed_dev *cdev, u8 state); + int (*setapp)(struct qed_dev *cdev, u8 idtype, u16 idval, u8 up); + u8 (*setdcbx)(struct qed_dev *cdev, u8 state); + u8 (*setfeatcfg)(struct qed_dev *cdev, int featid, u8 flags); + + /* Peer apps */ + int (*peer_getappinfo)(struct qed_dev *cdev, + struct dcb_peer_app_info *info, + u16 *app_count); + int (*peer_getapptable)(struct qed_dev *cdev, struct dcb_app *table); + + /* CEE peer */ + int (*cee_peer_getpfc)(struct qed_dev *cdev, struct cee_pfc *pfc); + int (*cee_peer_getpg)(struct qed_dev *cdev, struct cee_pg *pg); +}; +#endif + struct qed_eth_ops { const struct qed_common_ops *common; #ifdef CONFIG_QED_SRIOV const struct qed_iov_hv_ops *iov; #endif +#ifdef CONFIG_DCB + const struct qed_eth_dcbnl_ops *dcb; +#endif int (*fill_dev_info)(struct qed_dev *cdev, struct qed_dev_eth_info *info); -- cgit v1.2.3 From 123b36526592f009bf8eccb7c8833aeda296d9cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2016 07:22:49 -0700 Subject: net: sched: fix missing doc annotations "make htmldocs" complains otherwise: .//net/core/gen_stats.c:168: warning: No description found for parameter 'running' .//include/linux/netdevice.h:1867: warning: No description found for parameter 'qdisc_running_key' Fixes: f9eb8aea2a1e ("net_sched: transform qdisc running bit into a seqcount") Fixes: edb09eb17ed8 ("net: sched: do not acquire qdisc spinlock in qdisc/class stats dump") Signed-off-by: Eric Dumazet Reported-by: kbuild test robot Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 59d7e06d88d5..541562333ba5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1594,7 +1594,8 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * - * @qdisc_tx_busylock: XXX: need comments on this one + * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the -- cgit v1.2.3 From 0c73c523cf737b5d446705392e0e14ee0411a351 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 7 Jun 2016 16:32:42 -0700 Subject: net: dsa: Initialize CPU port ethtool ops per tree Now that we can properly support multiple distinct trees in the system, using a global variable: dsa_cpu_port_ethtool_ops is getting clobbered as soon as the second switch tree gets probed, and we don't want that. We need to move this to be dynamically allocated, and since we can't really be comparing addresses anymore to determine first time initialization versus any other times, just move this to dsa.c and dsa2.c where the remainder of the dst/ds initialization happens. The operations teardown restores the master netdev's ethtool_ops to its original ethtool_ops pointer (typically within the Ethernet driver) Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index cca7ef230742..20b3087ad193 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -116,6 +116,7 @@ struct dsa_switch_tree { * Original copy of the master netdev ethtool_ops */ struct ethtool_ops master_ethtool_ops; + const struct ethtool_ops *master_orig_ethtool_ops; /* * The switch and port to which the CPU is attached. -- cgit v1.2.3 From 96c63fa7393d0a346acfe5a91e0c7d4c7782641b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 8 Jun 2016 10:55:39 -0700 Subject: net: Add l3mdev rule Currently, VRFs require 1 oif and 1 iif rule per address family per VRF. As the number of VRF devices increases it brings scalability issues with the increasing rule list. All of the VRF rules have the same format with the exception of the specific table id to direct the lookup. Since the table id is available from the oif or iif in the loopup, the VRF rules can be consolidated to a single rule that pulls the table from the VRF device. This patch introduces a new rule attribute l3mdev. The l3mdev rule means the table id used for the lookup is pulled from the L3 master device (e.g., VRF) rather than being statically defined. With the l3mdev rule all of the basic VRF FIB rules are reduced to 1 l3mdev rule per address family (IPv4 and IPv6). If an admin wishes to insert higher priority rules for specific VRFs those rules will co-exist with the l3mdev rule. This capability means current VRF scripts will co-exist with this new simpler implementation. Currently, the rules list for both ipv4 and ipv6 look like this: $ ip ru ls 1000: from all oif vrf1 lookup 1001 1000: from all iif vrf1 lookup 1001 1000: from all oif vrf2 lookup 1002 1000: from all iif vrf2 lookup 1002 1000: from all oif vrf3 lookup 1003 1000: from all iif vrf3 lookup 1003 1000: from all oif vrf4 lookup 1004 1000: from all iif vrf4 lookup 1004 1000: from all oif vrf5 lookup 1005 1000: from all iif vrf5 lookup 1005 1000: from all oif vrf6 lookup 1006 1000: from all iif vrf6 lookup 1006 1000: from all oif vrf7 lookup 1007 1000: from all iif vrf7 lookup 1007 1000: from all oif vrf8 lookup 1008 1000: from all iif vrf8 lookup 1008 ... 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default With the l3mdev rule the list is just the following regardless of the number of VRFs: $ ip ru ls 1000: from all lookup [l3mdev table] 32765: from all lookup local 32766: from all lookup main 32767: from all lookup default (Note: the above pretty print of the rule is based on an iproute2 prototype. Actual verbage may change) Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/fib_rules.h | 24 ++++++++++++++++++++++-- include/net/l3mdev.h | 12 ++++++++++++ include/uapi/linux/fib_rules.h | 1 + 3 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 59160de702b6..456e4a6006ab 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -17,7 +17,8 @@ struct fib_rule { u32 flags; u32 table; u8 action; - /* 3 bytes hole, try to use */ + u8 l3mdev; + /* 2 bytes hole, try to use */ u32 target; __be64 tun_id; struct fib_rule __rcu *ctarget; @@ -36,6 +37,7 @@ struct fib_lookup_arg { void *lookup_ptr; void *result; struct fib_rule *rule; + u32 table; int flags; #define FIB_LOOKUP_NOREF 1 #define FIB_LOOKUP_IGNORE_LINKSTATE 2 @@ -89,7 +91,8 @@ struct fib_rules_ops { [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ - [FRA_GOTO] = { .type = NLA_U32 } + [FRA_GOTO] = { .type = NLA_U32 }, \ + [FRA_L3MDEV] = { .type = NLA_U8 } static inline void fib_rule_get(struct fib_rule *rule) { @@ -102,6 +105,20 @@ static inline void fib_rule_put(struct fib_rule *rule) kfree_rcu(rule, rcu); } +#ifdef CONFIG_NET_L3_MASTER_DEV +static inline u32 fib_rule_get_table(struct fib_rule *rule, + struct fib_lookup_arg *arg) +{ + return rule->l3mdev ? arg->table : rule->table; +} +#else +static inline u32 fib_rule_get_table(struct fib_rule *rule, + struct fib_lookup_arg *arg) +{ + return rule->table; +} +#endif + static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) { if (nla[FRA_TABLE]) @@ -117,4 +134,7 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh); +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh); #endif diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 374388dc01c8..34f33eb96a5e 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -11,6 +11,8 @@ #ifndef _NET_L3MDEV_H_ #define _NET_L3MDEV_H_ +#include + /** * struct l3mdev_ops - l3mdev operations * @@ -41,6 +43,9 @@ struct l3mdev_ops { #ifdef CONFIG_NET_L3_MASTER_DEV +int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, + struct fib_lookup_arg *arg); + int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { @@ -236,6 +241,13 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) { return skb; } + +static inline +int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, + struct fib_lookup_arg *arg) +{ + return 1; +} #endif #endif /* _NET_L3MDEV_H_ */ diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 620c8a5ddc00..14404b3ebb89 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -50,6 +50,7 @@ enum { FRA_FWMASK, /* mask for netfilter mark */ FRA_OIFNAME, FRA_PAD, + FRA_L3MDEV, /* iif or oif is l3mdev goto its table */ __FRA_MAX }; -- 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) --- include/linux/random.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') 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 f8bfc116cacbdf7e0e655d8a798a242087ed70a5 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 3 Jun 2016 10:58:47 +0530 Subject: cpufreq: Remove cpufreq_frequency_get_table() Most of the callers of cpufreq_frequency_get_table() already have the pointer to a valid 'policy' structure and they don't really need to go through the per-cpu variable first and then a check to validate the frequency, in order to find the freq-table for the policy. Directly use the policy->freq_table field instead for them. Only one user of that API is left after above changes, cpu_cooling.c and it accesses the freq_table in a racy way as the policy can get freed in between. Fix it by using cpufreq_cpu_get() properly. Since there are no more users of cpufreq_frequency_get_table() left, get rid of it. Signed-off-by: Viresh Kumar Acked-by: Javi Merino (cpu_cooling.c) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 7ed93c310c08..1342cbc0f25e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -632,8 +632,6 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) return false; } #endif -/* the following funtion is for cpufreq core use only */ -struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu); /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; -- cgit v1.2.3 From 7ab4aabbaa98fbf9f8967fd93162d675439337e1 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 3 Jun 2016 10:58:49 +0530 Subject: cpufreq: Drop freq-table param to cpufreq_frequency_table_target() The policy already has this pointer set, use it instead. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1342cbc0f25e..bdd7f0c035ae 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -598,7 +598,6 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy); int cpufreq_frequency_table_target(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table, unsigned int target_freq, unsigned int relation, unsigned int *index); -- cgit v1.2.3 From d218ed773915a2b762d132be6bb765637338c360 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 3 Jun 2016 10:58:51 +0530 Subject: cpufreq: Return index from cpufreq_frequency_table_target() This routine can't fail unless the frequency table is invalid and doesn't contain any valid entries. Make it return the index and WARN() in case it is used for an invalid table. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index bdd7f0c035ae..c378776628b4 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -599,8 +599,7 @@ int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy); int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int target_freq, - unsigned int relation, - unsigned int *index); + unsigned int relation); int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy, unsigned int freq); -- cgit v1.2.3 From dd47c1fa776cda48531b651c88341e951140b0a7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Jun 2016 00:27:40 +0200 Subject: cbq: remove TCA_CBQ_POLICE support iproute2 doesn't implement any cbq option that results in this attribute being sent to kernel. To make use of it, user would have to - patch iproute2 - add a class - attach a qdisc to the class (default pfifo doesn't work as q->handle is 0 and cbq_set_police() is a no-op in this case) - re-'add' the same class (tc class change ...) again - user must also specifiy a defmap (e.g. 'split 1:0 defmap 3f'), since this 'police' feature relies on its presence - the added qdisc must be one of bfifo, pfifo or netem If all of these conditions are met and _some_ leaf qdiscs, namely p/bfifo, netem, plug or tbf would drop a packet, kernel calls back into cbq, which will attempt to re-queue the skb into a different class as indicated by the parents' defmap entry for TC_PRIO_BESTEFFORT. [ i.e. we behave as if tc_classify returned TC_ACT_RECLASSIFY ]. This feature, which isn't documented or implemented in iproute2, and isn't implemented consistently (most qdiscs like sfq, codel, etc drop right away instead of attempting this reclassification) is the sole reason for the reshape_fail and __parent member in Qdisc struct. So remove TCA_CBQ_POLICE support from the kernel, reject it via EOPNOTSUPP so userspace knows we don't support it, and then remove no-longer needed infrastructure in followup commit. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/sch_generic.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c4f5749342ec..c069ac1dd75d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -68,10 +68,6 @@ struct Qdisc { void *u32_node; - /* This field is deprecated, but it is still used by CBQ - * and it will live until better solution will be invented. - */ - struct Qdisc *__parent; struct netdev_queue *dev_queue; struct gnet_stats_rate_est64 rate_est; -- cgit v1.2.3 From c3a173d7dba2d7c74dd4ab871b8f22bf56ac10b2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Jun 2016 00:27:41 +0200 Subject: sched: remove qdisc_rehape_fail After the removal of TCA_CBQ_POLICE in cbq scheduler qdisc->reshape_fail is always NULL, i.e. qdisc_rehape_fail is now the same as qdisc_drop. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/sch_generic.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c069ac1dd75d..a9aec633d467 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -63,9 +63,6 @@ struct Qdisc { struct list_head list; u32 handle; u32 parent; - int (*reshape_fail)(struct sk_buff *skb, - struct Qdisc *q); - void *u32_node; struct netdev_queue *dev_queue; @@ -771,22 +768,6 @@ static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_DROP; } -static inline int qdisc_reshape_fail(struct sk_buff *skb, struct Qdisc *sch) -{ - qdisc_qstats_drop(sch); - -#ifdef CONFIG_NET_CLS_ACT - if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) - goto drop; - - return NET_XMIT_SUCCESS; - -drop: -#endif - kfree_skb(skb); - return NET_XMIT_DROP; -} - /* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how long it will take to send a packet given its size. */ -- cgit v1.2.3 From a09ceb0e08140a1eec05b49b4c232d3481339cb0 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Jun 2016 00:27:42 +0200 Subject: sched: remove qdisc->drop after removal of TCA_CBQ_OVL_STRATEGY from cbq scheduler, there are no more callers of ->drop() outside of other ->drop functions, i.e. nothing calls them. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/sch_generic.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a9aec633d467..4dedb7f12ed5 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -174,7 +174,6 @@ struct Qdisc_ops { int (*enqueue)(struct sk_buff *, struct Qdisc *); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); - unsigned int (*drop)(struct Qdisc *); int (*init)(struct Qdisc *, struct nlattr *arg); void (*reset)(struct Qdisc *); @@ -658,22 +657,6 @@ static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch) return __qdisc_queue_drop_head(sch, &sch->q); } -static inline struct sk_buff *__qdisc_dequeue_tail(struct Qdisc *sch, - struct sk_buff_head *list) -{ - struct sk_buff *skb = __skb_dequeue_tail(list); - - if (likely(skb != NULL)) - qdisc_qstats_backlog_dec(sch, skb); - - return skb; -} - -static inline struct sk_buff *qdisc_dequeue_tail(struct Qdisc *sch) -{ - return __qdisc_dequeue_tail(sch, &sch->q); -} - static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { return skb_peek(&sch->q); @@ -741,25 +724,6 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, return old; } -static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch, - struct sk_buff_head *list) -{ - struct sk_buff *skb = __qdisc_dequeue_tail(sch, list); - - if (likely(skb != NULL)) { - unsigned int len = qdisc_pkt_len(skb); - kfree_skb(skb); - return len; - } - - return 0; -} - -static inline unsigned int qdisc_queue_drop(struct Qdisc *sch) -{ - return __qdisc_queue_drop(sch, &sch->q); -} - static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { kfree_skb(skb); -- cgit v1.2.3 From c8945043cdc687388b7a43fc6f474bddd9607e80 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 9 Jun 2016 00:27:43 +0200 Subject: sched: place state, next_sched and gso_skb in same cacheline again Earlier commits removed two members from struct Qdisc which places next_sched/gso_skb into a different cacheline than ->state. This restores the struct layout to what it was before the removal. Move the two members, then add an annotation so they all reside in the same cacheline. This adds a 16 byte hole after cpu_qstats. The hole could be closed but as it doesn't decrease total struct size just do it this way. Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/sch_generic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4dedb7f12ed5..49534e28824b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -71,11 +71,11 @@ struct Qdisc { struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; - struct Qdisc *next_sched; - struct sk_buff *gso_skb; /* * For performance sake on SMP, we put highly modified fields at the end */ + struct Qdisc *next_sched ____cacheline_aligned_in_smp; + struct sk_buff *gso_skb; unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; -- cgit v1.2.3 From 1dad640b9ef320e8de92c418bcc08448d67590a4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 9 Jun 2016 10:14:39 +0200 Subject: wext: reformat struct/union declarations Everytime I need to look for these, my usual strategy fails because it assumes the right formatting. Fix the formatting here to make it consistent with the rest of the kernel. Signed-off-by: Johannes Berg --- include/uapi/linux/wireless.h | 63 +++++++++++++++---------------------------- 1 file changed, 22 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index c1592e3e4036..d9ecd7c6d691 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -670,8 +670,7 @@ /* * Generic format for most parameters that fit in an int */ -struct iw_param -{ +struct iw_param { __s32 value; /* The value of the parameter itself */ __u8 fixed; /* Hardware should not use auto select */ __u8 disabled; /* Disable the feature */ @@ -682,8 +681,7 @@ struct iw_param * For all data larger than 16 octets, we need to use a * pointer to memory allocated in user space. */ -struct iw_point -{ +struct iw_point { void __user *pointer; /* Pointer to the data (in user space) */ __u16 length; /* number of fields or size in bytes */ __u16 flags; /* Optional params */ @@ -698,8 +696,7 @@ struct iw_point * of 10 to get 'm' lower than 10^9, with 'm'= f / (10^'e')... * The power of 10 is in 'e', the result of the division is in 'm'. */ -struct iw_freq -{ +struct iw_freq { __s32 m; /* Mantissa */ __s16 e; /* Exponent */ __u8 i; /* List index (when in range struct) */ @@ -709,8 +706,7 @@ struct iw_freq /* * Quality of the link */ -struct iw_quality -{ +struct iw_quality { __u8 qual; /* link quality (%retries, SNR, %missed beacons or better...) */ __u8 level; /* signal level (dBm) */ @@ -725,8 +721,7 @@ struct iw_quality * is already pretty exhaustive, and you should use that first. * This is only additional stats... */ -struct iw_discarded -{ +struct iw_discarded { __u32 nwid; /* Rx : Wrong nwid/essid */ __u32 code; /* Rx : Unable to code/decode (WEP) */ __u32 fragment; /* Rx : Can't perform MAC reassembly */ @@ -738,16 +733,14 @@ struct iw_discarded * Packet/Time period missed in the wireless adapter due to * "wireless" specific problems... */ -struct iw_missed -{ +struct iw_missed { __u32 beacon; /* Missed beacons/superframe */ }; /* * Quality range (for spy threshold) */ -struct iw_thrspy -{ +struct iw_thrspy { struct sockaddr addr; /* Source address (hw/mac) */ struct iw_quality qual; /* Quality of the link */ struct iw_quality low; /* Low threshold */ @@ -765,8 +758,7 @@ struct iw_thrspy * Especially, scan results are required to include an entry for the * current BSS if the driver is in Managed mode and associated with an AP. */ -struct iw_scan_req -{ +struct iw_scan_req { __u8 scan_type; /* IW_SCAN_TYPE_{ACTIVE,PASSIVE} */ __u8 essid_len; __u8 num_channels; /* num entries in channel_list; @@ -827,8 +819,7 @@ struct iw_scan_req * RX_SEQ_VALID for SIOCGIWENCODEEXT are optional, but can be useful for * debugging/testing. */ -struct iw_encode_ext -{ +struct iw_encode_ext { __u32 ext_flags; /* IW_ENCODE_EXT_* */ __u8 tx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ __u8 rx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ @@ -841,8 +832,7 @@ struct iw_encode_ext }; /* SIOCSIWMLME data */ -struct iw_mlme -{ +struct iw_mlme { __u16 cmd; /* IW_MLME_* */ __u16 reason_code; struct sockaddr addr; @@ -855,16 +845,14 @@ struct iw_mlme #define IW_PMKID_LEN 16 -struct iw_pmksa -{ +struct iw_pmksa { __u32 cmd; /* IW_PMKSA_* */ struct sockaddr bssid; __u8 pmkid[IW_PMKID_LEN]; }; /* IWEVMICHAELMICFAILURE data */ -struct iw_michaelmicfailure -{ +struct iw_michaelmicfailure { __u32 flags; struct sockaddr src_addr; __u8 tsc[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ @@ -872,8 +860,7 @@ struct iw_michaelmicfailure /* IWEVPMKIDCAND data */ #define IW_PMKID_CAND_PREAUTH 0x00000001 /* RNS pre-authentication enabled */ -struct iw_pmkid_cand -{ +struct iw_pmkid_cand { __u32 flags; /* IW_PMKID_CAND_* */ __u32 index; /* the smaller the index, the higher the * priority */ @@ -884,8 +871,7 @@ struct iw_pmkid_cand /* * Wireless statistics (used for /proc/net/wireless) */ -struct iw_statistics -{ +struct iw_statistics { __u16 status; /* Status * - device dependent for now */ @@ -897,7 +883,7 @@ struct iw_statistics /* ------------------------ IOCTL REQUEST ------------------------ */ /* - * This structure defines the payload of an ioctl, and is used + * This structure defines the payload of an ioctl, and is used * below. * * Note that this structure should fit on the memory footprint @@ -906,8 +892,7 @@ struct iw_statistics * You should check this when increasing the structures defined * above in this file... */ -union iwreq_data -{ +union iwreq_data { /* Config - generic */ char name[IFNAMSIZ]; /* Name : used to verify the presence of wireless extensions. @@ -944,15 +929,14 @@ union iwreq_data * convenience... * Do I need to remind you about structure size (32 octets) ? */ -struct iwreq -{ +struct iwreq { union { char ifrn_name[IFNAMSIZ]; /* if name, e.g. "eth0" */ } ifr_ifrn; /* Data part (defined just above) */ - union iwreq_data u; + union iwreq_data u; }; /* -------------------------- IOCTL DATA -------------------------- */ @@ -965,8 +949,7 @@ struct iwreq * Range of parameters */ -struct iw_range -{ +struct iw_range { /* Informative stuff (to choose between different interface) */ __u32 throughput; /* To give an idea... */ /* In theory this value should be the maximum benchmarked @@ -1069,9 +1052,8 @@ struct iw_range /* * Private ioctl interface information */ - -struct iw_priv_args -{ + +struct iw_priv_args { __u32 cmd; /* Number of the ioctl to issue */ __u16 set_args; /* Type and number of args */ __u16 get_args; /* Type and number of args */ @@ -1088,8 +1070,7 @@ struct iw_priv_args /* * A Wireless Event. Contains basically the same data as the ioctl... */ -struct iw_event -{ +struct iw_event { __u16 len; /* Real length of this stuff */ __u16 cmd; /* Wireless IOCTL */ union iwreq_data u; /* IOCTL fixed payload */ -- cgit v1.2.3 From 80a83cfc434b1e3afe38974570b460db4898bec6 Mon Sep 17 00:00:00 2001 From: Michal Kazior Date: Thu, 19 May 2016 10:37:48 +0200 Subject: mac80211: skip netdev queue control with software queuing Qdiscs are designed with no regard to 802.11 aggregation requirements and hand out packet-by-packet with no guarantee they are destined to the same tid. This does more bad than good no matter how fairly a given qdisc may behave on an ethernet interface. Software queuing used per-AC netdev subqueue congestion control whenever a global AC limit was hit. This meant in practice a single station or tid queue could starve others rather easily. This could resonate with qdiscs in a bad way or could just end up with poor aggregation performance. Increasing the AC limit would increase induced latency which is also bad. Disabling qdiscs by default and performing taildrop instead of netdev subqueue congestion control on the other hand makes it possible for tid queues to fill up "in the meantime" while preventing stations starving each other. This increases aggregation opportunities and should allow software queuing based drivers achieve better performance by utilizing airtime more efficiently with big aggregates. Signed-off-by: Michal Kazior Signed-off-by: Johannes Berg --- include/net/mac80211.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index be30b0549b88..a8683aec6dbe 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2147,9 +2147,6 @@ enum ieee80211_hw_flags { * @n_cipher_schemes: a size of an array of cipher schemes definitions. * @cipher_schemes: a pointer to an array of cipher scheme definitions * supported by HW. - * - * @txq_ac_max_pending: maximum number of frames per AC pending in all txq - * entries for a vif. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2180,7 +2177,6 @@ struct ieee80211_hw { u8 uapsd_max_sp_len; u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; - int txq_ac_max_pending; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, -- cgit v1.2.3 From 5caa328e3811b7cfa33fd02c93280ffa622deb0e Mon Sep 17 00:00:00 2001 From: Michal Kazior Date: Thu, 19 May 2016 10:37:51 +0200 Subject: mac80211: implement codel on fair queuing flows There is no other limit other than a global packet count limit when using software queuing. This means a single flow queue can grow insanely long. This is particularly bad for TCP congestion algorithms which requires a little more sophisticated frame dropping scheme than a mere headdrop on limit overflow. Hence apply (a slighly modified, to fit the knobs) CoDel5 on flow queues. This improves TCP convergence and stability when combined with wireless driver which keeps its own tx queue/fifo at a minimum fill level for given link conditions. Signed-off-by: Michal Kazior Signed-off-by: Johannes Berg --- include/net/mac80211.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a8683aec6dbe..a52009ffc19f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -21,6 +21,7 @@ #include #include #include +#include #include /** @@ -895,7 +896,18 @@ struct ieee80211_tx_info { unsigned long jiffies; }; /* NB: vif can be NULL for injected frames */ - struct ieee80211_vif *vif; + union { + /* NB: vif can be NULL for injected frames */ + struct ieee80211_vif *vif; + + /* When packets are enqueued on txq it's easy + * to re-construct the vif pointer. There's no + * more space in tx_info so it can be used to + * store the necessary enqueue time for packet + * sojourn time computation. + */ + codel_time_t enqueue_time; + }; struct ieee80211_key_conf *hw_key; u32 flags; /* 4 bytes free */ -- cgit v1.2.3 From fc1e1c4a249e8bf0aff68576fad776dd5adc0562 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 9 Jun 2016 10:49:02 +0100 Subject: regulator: Remove regulator_can_change_voltage() There is little obvious use case for a regualtor driver to know if it is possible to vary voltages at all by itself. If a consumer needs to limit what voltages it tries to set based on the system configuration then it will need to enumerate the possible voltages, and without that even if it is possible to change voltages that doesn't mean that constraints or other consumers will allow whatever change the driver is trying to do at a given time. It doesn't even indicate if _set_voltage() calls will work as noop _set_voltage() calls return success. There were no users of this API that weren't abusing it and now they're all gone so remove the API. Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 48603506f8de..cae500b2c1d7 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -224,7 +224,6 @@ int regulator_bulk_force_disable(int num_consumers, void regulator_bulk_free(int num_consumers, struct regulator_bulk_data *consumers); -int regulator_can_change_voltage(struct regulator *regulator); int regulator_count_voltages(struct regulator *regulator); int regulator_list_voltage(struct regulator *regulator, unsigned selector); int regulator_is_supported_voltage(struct regulator *regulator, @@ -436,11 +435,6 @@ static inline void regulator_bulk_free(int num_consumers, { } -static inline int regulator_can_change_voltage(struct regulator *regulator) -{ - return 0; -} - static inline int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV) { -- cgit v1.2.3 From ca93e45347e61cd85e5d71961f6c94fad143593d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 9 Jun 2016 16:00:35 +0200 Subject: block: better packing for struct request Keep the 32-bit CPU and cmd_type flags together to avoid holes on 64-bit architectures. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0c9f8793c87e..9746d223494c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -96,12 +96,11 @@ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; - u64 cmd_flags; + int cpu; unsigned cmd_type; + u64 cmd_flags; unsigned long atomic_flags; - int cpu; - /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ -- cgit v1.2.3 From 288dab8a35a0bde426a09870943c8d3ee3a50dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 9 Jun 2016 16:00:36 +0200 Subject: block: add a separate operation type for secure erase Instead of overloading the discard support with the REQ_SECURE flag. Use the opportunity to rename the queue flag as well, and remove the dead checks for this flag in the RAID 1 and RAID 10 drivers that don't claim support for secure erase. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 5 ++--- include/linux/blkdev.h | 23 ++++------------------- 2 files changed, 6 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 562ab8301217..efba1f2ace2e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -163,7 +163,6 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ - __REQ_SECURE, /* secure discard (used with REQ_OP_DISCARD) */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ @@ -212,7 +211,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) + REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE) #define REQ_CLONE_MASK REQ_COMMON_MASK /* This mask is used for both bio and request merge checking */ @@ -239,7 +238,6 @@ enum rq_flag_bits { #define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) #define REQ_IO_STAT (1ULL << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) -#define REQ_SECURE (1ULL << __REQ_SECURE) #define REQ_PM (1ULL << __REQ_PM) #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) @@ -248,6 +246,7 @@ enum req_op { REQ_OP_READ, REQ_OP_WRITE, REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ REQ_OP_WRITE_SAME, /* write same block many times */ REQ_OP_FLUSH, /* request for cache flush */ }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0c9f8793c87e..53fee6123893 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -497,7 +497,7 @@ struct request_queue { #define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ -#define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */ +#define QUEUE_FLAG_SECERASE 17 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ @@ -593,8 +593,8 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_stackable(q) \ test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) -#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \ - test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) +#define blk_queue_secure_erase(q) \ + (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ @@ -675,21 +675,6 @@ static inline bool rq_mergeable(struct request *rq) return true; } -static inline bool blk_check_merge_flags(unsigned int flags1, unsigned int op1, - unsigned int flags2, unsigned int op2) -{ - if ((op1 == REQ_OP_DISCARD) != (op2 == REQ_OP_DISCARD)) - return false; - - if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE)) - return false; - - if ((op1 == REQ_OP_WRITE_SAME) != (op2 == REQ_OP_WRITE_SAME)) - return false; - - return true; -} - static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_data(a) == bio_data(b)) @@ -1158,7 +1143,7 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int op_flags, + sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); -- cgit v1.2.3 From 8fc554552c9d89e7bf76cd4cbc0085648bf3125b Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 9 Jun 2016 10:00:58 -0600 Subject: block: move bvec iterator into include/linux/bvec.h bvec iterator helpers should be used to implement by iterate_bvec():lib/iov_iter.c too, and move them into one header, so that we can keep bvec iterator header out of CONFIG_BLOCK. Then we can remove the reinventing of wheel in iterate_bvec(). Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Tested-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 51 +----------------------------------- include/linux/bvec.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 75 insertions(+), 50 deletions(-) create mode 100644 include/linux/bvec.h (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0bbb2e332410..8e0f677c26d2 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -31,6 +31,7 @@ /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include +#include #define BIO_DEBUG @@ -47,29 +48,6 @@ #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) -/* - * various member access, note that bio_data should of course not be used - * on highmem page vectors - */ -#define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) - -#define bvec_iter_page(bvec, iter) \ - (__bvec_iter_bvec((bvec), (iter))->bv_page) - -#define bvec_iter_len(bvec, iter) \ - min((iter).bi_size, \ - __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) - -#define bvec_iter_offset(bvec, iter) \ - (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) - -#define bvec_iter_bvec(bvec, iter) \ -((struct bio_vec) { \ - .bv_page = bvec_iter_page((bvec), (iter)), \ - .bv_len = bvec_iter_len((bvec), (iter)), \ - .bv_offset = bvec_iter_offset((bvec), (iter)), \ -}) - #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) @@ -188,33 +166,6 @@ static inline void *bio_data(struct bio *bio) #define bio_for_each_segment_all(bvl, bio, i) \ for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++) -static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, - unsigned bytes) -{ - WARN_ONCE(bytes > iter->bi_size, - "Attempted to advance past end of bvec iter\n"); - - while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); - - bytes -= len; - iter->bi_size -= len; - iter->bi_bvec_done += len; - - if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { - iter->bi_bvec_done = 0; - iter->bi_idx++; - } - } -} - -#define for_each_bvec(bvl, bio_vec, iter, start) \ - for (iter = (start); \ - (iter).bi_size && \ - ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ - bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) - - static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, unsigned bytes) { diff --git a/include/linux/bvec.h b/include/linux/bvec.h new file mode 100644 index 000000000000..29c459da277e --- /dev/null +++ b/include/linux/bvec.h @@ -0,0 +1,74 @@ +/* + * bvec iterator + * + * Copyright (C) 2001 Ming Lei + * + * 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 Licens + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111- + */ +#ifndef __LINUX_BVEC_ITER_H +#define __LINUX_BVEC_ITER_H + +#include + +/* + * various member access, note that bio_data should of course not be used + * on highmem page vectors + */ +#define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) + +#define bvec_iter_page(bvec, iter) \ + (__bvec_iter_bvec((bvec), (iter))->bv_page) + +#define bvec_iter_len(bvec, iter) \ + min((iter).bi_size, \ + __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) + +#define bvec_iter_offset(bvec, iter) \ + (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) + +#define bvec_iter_bvec(bvec, iter) \ +((struct bio_vec) { \ + .bv_page = bvec_iter_page((bvec), (iter)), \ + .bv_len = bvec_iter_len((bvec), (iter)), \ + .bv_offset = bvec_iter_offset((bvec), (iter)), \ +}) + +static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, + unsigned bytes) +{ + WARN_ONCE(bytes > iter->bi_size, + "Attempted to advance past end of bvec iter\n"); + + while (bytes) { + unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + + bytes -= len; + iter->bi_size -= len; + iter->bi_bvec_done += len; + + if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { + iter->bi_bvec_done = 0; + iter->bi_idx++; + } + } +} + +#define for_each_bvec(bvl, bio_vec, iter, start) \ + for (iter = (start); \ + (iter).bi_size && \ + ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ + bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) + +#endif /* __LINUX_BVEC_ITER_H */ -- cgit v1.2.3 From 0781e79eb206a62c30cc3eff75aaa889cd85b276 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 30 May 2016 21:34:30 +0800 Subject: block: move two bvec structure into bvec.h This patch moves 'struct bio_vec' and 'struct bvec_iter' into 'include/linux/bvec.h', then always include this header into 'include/linux/blk_types.h'. With this change, both 'struct bvec_iter' and bvec iterator helpers don't depend on CONFIG_BLOCK any more, then we can use bvec iterator to implement iterate_bvec(): lib/iov_iter.c. Reviewed-by: Christoph Hellwig Suggested-by: Christoph Hellwig Signed-off-by: Ming Lei Tested-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - include/linux/blk_types.h | 22 +--------------------- include/linux/bvec.h | 23 ++++++++++++++++++++++- 3 files changed, 23 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 8e0f677c26d2..95500fee0544 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -31,7 +31,6 @@ /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include -#include #define BIO_DEBUG diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 562ab8301217..b588e968dc01 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -6,6 +6,7 @@ #define __LINUX_BLK_TYPES_H #include +#include struct bio_set; struct bio; @@ -17,28 +18,7 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); -/* - * was unsigned short, but we might as well be ready for > 64kB I/O pages - */ -struct bio_vec { - struct page *bv_page; - unsigned int bv_len; - unsigned int bv_offset; -}; - #ifdef CONFIG_BLOCK - -struct bvec_iter { - sector_t bi_sector; /* device address in 512 byte - sectors */ - unsigned int bi_size; /* residual I/O count */ - - unsigned int bi_idx; /* current index into bvl_vec */ - - unsigned int bi_bvec_done; /* number of bytes completed in - current bvec */ -}; - /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 29c459da277e..096efd2c83e5 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -20,7 +20,28 @@ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H -#include +#include +#include + +/* + * was unsigned short, but we might as well be ready for > 64kB I/O pages + */ +struct bio_vec { + struct page *bv_page; + unsigned int bv_len; + unsigned int bv_offset; +}; + +struct bvec_iter { + sector_t bi_sector; /* device address in 512 byte + sectors */ + unsigned int bi_size; /* residual I/O count */ + + unsigned int bi_idx; /* current index into bvl_vec */ + + unsigned int bi_bvec_done; /* number of bytes completed in + current bvec */ +}; /* * various member access, note that bio_data should of course not be used -- cgit v1.2.3 From 80f162ff061c9e280589bb1a1890c7fc21c932cd Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 30 May 2016 21:34:31 +0800 Subject: block: mark 1st parameter of bvec_iter_advance as const bvec_iter_advance() only writes the parameter of iterator, so the base address of bvec can be marked as const safely. Without the change, we can see compiling warning in the following patch for implementing iterate_bvec(): lib/iov_iter.c with bvec iterator. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Tested-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bvec.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 096efd2c83e5..701b64a3b7c5 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -66,7 +66,8 @@ struct bvec_iter { .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) -static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, +static inline void bvec_iter_advance(const struct bio_vec *bv, + struct bvec_iter *iter, unsigned bytes) { WARN_ONCE(bytes > iter->bi_size, -- cgit v1.2.3 From 30ac4607d553277b927457678e48bb2e5de1717d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 9 Jun 2016 10:03:28 -0600 Subject: block: bio: remove BIO_MAX_SECTORS No one need this macro, so remove it. The motivation is for supporting multipage bvecs, in which we only know what the max count of bvecs is supported in the bio, instead of max size or max sectors. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Tested-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 95500fee0544..b64a3d9434d4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -42,7 +42,6 @@ #define BIO_MAX_PAGES 256 #define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) -#define BIO_MAX_SECTORS (BIO_MAX_SIZE >> 9) #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) -- cgit v1.2.3 From eb53a15b1ab820f51603efd76cdc723fdfafaae0 Mon Sep 17 00:00:00 2001 From: Lokesh Vutla Date: Thu, 9 Jun 2016 09:40:21 -0700 Subject: ARM: dts: keystone: Header file for pinctrl constants The pinctrl IP used in some of the Keystone 2 devices differ vs other TI SoCs. Therefore, create a Keystone specific pinctrl header. Signed-off-by: Lokesh Vutla Signed-off-by: Franklin S Cooper Jr Signed-off-by: Tero Kristo Signed-off-by: Dave Gerlach Signed-off-by: Santosh Shilimkar --- include/dt-bindings/pinctrl/keystone.h | 39 ++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/dt-bindings/pinctrl/keystone.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/keystone.h b/include/dt-bindings/pinctrl/keystone.h new file mode 100644 index 000000000000..7f97d776a8ff --- /dev/null +++ b/include/dt-bindings/pinctrl/keystone.h @@ -0,0 +1,39 @@ +/* + * This header provides constants for Keystone pinctrl bindings. + * + * Copyright (C) 2016 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _DT_BINDINGS_PINCTRL_KEYSTONE_H +#define _DT_BINDINGS_PINCTRL_KEYSTONE_H + +#define MUX_MODE0 0 +#define MUX_MODE1 1 +#define MUX_MODE2 2 +#define MUX_MODE3 3 +#define MUX_MODE4 4 +#define MUX_MODE5 5 + +#define BUFFER_CLASS_B (0 << 19) +#define BUFFER_CLASS_C (1 << 19) +#define BUFFER_CLASS_D (2 << 19) +#define BUFFER_CLASS_E (3 << 19) + +#define PULL_DISABLE (1 << 16) +#define PIN_PULLUP (1 << 17) +#define PIN_PULLDOWN (0 << 17) + +#define KEYSTONE_IOPAD_OFFSET(pa, offset) (((pa) & 0xffff) - (offset)) + +#define K2G_CORE_IOPAD(pa) KEYSTONE_IOPAD_OFFSET((pa), 0x1000) + +#endif -- cgit v1.2.3 From 1c7fe6b438433e16d5b1211380c305351ac38299 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 9 Jun 2016 20:10:11 +0200 Subject: mtd: nand: add ESMT manufacturer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I got device with ESMT (Elite Semiconductor Memory Technology Inc) F59L1G81MA flash that was detected as: [ 0.852034] nand: device found, Manufacturer ID: 0xc8, Chip ID: 0xd1 [ 0.858402] nand: Unknown NAND 128MiB 3,3V 8-bit [ 0.863031] nand: 128MiB, SLC, page size: 2048, OOB size: 64 According to the F59L1G81MA datasheet (and Read Id documentation) C8h is a "Maker Code" which should mean ESMT. Add it to fix above "Unknown". Signed-off-by: Rafał Miłecki Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index fbe8e164a4ee..8dd6e01f45c0 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -783,6 +783,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) * NAND Flash Manufacturer ID Codes */ #define NAND_MFR_TOSHIBA 0x98 +#define NAND_MFR_ESMT 0xc8 #define NAND_MFR_SAMSUNG 0xec #define NAND_MFR_FUJITSU 0x04 #define NAND_MFR_NATIONAL 0x8f -- cgit v1.2.3 From 52fbb2907988aa0583c6d9d53a56aee090b2df7e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Jun 2016 07:45:11 -0700 Subject: net: sched: fix qdisc->running lockdep annotations 1) qdisc_run_begin() is really using the equivalent of a trylock. Instead of using write_seqcount_begin(), use a combination of raw_write_seqcount_begin() and correct lockdep annotation. 2) sch_direct_xmit() should use regular spin_lock(root_lock) Fixes: f9eb8aea2a1e ("net_sched: transform qdisc running bit into a seqcount") Signed-off-by: Eric Dumazet Reported-by: David Ahern Signed-off-by: David S. Miller --- include/net/sch_generic.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 49534e28824b..a4c0f1649e2b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -97,7 +97,11 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc_is_running(qdisc)) return false; - write_seqcount_begin(&qdisc->running); + /* Variant of write_seqcount_begin() telling lockdep a trylock + * was attempted. + */ + raw_write_seqcount_begin(&qdisc->running); + seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); return true; } -- cgit v1.2.3 From d3fff6c443fe8f8a5ef2bdcea45e2ff39db948c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Jun 2016 07:45:12 -0700 Subject: net: add netdev_lockdep_set_classes() helper It is time to add netdev_lockdep_set_classes() helper so that lockdep annotations per device type are easier to manage. This removes a lot of copies and missing annotations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 541562333ba5..4f234b102892 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1946,6 +1946,23 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_running_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + static struct lock_class_key dev_addr_list_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + (dev)->qdisc_running_key = &qdisc_running_key; \ + lockdep_set_class(&(dev)->addr_list_lock, \ + &dev_addr_list_lock_key); \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -- 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 --- include/linux/extcon.h | 80 +++++++++++++++----------------------------------- 1 file changed, 23 insertions(+), 57 deletions(-) (limited to 'include') 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 1a89694f7899d39aa58cc6f061e97a17089ac025 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 10 Jun 2016 11:27:12 +0800 Subject: block: bio: kill BIO_MAX_SIZE No one need this macro now, so remove it. Basically only how many bvecs in one bio matters instead of how many bytes in this bio. The motivation is for supporting multipage bvecs, in which we only know what the max count of bvecs is supported in the bio. Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index b64a3d9434d4..b7e1a00810f2 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -41,7 +41,6 @@ #endif #define BIO_MAX_PAGES 256 -#define BIO_MAX_SIZE (BIO_MAX_PAGES << PAGE_SHIFT) #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) -- cgit v1.2.3 From 967dd82ffc52e9d8ea0defde094f9a39a3f4eeed Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 9 Jun 2016 18:23:53 -0700 Subject: net: dsa: b53: Add support for Broadcom RoboSwitch This patch adds support for Broadcom's BCM53xx switch family, also known as RoboSwitch. Some of these switches are ubiquituous, found in home routers, Wi-Fi routers, DSL and cable modem gateways and other networking related products. This drivers adds the library driver (b53_common.c) as well as a few bus glue drivers for MDIO, SPI, Switch Register Access Block (SRAB) and memory-mapped I/O into a SoC's address space (Broadcom BCM63xx/33xx). Basic operations are supported to bring the Layer 1/2 up and running, but not much more at this point, subsequent patches add the remaining features. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/b53.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) create mode 100644 include/linux/platform_data/b53.h (limited to 'include') diff --git a/include/linux/platform_data/b53.h b/include/linux/platform_data/b53.h new file mode 100644 index 000000000000..69d279c0da96 --- /dev/null +++ b/include/linux/platform_data/b53.h @@ -0,0 +1,33 @@ +/* + * B53 platform data + * + * Copyright (C) 2013 Jonas Gorski + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef __B53_H +#define __B53_H + +#include + +struct b53_platform_data { + u32 chip_id; + u16 enabled_ports; + + /* only used by MMAP'd driver */ + unsigned big_endian:1; + void __iomem *regs; +}; + +#endif -- cgit v1.2.3 From 2341e0775747864b684abe8627f3d45b167f2940 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 9 Jun 2016 23:02:51 +0100 Subject: rxrpc: Simplify connect() implementation and simplify sendmsg() op Simplify the RxRPC connect() implementation. It will just note the destination address it is given, and if a sendmsg() comes along with no address, this will be assigned as the address. No transport struct will be held internally, which will allow us to remove this later. Simplify sendmsg() also. Whilst a call is active, userspace refers to it by a private unique user ID specified in a control message. When sendmsg() sees a user ID that doesn't map to an extant call, it creates a new call for that user ID and attempts to add it. If, when we try to add it, the user ID is now registered, we now reject the message with -EEXIST. We should never see this situation unless two threads are racing, trying to create a call with the same ID - which would be an error. It also isn't required to provide sendmsg() with an address - provided the control message data holds a user ID that maps to a currently active call. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/linux/rxrpc.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h index a53915cd5581..1e8f216e2cf1 100644 --- a/include/linux/rxrpc.h +++ b/include/linux/rxrpc.h @@ -40,16 +40,18 @@ struct sockaddr_rxrpc { /* * RxRPC control messages + * - If neither abort or accept are specified, the message is a data message. * - terminal messages mean that a user call ID tag can be recycled + * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() */ -#define RXRPC_USER_CALL_ID 1 /* user call ID specifier */ -#define RXRPC_ABORT 2 /* abort request / notification [terminal] */ -#define RXRPC_ACK 3 /* [Server] RPC op final ACK received [terminal] */ -#define RXRPC_NET_ERROR 5 /* network error received [terminal] */ -#define RXRPC_BUSY 6 /* server busy received [terminal] */ -#define RXRPC_LOCAL_ERROR 7 /* local error generated [terminal] */ -#define RXRPC_NEW_CALL 8 /* [Server] new incoming call notification */ -#define RXRPC_ACCEPT 9 /* [Server] accept request */ +#define RXRPC_USER_CALL_ID 1 /* sr: user call ID specifier */ +#define RXRPC_ABORT 2 /* sr: abort request / notification [terminal] */ +#define RXRPC_ACK 3 /* -r: [Service] RPC op final ACK received [terminal] */ +#define RXRPC_NET_ERROR 5 /* -r: network error received [terminal] */ +#define RXRPC_BUSY 6 /* -r: server busy received [terminal] */ +#define RXRPC_LOCAL_ERROR 7 /* -r: local error generated [terminal] */ +#define RXRPC_NEW_CALL 8 /* -r: [Service] new incoming call notification */ +#define RXRPC_ACCEPT 9 /* s-: [Service] accept request */ /* * RxRPC security levels -- cgit v1.2.3 From e434863718d4b99dd0d6e0cefd3c5e79e4fa2083 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 9 Jun 2016 10:21:00 -0700 Subject: net: vrf: Fix crash when IPv6 is disabled at boot time Frank Kellermann reported a kernel crash with 4.5.0 when IPv6 is disabled at boot using the kernel option ipv6.disable=1. Using current net-next with the boot option: $ ip link add red type vrf table 1001 Generates: [12210.919584] BUG: unable to handle kernel NULL pointer dereference at 0000000000000748 [12210.921341] IP: [] fib6_get_table+0x2c/0x5a [12210.922537] PGD b79e3067 PUD bb32b067 PMD 0 [12210.923479] Oops: 0000 [#1] SMP [12210.924001] Modules linked in: ipvlan 8021q garp mrp stp llc [12210.925130] CPU: 3 PID: 1177 Comm: ip Not tainted 4.7.0-rc1+ #235 [12210.926168] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 [12210.928065] task: ffff8800b9ac4640 ti: ffff8800bacac000 task.ti: ffff8800bacac000 [12210.929328] RIP: 0010:[] [] fib6_get_table+0x2c/0x5a [12210.930697] RSP: 0018:ffff8800bacaf888 EFLAGS: 00010202 [12210.931563] RAX: 0000000000000748 RBX: ffffffff81a9e280 RCX: ffff8800b9ac4e28 [12210.932688] RDX: 00000000000000e9 RSI: 0000000000000002 RDI: 0000000000000286 [12210.933820] RBP: ffff8800bacaf898 R08: ffff8800b9ac4df0 R09: 000000000052001b [12210.934941] R10: 00000000657c0000 R11: 000000000000c649 R12: 00000000000003e9 [12210.936032] R13: 00000000000003e9 R14: ffff8800bace7800 R15: ffff8800bb3ec000 [12210.937103] FS: 00007faa1766c700(0000) GS:ffff88013ac00000(0000) knlGS:0000000000000000 [12210.938321] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [12210.939166] CR2: 0000000000000748 CR3: 00000000b79d6000 CR4: 00000000000406e0 [12210.940278] Stack: [12210.940603] ffff8800bb3ec000 ffffffff81a9e280 ffff8800bacaf8c8 ffffffff814b3135 [12210.941818] ffff8800bb3ec000 ffffffff81a9e280 ffffffff81a9e280 ffff8800bace7800 [12210.943040] ffff8800bacaf8f0 ffffffff81397c88 ffff8800bb3ec000 ffffffff81a9e280 [12210.944288] Call Trace: [12210.944688] [] fib6_new_table+0x24/0x8a [12210.945516] [] vrf_dev_init+0xd4/0x162 [12210.946328] [] register_netdevice+0x100/0x396 [12210.947209] [] vrf_newlink+0x40/0xb3 [12210.948001] [] rtnl_newlink+0x5d3/0x6d5 ... The problem above is due to the fact that the fib hash table is not allocated when IPv6 is disabled at boot. As for the VRF driver it should not do any IPv6 initializations if IPv6 is disabled, so it needs to know if IPv6 is disabled at boot. The disable parameter is private to the IPv6 module, so provide an accessor for modules to determine if IPv6 was disabled at boot time. Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5c91b0b055d4..c6dbcd84a2c7 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -283,6 +283,8 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) +bool ipv6_mod_enabled(void); + static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; @@ -326,6 +328,11 @@ static inline int inet_v6_ipv6only(const struct sock *sk) #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 +static inline bool ipv6_mod_enabled(void) +{ + return false; +} + static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { return NULL; -- cgit v1.2.3 From 7d84e37e114215be0a0c80095891c8268a99352b Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Thu, 9 Jun 2016 13:41:15 -0400 Subject: virtio_net: Update the feature bit to comply with spec A draft version of the MTU Advice feature bit was specified as 25. This bit is not within the allowed range for network device feature bits, and should be changed to be feature bit 3 to fully comply with the spec. Fixes 14de9d114a82 ('virtio-net: Add initial MTU advice feature') Signed-off-by: Aaron Conole Suggested-by: "Michael S. Tsirkin" Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 1ab4ea6ec847..0da0e3a98f17 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -35,6 +35,7 @@ #define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */ #define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */ #define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */ +#define VIRTIO_NET_F_MTU 3 /* Initial MTU advice */ #define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */ #define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */ #define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */ @@ -55,7 +56,6 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ -#define VIRTIO_NET_F_MTU 25 /* Initial MTU advice */ #ifndef VIRTIO_NET_NO_LEGACY #define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */ -- cgit v1.2.3 From 0e4504470667d355b53ca3c9802fdd2120c9f946 Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Fri, 10 Jun 2016 13:56:32 +0900 Subject: clk: samsung: exynos5433: Add CLK_IGNORE_UNUSED flag to PCIE device This patch adds the CLK_IGNORE_UNUSED flag for PCI Express's clocks which need to remain enabled. The 'pcie' gate clock definition is also added. Signed-off-by: Jaehoon Chung Signed-off-by: Chanwoo Choi [s.nawrocki@samsung.com: edited the patch's summary] Signed-off-by: Sylwester Nawrocki --- include/dt-bindings/clock/exynos5433.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/exynos5433.h b/include/dt-bindings/clock/exynos5433.h index 8e024fea26e7..4fa6bb2136e3 100644 --- a/include/dt-bindings/clock/exynos5433.h +++ b/include/dt-bindings/clock/exynos5433.h @@ -622,8 +622,9 @@ #define CLK_SCLK_UFSUNIPRO 112 #define CLK_SCLK_USBHOST30 113 #define CLK_SCLK_USBDRD30 114 +#define CLK_PCIE 115 -#define FSYS_NR_CLK 115 +#define FSYS_NR_CLK 116 /* CMU_G2D */ #define CLK_MUX_ACLK_G2D_266_USER 1 -- cgit v1.2.3 From 7486216b3a0bd26375b17b2cc168a311106cea70 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 9 Jun 2016 15:11:34 +0300 Subject: {net,IB}/mlx5: mlx5_ifc updates Introducing mlx5_ifc updates for upcoming ConnectX-4 features. Needed bits and hardware structures for mlx5e netdev: - MLX5_CQ_PERIOD_NUM_MODES for adaptive moderation support - QoS rate limiting - SQ context rate limiting - Auto negotiation fields in PTYS register - Source SQN field in flow table entry match structure - DCBX parameters Needed bits and hardware structures for IB: - New XRQ opcodes, commands and capabilities layout - Extend q counters definition to support IB. Signed-off-by: Saeed Mahameed Signed-off-by: Leon Romanovsky Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 275 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 263 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9a05cd7e5890..209add93159f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -123,6 +123,10 @@ enum { MLX5_CMD_OP_DRAIN_DCT = 0x712, MLX5_CMD_OP_QUERY_DCT = 0x713, MLX5_CMD_OP_ARM_DCT_FOR_KEY_VIOLATION = 0x714, + MLX5_CMD_OP_CREATE_XRQ = 0x717, + MLX5_CMD_OP_DESTROY_XRQ = 0x718, + MLX5_CMD_OP_QUERY_XRQ = 0x719, + MLX5_CMD_OP_ARM_XRQ = 0x71a, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -139,6 +143,8 @@ enum { MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, + MLX5_CMD_OP_SET_RATE_LIMIT = 0x780, + MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, MLX5_CMD_OP_ALLOC_PD = 0x800, MLX5_CMD_OP_DEALLOC_PD = 0x801, MLX5_CMD_OP_ALLOC_UAR = 0x802, @@ -361,7 +367,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { }; struct mlx5_ifc_fte_match_set_misc_bits { - u8 reserved_at_0[0x20]; + u8 reserved_at_0[0x8]; + u8 source_sqn[0x18]; u8 reserved_at_20[0x10]; u8 source_port[0x10]; @@ -505,6 +512,17 @@ struct mlx5_ifc_e_switch_cap_bits { u8 reserved_at_20[0x7e0]; }; +struct mlx5_ifc_qos_cap_bits { + u8 packet_pacing[0x1]; + u8 reserved_0[0x1f]; + u8 reserved_1[0x20]; + u8 packet_pacing_max_rate[0x20]; + u8 packet_pacing_min_rate[0x20]; + u8 reserved_2[0x10]; + u8 packet_pacing_rate_table_size[0x10]; + u8 reserved_3[0x760]; +}; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 csum_cap[0x1]; u8 vlan_cap[0x1]; @@ -744,7 +762,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 out_of_seq_cnt[0x1]; u8 vport_counters[0x1]; - u8 reserved_at_182[0x4]; + u8 retransmission_q_counters[0x1]; + u8 reserved_at_183[0x3]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -771,7 +790,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_msg[0x5]; u8 reserved_at_1c8[0x4]; u8 max_tc[0x4]; - u8 reserved_at_1d0[0x6]; + u8 reserved_at_1d0[0x1]; + u8 dcbx[0x1]; + u8 reserved_at_1d2[0x4]; u8 rol_s[0x1]; u8 rol_g[0x1]; u8 reserved_at_1d8[0x1]; @@ -803,7 +824,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 tph[0x1]; u8 rf[0x1]; u8 dct[0x1]; - u8 reserved_at_21b[0x1]; + u8 qos[0x1]; u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; @@ -929,7 +950,15 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cqe_compression_timeout[0x10]; u8 cqe_compression_max_num[0x10]; - u8 reserved_at_5e0[0x220]; + u8 reserved_at_5e0[0x10]; + u8 tag_matching[0x1]; + u8 rndv_offload_rc[0x1]; + u8 rndv_offload_dc[0x1]; + u8 log_tag_matching_list_sz[0x5]; + u8 reserved_at_5e8[0x3]; + u8 log_max_xrq[0x5]; + + u8 reserved_at_5f0[0x200]; }; enum mlx5_flow_destination_type { @@ -1967,7 +1996,7 @@ struct mlx5_ifc_qpc_bits { u8 reserved_at_560[0x5]; u8 rq_type[0x3]; - u8 srqn_rmpn[0x18]; + u8 srqn_rmpn_xrqn[0x18]; u8 reserved_at_580[0x8]; u8 rmsn[0x18]; @@ -2018,6 +2047,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; + struct mlx5_ifc_qos_cap_bits qos_cap; u8 reserved_at_0[0x8000]; }; @@ -2244,8 +2274,9 @@ struct mlx5_ifc_sqc_bits { u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_at_60[0xa0]; + u8 reserved_at_60[0x90]; + u8 packet_pacing_rate_limit_index[0x10]; u8 tis_lst_sz[0x10]; u8 reserved_at_110[0x10]; @@ -2593,7 +2624,7 @@ struct mlx5_ifc_dctc_bits { u8 reserved_at_98[0x8]; u8 reserved_at_a0[0x8]; - u8 srqn[0x18]; + u8 srqn_xrqn[0x18]; u8 reserved_at_c0[0x8]; u8 pd[0x18]; @@ -2645,6 +2676,7 @@ enum { enum { MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, + MLX5_CQ_PERIOD_NUM_MODES }; struct mlx5_ifc_cqc_bits { @@ -2722,6 +2754,54 @@ struct mlx5_ifc_query_adapter_param_block_bits { u8 vsd_contd_psid[16][0x8]; }; +enum { + MLX5_XRQC_STATE_GOOD = 0x0, + MLX5_XRQC_STATE_ERROR = 0x1, +}; + +enum { + MLX5_XRQC_TOPOLOGY_NO_SPECIAL_TOPOLOGY = 0x0, + MLX5_XRQC_TOPOLOGY_TAG_MATCHING = 0x1, +}; + +enum { + MLX5_XRQC_OFFLOAD_RNDV = 0x1, +}; + +struct mlx5_ifc_tag_matching_topology_context_bits { + u8 log_matching_list_sz[0x4]; + u8 reserved_at_4[0xc]; + u8 append_next_index[0x10]; + + u8 sw_phase_cnt[0x10]; + u8 hw_phase_cnt[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_xrqc_bits { + u8 state[0x4]; + u8 rlkey[0x1]; + u8 reserved_at_5[0xf]; + u8 topology[0x4]; + u8 reserved_at_18[0x4]; + u8 offload[0x4]; + + u8 reserved_at_20[0x8]; + u8 user_index[0x18]; + + u8 reserved_at_40[0x8]; + u8 cqn[0x18]; + + u8 reserved_at_60[0xa0]; + + struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; + + u8 reserved_at_180[0x180]; + + struct mlx5_ifc_wq_bits wq; +}; + union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { struct mlx5_ifc_modify_field_select_bits modify_field_select; struct mlx5_ifc_resize_field_select_bits resize_field_select; @@ -3144,6 +3224,30 @@ struct mlx5_ifc_rst2init_qp_in_bits { u8 reserved_at_800[0x80]; }; +struct mlx5_ifc_query_xrq_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_xrqc_bits xrq_context; +}; + +struct mlx5_ifc_query_xrq_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 xrqn[0x18]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_query_xrc_srq_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -3547,7 +3651,27 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 out_of_sequence[0x20]; - u8 reserved_at_1e0[0x620]; + u8 reserved_at_1e0[0x20]; + + u8 duplicate_request[0x20]; + + u8 reserved_at_220[0x20]; + + u8 rnr_nak_retry_err[0x20]; + + u8 reserved_at_260[0x20]; + + u8 packet_seq_err[0x20]; + + u8 reserved_at_2a0[0x20]; + + u8 implied_nak_seq_err[0x20]; + + u8 reserved_at_2e0[0x20]; + + u8 local_ack_timeout_err[0x20]; + + u8 reserved_at_320[0x4e0]; }; struct mlx5_ifc_query_q_counter_in_bits { @@ -4998,6 +5122,28 @@ struct mlx5_ifc_detach_from_mcg_in_bits { u8 multicast_gid[16][0x8]; }; +struct mlx5_ifc_destroy_xrq_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_destroy_xrq_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 xrqn[0x18]; + + u8 reserved_at_60[0x20]; +}; + struct mlx5_ifc_destroy_xrc_srq_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5583,6 +5729,30 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_create_xrq_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x8]; + u8 xrqn[0x18]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_create_xrq_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_xrqc_bits xrq_context; +}; + struct mlx5_ifc_create_xrc_srq_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6124,6 +6294,29 @@ struct mlx5_ifc_attach_to_mcg_in_bits { u8 multicast_gid[16][0x8]; }; +struct mlx5_ifc_arm_xrq_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_arm_xrq_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x8]; + u8 xrqn[0x18]; + + u8 reserved_at_60[0x10]; + u8 lwm[0x10]; +}; + struct mlx5_ifc_arm_xrc_srq_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6161,7 +6354,8 @@ struct mlx5_ifc_arm_rq_out_bits { }; enum { - MLX5_ARM_RQ_IN_OP_MOD_SRQ_ = 0x1, + MLX5_ARM_RQ_IN_OP_MOD_SRQ = 0x1, + MLX5_ARM_RQ_IN_OP_MOD_XRQ = 0x2, }; struct mlx5_ifc_arm_rq_in_bits { @@ -6354,6 +6548,30 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits { u8 vxlan_udp_port[0x10]; }; +struct mlx5_ifc_set_rate_limit_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_set_rate_limit_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 rate_limit_index[0x10]; + + u8 reserved_at_60[0x20]; + + u8 rate_limit[0x20]; +}; + struct mlx5_ifc_access_register_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -6478,12 +6696,15 @@ struct mlx5_ifc_pude_reg_bits { }; struct mlx5_ifc_ptys_reg_bits { - u8 reserved_at_0[0x8]; + u8 an_disable_cap[0x1]; + u8 an_disable_admin[0x1]; + u8 reserved_at_2[0x6]; u8 local_port[0x8]; u8 reserved_at_10[0xd]; u8 proto_mask[0x3]; - u8 reserved_at_20[0x40]; + u8 an_status[0x4]; + u8 reserved_at_24[0x3c]; u8 eth_proto_capability[0x20]; @@ -7444,4 +7665,34 @@ struct mlx5_ifc_mcia_reg_bits { u8 dword_11[0x20]; }; +struct mlx5_ifc_dcbx_param_bits { + u8 dcbx_cee_cap[0x1]; + u8 dcbx_ieee_cap[0x1]; + u8 dcbx_standby_cap[0x1]; + u8 reserved_at_0[0x5]; + u8 port_number[0x8]; + u8 reserved_at_10[0xa]; + u8 max_application_table_size[6]; + u8 reserved_at_20[0x15]; + u8 version_oper[0x3]; + u8 reserved_at_38[5]; + u8 version_admin[0x3]; + u8 willing_admin[0x1]; + u8 reserved_at_41[0x3]; + u8 pfc_cap_oper[0x4]; + u8 reserved_at_48[0x4]; + u8 pfc_cap_admin[0x4]; + u8 reserved_at_50[0x4]; + u8 num_of_tc_oper[0x4]; + u8 reserved_at_58[0x4]; + u8 num_of_tc_admin[0x4]; + u8 remote_willing[0x1]; + u8 reserved_at_61[3]; + u8 remote_pfc_cap[4]; + u8 reserved_at_68[0x14]; + u8 remote_num_of_tc[0x4]; + u8 reserved_at_80[0x18]; + u8 error[0x8]; + u8 reserved_at_a0[0x160]; +}; #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 53ae95f6d5455ac1bbf50649fbd5158e0ef5f16c Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 30 May 2016 11:23:46 +0300 Subject: ARM: OMAP3: McBSP: New callback for McBSP2/3 ICLK idle configuration McBSP2/3 module's sidetone module operates using the module's ICLK clock. When the Sidetone is in use the interface clock of the module must not idle. The new callback expects to receive the *clk of the module's ick and not the id number of the McBSP. This will allow us more cleanups and going to simplify the ICLK handling. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- include/linux/platform_data/asoc-ti-mcbsp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/asoc-ti-mcbsp.h b/include/linux/platform_data/asoc-ti-mcbsp.h index 3c73c045f8da..73e5e832fa23 100644 --- a/include/linux/platform_data/asoc-ti-mcbsp.h +++ b/include/linux/platform_data/asoc-ti-mcbsp.h @@ -45,6 +45,7 @@ struct omap_mcbsp_platform_data { bool has_wakeup; /* Wakeup capability */ bool has_ccr; /* Transceiver has configuration control registers */ int (*enable_st_clock)(unsigned int, bool); + int (*force_ick_on)(struct clk *clk, bool force_on); }; /** -- cgit v1.2.3 From c26c84c92ba8907402faaab760dc0e4ecec89dd0 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 30 May 2016 11:23:47 +0300 Subject: ARM: OMAP3: pdata-quirks: Add support for McBSP2/3 sidetone handling McBSP2/3 module's sidetone module operates using the module's ICLK clock. When the Sidetone is in use the interface clock of the module must not idle. To prevent the iclk idling the driver expects to have pdata callback to call. With this patch the callback is going to be set up for DT boot also. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- include/linux/platform_data/asoc-ti-mcbsp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/platform_data/asoc-ti-mcbsp.h b/include/linux/platform_data/asoc-ti-mcbsp.h index 73e5e832fa23..5530971abf4d 100644 --- a/include/linux/platform_data/asoc-ti-mcbsp.h +++ b/include/linux/platform_data/asoc-ti-mcbsp.h @@ -56,4 +56,6 @@ struct omap_mcbsp_dev_attr { const char *sidetone; }; +void omap3_mcbsp_init_pdata_callback(struct omap_mcbsp_platform_data *pdata); + #endif -- cgit v1.2.3 From 3774bec74ea7cb30b8e80c87dd64396586d645c7 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 30 May 2016 11:23:50 +0300 Subject: ARM: OMAP2+: McBSP: Remove the old iclk allow/deny idle code The new pdata callback (force_ick_on) is now used by the driver and the old callback related code can be removed. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- include/linux/platform_data/asoc-ti-mcbsp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/asoc-ti-mcbsp.h b/include/linux/platform_data/asoc-ti-mcbsp.h index 5530971abf4d..e684543254f3 100644 --- a/include/linux/platform_data/asoc-ti-mcbsp.h +++ b/include/linux/platform_data/asoc-ti-mcbsp.h @@ -44,7 +44,6 @@ struct omap_mcbsp_platform_data { /* McBSP platform and instance specific features */ bool has_wakeup; /* Wakeup capability */ bool has_ccr; /* Transceiver has configuration control registers */ - int (*enable_st_clock)(unsigned int, bool); int (*force_ick_on)(struct clk *clk, bool force_on); }; -- cgit v1.2.3 From 3a3d1a4e32ab47323d7b8c8b7631a8d36a3098b2 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 8 Jun 2016 10:21:23 +0100 Subject: pwm: Add PWM capture support Supply a PWM capture callback op in order to pass back information obtained by running analysis on a PWM signal. This would normally (at least during testing) be called from the sysfs routines with a view to printing out PWM capture data which has been encoded into a string. Signed-off-by: Lee Jones [thierry.reding@gmail.com: make capture data unsigned int for symmetry] Signed-off-by: Thierry Reding --- include/linux/pwm.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 17018f3c066e..8402b5dd3e06 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -5,7 +5,9 @@ #include #include +struct pwm_capture; struct seq_file; + struct pwm_chip; /** @@ -153,6 +155,7 @@ static inline void pwm_get_args(const struct pwm_device *pwm, * @free: optional hook for freeing a PWM * @config: configure duty cycles and period length for this PWM * @set_polarity: configure the polarity of this PWM + * @capture: capture and report PWM signal * @enable: enable PWM output toggling * @disable: disable PWM output toggling * @apply: atomically apply a new PWM config. The state argument @@ -172,6 +175,8 @@ struct pwm_ops { int duty_ns, int period_ns); int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, enum pwm_polarity polarity); + int (*capture)(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_capture *result, unsigned long timeout); int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); int (*apply)(struct pwm_chip *chip, struct pwm_device *pwm, @@ -212,6 +217,16 @@ struct pwm_chip { bool can_sleep; }; +/** + * struct pwm_capture - PWM capture data + * @period: period of the PWM signal (in nanoseconds) + * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) + */ +struct pwm_capture { + unsigned int period; + unsigned int duty_cycle; +}; + #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ struct pwm_device *pwm_request(int pwm_id, const char *label); @@ -322,6 +337,8 @@ static inline void pwm_disable(struct pwm_device *pwm) /* PWM provider APIs */ +int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, + unsigned long timeout); int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); @@ -373,6 +390,13 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns, return -EINVAL; } +static inline int pwm_capture(struct pwm_device *pwm, + struct pwm_capture *result, + unsigned long timeout) +{ + return -EINVAL; +} + static inline int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity) { -- cgit v1.2.3 From e83068a5faafb8ca65d3b58bd1e1e3959ce1ddce Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 24 May 2016 21:16:51 -0400 Subject: dm mpath: add optional "queue_mode" feature Allow a user to specify an optional feature 'queue_mode ' where may be "bio", "rq" or "mq" -- which corresponds to bio-based, request_fn rq-based, and blk-mq rq-based respectively. If the queue_mode feature isn't specified the default for the "multipath" target is still "rq" but if dm_mod.use_blk_mq is set to Y it'll default to mode "mq". This new queue_mode feature introduces the ability for each multipath device to have its own queue_mode (whereas before this feature all multipath devices effectively had to have the same queue_mode). This commit also goes a long way to eliminate the awkward (ab)use of DM_TYPE_*, the associated filter_md_type() and other relatively fragile and difficult to maintain code. Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 0830c9e86f0d..2ce339212b6e 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -19,6 +19,14 @@ struct dm_table; struct mapped_device; struct bio_vec; +/* + * Type of table, mapped_device's mempool and request_queue + */ +#define DM_TYPE_NONE 0 +#define DM_TYPE_BIO_BASED 1 +#define DM_TYPE_REQUEST_BASED 2 +#define DM_TYPE_MQ_REQUEST_BASED 3 + typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; union map_info { @@ -443,6 +451,14 @@ int dm_table_add_target(struct dm_table *t, const char *type, */ void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb); +/* + * Target can use this to set the table's type. + * Can only ever be called from a target's ctr. + * Useful for "hybrid" target (supports both bio-based + * and request-based). + */ +void dm_table_set_type(struct dm_table *t, unsigned type); + /* * Finally call this to make the table ready for use. */ -- cgit v1.2.3 From 80955f9ee51760db64795b3778365ccb8c3a2729 Mon Sep 17 00:00:00 2001 From: Jayachandran C Date: Fri, 10 Jun 2016 21:55:09 +0200 Subject: PCI: Move ecam.h to linux/include/pci-ecam.h This header will be used from arch/arm64 for ACPI PCI implementation so it needs to be moved out of drivers/pci. Update users of the header file to use the new name. No functional changes. Signed-off-by: Jayachandran C Signed-off-by: Bjorn Helgaas Acked-by: Lorenzo Pieralisi --- include/linux/pci-ecam.h | 67 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 include/linux/pci-ecam.h (limited to 'include') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h new file mode 100644 index 000000000000..9878bebd45bb --- /dev/null +++ b/include/linux/pci-ecam.h @@ -0,0 +1,67 @@ +/* + * Copyright 2016 Broadcom + * + * 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 (the "GPL"). + * + * 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 version 2 (GPLv2) for more details. + * + * You should have received a copy of the GNU General Public License + * version 2 (GPLv2) along with this source code. + */ +#ifndef DRIVERS_PCI_ECAM_H +#define DRIVERS_PCI_ECAM_H + +#include +#include + +/* + * struct to hold pci ops and bus shift of the config window + * for a PCI controller. + */ +struct pci_config_window; +struct pci_ecam_ops { + unsigned int bus_shift; + struct pci_ops pci_ops; + int (*init)(struct device *, + struct pci_config_window *); +}; + +/* + * struct to hold the mappings of a config space window. This + * is expected to be used as sysdata for PCI controllers that + * use ECAM. + */ +struct pci_config_window { + struct resource res; + struct resource busr; + void *priv; + struct pci_ecam_ops *ops; + union { + void __iomem *win; /* 64-bit single mapping */ + void __iomem **winp; /* 32-bit per-bus mapping */ + }; +}; + +/* create and free pci_config_window */ +struct pci_config_window *pci_ecam_create(struct device *dev, + struct resource *cfgres, struct resource *busr, + struct pci_ecam_ops *ops); +void pci_ecam_free(struct pci_config_window *cfg); + +/* map_bus when ->sysdata is an instance of pci_config_window */ +void __iomem *pci_ecam_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); +/* default ECAM ops */ +extern struct pci_ecam_ops pci_generic_ecam_ops; + +#ifdef CONFIG_PCI_HOST_GENERIC +/* for DT-based PCI controllers that support ECAM */ +int pci_host_common_probe(struct platform_device *pdev, + struct pci_ecam_ops *ops); +#endif +#endif -- cgit v1.2.3 From 5c3d14f76fccd14f0882fe2a11e19534a11a1674 Mon Sep 17 00:00:00 2001 From: Jayachandran C Date: Fri, 10 Jun 2016 21:55:10 +0200 Subject: PCI: Add parent device field to ECAM struct pci_config_window Add a parent device field to struct pci_config_window. The parent is not saved now, but will be useful to save it in some cases. For ACPI on ARM64, it can be used to setup ACPI companion and domain. Since the parent dev is in struct pci_config_window now, we need not pass it to the init function as a separate argument. Signed-off-by: Jayachandran C Signed-off-by: Bjorn Helgaas Acked-by: Lorenzo Pieralisi --- include/linux/pci-ecam.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h index 9878bebd45bb..7adad206b1f4 100644 --- a/include/linux/pci-ecam.h +++ b/include/linux/pci-ecam.h @@ -27,8 +27,7 @@ struct pci_config_window; struct pci_ecam_ops { unsigned int bus_shift; struct pci_ops pci_ops; - int (*init)(struct device *, - struct pci_config_window *); + int (*init)(struct pci_config_window *); }; /* @@ -45,6 +44,7 @@ struct pci_config_window { void __iomem *win; /* 64-bit single mapping */ void __iomem **winp; /* 32-bit per-bus mapping */ }; + struct device *parent;/* ECAM res was from this dev */ }; /* create and free pci_config_window */ -- cgit v1.2.3 From 4d3f13845957a87729a324cce8509fad8826ef52 Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Fri, 10 Jun 2016 21:55:11 +0200 Subject: PCI: Add pci_unmap_iospace() to unmap I/O resources Add pci_unmap_iospace() to undo what pci_remap_iospace() did. This is needed to support hotplug removal of host bridges that use pci_remap_iospace(). [bhelgaas: changelog] Signed-off-by: Sinan Kaya Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas Acked-by: Lorenzo Pieralisi --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..12349deb688c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1167,6 +1167,7 @@ int pci_register_io_range(phys_addr_t addr, resource_size_t size); unsigned long pci_address_to_pio(phys_addr_t addr); phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); +void pci_unmap_iospace(struct resource *res); static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar) { -- cgit v1.2.3 From 935c760ec8101413248da23b6df45f0a7a643c62 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Fri, 10 Jun 2016 21:55:13 +0200 Subject: PCI/ACPI: Add generic MCFG table handling On ACPI systems that support memory-mapped config space access, i.e., ECAM, the PCI Firmware Specification says the OS can learn where the ECAM space is from either: - the static MCFG table (for non-hotpluggable bridges), or - the _CBA method (for hotpluggable bridges) The current MCFG table handling code cannot be easily generalized owing to x86-specific quirks, which makes it hard to reuse on other architectures. Implement generic MCFG handling from scratch, including: - Simple MCFG table parsing (via pci_mmcfg_late_init() as in current x86) - MCFG region lookup for a (domain, bus_start, bus_end) tuple [bhelgaas: changelog] Signed-off-by: Tomasz Nowicki Signed-off-by: Jayachandran C Signed-off-by: Bjorn Helgaas Reviewed-by: Lorenzo Pieralisi --- include/linux/pci-acpi.h | 2 ++ include/linux/pci.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 89ab0572dbc6..7d63a66e8ed4 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -24,6 +24,8 @@ static inline acpi_status pci_acpi_remove_pm_notifier(struct acpi_device *dev) } extern phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle); +extern phys_addr_t pci_mcfg_lookup(u16 domain, struct resource *bus_res); + static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { struct pci_bus *pbus = pdev->bus; diff --git a/include/linux/pci.h b/include/linux/pci.h index 12349deb688c..ce03d650279b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1723,7 +1723,7 @@ void pcibios_free_irq(struct pci_dev *dev); extern struct dev_pm_ops pcibios_pm_ops; #endif -#ifdef CONFIG_PCI_MMCONFIG +#if defined(CONFIG_PCI_MMCONFIG) || defined(CONFIG_ACPI_MCFG) void __init pci_mmcfg_early_init(void); void __init pci_mmcfg_late_init(void); #else -- cgit v1.2.3 From 9c7cb891ecfea3b88e4fa255afeec0da84ea6a86 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Fri, 10 Jun 2016 21:55:14 +0200 Subject: PCI: Refactor pci_bus_assign_domain_nr() for CONFIG_PCI_DOMAINS_GENERIC Instead of assigning bus->domain_nr inside pci_bus_assign_domain_nr(), return the domain and let the caller do the assignment. Rename pci_bus_assign_domain_nr() to pci_bus_find_domain_nr() to reflect this. No functional change intended. [bhelgaas: changelog] Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas Reviewed-by: Lorenzo Pieralisi --- include/linux/pci.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index ce03d650279b..48839e817ef2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1390,12 +1390,7 @@ static inline int pci_domain_nr(struct pci_bus *bus) { return bus->domain_nr; } -void pci_bus_assign_domain_nr(struct pci_bus *bus, struct device *parent); -#else -static inline void pci_bus_assign_domain_nr(struct pci_bus *bus, - struct device *parent) -{ -} +int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent); #endif /* some architectures require additional setup to direct VGA traffic */ -- cgit v1.2.3 From 2ab51ddeca2fc32a7040d8560415be3366fa9ba7 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Fri, 10 Jun 2016 15:36:26 -0500 Subject: ARM64: PCI: Add acpi_pci_bus_find_domain_nr() Extend pci_bus_find_domain_nr() so it can find the domain from either: - ACPI, via the new acpi_pci_bus_find_domain_nr() interface, or - DT, via of_pci_bus_find_domain_nr() Note that this is only used for CONFIG_PCI_DOMAINS_GENERIC=y, so it does not affect x86 or ia64. [bhelgaas: changelog] Signed-off-by: Tomasz Nowicki Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 48839e817ef2..0671e9a840cb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1390,6 +1390,12 @@ static inline int pci_domain_nr(struct pci_bus *bus) { return bus->domain_nr; } +#ifdef CONFIG_ACPI +int acpi_pci_bus_find_domain_nr(struct pci_bus *bus); +#else +static inline int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) +{ return 0; } +#endif int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent); #endif -- cgit v1.2.3 From f2a4d086ed4c588d32fe9b7aa67fead7280e7bf1 Mon Sep 17 00:00:00 2001 From: William Tu Date: Fri, 10 Jun 2016 11:49:33 -0700 Subject: openvswitch: Add packet truncation support. The patch adds a new OVS action, OVS_ACTION_ATTR_TRUNC, in order to truncate packets. A 'max_len' is added for setting up the maximum packet size, and a 'cutlen' field is to record the number of bytes to trim the packet when the packet is outputting to a port, or when the packet is sent to userspace. Signed-off-by: William Tu Cc: Pravin Shelar Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index bb0d515b7654..8274675ba9a3 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -580,6 +580,10 @@ enum ovs_userspace_attr { #define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1) +struct ovs_action_trunc { + uint32_t max_len; /* Max packet size in bytes. */ +}; + /** * struct ovs_action_push_mpls - %OVS_ACTION_ATTR_PUSH_MPLS action argument. * @mpls_lse: MPLS label stack entry to push. @@ -703,6 +707,7 @@ enum ovs_nat_attr { * enum ovs_action_attr - Action types. * * @OVS_ACTION_ATTR_OUTPUT: Output packet to port. + * @OVS_ACTION_ATTR_TRUNC: Output packet to port with truncated packet size. * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested * %OVS_USERSPACE_ATTR_* attributes. * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header. The @@ -756,6 +761,7 @@ enum ovs_action_attr { * The data must be zero for the unmasked * bits. */ OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */ + OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ -- cgit v1.2.3 From a70b506efe899dc8d650eafcc0b11fc9ee746627 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 10 Jun 2016 21:19:06 +0200 Subject: bpf: enforce recursion limit on redirects Respect the stack's xmit_recursion limit for calls into dev_queue_xmit(). Currently, they are not handeled by the limiter when attached to clsact's egress parent, for example, and a buggy program redirecting it to the same device again could run into stack overflow eventually. It would be good if we could notify an admin to give him a chance to react. We reuse xmit_recursion instead of having one private to eBPF, so that the stack's current recursion depth will be taken into account as well. Follow-up to commit 3896d655f4d4 ("bpf: introduce bpf_clone_redirect() helper") and 27b29f63058d ("bpf: add bpf_redirect() helper"). Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4f234b102892..94eef356a65f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2389,6 +2389,8 @@ void synchronize_net(void); int init_dummy_netdev(struct net_device *dev); DECLARE_PER_CPU(int, xmit_recursion); +#define XMIT_RECURSION_LIMIT 10 + static inline int dev_recursion_level(void) { return this_cpu_read(xmit_recursion); -- cgit v1.2.3 From 8387ff2577eb9ed245df9a39947f66976c6bcd02 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 10 Jun 2016 07:51:30 -0700 Subject: vfs: make the string hashes salt the hash We always mixed in the parent pointer into the dentry name hash, but we did it late at lookup time. It turns out that we can simplify that lookup-time action by salting the hash with the parent pointer early instead of late. A few other users of our string hashes also wanted to mix in their own pointers into the hash, and those are updated to use the same mechanism. Hash users that don't have any particular initial salt can just use the NULL pointer as a no-salt. Cc: Vegard Nossum Cc: George Spelvin Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/stringhash.h | 6 +++--- include/linux/sunrpc/svcauth.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h index 451771d9b9c0..eb7debb280c0 100644 --- a/include/linux/stringhash.h +++ b/include/linux/stringhash.h @@ -34,7 +34,7 @@ */ /* Hash courtesy of the R5 hash in reiserfs modulo sign bits */ -#define init_name_hash() 0 +#define init_name_hash(salt) (unsigned long)(salt) /* partial hash update function. Assume roughly 4 bits per character */ static inline unsigned long @@ -60,7 +60,7 @@ static inline unsigned long end_name_hash(unsigned long hash) * * If not set, this falls back to a wrapper around the preceding. */ -extern unsigned int __pure full_name_hash(const char *, unsigned int); +extern unsigned int __pure full_name_hash(const void *salt, const char *, unsigned int); /* * A hash_len is a u64 with the hash of a string in the low @@ -71,6 +71,6 @@ extern unsigned int __pure full_name_hash(const char *, unsigned int); #define hashlen_create(hash, len) ((u64)(len)<<32 | (u32)(hash)) /* Return the "hash_len" (hash and length) of a null-terminated string */ -extern u64 __pure hashlen_string(const char *name); +extern u64 __pure hashlen_string(const void *salt, const char *name); #endif /* __LINUX_STRINGHASH_H */ diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 91d5a5d6f52b..d03932055328 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -172,12 +172,12 @@ extern void unix_gid_cache_destroy(struct net *net); */ static inline unsigned long hash_str(char const *name, int bits) { - return hashlen_hash(hashlen_string(name)) >> (32 - bits); + return hashlen_hash(hashlen_string(NULL, name)) >> (32 - bits); } static inline unsigned long hash_mem(char const *buf, int length, int bits) { - return full_name_hash(buf, length) >> (32 - bits); + return full_name_hash(NULL, buf, length) >> (32 - bits); } #endif /* __KERNEL__ */ -- cgit v1.2.3 From 678ece30226ac05e95768d5f70db53a475569d37 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 8 Jun 2016 16:09:17 +0300 Subject: virtio_net: add _UAPI prefix to virtio_net header guards This gives better namespacing and prevents conflicts with no-uapi version of virtio_net header that will be introduced in the following patch. Signed-off-by: Mike Rapoport Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 0da0e3a98f17..fc353b518288 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -1,5 +1,5 @@ -#ifndef _LINUX_VIRTIO_NET_H -#define _LINUX_VIRTIO_NET_H +#ifndef _UAPI_LINUX_VIRTIO_NET_H +#define _UAPI_LINUX_VIRTIO_NET_H /* This header is BSD licensed so anyone can use the definitions to implement * compatible drivers/servers. * @@ -245,4 +245,4 @@ struct virtio_net_ctrl_mq { #define VIRTIO_NET_CTRL_GUEST_OFFLOADS 5 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET 0 -#endif /* _LINUX_VIRTIO_NET_H */ +#endif /* _UAPI_LINUX_VIRTIO_NET_H */ -- cgit v1.2.3 From fd2a0437dc33b6425cabf74cc7fc7fdba6d5903b Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 8 Jun 2016 16:09:18 +0300 Subject: virtio_net: introduce virtio_net_hdr_{from,to}_skb The code for conversion between virtio_net_hdr and skb GSO info is duplicated at several places. Let's put it to a common place to allow reuse. Signed-off-by: Mike Rapoport Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 101 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 include/linux/virtio_net.h (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h new file mode 100644 index 000000000000..1c912f85e041 --- /dev/null +++ b/include/linux/virtio_net.h @@ -0,0 +1,101 @@ +#ifndef _LINUX_VIRTIO_NET_H +#define _LINUX_VIRTIO_NET_H + +#include +#include + +static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, + const struct virtio_net_hdr *hdr, + bool little_endian) +{ + unsigned short gso_type = 0; + + if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + gso_type = SKB_GSO_TCPV4; + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + gso_type = SKB_GSO_TCPV6; + break; + case VIRTIO_NET_HDR_GSO_UDP: + gso_type = SKB_GSO_UDP; + break; + default: + return -EINVAL; + } + + if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) + gso_type |= SKB_GSO_TCP_ECN; + + if (hdr->gso_size == 0) + return -EINVAL; + } + + if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start); + u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); + + if (!skb_partial_csum_set(skb, start, off)) + return -EINVAL; + } + + if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { + u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + + skb_shinfo(skb)->gso_size = gso_size; + skb_shinfo(skb)->gso_type = gso_type; + + /* Header must be checked, and gso_segs computed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } + + return 0; +} + +static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, + struct virtio_net_hdr *hdr, + bool little_endian) +{ + memset(hdr, 0, sizeof(*hdr)); + + if (skb_is_gso(skb)) { + struct skb_shared_info *sinfo = skb_shinfo(skb); + + /* This is a hint as to how much should be linear. */ + hdr->hdr_len = __cpu_to_virtio16(little_endian, + skb_headlen(skb)); + hdr->gso_size = __cpu_to_virtio16(little_endian, + sinfo->gso_size); + if (sinfo->gso_type & SKB_GSO_TCPV4) + hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + else if (sinfo->gso_type & SKB_GSO_TCPV6) + hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; + else + return -EINVAL; + if (sinfo->gso_type & SKB_GSO_TCP_ECN) + hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; + } else + hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + if (skb_vlan_tag_present(skb)) + hdr->csum_start = __cpu_to_virtio16(little_endian, + skb_checksum_start_offset(skb) + VLAN_HLEN); + else + hdr->csum_start = __cpu_to_virtio16(little_endian, + skb_checksum_start_offset(skb)); + hdr->csum_offset = __cpu_to_virtio16(little_endian, + skb->csum_offset); + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; + } /* else everything is zero */ + + return 0; +} + +#endif /* _LINUX_VIRTIO_BYTEORDER */ -- cgit v1.2.3 From 6f094b9ec680209c5b7314feee983b2f4c910b1b Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Wed, 8 Jun 2016 21:16:44 -0700 Subject: tcp: add in_flight to tcp_skb_cb Add in_flight (bytes in flight when packet was sent) field to tx component of tcp_skb_cb and make it available to congestion modules' pkts_acked() function through the ack_sample function argument. Signed-off-by: Lawrence Brakmo Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 0bcc70f4e1fb..a79894b66726 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -767,6 +767,7 @@ struct tcp_skb_cb { union { struct { /* There is space for up to 20 bytes */ + __u32 in_flight;/* Bytes in flight when packet sent */ } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -859,6 +860,7 @@ union tcp_cc_info; struct ack_sample { u32 pkts_acked; s32 rtt_us; + u32 in_flight; }; struct tcp_congestion_ops { -- cgit v1.2.3 From 002245cc6407c8ff65b8024554080eb6de1a8e2c Mon Sep 17 00:00:00 2001 From: Zi Shen Lim Date: Wed, 8 Jun 2016 21:18:47 -0700 Subject: bpf: fix missing header inclusion Commit 0fc174dea545 ("ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs") introduced usage of ERR_PTR() in bpf_prog_get(), however did not include linux/err.h. Without this patch, when compiling arm64 BPF without CONFIG_BPF_SYSCALL: ... In file included from arch/arm64/net/bpf_jit_comp.c:21:0: include/linux/bpf.h: In function 'bpf_prog_get': include/linux/bpf.h:235:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration] return ERR_PTR(-EOPNOTSUPP); ^ include/linux/bpf.h:235:9: warning: return makes pointer from integer without a cast [-Wint-conversion] In file included from include/linux/rwsem.h:17:0, from include/linux/mm_types.h:10, from include/linux/sched.h:27, from arch/arm64/include/asm/compat.h:25, from arch/arm64/include/asm/stat.h:23, from include/linux/stat.h:5, from include/linux/compat.h:12, from include/linux/filter.h:10, from arch/arm64/net/bpf_jit_comp.c:22: include/linux/err.h: At top level: include/linux/err.h:23:35: error: conflicting types for 'ERR_PTR' static inline void * __must_check ERR_PTR(long error) ^ In file included from arch/arm64/net/bpf_jit_comp.c:21:0: include/linux/bpf.h:235:9: note: previous implicit declaration of 'ERR_PTR' was here return ERR_PTR(-EOPNOTSUPP); ^ ... Fixes: 0fc174dea545 ("ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs") Suggested-by: Daniel Borkmann Signed-off-by: Zi Shen Lim Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8ee27b8afe81..1bcae82c6cb1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -11,6 +11,7 @@ #include #include #include +#include struct bpf_map; -- cgit v1.2.3 From f20e6657a8758fe8d074889a6f1883674f01c7f2 Mon Sep 17 00:00:00 2001 From: Pramod Kumar Date: Fri, 10 Jun 2016 11:03:45 +0530 Subject: mdio: mux: Enhanced MDIO mux framework for integrated multiplexers An integrated multiplexer uses same address space for "muxed bus selection" and "generation of mdio transaction" hence its good to register parent bus from mux driver. Hence added a mechanism where mux driver could register a parent bus and pass it down to framework via mdio_mux_init api. Signed-off-by: Pramod Kumar Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio-mux.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mdio-mux.h b/include/linux/mdio-mux.h index a243dbba8659..61f5b21b31c7 100644 --- a/include/linux/mdio-mux.h +++ b/include/linux/mdio-mux.h @@ -10,11 +10,13 @@ #ifndef __LINUX_MDIO_MUX_H #define __LINUX_MDIO_MUX_H #include +#include int mdio_mux_init(struct device *dev, int (*switch_fn) (int cur, int desired, void *data), void **mux_handle, - void *data); + void *data, + struct mii_bus *mux_bus); void mdio_mux_uninit(void *mux_handle); -- cgit v1.2.3 From 45f50bed1d808794e514e9eed0e579a8756ce2ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Jun 2016 16:41:39 -0700 Subject: net_sched: remove generic throttled management __QDISC_STATE_THROTTLED bit manipulation is rather expensive for HTB and few others. I already removed it for sch_fq in commit f2600cf02b5b ("net: sched: avoid costly atomic operation in fq_dequeue()") and so far nobody complained. When one ore more packets are stuck in one or more throttled HTB class, a htb dequeue() performs two atomic operations to clear/set __QDISC_STATE_THROTTLED bit, while root qdisc lock is held. Removing this pair of atomic operations bring me a 8 % performance increase on 200 TCP_RR tests, in presence of throttled classes. This patch has no side effect, since nothing actually uses disc_is_throttled() anymore. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 4 ++-- include/net/sch_generic.h | 16 ---------------- 2 files changed, 2 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index fea53f4d92ca..7caa99b482c6 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -67,12 +67,12 @@ struct qdisc_watchdog { }; void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); -void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires, bool throttle); +void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires); static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { - qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires), true); + qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires)); } void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9f3581980c15..9a0d177884c6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -26,7 +26,6 @@ struct qdisc_rate_table { enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, - __QDISC_STATE_THROTTLED, }; struct qdisc_size_table { @@ -125,21 +124,6 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) #endif } -static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) -{ - return test_bit(__QDISC_STATE_THROTTLED, &qdisc->state) ? true : false; -} - -static inline void qdisc_throttled(struct Qdisc *qdisc) -{ - set_bit(__QDISC_STATE_THROTTLED, &qdisc->state); -} - -static inline void qdisc_unthrottled(struct Qdisc *qdisc) -{ - clear_bit(__QDISC_STATE_THROTTLED, &qdisc->state); -} - struct Qdisc_class_ops { /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); -- cgit v1.2.3 From 703b5faf22fbddf984a361e6555f3a03fdba63d9 Mon Sep 17 00:00:00 2001 From: George Spelvin Date: Fri, 10 Jun 2016 00:22:12 -0400 Subject: fs/dcache.c: Save one 32-bit multiply in dcache lookup Noe that we're mixing in the parent pointer earlier, we don't need to use hash_32() to mix its bits. Instead, we can just take the msbits of the hash value directly. For those applications which use the partial_name_hash(), move the multiply to end_name_hash. Signed-off-by: George Spelvin Signed-off-by: Linus Torvalds --- include/linux/stringhash.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h index eb7debb280c0..7c2d95170d01 100644 --- a/include/linux/stringhash.h +++ b/include/linux/stringhash.h @@ -3,6 +3,7 @@ #include /* For __pure */ #include /* For u32, u64 */ +#include /* * Routines for hashing strings of bytes to a 32-bit hash value. @@ -45,11 +46,12 @@ partial_name_hash(unsigned long c, unsigned long prevhash) /* * Finally: cut down the number of bits to a int value (and try to avoid - * losing bits) + * losing bits). This also has the property (wanted by the dcache) + * that the msbits make a good hash table index. */ static inline unsigned long end_name_hash(unsigned long hash) { - return (unsigned int)hash; + return __hash_32((unsigned int)hash); } /* -- cgit v1.2.3 From 29380905565655bb797bf670a173bddb8e641da6 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Fri, 3 Jun 2016 18:31:19 +0200 Subject: ARM: imx6: disable deeper idle states when FEC is active w/o HW workaround The i.MX6 Q/DL has an erratum (ERR006687) that prevents the FEC from waking the CPUs when they are in wait(unclocked) state. As the hardware workaround isn't applicable to all boards, disable the deeper idle state when the workaround isn't present and the FEC is in use. This allows to safely run a kernel with CPUidle enabled on all i.MX6 boards. Signed-off-by: Lucas Stach Acked-by: David S. Miller (for network changes) Signed-off-by: Shawn Guo --- include/soc/imx/cpuidle.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/soc/imx/cpuidle.h (limited to 'include') diff --git a/include/soc/imx/cpuidle.h b/include/soc/imx/cpuidle.h new file mode 100644 index 000000000000..986a4823bce1 --- /dev/null +++ b/include/soc/imx/cpuidle.h @@ -0,0 +1,25 @@ +/* + * Copyright 2016 Pengutronix, + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __SOC_IMX_CPUIDLE_H__ +#define __SOC_IMX_CPUIDLE_H__ + +#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SOC_IMX6Q) +void imx6q_cpuidle_fec_irqs_used(void); +void imx6q_cpuidle_fec_irqs_unused(void); +#else +void imx6q_cpuidle_fec_irqs_used(void) { } +void imx6q_cpuidle_fec_irqs_unused(void) { } +#endif + +#endif /* __SOC_IMX_CPUIDLE_H__ */ -- cgit v1.2.3 From 14e974a84e831bf9a44495c7256a6846e7f77630 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Jun 2016 23:20:43 +0200 Subject: nvme.h: add RTD3R, RTD3E and OAES fields These have been added in NVMe 1.2 and we'll need at least oaes for the NVMe target driver. Reviewed-by: Sagi Grimberg Reviewed-by: Jay Freyensee Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7d51b2904cb7..ff5ebc378cc3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,7 +107,10 @@ struct nvme_id_ctrl { __u8 mdts; __le16 cntlid; __le32 ver; - __u8 rsvd84[172]; + __le32 rtd3r; + __le32 rtd3e; + __le32 oaes; + __u8 rsvd96[160]; __le16 oacs; __u8 acl; __u8 aerl; -- cgit v1.2.3 From 725b358836ed038d7d8eafef86330b3a0b3f9c2f Mon Sep 17 00:00:00 2001 From: Armen Baloyan Date: Mon, 6 Jun 2016 23:20:44 +0200 Subject: nvme.h: Add get_log_page command strucure Add get_log_page command structure and a corresponding entry in nvme_command union Signed-off-by: Armen Baloyan Reviewed-by: Jay Freyensee Reviewed--by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index ff5ebc378cc3..9925b85246d8 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -519,6 +519,24 @@ struct nvme_format_cmd { __u32 rsvd11[5]; }; +struct nvme_get_log_page_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __u8 lid; + __u8 rsvd10; + __le16 numdl; + __le16 numdu; + __u16 rsvd11; + __le32 lpol; + __le32 lpou; + __u32 rsvd14[2]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -532,6 +550,7 @@ struct nvme_command { struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; struct nvme_abort_cmd abort; + struct nvme_get_log_page_command get_log_page; }; }; -- cgit v1.2.3 From 69cd27e2511616f9b402d1bad4c49f91aa7411a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Jun 2016 23:20:45 +0200 Subject: nvme.h: add NVM command set SQE/CQE size defines Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9925b85246d8..9807d98ca93a 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -50,6 +50,13 @@ enum { #define NVME_CMB_CQS(cmbsz) ((cmbsz) & 0x2) #define NVME_CMB_SQS(cmbsz) ((cmbsz) & 0x1) +/* + * Submission and Completion Queue Entry Sizes for the NVM command set. + * (In bytes and specified as a power of two (2^n)). + */ +#define NVME_NVM_IOSQES 6 +#define NVME_NVM_IOCQES 4 + enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, @@ -61,8 +68,8 @@ enum { NVME_CC_SHN_NORMAL = 1 << 14, NVME_CC_SHN_ABRUPT = 2 << 14, NVME_CC_SHN_MASK = 3 << 14, - NVME_CC_IOSQES = 6 << 16, - NVME_CC_IOCQES = 4 << 20, + NVME_CC_IOSQES = NVME_NVM_IOSQES << 16, + NVME_CC_IOCQES = NVME_NVM_IOCQES << 20, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, -- cgit v1.2.3 From 79f370eac63796a8933b210bca02f006ba32d22e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Jun 2016 23:20:46 +0200 Subject: nvme.h: add AER constants Reviewed-by: Jay Freyensee Reviewed-by: Sagi Grimberg Reviewed-by: Ming Lin Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9807d98ca93a..a9b8c7bcaf85 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -284,6 +284,12 @@ struct nvme_reservation_status { } regctl_ds[]; }; +enum nvme_async_event_type { + NVME_AER_TYPE_ERROR = 0, + NVME_AER_TYPE_SMART = 1, + NVME_AER_TYPE_NOTICE = 2, +}; + /* I/O commands */ enum nvme_opcode { -- cgit v1.2.3 From 3972be23bd2d2bcfaa44595a260a371cd9218872 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 6 Jun 2016 23:20:47 +0200 Subject: nvme.h: add constants for PSDT and FUSE values Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a9b8c7bcaf85..2b82f05fe4ec 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -306,6 +306,29 @@ enum nvme_opcode { nvme_cmd_resv_release = 0x15, }; +/* + * Lowest two bits of our flags field (FUSE field in the spec): + * + * @NVME_CMD_FUSE_FIRST: Fused Operation, first command + * @NVME_CMD_FUSE_SECOND: Fused Operation, second command + * + * Highest two bits in our flags field (PSDT field in the spec): + * + * @NVME_CMD_PSDT_SGL_METABUF: Use SGLS for this transfer, + * If used, MPTR contains addr of single physical buffer (byte aligned). + * @NVME_CMD_PSDT_SGL_METASEG: Use SGLS for this transfer, + * If used, MPTR contains an address of an SGL segment containing + * exactly 1 SGL descriptor (qword aligned). + */ +enum { + NVME_CMD_FUSE_FIRST = (1 << 0), + NVME_CMD_FUSE_SECOND = (1 << 1), + + NVME_CMD_SGL_METABUF = (1 << 6), + NVME_CMD_SGL_METASEG = (1 << 7), + NVME_CMD_SGL_ALL = NVME_CMD_SGL_METABUF | NVME_CMD_SGL_METASEG, +}; + struct nvme_common_command { __u8 opcode; __u8 flags; -- cgit v1.2.3 From 7a5abb4b48570c3552e33ff4c72ae1e8dac3ba15 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 6 Jun 2016 23:20:49 +0200 Subject: nvme: factor out a add nvme_is_write helper Centralize the check if a given NVMe command reads or writes data. Reviewed-by: Sagi Grimberg Reviewed-by: Jay Freyensee Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 2b82f05fe4ec..dc815cc6718d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -590,6 +590,11 @@ struct nvme_command { }; }; +static inline bool nvme_is_write(struct nvme_command *cmd) +{ + return cmd->common.opcode & 1; +} + enum { NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, -- cgit v1.2.3 From 99860208bc62d8ebd5c57495b84856506fe075bc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 11 Jun 2016 12:46:04 +0200 Subject: sched: remove NET_XMIT_POLICED sch_atm returns this when TC_ACT_SHOT classification occurs. But all other schedulers that use tc_classify (htb, hfsc, drr, fq_codel ...) return NET_XMIT_SUCCESS | __BYPASS in this case so just do that in atm. BATMAN uses it as an intermediate return value to signal forwarding vs. buffering, but it did not return POLICED to callers outside of BATMAN. Reviewed-by: Sven Eckelmann Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 94eef356a65f..d101e4d904ba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -90,7 +90,6 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_XMIT_SUCCESS 0x00 #define NET_XMIT_DROP 0x01 /* skb dropped */ #define NET_XMIT_CN 0x02 /* congestion notification */ -#define NET_XMIT_POLICED 0x03 /* skb is shot by police */ #define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */ /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It -- 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 +++ 1 file changed, 3 insertions(+) (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; -- 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 ++++ 1 file changed, 4 insertions(+) (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); -- 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 --- include/linux/irqchip/arm-gic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') 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 --- include/linux/irqchip/arm-gic.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') 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 --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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 --- include/linux/irqchip/arm-gic-v3.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') 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 7dd968163f7c12bcb2132792bf873133b397a2d2 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Wed, 25 May 2016 09:32:20 +0200 Subject: bitmap: bitmap_equal memcmp optimization The bitmap_equal function has optimized code for small bitmaps with less than BITS_PER_LONG bits. For larger bitmaps the out-of-line function __bitmap_equal is called. For a constant number of bits divisible by BITS_PER_LONG the memcmp function can be used. For s390 gcc knows how to optimize this function, memcmp calls with up to 256 bytes / 2048 bits are translated into a single instruction. Reviewed-by: David Hildenbrand Signed-off-by: Martin Schwidefsky --- include/linux/bitmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index e9b0b9ab07e5..27bfc0b631a9 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -267,6 +267,10 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); +#ifdef CONFIG_S390 + else if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + return !memcmp(src1, src2, nbits / 8); +#endif else return __bitmap_equal(src1, src2, nbits); } -- cgit v1.2.3 From 32fb2fc5c357fb99616bbe100dbcb27bc7f5d045 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 7 Jun 2016 12:20:51 +0200 Subject: vmlinux.lds.h: allow arch specific handling of ro_after_init data section commit c74ba8b3480d ("arch: Introduce post-init read-only memory") introduced the __ro_after_init attribute which allows to add variables to the ro_after_init data section. This new section was added to rodata, even though it contains writable data. This in turn causes problems on architectures which mark the page table entries read-only that point to rodata very early. This patch allows architectures to implement an own handling of the .data..ro_after_init section. Usually that would be: - mark the rodata section read-only very early - mark the ro_after_init section read-only within mark_rodata_ro Signed-off-by: Heiko Carstens Reviewed-by: Kees Cook Signed-off-by: Martin Schwidefsky --- include/asm-generic/vmlinux.lds.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab94b553..c4436d072d37 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -249,6 +249,14 @@ *(.data..init_task) \ VMLINUX_SYMBOL(__end_init_task) = .; +/* + * Allow architectures to handle ro_after_init data on their + * own by defining an empty RO_AFTER_INIT_DATA. + */ +#ifndef RO_AFTER_INIT_DATA +#define RO_AFTER_INIT_DATA *(.data..ro_after_init) +#endif + /* * Read only Data */ @@ -257,7 +265,7 @@ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start_rodata) = .; \ *(.rodata) *(.rodata.*) \ - *(.data..ro_after_init) /* Read only after init */ \ + RO_AFTER_INIT_DATA /* Read only after init */ \ *(__vermagic) /* Kernel version magic */ \ . = ALIGN(8); \ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \ -- cgit v1.2.3 From 9661e783d830699a65f7d42e4b4a76e6923089eb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Jun 2016 20:48:33 +0300 Subject: PCI / PM: Enforce type casting for pci_power_t When casting variables of type pci_power_t, a static analysis tool complains: include/linux/pci.h:119:37: warning: cast from restricted pci_power_t Enforce type casting to make the static analyzer happy. Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..8d748345b158 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -116,7 +116,7 @@ extern const char *pci_power_names[]; static inline const char *pci_power_name(pci_power_t state) { - return pci_power_names[1 + (int) state]; + return pci_power_names[1 + (__force int) state]; } #define PCI_PM_D2_DELAY 200 -- cgit v1.2.3 From a4f2d87c63571d4cd9467d369f2fbf2362646043 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 13 Jun 2016 14:17:10 +0100 Subject: ALSA: compress: Add function to indicate the stream has gone bad Currently, the avail IOCTL doesn't pass any error status, which means typically on error it simply shows no data available. This can lead to situations where user-space is waiting indefinitely for data that will never come as the DSP has suffered an unrecoverable error. Add snd_compr_stop_error which end drivers can call to indicate the stream has suffered an unrecoverable error and stop it. The avail and poll IOCTLs are then updated to report if the stream is in an error state to user-space. Allowing the error to propagate out. Processing of the actual snd_compr_stop needs to be deferred to a worker thread as the end driver may detect the errors during an existing operation callback. Signed-off-by: Charles Keepax Acked-by: Vinod Koul Signed-off-by: Mark Brown --- include/sound/compress_driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index c0abcdc11470..cee8c00f3d3e 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -68,6 +68,7 @@ struct snd_compr_runtime { * @ops: pointer to DSP callbacks * @runtime: pointer to runtime structure * @device: device pointer + * @error_work: delayed work used when closing the stream due to an error * @direction: stream direction, playback/recording * @metadata_set: metadata set flag, true when set * @next_track: has userspace signal next track transition, true when set @@ -78,6 +79,7 @@ struct snd_compr_stream { struct snd_compr_ops *ops; struct snd_compr_runtime *runtime; struct snd_compr *device; + struct delayed_work error_work; enum snd_compr_direction direction; bool metadata_set; bool next_track; @@ -187,4 +189,7 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) wake_up(&stream->runtime->sleep); } +int snd_compr_stop_error(struct snd_compr_stream *stream, + snd_pcm_state_t state); + #endif -- cgit v1.2.3 From 42d42a5b0cd263757f8e519debbc744fdaefdaf7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 23 May 2016 09:24:55 -0400 Subject: SUNRPC: Small optimisation of client receive Do not queue the client receive work if we're still processing. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprtsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 0ece4ba06f06..bef3fb0abb8f 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -80,6 +80,7 @@ struct sock_xprt { #define TCP_RPC_REPLY (1UL << 6) #define XPRT_SOCK_CONNECTING 1U +#define XPRT_SOCK_DATA_READY (2) #endif /* __KERNEL__ */ -- cgit v1.2.3 From 40a5f1b19bacb2de7a051be952dee85e38c9e5f5 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 May 2016 10:39:50 -0400 Subject: SUNRPC: RPC transport queue must be low latency rpciod can easily get congested due to the long list of queued rpc_tasks. Having the receive queue wait in turn for those tasks to complete can therefore be a bottleneck. Address the problem by separating the workqueues into: - rpciod: manages rpc_tasks - xprtiod: manages transport related work. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 05a1809c44d9..ef780b3b5e31 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -247,6 +247,7 @@ void rpc_show_tasks(struct net *); int rpc_init_mempool(void); void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; +extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); static inline int rpc_wait_for_completion_task(struct rpc_task *task) -- cgit v1.2.3 From f1dc237c60a5fdecc83062a28a702193f881cb19 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 27 May 2016 12:59:33 -0400 Subject: SUNRPC: Reduce latency when send queue is congested Use the low latency transport workqueue to process the task that is next in line on the xprt->sending queue. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ef780b3b5e31..817af0b4385e 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -230,6 +230,10 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *, struct rpc_task *); void rpc_wake_up(struct rpc_wait_queue *); struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *); +struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq, + struct rpc_wait_queue *, + bool (*)(struct rpc_task *, void *), + void *); struct rpc_task *rpc_wake_up_first(struct rpc_wait_queue *, bool (*)(struct rpc_task *, void *), void *); -- cgit v1.2.3 From 9d26d3a8f1b0c442339a235f9508bdad8af91043 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 2 Jun 2016 11:17:12 +0300 Subject: PCI: Put PCIe ports into D3 during suspend Currently the Linux PCI core does not touch power state of PCI bridges and PCIe ports when system suspend is entered. Leaving them in D0 consumes power unnecessarily and may prevent the CPU from entering deeper C-states. With recent PCIe hardware we can power down the ports to save power given that we take into account few restrictions: - The PCIe port hardware is recent enough, starting from 2015. - Devices connected to PCIe ports are effectively in D3cold once the port is transitioned to D3 (the config space is not accessible anymore and the link may be powered down). - Devices behind the PCIe port need to be allowed to transition to D3cold and back. There is a way both drivers and userspace can forbid this. - If the device behind the PCIe port is capable of waking the system it needs to be able to do so from D3cold. This patch adds a new flag to struct pci_device called 'bridge_d3'. This flag is set and cleared by the PCI core whenever there is a change in power management state of any of the devices behind the PCIe port. When system later on is suspended we only need to check this flag and if it is true transition the port to D3 otherwise we leave it in D0. Also provide override mechanism via command line parameter "pcie_port_pm=[off|force]" that can be used to disable or enable the feature regardless of the BIOS manufacturing date. Tested-by: Lukas Wunner Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8d748345b158..8597b423cb63 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -294,6 +294,7 @@ struct pci_dev { unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* D1 and D2 are forbidden */ unsigned int no_d3cold:1; /* D3cold is forbidden */ + unsigned int bridge_d3:1; /* Allow D3 for bridge */ unsigned int d3cold_allowed:1; /* D3cold is allowed by user */ unsigned int mmio_always_on:1; /* disallow turning off io/mem decoding during bar sizing */ @@ -1083,6 +1084,8 @@ int pci_back_from_sleep(struct pci_dev *dev); bool pci_dev_run_wake(struct pci_dev *dev); bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); +void pci_d3cold_enable(struct pci_dev *dev); +void pci_d3cold_disable(struct pci_dev *dev); static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) -- cgit v1.2.3 From 0f614d834bccd3537881c5d0933803b407ce3283 Mon Sep 17 00:00:00 2001 From: Jean-Michel Hautbois Date: Sun, 31 Jan 2016 16:33:00 +0100 Subject: i2c: Add generic support passing secondary devices addresses Some I2C devices have multiple addresses assigned, for example each address corresponding to a different internal register map page of the device. So far drivers which need support for this have handled this with a driver specific and non-generic implementation, e.g. passing the additional address via platform data. This patch provides a new helper function called i2c_new_secondary_device() which is intended to provide a generic way to get the secondary address as well as instantiate a struct i2c_client for the secondary address. The function expects a pointer to the primary i2c_client, a name for the secondary address and an optional default address. The name is used as a handle to specify which secondary address to get. The default address is used as a fallback in case no secondary address was explicitly specified. In case no secondary address and no default address were specified the function returns NULL. For now the function only supports look-up of the secondary address from devicetree, but it can be extended in the future to for example support board files and/or ACPI. Signed-off-by: Jean-Michel Hautbois Acked-by: Rob Herring Acked-by: Mika Westerberg Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 96a25ae14494..6df7bad8c26c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -349,6 +349,11 @@ extern int i2c_probe_func_quick_read(struct i2c_adapter *, unsigned short addr); extern struct i2c_client * i2c_new_dummy(struct i2c_adapter *adap, u16 address); +extern struct i2c_client * +i2c_new_secondary_device(struct i2c_client *client, + const char *name, + u16 default_addr); + extern void i2c_unregister_device(struct i2c_client *); #endif /* I2C */ -- cgit v1.2.3 From a5ca66c419410b4a26ab47b120d5424bd1d33700 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Tue, 14 Jun 2016 00:26:14 +0200 Subject: drbd: Introduce new disk config option rs-discard-granularity As long as the value is 0 the feature is disabled. With setting it to a positive value, DRBD limits and aligns its resync requests to the rs-discard-granularity setting. If the sync source detects all zeros in such a block, the resync target discards the range on disk. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_genl.h | 6 +++--- include/linux/drbd_limits.h | 6 ++++++ 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index 2d0e5ad5de9d..ab649d8e9ed2 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -123,14 +123,14 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, __u32_field_def(13, DRBD_GENLA_F_MANDATORY, c_fill_target, DRBD_C_FILL_TARGET_DEF) __u32_field_def(14, DRBD_GENLA_F_MANDATORY, c_max_rate, DRBD_C_MAX_RATE_DEF) __u32_field_def(15, DRBD_GENLA_F_MANDATORY, c_min_rate, DRBD_C_MIN_RATE_DEF) + __u32_field_def(20, DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF) + __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) + __u32_field_def(25, 0 /* OPTIONAL */, rs_discard_granularity, DRBD_RS_DISCARD_GRANULARITY_DEF) __flg_field_def(16, DRBD_GENLA_F_MANDATORY, disk_barrier, DRBD_DISK_BARRIER_DEF) __flg_field_def(17, DRBD_GENLA_F_MANDATORY, disk_flushes, DRBD_DISK_FLUSHES_DEF) __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) - __u32_field_def(20, DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF) - __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) - /* 9: __u32_field_def(22, DRBD_GENLA_F_MANDATORY, unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) */ __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) ) diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 8ac8c5d9a3ad..2e4aad8d8ae8 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -230,4 +230,10 @@ #define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX #define DRBD_SOCKET_CHECK_TIMEO_DEF 0 #define DRBD_SOCKET_CHECK_TIMEO_SCALE '1' + +#define DRBD_RS_DISCARD_GRANULARITY_MIN 0 +#define DRBD_RS_DISCARD_GRANULARITY_MAX (1<<20) /* 1MiByte */ +#define DRBD_RS_DISCARD_GRANULARITY_DEF 0 /* disabled by default */ +#define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ + #endif -- cgit v1.2.3 From dd4f699da674010c58d7a2534215b4ca1ff13b13 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 14 Jun 2016 00:26:20 +0200 Subject: drbd: when receiving P_TRIM, zero-out partial unaligned chunks We can avoid spurious data divergence caused by partially-ignored discards on certain backends with discard_zeroes_data=0, if we translate partial unaligned discard requests into explicit zero-out. The relevant use case is LVM/DM thin. If on different nodes, DRBD is backed by devices with differing discard characteristics, discards may lead to data divergence (old data or garbage left over on one backend, zeroes due to unmapped areas on the other backend). Online verify would now potentially report tons of spurious differences. While probably harmless for most use cases (fstrim on a file system), DRBD cannot have that, it would violate our promise to upper layers that our data instances on the nodes are identical. To be correct and play safe (make sure data is identical on both copies), we would have to disable discard support, if our local backend (on a Primary) does not support "discard_zeroes_data=true". We'd also have to translate discards to explicit zero-out on the receiving (typically: Secondary) side, unless the receiving side supports "discard_zeroes_data=true". Which both would allocate those blocks, instead of unmapping them, in contrast with expectations. LVM/DM thin does set discard_zeroes_data=0, because it silently ignores discards to partial chunks. We can work around this by checking the alignment first. For unaligned (wrt. alignment and granularity) or too small discards, we zero-out the initial (and/or) trailing unaligned partial chunks, but discard all the aligned full chunks. At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1". Arguably it should behave this way internally, by default, and we'll try to make that happen. But our workaround is still valid for already deployed setups, and for other devices that may behave this way. Setting discard-zeroes-if-aligned=yes will allow DRBD to use discards, and to announce discard_zeroes_data=true, even on backends that announce discard_zeroes_data=false. Setting discard-zeroes-if-aligned=no will cause DRBD to always fall-back to zero-out on the receiving side, and to not even announce discard capabilities on the Primary, if the respective backend announces discard_zeroes_data=false. We used to ignore the discard_zeroes_data setting completely. To not break established and expected behaviour, and suddenly cause fstrim on thin-provisioned LVs to run out-of-space, instead of freeing up space, the default value is "yes". Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_genl.h | 1 + include/linux/drbd_limits.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index ab649d8e9ed2..c934d3a96b5e 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -132,6 +132,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) + __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED) ) GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 2e4aad8d8ae8..a351c40087cd 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -210,6 +210,12 @@ #define DRBD_MD_FLUSHES_DEF 1 #define DRBD_TCP_CORK_DEF 1 #define DRBD_AL_UPDATES_DEF 1 +/* We used to ignore the discard_zeroes_data setting. + * To not change established (and expected) behaviour, + * by default assume that, for discard_zeroes_data=0, + * we can make that an effective discard_zeroes_data=1, + * if we only explicitly zero-out unaligned partial chunks. */ +#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1 #define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 #define DRBD_ALWAYS_ASBP_DEF 0 -- cgit v1.2.3 From 505675f96cf0f169647a18c3dda1f373eca957b1 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 14 Jun 2016 00:26:23 +0200 Subject: drbd: allow larger max_discard_sectors Make sure we have at least 67 (> AL_UPDATES_PER_TRANSACTION) al-extents available, and allow up to half of that to be discarded in one bio. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_limits.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index a351c40087cd..ddac68422a96 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -126,8 +126,7 @@ #define DRBD_RESYNC_RATE_DEF 250 #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - /* less than 7 would hit performance unnecessarily. */ -#define DRBD_AL_EXTENTS_MIN 7 +#define DRBD_AL_EXTENTS_MIN 67 /* we use u16 as "slot number", (u16)~0 is "FREE". * If you use >= 292 kB on-disk ring buffer, * this is the maximum you can use: */ -- cgit v1.2.3 From 7e5fec31685a5c69b81e9005eaed44318880d881 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 14 Jun 2016 00:26:35 +0200 Subject: drbd: code cleanups without semantic changes This contains various cosmetic fixes ranging from simple typos to const-ifying, and using booleans properly. Original commit messages from Fabian's patch set: drbd: debugfs: constify drbd_version_fops drbd: use seq_put instead of seq_print where possible drbd: include linux/uaccess.h instead of asm/uaccess.h drbd: use const char * const for drbd strings drbd: kerneldoc warning fix in w_e_end_data_req() drbd: use unsigned for one bit fields drbd: use bool for peer is_ states drbd: fix typo drbd: use | for bitmask combination drbd: use true/false for bool drbd: fix drbd_bm_init() comments drbd: introduce peer state union drbd: fix maybe_pull_ahead() locking comments drbd: use bool for growing drbd: remove redundant declarations drbd: replace if/BUG by BUG_ON Signed-off-by: Fabian Frederick Signed-off-by: Roland Kammerer Signed-off-by: Jens Axboe --- include/linux/drbd.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index d6b3c9943a2c..2b26156365ec 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -370,6 +370,14 @@ enum drbd_notification_type { NOTIFY_FLAGS = NOTIFY_CONTINUES, }; +enum drbd_peer_state { + P_INCONSISTENT = 3, + P_OUTDATED = 4, + P_DOWN = 5, + P_PRIMARY = 6, + P_FENCING = 7, +}; + #define UUID_JUST_CREATED ((__u64)4) enum write_ordering_e { -- cgit v1.2.3 From 1b57e66384e2d21150301e68078526fac5680a16 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 14 Jun 2016 00:26:39 +0200 Subject: drbd: correctly handle failed crypto_alloc_hash crypto_alloc_hash returns an ERR_PTR(), not NULL. Also reset peer_integrity_tfm to NULL, to not call crypto_free_hash() on an errno in the cleanup path. Reported-by: Insu Yun Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 2b26156365ec..002611c85318 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,7 +51,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.6" +#define REL_VERSION "8.4.7" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 -- 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 --- include/linux/nmi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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; -- cgit v1.2.3 From 965475acca2cbcc1d748a8b6a05f8c7cf57d075a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Jun 2016 10:29:44 +0100 Subject: KEYS: Strip trailing spaces Strip some trailing spaces. Signed-off-by: David Howells --- include/keys/rxrpc-type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/keys/rxrpc-type.h b/include/keys/rxrpc-type.h index fc4875433817..5de0673f333b 100644 --- a/include/keys/rxrpc-type.h +++ b/include/keys/rxrpc-type.h @@ -51,7 +51,7 @@ struct krb5_principal { struct krb5_tagged_data { /* for tag value, see /usr/include/krb5/krb5.h * - KRB5_AUTHDATA_* for auth data - * - + * - */ s32 tag; u32 data_len; -- 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 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 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__ */ -- 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 ++++++++++++----- 1 file changed, 12 insertions(+), 5 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 -- 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 --- include/asm-generic/barrier.h | 2 +- include/linux/spinlock_up.h | 10 +++++++--- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include') 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 2f275de5d1ed7269913ef9b4c64a13952c0a38e8 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 27 May 2016 12:57:02 -0700 Subject: seccomp: Add a seccomp_data parameter secure_computing() Currently, if arch code wants to supply seccomp_data directly to seccomp (which is generally much faster than having seccomp do it using the syscall_get_xyz() API), it has to use the two-phase seccomp hooks. Add it to the easy hooks, too. Cc: linux-arch@vger.kernel.org Signed-off-by: Andy Lutomirski Signed-off-by: Kees Cook --- include/linux/seccomp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 2296e6b2f690..9eaa7b34d6da 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -28,11 +28,11 @@ struct seccomp { }; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -extern int __secure_computing(void); -static inline int secure_computing(void) +extern int __secure_computing(const struct seccomp_data *sd); +static inline int secure_computing(const struct seccomp_data *sd) { if (unlikely(test_thread_flag(TIF_SECCOMP))) - return __secure_computing(); + return __secure_computing(sd); return 0; } @@ -61,7 +61,7 @@ struct seccomp { }; struct seccomp_filter { }; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER -static inline int secure_computing(void) { return 0; } +static inline int secure_computing(struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif -- cgit v1.2.3 From 8112c4f140fa03f9ee68aad2cc79afa7df5418d3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 1 Jun 2016 16:02:17 -0700 Subject: seccomp: remove 2-phase API Since nothing is using the 2-phase API, and it adds more complexity than benefit, remove it. Signed-off-by: Kees Cook Cc: Andy Lutomirski --- include/linux/seccomp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 9eaa7b34d6da..ecc296c137cd 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -35,12 +35,6 @@ static inline int secure_computing(const struct seccomp_data *sd) return __secure_computing(sd); return 0; } - -#define SECCOMP_PHASE1_OK 0 -#define SECCOMP_PHASE1_SKIP 1 - -extern u32 seccomp_phase1(struct seccomp_data *sd); -int seccomp_phase2(u32 phase1_result); #else extern void secure_computing_strict(int this_syscall); #endif -- cgit v1.2.3 From dc19ed1571dd3882b35e12fdaf50acbcc9b69714 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 14 Jun 2016 14:48:50 -0300 Subject: Update my main e-mails at the Kernel tree For the third time in three years, I'm changing my e-mail at Samsung. That's bad, as it may stop communications with me for a while. So, this time, I'll also the mchehab@kernel.org e-mail, as it remains stable since ever. Cc: stable@vger.kernel.org Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-mc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h index 98a938aabdfb..7a8d6037a4bb 100644 --- a/include/media/v4l2-mc.h +++ b/include/media/v4l2-mc.h @@ -1,7 +1,7 @@ /* * v4l2-mc.h - Media Controller V4L2 types and prototypes * - * Copyright (C) 2016 Mauro Carvalho Chehab + * Copyright (C) 2016 Mauro Carvalho Chehab * Copyright (C) 2006-2010 Nokia Corporation * Copyright (c) 2016 Intel Corporation. * -- 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 ++++ 1 file changed, 4 insertions(+) (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); -- cgit v1.2.3 From ca5f2b4c4fb7bb7397317ee2ead83485aa295a3e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 14 Jun 2016 16:23:22 +0200 Subject: PM / sleep: Make pm_prepare_console() return void Nothing is using its return value so change it to return void. No functionality change. Signed-off-by: Borislav Petkov Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8b6ec7ef0854..7693e39b14fe 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -18,12 +18,11 @@ static inline void pm_set_vt_switch(int do_switch) #endif #ifdef CONFIG_VT_CONSOLE_SLEEP -extern int pm_prepare_console(void); +extern void pm_prepare_console(void); extern void pm_restore_console(void); #else -static inline int pm_prepare_console(void) +static inline void pm_prepare_console(void) { - return 0; } static inline void pm_restore_console(void) -- cgit v1.2.3 From d7c51b47ac11e66f547b55640405c1c474642d72 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 26 Apr 2016 10:35:29 +0200 Subject: gpio: userspace ABI for reading/writing GPIO lines This adds a userspace ABI for reading and writing GPIO lines. The mechanism returns an anonymous file handle to a request to read/write n offsets from a gpiochip. This file handle in turn accepts two ioctl()s: one that reads and one that writes values to the selected lines. - Handles can be requested as input/output, active low, open drain, open source, however when you issue a request for n lines with GPIO_GET_LINEHANDLE_IOCTL, they must all have the same flags, i.e. all inputs or all outputs, all open drain etc. If a granular control of the flags for each line is desired, they need to be requested individually, not in a batch. - The GPIOHANDLE_GET_LINE_VALUES_IOCTL read ioctl() can be issued also to output lines to verify that the hardware is in the expected state. - It reads and writes up to GPIOHANDLES_MAX lines at once, utilizing the .set_multiple() call in the driver if possible, making the call efficient if several lines can be written with a single register update. The limitation of GPIOHANDLES_MAX to 64 lines is done under the assumption that we may expect hardware that can issue a transaction updating 64 bits at an instant but unlikely anything larger than that. ChangeLog v2->v3: - Use gpiod_get_value_cansleep() so we support also slowpath GPIO drivers. - Fix up the UAPI docs kerneldoc. - Allocate the anonymous fd last, so that the release function don't get called until that point of something fails. After this point, skip the errorpath. ChangeLog v1->v2: - Handle ioctl_compat() properly based on a similar patch to the other ioctl() handling code. - Use _IOWR() as we pass pointers both in and out of the ioctl() - Use kmalloc() and kfree() for the linehandled, do not try to be fancy with devm_* it doesn't work the way I thought. - Fix const-correctness on the linehandle name field. Acked-by: Michael Welling Signed-off-by: Linus Walleij --- include/uapi/linux/gpio.h | 61 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 58 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index d0a3cac72250..21905531dcf4 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -1,7 +1,7 @@ /* * - userspace ABI for the GPIO character devices * - * Copyright (C) 2015 Linus Walleij + * Copyright (C) 2016 Linus Walleij * * 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 @@ -26,8 +26,8 @@ struct gpiochip_info { __u32 lines; }; -/* Line is in use by the kernel */ -#define GPIOLINE_FLAG_KERNEL (1UL << 0) +/* Informational flags */ +#define GPIOLINE_FLAG_KERNEL (1UL << 0) /* Line used by the kernel */ #define GPIOLINE_FLAG_IS_OUT (1UL << 1) #define GPIOLINE_FLAG_ACTIVE_LOW (1UL << 2) #define GPIOLINE_FLAG_OPEN_DRAIN (1UL << 3) @@ -52,7 +52,62 @@ struct gpioline_info { char consumer[32]; }; +/* Maximum number of requested handles */ +#define GPIOHANDLES_MAX 64 + +/* Request flags */ +#define GPIOHANDLE_REQUEST_INPUT (1UL << 0) +#define GPIOHANDLE_REQUEST_OUTPUT (1UL << 1) +#define GPIOHANDLE_REQUEST_ACTIVE_LOW (1UL << 2) +#define GPIOHANDLE_REQUEST_OPEN_DRAIN (1UL << 3) +#define GPIOHANDLE_REQUEST_OPEN_SOURCE (1UL << 4) + +/** + * struct gpiohandle_request - Information about a GPIO handle request + * @lineoffsets: an array desired lines, specified by offset index for the + * associated GPIO device + * @flags: desired flags for the desired GPIO lines, such as + * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * together. Note that even if multiple lines are requested, the same flags + * must be applicable to all of them, if you want lines with individual + * flags set, request them one by one. It is possible to select + * a batch of input or output lines, but they must all have the same + * characteristics, i.e. all inputs or all outputs, all active low etc + * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested + * line, this specifies the default output value, should be 0 (low) or + * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) + * @consumer_label: a desired consumer label for the selected GPIO line(s) + * such as "my-bitbanged-relay" + * @lines: number of lines requested in this request, i.e. the number of + * valid fields in the above arrays, set to 1 to request a single line + * @fd: if successful this field will contain a valid anonymous file handle + * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value + * means error + */ +struct gpiohandle_request { + __u32 lineoffsets[GPIOHANDLES_MAX]; + __u32 flags; + __u8 default_values[GPIOHANDLES_MAX]; + char consumer_label[32]; + __u32 lines; + int fd; +}; + #define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info) #define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info) +#define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request) + +/** + * struct gpiohandle_data - Information of values on a GPIO handle + * @values: when getting the state of lines this contains the current + * state of a line, when setting the state of lines these should contain + * the desired target state + */ +struct gpiohandle_data { + __u8 values[GPIOHANDLES_MAX]; +}; + +#define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data) +#define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data) #endif /* _UAPI_GPIO_H_ */ -- cgit v1.2.3 From 61f922db72216b00386581c851db9c9095961522 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 2 Jun 2016 11:30:15 +0200 Subject: gpio: userspace ABI for reading GPIO line events This adds an ABI for listening to events on GPIO lines. The mechanism returns an anonymous file handle to a request to listen to a specific offset on a specific gpiochip. To fetch the stream of events from the file handle, userspace simply reads an event. - Events can be requested with the same flags as ordinary handles, i.e. open drain or open source. An ioctl() call GPIO_GET_LINEEVENT_IOCTL is issued indicating the desired line. - Events can be requested for falling edge events, rising edge events, or both. - All events are timestamped using the kernel real time nanosecond timestamp (the same as is used by IIO). - The supplied consumer label will appear in "lsgpio" listings of the lines, and in /proc/interrupts as the mechanism will request an interrupt from the gpio chip. - Events are not supported on gpiochips that do not serve interrupts (no legal .to_irq() call). The event interrupt is threaded to avoid any realtime problems. - It is possible to also directly read the current value of the registered GPIO line by issuing the same GPIOHANDLE_GET_LINE_VALUES_IOCTL as used by the line handles. Setting the value is not supported: we do not listen to events on output lines. This ABI is strongly influenced by Industrial I/O and surpasses the old sysfs ABI by providing proper precision timestamps, making it possible to set flags like open drain, and put consumer names on the GPIO lines. Signed-off-by: Linus Walleij --- include/uapi/linux/gpio.h | 54 ++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 49 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 21905531dcf4..333d3544c964 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -55,7 +55,7 @@ struct gpioline_info { /* Maximum number of requested handles */ #define GPIOHANDLES_MAX 64 -/* Request flags */ +/* Linerequest flags */ #define GPIOHANDLE_REQUEST_INPUT (1UL << 0) #define GPIOHANDLE_REQUEST_OUTPUT (1UL << 1) #define GPIOHANDLE_REQUEST_ACTIVE_LOW (1UL << 2) @@ -93,10 +93,6 @@ struct gpiohandle_request { int fd; }; -#define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info) -#define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info) -#define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request) - /** * struct gpiohandle_data - Information of values on a GPIO handle * @values: when getting the state of lines this contains the current @@ -110,4 +106,52 @@ struct gpiohandle_data { #define GPIOHANDLE_GET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x08, struct gpiohandle_data) #define GPIOHANDLE_SET_LINE_VALUES_IOCTL _IOWR(0xB4, 0x09, struct gpiohandle_data) +/* Eventrequest flags */ +#define GPIOEVENT_REQUEST_RISING_EDGE (1UL << 0) +#define GPIOEVENT_REQUEST_FALLING_EDGE (1UL << 1) +#define GPIOEVENT_REQUEST_BOTH_EDGES ((1UL << 0) | (1UL << 1)) + +/** + * struct gpioevent_request - Information about a GPIO event request + * @lineoffset: the desired line to subscribe to events from, specified by + * offset index for the associated GPIO device + * @handleflags: desired handle flags for the desired GPIO line, such as + * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN + * @eventflags: desired flags for the desired GPIO event line, such as + * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE + * @consumer_label: a desired consumer label for the selected GPIO line(s) + * such as "my-listener" + * @fd: if successful this field will contain a valid anonymous file handle + * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value + * means error + */ +struct gpioevent_request { + __u32 lineoffset; + __u32 handleflags; + __u32 eventflags; + char consumer_label[32]; + int fd; +}; + +/** + * GPIO event types + */ +#define GPIOEVENT_EVENT_RISING_EDGE 0x01 +#define GPIOEVENT_EVENT_FALLING_EDGE 0x02 + +/** + * struct gpioevent_data - The actual event being pushed to userspace + * @timestamp: best estimate of time of event occurrence, in nanoseconds + * @id: event identifier + */ +struct gpioevent_data { + __u64 timestamp; + __u32 id; +}; + +#define GPIO_GET_CHIPINFO_IOCTL _IOR(0xB4, 0x01, struct gpiochip_info) +#define GPIO_GET_LINEINFO_IOCTL _IOWR(0xB4, 0x02, struct gpioline_info) +#define GPIO_GET_LINEHANDLE_IOCTL _IOWR(0xB4, 0x03, struct gpiohandle_request) +#define GPIO_GET_LINEEVENT_IOCTL _IOWR(0xB4, 0x04, struct gpioevent_request) + #endif /* _UAPI_GPIO_H_ */ -- cgit v1.2.3 From 355912852115cd8aa4ad02c25182ae615ce925fb Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Tue, 14 Jun 2016 07:34:13 +0200 Subject: crypto: drbg - use CTR AES instead of ECB AES The CTR DRBG derives its random data from the CTR that is encrypted with AES. This patch now changes the CTR DRBG implementation such that the CTR AES mode is employed. This allows the use of steamlined CTR AES implementation such as ctr-aes-aesni. Unfortunately there are the following subtile changes we need to apply when using the CTR AES mode: - the CTR mode increments the counter after the cipher operation, but the CTR DRBG requires the increment before the cipher op. Hence, the crypto_inc is applied to the counter (drbg->V) once it is recalculated. - the CTR mode wants to encrypt data, but the CTR DRBG is interested in the encrypted counter only. The full CTR mode is the XOR of the encrypted counter with the plaintext data. To access the encrypted counter, the patch uses a NULL data vector as plaintext to be "encrypted". Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- include/crypto/drbg.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index d961b2b16f55..b2fe15d1ceba 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -115,6 +116,14 @@ struct drbg_state { /* some memory the DRBG can use for its operation */ unsigned char *scratchpad; void *priv_data; /* Cipher handle */ + + struct crypto_skcipher *ctr_handle; /* CTR mode cipher handle */ + struct skcipher_request *ctr_req; /* CTR mode request handle */ + __u8 *ctr_null_value_buf; /* CTR mode unaligned buffer */ + __u8 *ctr_null_value; /* CTR mode aligned zero buf */ + struct completion ctr_completion; /* CTR mode async handler */ + int ctr_async_err; /* CTR mode async error */ + bool seeded; /* DRBG fully seeded? */ bool pr; /* Prediction resistance enabled? */ struct work_struct seed_work; /* asynchronous seeding support */ -- cgit v1.2.3 From 3cfc3b97211238ffc1a7885ebe62f899180fe043 Mon Sep 17 00:00:00 2001 From: Stephan Mueller Date: Tue, 14 Jun 2016 07:35:13 +0200 Subject: crypto: drbg - use aligned buffers Hardware cipher implementation may require aligned buffers. All buffers that potentially are processed with a cipher are now aligned. Signed-off-by: Stephan Mueller Signed-off-by: Herbert Xu --- include/crypto/drbg.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h index b2fe15d1ceba..61580b19f9f6 100644 --- a/include/crypto/drbg.h +++ b/include/crypto/drbg.h @@ -108,13 +108,16 @@ struct drbg_test_data { struct drbg_state { struct mutex drbg_mutex; /* lock around DRBG */ unsigned char *V; /* internal state 10.1.1.1 1a) */ + unsigned char *Vbuf; /* hash: static value 10.1.1.1 1b) hmac / ctr: key */ unsigned char *C; + unsigned char *Cbuf; /* Number of RNG requests since last reseed -- 10.1.1.1 1c) */ size_t reseed_ctr; size_t reseed_threshold; /* some memory the DRBG can use for its operation */ unsigned char *scratchpad; + unsigned char *scratchpadbuf; void *priv_data; /* Cipher handle */ struct crypto_skcipher *ctr_handle; /* CTR mode cipher handle */ -- cgit v1.2.3 From 5a7de97309f5af4458b1a25a2a529a1a893c5269 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Tue, 14 Jun 2016 16:14:58 +0300 Subject: crypto: rsa - return raw integers for the ASN.1 parser Return the raw key with no other processing so that the caller can copy it or MPI parse it, etc. The scope is to have only one ANS.1 parser for all RSA implementations. Update the RSA software implementation so that it does the MPI conversion on top. Signed-off-by: Tudor Ambarus Signed-off-by: Herbert Xu --- include/crypto/internal/rsa.h | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h index c7585bdecbc2..d6c042a2ee52 100644 --- a/include/crypto/internal/rsa.h +++ b/include/crypto/internal/rsa.h @@ -12,12 +12,24 @@ */ #ifndef _RSA_HELPER_ #define _RSA_HELPER_ -#include +#include +/** + * rsa_key - RSA key structure + * @n : RSA modulus raw byte stream + * @e : RSA public exponent raw byte stream + * @d : RSA private exponent raw byte stream + * @n_sz : length in bytes of RSA modulus n + * @e_sz : length in bytes of RSA public exponent + * @d_sz : length in bytes of RSA private exponent + */ struct rsa_key { - MPI n; - MPI e; - MPI d; + const u8 *n; + const u8 *e; + const u8 *d; + size_t n_sz; + size_t e_sz; + size_t d_sz; }; int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key, @@ -26,7 +38,5 @@ int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key, int rsa_parse_priv_key(struct rsa_key *rsa_key, const void *key, unsigned int key_len); -void rsa_free_key(struct rsa_key *rsa_key); - extern struct crypto_template rsa_pkcs1pad_tmpl; #endif -- cgit v1.2.3 From cd2a9e62c8a3c5cae7691982667d79a0edc65283 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 13 Jun 2016 13:44:17 -0700 Subject: net: l3mdev: Remove const from flowi6 arg to get_rt6_dst Allow drivers to pass flow arg to functions where the arg is not const and allow the driver to make updates as needed (eg., setting oif). Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 34f33eb96a5e..f8a416ec674c 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -38,7 +38,7 @@ struct l3mdev_ops { /* IPv6 ops */ struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, - const struct flowi6 *fl6); + struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -139,7 +139,7 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4); -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6); +struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) @@ -225,7 +225,7 @@ static inline int l3mdev_get_saddr(struct net *net, int ifindex, } static inline -struct dst_entry *l3mdev_get_rt6_dst(struct net *net, const struct flowi6 *fl6) +struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6) { return NULL; } -- cgit v1.2.3 From 9ff74384600aeecba34ebdacbbde0627489ff601 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 13 Jun 2016 13:44:19 -0700 Subject: net: vrf: Handle ipv6 multicast and link-local addresses IPv6 multicast and link-local addresses require special handling by the VRF driver: 1. Rather than using the VRF device index and full FIB lookups, packets to/from these addresses should use direct FIB lookups based on the VRF device table. 2. fail sends/receives on a VRF device to/from a multicast address (e.g, make ping6 ff02::1% fail) 3. move the setting of the flow oif to the first dst lookup and revert the change in icmpv6_echo_reply made in ca254490c8dfd ("net: Add VRF support to IPv6 stack"). Linklocal/mcast addresses require use of the skb->dev. With this change connections into and out of a VRF enslaved device work for multicast and link-local addresses work (icmp, tcp, and udp) e.g., 1. packets into VM with VRF config: ping6 -c3 fe80::e0:f9ff:fe1c:b974%br1 ping6 -c3 ff02::1%br1 ssh -6 fe80::e0:f9ff:fe1c:b974%br1 2. packets going out a VRF enslaved device: ping6 -c3 fe80::18f8:83ff:fe4b:7a2e%eth1 ping6 -c3 ff02::1%eth1 ssh -6 root@fe80::18f8:83ff:fe4b:7a2e%eth1 Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_route.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 54c779416eec..f55bf3d294aa 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -76,6 +76,8 @@ static inline struct dst_entry *ip6_route_output(struct net *net, struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); +struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, + int ifindex, struct flowi6 *fl6, int flags); int ip6_route_init(void); void ip6_route_cleanup(void); -- cgit v1.2.3 From b2313077ed0db35ee186905d8076a737248edd24 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 13 Jun 2016 13:46:28 -0700 Subject: net_sched: make tcf_hash_check() boolean Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index db218a12efb5..fb82b5b5d9e7 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -155,8 +155,8 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct tc_action *a); int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index); u32 tcf_hash_new_index(struct tc_action_net *tn); -int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, - int bind); +bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, + int bind); int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action *a, int size, int bind, bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); -- cgit v1.2.3 From 163f1e93e995048b894c5fc86a6034d16beed740 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 23 Mar 2016 11:22:57 -0300 Subject: [media] media-devnode: fix namespace mess Along all media controller code, "mdev" is used to represent a pointer to struct media_device, and "devnode" for a pointer to struct media_devnode. However, inside media-devnode.[ch], "mdev" is used to represent a pointer to struct media_devnode. This is very confusing and may lead to development errors. So, let's change all occurrences at media-devnode.[ch] to also use "devnode" for such pointers. This patch doesn't make any functional changes. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- include/media/media-devnode.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h index fe42f08e72bd..e1d5af077adb 100644 --- a/include/media/media-devnode.h +++ b/include/media/media-devnode.h @@ -94,7 +94,7 @@ struct media_devnode { unsigned long flags; /* Use bitops to access flags */ /* callbacks */ - void (*release)(struct media_devnode *mdev); + void (*release)(struct media_devnode *devnode); }; /* dev to media_devnode */ @@ -103,7 +103,7 @@ struct media_devnode { /** * media_devnode_register - register a media device node * - * @mdev: media device node structure we want to register + * @devnode: media device node structure we want to register * @owner: should be filled with %THIS_MODULE * * The registration code assigns minor numbers and registers the new device node @@ -116,12 +116,12 @@ struct media_devnode { * the media_devnode structure is *not* called, so the caller is responsible for * freeing any data. */ -int __must_check media_devnode_register(struct media_devnode *mdev, +int __must_check media_devnode_register(struct media_devnode *devnode, struct module *owner); /** * media_devnode_unregister - unregister a media device node - * @mdev: the device node to unregister + * @devnode: the device node to unregister * * This unregisters the passed device. Future open calls will be met with * errors. @@ -129,7 +129,7 @@ int __must_check media_devnode_register(struct media_devnode *mdev, * This function can safely be called if the device node has never been * registered or has already been unregistered. */ -void media_devnode_unregister(struct media_devnode *mdev); +void media_devnode_unregister(struct media_devnode *devnode); /** * media_devnode_data - returns a pointer to the &media_devnode @@ -145,11 +145,11 @@ static inline struct media_devnode *media_devnode_data(struct file *filp) * media_devnode_is_registered - returns true if &media_devnode is registered; * false otherwise. * - * @mdev: pointer to struct &media_devnode. + * @devnode: pointer to struct &media_devnode. */ -static inline int media_devnode_is_registered(struct media_devnode *mdev) +static inline int media_devnode_is_registered(struct media_devnode *devnode) { - return test_bit(MEDIA_FLAG_REGISTERED, &mdev->flags); + return test_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); } #endif /* _MEDIA_DEVNODE_H */ -- cgit v1.2.3 From 2e0ab8ca83c122f275b21ea917d52fee506910bf Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 13 Jun 2016 23:54:31 +0300 Subject: ptr_ring: array based FIFO for pointers A simple array based FIFO of pointers. Intended for net stack which commonly has a single consumer/producer. Signed-off-by: Michael S. Tsirkin Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 264 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 264 insertions(+) create mode 100644 include/linux/ptr_ring.h (limited to 'include') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h new file mode 100644 index 000000000000..633406f9af8e --- /dev/null +++ b/include/linux/ptr_ring.h @@ -0,0 +1,264 @@ +/* + * Definitions for the 'struct ptr_ring' datastructure. + * + * Author: + * Michael S. Tsirkin + * + * Copyright (C) 2016 Red Hat, Inc. + * + * 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 is a limited-size FIFO maintaining pointers in FIFO order, with + * one CPU producing entries and another consuming entries from a FIFO. + * + * This implementation tries to minimize cache-contention when there is a + * single producer and a single consumer CPU. + */ + +#ifndef _LINUX_PTR_RING_H +#define _LINUX_PTR_RING_H 1 + +#ifdef __KERNEL__ +#include +#include +#include +#include +#include +#include +#include +#endif + +struct ptr_ring { + int producer ____cacheline_aligned_in_smp; + spinlock_t producer_lock; + int consumer ____cacheline_aligned_in_smp; + spinlock_t consumer_lock; + /* Shared consumer/producer data */ + /* Read-only by both the producer and the consumer */ + int size ____cacheline_aligned_in_smp; /* max entries in queue */ + void **queue; +}; + +/* Note: callers invoking this in a loop must use a compiler barrier, + * for example cpu_relax(). + * Callers don't need to take producer lock - if they don't + * the next call to __ptr_ring_produce may fail. + */ +static inline bool __ptr_ring_full(struct ptr_ring *r) +{ + return r->queue[r->producer]; +} + +static inline bool ptr_ring_full(struct ptr_ring *r) +{ + barrier(); + return __ptr_ring_full(r); +} + +/* Note: callers invoking this in a loop must use a compiler barrier, + * for example cpu_relax(). + */ +static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) +{ + if (__ptr_ring_full(r)) + return -ENOSPC; + + r->queue[r->producer++] = ptr; + if (unlikely(r->producer >= r->size)) + r->producer = 0; + return 0; +} + +static inline int ptr_ring_produce(struct ptr_ring *r, void *ptr) +{ + int ret; + + spin_lock(&r->producer_lock); + ret = __ptr_ring_produce(r, ptr); + spin_unlock(&r->producer_lock); + + return ret; +} + +static inline int ptr_ring_produce_irq(struct ptr_ring *r, void *ptr) +{ + int ret; + + spin_lock_irq(&r->producer_lock); + ret = __ptr_ring_produce(r, ptr); + spin_unlock_irq(&r->producer_lock); + + return ret; +} + +static inline int ptr_ring_produce_any(struct ptr_ring *r, void *ptr) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&r->producer_lock, flags); + ret = __ptr_ring_produce(r, ptr); + spin_unlock_irqrestore(&r->producer_lock, flags); + + return ret; +} + +static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) +{ + int ret; + + spin_lock_bh(&r->producer_lock); + ret = __ptr_ring_produce(r, ptr); + spin_unlock_bh(&r->producer_lock); + + return ret; +} + +/* Note: callers invoking this in a loop must use a compiler barrier, + * for example cpu_relax(). Callers must take consumer_lock + * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. + * There's no need for a lock if pointer is merely tested - see e.g. + * ptr_ring_empty. + */ +static inline void *__ptr_ring_peek(struct ptr_ring *r) +{ + return r->queue[r->consumer]; +} + +static inline bool ptr_ring_empty(struct ptr_ring *r) +{ + barrier(); + return !__ptr_ring_peek(r); +} + +/* Must only be called after __ptr_ring_peek returned !NULL */ +static inline void __ptr_ring_discard_one(struct ptr_ring *r) +{ + r->queue[r->consumer++] = NULL; + if (unlikely(r->consumer >= r->size)) + r->consumer = 0; +} + +static inline void *__ptr_ring_consume(struct ptr_ring *r) +{ + void *ptr; + + ptr = __ptr_ring_peek(r); + if (ptr) + __ptr_ring_discard_one(r); + + return ptr; +} + +static inline void *ptr_ring_consume(struct ptr_ring *r) +{ + void *ptr; + + spin_lock(&r->consumer_lock); + ptr = __ptr_ring_consume(r); + spin_unlock(&r->consumer_lock); + + return ptr; +} + +static inline void *ptr_ring_consume_irq(struct ptr_ring *r) +{ + void *ptr; + + spin_lock_irq(&r->consumer_lock); + ptr = __ptr_ring_consume(r); + spin_unlock_irq(&r->consumer_lock); + + return ptr; +} + +static inline void *ptr_ring_consume_any(struct ptr_ring *r) +{ + unsigned long flags; + void *ptr; + + spin_lock_irqsave(&r->consumer_lock, flags); + ptr = __ptr_ring_consume(r); + spin_unlock_irqrestore(&r->consumer_lock, flags); + + return ptr; +} + +static inline void *ptr_ring_consume_bh(struct ptr_ring *r) +{ + void *ptr; + + spin_lock_bh(&r->consumer_lock); + ptr = __ptr_ring_consume(r); + spin_unlock_bh(&r->consumer_lock); + + return ptr; +} + +/* Cast to structure type and call a function without discarding from FIFO. + * Function must return a value. + * Callers must take consumer_lock. + */ +#define __PTR_RING_PEEK_CALL(r, f) ((f)(__ptr_ring_peek(r))) + +#define PTR_RING_PEEK_CALL(r, f) ({ \ + typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ + \ + spin_lock(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ + spin_unlock(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v; \ +}) + +#define PTR_RING_PEEK_CALL_IRQ(r, f) ({ \ + typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ + \ + spin_lock_irq(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ + spin_unlock_irq(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v; \ +}) + +#define PTR_RING_PEEK_CALL_BH(r, f) ({ \ + typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ + \ + spin_lock_bh(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ + spin_unlock_bh(&(r)->consumer_lock); \ + __PTR_RING_PEEK_CALL_v; \ +}) + +#define PTR_RING_PEEK_CALL_ANY(r, f) ({ \ + typeof((f)(NULL)) __PTR_RING_PEEK_CALL_v; \ + unsigned long __PTR_RING_PEEK_CALL_f;\ + \ + spin_lock_irqsave(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \ + __PTR_RING_PEEK_CALL_v = __PTR_RING_PEEK_CALL(r, f); \ + spin_unlock_irqrestore(&(r)->consumer_lock, __PTR_RING_PEEK_CALL_f); \ + __PTR_RING_PEEK_CALL_v; \ +}) + +static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) +{ + r->queue = kzalloc(ALIGN(size * sizeof *(r->queue), SMP_CACHE_BYTES), + gfp); + if (!r->queue) + return -ENOMEM; + + r->size = size; + r->producer = r->consumer = 0; + spin_lock_init(&r->producer_lock); + spin_lock_init(&r->consumer_lock); + + return 0; +} + +static inline void ptr_ring_cleanup(struct ptr_ring *r) +{ + kfree(r->queue); +} + +#endif /* _LINUX_PTR_RING_H */ -- cgit v1.2.3 From a087ce704b802becbb4b0f2a20f2cb3f6911802e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 27 Apr 2016 19:28:26 -0300 Subject: [media] media-device: dynamically allocate struct media_devnode struct media_devnode is currently embedded at struct media_device. While this works fine during normal usage, it leads to a race condition during devnode unregister. the problem is that drivers assume that, after calling media_device_unregister(), the struct that contains media_device can be freed. This is not true, as it can't be freed until userspace closes all opened /dev/media devnodes. In other words, if the media devnode is still open, and media_device gets freed, any call to an ioctl will make the core to try to access struct media_device, with will cause an use-after-free and even GPF. Fix this by dynamically allocating the struct media_devnode and only freeing it when it is safe. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 5 +---- include/media/media-devnode.h | 13 ++++++++++++- 2 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index a9b33c47310d..f743ae2210ee 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -347,7 +347,7 @@ struct media_entity_notify { struct media_device { /* dev->driver_data points to this struct. */ struct device *dev; - struct media_devnode devnode; + struct media_devnode *devnode; char model[32]; char driver_name[32]; @@ -393,9 +393,6 @@ struct usb_device; #define MEDIA_DEV_NOTIFY_PRE_LINK_CH 0 #define MEDIA_DEV_NOTIFY_POST_LINK_CH 1 -/* media_devnode to media_device */ -#define to_media_device(node) container_of(node, struct media_device, devnode) - /** * media_entity_enum_init - Initialise an entity enumeration * diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h index e1d5af077adb..5bb3b0e86d73 100644 --- a/include/media/media-devnode.h +++ b/include/media/media-devnode.h @@ -33,6 +33,8 @@ #include #include +struct media_device; + /* * Flag to mark the media_devnode struct as registered. Drivers must not touch * this flag directly, it will be set and cleared by media_devnode_register and @@ -81,6 +83,8 @@ struct media_file_operations { * before registering the node. */ struct media_devnode { + struct media_device *media_dev; + /* device ops */ const struct media_file_operations *fops; @@ -103,6 +107,7 @@ struct media_devnode { /** * media_devnode_register - register a media device node * + * @media_dev: struct media_device we want to register a device node * @devnode: media device node structure we want to register * @owner: should be filled with %THIS_MODULE * @@ -116,7 +121,8 @@ struct media_devnode { * the media_devnode structure is *not* called, so the caller is responsible for * freeing any data. */ -int __must_check media_devnode_register(struct media_devnode *devnode, +int __must_check media_devnode_register(struct media_device *mdev, + struct media_devnode *devnode, struct module *owner); /** @@ -146,9 +152,14 @@ static inline struct media_devnode *media_devnode_data(struct file *filp) * false otherwise. * * @devnode: pointer to struct &media_devnode. + * + * Note: If mdev is NULL, it also returns false. */ static inline int media_devnode_is_registered(struct media_devnode *devnode) { + if (!devnode) + return false; + return test_bit(MEDIA_FLAG_REGISTERED, &devnode->flags); } -- cgit v1.2.3 From ad69f35d1dc0a79f86627ca56e01f86512602a49 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 13 Jun 2016 23:54:41 +0300 Subject: skb_array: array based FIFO for skbs A simple array based FIFO of pointers. Intended for net stack so uses skbs for type safety. Implemented as a set of wrappers around ptr_ring. Signed-off-by: Michael S. Tsirkin Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/skb_array.h | 144 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 144 insertions(+) create mode 100644 include/linux/skb_array.h (limited to 'include') diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h new file mode 100644 index 000000000000..c4c090223333 --- /dev/null +++ b/include/linux/skb_array.h @@ -0,0 +1,144 @@ +/* + * Definitions for the 'struct skb_array' datastructure. + * + * Author: + * Michael S. Tsirkin + * + * Copyright (C) 2016 Red Hat, Inc. + * + * 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. + * + * Limited-size FIFO of skbs. Can be used more or less whenever + * sk_buff_head can be used, except you need to know the queue size in + * advance. + * Implemented as a type-safe wrapper around ptr_ring. + */ + +#ifndef _LINUX_SKB_ARRAY_H +#define _LINUX_SKB_ARRAY_H 1 + +#ifdef __KERNEL__ +#include +#include +#include +#endif + +struct skb_array { + struct ptr_ring ring; +}; + +/* Might be slightly faster than skb_array_full below, but callers invoking + * this in a loop must use a compiler barrier, for example cpu_relax(). + */ +static inline bool __skb_array_full(struct skb_array *a) +{ + return __ptr_ring_full(&a->ring); +} + +static inline bool skb_array_full(struct skb_array *a) +{ + return ptr_ring_full(&a->ring); +} + +static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb) +{ + return ptr_ring_produce(&a->ring, skb); +} + +static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb) +{ + return ptr_ring_produce_irq(&a->ring, skb); +} + +static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb) +{ + return ptr_ring_produce_bh(&a->ring, skb); +} + +static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb) +{ + return ptr_ring_produce_any(&a->ring, skb); +} + +/* Might be slightly faster than skb_array_empty below, but callers invoking + * this in a loop must take care to use a compiler barrier, for example + * cpu_relax(). + */ +static inline bool __skb_array_empty(struct skb_array *a) +{ + return !__ptr_ring_peek(&a->ring); +} + +static inline bool skb_array_empty(struct skb_array *a) +{ + return ptr_ring_empty(&a->ring); +} + +static inline struct sk_buff *skb_array_consume(struct skb_array *a) +{ + return ptr_ring_consume(&a->ring); +} + +static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) +{ + return ptr_ring_consume_irq(&a->ring); +} + +static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) +{ + return ptr_ring_consume_any(&a->ring); +} + +static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) +{ + return ptr_ring_consume_bh(&a->ring); +} + +static inline int __skb_array_len_with_tag(struct sk_buff *skb) +{ + if (likely(skb)) { + int len = skb->len; + + if (skb_vlan_tag_present(skb)) + len += VLAN_HLEN; + + return len; + } else { + return 0; + } +} + +static inline int skb_array_peek_len(struct skb_array *a) +{ + return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag); +} + +static inline int skb_array_peek_len_irq(struct skb_array *a) +{ + return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag); +} + +static inline int skb_array_peek_len_bh(struct skb_array *a) +{ + return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag); +} + +static inline int skb_array_peek_len_any(struct skb_array *a) +{ + return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); +} + +static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) +{ + return ptr_ring_init(&a->ring, size, gfp); +} + +static inline void skb_array_cleanup(struct skb_array *a) +{ + ptr_ring_cleanup(&a->ring); +} + +#endif /* _LINUX_SKB_ARRAY_H */ -- cgit v1.2.3 From 5d49de532002f02755decd1758aac53063a68625 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 13 Jun 2016 23:54:45 +0300 Subject: ptr_ring: resize support This adds ring resize support. Seems to be necessary as users such as tun allow userspace control over queue size. If resize is used, this costs us ability to peek at queue without consumer lock - should not be a big deal as peek and consumer are usually run on the same CPU. If ring is made bigger, ring contents is preserved. If ring is made smaller, extra pointers are passed to an optional destructor callback. Cleanup function also gains destructor callback such that all pointers in queue can be cleaned up. This changes some APIs but we don't have any users yet, so it won't break bisect. Signed-off-by: Michael S. Tsirkin Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 157 ++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 143 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 633406f9af8e..562a65e8bcc0 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -43,9 +43,9 @@ struct ptr_ring { }; /* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). - * Callers don't need to take producer lock - if they don't - * the next call to __ptr_ring_produce may fail. + * for example cpu_relax(). If ring is ever resized, callers must hold + * producer_lock - see e.g. ptr_ring_full. Otherwise, if callers don't hold + * producer_lock, the next call to __ptr_ring_produce may fail. */ static inline bool __ptr_ring_full(struct ptr_ring *r) { @@ -54,16 +54,55 @@ static inline bool __ptr_ring_full(struct ptr_ring *r) static inline bool ptr_ring_full(struct ptr_ring *r) { - barrier(); - return __ptr_ring_full(r); + bool ret; + + spin_lock(&r->producer_lock); + ret = __ptr_ring_full(r); + spin_unlock(&r->producer_lock); + + return ret; +} + +static inline bool ptr_ring_full_irq(struct ptr_ring *r) +{ + bool ret; + + spin_lock_irq(&r->producer_lock); + ret = __ptr_ring_full(r); + spin_unlock_irq(&r->producer_lock); + + return ret; +} + +static inline bool ptr_ring_full_any(struct ptr_ring *r) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(&r->producer_lock, flags); + ret = __ptr_ring_full(r); + spin_unlock_irqrestore(&r->producer_lock, flags); + + return ret; +} + +static inline bool ptr_ring_full_bh(struct ptr_ring *r) +{ + bool ret; + + spin_lock_bh(&r->producer_lock); + ret = __ptr_ring_full(r); + spin_unlock_bh(&r->producer_lock); + + return ret; } /* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). + * for example cpu_relax(). Callers must hold producer_lock. */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { - if (__ptr_ring_full(r)) + if (r->queue[r->producer]) return -ENOSPC; r->queue[r->producer++] = ptr; @@ -120,20 +159,68 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) /* Note: callers invoking this in a loop must use a compiler barrier, * for example cpu_relax(). Callers must take consumer_lock * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. - * There's no need for a lock if pointer is merely tested - see e.g. - * ptr_ring_empty. + * If ring is never resized, and if the pointer is merely + * tested, there's no need to take the lock - see e.g. __ptr_ring_empty. */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { return r->queue[r->consumer]; } -static inline bool ptr_ring_empty(struct ptr_ring *r) +/* Note: callers invoking this in a loop must use a compiler barrier, + * for example cpu_relax(). Callers must take consumer_lock + * if the ring is ever resized - see e.g. ptr_ring_empty. + */ +static inline bool __ptr_ring_empty(struct ptr_ring *r) { - barrier(); return !__ptr_ring_peek(r); } +static inline bool ptr_ring_empty(struct ptr_ring *r) +{ + bool ret; + + spin_lock(&r->consumer_lock); + ret = __ptr_ring_empty(r); + spin_unlock(&r->consumer_lock); + + return ret; +} + +static inline bool ptr_ring_empty_irq(struct ptr_ring *r) +{ + bool ret; + + spin_lock_irq(&r->consumer_lock); + ret = __ptr_ring_empty(r); + spin_unlock_irq(&r->consumer_lock); + + return ret; +} + +static inline bool ptr_ring_empty_any(struct ptr_ring *r) +{ + unsigned long flags; + bool ret; + + spin_lock_irqsave(&r->consumer_lock, flags); + ret = __ptr_ring_empty(r); + spin_unlock_irqrestore(&r->consumer_lock, flags); + + return ret; +} + +static inline bool ptr_ring_empty_bh(struct ptr_ring *r) +{ + bool ret; + + spin_lock_bh(&r->consumer_lock); + ret = __ptr_ring_empty(r); + spin_unlock_bh(&r->consumer_lock); + + return ret; +} + /* Must only be called after __ptr_ring_peek returned !NULL */ static inline void __ptr_ring_discard_one(struct ptr_ring *r) { @@ -241,10 +328,14 @@ static inline void *ptr_ring_consume_bh(struct ptr_ring *r) __PTR_RING_PEEK_CALL_v; \ }) +static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp) +{ + return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp); +} + static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) { - r->queue = kzalloc(ALIGN(size * sizeof *(r->queue), SMP_CACHE_BYTES), - gfp); + r->queue = __ptr_ring_init_queue_alloc(size, gfp); if (!r->queue) return -ENOMEM; @@ -256,8 +347,46 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } -static inline void ptr_ring_cleanup(struct ptr_ring *r) +static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, + void (*destroy)(void *)) +{ + unsigned long flags; + int producer = 0; + void **queue = __ptr_ring_init_queue_alloc(size, gfp); + void **old; + void *ptr; + + if (!queue) + return -ENOMEM; + + spin_lock_irqsave(&(r)->producer_lock, flags); + + while ((ptr = ptr_ring_consume(r))) + if (producer < size) + queue[producer++] = ptr; + else if (destroy) + destroy(ptr); + + r->size = size; + r->producer = producer; + r->consumer = 0; + old = r->queue; + r->queue = queue; + + spin_unlock_irqrestore(&(r)->producer_lock, flags); + + kfree(old); + + return 0; +} + +static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { + void *ptr; + + if (destroy) + while ((ptr = ptr_ring_consume(r))) + destroy(ptr); kfree(r->queue); } -- cgit v1.2.3 From 7d7072e3bad5569f636d3c54a36da40976bfd505 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 13 Jun 2016 23:54:50 +0300 Subject: skb_array: resize support Update skb_array after ptr_ring API changes. Signed-off-by: Michael S. Tsirkin Acked-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/skb_array.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index c4c090223333..678bfbf78ac4 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -63,9 +63,9 @@ static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb return ptr_ring_produce_any(&a->ring, skb); } -/* Might be slightly faster than skb_array_empty below, but callers invoking - * this in a loop must take care to use a compiler barrier, for example - * cpu_relax(). +/* Might be slightly faster than skb_array_empty below, but only safe if the + * array is never resized. Also, callers invoking this in a loop must take care + * to use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_empty(struct skb_array *a) { @@ -77,6 +77,21 @@ static inline bool skb_array_empty(struct skb_array *a) return ptr_ring_empty(&a->ring); } +static inline bool skb_array_empty_bh(struct skb_array *a) +{ + return ptr_ring_empty_bh(&a->ring); +} + +static inline bool skb_array_empty_irq(struct skb_array *a) +{ + return ptr_ring_empty_irq(&a->ring); +} + +static inline bool skb_array_empty_any(struct skb_array *a) +{ + return ptr_ring_empty_any(&a->ring); +} + static inline struct sk_buff *skb_array_consume(struct skb_array *a) { return ptr_ring_consume(&a->ring); @@ -136,9 +151,19 @@ static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_init(&a->ring, size, gfp); } +void __skb_array_destroy_skb(void *ptr) +{ + kfree_skb(ptr); +} + +int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) +{ + return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); +} + static inline void skb_array_cleanup(struct skb_array *a) { - ptr_ring_cleanup(&a->ring); + ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb); } #endif /* _LINUX_SKB_ARRAY_H */ -- cgit v1.2.3 From 6f0dd24a084a17f9984dd49dffbf7055bf123993 Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Fri, 10 Jun 2016 14:37:23 -0300 Subject: [media] media: fix media devnode ioctl/syscall and unregister race Media devnode open/ioctl could be in progress when media device unregister is initiated. System calls and ioctls check media device registered status at the beginning, however, there is a window where unregister could be in progress without changing the media devnode status to unregistered. process 1 process 2 fd = open(/dev/media0) media_devnode_is_registered() (returns true here) media_device_unregister() (unregister is in progress and devnode isn't unregistered yet) ... ioctl(fd, ...) __media_ioctl() media_devnode_is_registered() (returns true here) ... media_devnode_unregister() ... (driver releases the media device memory) media_device_ioctl() (By this point devnode->media_dev does not point to allocated memory. use-after free in in mutex_lock_nested) BUG: KASAN: use-after-free in mutex_lock_nested+0x79c/0x800 at addr ffff8801ebe914f0 Fix it by clearing register bit when unregister starts to avoid the race. process 1 process 2 fd = open(/dev/media0) media_devnode_is_registered() (could return true here) media_device_unregister() (clear the register bit, then start unregister.) ... ioctl(fd, ...) __media_ioctl() media_devnode_is_registered() (return false here, ioctl returns I/O error, and will not access media device memory) ... media_devnode_unregister() ... (driver releases the media device memory) Signed-off-by: Shuah Khan Suggested-by: Sakari Ailus Reported-by: Mauro Carvalho Chehab Tested-by: Mauro Carvalho Chehab Signed-off-by: Mauro Carvalho Chehab --- include/media/media-devnode.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h index 5bb3b0e86d73..f0b7dd79fb92 100644 --- a/include/media/media-devnode.h +++ b/include/media/media-devnode.h @@ -125,6 +125,19 @@ int __must_check media_devnode_register(struct media_device *mdev, struct media_devnode *devnode, struct module *owner); +/** + * media_devnode_unregister_prepare - clear the media device node register bit + * @devnode: the device node to prepare for unregister + * + * This clears the passed device register bit. Future open calls will be met + * with errors. Should be called before media_devnode_unregister() to avoid + * races with unregister and device file open calls. + * + * This function can safely be called if the device node has never been + * registered or has already been unregistered. + */ +void media_devnode_unregister_prepare(struct media_devnode *devnode); + /** * media_devnode_unregister - unregister a media device node * @devnode: the device node to unregister @@ -132,8 +145,7 @@ int __must_check media_devnode_register(struct media_device *mdev, * This unregisters the passed device. Future open calls will be met with * errors. * - * This function can safely be called if the device node has never been - * registered or has already been unregistered. + * Should be called after media_devnode_unregister_prepare() */ void media_devnode_unregister(struct media_devnode *devnode); -- cgit v1.2.3 From 1b5c5493e3e68181be344cb51bf9df192d05ffc2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 13 Jun 2016 20:21:50 -0700 Subject: net_sched: add the ability to defer skb freeing qdisc are changed under RTNL protection and often while blocking BH and root qdisc spinlock. When lots of skbs need to be dropped, we free them under these locks causing TX/RX freezes, and more generally latency spikes. This commit adds rtnl_kfree_skbs(), used to queue skbs for deferred freeing. Actual freeing happens right after RTNL is released, with appropriate scheduling points. rtnl_qdisc_drop() can also be used in place of disc_drop() when RTNL is held. qdisc_reset_queue() and __qdisc_reset_queue() get the new behavior, so standard qdiscs like pfifo, pfifo_fast... have their ->reset() method automatically handled. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++-- include/net/sch_generic.h | 16 ++++++++++++---- 2 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index c006cc900c44..2daece8979f7 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -89,8 +89,9 @@ void net_inc_egress_queue(void); void net_dec_egress_queue(void); #endif -extern void rtnetlink_init(void); -extern void __rtnl_unlock(void); +void rtnetlink_init(void); +void __rtnl_unlock(void); +void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail); #define ASSERT_RTNL() do { \ if (unlikely(!rtnl_is_locked())) { \ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9a0d177884c6..4f7cee8344c4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -683,19 +683,21 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) return skb; } -static inline void __qdisc_reset_queue(struct Qdisc *sch, - struct sk_buff_head *list) +static inline void __qdisc_reset_queue(struct sk_buff_head *list) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ - __skb_queue_purge(list); + if (!skb_queue_empty(list)) { + rtnl_kfree_skbs(list->next, list->prev); + __skb_queue_head_init(list); + } } static inline void qdisc_reset_queue(struct Qdisc *sch) { - __qdisc_reset_queue(sch, &sch->q); + __qdisc_reset_queue(&sch->q); sch->qstats.backlog = 0; } @@ -716,6 +718,12 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, return old; } +static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) +{ + rtnl_kfree_skbs(skb, skb); + qdisc_qstats_drop(sch); +} + static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { kfree_skb(skb); -- cgit v1.2.3 From 6c7caebc26c5f0b618f0ef6b851e9f5f27c3812f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 13 Jun 2016 14:48:25 +0200 Subject: KVM: introduce kvm->created_vcpus The race between creating the irqchip and the first VCPU is currently fixed by checking the presence of an irqchip before updating kvm->online_vcpus, and undoing the whole VCPU creation if someone created the irqchip in the meanwhile. Instead, introduce a new field in struct kvm that will count VCPUs under a mutex, without the atomic access and memory ordering that we need elsewhere to protect the vcpus array. This also plugs the race and is more easily applicable in all similar circumstances. Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1c9c973a7dd9..63c6ab30bc81 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -371,7 +371,15 @@ struct kvm { struct srcu_struct srcu; struct srcu_struct irq_srcu; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + + /* + * created_vcpus is protected by kvm->lock, and is incremented + * at the beginning of KVM_CREATE_VCPU. online_vcpus is only + * incremented after storing the kvm_vcpu pointer in vcpus, + * and is accessed atomically. + */ atomic_t online_vcpus; + int created_vcpus; int last_boosted_vcpu; struct list_head vm_list; struct mutex lock; -- cgit v1.2.3 From 557abc40d121358883d2da8bc8bf976d6e8ec332 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 13 Jun 2016 14:50:04 +0200 Subject: KVM: remove kvm_vcpu_compatible The new created_vcpus field makes it possible to avoid the race between irqchip and VCPU creation in a much nicer way; just check under kvm->lock whether a VCPU has already been created. We can then remove KVM_APIC_ARCHITECTURE too, because at this point the symbol is only governing the default definition of kvm_vcpu_compatible. Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 63c6ab30bc81..0640ee92b978 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1105,12 +1105,6 @@ static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) #endif /* CONFIG_HAVE_KVM_EVENTFD */ -#ifdef CONFIG_KVM_APIC_ARCHITECTURE -bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu); -#else -static inline bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { return true; } -#endif - static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu) { /* -- 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 + 1 file changed, 1 insertion(+) (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 -- 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 --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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; -- cgit v1.2.3 From de0fae60b35d405d3aa2e9acf5914770cd328338 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 12 Jun 2016 23:53:04 +0300 Subject: ARM: dts: r8a7792: add clock index macros Add macros usable by the device tree sources to reference the R8A7792 clocks by index. Signed-off-by: Sergei Shtylyov Reviewed-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/dt-bindings/clock/r8a7792-clock.h | 102 ++++++++++++++++++++++++++++++ 1 file changed, 102 insertions(+) create mode 100644 include/dt-bindings/clock/r8a7792-clock.h (limited to 'include') diff --git a/include/dt-bindings/clock/r8a7792-clock.h b/include/dt-bindings/clock/r8a7792-clock.h new file mode 100644 index 000000000000..949801eb0652 --- /dev/null +++ b/include/dt-bindings/clock/r8a7792-clock.h @@ -0,0 +1,102 @@ +/* + * Copyright (C) 2016 Cogent Embedded, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __DT_BINDINGS_CLOCK_R8A7792_H__ +#define __DT_BINDINGS_CLOCK_R8A7792_H__ + +/* CPG */ +#define R8A7792_CLK_MAIN 0 +#define R8A7792_CLK_PLL0 1 +#define R8A7792_CLK_PLL1 2 +#define R8A7792_CLK_PLL3 3 +#define R8A7792_CLK_LB 4 +#define R8A7792_CLK_QSPI 5 +#define R8A7792_CLK_Z 6 +#define R8A7792_CLK_ADSP 7 + +/* MSTP0 */ +#define R8A7792_CLK_MSIOF0 0 + +/* MSTP1 */ +#define R8A7792_CLK_TMU1 11 +#define R8A7792_CLK_TMU3 21 +#define R8A7792_CLK_TMU2 22 +#define R8A7792_CLK_CMT0 24 +#define R8A7792_CLK_TMU0 25 +#define R8A7792_CLK_VSP1DU1 27 +#define R8A7792_CLK_VSP1DU0 28 +#define R8A7792_CLK_VSP1_SY 31 + +/* MSTP2 */ +#define R8A7792_CLK_MSIOF1 8 +#define R8A7792_CLK_SYS_DMAC1 18 +#define R8A7792_CLK_SYS_DMAC0 19 + +/* MSTP3 */ +#define R8A7792_CLK_TPU0 4 +#define R8A7792_CLK_SDHI0 14 +#define R8A7792_CLK_CMT1 29 + +/* MSTP4 */ +#define R8A7792_CLK_IRQC 7 + +/* MSTP5 */ +#define R8A7792_CLK_AUDIO_DMAC0 2 +#define R8A7792_CLK_THERMAL 22 +#define R8A7792_CLK_PWM 23 + +/* MSTP7 */ +#define R8A7792_CLK_HSCIF1 16 +#define R8A7792_CLK_HSCIF0 17 +#define R8A7792_CLK_SCIF3 18 +#define R8A7792_CLK_SCIF2 19 +#define R8A7792_CLK_SCIF1 20 +#define R8A7792_CLK_SCIF0 21 +#define R8A7792_CLK_DU1 23 +#define R8A7792_CLK_DU0 24 + +/* MSTP8 */ +#define R8A7792_CLK_VIN5 4 +#define R8A7792_CLK_VIN4 5 +#define R8A7792_CLK_VIN3 8 +#define R8A7792_CLK_VIN2 9 +#define R8A7792_CLK_VIN1 10 +#define R8A7792_CLK_VIN0 11 +#define R8A7792_CLK_ETHERAVB 12 + +/* MSTP9 */ +#define R8A7792_CLK_GPIO7 4 +#define R8A7792_CLK_GPIO6 5 +#define R8A7792_CLK_GPIO5 7 +#define R8A7792_CLK_GPIO4 8 +#define R8A7792_CLK_GPIO3 9 +#define R8A7792_CLK_GPIO2 10 +#define R8A7792_CLK_GPIO1 11 +#define R8A7792_CLK_GPIO0 12 +#define R8A7792_CLK_GPIO11 13 +#define R8A7792_CLK_GPIO10 14 +#define R8A7792_CLK_CAN1 15 +#define R8A7792_CLK_CAN0 16 +#define R8A7792_CLK_QSPI_MOD 17 +#define R8A7792_CLK_GPIO9 19 +#define R8A7792_CLK_GPIO8 21 +#define R8A7792_CLK_I2C5 25 +#define R8A7792_CLK_IICDVFS 26 +#define R8A7792_CLK_I2C4 27 +#define R8A7792_CLK_I2C3 28 +#define R8A7792_CLK_I2C2 29 +#define R8A7792_CLK_I2C1 30 +#define R8A7792_CLK_I2C0 31 + +/* MSTP10 */ +#define R8A7792_CLK_SSI_ALL 5 +#define R8A7792_CLK_SSI4 11 +#define R8A7792_CLK_SSI3 12 + +#endif /* __DT_BINDINGS_CLOCK_R8A7792_H__ */ -- cgit v1.2.3 From 5258bb5d980024dae22f4256329caec4fe5e98b3 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sun, 12 Jun 2016 23:54:49 +0300 Subject: ARM: dts: r8a7792: add power domain index macros Add macros usable by the device tree sources to reference R8A7792 SYSC power domains by index. Signed-off-by: Sergei Shtylyov Reviewed-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/dt-bindings/power/r8a7792-sysc.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 include/dt-bindings/power/r8a7792-sysc.h (limited to 'include') diff --git a/include/dt-bindings/power/r8a7792-sysc.h b/include/dt-bindings/power/r8a7792-sysc.h new file mode 100644 index 000000000000..74f4a78e29aa --- /dev/null +++ b/include/dt-bindings/power/r8a7792-sysc.h @@ -0,0 +1,26 @@ +/* + * Copyright (C) 2016 Cogent Embedded Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + */ +#ifndef __DT_BINDINGS_POWER_R8A7792_SYSC_H__ +#define __DT_BINDINGS_POWER_R8A7792_SYSC_H__ + +/* + * These power domain indices match the numbers of the interrupt bits + * representing the power areas in the various Interrupt Registers + * (e.g. SYSCISR, Interrupt Status Register) + */ + +#define R8A7792_PD_CA15_CPU0 0 +#define R8A7792_PD_CA15_CPU1 1 +#define R8A7792_PD_CA15_SCU 12 +#define R8A7792_PD_SGX 20 +#define R8A7792_PD_IMP 24 + +/* Always-on power area */ +#define R8A7792_PD_ALWAYS_ON 32 + +#endif /* __DT_BINDINGS_POWER_R8A7792_SYSC_H__ */ -- cgit v1.2.3 From e63a46bef01ff3064f44dba145833284fb6adeec Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 15 Jun 2016 18:17:27 -0700 Subject: block: introduce device_add_disk() In preparation for removing the ->driverfs_dev member of a gendisk, add an api that takes the parent device as a parameter to add_disk(). For now this maintains the status quo of WARN()ing on failure, but not return a error code. Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Signed-off-by: Dan Williams --- include/linux/genhd.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 359a8e4bd44d..df1dabbfd388 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -414,7 +414,13 @@ static inline void free_part_info(struct hd_struct *part) extern void part_round_stats(int cpu, struct hd_struct *part); /* block/genhd.c */ -extern void add_disk(struct gendisk *disk); +extern void device_add_disk(struct device *parent, struct gendisk *disk); +static inline void add_disk(struct gendisk *disk) +{ + /* temporary while we convert callers to device_add_disk */ + device_add_disk(disk->driverfs_dev, disk); +} + extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); -- cgit v1.2.3 From 8626a0c83b0d471d859bcd908d016874df951fc3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:16 +0200 Subject: 6lowpan: add private neighbour data This patch will introduce a 6lowpan neighbour private data. Like the interface private data we handle private data for generic 6lowpan and for link-layer specific 6lowpan. The current first use case if to save the short address for a 802.15.4 6lowpan neighbour. Cc: David S. Miller Reviewed-by: Stefan Schmidt Acked-by: YOSHIFUJI Hideaki Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- include/net/6lowpan.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d101e4d904ba..36e43bd422f8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,8 +1483,7 @@ enum netdev_priv_flags { * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length - * @neigh_priv_len; Used in neigh_alloc(), - * initialized only in atm/clip.c + * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address * @dev_port: Used to differentiate devices that share diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index da84cf920b78..2d9b9d39221e 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -141,6 +141,16 @@ struct lowpan_dev { u8 priv[0] __aligned(sizeof(void *)); }; +struct lowpan_802154_neigh { + __le16 short_addr; +}; + +static inline +struct lowpan_802154_neigh *lowpan_802154_neigh(void *neigh_priv) +{ + return neigh_priv; +} + static inline struct lowpan_dev *lowpan_dev(const struct net_device *dev) { -- cgit v1.2.3 From 2ad3ed59198c5404c34515cfcfd9a2b3c54d964f Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:17 +0200 Subject: 6lowpan: add 802.15.4 short addr slaac This patch adds the autoconfiguration if a valid 802.15.4 short address is available for 802.15.4 6LoWPAN interfaces. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Acked-by: Hannes Frederic Sowa Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/6lowpan.h | 6 ++++++ include/net/addrconf.h | 3 +++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 2d9b9d39221e..5ab4c9901ccc 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -254,6 +254,12 @@ static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data, return false; } +static inline bool lowpan_802154_is_valid_src_short_addr(__le16 addr) +{ + /* First bit of addr is multicast, reserved or 802.15.4 specific */ + return !(addr & cpu_to_le16(0x8000)); +} + static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, const size_t len) { diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 730d856683e5..b1774eb03f37 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -94,6 +94,9 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); +void addrconf_add_linklocal(struct inet6_dev *idev, + const struct in6_addr *addr, u32 flags); + static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) -- cgit v1.2.3 From 1e82f961ac8e94c50a933e89ee08071fc81a4bbd Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:19 +0200 Subject: ndisc: add __ndisc_opt_addr_space function This patch adds __ndisc_opt_addr_space as low-level function for ndisc_opt_addr_space which doesn't depend on net_device parameter. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Acked-by: YOSHIFUJI Hideaki Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/ndisc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 2d8edaad29cb..4cee82654fe5 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -127,10 +127,15 @@ static inline int ndisc_addr_option_pad(unsigned short type) } } +static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) +{ + return NDISC_OPT_SPACE(addr_len + pad); +} + static inline int ndisc_opt_addr_space(struct net_device *dev) { - return NDISC_OPT_SPACE(dev->addr_len + - ndisc_addr_option_pad(dev->type)); + return __ndisc_opt_addr_space(dev->addr_len, + ndisc_addr_option_pad(dev->type)); } static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, -- cgit v1.2.3 From 4f36ce84c54c971cd67c882035d9bde7b1a2ee53 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:20 +0200 Subject: ndisc: add __ndisc_opt_addr_data function This patch adds __ndisc_opt_addr_data as low-level function for ndisc_opt_addr_data which doesn't depend on net_device parameter. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Acked-by: YOSHIFUJI Hideaki Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/ndisc.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 4cee82654fe5..c8962adf24d0 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -138,17 +138,23 @@ static inline int ndisc_opt_addr_space(struct net_device *dev) ndisc_addr_option_pad(dev->type)); } -static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, - struct net_device *dev) +static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, + unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; - int prepad = ndisc_addr_option_pad(dev->type); - if (lladdrlen != ndisc_opt_addr_space(dev)) + if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } +static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, + struct net_device *dev) +{ + return __ndisc_opt_addr_data(p, dev->addr_len, + ndisc_addr_option_pad(dev->type)); +} + static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; -- cgit v1.2.3 From f997c55c1dc8841b3ee4df0493d0ac7966d42165 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:23 +0200 Subject: ipv6: introduce neighbour discovery ops This patch introduces neighbour discovery ops callback structure. The idea is to separate the handling for 6LoWPAN into the 6lowpan module. These callback offers 6lowpan different handling, such as 802.15.4 short address handling or RFC6775 (Neighbor Discovery Optimization for IPv6 over 6LoWPANs). Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Acked-by: YOSHIFUJI Hideaki Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++ include/net/ndisc.h | 197 +++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 199 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 36e43bd422f8..890158e99159 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1456,6 +1456,8 @@ enum netdev_priv_flags { * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @ethtool_ops: Management operations + * @ndisc_ops: Includes callbacks for different IPv6 neighbour + * discovery handling. Necessary for e.g. 6LoWPAN. * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * @@ -1672,6 +1674,9 @@ struct net_device { #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; #endif +#if IS_ENABLED(CONFIG_IPV6) + const struct ndisc_ops *ndisc_ops; +#endif const struct header_ops *header_ops; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index c8962adf24d0..a5e276703cb3 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -58,6 +58,7 @@ struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; +struct prefix_info; extern struct neigh_table nd_tbl; @@ -110,9 +111,182 @@ struct ndisc_options { #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) -struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len, +struct ndisc_options *ndisc_parse_options(const struct net_device *dev, + u8 *opt, int opt_len, struct ndisc_options *ndopts); +#define NDISC_OPS_REDIRECT_DATA_SPACE 2 + +/* + * This structure defines the hooks for IPv6 neighbour discovery. + * The following hooks can be defined; unless noted otherwise, they are + * optional and can be filled with a null pointer. + * + * int (*is_useropt)(u8 nd_opt_type): + * This function is called when IPv6 decide RA userspace options. if + * this function returns 1 then the option given by nd_opt_type will + * be handled as userspace option additional to the IPv6 options. + * + * int (*parse_options)(const struct net_device *dev, + * struct nd_opt_hdr *nd_opt, + * struct ndisc_options *ndopts): + * This function is called while parsing ndisc ops and put each position + * as pointer into ndopts. If this function return unequal 0, then this + * function took care about the ndisc option, if 0 then the IPv6 ndisc + * option parser will take care about that option. + * + * void (*update)(const struct net_device *dev, struct neighbour *n, + * u32 flags, u8 icmp6_type, + * const struct ndisc_options *ndopts): + * This function is called when IPv6 ndisc updates the neighbour cache + * entry. Additional options which can be updated may be previously + * parsed by parse_opts callback and accessible over ndopts parameter. + * + * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, + * struct neighbour *neigh, u8 *ha_buf, + * u8 **ha): + * This function is called when the necessary option space will be + * calculated before allocating a skb. The parameters neigh, ha_buf + * abd ha are available on NDISC_REDIRECT messages only. + * + * void (*fill_addr_option)(const struct net_device *dev, + * struct sk_buff *skb, u8 icmp6_type, + * const u8 *ha): + * This function is called when the skb will finally fill the option + * fields inside skb. NOTE: this callback should fill the option + * fields to the skb which are previously indicated by opt_space + * parameter. That means the decision to add such option should + * not lost between these two callbacks, e.g. protected by interface + * up state. + * + * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, + * const struct prefix_info *pinfo, + * struct inet6_dev *in6_dev, + * struct in6_addr *addr, + * int addr_type, u32 addr_flags, + * bool sllao, bool tokenized, + * __u32 valid_lft, u32 prefered_lft, + * bool dev_addr_generated): + * This function is called when a RA messages is received with valid + * PIO option fields and an IPv6 address will be added to the interface + * for autoconfiguration. The parameter dev_addr_generated reports about + * if the address was based on dev->dev_addr or not. This can be used + * to add a second address if link-layer operates with two link layer + * addresses. E.g. 802.15.4 6LoWPAN. + */ +struct ndisc_ops { + int (*is_useropt)(u8 nd_opt_type); + int (*parse_options)(const struct net_device *dev, + struct nd_opt_hdr *nd_opt, + struct ndisc_options *ndopts); + void (*update)(const struct net_device *dev, struct neighbour *n, + u32 flags, u8 icmp6_type, + const struct ndisc_options *ndopts); + int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, + struct neighbour *neigh, u8 *ha_buf, + u8 **ha); + void (*fill_addr_option)(const struct net_device *dev, + struct sk_buff *skb, u8 icmp6_type, + const u8 *ha); + void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + struct in6_addr *addr, + int addr_type, u32 addr_flags, + bool sllao, bool tokenized, + __u32 valid_lft, u32 prefered_lft, + bool dev_addr_generated); +}; + +#if IS_ENABLED(CONFIG_IPV6) +static inline int ndisc_ops_is_useropt(const struct net_device *dev, + u8 nd_opt_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) + return dev->ndisc_ops->is_useropt(nd_opt_type); + else + return 0; +} + +static inline int ndisc_ops_parse_options(const struct net_device *dev, + struct nd_opt_hdr *nd_opt, + struct ndisc_options *ndopts) +{ + if (dev->ndisc_ops && dev->ndisc_ops->parse_options) + return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); + else + return 0; +} + +static inline void ndisc_ops_update(const struct net_device *dev, + struct neighbour *n, u32 flags, + u8 icmp6_type, + const struct ndisc_options *ndopts) +{ + if (dev->ndisc_ops && dev->ndisc_ops->update) + dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); +} + +static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, + u8 icmp6_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && + icmp6_type != NDISC_REDIRECT) + return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, + NULL, NULL); + else + return 0; +} + +static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, + struct neighbour *neigh, + u8 *ha_buf, u8 **ha) +{ + if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) + return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, + neigh, ha_buf, ha); + else + return 0; +} + +static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, + struct sk_buff *skb, + u8 icmp6_type) +{ + if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && + icmp6_type != NDISC_REDIRECT) + dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); +} + +static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, + struct sk_buff *skb, + const u8 *ha) +{ + if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) + dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); +} + +static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, + struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + struct in6_addr *addr, + int addr_type, u32 addr_flags, + bool sllao, bool tokenized, + __u32 valid_lft, + u32 prefered_lft, + bool dev_addr_generated) +{ + if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) + dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, + addr, addr_type, + addr_flags, sllao, + tokenized, valid_lft, + prefered_lft, + dev_addr_generated); +} +#endif + /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although @@ -132,11 +306,25 @@ static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) return NDISC_OPT_SPACE(addr_len + pad); } -static inline int ndisc_opt_addr_space(struct net_device *dev) +#if IS_ENABLED(CONFIG_IPV6) +static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) +{ + return __ndisc_opt_addr_space(dev->addr_len, + ndisc_addr_option_pad(dev->type)) + + ndisc_ops_opt_addr_space(dev, icmp6_type); +} + +static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, + struct neighbour *neigh, + u8 *ops_data_buf, + u8 **ops_data) { return __ndisc_opt_addr_space(dev->addr_len, - ndisc_addr_option_pad(dev->type)); + ndisc_addr_option_pad(dev->type)) + + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, + ops_data); } +#endif static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, unsigned char addr_len, int prepad) @@ -205,6 +393,9 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); +void ndisc_update(const struct net_device *dev, struct neighbour *neigh, + const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, + struct ndisc_options *ndopts); /* * IGMP -- cgit v1.2.3 From cc84b3c6b48ae81748c5e25d3558872385196162 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:24 +0200 Subject: ipv6: export several functions This patch exports some neighbour discovery functions which can be used by 6lowpan neighbour discovery ops functionality then. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Acked-by: YOSHIFUJI Hideaki Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/addrconf.h | 7 +++++++ include/net/ndisc.h | 12 ++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b1774eb03f37..9826d3a9464c 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -97,6 +97,13 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags); +int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, + const struct prefix_info *pinfo, + struct inet6_dev *in6_dev, + const struct in6_addr *addr, int addr_type, + u32 addr_flags, bool sllao, bool tokenized, + __u32 valid_lft, u32 prefered_lft); + static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) { if (dev->addr_len != ETH_ALEN) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index a5e276703cb3..3f0f41ddbeb0 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -53,6 +53,15 @@ enum { #include +/* Set to 3 to get tracing... */ +#define ND_DEBUG 1 + +#define ND_PRINTK(val, level, fmt, ...) \ +do { \ + if (val <= ND_DEBUG) \ + net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ +} while (0) + struct ctl_table; struct inet6_dev; struct net_device; @@ -115,6 +124,9 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, + int data_len, int pad); + #define NDISC_OPS_REDIRECT_DATA_SPACE 2 /* -- cgit v1.2.3 From bbe5f5cefe2818eda0392c178de141ffc5734d90 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 15 Jun 2016 21:20:25 +0200 Subject: 6lowpan: introduce 6lowpan-nd This patch introduce different 6lowpan handling for receive and transmit NS/NA messages for the ipv6 neighbour discovery. The first use-case is for supporting 802.15.4 short addresses inside the option fields and handling for RFC6775 6CO option field as userspace option. Cc: David S. Miller Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Reviewed-by: Stefan Schmidt Acked-by: YOSHIFUJI Hideaki Signed-off-by: Alexander Aring Signed-off-by: David S. Miller --- include/net/ndisc.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 3f0f41ddbeb0..be1fe2283254 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -35,6 +35,7 @@ enum { ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ + ND_OPT_6CO = 34, /* RFC6775 */ __ND_OPT_MAX }; @@ -109,14 +110,19 @@ struct ndisc_options { #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; +#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) + struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; +#endif }; -#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] -#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] -#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] -#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] -#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] -#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] +#define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] +#define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] +#define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] +#define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] +#define nd_opts_mtu nd_opt_array[ND_OPT_MTU] +#define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] +#define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) -- cgit v1.2.3 From 22a59be8b7693eb2d0897a9638f5991f2f8e4ddd Mon Sep 17 00:00:00 2001 From: Philip Prindeville Date: Tue, 14 Jun 2016 15:53:02 -0600 Subject: net: ipv4: Add ability to have GRE ignore DF bit in IPv4 payloads In the presence of firewalls which improperly block ICMP Unreachable (including Fragmentation Required) messages, Path MTU Discovery is prevented from working. A workaround is to handle IPv4 payloads opaquely, ignoring the DF bit--as is done for other payloads like AppleTalk--and doing transparent fragmentation and reassembly. Redux includes the enforcement of mutual exclusion between this feature and Path MTU Discovery as suggested by Alexander Duyck. Cc: Alexander Duyck Reviewed-by: Stephen Hemminger Signed-off-by: Philip Prindeville Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 1 + include/uapi/linux/if_tunnel.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index dbf444428437..9222678426a1 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -132,6 +132,7 @@ struct ip_tunnel { int ip_tnl_net_id; struct gro_cells gro_cells; bool collect_md; + bool ignore_df; }; #define TUNNEL_CSUM __cpu_to_be16(0x01) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index af4de90ba27d..1046f5515174 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -113,6 +113,7 @@ enum { IFLA_GRE_ENCAP_SPORT, IFLA_GRE_ENCAP_DPORT, IFLA_GRE_COLLECT_METADATA, + IFLA_GRE_IGNORE_DF, __IFLA_GRE_MAX, }; -- cgit v1.2.3 From 61d1b6a42fec61c5065f54cc62cef02b483c69fb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jun 2016 22:47:12 +0200 Subject: bpf, maps: add release callback Add a release callback for maps that is invoked when the last reference to its struct file is gone and the struct file about to be released by vfs. The handler will be used by fd array maps. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1bcae82c6cb1..29b5a1ae22cb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -19,7 +19,8 @@ struct bpf_map; struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ struct bpf_map *(*map_alloc)(union bpf_attr *attr); - void (*map_free)(struct bpf_map *); + void (*map_release)(struct bpf_map *map, struct file *map_file); + void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); /* funcs callable from userspace and from eBPF programs */ -- cgit v1.2.3 From d056a788765e67773124f520159185bc89f5d1ad Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jun 2016 22:47:13 +0200 Subject: bpf, maps: extend map_fd_get_ptr arguments This patch extends map_fd_get_ptr() callback that is used by fd array maps, so that struct file pointer from the related map can be passed in. It's safe to remove map_update_elem() callback for the two maps since this is only allowed from syscall side, but not from eBPF programs for these two map types. Like in per-cpu map case, bpf_fd_array_map_update_elem() needs to be called directly here due to the extra argument. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 29b5a1ae22cb..d7b43e73fe87 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -29,8 +29,9 @@ struct bpf_map_ops { int (*map_delete_elem)(struct bpf_map *map, void *key); /* funcs called by prog_array and perf_event_array map */ - void *(*map_fd_get_ptr) (struct bpf_map *map, int fd); - void (*map_fd_put_ptr) (void *ptr); + void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, + int fd); + void (*map_fd_put_ptr)(void *ptr); }; struct bpf_map { @@ -169,7 +170,7 @@ struct bpf_array { u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -void bpf_fd_array_map_clear(struct bpf_map *map); + bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -207,8 +208,13 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); + int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); +int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, + void *key, void *value, u64 map_flags); +void bpf_fd_array_map_clear(struct bpf_map *map); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent -- cgit v1.2.3 From 3b1efb196eee45b2f0c4994e0c43edb5e367f620 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jun 2016 22:47:14 +0200 Subject: bpf, maps: flush own entries on perf map release The behavior of perf event arrays are quite different from all others as they are tightly coupled to perf event fds, f.e. shown recently by commit e03e7ee34fdd ("perf/bpf: Convert perf_event_array to use struct file") to make refcounting on perf event more robust. A remaining issue that the current code still has is that since additions to the perf event array take a reference on the struct file via perf_event_get() and are only released via fput() (that cleans up the perf event eventually via perf_event_release_kernel()) when the element is either manually removed from the map from user space or automatically when the last reference on the perf event map is dropped. However, this leads us to dangling struct file's when the map gets pinned after the application owning the perf event descriptor exits, and since the struct file reference will in such case only be manually dropped or via pinned file removal, it leads to the perf event living longer than necessary, consuming needlessly resources for that time. Relations between perf event fds and bpf perf event map fds can be rather complex. F.e. maps can act as demuxers among different perf event fds that can possibly be owned by different threads and based on the index selection from the program, events get dispatched to one of the per-cpu fd endpoints. One perf event fd (or, rather a per-cpu set of them) can also live in multiple perf event maps at the same time, listening for events. Also, another requirement is that perf event fds can get closed from application side after they have been attached to the perf event map, so that on exit perf event map will take care of dropping their references eventually. Likewise, when such maps are pinned, the intended behavior is that a user application does bpf_obj_get(), puts its fds in there and on exit when fd is released, they are dropped from the map again, so the map acts rather as connector endpoint. This also makes perf event maps inherently different from program arrays as described in more detail in commit c9da161c6517 ("bpf: fix clearing on persistent program array maps"). To tackle this, map entries are marked by the map struct file that added the element to the map. And when the last reference to that map struct file is released from user space, then the tracked entries are purged from the map. This is okay, because new map struct files instances resp. frontends to the anon inode are provided via bpf_map_new_fd() that is called when we invoke bpf_obj_get_user() for retrieving a pinned map, but also when an initial instance is created via map_create(). The rest is resolved by the vfs layer automatically for us by keeping reference count on the map's struct file. Any concurrent updates on the map slot are fine as well, it just means that perf_event_fd_array_release() needs to delete less of its own entires. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d7b43e73fe87..9adfef694a25 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -13,6 +13,7 @@ #include #include +struct perf_event; struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ @@ -166,8 +167,16 @@ struct bpf_array { void __percpu *pptrs[0] __aligned(8); }; }; + #define MAX_TAIL_CALL_CNT 32 +struct bpf_event_entry { + struct perf_event *event; + struct file *perf_file; + struct file *map_file; + struct rcu_head rcu; +}; + u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -- 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 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 431 insertions(+), 5 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 -- 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 --- include/asm-generic/atomic.h | 2 -- include/linux/atomic.h | 21 --------------------- 2 files changed, 23 deletions(-) (limited to 'include') 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 ---------- 1 file changed, 10 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 -- cgit v1.2.3 From 0db5c79989de2c68d5abb7ba891bfdb3cd3b7e05 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 16 Jun 2016 08:04:40 -0300 Subject: [media] media-devnode.h: Fix documentation Two parameters were documented with a wrong name, and a struct device pointer description was missing. That caused the following warnings, when building documentation: include/media/media-devnode.h:102: warning: No description found for parameter 'media_dev' include/media/media-devnode.h:126: warning: No description found for parameter 'mdev' include/media/media-devnode.h:126: warning: Excess function parameter 'media_dev' description in 'media_devnode_register' Rename the description, to match the function parameter and fix Documentation. No funcional changes. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-devnode.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/media-devnode.h b/include/media/media-devnode.h index f0b7dd79fb92..37d494805944 100644 --- a/include/media/media-devnode.h +++ b/include/media/media-devnode.h @@ -69,8 +69,9 @@ struct media_file_operations { /** * struct media_devnode - Media device node + * @media_dev: pointer to struct &media_device * @fops: pointer to struct &media_file_operations with media device ops - * @dev: struct device pointer for the media controller device + * @dev: pointer to struct &device containing the media controller device * @cdev: struct cdev pointer character device * @parent: parent device * @minor: device node minor number @@ -107,7 +108,7 @@ struct media_devnode { /** * media_devnode_register - register a media device node * - * @media_dev: struct media_device we want to register a device node + * @mdev: struct media_device we want to register a device node * @devnode: media device node structure we want to register * @owner: should be filled with %THIS_MODULE * -- cgit v1.2.3 From 39dd0f234fc37da071dadbd9b49fe800d62139b4 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Mon, 30 May 2016 11:43:07 +0200 Subject: PM / Domains: Allow genpd to power on during system PM phases If a PM domain is powered off when the first device starts its system PM prepare phase, genpd prevents any further attempts to power on the PM domain during the following system PM phases. Not until the system PM complete phase is finalized for all devices in the PM domain, genpd again allows it to be powered on. This behaviour needs to be changed, as a subsystem/driver for a device in the same PM domain may still need to be able to serve requests in some of the system PM phases. Accordingly, it may need to runtime resume its device and thus also request the corresponding PM domain to be powered on. To deal with these scenarios, let's make the device operational in the system PM prepare phase by runtime resuming it, no matter if the PM domain is powered on or off. Changing this also enables us to remove genpd's suspend_power_off flag, as it's being used to track this condition. Additionally, we must allow the PM domain to be powered on via runtime PM during the system PM phases. This change also requires a fix in the AMD ACP (Audio CoProcessor) drm driver. It registers a genpd to model the ACP as a PM domain, but unfortunately it's also abuses genpd's "internal" suspend_power_off flag to deal with a corner case at system PM resume. More precisely, the so called SMU block powers on the ACP at system PM resume, unconditionally if it's being used or not. This may lead to that genpd's internal status of the power state, may not correctly reflect the power state of the HW after a system PM resume. Because of changing the behaviour of genpd, by runtime resuming devices in the prepare phase, the AMD ACP drm driver no longer have to deal with this corner case. So let's just drop the related code in this driver. Signed-off-by: Ulf Hansson Reviewed-by: Kevin Hilman Acked-by: Maruthi Bayyavarapu Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 39285c7bd3f5..dd5b0447d572 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -57,7 +57,6 @@ struct generic_pm_domain { unsigned int device_count; /* Number of devices */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ - bool suspend_power_off; /* Power status before system suspend */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); struct gpd_dev_ops dev_ops; -- cgit v1.2.3 From 5fb384b066d7c320832c4541658e5c655c590ac5 Mon Sep 17 00:00:00 2001 From: Fabien Siron Date: Wed, 15 Jun 2016 15:37:49 +0000 Subject: netlink: Add comment to warn about deprecated netlink rings attribute request Signed-off-by: Fabien Siron Signed-off-by: David S. Miller --- include/uapi/linux/netlink_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h index d79399394b46..76b4d87c83a8 100644 --- a/include/uapi/linux/netlink_diag.h +++ b/include/uapi/linux/netlink_diag.h @@ -49,6 +49,7 @@ enum { #define NDIAG_SHOW_MEMINFO 0x00000001 /* show memory info of a socket */ #define NDIAG_SHOW_GROUPS 0x00000002 /* show groups of a netlink socket */ #ifndef __KERNEL__ +/* deprecated since 4.6 */ #define NDIAG_SHOW_RING_CFG 0x00000004 /* show ring configuration */ #endif -- cgit v1.2.3 From cecbc5563a02289164fa6379130243cbe08b2dd6 Mon Sep 17 00:00:00 2001 From: Vincent Palatin Date: Wed, 15 Jun 2016 11:32:21 -0700 Subject: net: stmmac: allow to split suspend/resume from init/exit callbacks Let the stmmac platform drivers provide dedicated suspend and resume callbacks rather than always re-using the init and exits callbacks. If the driver does not provide the suspend or resume callback, we fall back to the old behavior trying to use exit or init. This allows a specific platform to perform only a partial power-down on suspend if Wake-on-Lan is enabled but always perform the full shutdown sequence if the module is unloaded. Signed-off-by: Vincent Palatin Signed-off-by: David S. Miller --- include/linux/stmmac.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index ffdaca9c01af..0507dbfbf63c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -135,6 +135,8 @@ struct plat_stmmacenet_data { void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); + void (*suspend)(struct platform_device *pdev, void *priv); + void (*resume)(struct platform_device *pdev, void *priv); void *bsp_priv; struct stmmac_axi *axi; int has_gmac4; -- cgit v1.2.3 From b4f210541fc319bd643ad9a4fdbfe2ce31be6cfc Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 9 Jun 2016 16:53:47 +0200 Subject: i2c: add a protocol parameter to the alert callback .alert() is meant to be generic, but there is currently no way for the device driver to know which protocol generated the alert. Add a parameter in .alert() to help the device driver to understand what is given in data. This patch is required to have the support of SMBus Host Notify protocol through .alert(). Tested-by: Andrew Duggan For hwmon: Acked-by: Guenter Roeck For IPMI: Acked-by: Corey Minyard Signed-off-by: Benjamin Tissoires Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 6df7bad8c26c..37a45dcd6592 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -126,6 +126,10 @@ i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, u8 command, u8 length, u8 *values); #endif /* I2C */ +enum i2c_alert_protocol { + I2C_PROTOCOL_SMBUS_ALERT, +}; + /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) @@ -181,7 +185,8 @@ struct i2c_driver { * For the SMBus alert protocol, there is a single bit of data passed * as the alert response's low bit ("event flag"). */ - void (*alert)(struct i2c_client *, unsigned int data); + void (*alert)(struct i2c_client *, enum i2c_alert_protocol protocol, + unsigned int data); /* a ioctl like command that can be used to perform specific functions * with the device. -- cgit v1.2.3 From 7b49235e83b2347caf4bc66dd0154cb799bd7405 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Thu, 11 Feb 2016 22:29:58 -0200 Subject: [media] v4l: Add Renesas R-Car FCP driver The FCP is a companion module of video processing modules in the Renesas R-Car Gen3 SoCs. It provides data compression and decompression, data caching, and conversion of AXI transactions in order to reduce the memory bandwidth. The driver is not meant to be used standalone but provides an API to the video processing modules to control the FCP. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/rcar-fcp.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/media/rcar-fcp.h (limited to 'include') diff --git a/include/media/rcar-fcp.h b/include/media/rcar-fcp.h new file mode 100644 index 000000000000..4c7fc77eaf29 --- /dev/null +++ b/include/media/rcar-fcp.h @@ -0,0 +1,37 @@ +/* + * rcar-fcp.h -- R-Car Frame Compression Processor Driver + * + * Copyright (C) 2016 Renesas Electronics Corporation + * + * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef __MEDIA_RCAR_FCP_H__ +#define __MEDIA_RCAR_FCP_H__ + +struct device_node; +struct rcar_fcp_device; + +#if IS_ENABLED(CONFIG_VIDEO_RENESAS_FCP) +struct rcar_fcp_device *rcar_fcp_get(const struct device_node *np); +void rcar_fcp_put(struct rcar_fcp_device *fcp); +int rcar_fcp_enable(struct rcar_fcp_device *fcp); +void rcar_fcp_disable(struct rcar_fcp_device *fcp); +#else +static inline struct rcar_fcp_device *rcar_fcp_get(const struct device_node *np) +{ + return ERR_PTR(-ENOENT); +} +static inline void rcar_fcp_put(struct rcar_fcp_device *fcp) { } +static inline int rcar_fcp_enable(struct rcar_fcp_device *fcp) +{ + return -ENOSYS; +} +static inline void rcar_fcp_disable(struct rcar_fcp_device *fcp) { } +#endif + +#endif /* __MEDIA_RCAR_FCP_H__ */ -- cgit v1.2.3 From c6b013ab517b0ae09036d50f6b1684d9dbedf596 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sat, 23 Apr 2016 19:08:59 -0300 Subject: [media] v4l: vsp1: Group DRM RPF parameters in a structure The vsp1_du_atomic_update_ext() function takes 7 RPF configuration parameters, and more will likely be added later. This makes the code difficult to read and error-prone as multiple parameters have the same type. Make the API safer and easier to extend in the future by grouping all parameters in a structure. Use macro magic to ease the transition to the new function by allowing the old and new functions to be called using the same name. The macros and static inline wrapper will be removed as soon as the caller is updated. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/vsp1.h | 47 ++++++++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/media/vsp1.h b/include/media/vsp1.h index 3e654a0455bd..ea8ad7537057 100644 --- a/include/media/vsp1.h +++ b/include/media/vsp1.h @@ -14,31 +14,52 @@ #define __MEDIA_VSP1_H__ #include +#include struct device; -struct v4l2_rect; int vsp1_du_init(struct device *dev); int vsp1_du_setup_lif(struct device *dev, unsigned int width, unsigned int height); +struct vsp1_du_atomic_config { + u32 pixelformat; + unsigned int pitch; + dma_addr_t mem[2]; + struct v4l2_rect src; + struct v4l2_rect dst; + unsigned int alpha; + unsigned int zpos; +}; + void vsp1_du_atomic_begin(struct device *dev); -int vsp1_du_atomic_update_ext(struct device *dev, unsigned int rpf, - u32 pixelformat, unsigned int pitch, - dma_addr_t mem[2], const struct v4l2_rect *src, - const struct v4l2_rect *dst, unsigned int alpha, - unsigned int zpos); +int __vsp1_du_atomic_update(struct device *dev, unsigned int rpf, + const struct vsp1_du_atomic_config *cfg); void vsp1_du_atomic_flush(struct device *dev); -static inline int vsp1_du_atomic_update(struct device *dev, - unsigned int rpf_index, u32 pixelformat, - unsigned int pitch, dma_addr_t mem[2], - const struct v4l2_rect *src, - const struct v4l2_rect *dst) +static inline int vsp1_du_atomic_update_old(struct device *dev, + unsigned int rpf, u32 pixelformat, unsigned int pitch, + dma_addr_t mem[2], const struct v4l2_rect *src, + const struct v4l2_rect *dst) { - return vsp1_du_atomic_update_ext(dev, rpf_index, pixelformat, pitch, - mem, src, dst, 255, 0); + struct vsp1_du_atomic_config cfg = { + .pixelformat = pixelformat, + .pitch = pitch, + .mem[0] = mem[0], + .mem[1] = mem[1], + .src = *src, + .dst = *dst, + .alpha = 255, + .zpos = 0, + }; + + return __vsp1_du_atomic_update(dev, rpf, &cfg); } +#define _vsp1_du_atomic_update(_1, _2, _3, _4, _5, _6, _7, f, ...) f +#define vsp1_du_atomic_update(...) \ + _vsp1_du_atomic_update(__VA_ARGS__, vsp1_du_atomic_update_old, 0, 0, \ + 0, __vsp1_du_atomic_update)(__VA_ARGS__) + #endif /* __MEDIA_VSP1_H__ */ -- cgit v1.2.3 From e456cd37bc28abe47dc65189df916ac0510ac1d4 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 9 Jun 2016 16:53:48 +0200 Subject: i2c: smbus: add SMBus Host Notify support SMBus Host Notify allows a slave device to act as a master on a bus to notify the host of an interrupt. On Intel chipsets, the functionality is directly implemented in the firmware. We just need to export a function to call .alert() on the proper device driver. i2c_handle_smbus_host_notify() behaves like i2c_handle_smbus_alert(). When called, it schedules a task that will be able to sleep to go through the list of devices attached to the adapter. The current implementation allows one Host Notification to be scheduled while an other is running. Tested-by: Andrew Duggan Signed-off-by: Benjamin Tissoires Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/i2c.h | 3 +++ include/uapi/linux/i2c.h | 1 + 3 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 8f1b086ca5bc..4ac95bbe53ef 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -23,6 +23,8 @@ #define _LINUX_I2C_SMBUS_H #include +#include +#include /** @@ -48,4 +50,46 @@ struct i2c_client *i2c_setup_smbus_alert(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); +/** + * smbus_host_notify - internal structure used by the Host Notify mechanism. + * @adapter: the I2C adapter associated with this struct + * @work: worker used to schedule the IRQ in the slave device + * @lock: spinlock to check if a notification is already pending + * @pending: flag set when a notification is pending (any new notification will + * be rejected if pending is true) + * @payload: the actual payload of the Host Notify event + * @addr: the address of the slave device which raised the notification + * + * This struct needs to be allocated by i2c_setup_smbus_host_notify() and does + * not need to be freed. Internally, i2c_setup_smbus_host_notify() uses a + * managed resource to clean this up when the adapter get released. + */ +struct smbus_host_notify { + struct i2c_adapter *adapter; + struct work_struct work; + spinlock_t lock; + bool pending; + u16 payload; + u8 addr; +}; + +#if IS_ENABLED(CONFIG_I2C_SMBUS) +struct smbus_host_notify *i2c_setup_smbus_host_notify(struct i2c_adapter *adap); +int i2c_handle_smbus_host_notify(struct smbus_host_notify *host_notify, + unsigned short addr, unsigned int data); +#else +static inline struct smbus_host_notify * +i2c_setup_smbus_host_notify(struct i2c_adapter *adap) +{ + return NULL; +} + +static inline int +i2c_handle_smbus_host_notify(struct smbus_host_notify *host_notify, + unsigned short addr, unsigned int data) +{ + return 0; +} +#endif /* I2C_SMBUS */ + #endif /* _LINUX_I2C_SMBUS_H */ diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 37a45dcd6592..fffdc270ca18 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -128,6 +128,7 @@ i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, enum i2c_alert_protocol { I2C_PROTOCOL_SMBUS_ALERT, + I2C_PROTOCOL_SMBUS_HOST_NOTIFY, }; /** @@ -184,6 +185,8 @@ struct i2c_driver { * The format and meaning of the data value depends on the protocol. * For the SMBus alert protocol, there is a single bit of data passed * as the alert response's low bit ("event flag"). + * For the SMBus Host Notify protocol, the data corresponds to the + * 16-bit payload data reported by the slave device acting as master. */ void (*alert)(struct i2c_client *, enum i2c_alert_protocol protocol, unsigned int data); diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index adcbef4bff61..009e27bb9abe 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -102,6 +102,7 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ +#define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) -- cgit v1.2.3 From 6f3b911d5f29b98752e5da86a295210c0c4f4e14 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 17 Jun 2016 15:35:27 +0200 Subject: can: bcm: add support for CAN FD frames The programming API of the CAN_BCM depends on struct can_frame which is given as array directly behind the bcm_msg_head structure. To follow this schema for the CAN FD frames a new flag 'CAN_FD_FRAME' in the bcm_msg_head flags indicates that the concatenated CAN frame structures behind the bcm_msg_head are defined as struct canfd_frame. This patch adds the support to handle CAN and CAN FD frames on a per BCM-op base. Main changes: - generally use struct canfd_frames instead if struct can_frames - use canfd_frame.flags instead of can_frame.can_dlc for private BCM flags - make all CAN frame sizes depending on the new CAN_FD_FRAME flags - separate between CAN and CAN FD when sending/receiving frames Due to the dependence of the CAN_FD_FRAME flag the former binary interface for classic CAN frames remains stable. Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/bcm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 7a291dc1ff15..cefb304414ba 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -99,5 +99,6 @@ enum { #define RX_ANNOUNCE_RESUME 0x0100 #define TX_RESET_MULTI_IDX 0x0200 #define RX_RTR_FRAME 0x0400 +#define CAN_FD_FRAME 0x0800 #endif /* !_UAPI_CAN_BCM_H */ -- cgit v1.2.3 From e452b818db48dc2c7edb5afd62de47ae0363aec2 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 9 Jun 2016 17:47:17 +0200 Subject: clk: tegra: Enable sor1 and sor1_src on Tegra210 Make the sor1 and sor1_src clocks available on Tegra210. They will be used by the display driver to support HDMI and DP. Signed-off-by: Thierry Reding --- include/dt-bindings/clock/tegra210-car.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h index bd3530e56d46..35288b20f2c9 100644 --- a/include/dt-bindings/clock/tegra210-car.h +++ b/include/dt-bindings/clock/tegra210-car.h @@ -308,7 +308,7 @@ #define TEGRA210_CLK_CLK_OUT_3 279 #define TEGRA210_CLK_BLINK 280 /* 281 */ -/* 282 */ +#define TEGRA210_CLK_SOR1_SRC 282 /* 283 */ #define TEGRA210_CLK_XUSB_HOST_SRC 284 #define TEGRA210_CLK_XUSB_FALCON_SRC 285 -- cgit v1.2.3 From 8221a013528597edc18d371b22667e8eefca599b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 17 Jun 2016 14:43:34 -0500 Subject: PCI: Unify pci_resource_to_user() declarations Replace the pci_resource_to_user() declarations in each arch that defines HAVE_ARCH_PCI_RESOURCE_TO_USER with a single one in linux/pci.h. Change the MIPS static inline implementation to a non-inline version so the static inline doesn't conflict with the new non-static linux/pci.h declaration. No functional change intended. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..9c201d4dbd51 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1554,7 +1554,11 @@ static inline const char *pci_name(const struct pci_dev *pdev) /* Some archs don't want to expose struct resource to userland as-is * in sysfs and /proc */ -#ifndef HAVE_ARCH_PCI_RESOURCE_TO_USER +#ifdef HAVE_ARCH_PCI_RESOURCE_TO_USER +void pci_resource_to_user(const struct pci_dev *dev, int bar, + const struct resource *rsrc, + resource_size_t *start, resource_size_t *end); +#else static inline void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, resource_size_t *start, resource_size_t *end) -- cgit v1.2.3 From 224abb67e6eb5ac062de9239163136d5ec3155c8 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 17 Jun 2016 15:23:52 -0500 Subject: PCI: Document connection between pci_power_t and hardware PM capability The dev.pme_support field, pci_pm_init(), pci_pme_capable(), and pci_raw_set_power_state() depend on the fact that the pci_power_t values (PCI_D0, PCI_D1, etc.) match the definition of the Capabilities PME_Support and the Control/Status PowerState fields in the Power Management capability (see PCI Bus Power Management spec r1.2, sec 3.2.3). Add a note to this effect at the pci_power_t typedef. Signed-off-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg --- include/linux/pci.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 8597b423cb63..0a1a9e30359c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -101,6 +101,10 @@ enum { DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES, }; +/* + * pci_power_t values must match the bits in the Capabilities PME_Support + * and Control/Status PowerState fields in the Power Management capability. + */ typedef int __bitwise pci_power_t; #define PCI_D0 ((pci_power_t __force) 0) -- cgit v1.2.3 From 70f4f9352317ed8bc70cd7fe2bf34a3f9f7f21e3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 17 Jun 2016 16:48:17 +0200 Subject: ia64: efi: use timespec64 for persistent clock We have a generic read_persistent_clock64 interface now, and can change the ia64 implementation to provide that instead of read_persistent_clock. The main point of this is to avoid the use of struct timespec in the global efi.h, which would cause build errors as soon as we want to build a kernel without 'struct timespec' defined on 32-bit architectures. Aside from this, we get a little closer to removing the __weak read_persistent_clock() definition, which relies on converting all architectures to provide read_persistent_clock64 instead. Signed-off-by: Arnd Bergmann Signed-off-by: Tony Luck --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/efi.h b/include/linux/efi.h index f196dd0b0f2f..acb6adace01e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -937,7 +937,7 @@ extern void efi_init (void); extern void *efi_get_pal_addr (void); extern void efi_map_pal_code (void); extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg); -extern void efi_gettimeofday (struct timespec *ts); +extern void efi_gettimeofday (struct timespec64 *ts); extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #ifdef CONFIG_X86 extern void efi_late_init(void); -- cgit v1.2.3 From 86a98057256020e75e1be0f88d7617491a06e8f1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 16 Jun 2016 12:20:44 -0700 Subject: vxlan/geneve: Include udp_tunnel.h in vxlan/geneve.h and fixup includes This patch makes it so that we add udp_tunnel.h to vxlan.h and geneve.h header files. This is useful as I plan to move the generic handlers for the port offloads into the udp_tunnel header file and leave the vxlan and geneve headers to be a bit more protocol specific. I also went through and cleaned out a number of redundant includes that where in the .h and .c files for these drivers. Signed-off-by: Alexander Duyck Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/geneve.h | 3 --- include/net/udp_tunnel.h | 2 ++ include/net/vxlan.h | 6 +----- 3 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/geneve.h b/include/net/geneve.h index cb544a530146..f8aff18d6702 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -1,10 +1,7 @@ #ifndef __NET_GENEVE_H #define __NET_GENEVE_H 1 -#ifdef CONFIG_INET #include -#endif - /* Geneve Header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 9d14f707e534..59019562d14c 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -105,12 +105,14 @@ struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); +#ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } +#endif static inline void udp_tunnel_encap_enable(struct socket *sock) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b8803165df91..7d944941f32f 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -1,12 +1,8 @@ #ifndef __NET_VXLAN_H #define __NET_VXLAN_H 1 -#include -#include #include -#include -#include -#include +#include #include /* VXLAN protocol (RFC 7348) header: -- cgit v1.2.3 From e7b3db5e60e8f471c3f5ef93b497bafe5863e56a Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 16 Jun 2016 12:20:52 -0700 Subject: net: Combine GENEVE and VXLAN port notifiers into single functions This patch merges the GENEVE and VXLAN code so that both functions pass through a shared code path. This way we can start the effort of using a single function on the network device drivers to handle both of these tunnel types. Signed-off-by: Alexander Duyck Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/udp_tunnel.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include') diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 59019562d14c..71afbea873a0 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -84,6 +84,39 @@ struct udp_tunnel_sock_cfg { void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); +/* -- List of parsable UDP tunnel types -- + * + * Adding to this list will result in serious debate. The main issue is + * that this list is essentially a list of workarounds for either poorly + * designed tunnels, or poorly designed device offloads. + * + * The parsing supported via these types should really be used for Rx + * traffic only as the network stack will have already inserted offsets for + * the location of the headers in the skb. In addition any ports that are + * pushed should be kept within the namespace without leaking to other + * devices such as VFs or other ports on the same device. + * + * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the + * need to use this for Rx checksum offload. It should not be necessary to + * call this function to perform Tx offloads on outgoing traffic. + */ +enum udp_parsable_tunnel_type { + UDP_TUNNEL_TYPE_VXLAN, /* RFC 7348 */ + UDP_TUNNEL_TYPE_GENEVE, /* draft-ietf-nvo3-geneve */ +}; + +struct udp_tunnel_info { + unsigned short type; + sa_family_t sa_family; + __be16 port; +}; + +/* Notify network devices of offloadable types */ +void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, + unsigned short type); +void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); +void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); + /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, -- cgit v1.2.3 From 7c46a640de6fcc4f35d0702710356a024eadf68f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 16 Jun 2016 12:21:00 -0700 Subject: net: Merge VXLAN and GENEVE push notifiers into a single notifier This patch merges the notifiers for VXLAN and GENEVE into a single UDP tunnel notifier. The idea is that we will want to only have to make one notifier call to receive the list of ports for VXLAN and GENEVE tunnels that need to be offloaded. In addition we add a new set of ndo functions named ndo_udp_tunnel_add and ndo_udp_tunnel_del that are meant to allow us to track the tunnel meta-data such as port and address family as tunnels are added and removed. The tunnel meta-data is now transported in a structure named udp_tunnel_info which for now carries the type, address family, and port number. In the future this could be updated so that we can include a tuple of values including things such as the destination IP address and other fields. I also ended up going with a naming scheme that consisted of using the prefix udp_tunnel on function names. I applied this to the notifier and ndo ops as well so that it hopefully points to the fact that these are primarily used in the udp_tunnel functions. Signed-off-by: Alexander Duyck Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 ++++++++++++++++++++-- include/net/geneve.h | 3 +-- include/net/udp_tunnel.h | 6 ++++++ include/net/vxlan.h | 4 ++-- 4 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 890158e99159..577d2a1814b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -61,6 +61,8 @@ struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; struct mpls_dev; +/* UDP Tunnel offloads */ +struct udp_tunnel_info; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1050,6 +1052,19 @@ struct tc_to_netdev { * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. * + * void (*ndo_udp_tunnel_add)(struct net_device *dev, + * struct udp_tunnel_info *ti); + * Called by UDP tunnel to notify a driver about the UDP port and socket + * address family that a UDP tunnel is listnening to. It is called only + * when a new port starts listening. The operation is protected by the + * RTNL. + * + * void (*ndo_udp_tunnel_del)(struct net_device *dev, + * struct udp_tunnel_info *ti); + * Called by UDP tunnel to notify the driver about a UDP port and socket + * address family that the UDP tunnel is not listening to anymore. The + * operation is protected by the RTNL. + * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other @@ -1269,6 +1284,10 @@ struct net_device_ops { void (*ndo_del_geneve_port)(struct net_device *dev, sa_family_t sa_family, __be16 port); + void (*ndo_udp_tunnel_add)(struct net_device *dev, + struct udp_tunnel_info *ti); + void (*ndo_udp_tunnel_del)(struct net_device *dev, + struct udp_tunnel_info *ti); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, @@ -2255,8 +2274,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_BONDING_INFO 0x0019 #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B -#define NETDEV_OFFLOAD_PUSH_VXLAN 0x001C -#define NETDEV_OFFLOAD_PUSH_GENEVE 0x001D +#define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); diff --git a/include/net/geneve.h b/include/net/geneve.h index f8aff18d6702..3410c4b5a382 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -61,8 +61,7 @@ struct genevehdr { static inline void geneve_get_rx_port(struct net_device *netdev) { - ASSERT_RTNL(); - call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_GENEVE, netdev); + udp_tunnel_get_rx_info(netdev); } #ifdef CONFIG_INET diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 71afbea873a0..1c9408a04213 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -117,6 +117,12 @@ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); +static inline void udp_tunnel_get_rx_info(struct net_device *dev) +{ + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); +} + /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 7d944941f32f..c62e2ed1c3af 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -4,6 +4,7 @@ #include #include #include +#include /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ @@ -390,8 +391,7 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) static inline void vxlan_get_rx_port(struct net_device *netdev) { - ASSERT_RTNL(); - call_netdevice_notifiers(NETDEV_OFFLOAD_PUSH_VXLAN, netdev); + udp_tunnel_get_rx_info(netdev); } static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) -- cgit v1.2.3 From 1938ee1fd3de74d761a60806b048df652666afec Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 16 Jun 2016 12:23:12 -0700 Subject: net: Remove deprecated tunnel specific UDP offload functions Now that we have all the drivers using udp_tunnel_get_rx_ports, ndo_add_udp_enc_rx_port, and ndo_del_udp_enc_rx_port we can drop the function calls that were specific to VXLAN and GENEVE. Signed-off-by: Alexander Duyck Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/netdevice.h | 38 -------------------------------------- include/net/geneve.h | 5 ----- include/net/vxlan.h | 5 ----- 3 files changed, 48 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 577d2a1814b1..e84d9d23c2d5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1026,32 +1026,6 @@ struct tc_to_netdev { * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * - * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); - * Called by vxlan to notify a driver about the UDP port and socket - * address family that vxlan is listening to. It is called only when - * a new port starts listening. The operation is protected by the - * vxlan_net->sock_lock. - * - * void (*ndo_add_geneve_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); - * Called by geneve to notify a driver about the UDP port and socket - * address family that geneve is listnening to. It is called only when - * a new port starts listening. The operation is protected by the - * geneve_net->sock_lock. - * - * void (*ndo_del_geneve_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); - * Called by geneve to notify the driver about a UDP port and socket - * address family that geneve is not listening to anymore. The operation - * is protected by the geneve_net->sock_lock. - * - * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __be16 port); - * Called by vxlan to notify the driver about a UDP port and socket - * address family that vxlan is not listening to anymore. The operation - * is protected by the vxlan_net->sock_lock. - * * void (*ndo_udp_tunnel_add)(struct net_device *dev, * struct udp_tunnel_info *ti); * Called by UDP tunnel to notify a driver about the UDP port and socket @@ -1272,18 +1246,6 @@ struct net_device_ops { struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); - void (*ndo_add_vxlan_port)(struct net_device *dev, - sa_family_t sa_family, - __be16 port); - void (*ndo_del_vxlan_port)(struct net_device *dev, - sa_family_t sa_family, - __be16 port); - void (*ndo_add_geneve_port)(struct net_device *dev, - sa_family_t sa_family, - __be16 port); - void (*ndo_del_geneve_port)(struct net_device *dev, - sa_family_t sa_family, - __be16 port); void (*ndo_udp_tunnel_add)(struct net_device *dev, struct udp_tunnel_info *ti); void (*ndo_udp_tunnel_del)(struct net_device *dev, diff --git a/include/net/geneve.h b/include/net/geneve.h index 3410c4b5a382..ec0327d4331b 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -59,11 +59,6 @@ struct genevehdr { struct geneve_opt options[]; }; -static inline void geneve_get_rx_port(struct net_device *netdev) -{ - udp_tunnel_get_rx_info(netdev); -} - #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index c62e2ed1c3af..b96d0360c095 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -389,11 +389,6 @@ static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) return vni_field; } -static inline void vxlan_get_rx_port(struct net_device *netdev) -{ - udp_tunnel_get_rx_info(netdev); -} - static inline unsigned short vxlan_get_sk_family(struct vxlan_sock *vs) { return vs->sock->sk->sk_family; -- cgit v1.2.3 From b9adcd69bd7b41625201686b4cfec7ff13357afc Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 16 Jun 2016 12:23:19 -0700 Subject: vxlan: Add new UDP encapsulation offload type for VXLAN-GPE The fact is VXLAN with Generic Protocol Extensions cannot be supported by the same hardware parsers that support VXLAN. The protocol extensions allow for things like a Next Protocol field which in turn allows for things other than Ethernet to be passed over the tunnel. Most existing parsers will not know how to interpret this. To resolve this I am giving VXLAN-GPE its own UDP encapsulation offload type. This way hardware that does support GPE can simply add this type to the switch statement for VXLAN, and if they don't support it then this will fix any issues where headers might be interpreted incorrectly. Signed-off-by: Alexander Duyck Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/udp_tunnel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 1c9408a04213..02c5be037451 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -103,6 +103,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN, /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE, /* draft-ietf-nvo3-geneve */ + UDP_TUNNEL_TYPE_VXLAN_GPE, /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { -- 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 --- include/linux/fence.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') 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 a2e2ff560f5113e8ca31432fbd985f5f1889efdc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 16 Jun 2016 16:24:24 -0700 Subject: net: ipv6: Move ip6_route_get_saddr to inline VRF driver needs access to ip6_route_get_saddr code. Since it does little beyond ipv6_dev_get_saddr and ipv6_dev_get_saddr is already exported for modules move ip6_route_get_saddr to the header as an inline. Code move only; no functional change. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_route.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f55bf3d294aa..d97305d0e71f 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -18,6 +18,7 @@ struct route_info { __u8 prefix[0]; /* 0,8 or 16 */ }; +#include #include #include #include @@ -88,9 +89,23 @@ int ip6_route_add(struct fib6_config *cfg); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); -int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, - const struct in6_addr *daddr, unsigned int prefs, - struct in6_addr *saddr); +static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, + const struct in6_addr *daddr, + unsigned int prefs, + struct in6_addr *saddr) +{ + struct inet6_dev *idev = + rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL; + int err = 0; + + if (rt && rt->rt6i_prefsrc.plen) + *saddr = rt->rt6i_prefsrc.addr; + else + err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, + daddr, prefs, saddr); + + return err; +} struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, int flags); -- cgit v1.2.3 From 0d240e7811c4ec1965760ee4643b5bbc9cfacbb3 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 16 Jun 2016 16:24:25 -0700 Subject: net: vrf: Implement get_saddr for IPv6 IPv6 source address selection needs to consider the real egress route. Similar to IPv4 implement a get_saddr6 method which is called if source address has not been set. The get_saddr6 method does a full lookup which means pulling a route from the VRF FIB table and properly considering linklocal/multicast destination addresses. Lookup failures (eg., unreachable) then cause the source address selection to fail which gets propagated back to the caller. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index f8a416ec674c..818fd4f100fc 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -39,6 +39,9 @@ struct l3mdev_ops { /* IPv6 ops */ struct dst_entry * (*l3mdev_get_rt6_dst)(const struct net_device *dev, struct flowi6 *fl6); + int (*l3mdev_get_saddr6)(struct net_device *dev, + const struct sock *sk, + struct flowi6 *fl6); }; #ifdef CONFIG_NET_L3_MASTER_DEV @@ -140,6 +143,8 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4); struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6); +int l3mdev_get_saddr6(struct net *net, const struct sock *sk, + struct flowi6 *fl6); static inline struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) @@ -230,6 +235,12 @@ struct dst_entry *l3mdev_get_rt6_dst(struct net *net, struct flowi6 *fl6) return NULL; } +static inline int l3mdev_get_saddr6(struct net *net, const struct sock *sk, + struct flowi6 *fl6) +{ + return 0; +} + static inline struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb) { -- cgit v1.2.3 From afbac6010aec514998214fb19a1f37732b7a1d77 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 16 Jun 2016 16:24:26 -0700 Subject: net: ipv6: Address selection needs to consider L3 domains IPv6 version of 3f2fb9a834cb ("net: l3mdev: address selection should only consider devices in L3 domain") and the follow up commit, a17b693cdd876 ("net: l3mdev: prefer VRF master for source address selection"). That is, if outbound device is given then the address preference order is an address from that device, an address from the master device if it is enslaved, and then an address from a device in the same L3 domain. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/l3mdev.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 818fd4f100fc..e90095091aa0 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -79,6 +79,31 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) return rc; } +static inline +const struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) +{ + /* netdev_master_upper_dev_get_rcu calls + * list_first_or_null_rcu to walk the upper dev list. + * list_first_or_null_rcu does not handle a const arg. We aren't + * making changes, just want the master device from that list so + * typecast to remove the const + */ + struct net_device *dev = (struct net_device *)_dev; + const struct net_device *master; + + if (!dev) + return NULL; + + if (netif_is_l3_master(dev)) + master = dev; + else if (netif_is_l3_slave(dev)) + master = netdev_master_upper_dev_get_rcu(dev); + else + master = NULL; + + return master; +} + /* get index of an interface to use for FIB lookups. For devices * enslaved to an L3 master device FIB lookups are based on the * master index @@ -190,6 +215,12 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) return 0; } +static inline +const struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) +{ + return NULL; +} + static inline int l3mdev_fib_oif_rcu(struct net_device *dev) { return dev ? dev->ifindex : 0; -- 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 + 1 file changed, 1 insertion(+) (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); -- cgit v1.2.3 From b1cadc1a0949c82ff7fcb15603e3caf2d32ff9f6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 18 Jun 2016 21:52:02 -0700 Subject: ipv6: icmp: add a force_saddr param to icmp6_send() SIT or GRE tunnels might want to translate an IPV4 address into a v4mapped one when translating ICMP to ICMPv6. This patch adds the parameter to icmp6_send() but does not change icmpv6_send() signature. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 630f45335c73..432611a297fb 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -14,7 +14,8 @@ static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) extern void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info); -typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info); +typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct in6_addr *force_saddr); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); -- cgit v1.2.3 From 5fbba8ac9358f1e796c8aedcccc3487364643723 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 18 Jun 2016 21:52:03 -0700 Subject: ip6: move ipip6_err_gen_icmpv6_unreach() We want to use this helper from GRE as well, so this is the time to move it in net/ipv6/icmp.c Also add a @nhs parameter, since SIT and GRE have different values for the header(s) to skip. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 432611a297fb..9796481edbdb 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -18,6 +18,7 @@ typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); +int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs); #else -- cgit v1.2.3 From 2d7a3b276be2d032a6c1a48ced87a474327ee3d3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 18 Jun 2016 21:52:04 -0700 Subject: ipv6: translate ICMP_TIME_EXCEEDED to ICMPV6_TIME_EXCEED For better traceroute/mtr support for SIT and GRE tunnels, we translate IPV4 ICMP ICMP_TIME_EXCEEDED to ICMPV6_TIME_EXCEED We also have to translate the IPv4 source IP address of ICMP message to IPv6 v4mapped. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 9796481edbdb..97ae98071a03 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -18,7 +18,7 @@ typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); -int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs); +int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type); #else -- cgit v1.2.3 From 9b8c6d7bf2e08a7d3eb6660a2bfaf29b8b49c329 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 18 Jun 2016 21:52:05 -0700 Subject: gre: better support for ICMP messages for gre+ipv6 ipgre_err() can call ip6_err_gen_icmpv6_unreach() for proper support of ipv4+gre+icmp+ipv6+... frames, used for example by traceroute/mtr. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 9222678426a1..a5e7035fb93f 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -157,6 +157,7 @@ struct tnl_ptk_info { __be16 proto; __be32 key; __be32 seq; + int hdr_len; }; #define PACKET_RCVD 0 -- cgit v1.2.3 From 20e1954fe238dbe5f8d3a979e593fe352bd703cf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 18 Jun 2016 21:52:06 -0700 Subject: ipv6: RFC 4884 partial support for SIT/GRE tunnels When receiving an ICMPv4 message containing extensions as defined in RFC 4884, and translating it to ICMPv6 at SIT or GRE tunnel, we need some extra manipulation in order to properly forward the extensions. This patch only takes care of Time Exceeded messages as they are the ones that typically carry information from various routers in a fabric during a traceroute session. It also avoids complex skb logic if the data_len is not a multiple of 8. RFC states : The "original datagram" field MUST contain at least 128 octets. If the original datagram did not contain 128 octets, the "original datagram" field MUST be zero padded to 128 octets. In practice routers use 128 bytes of original datagram, not more. Initial translation was added in commit ca15a078bd90 ("sit: generate icmpv6 error when receiving icmpv4 error") Signed-off-by: Eric Dumazet Cc: Oussama Ghorbel Signed-off-by: David S. Miller --- include/linux/icmpv6.h | 3 ++- include/uapi/linux/icmp.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index 97ae98071a03..57086e9fc64c 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -18,7 +18,8 @@ typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); -int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type); +int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, + unsigned int data_len); #else diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h index 16fff055f734..fddd9d736284 100644 --- a/include/uapi/linux/icmp.h +++ b/include/uapi/linux/icmp.h @@ -79,6 +79,7 @@ struct icmphdr { __be16 __unused; __be16 mtu; } frag; + __u8 reserved[4]; } un; }; -- cgit v1.2.3 From e008bb6134a6e68fd2c827a46b27d017d920de8f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 17 Jun 2016 22:03:16 +0200 Subject: quota: use time64_t internally The quota subsystem has two formats, the old v1 format using architecture specific time_t values on the on-disk format, while the v2 format (introduced in Linux 2.5.16 and 2.4.22) uses fixed 64-bit little-endian. While there is no future for the v1 format beyond y2038, the v2 format is almost there on 32-bit architectures, as both the user interface and the on-disk format use 64-bit timestamps, just not the time_t inbetween. This changes the internal representation to use time64_t, which will end up doing the right thing everywhere for v2 format. Signed-off-by: Arnd Bergmann Signed-off-by: Jan Kara --- include/linux/quota.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/quota.h b/include/linux/quota.h index 9dfb6bce8c9e..8486d27cf360 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -200,8 +200,8 @@ struct mem_dqblk { qsize_t dqb_ihardlimit; /* absolute limit on allocated inodes */ qsize_t dqb_isoftlimit; /* preferred inode limit */ qsize_t dqb_curinodes; /* current # allocated inodes */ - time_t dqb_btime; /* time limit for excessive disk use */ - time_t dqb_itime; /* time limit for excessive inode use */ + time64_t dqb_btime; /* time limit for excessive disk use */ + time64_t dqb_itime; /* time limit for excessive inode use */ }; /* -- cgit v1.2.3 From fa4191a609f219262a18dd8b02ab7dc30896b707 Mon Sep 17 00:00:00 2001 From: Phil Reid Date: Tue, 14 Jun 2016 15:36:17 +0800 Subject: leds: pca9532: Add device tree support This patch adds basic device tree support for the pca9532 LEDs. Signed-off-by: Phil Reid Signed-off-by: Jacek Anaszewski --- include/dt-bindings/leds/leds-pca9532.h | 18 ++++++++++++++++++ include/linux/leds-pca9532.h | 9 ++++----- 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 include/dt-bindings/leds/leds-pca9532.h (limited to 'include') diff --git a/include/dt-bindings/leds/leds-pca9532.h b/include/dt-bindings/leds/leds-pca9532.h new file mode 100644 index 000000000000..4d917aab7e1e --- /dev/null +++ b/include/dt-bindings/leds/leds-pca9532.h @@ -0,0 +1,18 @@ +/* + * This header provides constants for pca9532 LED bindings. + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + */ + +#ifndef _DT_BINDINGS_LEDS_PCA9532_H +#define _DT_BINDINGS_LEDS_PCA9532_H + +#define PCA9532_TYPE_NONE 0 +#define PCA9532_TYPE_LED 1 +#define PCA9532_TYPE_N2100_BEEP 2 +#define PCA9532_TYPE_GPIO 3 +#define PCA9532_LED_TIMER2 4 + +#endif /* _DT_BINDINGS_LEDS_PCA9532_H */ diff --git a/include/linux/leds-pca9532.h b/include/linux/leds-pca9532.h index b8d6fffed4d8..d215b4561180 100644 --- a/include/linux/leds-pca9532.h +++ b/include/linux/leds-pca9532.h @@ -16,6 +16,7 @@ #include #include +#include enum pca9532_state { PCA9532_OFF = 0x0, @@ -24,16 +25,14 @@ enum pca9532_state { PCA9532_PWM1 = 0x3 }; -enum pca9532_type { PCA9532_TYPE_NONE, PCA9532_TYPE_LED, - PCA9532_TYPE_N2100_BEEP, PCA9532_TYPE_GPIO }; - struct pca9532_led { u8 id; struct i2c_client *client; - char *name; + const char *name; + const char *default_trigger; struct led_classdev ldev; struct work_struct work; - enum pca9532_type type; + u32 type; enum pca9532_state state; }; -- cgit v1.2.3 From eb25cb9956cc9384b7fa0d75dec908c9fac8c444 Mon Sep 17 00:00:00 2001 From: Stephan Linz Date: Fri, 10 Jun 2016 07:59:56 +0200 Subject: leds: convert IDE trigger to common disk trigger MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch converts the IDE specific LED trigger to a generic disk activity LED trigger. The libata core is now a trigger source just like before the IDE disk driver. It's merely a replacement of the string ide by disk. The patch is taken from http://dev.gentoo.org/~josejx/ata.patch and is widely used by any ibook/powerbook owners with great satisfaction. Likewise, it is very often used successfully on different ARM platforms. Unlike the original patch, the existing 'ide-disk' trigger is still available for backward compatibility. That reduce the amount of patches in affected device trees out of the mainline kernel. For further development, the new name 'disk-activity' should be used. Cc: Joseph Jezak Cc: Jörg Sommer Cc: Richard Purdie Signed-off-by: Stephan Linz Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index e5e7f2e80a54..0aa3701f2bf4 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -325,10 +325,10 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific functions */ -#ifdef CONFIG_LEDS_TRIGGER_IDE_DISK -extern void ledtrig_ide_activity(void); +#ifdef CONFIG_LEDS_TRIGGER_DISK +extern void ledtrig_disk_activity(void); #else -static inline void ledtrig_ide_activity(void) {} +static inline void ledtrig_disk_activity(void) {} #endif #ifdef CONFIG_LEDS_TRIGGER_MTD -- cgit v1.2.3 From 53964b9ee63b7075931b8df85307c449da564b50 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Fri, 17 Jun 2016 10:30:35 +0530 Subject: crypto: sha3 - Add SHA-3 hash algorithm This patch adds the implementation of SHA3 algorithm in software and it's based on original implementation pushed in patch https://lwn.net/Articles/518415/ with additional changes to match the padding rules specified in SHA-3 specification. Signed-off-by: Jeff Garzik Signed-off-by: Raveendra Padasalagi Signed-off-by: Herbert Xu --- include/crypto/sha3.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/crypto/sha3.h (limited to 'include') diff --git a/include/crypto/sha3.h b/include/crypto/sha3.h new file mode 100644 index 000000000000..f4c9f68f5ffe --- /dev/null +++ b/include/crypto/sha3.h @@ -0,0 +1,29 @@ +/* + * Common values for SHA-3 algorithms + */ +#ifndef __CRYPTO_SHA3_H__ +#define __CRYPTO_SHA3_H__ + +#define SHA3_224_DIGEST_SIZE (224 / 8) +#define SHA3_224_BLOCK_SIZE (200 - 2 * SHA3_224_DIGEST_SIZE) + +#define SHA3_256_DIGEST_SIZE (256 / 8) +#define SHA3_256_BLOCK_SIZE (200 - 2 * SHA3_256_DIGEST_SIZE) + +#define SHA3_384_DIGEST_SIZE (384 / 8) +#define SHA3_384_BLOCK_SIZE (200 - 2 * SHA3_384_DIGEST_SIZE) + +#define SHA3_512_DIGEST_SIZE (512 / 8) +#define SHA3_512_BLOCK_SIZE (200 - 2 * SHA3_512_DIGEST_SIZE) + +struct sha3_state { + u64 st[25]; + unsigned int md_len; + unsigned int rsiz; + unsigned int rsizw; + + unsigned int partial; + u8 buf[SHA3_224_BLOCK_SIZE]; +}; + +#endif -- 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 --- include/soc/at91/at91_sfr.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/soc/at91/at91_sfr.h (limited to 'include') 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 e02fb7264d8a31dddb9a80fbde603feb502d6478 Mon Sep 17 00:00:00 2001 From: stuart hayes Date: Thu, 26 May 2016 11:38:41 -0500 Subject: nfit: add Microsoft NVDIMM DSM command set to white list Add the Microsoft _DSM command set to the white list of NVDIMM command sets. This command set is documented at: https://msdn.microsoft.com/library/windows/hardware/mt604741 Cc: Pavel Machek [pavel: fix up braces] Signed-off-by: Stuart Hayes Signed-off-by: Dan Williams --- include/uapi/linux/ndctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 309915f74492..ba5a8c79652a 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -298,6 +298,7 @@ struct nd_cmd_pkg { #define NVDIMM_FAMILY_INTEL 0 #define NVDIMM_FAMILY_HPE1 1 #define NVDIMM_FAMILY_HPE2 2 +#define NVDIMM_FAMILY_MSFT 3 #define ND_IOCTL_CALL _IOWR(ND_IOCTL, ND_CMD_CALL,\ struct nd_cmd_pkg) -- 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 +++--- 1 file changed, 3 insertions(+), 3 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 { -- 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 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (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 -- cgit v1.2.3 From 4f920843d248946545415c1bf6120942048708ed Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:54 +0900 Subject: kconfig.h: use __is_defined() to check if MODULE is defined The macro MODULE is not a config option, it is a per-file build option. So, config_enabled(MODULE) is not sensible. (There is another case in include/linux/export.h, where config_enabled() is used against a non-config option.) This commit renames some macros in include/linux/kconfig.h for the use for non-config macros and replaces config_enabled(MODULE) with __is_defined(MODULE). I am keeping config_enabled() because it is still referenced from some places, but I expect it would be deprecated in the future. Signed-off-by: Masahiro Yamada Signed-off-by: Michal Marek --- include/linux/kconfig.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index b33c7797eb57..a94b5bf57f51 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -17,10 +17,11 @@ * the last step cherry picks the 2nd arg, we get a zero. */ #define __ARG_PLACEHOLDER_1 0, -#define config_enabled(cfg) _config_enabled(cfg) -#define _config_enabled(value) __config_enabled(__ARG_PLACEHOLDER_##value) -#define __config_enabled(arg1_or_junk) ___config_enabled(arg1_or_junk 1, 0) -#define ___config_enabled(__ignored, val, ...) val +#define config_enabled(cfg) ___is_defined(cfg) +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) +#define __take_second_arg(__ignored, val, ...) val /* * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 @@ -42,7 +43,7 @@ * built-in code when CONFIG_FOO is set to 'm'. */ #define IS_REACHABLE(option) (config_enabled(option) || \ - (config_enabled(option##_MODULE) && config_enabled(MODULE))) + (config_enabled(option##_MODULE) && __is_defined(MODULE))) /* * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', -- cgit v1.2.3 From 6023d2369ba7b82b0588fd6fcdd558a6fef200ae Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:55 +0900 Subject: export.h: use __is_defined() to check if __KSYM_* is defined Here the need is for a macro that checks whether the given symbol is defined or not, which has nothing to do with config. The new macro __is_defined() is a better fit for this case. Signed-off-by: Masahiro Yamada Acked-by: Nicolas Pitre Signed-off-by: Michal Marek --- include/linux/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/export.h b/include/linux/export.h index 2f9ccbe6a639..c565f87f005e 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -82,7 +82,7 @@ extern struct module __this_module; #include #define __EXPORT_SYMBOL(sym, sec) \ - __cond_export_sym(sym, sec, config_enabled(__KSYM_##sym)) + __cond_export_sym(sym, sec, __is_defined(__KSYM_##sym)) #define __cond_export_sym(sym, sec, conf) \ ___cond_export_sym(sym, sec, conf) #define ___cond_export_sym(sym, sec, enabled) \ -- cgit v1.2.3 From 05a25c8e2c593914c18faf91dfb5ee471b79ce58 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:56 +0900 Subject: kconfig.h: use already defined macros for IS_REACHABLE() define For the same reason as commit 02d699f1f464 ("include/linux/kconfig.h: ese macros which are already defined"), it is better to use macros IS_BUILTIN() and IS_MODULE() for defining IS_REACHABLE(). Signed-off-by: Masahiro Yamada Signed-off-by: Michal Marek --- include/linux/kconfig.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index a94b5bf57f51..722c7d2c48d6 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -42,8 +42,8 @@ * This is similar to IS_ENABLED(), but returns false when invoked from * built-in code when CONFIG_FOO is set to 'm'. */ -#define IS_REACHABLE(option) (config_enabled(option) || \ - (config_enabled(option##_MODULE) && __is_defined(MODULE))) +#define IS_REACHABLE(option) (IS_BUILTIN(option) || \ + (IS_MODULE(option) && __is_defined(MODULE))) /* * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', -- cgit v1.2.3 From 5e8754fd80b0a594f720f44d32bf28c7b06ba5a6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:57 +0900 Subject: kconfig.h: allow to use IS_{ENABLE,REACHABLE} in macro expansion The typical usage of IS_ENABLED() is if (IS_ENABLED(CONFIG_FOO)) { ... } or #if IS_ENABLED(CONFIG_FOO) ... #endif The current implementation of IS_ENABLED() includes "||" operator, which works well in those expressions like above. However, there is a case where we want to evaluate a config option beyond those use cases. For example, the OF_TABLE() in include/asm-generic/vmlinux.lds.h needs to evaluate a config option in macro expansion: #define ___OF_TABLE(cfg, name) _OF_TABLE_##cfg(name) #define __OF_TABLE(cfg, name) ___OF_TABLE(cfg, name) #define OF_TABLE(cfg, name) __OF_TABLE(config_enabled(cfg), name) #define _OF_TABLE_0(name) #define _OF_TABLE_1(name) \ ... Here, we can not use IS_ENABLED() because of the "||" operator in its define. It is true config_enabled() works well, but it is a bit ambiguous to be used against config options. This commit makes IS_ENABLED() available in more generic context by calculating "or" with macro expansion only. Do likewise for IS_REACHABLE(). Signed-off-by: Masahiro Yamada Signed-off-by: Michal Marek --- include/linux/kconfig.h | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 722c7d2c48d6..15ec117ec537 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -3,6 +3,21 @@ #include +#define __ARG_PLACEHOLDER_1 0, +#define __take_second_arg(__ignored, val, ...) val + +/* + * The use of "&&" / "||" is limited in certain expressions. + * The followings enable to calculate "and" / "or" with macro expansion only. + */ +#define __and(x, y) ___and(x, y) +#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) +#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0) + +#define __or(x, y) ___or(x, y) +#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y) +#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y) + /* * Helper macros to use CONFIG_ options in C/CPP expressions. Note that * these only work with boolean and tristate options. @@ -16,12 +31,10 @@ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when * the last step cherry picks the 2nd arg, we get a zero. */ -#define __ARG_PLACEHOLDER_1 0, #define config_enabled(cfg) ___is_defined(cfg) #define __is_defined(x) ___is_defined(x) #define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) #define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) -#define __take_second_arg(__ignored, val, ...) val /* * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 @@ -42,14 +55,13 @@ * This is similar to IS_ENABLED(), but returns false when invoked from * built-in code when CONFIG_FOO is set to 'm'. */ -#define IS_REACHABLE(option) (IS_BUILTIN(option) || \ - (IS_MODULE(option) && __is_defined(MODULE))) +#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \ + __and(IS_MODULE(option), __is_defined(MODULE))) /* * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', * 0 otherwise. */ -#define IS_ENABLED(option) \ - (IS_BUILTIN(option) || IS_MODULE(option)) +#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) #endif /* __LINUX_KCONFIG_H */ -- cgit v1.2.3 From 5ee02af153661ed98b5ccdfb984d78e7a8881b56 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 14 Jun 2016 14:58:58 +0900 Subject: vmlinux.lds.h: replace config_enabled() with IS_ENABLED() The use of config_enabled() against config options is ambiguous. Now, IS_ENABLED() is implemented purely with macro expansion, so let's replace config_enabled() with IS_ENABLED(). Signed-off-by: Masahiro Yamada Signed-off-by: Michal Marek --- include/asm-generic/vmlinux.lds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 6a67ab94b553..faa4d2bf92f5 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -164,7 +164,7 @@ #define ___OF_TABLE(cfg, name) _OF_TABLE_##cfg(name) #define __OF_TABLE(cfg, name) ___OF_TABLE(cfg, name) -#define OF_TABLE(cfg, name) __OF_TABLE(config_enabled(cfg), name) +#define OF_TABLE(cfg, name) __OF_TABLE(IS_ENABLED(cfg), name) #define _OF_TABLE_0(name) #define _OF_TABLE_1(name) \ . = ALIGN(8); \ -- cgit v1.2.3 From c3f34a4bdd596127000666c17bbf8ba1c3d2d332 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Sat, 23 Apr 2016 20:11:59 -0300 Subject: [media] v4l: vsp1: Remove deprecated DRM API The DRM driver has switched to the new API, remove the deprecated macros and inline wrapper. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/media/vsp1.h | 28 ++-------------------------- 1 file changed, 2 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/media/vsp1.h b/include/media/vsp1.h index ea8ad7537057..9322d9775fb7 100644 --- a/include/media/vsp1.h +++ b/include/media/vsp1.h @@ -34,32 +34,8 @@ struct vsp1_du_atomic_config { }; void vsp1_du_atomic_begin(struct device *dev); -int __vsp1_du_atomic_update(struct device *dev, unsigned int rpf, - const struct vsp1_du_atomic_config *cfg); +int vsp1_du_atomic_update(struct device *dev, unsigned int rpf, + const struct vsp1_du_atomic_config *cfg); void vsp1_du_atomic_flush(struct device *dev); -static inline int vsp1_du_atomic_update_old(struct device *dev, - unsigned int rpf, u32 pixelformat, unsigned int pitch, - dma_addr_t mem[2], const struct v4l2_rect *src, - const struct v4l2_rect *dst) -{ - struct vsp1_du_atomic_config cfg = { - .pixelformat = pixelformat, - .pitch = pitch, - .mem[0] = mem[0], - .mem[1] = mem[1], - .src = *src, - .dst = *dst, - .alpha = 255, - .zpos = 0, - }; - - return __vsp1_du_atomic_update(dev, rpf, &cfg); -} - -#define _vsp1_du_atomic_update(_1, _2, _3, _4, _5, _6, _7, f, ...) f -#define vsp1_du_atomic_update(...) \ - _vsp1_du_atomic_update(__VA_ARGS__, vsp1_du_atomic_update_old, 0, 0, \ - 0, __vsp1_du_atomic_update)(__VA_ARGS__) - #endif /* __MEDIA_VSP1_H__ */ -- cgit v1.2.3 From 199a31c6d93ba9dc6f831fa1e77d9926f34f4e8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jun 2016 09:22:39 +1000 Subject: fs: move struct iomap from exportfs.h to a separate header Signed-off-by: Christoph Hellwig Reviewed-by: Bob Peterson Signed-off-by: Dave Chinner --- include/linux/exportfs.h | 16 +--------------- include/linux/iomap.h | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+), 15 deletions(-) create mode 100644 include/linux/iomap.h (limited to 'include') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index d8414502edb4..b03c0625fa6e 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -6,6 +6,7 @@ struct dentry; struct iattr; struct inode; +struct iomap; struct super_block; struct vfsmount; @@ -187,21 +188,6 @@ struct fid { * get_name is not (which is possibly inconsistent) */ -/* types of block ranges for multipage write mappings. */ -#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ -#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ -#define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ -#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ - -#define IOMAP_NULL_BLOCK -1LL /* blkno is not valid */ - -struct iomap { - sector_t blkno; /* first sector of mapping */ - loff_t offset; /* file offset of mapping, bytes */ - u64 length; /* length of mapping, bytes */ - int type; /* type of mapping */ -}; - struct export_operations { int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent); diff --git a/include/linux/iomap.h b/include/linux/iomap.h new file mode 100644 index 000000000000..1b22197bcf01 --- /dev/null +++ b/include/linux/iomap.h @@ -0,0 +1,21 @@ +#ifndef LINUX_IOMAP_H +#define LINUX_IOMAP_H 1 + +#include + +/* types of block ranges for multipage write mappings. */ +#define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ +#define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ +#define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ +#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ + +#define IOMAP_NULL_BLOCK -1LL /* blkno is not valid */ + +struct iomap { + sector_t blkno; /* first sector of mapping */ + loff_t offset; /* file offset of mapping, bytes */ + u64 length; /* length of mapping, bytes */ + int type; /* type of mapping */ +}; + +#endif /* LINUX_IOMAP_H */ -- cgit v1.2.3 From ae259a9c8593f98aa60d045df978a5482a67c53f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jun 2016 09:23:11 +1000 Subject: fs: introduce iomap infrastructure Add infrastructure for multipage buffered writes. This is implemented using an main iterator that applies an actor function to a range that can be written. This infrastucture is used to implement a buffered write helper, one to zero file ranges and one to implement the ->page_mkwrite VM operations. All of them borrow a fair amount of code from fs/buffers. for now by using an internal version of __block_write_begin that gets passed an iomap and builds the corresponding buffer head. The file system is gets a set of paired ->iomap_begin and ->iomap_end calls which allow it to map/reserve a range and get a notification once the write code is finished with it. Based on earlier code from Dave Chinner. Signed-off-by: Christoph Hellwig Reviewed-by: Bob Peterson Signed-off-by: Dave Chinner --- include/linux/iomap.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1b22197bcf01..d2f469ae899a 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -3,19 +3,65 @@ #include -/* types of block ranges for multipage write mappings. */ +struct inode; +struct iov_iter; +struct kiocb; +struct vm_area_struct; +struct vm_fault; + +/* + * Types of block ranges for iomap mappings: + */ #define IOMAP_HOLE 0x01 /* no blocks allocated, need allocation */ #define IOMAP_DELALLOC 0x02 /* delayed allocation blocks */ #define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ +/* + * Magic value for blkno: + */ #define IOMAP_NULL_BLOCK -1LL /* blkno is not valid */ struct iomap { - sector_t blkno; /* first sector of mapping */ - loff_t offset; /* file offset of mapping, bytes */ - u64 length; /* length of mapping, bytes */ - int type; /* type of mapping */ + sector_t blkno; /* 1st sector of mapping, 512b units */ + loff_t offset; /* file offset of mapping, bytes */ + u64 length; /* length of mapping, bytes */ + int type; /* type of mapping */ + struct block_device *bdev; /* block device for I/O */ +}; + +/* + * Flags for iomap_begin / iomap_end. No flag implies a read. + */ +#define IOMAP_WRITE (1 << 0) +#define IOMAP_ZERO (1 << 1) + +struct iomap_ops { + /* + * Return the existing mapping at pos, or reserve space starting at + * pos for up to length, as long as we can do it as a single mapping. + * The actual length is returned in iomap->length. + */ + int (*iomap_begin)(struct inode *inode, loff_t pos, loff_t length, + unsigned flags, struct iomap *iomap); + + /* + * Commit and/or unreserve space previous allocated using iomap_begin. + * Written indicates the length of the successful write operation which + * needs to be commited, while the rest needs to be unreserved. + * Written might be zero if no data was written. + */ + int (*iomap_end)(struct inode *inode, loff_t pos, loff_t length, + ssize_t written, unsigned flags, struct iomap *iomap); }; +ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, + struct iomap_ops *ops); +int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, + bool *did_zero, struct iomap_ops *ops); +int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + struct iomap_ops *ops); +int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, + struct iomap_ops *ops); + #endif /* LINUX_IOMAP_H */ -- cgit v1.2.3 From 8be9f564d25e7adc582f9f3689040ce5aa6f1f5b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 21 Jun 2016 09:38:45 +1000 Subject: fs: iomap based fiemap implementation Add a simple fiemap implementation based on iomap_ops, partially based on a previous implementation from Bob Peterson . Signed-off-by: Christoph Hellwig Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- include/linux/iomap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iomap.h b/include/linux/iomap.h index d2f469ae899a..3267df461012 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -3,6 +3,7 @@ #include +struct fiemap_extent_info; struct inode; struct iov_iter; struct kiocb; @@ -63,5 +64,7 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, struct iomap_ops *ops); int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops); +int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + loff_t start, loff_t len, struct iomap_ops *ops); #endif /* LINUX_IOMAP_H */ -- cgit v1.2.3 From d366d28cd1325f11d582ec6d4a14b8329d3e1a20 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 20 May 2016 16:41:25 +1000 Subject: PCI: Add pcibios_setup_bridge() Currently, PowerPC PowerNV platform utilizes ppc_md.pcibios_fixup(), which is called for once after PCI probing and resource assignment are completed, to allocate platform required resources for PCI devices: PE#, IO and MMIO mapping, DMA address translation (TCE) table etc. Obviously, it's not hotplug friendly. This adds weak function pcibios_setup_bridge(), which is called by pci_setup_bridge(). PowerPC PowerNV platform will reuse the function to assign above platform required resources to newly plugged PCI devices during PCI hotplug in subsequent patches. Signed-off-by: Gavin Shan Acked-by: Bjorn Helgaas Signed-off-by: Michael Ellerman --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..c40ac910cce4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -854,6 +854,7 @@ void pci_stop_and_remove_bus_device_locked(struct pci_dev *dev); void pci_stop_root_bus(struct pci_bus *bus); void pci_remove_root_bus(struct pci_bus *bus); void pci_setup_cardbus(struct pci_bus *bus); +void pcibios_setup_bridge(struct pci_bus *bus, unsigned long type); void pci_sort_breadthfirst(void); #define dev_is_pci(d) ((d)->bus == &pci_bus_type) #define dev_is_pf(d) ((dev_is_pci(d) ? to_pci_dev(d)->is_physfn : false)) -- cgit v1.2.3 From 4dbc39e98b57a7f67c739b04f12d9829fe659bfa Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Fri, 17 Jun 2016 15:51:41 +0100 Subject: ARM: imx6: fix static declaration in include/soc/imx/cpuidle.h If both CONFIG_CPU_IDLE or CONFIG_SOC_IMX6Q are not set then the imx6q_cpuidle_fec_irqs_used() and other functions should be marked static inline to avoid the following warnings whilst building drivers/net/ethernet/freescale: include/soc/imx/cpuidle.h:21:6: warning: symbol 'imx6q_cpuidle_fec_irqs_used' was not declared. Should it be static? include/soc/imx/cpuidle.h:22:6: warning: symbol 'imx6q_cpuidle_fec_irqs_unused' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: Shawn Guo --- include/soc/imx/cpuidle.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/soc/imx/cpuidle.h b/include/soc/imx/cpuidle.h index 986a4823bce1..8e7743d3b34d 100644 --- a/include/soc/imx/cpuidle.h +++ b/include/soc/imx/cpuidle.h @@ -18,8 +18,8 @@ void imx6q_cpuidle_fec_irqs_used(void); void imx6q_cpuidle_fec_irqs_unused(void); #else -void imx6q_cpuidle_fec_irqs_used(void) { } -void imx6q_cpuidle_fec_irqs_unused(void) { } +static inline void imx6q_cpuidle_fec_irqs_used(void) { } +static inline void imx6q_cpuidle_fec_irqs_unused(void) { } #endif #endif /* __SOC_IMX_CPUIDLE_H__ */ -- 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 --- include/linux/usb/gadget.h | 585 +++++---------------------------------------- 1 file changed, 60 insertions(+), 525 deletions(-) (limited to 'include') 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 --- include/linux/usb/gadget.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') 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 df9b2b4a4aa49f874f8507680a533369e4b9c378 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 20 Jun 2016 12:09:41 +0200 Subject: mm/page_ref: introduce page_ref_inc_return Let's introduce that helper. Signed-off-by: David Hildenbrand Acked-by: Andrew Morton Signed-off-by: Christian Borntraeger --- include/linux/page_ref.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 8b5e0a9f2431..610e13271918 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -124,6 +124,15 @@ static inline int page_ref_sub_and_test(struct page *page, int nr) return ret; } +static inline int page_ref_inc_return(struct page *page) +{ + int ret = atomic_inc_return(&page->_refcount); + + if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) + __page_ref_mod_and_return(page, 1, ret); + return ret; +} + static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); -- 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 --- include/linux/usb/of.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') 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 --- include/linux/usb/msm_hsusb.h | 200 ------------------------------------------ 1 file changed, 200 deletions(-) delete mode 100644 include/linux/usb/msm_hsusb.h (limited to 'include') 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 37a441dcd5f4db7f769fee50ba7a2c602903a052 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 20 Apr 2016 14:05:14 +0100 Subject: firmware: arm_scpi: add support for device power state management SCPI protocol supports device power state management. This deals with power states of various peripheral devices in the system other than the core compute subsystem. This patch adds support for the power state management of those peripheral devices. Tested-by: Mathieu Poirier Tested-by: Jon Medhurst Reviewed-by: Jon Medhurst Reviewed-by: Kevin Hilman Reviewed-by: Ulf Hansson Signed-off-by: Sudeep Holla --- include/linux/scpi_protocol.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index 35de50a65665..dc5f989be226 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -70,6 +70,8 @@ struct scpi_ops { int (*sensor_get_capability)(u16 *sensors); int (*sensor_get_info)(u16 sensor_id, struct scpi_sensor_info *); int (*sensor_get_value)(u16, u64 *); + int (*device_get_power_state)(u16); + int (*device_set_power_state)(u16, u8); }; #if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL) -- cgit v1.2.3 From 7e42626ad3f4540143e68ba41e5e553f2715b451 Mon Sep 17 00:00:00 2001 From: Honghui Zhang Date: Wed, 8 Jun 2016 17:50:57 +0800 Subject: dt-bindings: mediatek: add descriptions for mediatek mt2701 iommu and smi This patch defines the local arbitor port IDs for mediatek SoC MT2701 and add descriptions of binding for mediatek generation one iommu and smi. Signed-off-by: Honghui Zhang Acked-by: Rob Herring Signed-off-by: Joerg Roedel --- include/dt-bindings/memory/mt2701-larb-port.h | 85 +++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) create mode 100644 include/dt-bindings/memory/mt2701-larb-port.h (limited to 'include') diff --git a/include/dt-bindings/memory/mt2701-larb-port.h b/include/dt-bindings/memory/mt2701-larb-port.h new file mode 100644 index 000000000000..78f66786da91 --- /dev/null +++ b/include/dt-bindings/memory/mt2701-larb-port.h @@ -0,0 +1,85 @@ +/* + * Copyright (c) 2015 MediaTek Inc. + * Author: Honghui Zhang + * + * 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 _MT2701_LARB_PORT_H_ +#define _MT2701_LARB_PORT_H_ + +/* + * Mediatek m4u generation 1 such as mt2701 has flat m4u port numbers, + * the first port's id for larb[N] would be the last port's id of larb[N - 1] + * plus one while larb[0]'s first port number is 0. The definition of + * MT2701_M4U_ID_LARBx is following HW register spec. + * But m4u generation 2 like mt8173 have different port number, it use fixed + * offset for each larb, the first port's id for larb[N] would be (N * 32). + */ +#define LARB0_PORT_OFFSET 0 +#define LARB1_PORT_OFFSET 11 +#define LARB2_PORT_OFFSET 21 +#define LARB3_PORT_OFFSET 43 + +#define MT2701_M4U_ID_LARB0(port) ((port) + LARB0_PORT_OFFSET) +#define MT2701_M4U_ID_LARB1(port) ((port) + LARB1_PORT_OFFSET) +#define MT2701_M4U_ID_LARB2(port) ((port) + LARB2_PORT_OFFSET) + +/* Port define for larb0 */ +#define MT2701_M4U_PORT_DISP_OVL_0 MT2701_M4U_ID_LARB0(0) +#define MT2701_M4U_PORT_DISP_RDMA1 MT2701_M4U_ID_LARB0(1) +#define MT2701_M4U_PORT_DISP_RDMA MT2701_M4U_ID_LARB0(2) +#define MT2701_M4U_PORT_DISP_WDMA MT2701_M4U_ID_LARB0(3) +#define MT2701_M4U_PORT_MM_CMDQ MT2701_M4U_ID_LARB0(4) +#define MT2701_M4U_PORT_MDP_RDMA MT2701_M4U_ID_LARB0(5) +#define MT2701_M4U_PORT_MDP_WDMA MT2701_M4U_ID_LARB0(6) +#define MT2701_M4U_PORT_MDP_ROTO MT2701_M4U_ID_LARB0(7) +#define MT2701_M4U_PORT_MDP_ROTCO MT2701_M4U_ID_LARB0(8) +#define MT2701_M4U_PORT_MDP_ROTVO MT2701_M4U_ID_LARB0(9) +#define MT2701_M4U_PORT_MDP_RDMA1 MT2701_M4U_ID_LARB0(10) + +/* Port define for larb1 */ +#define MT2701_M4U_PORT_VDEC_MC_EXT MT2701_M4U_ID_LARB1(0) +#define MT2701_M4U_PORT_VDEC_PP_EXT MT2701_M4U_ID_LARB1(1) +#define MT2701_M4U_PORT_VDEC_PPWRAP_EXT MT2701_M4U_ID_LARB1(2) +#define MT2701_M4U_PORT_VDEC_AVC_MV_EXT MT2701_M4U_ID_LARB1(3) +#define MT2701_M4U_PORT_VDEC_PRED_RD_EXT MT2701_M4U_ID_LARB1(4) +#define MT2701_M4U_PORT_VDEC_PRED_WR_EXT MT2701_M4U_ID_LARB1(5) +#define MT2701_M4U_PORT_VDEC_VLD_EXT MT2701_M4U_ID_LARB1(6) +#define MT2701_M4U_PORT_VDEC_VLD2_EXT MT2701_M4U_ID_LARB1(7) +#define MT2701_M4U_PORT_VDEC_TILE_EXT MT2701_M4U_ID_LARB1(8) +#define MT2701_M4U_PORT_VDEC_IMG_RESZ_EXT MT2701_M4U_ID_LARB1(9) + +/* Port define for larb2 */ +#define MT2701_M4U_PORT_VENC_RCPU MT2701_M4U_ID_LARB2(0) +#define MT2701_M4U_PORT_VENC_REC_FRM MT2701_M4U_ID_LARB2(1) +#define MT2701_M4U_PORT_VENC_BSDMA MT2701_M4U_ID_LARB2(2) +#define MT2701_M4U_PORT_JPGENC_RDMA MT2701_M4U_ID_LARB2(3) +#define MT2701_M4U_PORT_VENC_LT_RCPU MT2701_M4U_ID_LARB2(4) +#define MT2701_M4U_PORT_VENC_LT_REC_FRM MT2701_M4U_ID_LARB2(5) +#define MT2701_M4U_PORT_VENC_LT_BSDMA MT2701_M4U_ID_LARB2(6) +#define MT2701_M4U_PORT_JPGDEC_BSDMA MT2701_M4U_ID_LARB2(7) +#define MT2701_M4U_PORT_VENC_SV_COMV MT2701_M4U_ID_LARB2(8) +#define MT2701_M4U_PORT_VENC_RD_COMV MT2701_M4U_ID_LARB2(9) +#define MT2701_M4U_PORT_JPGENC_BSDMA MT2701_M4U_ID_LARB2(10) +#define MT2701_M4U_PORT_VENC_CUR_LUMA MT2701_M4U_ID_LARB2(11) +#define MT2701_M4U_PORT_VENC_CUR_CHROMA MT2701_M4U_ID_LARB2(12) +#define MT2701_M4U_PORT_VENC_REF_LUMA MT2701_M4U_ID_LARB2(13) +#define MT2701_M4U_PORT_VENC_REF_CHROMA MT2701_M4U_ID_LARB2(14) +#define MT2701_M4U_PORT_IMG_RESZ MT2701_M4U_ID_LARB2(15) +#define MT2701_M4U_PORT_VENC_LT_SV_COMV MT2701_M4U_ID_LARB2(16) +#define MT2701_M4U_PORT_VENC_LT_RD_COMV MT2701_M4U_ID_LARB2(17) +#define MT2701_M4U_PORT_VENC_LT_CUR_LUMA MT2701_M4U_ID_LARB2(18) +#define MT2701_M4U_PORT_VENC_LT_CUR_CHROMA MT2701_M4U_ID_LARB2(19) +#define MT2701_M4U_PORT_VENC_LT_REF_LUMA MT2701_M4U_ID_LARB2(20) +#define MT2701_M4U_PORT_VENC_LT_REF_CHROMA MT2701_M4U_ID_LARB2(21) +#define MT2701_M4U_PORT_JPGDEC_WDMA MT2701_M4U_ID_LARB2(22) + +#endif -- cgit v1.2.3 From be9d2e8927cef02076bb7b5b2637cd9f4be2e8df Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 7 Jun 2016 09:44:01 +0200 Subject: PCI: Add helpers to request/release memory and I/O regions Add helpers to request and release a device's memory or I/O regions. With these helpers in place, one does not need to select a device's memory or I/O regions with pci_select_bars() prior to requesting or releasing them. Suggested-by: Christoph Hellwig Signed-off-by: Johannes Thumshirn Signed-off-by: Bjorn Helgaas Reviewed-by: Christoph Hellwig --- include/linux/pci.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9c201d4dbd51..6af3b93f0710 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1402,6 +1402,34 @@ typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); void pci_register_set_vga_state(arch_set_vga_state_t func); +static inline int +pci_request_io_regions(struct pci_dev *pdev, const char *name) +{ + return pci_request_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_IO), name); +} + +static inline void +pci_release_io_regions(struct pci_dev *pdev) +{ + return pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_IO)); +} + +static inline int +pci_request_mem_regions(struct pci_dev *pdev, const char *name) +{ + return pci_request_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM), name); +} + +static inline void +pci_release_mem_regions(struct pci_dev *pdev) +{ + return pci_release_selected_regions(pdev, + pci_select_bars(pdev, IORESOURCE_MEM)); +} + #else /* CONFIG_PCI is not enabled */ static inline void pci_set_flags(int flags) { } -- cgit v1.2.3 From 5f6d71044f4d766c3636b9fd2c43e7c9d71d31af Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Tue, 21 Jun 2016 12:53:29 +0800 Subject: clk: rockchip: add clock-ids for rk3228 audio clocks This patch exports related i2s/spdif clocks for dts reference. Signed-off-by: Xing Zheng Signed-off-by: Heiko Stuebner --- include/dt-bindings/clock/rk3228-cru.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/rk3228-cru.h b/include/dt-bindings/clock/rk3228-cru.h index 5d43ed9b05ad..c992f3e50e25 100644 --- a/include/dt-bindings/clock/rk3228-cru.h +++ b/include/dt-bindings/clock/rk3228-cru.h @@ -84,6 +84,10 @@ #define PCLK_HDMI_PHY 365 /* hclk gates */ +#define HCLK_I2S0_8CH 442 +#define HCLK_I2S1_8CH 443 +#define HCLK_I2S2_2CH 444 +#define HCLK_SPDIF_8CH 445 #define HCLK_VOP 452 #define HCLK_NANDC 453 #define HCLK_SDMMC 456 -- cgit v1.2.3 From 9ff59360b863706b50cbcd7ffad9287d67254063 Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Tue, 21 Jun 2016 12:59:47 +0800 Subject: clk: rockchip: add clock-ids for rk3228 MAC clocks This patch exports related MAC clocks for dts reference. Signed-off-by: Xing Zheng Signed-off-by: Heiko Stuebner --- include/dt-bindings/clock/rk3228-cru.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/rk3228-cru.h b/include/dt-bindings/clock/rk3228-cru.h index c992f3e50e25..b27e2b1a65e3 100644 --- a/include/dt-bindings/clock/rk3228-cru.h +++ b/include/dt-bindings/clock/rk3228-cru.h @@ -52,6 +52,15 @@ #define SCLK_EMMC_SAMPLE 121 #define SCLK_VOP 122 #define SCLK_HDMI_HDCP 123 +#define SCLK_MAC_SRC 124 +#define SCLK_MAC_EXTCLK 125 +#define SCLK_MAC 126 +#define SCLK_MAC_REFOUT 127 +#define SCLK_MAC_REF 128 +#define SCLK_MAC_RX 129 +#define SCLK_MAC_TX 130 +#define SCLK_MAC_PHY 131 +#define SCLK_MAC_OUT 132 /* dclk gates */ #define DCLK_VOP 190 @@ -61,6 +70,7 @@ #define ACLK_DMAC 194 #define ACLK_PERI 210 #define ACLK_VOP 211 +#define ACLK_GMAC 212 /* pclk gates */ #define PCLK_GPIO0 320 @@ -82,6 +92,7 @@ #define PCLK_PERI 363 #define PCLK_HDMI_CTRL 364 #define PCLK_HDMI_PHY 365 +#define PCLK_GMAC 367 /* hclk gates */ #define HCLK_I2S0_8CH 442 -- cgit v1.2.3 From da3d3f98d28bc071a2d566aefc8c461bd564be35 Mon Sep 17 00:00:00 2001 From: Aleksey Makarov Date: Mon, 20 Jun 2016 13:56:10 +0300 Subject: ACPI / tables: table upgrade: refactor function definitions Refer initrd_start, initrd_end directly from drivers/acpi/tables.c. This allows to use the table upgrade feature in architectures other than x86. Also this simplifies header files. The patch renames acpi_table_initrd_init() to acpi_table_upgrade() (what reflects the purpose of the function) and removes the unneeded wraps early_acpi_table_init() and early_initrd_acpi_init(). Signed-off-by: Aleksey Makarov Acked-by: Lv Zheng Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..ef2ad26abede 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -208,7 +208,6 @@ void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); -void early_acpi_table_init(void *data, size_t size); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init acpi_parse_entries(char *id, unsigned long table_size, @@ -588,7 +587,6 @@ static inline const char *acpi_dev_name(struct acpi_device *adev) return NULL; } -static inline void early_acpi_table_init(void *data, size_t size) { } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } @@ -997,4 +995,10 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif +#ifdef CONFIG_ACPI_TABLE_UPGRADE +void acpi_table_upgrade(void); +#else +static inline void acpi_table_upgrade(void) { } +#endif + #endif /*_LINUX_ACPI_H*/ -- cgit v1.2.3 From 4bac6fa73db77d4ff49a965a7c6dc69d9e235e5f Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Fri, 17 Jun 2016 11:53:02 +0800 Subject: ACPI / NUMA: Enable ACPI based NUMA on ARM64 Add function needed for cpu to node mapping, and enable ACPI based NUMA for ARM64 in Kconfig Signed-off-by: Hanjun Guo Signed-off-by: Robert Richter [david.daney@cavium.com added ACPI_NUMA default to y for ARM64] Signed-off-by: David Daney Acked-by: Catalin Marinas Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 8010b266e856..9515db6f03f0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -232,10 +232,25 @@ int acpi_table_parse_madt(enum acpi_madt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -/* the following four functions are architecture-dependent */ +/* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); + +#if defined(CONFIG_X86) || defined(CONFIG_IA64) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); +#else +static inline void +acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } +#endif + void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); + +#ifdef CONFIG_ARM64 +void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); +#else +static inline void +acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } +#endif + int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); #ifndef PHYS_CPUID_INVALID -- cgit v1.2.3 From cc8feb8edd92d854be552fe4f5e0eeabca40b9ee Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 4 Apr 2016 14:00:37 +0100 Subject: rxrpc: Fix exclusive connection handling "Exclusive connections" are meant to be used for a single client call and then scrapped. The idea is to limit the use of the negotiated security context. The current code, however, isn't doing this: it is instead restricting the socket to a single virtual connection and doing all the calls over that. This is changed such that the socket no longer maintains a special virtual connection over which it will do all the calls, but rather gets a new one each time a new exclusive call is made. Further, using a socket option for this is a poor choice. It should be done on sendmsg with a control message marker instead so that calls can be marked exclusive individually. To that end, add RXRPC_EXCLUSIVE_CALL which, if passed to sendmsg() as a control message element, will cause the call to be done on an single-use connection. The socket option (RXRPC_EXCLUSIVE_CONNECTION) still exists and, if set, will override any lack of RXRPC_EXCLUSIVE_CALL being specified so that programs using the setsockopt() will appear to work the same. Signed-off-by: David Howells --- include/linux/rxrpc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h index 1e8f216e2cf1..c68307bc306f 100644 --- a/include/linux/rxrpc.h +++ b/include/linux/rxrpc.h @@ -35,7 +35,7 @@ struct sockaddr_rxrpc { */ #define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ #define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ -#define RXRPC_EXCLUSIVE_CONNECTION 3 /* [clnt] use exclusive RxRPC connection */ +#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ #define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ /* @@ -52,6 +52,7 @@ struct sockaddr_rxrpc { #define RXRPC_LOCAL_ERROR 7 /* -r: local error generated [terminal] */ #define RXRPC_NEW_CALL 8 /* -r: [Service] new incoming call notification */ #define RXRPC_ACCEPT 9 /* s-: [Service] accept request */ +#define RXRPC_EXCLUSIVE_CALL 10 /* s-: Call should be on exclusive connection */ /* * RxRPC security levels -- cgit v1.2.3 From ff42c8aa6c5d05b7e084c81c1d02554839d7e9e1 Mon Sep 17 00:00:00 2001 From: Kamil Debski Date: Mon, 17 Aug 2015 08:47:41 -0300 Subject: [media] rc: Add HDMI CEC protocol handling Add handling of remote control events coming from the HDMI CEC bus and the new protocol required for that. Signed-off-by: Kamil Debski Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 7844e9879497..6e6557dbeb9f 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -31,6 +31,7 @@ enum rc_type { RC_TYPE_RC6_MCE = 16, /* MCE (Philips RC6-6A-32 subtype) protocol */ RC_TYPE_SHARP = 17, /* Sharp protocol */ RC_TYPE_XMP = 18, /* XMP protocol */ + RC_TYPE_CEC = 19, /* CEC protocol */ }; #define RC_BIT_NONE 0ULL @@ -53,6 +54,7 @@ enum rc_type { #define RC_BIT_RC6_MCE (1ULL << RC_TYPE_RC6_MCE) #define RC_BIT_SHARP (1ULL << RC_TYPE_SHARP) #define RC_BIT_XMP (1ULL << RC_TYPE_XMP) +#define RC_BIT_CEC (1ULL << RC_TYPE_CEC) #define RC_BIT_ALL (RC_BIT_UNKNOWN | RC_BIT_OTHER | \ RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ | \ @@ -61,7 +63,7 @@ enum rc_type { RC_BIT_NEC | RC_BIT_SANYO | RC_BIT_MCE_KBD | \ RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 | \ RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE | RC_BIT_SHARP | \ - RC_BIT_XMP) + RC_BIT_XMP | RC_BIT_CEC) #define RC_SCANCODE_UNKNOWN(x) (x) @@ -123,6 +125,7 @@ void rc_map_init(void); #define RC_MAP_BEHOLD_COLUMBUS "rc-behold-columbus" #define RC_MAP_BEHOLD "rc-behold" #define RC_MAP_BUDGET_CI_OLD "rc-budget-ci-old" +#define RC_MAP_CEC "rc-cec" #define RC_MAP_CINERGY_1400 "rc-cinergy-1400" #define RC_MAP_CINERGY "rc-cinergy" #define RC_MAP_DELOCK_61959 "rc-delock-61959" -- cgit v1.2.3 From 6b56a89833fa7903595c8d138bb4927187315cba Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 1 Jun 2016 18:23:01 -0400 Subject: NFS: Kill NFS_INO_NFS_INO_FLUSHING: it is a performance killer filemap_datawrite() and friends already deal just fine with livelock. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d71278c3c5bd..120dd04b553c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -205,7 +205,6 @@ struct nfs_inode { #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ -#define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ -- cgit v1.2.3 From b95e5928fcc76d156352570858abdea7b2628efd Mon Sep 17 00:00:00 2001 From: William Tu Date: Mon, 20 Jun 2016 07:26:17 -0700 Subject: openvswitch: Add packet len info to upcall. The commit f2a4d086ed4c ("openvswitch: Add packet truncation support.") introduces packet truncation before sending to userspace upcall receiver. This patch passes up the skb->len before truncation so that the upcall receiver knows the original packet size. Potentially this will be used by sFlow, where OVS translates sFlow config header=N to a sample action, truncating packet to N byte in kernel datapath. Thus, only N bytes instead of full-packet size is copied from kernel to userspace, saving the kernel-to-userspace bandwidth. Signed-off-by: William Tu Cc: Pravin Shelar Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 8274675ba9a3..d95a3018f6a1 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -166,6 +166,7 @@ enum ovs_packet_cmd { * output port is actually a tunnel port. Contains the output tunnel key * extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes. * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and + * @OVS_PACKET_ATTR_LEN: Packet size before truncation. * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment * size. * @@ -185,6 +186,7 @@ enum ovs_packet_attr { OVS_PACKET_ATTR_PROBE, /* Packet operation is a feature probe, error logging should be suppressed. */ OVS_PACKET_ATTR_MRU, /* Maximum received IP fragment size. */ + OVS_PACKET_ATTR_LEN, /* Packet size before truncation. */ __OVS_PACKET_ATTR_MAX }; -- cgit v1.2.3 From c0daa3e6f5b0b707f5c4b408bc8ef541c9a7742a Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Thu, 28 Apr 2016 12:01:51 -0700 Subject: clk: meson8b: clean up composite clocks Remove the composite clock registration function and helpers. Replace unnecessary configuration struct with static initialization of the desired clock type. To preserve git bisect this patch also flips the switch and starts using of_clk_add_hw_provider instead of the deprecated meson_clk_register_clks method. As a byproduct clk.c can be deleted. Tested-by: Kevin Hilman Signed-off-by: Michael Turquette --- include/dt-bindings/clock/meson8b-clkc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/meson8b-clkc.h b/include/dt-bindings/clock/meson8b-clkc.h index bd2720d58e0c..595a58d0969a 100644 --- a/include/dt-bindings/clock/meson8b-clkc.h +++ b/include/dt-bindings/clock/meson8b-clkc.h @@ -19,7 +19,9 @@ #define CLKID_MALI 11 #define CLKID_CPUCLK 12 #define CLKID_ZERO 13 +#define CLKID_MPEG_SEL 14 +#define CLKID_MPEG_DIV 15 -#define CLK_NR_CLKS (CLKID_ZERO + 1) +#define CLK_NR_CLKS (CLKID_MPEG_DIV + 1) #endif /* __MESON8B_CLKC_H */ -- cgit v1.2.3 From 738f66d3211d7ae0cd0012ba6457dac9a03bfd6b Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Mon, 23 May 2016 15:44:26 -0700 Subject: clk: gxbb: add AmLogic GXBB clk controller driver The gxbb clock controller is the primary clock generation unit for the AmLogic GXBB SoC. It is clocked by a fixed 24MHz xtal, contains several PLLs and the usual post-dividers, muxes, dividers and leaf gates that are fed into various IP blocks in the SoC. Tested-by: Kevin Hilman Signed-off-by: Michael Turquette --- include/dt-bindings/clock/gxbb-clkc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 include/dt-bindings/clock/gxbb-clkc.h (limited to 'include') diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h new file mode 100644 index 000000000000..f889d80246cb --- /dev/null +++ b/include/dt-bindings/clock/gxbb-clkc.h @@ -0,0 +1,12 @@ +/* + * GXBB clock tree IDs + */ + +#ifndef __GXBB_CLKC_H +#define __GXBB_CLKC_H + +#define CLKID_CPUCLK 1 +#define CLKID_CLK81 12 +#define CLKID_ETH 36 + +#endif /* __GXBB_CLKC_H */ -- cgit v1.2.3 From 81760ea6a95ad4c41273a71052f61b9f087b5753 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 21 Jun 2016 16:55:13 +0800 Subject: crypto: cryptd - Add helpers to check whether a tfm is queued This patch adds helpers to check whether a given tfm is currently queued. This is meant to be used by ablk_helper and similar entities to ensure that no reordering is introduced because of requests queued in cryptd with respect to requests being processed in softirq context. The per-cpu queue length limit is also increased to 1000 in line with network limits. Signed-off-by: Herbert Xu --- include/crypto/cryptd.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/crypto/cryptd.h b/include/crypto/cryptd.h index 1547f540c920..bc792d5a9e88 100644 --- a/include/crypto/cryptd.h +++ b/include/crypto/cryptd.h @@ -31,6 +31,7 @@ static inline struct cryptd_ablkcipher *__cryptd_ablkcipher_cast( struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name, u32 type, u32 mask); struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm); +bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm); void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm); struct cryptd_ahash { @@ -48,6 +49,8 @@ struct cryptd_ahash *cryptd_alloc_ahash(const char *alg_name, u32 type, u32 mask); struct crypto_shash *cryptd_ahash_child(struct cryptd_ahash *tfm); struct shash_desc *cryptd_shash_desc(struct ahash_request *req); +/* Must be called without moving CPUs. */ +bool cryptd_ahash_queued(struct cryptd_ahash *tfm); void cryptd_free_ahash(struct cryptd_ahash *tfm); struct cryptd_aead { @@ -64,6 +67,8 @@ struct cryptd_aead *cryptd_alloc_aead(const char *alg_name, u32 type, u32 mask); struct crypto_aead *cryptd_aead_child(struct cryptd_aead *tfm); +/* Must be called without moving CPUs. */ +bool cryptd_aead_queued(struct cryptd_aead *tfm); void cryptd_free_aead(struct cryptd_aead *tfm); -- cgit v1.2.3 From 331bf739c4f9992a73547d20bd8f2378b97d386a Mon Sep 17 00:00:00 2001 From: Megha Dey Date: Tue, 21 Jun 2016 18:21:46 -0700 Subject: crypto: sha1-mb - async implementation for sha1-mb Herbert wants the sha1-mb algorithm to have an async implementation: https://lkml.org/lkml/2016/4/5/286. Currently, sha1-mb uses an async interface for the outer algorithm and a sync interface for the inner algorithm. This patch introduces a async interface for even the inner algorithm. Signed-off-by: Megha Dey Signed-off-by: Tim Chen Signed-off-by: Herbert Xu --- include/crypto/internal/hash.h | 12 ++++-------- include/crypto/mcryptd.h | 8 ++++---- 2 files changed, 8 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/crypto/internal/hash.h b/include/crypto/internal/hash.h index 49dae16f8929..1d4f365d8f03 100644 --- a/include/crypto/internal/hash.h +++ b/include/crypto/internal/hash.h @@ -114,14 +114,10 @@ int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); -int shash_ahash_mcryptd_update(struct ahash_request *req, - struct shash_desc *desc); -int shash_ahash_mcryptd_final(struct ahash_request *req, - struct shash_desc *desc); -int shash_ahash_mcryptd_finup(struct ahash_request *req, - struct shash_desc *desc); -int shash_ahash_mcryptd_digest(struct ahash_request *req, - struct shash_desc *desc); +int ahash_mcryptd_update(struct ahash_request *desc); +int ahash_mcryptd_final(struct ahash_request *desc); +int ahash_mcryptd_finup(struct ahash_request *desc); +int ahash_mcryptd_digest(struct ahash_request *desc); int crypto_init_shash_ops_async(struct crypto_tfm *tfm); diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h index c23ee1f7ee80..4a53c0d38cd2 100644 --- a/include/crypto/mcryptd.h +++ b/include/crypto/mcryptd.h @@ -39,7 +39,7 @@ struct mcryptd_instance_ctx { }; struct mcryptd_hash_ctx { - struct crypto_shash *child; + struct crypto_ahash *child; struct mcryptd_alg_state *alg_state; }; @@ -59,13 +59,13 @@ struct mcryptd_hash_request_ctx { struct crypto_hash_walk walk; u8 *out; int flag; - struct shash_desc desc; + struct ahash_request areq; }; struct mcryptd_ahash *mcryptd_alloc_ahash(const char *alg_name, u32 type, u32 mask); -struct crypto_shash *mcryptd_ahash_child(struct mcryptd_ahash *tfm); -struct shash_desc *mcryptd_shash_desc(struct ahash_request *req); +struct crypto_ahash *mcryptd_ahash_child(struct mcryptd_ahash *tfm); +struct ahash_request *mcryptd_ahash_desc(struct ahash_request *req); void mcryptd_free_ahash(struct mcryptd_ahash *tfm); void mcryptd_flusher(struct work_struct *work); -- cgit v1.2.3 From 4e5f2c400765e3a3ce512dc1ae890bac53401798 Mon Sep 17 00:00:00 2001 From: Salvatore Benedetto Date: Wed, 22 Jun 2016 17:49:13 +0100 Subject: crypto: kpp - Key-agreement Protocol Primitives API (KPP) Add key-agreement protocol primitives (kpp) API which allows to implement primitives required by protocols such as DH and ECDH. The API is composed mainly by the following functions * set_secret() - It allows the user to set his secret, also referred to as his private key, along with the parameters known to both parties involved in the key-agreement session. * generate_public_key() - It generates the public key to be sent to the other counterpart involved in the key-agreement session. The function has to be called after set_params() and set_secret() * generate_secret() - It generates the shared secret for the session Other functions such as init() and exit() are provided for allowing cryptographic hardware to be inizialized properly before use Signed-off-by: Salvatore Benedetto Signed-off-by: Herbert Xu --- include/crypto/internal/kpp.h | 64 ++++++++ include/crypto/kpp.h | 328 ++++++++++++++++++++++++++++++++++++++++ include/linux/crypto.h | 1 + include/uapi/linux/cryptouser.h | 5 + 4 files changed, 398 insertions(+) create mode 100644 include/crypto/internal/kpp.h create mode 100644 include/crypto/kpp.h (limited to 'include') diff --git a/include/crypto/internal/kpp.h b/include/crypto/internal/kpp.h new file mode 100644 index 000000000000..ad3acf3649be --- /dev/null +++ b/include/crypto/internal/kpp.h @@ -0,0 +1,64 @@ +/* + * Key-agreement Protocol Primitives (KPP) + * + * Copyright (c) 2016, Intel Corporation + * Authors: Salvatore Benedetto + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_KPP_INT_H +#define _CRYPTO_KPP_INT_H +#include +#include + +/* + * Transform internal helpers. + */ +static inline void *kpp_request_ctx(struct kpp_request *req) +{ + return req->__ctx; +} + +static inline void *kpp_tfm_ctx(struct crypto_kpp *tfm) +{ + return tfm->base.__crt_ctx; +} + +static inline void kpp_request_complete(struct kpp_request *req, int err) +{ + req->base.complete(&req->base, err); +} + +static inline const char *kpp_alg_name(struct crypto_kpp *tfm) +{ + return crypto_kpp_tfm(tfm)->__crt_alg->cra_name; +} + +/** + * crypto_register_kpp() -- Register key-agreement protocol primitives algorithm + * + * Function registers an implementation of a key-agreement protocol primitive + * algorithm + * + * @alg: algorithm definition + * + * Return: zero on success; error code in case of error + */ +int crypto_register_kpp(struct kpp_alg *alg); + +/** + * crypto_unregister_kpp() -- Unregister key-agreement protocol primitive + * algorithm + * + * Function unregisters an implementation of a key-agreement protocol primitive + * algorithm + * + * @alg: algorithm definition + */ +void crypto_unregister_kpp(struct kpp_alg *alg); + +#endif diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h new file mode 100644 index 000000000000..4fa897f3366b --- /dev/null +++ b/include/crypto/kpp.h @@ -0,0 +1,328 @@ +/* + * Key-agreement Protocol Primitives (KPP) + * + * Copyright (c) 2016, Intel Corporation + * Authors: Salvatore Benedetto + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _CRYPTO_KPP_ +#define _CRYPTO_KPP_ +#include + +/** + * struct kpp_request + * + * @base: Common attributes for async crypto requests + * @src: Source data + * @dst: Destination data + * @src_len: Size of the input buffer + * @dst_len: Size of the output buffer. It needs to be at least + * as big as the expected result depending on the operation + * After operation it will be updated with the actual size of the + * result. In case of error where the dst sgl size was insufficient, + * it will be updated to the size required for the operation. + * @__ctx: Start of private context data + */ +struct kpp_request { + struct crypto_async_request base; + struct scatterlist *src; + struct scatterlist *dst; + unsigned int src_len; + unsigned int dst_len; + void *__ctx[] CRYPTO_MINALIGN_ATTR; +}; + +/** + * struct crypto_kpp - user-instantiated object which encapsulate + * algorithms and core processing logic + * + * @base: Common crypto API algorithm data structure + */ +struct crypto_kpp { + struct crypto_tfm base; +}; + +/** + * struct kpp_alg - generic key-agreement protocol primitives + * + * @set_secret: Function invokes the protocol specific function to + * store the secret private key along with parameters. + * The implementation knows how to decode thie buffer + * @generate_public_key: Function generate the public key to be sent to the + * counterpart. In case of error, where output is not big + * enough req->dst_len will be updated to the size + * required + * @compute_shared_secret: Function compute the shared secret as defined by + * the algorithm. The result is given back to the user. + * In case of error, where output is not big enough, + * req->dst_len will be updated to the size required + * @max_size: Function returns the size of the output buffer + * @init: Initialize the object. This is called only once at + * instantiation time. In case the cryptographic hardware + * needs to be initialized. Software fallback should be + * put in place here. + * @exit: Undo everything @init did. + * + * @reqsize: Request context size required by algorithm + * implementation + * @base Common crypto API algorithm data structure + */ +struct kpp_alg { + int (*set_secret)(struct crypto_kpp *tfm, void *buffer, + unsigned int len); + int (*generate_public_key)(struct kpp_request *req); + int (*compute_shared_secret)(struct kpp_request *req); + + int (*max_size)(struct crypto_kpp *tfm); + + int (*init)(struct crypto_kpp *tfm); + void (*exit)(struct crypto_kpp *tfm); + + unsigned int reqsize; + struct crypto_alg base; +}; + +/** + * DOC: Generic Key-agreement Protocol Primitevs API + * + * The KPP API is used with the algorithm type + * CRYPTO_ALG_TYPE_KPP (listed as type "kpp" in /proc/crypto) + */ + +/** + * crypto_alloc_kpp() - allocate KPP tfm handle + * @alg_name: is the name of the kpp algorithm (e.g. "dh", "ecdh") + * @type: specifies the type of the algorithm + * @mask: specifies the mask for the algorithm + * + * Allocate a handle for kpp algorithm. The returned struct crypto_kpp + * is requeried for any following API invocation + * + * Return: allocated handle in case of success; IS_ERR() is true in case of + * an error, PTR_ERR() returns the error code. + */ +struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask); + +static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm) +{ + return &tfm->base; +} + +static inline struct kpp_alg *__crypto_kpp_alg(struct crypto_alg *alg) +{ + return container_of(alg, struct kpp_alg, base); +} + +static inline struct crypto_kpp *__crypto_kpp_tfm(struct crypto_tfm *tfm) +{ + return container_of(tfm, struct crypto_kpp, base); +} + +static inline struct kpp_alg *crypto_kpp_alg(struct crypto_kpp *tfm) +{ + return __crypto_kpp_alg(crypto_kpp_tfm(tfm)->__crt_alg); +} + +static inline unsigned int crypto_kpp_reqsize(struct crypto_kpp *tfm) +{ + return crypto_kpp_alg(tfm)->reqsize; +} + +static inline void kpp_request_set_tfm(struct kpp_request *req, + struct crypto_kpp *tfm) +{ + req->base.tfm = crypto_kpp_tfm(tfm); +} + +static inline struct crypto_kpp *crypto_kpp_reqtfm(struct kpp_request *req) +{ + return __crypto_kpp_tfm(req->base.tfm); +} + +/** + * crypto_free_kpp() - free KPP tfm handle + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() + */ +static inline void crypto_free_kpp(struct crypto_kpp *tfm) +{ + crypto_destroy_tfm(tfm, crypto_kpp_tfm(tfm)); +} + +/** + * kpp_request_alloc() - allocates kpp request + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() + * @gfp: allocation flags + * + * Return: allocated handle in case of success or NULL in case of an error. + */ +static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm, + gfp_t gfp) +{ + struct kpp_request *req; + + req = kmalloc(sizeof(*req) + crypto_kpp_reqsize(tfm), gfp); + if (likely(req)) + kpp_request_set_tfm(req, tfm); + + return req; +} + +/** + * kpp_request_free() - zeroize and free kpp request + * + * @req: request to free + */ +static inline void kpp_request_free(struct kpp_request *req) +{ + kzfree(req); +} + +/** + * kpp_request_set_callback() - Sets an asynchronous callback. + * + * Callback will be called when an asynchronous operation on a given + * request is finished. + * + * @req: request that the callback will be set for + * @flgs: specify for instance if the operation may backlog + * @cmpl: callback which will be called + * @data: private data used by the caller + */ +static inline void kpp_request_set_callback(struct kpp_request *req, + u32 flgs, + crypto_completion_t cmpl, + void *data) +{ + req->base.complete = cmpl; + req->base.data = data; + req->base.flags = flgs; +} + +/** + * kpp_request_set_input() - Sets input buffer + * + * Sets parameters required by generate_public_key + * + * @req: kpp request + * @input: ptr to input scatter list + * @input_len: size of the input scatter list + */ +static inline void kpp_request_set_input(struct kpp_request *req, + struct scatterlist *input, + unsigned int input_len) +{ + req->src = input; + req->src_len = input_len; +} + +/** + * kpp_request_set_output() - Sets output buffer + * + * Sets parameters required by kpp operation + * + * @req: kpp request + * @output: ptr to output scatter list + * @output_len: size of the output scatter list + */ +static inline void kpp_request_set_output(struct kpp_request *req, + struct scatterlist *output, + unsigned int output_len) +{ + req->dst = output; + req->dst_len = output_len; +} + +enum { + CRYPTO_KPP_SECRET_TYPE_UNKNOWN, +}; + +/** + * struct kpp_secret - small header for packing secret buffer + * + * @type: define type of secret. Each kpp type will define its own + * @len: specify the len of the secret, include the header, that + * follows the struct + */ +struct kpp_secret { + unsigned short type; + unsigned short len; +}; + +/** + * crypto_kpp_set_secret() - Invoke kpp operation + * + * Function invokes the specific kpp operation for a given alg. + * + * @tfm: tfm handle + * + * Return: zero on success; error code in case of error + */ +static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, void *buffer, + unsigned int len) +{ + struct kpp_alg *alg = crypto_kpp_alg(tfm); + + return alg->set_secret(tfm, buffer, len); +} + +/** + * crypto_kpp_generate_public_key() - Invoke kpp operation + * + * Function invokes the specific kpp operation for generating the public part + * for a given kpp algorithm + * + * @req: kpp key request + * + * Return: zero on success; error code in case of error + */ +static inline int crypto_kpp_generate_public_key(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct kpp_alg *alg = crypto_kpp_alg(tfm); + + return alg->generate_public_key(req); +} + +/** + * crypto_kpp_compute_shared_secret() - Invoke kpp operation + * + * Function invokes the specific kpp operation for computing the shared secret + * for a given kpp algorithm. + * + * @req: kpp key request + * + * Return: zero on success; error code in case of error + */ +static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct kpp_alg *alg = crypto_kpp_alg(tfm); + + return alg->compute_shared_secret(req); +} + +/** + * crypto_kpp_maxsize() - Get len for output buffer + * + * Function returns the output buffer size required + * + * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() + * + * Return: minimum len for output buffer or error code if key hasn't been set + */ +static inline int crypto_kpp_maxsize(struct crypto_kpp *tfm) +{ + struct kpp_alg *alg = crypto_kpp_alg(tfm); + + return alg->max_size(tfm); +} + +#endif diff --git a/include/linux/crypto.h b/include/linux/crypto.h index d844cbc365f7..992cfc2e5df1 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -48,6 +48,7 @@ #define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 +#define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_AKCIPHER 0x0000000d #define CRYPTO_ALG_TYPE_DIGEST 0x0000000e diff --git a/include/uapi/linux/cryptouser.h b/include/uapi/linux/cryptouser.h index 2e67bb64c1da..79b5ded2001a 100644 --- a/include/uapi/linux/cryptouser.h +++ b/include/uapi/linux/cryptouser.h @@ -45,6 +45,7 @@ enum crypto_attr_type_t { CRYPTOCFGA_REPORT_RNG, /* struct crypto_report_rng */ CRYPTOCFGA_REPORT_CIPHER, /* struct crypto_report_cipher */ CRYPTOCFGA_REPORT_AKCIPHER, /* struct crypto_report_akcipher */ + CRYPTOCFGA_REPORT_KPP, /* struct crypto_report_kpp */ __CRYPTOCFGA_MAX #define CRYPTOCFGA_MAX (__CRYPTOCFGA_MAX - 1) @@ -107,5 +108,9 @@ struct crypto_report_akcipher { char type[CRYPTO_MAX_NAME]; }; +struct crypto_report_kpp { + char type[CRYPTO_MAX_NAME]; +}; + #define CRYPTO_REPORT_MAXSIZE (sizeof(struct crypto_user_alg) + \ sizeof(struct crypto_report_blkcipher)) -- cgit v1.2.3 From 802c7f1c84e4b5a6ac78635878041023fc5831b1 Mon Sep 17 00:00:00 2001 From: Salvatore Benedetto Date: Wed, 22 Jun 2016 17:49:14 +0100 Subject: crypto: dh - Add DH software implementation * Implement MPI based Diffie-Hellman under kpp API * Test provided uses data generad by OpenSSL Signed-off-by: Salvatore Benedetto Signed-off-by: Herbert Xu --- include/crypto/dh.h | 29 +++++++++++++++++++++++++++++ include/crypto/kpp.h | 1 + 2 files changed, 30 insertions(+) create mode 100644 include/crypto/dh.h (limited to 'include') diff --git a/include/crypto/dh.h b/include/crypto/dh.h new file mode 100644 index 000000000000..5102a8f282e6 --- /dev/null +++ b/include/crypto/dh.h @@ -0,0 +1,29 @@ +/* + * Diffie-Hellman secret to be used with kpp API along with helper functions + * + * Copyright (c) 2016, Intel Corporation + * Authors: Salvatore Benedetto + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_DH_ +#define _CRYPTO_DH_ + +struct dh { + void *key; + void *p; + void *g; + unsigned int key_size; + unsigned int p_size; + unsigned int g_size; +}; + +int crypto_dh_key_len(const struct dh *params); +int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params); +int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params); + +#endif diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index 4fa897f3366b..937ac122354a 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -242,6 +242,7 @@ static inline void kpp_request_set_output(struct kpp_request *req, enum { CRYPTO_KPP_SECRET_TYPE_UNKNOWN, + CRYPTO_KPP_SECRET_TYPE_DH, }; /** -- cgit v1.2.3 From 3c4b23901a0c766879dff680cd6bdab47bcdbbd2 Mon Sep 17 00:00:00 2001 From: Salvatore Benedetto Date: Wed, 22 Jun 2016 17:49:15 +0100 Subject: crypto: ecdh - Add ECDH software support * Implement ECDH under kpp API * Provide ECC software support for curve P-192 and P-256. * Add kpp test for ECDH with data generated by OpenSSL Signed-off-by: Salvatore Benedetto Signed-off-by: Herbert Xu --- include/crypto/ecdh.h | 30 ++++++++++++++++++++++++++++++ include/crypto/kpp.h | 1 + 2 files changed, 31 insertions(+) create mode 100644 include/crypto/ecdh.h (limited to 'include') diff --git a/include/crypto/ecdh.h b/include/crypto/ecdh.h new file mode 100644 index 000000000000..84bad548d194 --- /dev/null +++ b/include/crypto/ecdh.h @@ -0,0 +1,30 @@ +/* + * ECDH params to be used with kpp API + * + * Copyright (c) 2016, Intel Corporation + * Authors: Salvatore Benedetto + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ +#ifndef _CRYPTO_ECDH_ +#define _CRYPTO_ECDH_ + +/* Curves IDs */ +#define ECC_CURVE_NIST_P192 0x0001 +#define ECC_CURVE_NIST_P256 0x0002 + +struct ecdh { + unsigned short curve_id; + char *key; + unsigned short key_size; +}; + +int crypto_ecdh_key_len(const struct ecdh *params); +int crypto_ecdh_encode_key(char *buf, unsigned int len, const struct ecdh *p); +int crypto_ecdh_decode_key(const char *buf, unsigned int len, struct ecdh *p); + +#endif diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index 937ac122354a..30791f75c180 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -243,6 +243,7 @@ static inline void kpp_request_set_output(struct kpp_request *req, enum { CRYPTO_KPP_SECRET_TYPE_UNKNOWN, CRYPTO_KPP_SECRET_TYPE_DH, + CRYPTO_KPP_SECRET_TYPE_ECDH, }; /** -- cgit v1.2.3 From 506e65df52f2bf250aa9b4264efd180d1646bdec Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 10 Jun 2016 23:09:01 +0200 Subject: netfilter: make comparision helpers stub functions in ZONES=n case Those comparisions are useless in case of ZONES=n; all conntracks will reside in the same zone by definition. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_zones.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h index 4e32512cef32..bd4692690914 100644 --- a/include/net/netfilter/nf_conntrack_zones.h +++ b/include/net/netfilter/nf_conntrack_zones.h @@ -68,22 +68,34 @@ static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_matches_dir(zone, dir) ? zone->id : NF_CT_DEFAULT_ZONE_ID; +#else + return NF_CT_DEFAULT_ZONE_ID; +#endif } static inline bool nf_ct_zone_equal(const struct nf_conn *a, const struct nf_conntrack_zone *b, enum ip_conntrack_dir dir) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_id(nf_ct_zone(a), dir) == nf_ct_zone_id(b, dir); +#else + return true; +#endif } static inline bool nf_ct_zone_equal_any(const struct nf_conn *a, const struct nf_conntrack_zone *b) { +#ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone(a)->id == b->id; +#else + return true; +#endif } #endif /* IS_ENABLED(CONFIG_NF_CONNTRACK) */ #endif /* _NF_CONNTRACK_ZONES_H */ -- cgit v1.2.3 From 6c8dee9842461e6ee6eb46081478999b3d5cb297 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 11 Jun 2016 21:57:35 +0200 Subject: netfilter: move zone info into struct nf_conn Curently we store zone information as a conntrack extension. This has one drawback: for every lookup we need to fetch the zone data from the extension area. This change place the zone data directly into the main conntrack object structure and then removes the zone conntrack extension. The zone data is just 4 bytes, it fits into a padding hole before the tuplehash info, so we do not even increase the nf_conn structure size. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 +++ include/net/netfilter/nf_conntrack_extend.h | 4 ---- include/net/netfilter/nf_conntrack_zones.h | 33 ++++++++++------------------- 3 files changed, 14 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dd78bea227c8..9c0ed3d7af89 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -85,6 +85,9 @@ struct nf_conn { spinlock_t lock; u16 cpu; +#ifdef CONFIG_NF_CONNTRACK_ZONES + struct nf_conntrack_zone zone; +#endif /* XXX should I move this to the tail ? - Y.K */ /* These are my tuples; original and reply */ struct nf_conntrack_tuple_hash tuplehash[IP_CT_DIR_MAX]; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 55d15049ab2f..b925395fa5ed 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -15,9 +15,6 @@ enum nf_ct_ext_id { #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, #endif -#ifdef CONFIG_NF_CONNTRACK_ZONES - NF_CT_EXT_ZONE, -#endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_CT_EXT_TSTAMP, #endif @@ -38,7 +35,6 @@ enum nf_ct_ext_id { #define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj #define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache -#define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp #define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout #define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels diff --git a/include/net/netfilter/nf_conntrack_zones.h b/include/net/netfilter/nf_conntrack_zones.h index bd4692690914..64a718b60839 100644 --- a/include/net/netfilter/nf_conntrack_zones.h +++ b/include/net/netfilter/nf_conntrack_zones.h @@ -9,12 +9,11 @@ static inline const struct nf_conntrack_zone * nf_ct_zone(const struct nf_conn *ct) { - const struct nf_conntrack_zone *nf_ct_zone = NULL; - #ifdef CONFIG_NF_CONNTRACK_ZONES - nf_ct_zone = nf_ct_ext_find(ct, NF_CT_EXT_ZONE); + return &ct->zone; +#else + return &nf_ct_zone_dflt; #endif - return nf_ct_zone ? nf_ct_zone : &nf_ct_zone_dflt; } static inline const struct nf_conntrack_zone * @@ -31,32 +30,22 @@ static inline const struct nf_conntrack_zone * nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb, struct nf_conntrack_zone *tmp) { - const struct nf_conntrack_zone *zone; - +#ifdef CONFIG_NF_CONNTRACK_ZONES if (!tmpl) return &nf_ct_zone_dflt; - zone = nf_ct_zone(tmpl); - if (zone->flags & NF_CT_FLAG_MARK) - zone = nf_ct_zone_init(tmp, skb->mark, zone->dir, 0); - - return zone; + if (tmpl->zone.flags & NF_CT_FLAG_MARK) + return nf_ct_zone_init(tmp, skb->mark, tmpl->zone.dir, 0); +#endif + return nf_ct_zone(tmpl); } -static inline int nf_ct_zone_add(struct nf_conn *ct, gfp_t flags, - const struct nf_conntrack_zone *info) +static inline void nf_ct_zone_add(struct nf_conn *ct, + const struct nf_conntrack_zone *zone) { #ifdef CONFIG_NF_CONNTRACK_ZONES - struct nf_conntrack_zone *nf_ct_zone; - - nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, flags); - if (!nf_ct_zone) - return -ENOMEM; - - nf_ct_zone_init(nf_ct_zone, info->id, info->dir, - info->flags); + ct->zone = *zone; #endif - return 0; } static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, -- cgit v1.2.3 From 5fd251c8b4c52da0d0916470a67fbb77b972125e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:48 +0300 Subject: IB/core: Introduce Work Queue object and its verbs Introduce Work Queue object and its create/destroy/modify verbs. QP can be created without internal WQs "packaged" inside it, this QP can be configured to use "external" WQ object as its receive/send queue. WQ is a necessary component for RSS technology since RSS mechanism is supposed to distribute the traffic between multiple Receive Work Queues. WQ associated (many to one) with Completion Queue and it owns WQ properties (PD, WQ size, etc.). WQ has a type, this patch introduces the IB_WQT_RQ (i.e.receive queue), it may be extend to others such as IB_WQT_SQ. (send queue). WQ from type IB_WQT_RQ contains receive work requests. PD is an attribute of a work queue (i.e. send/receive queue), it's used by the hardware for security validation before scattering to a memory region which is pointed by the WQ. For that, an external WQ object needs a PD, letting the hardware makes that validation. When accessing a memory region that is pointed by the WQ its PD is used and not the QP's PD, this behavior is similar to a SRQ and a QP. WQ context is subject to a well-defined state transitions done by the modify_wq verb. When WQ is created its initial state becomes IB_WQS_RESET. >From IB_WQS_RESET it can be modified to itself or to IB_WQS_RDY. >From IB_WQS_RDY it can be modified to itself, to IB_WQS_RESET or to IB_WQS_ERR. >From IB_WQS_ERR it can be modified to IB_WQS_RESET. Note: transition to IB_WQS_ERR might occur implicitly in case there was some HW error. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 7e440d41487a..f2d954ac42f6 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1428,6 +1428,48 @@ struct ib_srq { } ext; }; +enum ib_wq_type { + IB_WQT_RQ +}; + +enum ib_wq_state { + IB_WQS_RESET, + IB_WQS_RDY, + IB_WQS_ERR +}; + +struct ib_wq { + struct ib_device *device; + struct ib_uobject *uobject; + void *wq_context; + void (*event_handler)(struct ib_event *, void *); + struct ib_pd *pd; + struct ib_cq *cq; + u32 wq_num; + enum ib_wq_state state; + enum ib_wq_type wq_type; + atomic_t usecnt; +}; + +struct ib_wq_init_attr { + void *wq_context; + enum ib_wq_type wq_type; + u32 max_wr; + u32 max_sge; + struct ib_cq *cq; + void (*event_handler)(struct ib_event *, void *); +}; + +enum ib_wq_attr_mask { + IB_WQ_STATE = 1 << 0, + IB_WQ_CUR_STATE = 1 << 1, +}; + +struct ib_wq_attr { + enum ib_wq_state wq_state; + enum ib_wq_state curr_wq_state; +}; + struct ib_qp { struct ib_device *device; struct ib_pd *pd; @@ -1921,7 +1963,14 @@ struct ib_device { struct ifla_vf_stats *stats); int (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid, int type); - + struct ib_wq * (*create_wq)(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr, + struct ib_udata *udata); + int (*destroy_wq)(struct ib_wq *wq); + int (*modify_wq)(struct ib_wq *wq, + struct ib_wq_attr *attr, + u32 wq_attr_mask, + struct ib_udata *udata); struct ib_dma_mapping_ops *dma_ops; struct module *owner; @@ -3167,6 +3216,11 @@ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); +struct ib_wq *ib_create_wq(struct ib_pd *pd, + struct ib_wq_init_attr *init_attr); +int ib_destroy_wq(struct ib_wq *wq); +int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, + u32 wq_attr_mask); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); -- cgit v1.2.3 From f213c05272100f385912372fff678d0af4d7f8ad Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:49 +0300 Subject: IB/uverbs: Add WQ support User space applications which use RSS functionality need to create a work queue object (WQ). The lifetime of such an object is: * Create a WQ * Modify the WQ from reset to init state. * Use the WQ (by downstream patches). * Destroy the WQ. These commands are added to the uverbs API. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 3 +++ include/uapi/rdma/ib_user_verbs.h | 41 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index f2d954ac42f6..0c1956a98573 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -562,6 +562,7 @@ enum ib_event_type { IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, + IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); @@ -572,6 +573,7 @@ struct ib_event { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; + struct ib_wq *wq; u8 port_num; } element; enum ib_event_type event; @@ -1323,6 +1325,7 @@ struct ib_ucontext { struct list_head ah_list; struct list_head xrcd_list; struct list_head rule_list; + struct list_head wq_list; int closing; struct pid *tgid; diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index b6543d73d20a..c9470e511e03 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -95,6 +95,9 @@ enum { IB_USER_VERBS_EX_CMD_CREATE_QP = IB_USER_VERBS_CMD_CREATE_QP, IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD, IB_USER_VERBS_EX_CMD_DESTROY_FLOW, + IB_USER_VERBS_EX_CMD_CREATE_WQ, + IB_USER_VERBS_EX_CMD_MODIFY_WQ, + IB_USER_VERBS_EX_CMD_DESTROY_WQ, }; /* @@ -946,4 +949,42 @@ struct ib_uverbs_destroy_srq_resp { __u32 events_reported; }; +struct ib_uverbs_ex_create_wq { + __u32 comp_mask; + __u32 wq_type; + __u64 user_handle; + __u32 pd_handle; + __u32 cq_handle; + __u32 max_wr; + __u32 max_sge; +}; + +struct ib_uverbs_ex_create_wq_resp { + __u32 comp_mask; + __u32 response_length; + __u32 wq_handle; + __u32 max_wr; + __u32 max_sge; + __u32 wqn; +}; + +struct ib_uverbs_ex_destroy_wq { + __u32 comp_mask; + __u32 wq_handle; +}; + +struct ib_uverbs_ex_destroy_wq_resp { + __u32 comp_mask; + __u32 response_length; + __u32 events_reported; + __u32 reserved; +}; + +struct ib_uverbs_ex_modify_wq { + __u32 attr_mask; + __u32 wq_handle; + __u32 wq_state; + __u32 curr_wq_state; +}; + #endif /* IB_USER_VERBS_H */ -- cgit v1.2.3 From 6d39786bf116e476d75eca91f7cfa22586a32e5f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:51 +0300 Subject: IB/core: Introduce Receive Work Queue indirection table Introduce Receive Work Queue (WQ) indirection table. This object can be used to spread incoming traffic to different receive Work Queues. A Receive WQ indirection table points to variable size of WQs. This table is given to a QP in downstream patches. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 0c1956a98573..fa2e0184dcc5 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1473,6 +1473,21 @@ struct ib_wq_attr { enum ib_wq_state curr_wq_state; }; +struct ib_rwq_ind_table { + struct ib_device *device; + struct ib_uobject *uobject; + atomic_t usecnt; + u32 ind_tbl_num; + u32 log_ind_tbl_size; + struct ib_wq **ind_tbl; +}; + +struct ib_rwq_ind_table_init_attr { + u32 log_ind_tbl_size; + /* Each entry is a pointer to Receive Work Queue */ + struct ib_wq **ind_tbl; +}; + struct ib_qp { struct ib_device *device; struct ib_pd *pd; @@ -1974,6 +1989,10 @@ struct ib_device { struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); + struct ib_rwq_ind_table * (*create_rwq_ind_table)(struct ib_device *device, + struct ib_rwq_ind_table_init_attr *init_attr, + struct ib_udata *udata); + int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); struct ib_dma_mapping_ops *dma_ops; struct module *owner; @@ -3224,6 +3243,10 @@ struct ib_wq *ib_create_wq(struct ib_pd *pd, int ib_destroy_wq(struct ib_wq *wq); int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask); +struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, + struct ib_rwq_ind_table_init_attr* + wq_ind_table_init_attr); +int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); -- cgit v1.2.3 From de019a94049d579608a5511f8c50652faf125182 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:52 +0300 Subject: IB/uverbs: Introduce RWQ Indirection table User applications that want to spread traffic on several WQs, need to create an indirection table, by using already created WQs. Adding uverbs API in order to create and destroy this table. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 1 + include/uapi/rdma/ib_user_verbs.h | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index fa2e0184dcc5..e305c9a36663 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1326,6 +1326,7 @@ struct ib_ucontext { struct list_head xrcd_list; struct list_head rule_list; struct list_head wq_list; + struct list_head rwq_ind_tbl_list; int closing; struct pid *tgid; diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index c9470e511e03..2cf7c95860d8 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -98,6 +98,8 @@ enum { IB_USER_VERBS_EX_CMD_CREATE_WQ, IB_USER_VERBS_EX_CMD_MODIFY_WQ, IB_USER_VERBS_EX_CMD_DESTROY_WQ, + IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL, + IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL }; /* @@ -987,4 +989,28 @@ struct ib_uverbs_ex_modify_wq { __u32 curr_wq_state; }; +/* Prevent memory allocation rather than max expected size */ +#define IB_USER_VERBS_MAX_LOG_IND_TBL_SIZE 0x0d +struct ib_uverbs_ex_create_rwq_ind_table { + __u32 comp_mask; + __u32 log_ind_tbl_size; + /* Following are the wq handles according to log_ind_tbl_size + * wq_handle1 + * wq_handle2 + */ + __u32 wq_handles[0]; +}; + +struct ib_uverbs_ex_create_rwq_ind_table_resp { + __u32 comp_mask; + __u32 response_length; + __u32 ind_tbl_handle; + __u32 ind_tbl_num; +}; + +struct ib_uverbs_ex_destroy_rwq_ind_table { + __u32 comp_mask; + __u32 ind_tbl_handle; +}; + #endif /* IB_USER_VERBS_H */ -- cgit v1.2.3 From a9017e232ff9eaabeb50eb89841d99310cfc98dc Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:54 +0300 Subject: IB/core: Extend create QP to get indirection table Extend create QP to get Receive Work Queue (WQ) indirection table. QP can be created with external Receive Work Queue indirection table, in that case it is ready to receive immediately. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e305c9a36663..9b2fafe5eb38 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1017,6 +1017,7 @@ struct ib_qp_init_attr { * Only needed for special QP types, or when using the RW API. */ u8 port_num; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_qp_open_attr { @@ -1511,6 +1512,7 @@ struct ib_qp { void *qp_context; u32 qp_num; enum ib_qp_type qp_type; + struct ib_rwq_ind_table *rwq_ind_tbl; }; struct ib_mr { -- cgit v1.2.3 From c70285f880e88cb4f73effb722065a182ba5936f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 23 May 2016 15:20:55 +0300 Subject: IB/uverbs: Extend create QP to get RWQ indirection table User applications that want to spread incoming traffic between several WQs should create a QP which contains an indirection table. When such a QP is created other receive side parameters are not valid and should not be given. Its send side is optional and assumed active based on max_send_wr capability value. Extend create QP to work accordingly. Signed-off-by: Yishai Hadas Signed-off-by: Matan Barak Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/uapi/rdma/ib_user_verbs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 2cf7c95860d8..2c8bca8cd2c2 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -523,6 +523,14 @@ struct ib_uverbs_create_qp { __u64 driver_data[0]; }; +enum ib_uverbs_create_qp_mask { + IB_UVERBS_CREATE_QP_MASK_IND_TABLE = 1UL << 0, +}; + +enum { + IB_UVERBS_CREATE_QP_SUP_COMP_MASK = IB_UVERBS_CREATE_QP_MASK_IND_TABLE, +}; + struct ib_uverbs_ex_create_qp { __u64 user_handle; __u32 pd_handle; @@ -540,6 +548,8 @@ struct ib_uverbs_ex_create_qp { __u8 reserved; __u32 comp_mask; __u32 create_flags; + __u32 rwq_ind_tbl_handle; + __u32 reserved1; }; struct ib_uverbs_open_qp { -- cgit v1.2.3 From 89ea94a7b6c40eb423c144aef1caceebaff79c8d Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 17 Jun 2016 15:01:38 +0300 Subject: IB/mlx5: Reset flow support for IB kernel ULPs The driver exposes interfaces that directly relate to HW state. Upon fatal error, consumers of these interfaces (ULPs) that rely on completion of all their posted work-request could hang, thereby introducing dependencies in shutdown order. To prevent this from happening, we manage the relevant resources (CQs, QPs) that are used by the device. Upon a fatal error, we now generate simulated completions for outstanding WQEs that were not completed at the time the HW was reset. It includes invoking the completion event handler for all involved CQs so that the ULPs will poll those CQs. When polled we return simulated CQEs with IB_WC_WR_FLUSH_ERR return code enabling ULPs to clean up their resources and not wait forever for completions upon receiving remove_one. The above change requires an extra check in the data path to make sure that when device is in error state, the simulated CQEs will be returned and no further WQEs will be posted. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/cq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 2be976dd4966..2566f6d6444f 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -58,6 +58,8 @@ struct mlx5_core_cq { void (*comp)(struct mlx5_core_cq *); void *priv; } tasklet_ctx; + int reset_notify_added; + struct list_head reset_notify; }; -- cgit v1.2.3 From 4c2aae712cb024f9d30a1fa62e3ba2ff785c6a3e Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 17 Jun 2016 15:14:50 +0300 Subject: IB/core: Add IPv6 support to flow steering Add IPv6 flow specification support. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 14 ++++++++++++++ include/uapi/rdma/ib_user_verbs.h | 18 ++++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9b2fafe5eb38..9bbca6887f7f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1569,6 +1569,7 @@ enum ib_flow_spec_type { IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, + IB_FLOW_SPEC_IPV6 = 0x31, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41 @@ -1630,6 +1631,18 @@ struct ib_flow_spec_ipv4 { struct ib_flow_ipv4_filter mask; }; +struct ib_flow_ipv6_filter { + u8 src_ip[16]; + u8 dst_ip[16]; +}; + +struct ib_flow_spec_ipv6 { + enum ib_flow_spec_type type; + u16 size; + struct ib_flow_ipv6_filter val; + struct ib_flow_ipv6_filter mask; +}; + struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; @@ -1651,6 +1664,7 @@ union ib_flow_spec { struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; + struct ib_flow_spec_ipv6 ipv6; }; struct ib_flow_attr { diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 2c8bca8cd2c2..7f035f4b53b0 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -867,6 +867,24 @@ struct ib_uverbs_flow_spec_tcp_udp { struct ib_uverbs_flow_tcp_udp_filter mask; }; +struct ib_uverbs_flow_ipv6_filter { + __u8 src_ip[16]; + __u8 dst_ip[16]; +}; + +struct ib_uverbs_flow_spec_ipv6 { + union { + struct ib_uverbs_flow_spec_hdr hdr; + struct { + __u32 type; + __u16 size; + __u16 reserved; + }; + }; + struct ib_uverbs_flow_ipv6_filter val; + struct ib_uverbs_flow_ipv6_filter mask; +}; + struct ib_uverbs_flow_attr { __u32 type; __u16 size; -- cgit v1.2.3 From e3353c268b06236d6c40fa1714c114f21f44451c Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Fri, 17 Jun 2016 15:33:31 +0300 Subject: IB/mlx5: Fix MODIFY_QP command input structure Make MODIFY_QP command input structure compliant to specification Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/qp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 266320feb160..acb28c989dee 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -555,9 +555,9 @@ struct mlx5_destroy_qp_mbox_out { struct mlx5_modify_qp_mbox_in { struct mlx5_inbox_hdr hdr; __be32 qpn; - u8 rsvd1[4]; - __be32 optparam; u8 rsvd0[4]; + __be32 optparam; + u8 rsvd1[4]; struct mlx5_qp_context ctx; u8 rsvd2[16]; }; -- cgit v1.2.3 From af1ba291c5e498973cc325c501dd8da80b234571 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Fri, 17 Jun 2016 15:33:32 +0300 Subject: {net, IB}/mlx5: Refactor internal SRQ API Currently, the SRQ API uses the obsolete mlx5_*_srq_mbox_{in,out} structs which limit the ability to pass the SRQ attributes between net and IB parts of the driver. This patch changes the SRQ API so as to use auto-generated structs and provides a better way to pass attributes which will be in use by coming features. Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 6 +++--- include/linux/mlx5/srq.h | 25 +++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80776d0c52dc..ba933335772c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -46,6 +46,7 @@ #include #include +#include enum { MLX5_RQ_BITMASK_VSD = 1 << 1, @@ -772,11 +773,10 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_create_srq_mbox_in *in, int inlen, - int is_xrc); + struct mlx5_srq_attr *in); int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq); int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_query_srq_mbox_out *out); + struct mlx5_srq_attr *out); int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, u16 lwm, int is_srq); void mlx5_init_mkey_table(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index f43ed054a3e0..33c97dc900f8 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -35,6 +35,31 @@ #include +enum { + MLX5_SRQ_FLAG_ERR = (1 << 0), + MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), +}; + +struct mlx5_srq_attr { + u32 type; + u32 flags; + u32 log_size; + u32 wqe_shift; + u32 log_page_size; + u32 wqe_cnt; + u32 srqn; + u32 xrcd; + u32 page_offset; + u32 cqn; + u32 pd; + u32 lwm; + u32 user_index; + u64 db_record; + u64 *pas; +}; + +struct mlx5_core_dev; + void mlx5_init_srq_table(struct mlx5_core_dev *dev); void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 5fa76c20458518ed6181adddef2e31c5afc0745c Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 15 Jun 2016 02:21:56 -0400 Subject: IB/core: Add get FW version string to the core Allow for a common core function to get firmware version strings from the individual devices. In later patches this format can then then be used to pass a properly formated version string through the IPoIB layer. The problem with the current code in the IPoIB layer is that it is specific to certain hardware types. Furthermore, this gives us a common function through which the core can provide a common sysfs entry. Eventually we may want to remove the sysfs export but this provides for user space backwards compatibility. Reviewed-by: Dennis Dalessandro Signed-off-by: Ira Weiny Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 7e440d41487a..1dc3d0d90202 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1956,6 +1956,7 @@ struct ib_device { * in fast paths. */ int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *); + void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len); }; struct ib_client { @@ -1991,6 +1992,8 @@ struct ib_client { struct ib_device *ib_alloc_device(size_t size); void ib_dealloc_device(struct ib_device *device); +void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len); + int ib_register_device(struct ib_device *device, int (*port_callback)(struct ib_device *, u8, struct kobject *)); -- cgit v1.2.3 From 765bf9b739731b925ca26a8f05765b87f2bd9724 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 8 Jun 2016 12:04:47 +0100 Subject: PCI: Add generic pci_bus_claim_resources() All PCI resources (bridge windows and BARs) should be inserted in the iomem_resource and ioport_resource trees so we know what space is occupied and what is available for other devices. There's nothing arch-specific about this, but it is currently done by arch-specific code. Add a generic pci_bus_claim_resources() interface so we can migrate away from the arch-specific code. [bhelgaas: changelog] Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas CC: Arnd Bergmann CC: Yinghai Lu --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 6af3b93f0710..d6cfecfee864 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1114,6 +1114,7 @@ int pci_set_vpd_size(struct pci_dev *dev, size_t len); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); void pci_bus_assign_resources(const struct pci_bus *bus); +void pci_bus_claim_resources(struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); int pci_claim_bridge_resource(struct pci_dev *bridge, int i); -- cgit v1.2.3 From d1bd330a229fc8a69f0e7532138dfd42b4542fd4 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 21 Jun 2016 01:17:17 +0100 Subject: of_mdio: Enable fixed PHY support if driver is a module The fixed_phy driver doesn't have to be built-in, and it's important that of_mdio supports it even if it's a module. Signed-off-by: Ben Hutchings Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 8f2237eb3485..6c8cb9aa4c00 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -69,7 +69,7 @@ static inline int of_mdio_parse_addr(struct device *dev, } #endif /* CONFIG_OF */ -#if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY) +#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_FIXED_PHY) extern int of_phy_register_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); #else -- cgit v1.2.3 From af7d5185263133f859dd4f35d45594deef9db854 Mon Sep 17 00:00:00 2001 From: Rana Shahout Date: Tue, 21 Jun 2016 12:43:59 +0300 Subject: net/mlx4_en: Add DCB PFC support through CEE netlink commands This patch adds support for reading and updating priority flow control (PFC) attributes in the driver via netlink. Signed-off-by: Rana Shahout Signed-off-by: Eran Ben Elisha Signed-off-by: Eugenia Emantayev Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 80dec87a94f8..4dbc1450bbe0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -535,6 +535,7 @@ struct mlx4_caps { int max_rq_desc_sz; int max_qp_init_rdma; int max_qp_dest_rdma; + int max_tc_eth; u32 *qp0_qkey; u32 *qp0_proxy; u32 *qp1_proxy; @@ -1494,6 +1495,7 @@ int mlx4_mr_rereg_mem_write(struct mlx4_dev *dev, struct mlx4_mr *mr, int mlx4_get_module_info(struct mlx4_dev *dev, u8 port, u16 offset, u16 size, u8 *data); +int mlx4_max_tc(struct mlx4_dev *dev); /* Returns true if running in low memory profile (kdump kernel) */ static inline bool mlx4_low_memory_profile(void) -- cgit v1.2.3 From 722003ac40c2c397bd5bc2b714125bc82ab27043 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Tue, 21 Jun 2016 09:36:21 -0400 Subject: qed: Add support for coalescing config read/update. This patch adds support for configuring the device tx/rx coalescing timeout values in the order of micro seconds. It also adds APIs for upper layer drivers for reading/updating the coalescing values. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index e1d5122e8a96..b1e3c57c7117 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -488,6 +488,30 @@ struct qed_common_ops { void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); +/** + * @brief get_coalesce - Get coalesce parameters in usec + * + * @param cdev + * @param rx_coal - Rx coalesce value in usec + * @param tx_coal - Tx coalesce value in usec + * + */ + void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal); + +/** + * @brief set_coalesce - Configure Rx coalesce value in usec + * + * @param cdev + * @param rx_coal - Rx coalesce value in usec + * @param tx_coal - Tx coalesce value in usec + * @param qid - Queue index + * @param sb_id - Status Block Id + * + * @return 0 on success, error otherwise. + */ + int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, + u8 qid, u16 sb_id); + /** * @brief set_led - Configure LED mode * -- cgit v1.2.3 From bb8e15d60462a84a25a3bf33e8bc29b46c6d470a Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 1 Jun 2016 14:06:15 +0800 Subject: of: iommu: make of_iommu_init() postcore_initcall_sync The of_iommu_init() is called multiple times by arch code, make it postcore_initcall_sync, then we can drop relevant calls fully. Note, the IOMMUs should have a chance to perform some basic initialisation before we start adding masters to them. So postcore_initcall_sync is good choice, it ensures of_iommu_init() called before of_platform_populate. Acked-by: Rich Felker Tested-by: Marek Szyprowski Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Marek Szyprowski Cc: Rich Felker Cc: Rob Herring Cc: Robin Murphy Cc: Will Deacon Signed-off-by: Kefeng Wang Acked-by: Joerg Roedel Signed-off-by: Rob Herring --- include/linux/of_iommu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h index bd02b44902d0..e80b9c762a03 100644 --- a/include/linux/of_iommu.h +++ b/include/linux/of_iommu.h @@ -11,7 +11,6 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix, int index, unsigned long *busno, dma_addr_t *addr, size_t *size); -extern void of_iommu_init(void); extern const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np); @@ -24,7 +23,6 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix, return -EINVAL; } -static inline void of_iommu_init(void) { } static inline const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np) { -- cgit v1.2.3 From 8654df4e2ac9704905198d63845554c2ddf6a93f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Jun 2016 16:06:06 -0500 Subject: mnt: Refactor fs_fully_visible into mount_too_revealing Replace the call of fs_fully_visible in do_new_mount from before the new superblock is allocated with a call of mount_too_revealing after the superblock is allocated. This winds up being a much better location for maintainability of the code. The first change this enables is the replacement of FS_USERNS_VISIBLE with SB_I_USERNS_VISIBLE. Moving the flag from struct filesystem_type to sb_iflags on the superblock. Unfortunately mount_too_revealing fundamentally needs to touch mnt_flags adding several MNT_LOCKED_XXX flags at the appropriate times. If the mnt_flags did not need to be touched the code could be easily moved into the filesystem specific mount code. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..71988dd3af95 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1328,6 +1328,9 @@ struct mm_struct; #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ +/* sb->s_iflags to limit user namespace mounts */ +#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ + /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ @@ -2011,7 +2014,6 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ -#define FS_USERNS_VISIBLE 32 /* FS must already be visible */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); -- cgit v1.2.3 From d91ee87d8d85a0808c01787e8b4a6b48f2ba487b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 23 May 2016 14:51:59 -0500 Subject: vfs: Pass data, ns, and ns->userns to mount_ns Today what is normally called data (the mount options) is not passed to fill_super through mount_ns. Pass the mount options and the namespace separately to mount_ns so that filesystems such as proc that have mount options, can use mount_ns. Pass the user namespace to mount_ns so that the standard permission check that verifies the mounter has permissions over the namespace can be performed in mount_ns instead of in each filesystems .mount method. Thus removing the duplication between mqueuefs and proc in terms of permission checks. The extra permission check does not currently affect the rpc_pipefs filesystem and the nfsd filesystem as those filesystems do not currently allow unprivileged mounts. Without unpvileged mounts it is guaranteed that the caller has already passed capable(CAP_SYS_ADMIN) which guarantees extra permission check will pass. Update rpc_pipefs and the nfsd filesystem to ensure that the network namespace reference is always taken in fill_super and always put in kill_sb so that the logic is simpler and so that errors originating inside of fill_super do not cause a network namespace leak. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 71988dd3af95..1ce006a24f49 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2034,8 +2034,9 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags, - void *data, int (*fill_super)(struct super_block *, void *, int)); +extern struct dentry *mount_ns(struct file_system_type *fs_type, + int flags, void *data, void *ns, struct user_namespace *user_ns, + int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -- cgit v1.2.3 From 6e4eab577a0cae15b3da9b888cff16fe57981b3e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 24 May 2016 09:29:01 -0500 Subject: fs: Add user namespace member to struct super_block Start marking filesystems with a user namespace owner, s_user_ns. In this change this is only used for permission checks of who may mount a filesystem. Ultimately s_user_ns will be used for translating ids and checking capabilities for filesystems mounted from user namespaces. The default policy for setting s_user_ns is implemented in sget(), which arranges for s_user_ns to be set to current_user_ns() and to ensure that the mounter of the filesystem has CAP_SYS_ADMIN in that user_ns. The guts of sget are split out into another function sget_userns(). The function sget_userns calls alloc_super with the specified user namespace or it verifies the existing superblock that was found has the expected user namespace, and fails with EBUSY when it is not. This failing prevents users with the wrong privileges mounting a filesystem. The reason for the split of sget_userns from sget is that in some cases such as mount_ns and kernfs_mount_ns a different policy for permission checking of mounts and setting s_user_ns is necessary, and the existence of sget_userns() allows those policies to be implemented. The helper mount_ns is expected to be used for filesystems such as proc and mqueuefs which present per namespace information. The function mount_ns is modified to call sget_userns instead of sget to ensure the user namespace owner of the namespace whose information is presented by the filesystem is used on the superblock. For sysfs and cgroup the appropriate permission checks are already in place, and kernfs_mount_ns is modified to call sget_userns so that the init_user_ns is the only user namespace used. For the cgroup filesystem cgroup namespace mounts are bind mounts of a subset of the full cgroup filesystem and as such s_user_ns must be the same for all of them as there is only a single superblock. Mounts of sysfs that vary based on the network namespace could in principle change s_user_ns but it keeps the analysis and implementation of kernfs simpler if that is not supported, and at present there appear to be no benefits from supporting a different s_user_ns on any sysfs mount. Getting the details of setting s_user_ns correct has been a long process. Thanks to Pavel Tikhorirorv who spotted a leak in sget_userns. Thanks to Seth Forshee who has kept the work alive. Thanks-to: Seth Forshee Thanks-to: Pavel Tikhomirov Acked-by: Seth Forshee Signed-off-by: Eric W. Biederman --- include/linux/fs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ce006a24f49..9eef64f23a75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1432,6 +1432,13 @@ struct super_block { struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; + /* + * Owning user namespace and default context in which to + * interpret filesystem uids, gids, quotas, device nodes, + * xattrs and security labels. + */ + struct user_namespace *s_user_ns; + /* * Keep the lru lists last in the structure so they always sit on their * own individual cachelines. @@ -2056,6 +2063,11 @@ void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); +struct super_block *sget_userns(struct file_system_type *type, + int (*test)(struct super_block *,void *), + int (*set)(struct super_block *,void *), + int flags, struct user_namespace *user_ns, + void *data); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), -- cgit v1.2.3 From a2982cc922c3068783eb9a1f77a5626a1ec36a1f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Jun 2016 15:34:02 -0500 Subject: vfs: Generalize filesystem nodev handling. Introduce a function may_open_dev that tests MNT_NODEV and a new superblock flab SB_I_NODEV. Use this new function in all of the places where MNT_NODEV was previously tested. Add the new SB_I_NODEV s_iflag to proc, sysfs, and mqueuefs as those filesystems should never support device nodes, and a simple superblock flags makes that very hard to get wrong. With SB_I_NODEV set if any device nodes somehow manage to show up on on a filesystem those device nodes will be unopenable. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9eef64f23a75..e05983170d23 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1327,6 +1327,7 @@ struct mm_struct; /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ +#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ @@ -1602,6 +1603,7 @@ extern int vfs_whiteout(struct inode *, struct dentry *); */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); +extern bool may_open_dev(const struct path *path); /* * VFS FS_IOC_FIEMAP helper definitions. */ -- cgit v1.2.3 From cc50a07a247e17db76b1f0b0ca06652556e04fa3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 9 Jun 2016 15:44:48 -0500 Subject: userns: Remove the now unnecessary FS_USERNS_DEV_MOUNT flag Now that SB_I_NODEV controls the nodev behavior devpts can just clear this flag during mount. Simplifying the code and making it easier to audit how the code works. While still preserving the invariant that s_iflags is only modified during mount. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index e05983170d23..375e37f42cdf 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2022,7 +2022,6 @@ struct file_system_type { #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ -#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); -- cgit v1.2.3 From eebc8e2c5b7a3db19075a02730db8b73be933485 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Fri, 17 Jun 2016 01:02:48 +0300 Subject: ARM: dts: r8a7792: add JPU clocks Add JPU clock and its parent, M2 clock to the R8A7792 device tree. Signed-off-by: Sergei Shtylyov Reviewed-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/dt-bindings/clock/r8a7792-clock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/r8a7792-clock.h b/include/dt-bindings/clock/r8a7792-clock.h index 949801eb0652..89a5155913f6 100644 --- a/include/dt-bindings/clock/r8a7792-clock.h +++ b/include/dt-bindings/clock/r8a7792-clock.h @@ -24,6 +24,7 @@ #define R8A7792_CLK_MSIOF0 0 /* MSTP1 */ +#define R8A7792_CLK_JPU 6 #define R8A7792_CLK_TMU1 11 #define R8A7792_CLK_TMU3 21 #define R8A7792_CLK_TMU2 22 -- cgit v1.2.3 From 7643507fe8b5bd8ab7522f6a81058cc1209d2585 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Tue, 21 Jun 2016 14:58:46 -0400 Subject: netfilter: xt_NFLOG: nflog-range does not truncate packets li->u.ulog.copy_len is currently ignored by the kernel, we should truncate the packet to either li->u.ulog.copy_len (if set) or copy_range before sending it to userspace. 0 is a valid input for copy_len, so add a new flag to indicate whether this was option was specified by the user or not. Add two flags to indicate whether nflog-size/copy_len was set or not. XT_NFLOG_F_COPY_LEN is for XT_NFLOG and NFLOG_F_COPY_LEN for nfnetlink_log On the userspace side, this was initially represented by the option nflog-range, this will be replaced by --nflog-size now. --nflog-range would still exist but does not do anything. Reported-by: Joe Dollard Reviewed-by: Josh Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_log.h | 7 +++++++ include/uapi/linux/netfilter/xt_NFLOG.h | 6 +++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h index 57639fca223a..83d855ba6af1 100644 --- a/include/net/netfilter/nf_log.h +++ b/include/net/netfilter/nf_log.h @@ -12,6 +12,9 @@ #define NF_LOG_UID 0x08 /* Log UID owning local socket */ #define NF_LOG_MASK 0x0f +/* This flag indicates that copy_len field in nf_loginfo is set */ +#define NF_LOG_F_COPY_LEN 0x1 + enum nf_log_type { NF_LOG_TYPE_LOG = 0, NF_LOG_TYPE_ULOG, @@ -22,9 +25,13 @@ struct nf_loginfo { u_int8_t type; union { struct { + /* copy_len will be used iff you set + * NF_LOG_F_COPY_LEN in flags + */ u_int32_t copy_len; u_int16_t group; u_int16_t qthreshold; + u_int16_t flags; } ulog; struct { u_int8_t level; diff --git a/include/uapi/linux/netfilter/xt_NFLOG.h b/include/uapi/linux/netfilter/xt_NFLOG.h index 87b58311ce6b..f33070730fc8 100644 --- a/include/uapi/linux/netfilter/xt_NFLOG.h +++ b/include/uapi/linux/netfilter/xt_NFLOG.h @@ -6,9 +6,13 @@ #define XT_NFLOG_DEFAULT_GROUP 0x1 #define XT_NFLOG_DEFAULT_THRESHOLD 0 -#define XT_NFLOG_MASK 0x0 +#define XT_NFLOG_MASK 0x1 + +/* This flag indicates that 'len' field in xt_nflog_info is set*/ +#define XT_NFLOG_F_COPY_LEN 0x1 struct xt_nflog_info { + /* 'len' will be used iff you set XT_NFLOG_F_COPY_LEN in flags */ __u32 len; __u16 group; __u16 threshold; -- cgit v1.2.3 From 889f7ee7c6e84251215d43cbc856ea116c72d3f2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 12 Jun 2016 18:07:07 +0200 Subject: netfilter: nf_tables: add generic macros to check for generation mask Thus, we can reuse these to check the genmask of any object type, not only rules. This is required now that tables, chain and sets will get a generation mask field too in follow up patches. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 092235458691..d0778cbaf7f1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -969,6 +969,30 @@ static inline u8 nft_genmask_cur(const struct net *net) #define NFT_GENMASK_ANY ((1 << 0) | (1 << 1)) +/* + * Generic transaction helpers + */ + +/* Check if this object is currently active. */ +#define nft_is_active(__net, __obj) \ + (((__obj)->genmask & nft_genmask_cur(__net)) == 0) + +/* Check if this object is active in the next generation. */ +#define nft_is_active_next(__net, __obj) \ + (((__obj)->genmask & nft_genmask_next(__net)) == 0) + +/* This object becomes active in the next generation. */ +#define nft_activate_next(__net, __obj) \ + (__obj)->genmask = nft_genmask_cur(__net) + +/* This object becomes inactive in the next generation. */ +#define nft_deactivate_next(__net, __obj) \ + (__obj)->genmask = nft_genmask_next(__net) + +/* After committing the ruleset, clear the stale generation bit. */ +#define nft_clear(__net, __obj) \ + (__obj)->genmask &= ~nft_genmask_next(__net) + /* * Set element transaction helpers */ -- cgit v1.2.3 From f2a6d766765d2794e26e25655d4ffcfe29c3ec2f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 14 Jun 2016 17:29:18 +0200 Subject: netfilter: nf_tables: add generation mask to tables This patch addresses two problems: 1) The netlink dump is inconsistent when interfering with an ongoing transaction update for several reasons: 1.a) We don't honor the internal NFT_TABLE_INACTIVE flag, and we should be skipping these inactive objects in the dump. 1.b) We perform speculative deletion during the preparation phase, that may result in skipping active objects. 1.c) The listing order changes, which generates noise when tracking incremental ruleset update via tools like git or our own testsuite. 2) We don't allow to add and to update the object in the same batch, eg. add table x; add table x { flags dormant\; }. In order to resolve these problems: 1) If the user requests a deletion, the object becomes inactive in the next generation. Then, ignore objects that scheduled to be deleted from the lookup path, as they will be effectively removed in the next generation. 2) From the get/dump path, if the object is not currently active, we skip it. 3) Support 'add X -> update X' sequence from a transaction. After this update, we obtain a consistent list as long as we stay in the same generation. The userspace side can detect interferences through the generation counter so it can restart the dumping. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d0778cbaf7f1..05c9a64b39aa 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -838,6 +838,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); * @hgenerator: handle generator state * @use: number of chain references to this table * @flags: table flag (see enum nft_table_flags) + * @genmask: generation mask * @name: name of the table */ struct nft_table { @@ -846,7 +847,8 @@ struct nft_table { struct list_head sets; u64 hgenerator; u32 use; - u16 flags; + u16 flags:14, + genmask:2; char name[NFT_TABLE_MAXNAMELEN]; }; @@ -992,6 +994,8 @@ static inline u8 nft_genmask_cur(const struct net *net) /* After committing the ruleset, clear the stale generation bit. */ #define nft_clear(__net, __obj) \ (__obj)->genmask &= ~nft_genmask_next(__net) +#define nft_active_genmask(__obj, __genmask) \ + !((__obj)->genmask & __genmask) /* * Set element transaction helpers -- cgit v1.2.3 From 664b0f8cd8c66d02d14168ee7ac6a957cc88177f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 12 Jun 2016 19:21:31 +0200 Subject: netfilter: nf_tables: add generation mask to chains Similar to ("netfilter: nf_tables: add generation mask to tables"). Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 05c9a64b39aa..b023e287ea92 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -732,7 +732,6 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) enum nft_chain_flags { NFT_BASE_CHAIN = 0x1, - NFT_CHAIN_INACTIVE = 0x2, }; /** @@ -754,7 +753,8 @@ struct nft_chain { u64 handle; u32 use; u16 level; - u8 flags; + u8 flags:6, + genmask:2; char name[NFT_CHAIN_MAXNAMELEN]; }; -- cgit v1.2.3 From 37a9cc52552579f22e18cca401cfc4351b6cbc72 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 12 Jun 2016 22:52:45 +0200 Subject: netfilter: nf_tables: add generation mask to sets Similar to ("netfilter: nf_tables: add generation mask to tables"). Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index b023e287ea92..07a5ba47cbda 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -296,6 +296,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @ops: set ops * @pnet: network namespace * @flags: set flags + * @genmask: generation mask * @klen: key length * @dlen: data length * @data: private set data @@ -317,7 +318,8 @@ struct nft_set { /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; possible_net_t pnet; - u16 flags; + u16 flags:14, + genmask:2; u8 klen; u8 dlen; unsigned char data[] @@ -335,9 +337,9 @@ static inline struct nft_set *nft_set_container_of(const void *priv) } struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla); + const struct nlattr *nla, u8 genmask); struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla); + const struct nlattr *nla, u8 genmask); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { -- cgit v1.2.3 From 3183ab8997a477c8d9ad175a1cef70dff77c6dbc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 22 Jun 2016 13:26:10 +0200 Subject: netfilter: conntrack: allow increasing bucket size via sysctl too No need to restrict this to module parameter. We export a copy of the real hash size -- when user alters the value we allocate the new table, copy entries etc before we update the real size to the requested one. This is also needed because the real size is used by concurrent readers and cannot be changed without synchronizing the conntrack generation seqcnt. We only allow changing this value from the initial net namespace. Tested using http-client-benchmark vs. httpterm with concurrent while true;do echo $RANDOM > /proc/sys/net/netfilter/nf_conntrack_buckets done Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 9c0ed3d7af89..5d3397f34583 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -290,6 +290,7 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) struct kernel_param; int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); +int nf_conntrack_hash_resize(unsigned int hashsize); extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; -- cgit v1.2.3 From 82bec71d46b83f39860e2838ff8394e4fcd6efab Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 22 Jun 2016 14:26:33 +0200 Subject: netfilter: nf_tables: get rid of NFT_BASECHAIN_DISABLED This flag was introduced to restore rulesets from the new netdev family, but since 5ebe0b0eec9d6f7 ("netfilter: nf_tables: destroy basechain and rules on netdevice removal") the ruleset is released once the netdev is gone. This also removes nft_register_basechain() and nft_unregister_basechain() since they have no clients anymore after this rework. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 07a5ba47cbda..1ea19a6e72e6 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -798,7 +798,6 @@ struct nft_stats { }; #define NFT_HOOK_OPS_MAX 2 -#define NFT_BASECHAIN_DISABLED (1 << 0) /** * struct nft_base_chain - nf_tables base chain -- cgit v1.2.3 From 0071e184a535e40ce487528cb04f4690cb0da881 Mon Sep 17 00:00:00 2001 From: Arturo Borrero Date: Thu, 23 Jun 2016 12:24:08 +0200 Subject: netfilter: nf_tables: add support for inverted logic in nft_lookup Introduce a new configuration option for this expression, which allows users to invert the logic of set lookups. In _init() we will now return EINVAL if NFT_LOOKUP_F_INV is in anyway related to a map lookup. The code in the _eval() function has been untangled and updated to sopport the XOR of options, as we should consider 4 cases: * lookup false, invert false -> NFT_BREAK * lookup false, invert true -> return w/o NFT_BREAK * lookup true, invert false -> return w/o NFT_BREAK * lookup true, invert true -> NFT_BREAK Signed-off-by: Arturo Borrero Gonzalez Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 6a4dbe04f09e..01751faccaf8 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -546,6 +546,10 @@ enum nft_cmp_attributes { }; #define NFTA_CMP_MAX (__NFTA_CMP_MAX - 1) +enum nft_lookup_flags { + NFT_LOOKUP_F_INV = (1 << 0), +}; + /** * enum nft_lookup_attributes - nf_tables set lookup expression netlink attributes * @@ -553,6 +557,7 @@ enum nft_cmp_attributes { * @NFTA_LOOKUP_SREG: source register of the data to look for (NLA_U32: nft_registers) * @NFTA_LOOKUP_DREG: destination register (NLA_U32: nft_registers) * @NFTA_LOOKUP_SET_ID: uniquely identifies a set in a transaction (NLA_U32) + * @NFTA_LOOKUP_FLAGS: flags (NLA_U32: enum nft_lookup_flags) */ enum nft_lookup_attributes { NFTA_LOOKUP_UNSPEC, @@ -560,6 +565,7 @@ enum nft_lookup_attributes { NFTA_LOOKUP_SREG, NFTA_LOOKUP_DREG, NFTA_LOOKUP_SET_ID, + NFTA_LOOKUP_FLAGS, __NFTA_LOOKUP_MAX }; #define NFTA_LOOKUP_MAX (__NFTA_LOOKUP_MAX - 1) -- cgit v1.2.3 From d07b846f6200454c50d791796edb82660192513d Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Wed, 23 Sep 2015 15:16:04 -0500 Subject: fs: Limit file caps to the user namespace of the super block Capability sets attached to files must be ignored except in the user namespaces where the mounter is privileged, i.e. s_user_ns and its descendants. Otherwise a vector exists for gaining privileges in namespaces where a user is not already privileged. Add a new helper function, current_in_user_ns(), to test whether a user namespace is the same as or a descendant of another namespace. Use this helper to determine whether a file's capability set should be applied to the caps constructed during exec. --EWB Replaced in_userns with the simpler current_in_userns. Acked-by: Serge Hallyn Signed-off-by: Seth Forshee Signed-off-by: Eric W. Biederman --- include/linux/user_namespace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 8297e5b341d8..9217169c64cb 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -72,6 +72,7 @@ extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); +extern bool current_in_userns(const struct user_namespace *target_ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) @@ -100,6 +101,11 @@ static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } + +static inline bool current_in_userns(const struct user_namespace *target_ns) +{ + return true; +} #endif #endif /* _LINUX_USER_H */ -- cgit v1.2.3 From 380cf5ba6b0a0b307f4afb62b186ca801defb203 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 23 Jun 2016 16:41:05 -0500 Subject: fs: Treat foreign mounts as nosuid If a process gets access to a mount from a different user namespace, that process should not be able to take advantage of setuid files or selinux entrypoints from that filesystem. Prevent this by treating mounts from other mount namespaces and those not owned by current_user_ns() or an ancestor as nosuid. This will make it safer to allow more complex filesystems to be mounted in non-root user namespaces. This does not remove the need for MNT_LOCK_NOSUID. The setuid, setgid, and file capability bits can no longer be abused if code in a user namespace were to clear nosuid on an untrusted filesystem, but this patch, by itself, is insufficient to protect the system from abuse of files that, when execed, would increase MAC privilege. As a more concrete explanation, any task that can manipulate a vfsmount associated with a given user namespace already has capabilities in that namespace and all of its descendents. If they can cause a malicious setuid, setgid, or file-caps executable to appear in that mount, then that executable will only allow them to elevate privileges in exactly the set of namespaces in which they are already privileges. On the other hand, if they can cause a malicious executable to appear with a dangerous MAC label, running it could change the caller's security context in a way that should not have been possible, even inside the namespace in which the task is confined. As a hardening measure, this would have made CVE-2014-5207 much more difficult to exploit. Signed-off-by: Andy Lutomirski Signed-off-by: Seth Forshee Acked-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/mount.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index f822c3c11377..54a594d49733 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -81,6 +81,7 @@ extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(struct path *path); extern int __mnt_is_readonly(struct vfsmount *mnt); +extern bool mnt_may_suid(struct vfsmount *mnt); struct path; extern struct vfsmount *clone_private_mount(struct path *path); -- cgit v1.2.3 From 6be2b3d0848d1ed3e78e416cc4ae9007e85c7533 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 6 Jun 2016 16:58:20 -0700 Subject: soc: qcom: wcnss_ctrl: Make wcnss_ctrl parent the other components We need the signal from wcnss_ctrl indicating that the firmware is up and running before we can communicate with the other components of the chip. So make these other components children of the wcnss_ctrl device, so they can be probed in order. The process seems to take between 1/2-5 seconds, so this is done in a worker, instead of holding up the probe. Signed-off-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/soc/qcom/wcnss_ctrl.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/linux/soc/qcom/wcnss_ctrl.h (limited to 'include') diff --git a/include/linux/soc/qcom/wcnss_ctrl.h b/include/linux/soc/qcom/wcnss_ctrl.h new file mode 100644 index 000000000000..a37bc5538f19 --- /dev/null +++ b/include/linux/soc/qcom/wcnss_ctrl.h @@ -0,0 +1,8 @@ +#ifndef __WCNSS_CTRL_H__ +#define __WCNSS_CTRL_H__ + +#include + +struct qcom_smd_channel *qcom_wcnss_open_channel(void *wcnss, const char *name, qcom_smd_cb_t cb); + +#endif -- cgit v1.2.3 From f295e53b60eb93ee53ed5ac610374ed293caa57b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 17 Jun 2016 11:08:06 -0700 Subject: libnvdimm, pmem: allow nfit_test to override pmem_direct_access() Currently phys_to_pfn_t() is an exported symbol to allow nfit_test to override it and indicate that nfit_test-pmem is not device-mapped. Now, we want to enable nfit_test to operate without DMA_CMA and the pmem it provides will no longer be physically contiguous, i.e. won't be capable of supporting direct_access requests larger than a page. Make pmem_direct_access() a weak symbol so that it can be replaced by the tools/testing/nvdimm/ version, and move phys_to_pfn_t() to a static inline now that it no longer needs to be overridden. Acked-by: Johannes Thumshirn Signed-off-by: Dan Williams --- include/linux/pfn_t.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 94994810c7c0..a3d90b9da18d 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -28,7 +28,10 @@ static inline pfn_t pfn_to_pfn_t(unsigned long pfn) return __pfn_to_pfn_t(pfn, 0); } -extern pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags); +static inline pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags) +{ + return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); +} static inline bool pfn_t_has_page(pfn_t pfn) { -- cgit v1.2.3 From 866ae696e26ee2b1fa0d04e67d6dafc477543fd6 Mon Sep 17 00:00:00 2001 From: Hoan Tran Date: Thu, 16 Jun 2016 14:09:38 -0700 Subject: mailbox: pcc: Add PCC request and free channel declarations Exports pcc_mbox_request_channel() and pcc_mbox_free_channel() declarations into a pcc.h header file. Looks-good-to: Prashanth Prakash Signed-off-by: Hoan Tran Signed-off-by: Rafael J. Wysocki --- include/acpi/cppc_acpi.h | 7 +------ include/acpi/pcc.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 6 deletions(-) create mode 100644 include/acpi/pcc.h (limited to 'include') diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index dad8af3ebeb5..284965cbc9af 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -15,10 +15,9 @@ #define _CPPC_ACPI_H #include -#include -#include #include +#include #include /* Only support CPPCv2 for now. */ @@ -130,8 +129,4 @@ extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls); extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps); extern int acpi_get_psd_map(struct cpudata **); -/* Methods to interact with the PCC mailbox controller. */ -extern struct mbox_chan * - pcc_mbox_request_channel(struct mbox_client *, unsigned int); - #endif /* _CPPC_ACPI_H*/ diff --git a/include/acpi/pcc.h b/include/acpi/pcc.h new file mode 100644 index 000000000000..17a940a14477 --- /dev/null +++ b/include/acpi/pcc.h @@ -0,0 +1,29 @@ +/* + * PCC (Platform Communications Channel) methods + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#ifndef _PCC_H +#define _PCC_H + +#include +#include + +#ifdef CONFIG_PCC +extern struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl, + int subspace_id); +extern void pcc_mbox_free_channel(struct mbox_chan *chan); +#else +static inline struct mbox_chan *pcc_mbox_request_channel(struct mbox_client *cl, + int subspace_id) +{ + return NULL; +} +static inline void pcc_mbox_free_channel(struct mbox_chan *chan) { } +#endif + +#endif /* _PCC_H */ -- cgit v1.2.3 From 0346223a2fefeda6e453e3dde44dc95c32d54d04 Mon Sep 17 00:00:00 2001 From: Arvind Yadav Date: Thu, 23 Jun 2016 00:26:01 +0530 Subject: ACPI / video: Dummy acpi_video_register should return error code The inline acpi_video_register stub simply allows compilation on systems with CONFIG_ACPI_VIDEO disabled. the dummy acpi_video_register does not register an acpi_bus_driver at all. The inline acpi_video_register should return to indicate lack of support when attempting to register an acpi_bus_driver on such a system with CONFIG_ACPI_VIDEO disabled. Signed-off-by: Arvind Yadav Reviewed-by: Aaron Lu Signed-off-by: Rafael J. Wysocki --- include/acpi/video.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/video.h b/include/acpi/video.h index 5731ccb42585..4536bd345ab4 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -54,7 +54,7 @@ extern int acpi_video_get_levels(struct acpi_device *device, struct acpi_video_device_brightness **dev_br, int *pmax_level); #else -static inline int acpi_video_register(void) { return 0; } +static inline int acpi_video_register(void) { return -ENODEV; } static inline void acpi_video_unregister(void) { return; } static inline int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, void **edid) -- cgit v1.2.3 From f01e90fe34f563a5e189d4070de4a23948105642 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Wed, 23 Sep 2015 12:56:12 -0700 Subject: firmware: qcom: scm: Peripheral Authentication Service This adds the Peripheral Authentication Service (PAS) interface to the Qualcomm SCM interface. The API is used to authenticate and boot a range of external processors in various Qualcomm platforms. Signed-off-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom_scm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 9e12000914b3..cc32ab852fbc 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -29,6 +29,14 @@ extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern bool qcom_scm_pas_supported(u32 peripheral); +extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, + size_t size); +extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, + phys_addr_t size); +extern int qcom_scm_pas_auth_and_reset(u32 peripheral); +extern int qcom_scm_pas_shutdown(u32 peripheral); + #define QCOM_SCM_CPU_PWR_DOWN_L2_ON 0x0 #define QCOM_SCM_CPU_PWR_DOWN_L2_OFF 0x1 -- cgit v1.2.3 From 2c2b217a13ed11ff6d8f4583f9bee3a54e8f1034 Mon Sep 17 00:00:00 2001 From: Christophe RICARD Date: Sat, 13 Feb 2016 16:15:31 +0100 Subject: tpm/st33zp24: Extend Copyright headers Extend copyright header to 2016 Signed-off-by: Christophe Ricard Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/platform_data/st33zp24.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/st33zp24.h b/include/linux/platform_data/st33zp24.h index 817dfdb37885..6f0fb6ebd7db 100644 --- a/include/linux/platform_data/st33zp24.h +++ b/include/linux/platform_data/st33zp24.h @@ -1,6 +1,6 @@ /* * STMicroelectronics TPM Linux driver for TPM 1.2 ST33ZP24 - * Copyright (C) 2009 - 2015 STMicroelectronics + * Copyright (C) 2009 - 2016 STMicroelectronics * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by -- cgit v1.2.3 From 6f99612e250041a2402d3b1694bccb149cd424a4 Mon Sep 17 00:00:00 2001 From: Stefan Berger Date: Mon, 18 Apr 2016 13:26:15 -0400 Subject: tpm: Proxy driver for supporting multiple emulated TPMs This patch implements a proxy driver for supporting multiple emulated TPMs in a system. The driver implements a device /dev/vtpmx that is used to created a client device pair /dev/tpmX (e.g., /dev/tpm10) and a server side that is accessed using a file descriptor returned by an ioctl. The device /dev/tpmX is the usual TPM device created by the core TPM driver. Applications or kernel subsystems can send TPM commands to it and the corresponding server-side file descriptor receives these commands and delivers them to an emulated TPM. The driver retrievs the TPM 1.2 durations and timeouts. Since this requires the startup of the TPM, we send a startup for TPM 1.2 as well as TPM 2. Signed-off-by: Stefan Berger Reviewed-by: Jason Gunthorpe CC: linux-kernel@vger.kernel.org CC: linux-doc@vger.kernel.org CC: linux-api@vger.kernel.org Reviewed-by: Jarkko Sakkinen Tested-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/uapi/linux/Kbuild | 1 + include/uapi/linux/vtpm_proxy.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) create mode 100644 include/uapi/linux/vtpm_proxy.h (limited to 'include') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 8bdae34d1f9a..ad821a3a99f5 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -454,6 +454,7 @@ header-y += virtio_scsi.h header-y += virtio_types.h header-y += vm_sockets.h header-y += vt.h +header-y += vtpm_proxy.h header-y += wait.h header-y += wanrouter.h header-y += watchdog.h diff --git a/include/uapi/linux/vtpm_proxy.h b/include/uapi/linux/vtpm_proxy.h new file mode 100644 index 000000000000..41e8e2252a30 --- /dev/null +++ b/include/uapi/linux/vtpm_proxy.h @@ -0,0 +1,36 @@ +/* + * Definitions for the VTPM proxy driver + * Copyright (c) 2015, 2016, IBM Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _UAPI_LINUX_VTPM_PROXY_H +#define _UAPI_LINUX_VTPM_PROXY_H + +#include +#include + +/* ioctls */ + +struct vtpm_proxy_new_dev { + __u32 flags; /* input */ + __u32 tpm_num; /* output */ + __u32 fd; /* output */ + __u32 major; /* output */ + __u32 minor; /* output */ +}; + +/* above flags */ +#define VTPM_PROXY_FLAG_TPM2 1 /* emulator is TPM 2 */ + +#define VTPM_PROXY_IOC_NEW_DEV _IOWR(0xa1, 0x00, struct vtpm_proxy_new_dev) + +#endif /* _UAPI_LINUX_VTPM_PROXY_H */ -- 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 --- include/linux/vt_kern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') 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 --- include/linux/console.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') 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 --- include/linux/console.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') 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 --- include/linux/console.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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 --- include/linux/console_struct.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') 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 --- include/linux/vt_kern.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') 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 --- include/linux/console_struct.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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 520ac30f45519b0a82dd92117c181d1d6144677b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Jun 2016 23:16:49 -0700 Subject: net_sched: drop packets after root qdisc lock is released Qdisc performance suffers when packets are dropped at enqueue() time because drops (kfree_skb()) are done while qdisc lock is held, delaying a dequeue() draining the queue. Nominal throughput can be reduced by 50 % when this happens, at a time we would like the dequeue() to proceed as fast as possible. Even FQ is vulnerable to this problem, while one of FQ goals was to provide some flow isolation. This patch adds a 'struct sk_buff **to_free' parameter to all qdisc->enqueue(), and in qdisc_drop() helper. I measured a performance increase of up to 12 %, but this patch is a prereq so that future batches in enqueue() can fly. Signed-off-by: Eric Dumazet Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/sch_generic.h | 41 ++++++++++++++++++++++++++++++----------- 1 file changed, 30 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4f7cee8344c4..04e84c07c94f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -37,8 +37,10 @@ struct qdisc_size_table { }; struct Qdisc { - int (*enqueue)(struct sk_buff *skb, struct Qdisc *dev); - struct sk_buff * (*dequeue)(struct Qdisc *dev); + int (*enqueue)(struct sk_buff *skb, + struct Qdisc *sch, + struct sk_buff **to_free); + struct sk_buff * (*dequeue)(struct Qdisc *sch); unsigned int flags; #define TCQ_F_BUILTIN 1 #define TCQ_F_INGRESS 2 @@ -160,7 +162,9 @@ struct Qdisc_ops { char id[IFNAMSIZ]; int priv_size; - int (*enqueue)(struct sk_buff *, struct Qdisc *); + int (*enqueue)(struct sk_buff *skb, + struct Qdisc *sch, + struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); @@ -498,10 +502,11 @@ static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, #endif } -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) { qdisc_calculate_pkt_len(skb, sch); - return sch->enqueue(skb, sch); + return sch->enqueue(skb, sch, to_free); } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) @@ -626,24 +631,36 @@ static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) return __qdisc_dequeue_head(sch, &sch->q); } +/* Instead of calling kfree_skb() while root qdisc lock is held, + * queue the skb for future freeing at end of __dev_xmit_skb() + */ +static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) +{ + skb->next = *to_free; + *to_free = skb; +} + static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct sk_buff **to_free) { struct sk_buff *skb = __skb_dequeue(list); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); - kfree_skb(skb); + __qdisc_drop(skb, to_free); return len; } return 0; } -static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch) +static inline unsigned int qdisc_queue_drop_head(struct Qdisc *sch, + struct sk_buff **to_free) { - return __qdisc_queue_drop_head(sch, &sch->q); + return __qdisc_queue_drop_head(sch, &sch->q, to_free); } static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) @@ -724,9 +741,11 @@ static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) qdisc_qstats_drop(sch); } -static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) + +static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) { - kfree_skb(skb); + __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; -- cgit v1.2.3 From 008830bc321c0fc22c0db8d5b0b56f854ed90a5c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Jun 2016 23:16:50 -0700 Subject: net_sched: fq_codel: cache skb->truesize into skb->cb Now we defer skb drops, it makes sense to keep a copy of skb->truesize in struct codel_skb_cb to avoid one cache line miss per dropped skb in fq_codel_drop(), to reduce latencies a bit further. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/codel_qdisc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/codel_qdisc.h b/include/net/codel_qdisc.h index 8144d9cd2908..098630f83a55 100644 --- a/include/net/codel_qdisc.h +++ b/include/net/codel_qdisc.h @@ -52,6 +52,7 @@ /* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */ struct codel_skb_cb { codel_time_t enqueue_time; + unsigned int mem_usage; }; static struct codel_skb_cb *get_codel_cb(const struct sk_buff *skb) -- cgit v1.2.3 From 4d202a0d31b96ab3324b21e7500d9a2da9ef57dd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Jun 2016 23:16:52 -0700 Subject: net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet Cc: John Fastabend Cc: Jesper Dangaard Brouer Cc: Hannes Frederic Sowa Cc: Florian Westphal Cc: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/sch_generic.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 04e84c07c94f..909aff2db2b3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -75,13 +75,14 @@ struct Qdisc { /* * For performance sake on SMP, we put highly modified fields at the end */ - struct Qdisc *next_sched ____cacheline_aligned_in_smp; - struct sk_buff *gso_skb; - unsigned long state; + struct sk_buff *gso_skb ____cacheline_aligned_in_smp; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; seqcount_t running; struct gnet_stats_queue qstats; + unsigned long state; + struct Qdisc *next_sched; + struct sk_buff *skb_bad_txq; struct rcu_head rcu_head; int padded; atomic_t refcnt; -- 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 --- include/linux/dma/hsu.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') 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 --- include/linux/serial_8250.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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 d6faca40f40b62aca8ea8c29289c7bf7456172bb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 1 Jun 2016 16:46:23 +0200 Subject: rtc: move mc146818 helper functions out-of-line The mc146818_get_time/mc146818_set_time functions are rather large inline functions in a global header file and are used in several drivers and in x86 specific code. Here we move them into a separate .c file that is compiled whenever any of the users require it. This also lets us remove the linux/acpi.h header inclusion from mc146818rtc.h, which in turn avoids some warnings about duplicate definition of the TRUE/FALSE macros. Signed-off-by: Arnd Bergmann Signed-off-by: Alexandre Belloni --- include/linux/mc146818rtc.h | 193 +------------------------------------------- 1 file changed, 2 insertions(+), 191 deletions(-) (limited to 'include') diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index e9e346b37846..a585b4b5fa0e 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -17,10 +17,6 @@ #include #include -#ifdef CONFIG_ACPI -#include -#endif - #ifdef __KERNEL__ #include /* spinlock_t */ extern spinlock_t rtc_lock; /* serialize CMOS RAM access */ @@ -126,192 +122,7 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ -/* - * Returns true if a clock update is in progress - */ -static inline unsigned char mc146818_is_updating(void) -{ - unsigned char uip; - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); - spin_unlock_irqrestore(&rtc_lock, flags); - return uip; -} - -static inline unsigned int mc146818_get_time(struct rtc_time *time) -{ - unsigned char ctrl; - unsigned long flags; - unsigned char century = 0; - -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_year; -#endif - - /* - * read RTC once any update in progress is done. The update - * can take just over 2ms. We wait 20ms. There is no need to - * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. - * If you need to know *exactly* when a second has started, enable - * periodic update complete interrupts, (via ioctl) and then - * immediately read /dev/rtc which will block until you get the IRQ. - * Once the read clears, read the RTC time (again via ioctl). Easy. - */ - if (mc146818_is_updating()) - mdelay(20); - - /* - * Only the values that we read from the RTC are set. We leave - * tm_wday, tm_yday and tm_isdst untouched. Even though the - * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated - * by the RTC when initially set to a non-zero value. - */ - spin_lock_irqsave(&rtc_lock, flags); - time->tm_sec = CMOS_READ(RTC_SECONDS); - time->tm_min = CMOS_READ(RTC_MINUTES); - time->tm_hour = CMOS_READ(RTC_HOURS); - time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); - time->tm_mon = CMOS_READ(RTC_MONTH); - time->tm_year = CMOS_READ(RTC_YEAR); -#ifdef CONFIG_MACH_DECSTATION - real_year = CMOS_READ(RTC_DEC_YEAR); -#endif -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - ctrl = CMOS_READ(RTC_CONTROL); - spin_unlock_irqrestore(&rtc_lock, flags); - - if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - time->tm_sec = bcd2bin(time->tm_sec); - time->tm_min = bcd2bin(time->tm_min); - time->tm_hour = bcd2bin(time->tm_hour); - time->tm_mday = bcd2bin(time->tm_mday); - time->tm_mon = bcd2bin(time->tm_mon); - time->tm_year = bcd2bin(time->tm_year); - century = bcd2bin(century); - } - -#ifdef CONFIG_MACH_DECSTATION - time->tm_year += real_year - 72; -#endif - - if (century) - time->tm_year += (century - 19) * 100; - - /* - * Account for differences between how the RTC uses the values - * and how they are defined in a struct rtc_time; - */ - if (time->tm_year <= 69) - time->tm_year += 100; - - time->tm_mon--; - - return RTC_24H; -} - -/* Set the current date and time in the real time clock. */ -static inline int mc146818_set_time(struct rtc_time *time) -{ - unsigned long flags; - unsigned char mon, day, hrs, min, sec; - unsigned char save_control, save_freq_select; - unsigned int yrs; -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_yrs, leap_yr; -#endif - unsigned char century = 0; - - yrs = time->tm_year; - mon = time->tm_mon + 1; /* tm_mon starts at zero */ - day = time->tm_mday; - hrs = time->tm_hour; - min = time->tm_min; - sec = time->tm_sec; - - if (yrs > 255) /* They are unsigned */ - return -EINVAL; - - spin_lock_irqsave(&rtc_lock, flags); -#ifdef CONFIG_MACH_DECSTATION - real_yrs = yrs; - leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || - !((yrs + 1900) % 400)); - yrs = 72; - - /* - * We want to keep the year set to 73 until March - * for non-leap years, so that Feb, 29th is handled - * correctly. - */ - if (!leap_yr && mon < 3) { - real_yrs--; - yrs = 73; - } -#endif - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) { - century = (yrs + 1900) / 100; - yrs %= 100; - } -#endif - - /* These limits and adjustments are independent of - * whether the chip is in binary mode or not. - */ - if (yrs > 169) { - spin_unlock_irqrestore(&rtc_lock, flags); - return -EINVAL; - } - - if (yrs >= 100) - yrs -= 100; - - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) - || RTC_ALWAYS_BCD) { - sec = bin2bcd(sec); - min = bin2bcd(min); - hrs = bin2bcd(hrs); - day = bin2bcd(day); - mon = bin2bcd(mon); - yrs = bin2bcd(yrs); - century = bin2bcd(century); - } - - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - -#ifdef CONFIG_MACH_DECSTATION - CMOS_WRITE(real_yrs, RTC_DEC_YEAR); -#endif - CMOS_WRITE(yrs, RTC_YEAR); - CMOS_WRITE(mon, RTC_MONTH); - CMOS_WRITE(day, RTC_DAY_OF_MONTH); - CMOS_WRITE(hrs, RTC_HOURS); - CMOS_WRITE(min, RTC_MINUTES); - CMOS_WRITE(sec, RTC_SECONDS); -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - CMOS_WRITE(century, acpi_gbl_FADT.century); -#endif - - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - spin_unlock_irqrestore(&rtc_lock, flags); - - return 0; -} +unsigned int mc146818_get_time(struct rtc_time *time); +int mc146818_set_time(struct rtc_time *time); #endif /* _MC146818RTC_H */ -- cgit v1.2.3 From 613e97218ccbd7f33895cad4525d861810a9d5d5 Mon Sep 17 00:00:00 2001 From: Adam Thomson Date: Tue, 21 Jun 2016 18:50:20 +0100 Subject: device property: Add function to search for named child of device For device nodes in both DT and ACPI, it possible to have named child nodes which contain properties (an existing example being gpio-leds). This adds a function to find a named child node for a device which can be used by drivers for property retrieval. For DT data node name matching, of_node_cmp() and similar functions are made available outside of CONFIG_OF block so the new function can reference these for DT and non-DT builds. For ACPI data node name matching, a helper function is also added which returns false if CONFIG_ACPI is not set, otherwise it performs a string comparison on the data node name. This avoids using the acpi_data_node struct for non CONFIG_ACPI builds, which would otherwise cause a build failure. Signed-off-by: Adam Thomson Acked-by: Sathyanarayana Nujella Acked-by: Rob Herring Acked-by: Rafael J. Wysocki Signed-off-by: Mark Brown --- include/acpi/acpi_bus.h | 7 +++++++ include/linux/acpi.h | 6 ++++++ include/linux/of.h | 14 +++++++------- include/linux/property.h | 3 +++ 4 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 788c6c35291a..c1a524de67c5 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -420,6 +420,13 @@ static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwn container_of(fwnode, struct acpi_data_node, fwnode) : NULL; } +static inline bool acpi_data_node_match(struct fwnode_handle *fwnode, + const char *name) +{ + return is_acpi_data_node(fwnode) ? + (!strcmp(to_acpi_data_node(fwnode)->name, name)) : false; +} + static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return &adev->fwnode; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..03039c472e95 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -568,6 +568,12 @@ static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwn return NULL; } +static inline bool acpi_data_node_match(struct fwnode_handle *fwnode, + const char *name) +{ + return false; +} + static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; diff --git a/include/linux/of.h b/include/linux/of.h index c7292e8ea080..8455741e313e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -238,13 +238,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 #endif -/* Default string compare functions, Allow arch asm/prom.h to override */ -#if !defined(of_compat_cmp) -#define of_compat_cmp(s1, s2, l) strcasecmp((s1), (s2)) -#define of_prop_cmp(s1, s2) strcmp((s1), (s2)) -#define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) -#endif - #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) @@ -726,6 +719,13 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ +/* Default string compare functions, Allow arch asm/prom.h to override */ +#if !defined(of_compat_cmp) +#define of_compat_cmp(s1, s2, l) strcasecmp((s1), (s2)) +#define of_prop_cmp(s1, s2) strcmp((s1), (s2)) +#define of_node_cmp(s1, s2) strcasecmp((s1), (s2)) +#endif + #if defined(CONFIG_OF) && defined(CONFIG_NUMA) extern int of_node_to_nid(struct device_node *np); #else diff --git a/include/linux/property.h b/include/linux/property.h index ecab11e40794..3a2f9ae25c86 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -77,6 +77,9 @@ struct fwnode_handle *device_get_next_child_node(struct device *dev, for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) +struct fwnode_handle *device_get_named_child_node(struct device *dev, + const char *childname); + void fwnode_handle_put(struct fwnode_handle *fwnode); unsigned int device_get_child_node_count(struct device *dev); -- 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 --- include/linux/usb/xhci_pdriver.h | 27 --------------------------- 1 file changed, 27 deletions(-) delete mode 100644 include/linux/usb/xhci_pdriver.h (limited to 'include') 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 --- include/linux/mod_devicetable.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') 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 */ -- cgit v1.2.3 From fca23e47dfdbcdacaae523f8b87d2240ce056ac1 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Tue, 21 Jun 2016 14:40:11 +0200 Subject: leds: Add no-op gpio_led_register_device when LED subsystem is disabled Some systems use 'gpio_led_register_device' to make an in-memory copy of their LED device table so the original can be removed as .init.rodata. When the LED subsystem is not enabled source in the led directory is not built and so this function may be undefined. Fix this here. Signed-off-by: Andrew F. Davis Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/leds.h b/include/linux/leds.h index 0aa3701f2bf4..8a3b5d29602f 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -387,8 +387,16 @@ struct gpio_led_platform_data { unsigned long *delay_off); }; +#ifdef CONFIG_NEW_LEDS struct platform_device *gpio_led_register_device( int id, const struct gpio_led_platform_data *pdata); +#else +static inline struct platform_device *gpio_led_register_device( + int id, const struct gpio_led_platform_data *pdata) +{ + return 0; +} +#endif enum cpu_led_event { CPU_LED_IDLE_START, /* CPU enters idle */ -- cgit v1.2.3 From 1466cc5b23d18e7b6b8f1a45443d595393dbcae7 Mon Sep 17 00:00:00 2001 From: Yevgeny Petrilin Date: Thu, 23 Jun 2016 17:02:37 +0300 Subject: net/mlx5: Rate limit tables support Configuring and managing HW rate limit tables. The HW holds a table of rate limits, each rate is associated with an index in that table. Later a Send Queue uses this index to set the rate limit. Multiple Send Queues can have the same rate limit, which is represented by a single entry in this table. Even though a rate can be shared, each queue is being rate limited independently of others. The SW shadow of this table holds the rate itself, the index in the HW table and the refcount (number of queues) working with this rate. The exported functions are mlx5_rl_add_rate and mlx5_rl_remove_rate. Number of different rates and their values are derived from HW capabilities. Signed-off-by: Yevgeny Petrilin Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 4 ++++ include/linux/mlx5/driver.h | 27 +++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 73a48479892d..e0a3ed758287 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1330,6 +1330,7 @@ enum mlx5_cap_type { MLX5_CAP_ESWITCH, MLX5_CAP_RESERVED, MLX5_CAP_VECTOR_CALC, + MLX5_CAP_QOS, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1414,6 +1415,9 @@ enum mlx5_cap_type { MLX5_GET(vector_calc_cap, \ mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap) +#define MLX5_CAP_QOS(mdev, cap)\ + MLX5_GET(qos_cap, mdev->hca_caps_cur[MLX5_CAP_QOS], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80776d0c52dc..46260fdc5305 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -481,6 +481,21 @@ struct mlx5_fc_stats { struct mlx5_eswitch; +struct mlx5_rl_entry { + u32 rate; + u16 index; + u16 refcount; +}; + +struct mlx5_rl_table { + /* protect rate limit table */ + struct mutex rl_lock; + u16 max_size; + u32 max_rate; + u32 min_rate; + struct mlx5_rl_entry *rl_entry; +}; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; @@ -544,6 +559,7 @@ struct mlx5_priv { struct mlx5_flow_root_namespace *esw_ingress_root_ns; struct mlx5_fc_stats fc_stats; + struct mlx5_rl_table rl_table; }; enum mlx5_device_state { @@ -861,6 +877,12 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev, int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev, u8 port_num, void *out, size_t sz); +int mlx5_init_rl_table(struct mlx5_core_dev *dev); +void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); +int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index); +void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate); +bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate); + static inline int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -938,6 +960,11 @@ static inline int mlx5_get_gid_table_len(u16 param) return 8 * (1 << param); } +static inline bool mlx5_rl_is_supported(struct mlx5_core_dev *dev) +{ + return !!(dev->priv.rl_table.max_size); +} + enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; -- cgit v1.2.3 From 667daedaecd15b89d0ded7af49519f28d6ea2cf4 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 23 Jun 2016 17:02:42 +0300 Subject: net/mlx5e: Toggle link only after modifying port parameters Add a dedicated function to toggle port link. It should be called only after setting a port register. Toggle will set port link to down and bring it back up in case that it's admin status was up. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 9851862c0ec5..4adfac15f0e9 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -67,6 +67,7 @@ int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, u8 local_port); int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, int proto_mask); +void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, -- cgit v1.2.3 From 89da45b8b5b2187734a11038b8593714f964ffd1 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 23 Jun 2016 17:02:43 +0300 Subject: ethtool: Add 50G baseSR2 link mode Add ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT bit. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Cc: Ben Hutchings Cc: David Decotigny Acked-By: David Decotigny Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 5f030b46cff4..b8f38e84d93a 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1362,6 +1362,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT = 37, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT = 38, ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40, /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* @@ -1370,7 +1371,7 @@ enum ethtool_link_mode_bit_indices { */ __ETHTOOL_LINK_MODE_LAST - = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, }; #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ -- cgit v1.2.3 From 52244d960755936fa9c8ce54d583d0ed46f24fb6 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 23 Jun 2016 17:02:46 +0300 Subject: net/mlx5e: Report correct auto negotiation and allow toggling Previous to this patch auto negotiation was reported off although it was on by default in hardware. This patch reports the correct information to ethtool and allows the user to toggle it on/off. Added another parameter to set port proto function in order to pass the auto negotiation field to the hardware. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/port.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 4adfac15f0e9..e3012cc64b8a 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -47,6 +47,14 @@ enum mlx5_module_id { MLX5_MODULE_ID_QSFP28 = 0x11, }; +enum mlx5_an_status { + MLX5_AN_UNAVAILABLE = 0, + MLX5_AN_COMPLETE = 1, + MLX5_AN_FAILED = 2, + MLX5_AN_LINK_UP = 3, + MLX5_AN_LINK_DOWN = 4, +}; + #define MLX5_EEPROM_MAX_BYTES 32 #define MLX5_EEPROM_IDENTIFIER_BYTE_MASK 0x000000ff #define MLX5_I2C_ADDR_LOW 0x50 @@ -65,14 +73,17 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, int proto_mask, u8 local_port); -int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, - int proto_mask); +int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin, int proto_mask); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration); +void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, + u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); -- cgit v1.2.3 From d68fa32dccc136bb4e092d53606bb6f5515fa972 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 23:20:37 +0200 Subject: rtc: ds17287: remove unused header ds17287rtc.h is unused since 15beb694c661 ("mips: ip32: add platform data hooks to use DS1685 driver"), remove it. Signed-off-by: Alexandre Belloni --- include/linux/ds17287rtc.h | 66 ---------------------------------------------- 1 file changed, 66 deletions(-) delete mode 100644 include/linux/ds17287rtc.h (limited to 'include') diff --git a/include/linux/ds17287rtc.h b/include/linux/ds17287rtc.h deleted file mode 100644 index d85d3f497b96..000000000000 --- a/include/linux/ds17287rtc.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * ds17287rtc.h - register definitions for the ds1728[57] RTC / CMOS RAM - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * (C) 2003 Guido Guenther - */ -#ifndef __LINUX_DS17287RTC_H -#define __LINUX_DS17287RTC_H - -#include /* get the user-level API */ -#include - -/* Register A */ -#define DS_REGA_DV2 0x40 /* countdown chain */ -#define DS_REGA_DV1 0x20 /* oscillator enable */ -#define DS_REGA_DV0 0x10 /* bank select */ - -/* bank 1 registers */ -#define DS_B1_MODEL 0x40 /* model number byte */ -#define DS_B1_SN1 0x41 /* serial number byte 1 */ -#define DS_B1_SN2 0x42 /* serial number byte 2 */ -#define DS_B1_SN3 0x43 /* serial number byte 3 */ -#define DS_B1_SN4 0x44 /* serial number byte 4 */ -#define DS_B1_SN5 0x45 /* serial number byte 5 */ -#define DS_B1_SN6 0x46 /* serial number byte 6 */ -#define DS_B1_CRC 0x47 /* CRC byte */ -#define DS_B1_CENTURY 0x48 /* Century byte */ -#define DS_B1_DALARM 0x49 /* date alarm */ -#define DS_B1_XCTRL4A 0x4a /* extendec control register 4a */ -#define DS_B1_XCTRL4B 0x4b /* extendec control register 4b */ -#define DS_B1_RTCADDR2 0x4e /* rtc address 2 */ -#define DS_B1_RTCADDR3 0x4f /* rtc address 3 */ -#define DS_B1_RAMLSB 0x50 /* extended ram LSB */ -#define DS_B1_RAMMSB 0x51 /* extended ram MSB */ -#define DS_B1_RAMDPORT 0x53 /* extended ram data port */ - -/* register details */ -/* extended control register 4a */ -#define DS_XCTRL4A_VRT2 0x80 /* valid ram and time */ -#define DS_XCTRL4A_INCR 0x40 /* increment progress status */ -#define DS_XCTRL4A_BME 0x20 /* burst mode enable */ -#define DS_XCTRL4A_PAB 0x08 /* power active bar ctrl */ -#define DS_XCTRL4A_RF 0x04 /* ram clear flag */ -#define DS_XCTRL4A_WF 0x02 /* wake up alarm flag */ -#define DS_XCTRL4A_KF 0x01 /* kickstart flag */ - -/* interrupt causes */ -#define DS_XCTRL4A_IFS (DS_XCTRL4A_RF|DS_XCTRL4A_WF|DS_XCTRL4A_KF) - -/* extended control register 4b */ -#define DS_XCTRL4B_ABE 0x80 /* auxiliary battery enable */ -#define DS_XCTRL4B_E32K 0x40 /* enable 32.768 kHz Output */ -#define DS_XCTRL4B_CS 0x20 /* crystal select */ -#define DS_XCTRL4B_RCE 0x10 /* ram clear enable */ -#define DS_XCTRL4B_PRS 0x08 /* PAB resec select */ -#define DS_XCTRL4B_RIE 0x04 /* ram clear interrupt enable */ -#define DS_XCTRL4B_WFE 0x02 /* wake up alarm interrupt enable */ -#define DS_XCTRL4B_KFE 0x01 /* kickstart interrupt enable */ - -/* interrupt enable bits */ -#define DS_XCTRL4B_IFES (DS_XCTRL4B_RIE|DS_XCTRL4B_WFE|DS_XCTRL4B_KFE) - -#endif /* __LINUX_DS17287RTC_H */ -- cgit v1.2.3 From 10c2a2e71301deb4d7760c140606bc61841aacd3 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 23:38:44 +0200 Subject: rtc: ds2404: move rtc-ds2404.h to platform_data rtc-ds2404.h belongs to include/linux/platform_data/ Signed-off-by: Alexandre Belloni --- include/linux/platform_data/rtc-ds2404.h | 20 ++++++++++++++++++++ include/linux/rtc-ds2404.h | 20 -------------------- 2 files changed, 20 insertions(+), 20 deletions(-) create mode 100644 include/linux/platform_data/rtc-ds2404.h delete mode 100644 include/linux/rtc-ds2404.h (limited to 'include') diff --git a/include/linux/platform_data/rtc-ds2404.h b/include/linux/platform_data/rtc-ds2404.h new file mode 100644 index 000000000000..22c53825528f --- /dev/null +++ b/include/linux/platform_data/rtc-ds2404.h @@ -0,0 +1,20 @@ +/* + * ds2404.h - platform data structure for the DS2404 RTC. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2012 Sven Schnelle + */ + +#ifndef __LINUX_DS2404_H +#define __LINUX_DS2404_H + +struct ds2404_platform_data { + + unsigned int gpio_rst; + unsigned int gpio_clk; + unsigned int gpio_dq; +}; +#endif diff --git a/include/linux/rtc-ds2404.h b/include/linux/rtc-ds2404.h deleted file mode 100644 index 22c53825528f..000000000000 --- a/include/linux/rtc-ds2404.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * ds2404.h - platform data structure for the DS2404 RTC. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2012 Sven Schnelle - */ - -#ifndef __LINUX_DS2404_H -#define __LINUX_DS2404_H - -struct ds2404_platform_data { - - unsigned int gpio_rst; - unsigned int gpio_clk; - unsigned int gpio_dq; -}; -#endif -- 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 +++-- 1 file changed, 3 insertions(+), 2 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)]; -- 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 --- include/linux/efi.h | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include') 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 --- include/linux/efi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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 --- include/linux/extcon.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include') 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 --- include/linux/extcon.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') 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 --- include/linux/buffer_head.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') 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 86b2efbe3a390e07dbba725ef700b0d143e9a385 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Fri, 24 Jun 2016 16:35:46 -0400 Subject: audit: add fields to exclude filter by reusing user filter RFE: add additional fields for use in audit filter exclude rules https://github.com/linux-audit/audit-kernel/issues/5 Re-factor and combine audit_filter_type() with audit_filter_user() to use audit_filter_user_rules() to enable the exclude filter to additionally filter on PID, UID, GID, AUID, LOGINUID_SET, SUBJ_*. The process of combining the similar audit_filter_user() and audit_filter_type() functions, required inverting the meaning and including the ALWAYS action of the latter. Include audit_filter_user_rules() into audit_filter(), removing unneeded logic in the process. Keep the check to quit early if the list is empty. Signed-off-by: Richard Guy Briggs [PM: checkpatch.pl fixes - whitespace damage, wrapped description] Signed-off-by: Paul Moore --- include/linux/audit.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index e38e3fc13ea8..9d4443f93db6 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -163,8 +163,6 @@ extern void audit_log_task_info(struct audit_buffer *ab, extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ -extern int audit_filter_user(int type); -extern int audit_filter_type(int type); extern int audit_rule_change(int type, __u32 portid, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); -- cgit v1.2.3 From d28f6df1305a86715e4e7ea0f043ba01c0a0e8d9 Mon Sep 17 00:00:00 2001 From: Geoff Levand Date: Thu, 23 Jun 2016 17:54:48 +0000 Subject: arm64/kexec: Add core kexec support Add three new files, kexec.h, machine_kexec.c and relocate_kernel.S to the arm64 architecture that add support for the kexec re-boot mechanism (CONFIG_KEXEC) on arm64 platforms. Signed-off-by: Geoff Levand Reviewed-by: James Morse [catalin.marinas@arm.com: removed dead code following James Morse's comments] Signed-off-by: Catalin Marinas --- include/uapi/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 99048e501b88..aae5ebf2022b 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -39,6 +39,7 @@ #define KEXEC_ARCH_SH (42 << 16) #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) +#define KEXEC_ARCH_AARCH64 (183 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 -- cgit v1.2.3 From 803bb30145df3132f9c8c8704d11a9e6732340c7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 22:57:52 +0200 Subject: rtc: m48t86: move m48t86.h to platform_data m48t86.h belongs to include/linux/platform_data/ Acked-by: Jason Cooper Acked-by: H Hartley Sweeten Acked-by: Alexander Clouter Signed-off-by: Alexandre Belloni --- include/linux/m48t86.h | 16 ---------------- include/linux/platform_data/rtc-m48t86.h | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 16 deletions(-) delete mode 100644 include/linux/m48t86.h create mode 100644 include/linux/platform_data/rtc-m48t86.h (limited to 'include') diff --git a/include/linux/m48t86.h b/include/linux/m48t86.h deleted file mode 100644 index 915d6b4f0f89..000000000000 --- a/include/linux/m48t86.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * ST M48T86 / Dallas DS12887 RTC driver - * Copyright (c) 2006 Tower Technologies - * - * Author: Alessandro Zummo - * - * 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. -*/ - -struct m48t86_ops -{ - void (*writebyte)(unsigned char value, unsigned long addr); - unsigned char (*readbyte)(unsigned long addr); -}; diff --git a/include/linux/platform_data/rtc-m48t86.h b/include/linux/platform_data/rtc-m48t86.h new file mode 100644 index 000000000000..915d6b4f0f89 --- /dev/null +++ b/include/linux/platform_data/rtc-m48t86.h @@ -0,0 +1,16 @@ +/* + * ST M48T86 / Dallas DS12887 RTC driver + * Copyright (c) 2006 Tower Technologies + * + * Author: Alessandro Zummo + * + * 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. +*/ + +struct m48t86_ops +{ + void (*writebyte)(unsigned char value, unsigned long addr); + unsigned char (*readbyte)(unsigned long addr); +}; -- cgit v1.2.3 From 3333cb7187b9c8d28f7a6405bbe9cec7a10efdc8 Mon Sep 17 00:00:00 2001 From: Paul Handrigan Date: Mon, 20 Jun 2016 11:45:18 -0500 Subject: ASoC: cs35l33: Initial commit of the cs35l33 CODEC driver. Initial commit of the Cirrus Logic cs35l33 8V boosted class D amplifier. Signed-off-by: Paul Handrigan Signed-off-by: Mark Brown --- include/sound/cs35l33.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) create mode 100644 include/sound/cs35l33.h (limited to 'include') diff --git a/include/sound/cs35l33.h b/include/sound/cs35l33.h new file mode 100644 index 000000000000..b6eadce76fc8 --- /dev/null +++ b/include/sound/cs35l33.h @@ -0,0 +1,48 @@ +/* + * linux/sound/cs35l33.h -- Platform data for CS35l33 + * + * Copyright (c) 2016 Cirrus Logic Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __CS35L33_H +#define __CS35L33_H + +struct cs35l33_hg { + bool enable_hg_algo; + unsigned int mem_depth; + unsigned int release_rate; + unsigned int hd_rm; + unsigned int ldo_thld; + unsigned int ldo_path_disable; + unsigned int ldo_entry_delay; + bool vp_hg_auto; + unsigned int vp_hg; + unsigned int vp_hg_rate; + unsigned int vp_hg_va; +}; + +struct cs35l33_pdata { + /* Boost Controller Voltage Setting */ + unsigned int boost_ctl; + + /* Boost Controller Peak Current */ + unsigned int boost_ipk; + + /* Amplifier Drive Select */ + unsigned int amp_drv_sel; + + /* soft volume ramp */ + unsigned int ramp_rate; + + /* IMON adc scale */ + unsigned int imon_adc_scale; + + /* H/G algo configuration */ + struct cs35l33_hg hg_config; +}; + +#endif /* __CS35L33_H */ -- cgit v1.2.3 From 3de56099591a4042556a2d05d4703387ad950c6f Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Fri, 24 Jun 2016 13:58:07 +0530 Subject: regulator: tps65217: Enable suspend configuration The TPS65217 has a pre-defined power-up / power-down sequence which in a typical application does not need to be changed. However, it is possible to define custom sequences under I2C control. The power-up sequence is defined by strobes and delay times. Each output rail is assigned to a strobe to determine the order in which the rails are enabled. Every regulator of tps65217 PMIC has sequence registers and every regulator has a default strobe value and gets disabled when a particular power down sequence occurs. To keep a regulator on during suspend we write value 0 to strobe so that the regulator is out of all sequencers and is not impacted by any power down sequence. Hence saving the default strobe value during probe so that when we want to regulator to be enabled during suspend we write 0 to strobe and when we want it to get disabled during suspend we write the default saved strobe value. This allows platform data to specify which power rails should be on or off during RTC only suspend. This is necessary to keep DDR state while in RTC only suspend. Signed-off-by: Russ Dill [Enhanced commit log and added dynamic allocation for strobes] Signed-off-by: Keerthy Signed-off-by: Mark Brown --- include/linux/mfd/tps65217.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index ac7fba44d7e4..1c88231496d3 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -257,6 +257,7 @@ struct tps65217 { unsigned long id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regmap *regmap; + u8 *strobes; }; static inline struct tps65217 *dev_to_tps65217(struct device *dev) -- cgit v1.2.3 From b9a0d359413d7f4e078d81cd59f9d851a6febb7a Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 24 Jun 2016 13:58:08 +0530 Subject: regulator: tps65218: Enable suspend configuration TPS65218 has a pre-defined power-up / power-down sequence which in a typical application does not need to be changed. However, it is possible to define custom sequences under I2C control. The power-up sequence is defined by strobes and delay times. Each output rail is assigned to a strobe to determine the order in which the rails are enabled. Every regulator has sequence registers and every regulator has a default strobe value and gets disabled when a particular power down sequence occurs. To keep a regulator on during suspend we write value 0 to strobe so that the regulator is out of all sequencers and is not impacted by any power down sequence. Hence saving the default strobe value during probe so that when we want to regulator to be enabled during suspend we write 0 to strobe and when we want it to get disabled during suspend we write the default saved strobe value. This allows platform data to specify which power rails should be on or off during RTC only suspend. This is necessary to keep DDR state while in RTC only suspend. Signed-off-by: Tero Kristo Signed-off-by: Keerthy Signed-off-by: Mark Brown --- include/linux/mfd/tps65218.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h index d58f3b5f585a..7fdf5326f34e 100644 --- a/include/linux/mfd/tps65218.h +++ b/include/linux/mfd/tps65218.h @@ -246,6 +246,7 @@ enum tps65218_irqs { * @name: Voltage regulator name * @min_uV: minimum micro volts * @max_uV: minimum micro volts + * @strobe: sequencing strobe value for the regulator * * This data is used to check the regualtor voltage limits while setting. */ @@ -254,6 +255,7 @@ struct tps_info { const char *name; int min_uV; int max_uV; + int strobe; }; /** -- cgit v1.2.3 From cb72d38211eacda2dd90b09540542b6582da614e Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:46 -0400 Subject: netlabel: Initial support for the CALIPSO netlink protocol. CALIPSO is a packet labelling protocol for IPv6 which is very similar to CIPSO. It is specified in RFC 5570. Much of the code is based on the current CIPSO code. This adds support for adding passthrough-type CALIPSO DOIs through the NLBL_CALIPSO_C_ADD command. It requires attributes: NLBL_CALIPSO_A_TYPE which must be CALIPSO_MAP_PASS. NLBL_CALIPSO_A_DOI. In passthrough mode the CALIPSO engine will map MLS secattr levels and categories directly to the packet label. At this stage, the major difference between this and the CIPSO code is that IPv6 may be compiled as a module. To allow for this the CALIPSO functions are registered at module init time. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/calipso.h | 79 ++++++++++++++++++++++++++++++++++++++++++++++ include/net/netlabel.h | 23 ++++++++++++++ include/uapi/linux/audit.h | 2 ++ 3 files changed, 104 insertions(+) create mode 100644 include/net/calipso.h (limited to 'include') diff --git a/include/net/calipso.h b/include/net/calipso.h new file mode 100644 index 000000000000..38dbb4707150 --- /dev/null +++ b/include/net/calipso.h @@ -0,0 +1,79 @@ +/* + * CALIPSO - Common Architecture Label IPv6 Security Option + * + * This is an implementation of the CALIPSO protocol as specified in + * RFC 5570. + * + * Authors: Paul Moore + * Huw Davies + * + */ + +/* + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * (c) Copyright Huw Davies , 2015 + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see . + * + */ + +#ifndef _CALIPSO_H +#define _CALIPSO_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* known doi values */ +#define CALIPSO_DOI_UNKNOWN 0x00000000 + +/* doi mapping types */ +#define CALIPSO_MAP_UNKNOWN 0 +#define CALIPSO_MAP_PASS 2 + +/* + * CALIPSO DOI definitions + */ + +/* DOI definition struct */ +struct calipso_doi { + u32 doi; + u32 type; + + atomic_t refcount; + struct list_head list; + struct rcu_head rcu; +}; + +#ifdef CONFIG_NETLABEL +int __init calipso_init(void); +void calipso_exit(void); +#else +static inline int __init calipso_init(void) +{ + return 0; +} + +static inline void calipso_exit(void) +{ +} +#endif /* CONFIG_NETLABEL */ + +#endif /* _CALIPSO_H */ diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 7b5a300de7f5..6af1bb6df4ab 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -40,6 +40,7 @@ #include struct cipso_v4_doi; +struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label @@ -94,6 +95,8 @@ struct cipso_v4_doi; #define NETLBL_NLTYPE_UNLABELED_NAME "NLBL_UNLBL" #define NETLBL_NLTYPE_ADDRSELECT 6 #define NETLBL_NLTYPE_ADDRSELECT_NAME "NLBL_ADRSEL" +#define NETLBL_NLTYPE_CALIPSO 7 +#define NETLBL_NLTYPE_CALIPSO_NAME "NLBL_CALIPSO" /* * NetLabel - Kernel API for accessing the network packet label mappings. @@ -216,6 +219,23 @@ struct netlbl_lsm_secattr { } attr; }; +/** + * struct netlbl_calipso_ops - NetLabel CALIPSO operations + * @doi_add: add a CALIPSO DOI + * @doi_free: free a CALIPSO DOI + * + * Description: + * This structure is filled out by the CALIPSO engine and passed + * to the NetLabel core via a call to netlbl_calipso_ops_register(). + * It enables the CALIPSO engine (and hence IPv6) to be compiled + * as a module. + */ +struct netlbl_calipso_ops { + int (*doi_add)(struct calipso_doi *doi_def, + struct netlbl_audit *audit_info); + void (*doi_free)(struct calipso_doi *doi_def); +}; + /* * LSM security attribute operations (inline) */ @@ -598,4 +618,7 @@ static inline struct audit_buffer *netlbl_audit_start(int type, } #endif /* CONFIG_NETLABEL */ +const struct netlbl_calipso_ops * +netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops); + #endif /* _NETLABEL_H */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index d820aa979620..82e8aa59446b 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -130,6 +130,8 @@ #define AUDIT_MAC_IPSEC_EVENT 1415 /* Audit an IPSec event */ #define AUDIT_MAC_UNLBL_STCADD 1416 /* NetLabel: add a static label */ #define AUDIT_MAC_UNLBL_STCDEL 1417 /* NetLabel: del a static label */ +#define AUDIT_MAC_CALIPSO_ADD 1418 /* NetLabel: add CALIPSO DOI entry */ +#define AUDIT_MAC_CALIPSO_DEL 1419 /* NetLabel: del CALIPSO DOI entry */ #define AUDIT_FIRST_KERN_ANOM_MSG 1700 #define AUDIT_LAST_KERN_ANOM_MSG 1799 -- cgit v1.2.3 From a5e34490c3160e09814403d040765b0ae0003121 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:47 -0400 Subject: netlabel: Add support for querying a CALIPSO DOI. Query a specified DOI through the NLBL_CALIPSO_C_LIST command. It requires the attribute: NLBL_CALIPSO_A_DOI. The reply will contain: NLBL_CALIPSO_A_MTYPE Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 6af1bb6df4ab..0f05b83851e2 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -223,6 +223,8 @@ struct netlbl_lsm_secattr { * struct netlbl_calipso_ops - NetLabel CALIPSO operations * @doi_add: add a CALIPSO DOI * @doi_free: free a CALIPSO DOI + * @doi_getdef: returns a reference to a DOI + * @doi_putdef: releases a reference of a DOI * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -234,6 +236,8 @@ struct netlbl_calipso_ops { int (*doi_add)(struct calipso_doi *doi_def, struct netlbl_audit *audit_info); void (*doi_free)(struct calipso_doi *doi_def); + struct calipso_doi *(*doi_getdef)(u32 doi); + void (*doi_putdef)(struct calipso_doi *doi_def); }; /* -- cgit v1.2.3 From e1ce69df7e6e8cbdca78ae831ecf435b12b4c168 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:48 -0400 Subject: netlabel: Add support for enumerating the CALIPSO DOI list. Enumerate the DOI list through the NLBL_CALIPSO_C_LISTALL command. It takes no attributes. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 0f05b83851e2..2653d3a8cde8 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -225,6 +225,7 @@ struct netlbl_lsm_secattr { * @doi_free: free a CALIPSO DOI * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI + * @doi_walk: enumerate the DOI list * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -238,6 +239,9 @@ struct netlbl_calipso_ops { void (*doi_free)(struct calipso_doi *doi_def); struct calipso_doi *(*doi_getdef)(u32 doi); void (*doi_putdef)(struct calipso_doi *doi_def); + int (*doi_walk)(u32 *skip_cnt, + int (*callback)(struct calipso_doi *doi_def, void *arg), + void *cb_arg); }; /* -- cgit v1.2.3 From d7cce01504a0ccb95b5007d846560cfccbc1947f Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:49 -0400 Subject: netlabel: Add support for removing a CALIPSO DOI. Remove a specified DOI through the NLBL_CALIPSO_C_REMOVE command. It requires the attribute: NLBL_CALIPSO_A_DOI. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 2653d3a8cde8..2c0513b0cc88 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -237,6 +237,7 @@ struct netlbl_calipso_ops { int (*doi_add)(struct calipso_doi *doi_def, struct netlbl_audit *audit_info); void (*doi_free)(struct calipso_doi *doi_def); + int (*doi_remove)(u32 doi, struct netlbl_audit *audit_info); struct calipso_doi *(*doi_getdef)(u32 doi); void (*doi_putdef)(struct calipso_doi *doi_def); int (*doi_walk)(u32 *skip_cnt, -- cgit v1.2.3 From e67ae213c72f72be50561c060ae17e92426651da Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:50 -0400 Subject: ipv6: Add ipv6_renew_options_kern() that accepts a kernel mem pointer. The functionality is equivalent to ipv6_renew_options() except that the newopt pointer is in kernel, not user, memory The kernel memory implementation will be used by the CALIPSO network labelling engine, which needs to be able to set IPv6 hop-by-hop options. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/ipv6.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d0aeb97aec5d..887313d978d0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -308,6 +308,12 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, int newtype, struct ipv6_opt_hdr __user *newopt, int newoptlen); +struct ipv6_txoptions * +ipv6_renew_options_kern(struct sock *sk, + struct ipv6_txoptions *opt, + int newtype, + struct ipv6_opt_hdr *newopt, + int newoptlen); struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); -- cgit v1.2.3 From 3faa8f982f958961fda68b8d63e682fe77a032d4 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:51 -0400 Subject: netlabel: Move bitmap manipulation functions to the NetLabel core. This is to allow the CALIPSO labelling engine to use these. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 2c0513b0cc88..9fc2cab9be98 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -434,6 +434,12 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, unsigned long bitmap, gfp_t flags); +/* Bitmap functions + */ +int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, + u32 offset, u8 state); +void netlbl_bitmap_setbit(unsigned char *bitmap, u32 bit, u8 state); + /* * LSM protocol operations (NetLabel LSM/kernel API) */ -- cgit v1.2.3 From ceba1832b1b2da0149c51de62a847c00bca1677a Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:02:51 -0400 Subject: calipso: Set the calipso socket label to match the secattr. CALIPSO is a hop-by-hop IPv6 option. A lot of this patch is based on the equivalent CISPO code. The main difference is due to manipulating the options in the hop-by-hop header. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/ipv6.h | 2 ++ include/net/netlabel.h | 9 +++++++++ include/uapi/linux/in6.h | 1 + 3 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 887313d978d0..4e279a83cdd0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -319,6 +319,8 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); +struct ipv6_txoptions *ipv6_update_options(struct sock *sk, + struct ipv6_txoptions *opt); static inline bool ipv6_accept_ra(struct inet6_dev *idev) { diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 9fc2cab9be98..918a6044c89c 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -226,6 +226,9 @@ struct netlbl_lsm_secattr { * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI * @doi_walk: enumerate the DOI list + * @sock_getattr: retrieve the socket's attr + * @sock_setattr: set the socket's attr + * @sock_delattr: remove the socket's attr * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -243,6 +246,12 @@ struct netlbl_calipso_ops { int (*doi_walk)(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg); + int (*sock_getattr)(struct sock *sk, + struct netlbl_lsm_secattr *secattr); + int (*sock_setattr)(struct sock *sk, + const struct calipso_doi *doi_def, + const struct netlbl_lsm_secattr *secattr); + void (*sock_delattr)(struct sock *sk); }; /* diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 318a4828bf98..b39ea4f2e701 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -143,6 +143,7 @@ struct in6_flowlabel_req { #define IPV6_TLV_PAD1 0 #define IPV6_TLV_PADN 1 #define IPV6_TLV_ROUTERALERT 5 +#define IPV6_TLV_CALIPSO 7 /* RFC 5570 */ #define IPV6_TLV_JUMBO 194 #define IPV6_TLV_HAO 201 /* home address option */ -- cgit v1.2.3 From 56ac42bc94b18d45b6c484edeac33be86bfb3efa Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:05:28 -0400 Subject: ipv6: Allow request socks to contain IPv6 options. If set, these will take precedence over the parent's options during both sending and child creation. If they're not set, the parent's options (if any) will be used. This is to allow the security_inet_conn_request() hook to modify the IPv6 options in just the same way that it already may do for IPv4. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/inet_sock.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 012b1f91f3ec..236a81034fef 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -97,7 +97,12 @@ struct inet_request_sock { u32 ir_mark; union { struct ip_options_rcu *opt; - struct sk_buff *pktopts; +#if IS_ENABLED(CONFIG_IPV6) + struct { + struct ipv6_txoptions *ipv6_opt; + struct sk_buff *pktopts; + }; +#endif }; }; -- cgit v1.2.3 From e1adea927080821ebfa7505bff752a4015955660 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:05:29 -0400 Subject: calipso: Allow request sockets to be relabelled by the lsm. Request sockets need to have a label that takes into account the incoming connection as well as their parent's label. This is used for the outgoing SYN-ACK and for their child full-socket. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 918a6044c89c..a2408c30a7f7 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -229,6 +229,8 @@ struct netlbl_lsm_secattr { * @sock_getattr: retrieve the socket's attr * @sock_setattr: set the socket's attr * @sock_delattr: remove the socket's attr + * @req_setattr: set the req socket's attr + * @req_delattr: remove the req socket's attr * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -252,6 +254,10 @@ struct netlbl_calipso_ops { const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void (*sock_delattr)(struct sock *sk); + int (*req_setattr)(struct request_sock *req, + const struct calipso_doi *doi_def, + const struct netlbl_lsm_secattr *secattr); + void (*req_delattr)(struct request_sock *req); }; /* -- cgit v1.2.3 From 0868383b822e4d8ebde980c7aac973a6aa81a3ec Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:15 -0400 Subject: ipv6: constify the skb pointer of ipv6_find_tlv(). Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 4e279a83cdd0..24a5ebecaf1f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -945,7 +945,7 @@ enum { int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); -int ipv6_find_tlv(struct sk_buff *skb, int offset, int type); +int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, -- cgit v1.2.3 From 2917f57b6bc15cc6787496ee5f2fdf17f0e9b7d3 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:15 -0400 Subject: calipso: Allow the lsm to label the skbuff directly. In some cases, the lsm needs to add the label to the skbuff directly. A NF_INET_LOCAL_OUT IPv6 hook is added to selinux to match the IPv4 behaviour. This allows selinux to label the skbuffs that it requires. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index a2408c30a7f7..e0e4ce8f22af 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -231,6 +231,10 @@ struct netlbl_lsm_secattr { * @sock_delattr: remove the socket's attr * @req_setattr: set the req socket's attr * @req_delattr: remove the req socket's attr + * @opt_getattr: retrieve attr from memory block + * @skbuff_optptr: find option in packet + * @skbuff_setattr: set the skbuff's attr + * @skbuff_delattr: remove the skbuff's attr * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -258,6 +262,13 @@ struct netlbl_calipso_ops { const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); void (*req_delattr)(struct request_sock *req); + int (*opt_getattr)(const unsigned char *calipso, + struct netlbl_lsm_secattr *secattr); + unsigned char *(*skbuff_optptr)(const struct sk_buff *skb); + int (*skbuff_setattr)(struct sk_buff *skb, + const struct calipso_doi *doi_def, + const struct netlbl_lsm_secattr *secattr); + int (*skbuff_delattr)(struct sk_buff *skb); }; /* -- cgit v1.2.3 From a04e71f631fa3d2fd2aa0404c11484739d1e9073 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:16 -0400 Subject: netlabel: Pass a family parameter to netlbl_skbuff_err(). This makes it possible to route the error to the appropriate labelling engine. CALIPSO is far less verbose than CIPSO when encountering a bogus packet, so there is no need for a CALIPSO error handler. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index e0e4ce8f22af..d8a46a8ed512 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -488,7 +488,7 @@ int netlbl_skbuff_setattr(struct sk_buff *skb, int netlbl_skbuff_getattr(const struct sk_buff *skb, u16 family, struct netlbl_lsm_secattr *secattr); -void netlbl_skbuff_err(struct sk_buff *skb, int error, int gateway); +void netlbl_skbuff_err(struct sk_buff *skb, u16 family, int error, int gateway); /* * LSM label mapping cache operations -- cgit v1.2.3 From 2e532b702834c07f614caf4489feb691e713232a Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:17 -0400 Subject: calipso: Add validation of CALIPSO option. Lengths, checksum and the DOI are checked. Checking of the level and categories are left for the socket layer. CRC validation is performed in the calipso module to avoid unconditionally linking crc_ccitt() into ipv6. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/calipso.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/calipso.h b/include/net/calipso.h index 38dbb4707150..85404e2375d8 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -65,6 +65,7 @@ struct calipso_doi { #ifdef CONFIG_NETLABEL int __init calipso_init(void); void calipso_exit(void); +bool calipso_validate(const struct sk_buff *skb, const unsigned char *option); #else static inline int __init calipso_init(void) { @@ -74,6 +75,11 @@ static inline int __init calipso_init(void) static inline void calipso_exit(void) { } +static inline bool calipso_validate(const struct sk_buff *skb, + const unsigned char *option) +{ + return true; +} #endif /* CONFIG_NETLABEL */ #endif /* _CALIPSO_H */ -- cgit v1.2.3 From 4fee5242bf41d9ad641d4c1b821e36eb7ba37fbf Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:17 -0400 Subject: calipso: Add a label cache. This works in exactly the same way as the CIPSO label cache. The idea is to allow the lsm to cache the result of a secattr lookup so that it doesn't need to perform the lookup for every skbuff. It introduces two sysctl controls: calipso_cache_enable - enables/disables the cache. calipso_cache_bucket_size - sets the size of a cache bucket. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/calipso.h | 6 ++++++ include/net/netlabel.h | 9 +++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/calipso.h b/include/net/calipso.h index 85404e2375d8..b1b30cd36601 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -62,6 +62,12 @@ struct calipso_doi { struct rcu_head rcu; }; +/* + * Sysctl Variables + */ +extern int calipso_cache_enabled; +extern int calipso_cache_bucketsize; + #ifdef CONFIG_NETLABEL int __init calipso_init(void); void calipso_exit(void); diff --git a/include/net/netlabel.h b/include/net/netlabel.h index d8a46a8ed512..a306bc7d2642 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -235,6 +235,8 @@ struct netlbl_lsm_secattr { * @skbuff_optptr: find option in packet * @skbuff_setattr: set the skbuff's attr * @skbuff_delattr: remove the skbuff's attr + * @cache_invalidate: invalidate cache + * @cache_add: add cache entry * * Description: * This structure is filled out by the CALIPSO engine and passed @@ -269,6 +271,9 @@ struct netlbl_calipso_ops { const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr); int (*skbuff_delattr)(struct sk_buff *skb); + void (*cache_invalidate)(void); + int (*cache_add)(const unsigned char *calipso_ptr, + const struct netlbl_lsm_secattr *secattr); }; /* @@ -494,7 +499,7 @@ void netlbl_skbuff_err(struct sk_buff *skb, u16 family, int error, int gateway); * LSM label mapping cache operations */ void netlbl_cache_invalidate(void); -int netlbl_cache_add(const struct sk_buff *skb, +int netlbl_cache_add(const struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr); /* @@ -647,7 +652,7 @@ static inline void netlbl_cache_invalidate(void) { return; } -static inline int netlbl_cache_add(const struct sk_buff *skb, +static inline int netlbl_cache_add(const struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr) { return 0; -- cgit v1.2.3 From 3f09354ac84c6904787189d85fb306bf60f714b8 Mon Sep 17 00:00:00 2001 From: Huw Davies Date: Mon, 27 Jun 2016 15:06:18 -0400 Subject: netlabel: Implement CALIPSO config functions for SMACK. SMACK uses similar functions to control CIPSO, these are the equivalent functions for CALIPSO and follow exactly the same semantics. int netlbl_cfg_calipso_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) Adds a CALIPSO doi. void netlbl_cfg_calipso_del(u32 doi, struct netlbl_audit *audit_info) Removes a CALIPSO doi. int netlbl_cfg_calipso_map_add(u32 doi, const char *domain, const struct in6_addr *addr, const struct in6_addr *mask, struct netlbl_audit *audit_info) Creates a mapping between a domain and a CALIPSO doi. If addr and mask are non-NULL this creates an address-selector type mapping. This also extends netlbl_cfg_map_del() to remove IPv6 address-selector mappings. Signed-off-by: Huw Davies Signed-off-by: Paul Moore --- include/net/netlabel.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index a306bc7d2642..efe98068880f 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -445,6 +445,14 @@ int netlbl_cfg_cipsov4_map_add(u32 doi, const struct in_addr *addr, const struct in_addr *mask, struct netlbl_audit *audit_info); +int netlbl_cfg_calipso_add(struct calipso_doi *doi_def, + struct netlbl_audit *audit_info); +void netlbl_cfg_calipso_del(u32 doi, struct netlbl_audit *audit_info); +int netlbl_cfg_calipso_map_add(u32 doi, + const char *domain, + const struct in6_addr *addr, + const struct in6_addr *mask, + struct netlbl_audit *audit_info); /* * LSM security attribute operations */ @@ -561,6 +569,24 @@ static inline int netlbl_cfg_cipsov4_map_add(u32 doi, { return -ENOSYS; } +static inline int netlbl_cfg_calipso_add(struct calipso_doi *doi_def, + struct netlbl_audit *audit_info) +{ + return -ENOSYS; +} +static inline void netlbl_cfg_calipso_del(u32 doi, + struct netlbl_audit *audit_info) +{ + return; +} +static inline int netlbl_cfg_calipso_map_add(u32 doi, + const char *domain, + const struct in6_addr *addr, + const struct in6_addr *mask, + struct netlbl_audit *audit_info) +{ + return -ENOSYS; +} static inline int netlbl_catmap_walk(struct netlbl_lsm_catmap *catmap, u32 offset) { -- cgit v1.2.3 From 52c44d93c26f5a76068c0a8cc83bb8f56f38043d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 15 Jun 2016 19:43:07 -0700 Subject: block: remove ->driverfs_dev Now that all drivers that specify a ->driverfs_dev have been converted to device_add_disk(), the pointer can be removed from struct gendisk. Cc: Jens Axboe Cc: Ross Zwisler Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Dan Williams --- include/linux/genhd.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index df1dabbfd388..1dbf52f9c24b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -205,7 +205,6 @@ struct gendisk { void *private_data; int flags; - struct device *driverfs_dev; // FIXME: remove struct kobject *slave_dir; struct timer_rand_state *random; @@ -417,8 +416,7 @@ extern void part_round_stats(int cpu, struct hd_struct *part); extern void device_add_disk(struct device *parent, struct gendisk *disk); static inline void add_disk(struct gendisk *disk) { - /* temporary while we convert callers to device_add_disk */ - device_add_disk(disk->driverfs_dev, disk); + device_add_disk(NULL, disk); } extern void del_gendisk(struct gendisk *gp); -- cgit v1.2.3 From de5a3774dde2c2f3b3a9a48b880fd820142706f0 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sat, 30 Apr 2016 18:08:06 +0200 Subject: HSI: core: switch port event notifier from atomic to blocking port events should be sent from process context after irq_safe runtime pm flag is removed in omap-ssi. Signed-off-By: Sebastian Reichel Tested-by: Pavel Machek --- include/linux/hsi/hsi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h index 2790591c77cf..57402544b53f 100644 --- a/include/linux/hsi/hsi.h +++ b/include/linux/hsi/hsi.h @@ -246,7 +246,7 @@ struct hsi_port { int (*stop_tx)(struct hsi_client *cl); int (*release)(struct hsi_client *cl); /* private */ - struct atomic_notifier_head n_head; + struct blocking_notifier_head n_head; }; #define to_hsi_port(dev) container_of(dev, struct hsi_port, device) -- cgit v1.2.3 From 498b5fdd40dd3881a3119d11bff8441cfd902850 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 21 Jun 2016 11:33:25 +0100 Subject: PM / clk: Add support for adding a specific clock from device-tree Some drivers using the PM clocks framework need to add specific clocks from device-tree using a name by calling the functions of_clk_get_by_name() and then pm_clk_add_clk(). Rather than having drivers call both functions, add a helper function of_pm_clk_add_clk() that will call these functions so drivers can call a single function to add a specific clock from device-tree. Signed-off-by: Jon Hunter Signed-off-by: Rafael J. Wysocki --- include/linux/pm_clock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h index 308d6044f153..09779b0ae720 100644 --- a/include/linux/pm_clock.h +++ b/include/linux/pm_clock.h @@ -42,6 +42,7 @@ extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); extern int pm_clk_add(struct device *dev, const char *con_id); extern int pm_clk_add_clk(struct device *dev, struct clk *clk); +extern int of_pm_clk_add_clk(struct device *dev, const char *name); extern int of_pm_clk_add_clks(struct device *dev); extern void pm_clk_remove(struct device *dev, const char *con_id); extern void pm_clk_remove_clk(struct device *dev, struct clk *clk); -- 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 --- include/linux/platform_data/sht3x.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 include/linux/platform_data/sht3x.h (limited to 'include') 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 --- include/asm-generic/vmlinux.lds.h | 2 ++ include/linux/clocksource.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') 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 --- include/clocksource/timer-sp804.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') 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 --- include/asm-generic/vmlinux.lds.h | 2 -- include/linux/clocksource.h | 5 +---- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include') 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 b810253bd9342f863a86ec7dfff4a5a7a0394d2f Mon Sep 17 00:00:00 2001 From: Philippe Bergheaud Date: Thu, 23 Jun 2016 15:03:53 +0200 Subject: cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/misc/cxl.h | 17 +++++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index 56560c5781b4..17419f61e611 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -220,4 +220,52 @@ void cxl_perst_reloads_same_image(struct cxl_afu *afu, */ ssize_t cxl_read_adapter_vpd(struct pci_dev *dev, void *buf, size_t count); +/* + * AFU driver ops allow an AFU driver to create their own events to pass to + * userspace through the file descriptor as a simpler alternative to overriding + * the read() and poll() calls that works with the generic cxl events. These + * events are given priority over the generic cxl events, so they will be + * delivered first if multiple types of events are pending. + * + * The AFU driver must call cxl_context_events_pending() to notify the cxl + * driver that new events are ready to be delivered for a specific context. + * cxl_context_events_pending() will adjust the current count of AFU driver + * events for this context, and wake up anyone waiting on the context wait + * queue. + * + * The cxl driver will then call fetch_event() to get a structure defining + * the size and address of the driver specific event data. The cxl driver + * will build a cxl header with type and process_element fields filled in, + * and header.size set to sizeof(struct cxl_event_header) + data_size. + * The total size of the event is limited to CXL_READ_MIN_SIZE (4K). + * + * fetch_event() is called with a spin lock held, so it must not sleep. + * + * The cxl driver will then deliver the event to userspace, and finally + * call event_delivered() to return the status of the operation, identified + * by cxl context and AFU driver event data pointers. + * 0 Success + * -EFAULT copy_to_user() has failed + * -EINVAL Event data pointer is NULL, or event size is greater than + * CXL_READ_MIN_SIZE. + */ +struct cxl_afu_driver_ops { + struct cxl_event_afu_driver_reserved *(*fetch_event) ( + struct cxl_context *ctx); + void (*event_delivered) (struct cxl_context *ctx, + struct cxl_event_afu_driver_reserved *event, + int rc); +}; + +/* + * Associate the above driver ops with a specific context. + * Reset the current count of AFU driver events. + */ +void cxl_set_driver_ops(struct cxl_context *ctx, + struct cxl_afu_driver_ops *ops); + +/* Notify cxl driver that new events are ready to be delivered for context */ +void cxl_context_events_pending(struct cxl_context *ctx, + unsigned int new_events); + #endif /* _MISC_CXL_H */ diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index 8cd334f99ddc..cbae529b7ce0 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -93,6 +93,7 @@ enum cxl_event_type { CXL_EVENT_AFU_INTERRUPT = 1, CXL_EVENT_DATA_STORAGE = 2, CXL_EVENT_AFU_ERROR = 3, + CXL_EVENT_AFU_DRIVER = 4, }; struct cxl_event_header { @@ -124,12 +125,28 @@ struct cxl_event_afu_error { __u64 error; }; +struct cxl_event_afu_driver_reserved { + /* + * Defines the buffer passed to the cxl driver by the AFU driver. + * + * This is not ABI since the event header.size passed to the user for + * existing events is set in the read call to sizeof(cxl_event_header) + * + sizeof(whatever event is being dispatched) and the user is already + * required to use a 4K buffer on the read call. + * + * Of course the contents will be ABI, but that's up the AFU driver. + */ + size_t data_size; + u8 data[]; +}; + struct cxl_event { struct cxl_event_header header; union { struct cxl_event_afu_interrupt irq; struct cxl_event_data_storage fault; struct cxl_event_afu_error afu_error; + struct cxl_event_afu_driver_reserved afu_driver_event; }; }; -- cgit v1.2.3 From ad42de859ff14c079e966e61cbcba85265b982e1 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 24 Jun 2016 08:47:07 +0200 Subject: cxl: Add set and get private data to context struct This provides AFU drivers a means to associate private data with a cxl context. This is particularly intended for make the new callbacks for driver specific events easier for AFU drivers to use, as they can easily get back to any private data structures they may use. Signed-off-by: Michael Neuling Signed-off-by: Ian Munsie Signed-off-by: Philippe Bergheaud Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index 17419f61e611..b6d040f31f76 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -85,6 +85,13 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev); */ int cxl_release_context(struct cxl_context *ctx); +/* + * Set and get private data associated with a context. Allows drivers to have a + * back pointer to some useful structure. + */ +int cxl_set_priv(struct cxl_context *ctx, void *priv); +void *cxl_get_priv(struct cxl_context *ctx); + /* * Allocate AFU interrupts for this context. num=0 will allocate the default * for this AFU as given in the AFU descriptor. This number doesn't include the -- cgit v1.2.3 From 637c841dd7a5f9bd97b75cbe90b526fa1a52e530 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 23 Jun 2016 18:42:51 -0700 Subject: net: diag: Add support to filter on device index Add support to inet_diag facility to filter sockets based on device index. If an interface index is in the filter only sockets bound to that index (sk_bound_dev_if) are returned. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index a16643705669..abbd1dc5d683 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -72,6 +72,7 @@ enum { INET_DIAG_BC_AUTO, INET_DIAG_BC_S_COND, INET_DIAG_BC_D_COND, + INET_DIAG_BC_DEV_COND, /* u32 ifindex */ }; struct inet_diag_hostcond { -- cgit v1.2.3 From a5e4bd991362223346e1d3561e61d7a25797fe25 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 24 Jun 2016 11:24:08 +0200 Subject: of_mdio: select fixed phy support unconditionally Calling the fixed-phy functions when CONFIG_FIXED_PHY=m as a previous change tried cannot work if the caller is in built-in code: drivers/of/built-in.o: In function `of_phy_register_fixed_link': of_reserved_mem.c:(.text+0x85e0): undefined reference to `fixed_phy_register' Making of_mdio depend on 'FIXED_PHY || !FIXED_PHY' would solve this dependency by enforcing that OF_MDIO itself becomes a loadable module when FIXED_PHY=y, but that creates a different dependency as it breaks any built-in ethernet driver that uses of_mdio. Making FIXED_PHY a bool option also cannot work, since it depends on PHYLIB, which again is tristate. This version now uses 'select FIXED_PHY' to ensure that the fixed-phy portion of of_mdio is not optional. The main downside of this is a small increase in code size for cases that do not need fixed phy support, but it should avoid all of the link-time problems. Signed-off-by: Arnd Bergmann Fixes: d1bd330a229f ("of_mdio: Enable fixed PHY support if driver is a module") Acked-by: Randy Dunlap Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 6c8cb9aa4c00..4b04587d0441 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -25,6 +25,8 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); +extern int of_phy_register_fixed_link(struct device_node *np); +extern bool of_phy_is_fixed_link(struct device_node *np); #else /* CONFIG_OF */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) @@ -67,12 +69,6 @@ static inline int of_mdio_parse_addr(struct device *dev, { return -ENOSYS; } -#endif /* CONFIG_OF */ - -#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_FIXED_PHY) -extern int of_phy_register_fixed_link(struct device_node *np); -extern bool of_phy_is_fixed_link(struct device_node *np); -#else static inline int of_phy_register_fixed_link(struct device_node *np) { return -ENOSYS; -- cgit v1.2.3 From 904aef0f9f6deff94223c0ce93eb598c47dd3aad Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 15 Jun 2016 09:57:48 -0300 Subject: [media] v4l2-ctrl.h: fix comments The comments for the unlocked v4l2_ctrl_s_ctrl* functions were wrong (copy and pasted from the locked variants). Fix this, since it is confusing. Acked-by: Sakari Ailus Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ctrls.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 0bc9b35b8f3e..5c2ed0cfb841 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -759,9 +759,9 @@ s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl); * @ctrl: The control. * @val: The new value. * - * This set the control's new value safely by going through the control - * framework. This function will lock the control's handler, so it cannot be - * used from within the &v4l2_ctrl_ops functions. + * This sets the control's new value safely by going through the control + * framework. This function assumes the control's handler is already locked, + * allowing it to be used from within the &v4l2_ctrl_ops functions. * * This function is for integer type controls only. */ @@ -771,7 +771,7 @@ int __v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val); * @ctrl: The control. * @val: The new value. * - * This set the control's new value safely by going through the control + * This sets the control's new value safely by going through the control * framework. This function will lock the control's handler, so it cannot be * used from within the &v4l2_ctrl_ops functions. * @@ -807,9 +807,9 @@ s64 v4l2_ctrl_g_ctrl_int64(struct v4l2_ctrl *ctrl); * @ctrl: The control. * @val: The new value. * - * This set the control's new value safely by going through the control - * framework. This function will lock the control's handler, so it cannot be - * used from within the &v4l2_ctrl_ops functions. + * This sets the control's new value safely by going through the control + * framework. This function assumes the control's handler is already locked, + * allowing it to be used from within the &v4l2_ctrl_ops functions. * * This function is for 64-bit integer type controls only. */ @@ -821,7 +821,7 @@ int __v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val); * @ctrl: The control. * @val: The new value. * - * This set the control's new value safely by going through the control + * This sets the control's new value safely by going through the control * framework. This function will lock the control's handler, so it cannot be * used from within the &v4l2_ctrl_ops functions. * @@ -843,9 +843,9 @@ static inline int v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val) * @ctrl: The control. * @s: The new string. * - * This set the control's new string safely by going through the control - * framework. This function will lock the control's handler, so it cannot be - * used from within the &v4l2_ctrl_ops functions. + * This sets the control's new string safely by going through the control + * framework. This function assumes the control's handler is already locked, + * allowing it to be used from within the &v4l2_ctrl_ops functions. * * This function is for string type controls only. */ @@ -857,7 +857,7 @@ int __v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s); * @ctrl: The control. * @s: The new string. * - * This set the control's new string safely by going through the control + * This sets the control's new string safely by going through the control * framework. This function will lock the control's handler, so it cannot be * used from within the &v4l2_ctrl_ops functions. * -- cgit v1.2.3 From ebaac1736245e78109cd47d453a86a18dcfc94b8 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 15 Jun 2016 15:09:28 +0200 Subject: context_tracking: move rcu_virt_note_context_switch out of kvm_host.h Make kvm_guest_{enter,exit} and __kvm_guest_{enter,exit} trivial wrappers around the code in context_tracking.h. Name the context_tracking.h functions consistently with what those for kernel<->user switch. Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Thomas Gleixner Reviewed-by: Rik van Riel Signed-off-by: Paolo Bonzini --- include/linux/context_tracking.h | 38 ++++++++++++++++++++++++++++++++++---- include/linux/kvm_host.h | 25 ++++--------------------- 2 files changed, 38 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d259274238db..ff4a32d24d56 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -84,7 +84,8 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static inline void guest_enter(void) +/* must be called with irqs disabled */ +static inline void guest_enter_irqoff(void) { if (vtime_accounting_cpu_enabled()) vtime_guest_enter(current); @@ -93,9 +94,19 @@ static inline void guest_enter(void) if (context_tracking_is_enabled()) __context_tracking_enter(CONTEXT_GUEST); + + /* KVM does not hold any references to rcu protected data when it + * switches CPU into a guest mode. In fact switching to a guest mode + * is very similar to exiting to userspace from rcu point of view. In + * addition CPU may stay in a guest mode for quite a long time (up to + * one time slice). Lets treat guest mode as quiescent state, just like + * we do with user-mode execution. + */ + if (!context_tracking_cpu_is_enabled()) + rcu_virt_note_context_switch(smp_processor_id()); } -static inline void guest_exit(void) +static inline void guest_exit_irqoff(void) { if (context_tracking_is_enabled()) __context_tracking_exit(CONTEXT_GUEST); @@ -107,7 +118,7 @@ static inline void guest_exit(void) } #else -static inline void guest_enter(void) +static inline void guest_enter_irqoff(void) { /* * This is running in ioctl context so its safe @@ -116,9 +127,10 @@ static inline void guest_enter(void) */ vtime_account_system(current); current->flags |= PF_VCPU; + rcu_virt_note_context_switch(smp_processor_id()); } -static inline void guest_exit(void) +static inline void guest_exit_irqoff(void) { /* Flush the guest cputime we spent on the guest */ vtime_account_system(current); @@ -126,4 +138,22 @@ static inline void guest_exit(void) } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ +static inline void guest_enter(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_enter_irqoff(); + local_irq_restore(flags); +} + +static inline void guest_exit(void) +{ + unsigned long flags; + + local_irq_save(flags); + guest_exit_irqoff(); + local_irq_restore(flags); +} + #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0640ee92b978..ffff40522688 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -878,40 +878,23 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, /* must be called with irqs disabled */ static inline void __kvm_guest_enter(void) { - guest_enter(); - /* KVM does not hold any references to rcu protected data when it - * switches CPU into a guest mode. In fact switching to a guest mode - * is very similar to exiting to userspace from rcu point of view. In - * addition CPU may stay in a guest mode for quite a long time (up to - * one time slice). Lets treat guest mode as quiescent state, just like - * we do with user-mode execution. - */ - if (!context_tracking_cpu_is_enabled()) - rcu_virt_note_context_switch(smp_processor_id()); + guest_enter_irqoff(); } /* must be called with irqs disabled */ static inline void __kvm_guest_exit(void) { - guest_exit(); + guest_exit_irqoff(); } static inline void kvm_guest_enter(void) { - unsigned long flags; - - local_irq_save(flags); - __kvm_guest_enter(); - local_irq_restore(flags); + guest_enter(); } static inline void kvm_guest_exit(void) { - unsigned long flags; - - local_irq_save(flags); - __kvm_guest_exit(); - local_irq_restore(flags); + guest_exit(); } /* -- cgit v1.2.3 From 29fb44a58ac12bffe4c225f95afdc22364db070e Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 17 Jun 2016 09:13:08 -0300 Subject: [media] cec-edid: add module for EDID CEC helper functions The cec-edid module contains helper functions to find and manipulate the CEC physical address inside an EDID. Even if the CEC support itself is disabled, drivers will still need these functions. Which is the reason this is module is separate from the upcoming CEC framework. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec-edid.h | 104 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 include/media/cec-edid.h (limited to 'include') diff --git a/include/media/cec-edid.h b/include/media/cec-edid.h new file mode 100644 index 000000000000..bdf731ecba1a --- /dev/null +++ b/include/media/cec-edid.h @@ -0,0 +1,104 @@ +/* + * cec-edid - HDMI Consumer Electronics Control & EDID helpers + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _MEDIA_CEC_EDID_H +#define _MEDIA_CEC_EDID_H + +#include + +#define CEC_PHYS_ADDR_INVALID 0xffff +#define cec_phys_addr_exp(pa) \ + ((pa) >> 12), ((pa) >> 8) & 0xf, ((pa) >> 4) & 0xf, (pa) & 0xf + +/** + * cec_get_edid_phys_addr() - find and return the physical address + * + * @edid: pointer to the EDID data + * @size: size in bytes of the EDID data + * @offset: If not %NULL then the location of the physical address + * bytes in the EDID will be returned here. This is set to 0 + * if there is no physical address found. + * + * Return: the physical address or CEC_PHYS_ADDR_INVALID if there is none. + */ +u16 cec_get_edid_phys_addr(const u8 *edid, unsigned int size, + unsigned int *offset); + +/** + * cec_set_edid_phys_addr() - find and set the physical address + * + * @edid: pointer to the EDID data + * @size: size in bytes of the EDID data + * @phys_addr: the new physical address + * + * This function finds the location of the physical address in the EDID + * and fills in the given physical address and updates the checksum + * at the end of the EDID block. It does nothing if the EDID doesn't + * contain a physical address. + */ +void cec_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr); + +/** + * cec_phys_addr_for_input() - calculate the PA for an input + * + * @phys_addr: the physical address of the parent + * @input: the number of the input port, must be between 1 and 15 + * + * This function calculates a new physical address based on the input + * port number. For example: + * + * PA = 0.0.0.0 and input = 2 becomes 2.0.0.0 + * + * PA = 3.0.0.0 and input = 1 becomes 3.1.0.0 + * + * PA = 3.2.1.0 and input = 5 becomes 3.2.1.5 + * + * PA = 3.2.1.3 and input = 5 becomes f.f.f.f since it maxed out the depth. + * + * Return: the new physical address or CEC_PHYS_ADDR_INVALID. + */ +u16 cec_phys_addr_for_input(u16 phys_addr, u8 input); + +/** + * cec_phys_addr_validate() - validate a physical address from an EDID + * + * @phys_addr: the physical address to validate + * @parent: if not %NULL, then this is filled with the parents PA. + * @port: if not %NULL, then this is filled with the input port. + * + * This validates a physical address as read from an EDID. If the + * PA is invalid (such as 1.0.1.0 since '0' is only allowed at the end), + * then it will return -EINVAL. + * + * The parent PA is passed into %parent and the input port is passed into + * %port. For example: + * + * PA = 0.0.0.0: has parent 0.0.0.0 and input port 0. + * + * PA = 1.0.0.0: has parent 0.0.0.0 and input port 1. + * + * PA = 3.2.0.0: has parent 3.0.0.0 and input port 2. + * + * PA = f.f.f.f: has parent f.f.f.f and input port 0. + * + * Return: 0 if the PA is valid, -EINVAL if not. + */ +int cec_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port); + +#endif /* _MEDIA_CEC_EDID_H */ -- cgit v1.2.3 From 02e57b9d7c8ce9e403f15f48fb91dd6549aaf465 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Fri, 24 Jun 2016 15:16:26 +0200 Subject: drivers: net: stmmac: add port selection programming In case of SGMII more, for example when a MAC2MAC connection is needed, the port selection bits (inside the MAC configuration registers) have to be programmed according to the link selected. So the patch adds a new DT parameter to pass the port selection and to programmed related PCS and CORE to use it. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0507dbfbf63c..705840e0438f 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -141,5 +141,6 @@ struct plat_stmmacenet_data { struct stmmac_axi *axi; int has_gmac4; bool tso_en; + int mac_port_sel_speed; }; #endif -- cgit v1.2.3 From 3132583e5bd7cb56dffb2c04128ec4db12c32027 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 17 Jun 2016 09:17:57 -0300 Subject: [media] cec.h: add cec header This header contains the CEC public API. Since the CEC framework will initially be part of staging this header is kept out of include/uapi for the time being until the CEC framework will be moved out of staging. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 993 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 993 insertions(+) create mode 100644 include/linux/cec.h (limited to 'include') diff --git a/include/linux/cec.h b/include/linux/cec.h new file mode 100644 index 000000000000..40924e79465d --- /dev/null +++ b/include/linux/cec.h @@ -0,0 +1,993 @@ +/* + * cec - HDMI Consumer Electronics Control public header + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* + * Note: this framework is still in staging and it is likely the API + * will change before it goes out of staging. + * + * Once it is moved out of staging this header will move to uapi. + */ +#ifndef _CEC_UAPI_H +#define _CEC_UAPI_H + +#include + +#define CEC_MAX_MSG_SIZE 16 + +/** + * struct cec_msg - CEC message structure. + * @ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the + * driver. It is set when the message transmission has finished + * and it is set when a message was received. + * @len: Length in bytes of the message. + * @timeout: The timeout (in ms) that is used to timeout CEC_RECEIVE. + * Set to 0 if you want to wait forever. This timeout can also be + * used with CEC_TRANSMIT as the timeout for waiting for a reply. + * If 0, then it will use a 1 second timeout instead of waiting + * forever as is done with CEC_RECEIVE. + * @sequence: The framework assigns a sequence number to messages that are + * sent. This can be used to track replies to previously sent + * messages. + * @flags: Set to 0. + * @rx_status: The message receive status bits. Set by the driver. + * @tx_status: The message transmit status bits. Set by the driver. + * @msg: The message payload. + * @reply: This field is ignored with CEC_RECEIVE and is only used by + * CEC_TRANSMIT. If non-zero, then wait for a reply with this + * opcode. Set to CEC_MSG_FEATURE_ABORT if you want to wait for + * a possible ABORT reply. If there was an error when sending the + * msg or FeatureAbort was returned, then reply is set to 0. + * If reply is non-zero upon return, then len/msg are set to + * the received message. + * If reply is zero upon return and status has the + * CEC_TX_STATUS_FEATURE_ABORT bit set, then len/msg are set to + * the received feature abort message. + * If reply is zero upon return and status has the + * CEC_TX_STATUS_MAX_RETRIES bit set, then no reply was seen at + * all. If reply is non-zero for CEC_TRANSMIT and the message is a + * broadcast, then -EINVAL is returned. + * if reply is non-zero, then timeout is set to 1000 (the required + * maximum response time). + * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver. + * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver. + * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the + * driver. + * @tx_error_cnt: The number of 'Error' events. Set by the driver. + */ +struct cec_msg { + __u64 ts; + __u32 len; + __u32 timeout; + __u32 sequence; + __u32 flags; + __u8 rx_status; + __u8 tx_status; + __u8 msg[CEC_MAX_MSG_SIZE]; + __u8 reply; + __u8 tx_arb_lost_cnt; + __u8 tx_nack_cnt; + __u8 tx_low_drive_cnt; + __u8 tx_error_cnt; +}; + +/** + * cec_msg_initiator - return the initiator's logical address. + * @msg: the message structure + */ +static inline __u8 cec_msg_initiator(const struct cec_msg *msg) +{ + return msg->msg[0] >> 4; +} + +/** + * cec_msg_destination - return the destination's logical address. + * @msg: the message structure + */ +static inline __u8 cec_msg_destination(const struct cec_msg *msg) +{ + return msg->msg[0] & 0xf; +} + +/** + * cec_msg_opcode - return the opcode of the message, -1 for poll + * @msg: the message structure + */ +static inline int cec_msg_opcode(const struct cec_msg *msg) +{ + return msg->len > 1 ? msg->msg[1] : -1; +} + +/** + * cec_msg_is_broadcast - return true if this is a broadcast message. + * @msg: the message structure + */ +static inline bool cec_msg_is_broadcast(const struct cec_msg *msg) +{ + return (msg->msg[0] & 0xf) == 0xf; +} + +/** + * cec_msg_init - initialize the message structure. + * @msg: the message structure + * @initiator: the logical address of the initiator + * @destination:the logical address of the destination (0xf for broadcast) + * + * The whole structure is zeroed, the len field is set to 1 (i.e. a poll + * message) and the initiator and destination are filled in. + */ +static inline void cec_msg_init(struct cec_msg *msg, + __u8 initiator, __u8 destination) +{ + memset(msg, 0, sizeof(*msg)); + msg->msg[0] = (initiator << 4) | destination; + msg->len = 1; +} + +/** + * cec_msg_set_reply_to - fill in destination/initiator in a reply message. + * @msg: the message structure for the reply + * @orig: the original message structure + * + * Set the msg destination to the orig initiator and the msg initiator to the + * orig destination. Note that msg and orig may be the same pointer, in which + * case the change is done in place. + */ +static inline void cec_msg_set_reply_to(struct cec_msg *msg, + struct cec_msg *orig) +{ + /* The destination becomes the initiator and vice versa */ + msg->msg[0] = (cec_msg_destination(orig) << 4) | + cec_msg_initiator(orig); + msg->reply = msg->timeout = 0; +} + +/* cec status field */ +#define CEC_TX_STATUS_OK (1 << 0) +#define CEC_TX_STATUS_ARB_LOST (1 << 1) +#define CEC_TX_STATUS_NACK (1 << 2) +#define CEC_TX_STATUS_LOW_DRIVE (1 << 3) +#define CEC_TX_STATUS_ERROR (1 << 4) +#define CEC_TX_STATUS_MAX_RETRIES (1 << 5) + +#define CEC_RX_STATUS_OK (1 << 0) +#define CEC_RX_STATUS_TIMEOUT (1 << 1) +#define CEC_RX_STATUS_FEATURE_ABORT (1 << 2) + +static inline bool cec_msg_status_is_ok(const struct cec_msg *msg) +{ + if (msg->tx_status && !(msg->tx_status & CEC_TX_STATUS_OK)) + return false; + if (msg->rx_status && !(msg->rx_status & CEC_RX_STATUS_OK)) + return false; + if (!msg->tx_status && !msg->rx_status) + return false; + return !(msg->rx_status & CEC_RX_STATUS_FEATURE_ABORT); +} + +#define CEC_LOG_ADDR_INVALID 0xff +#define CEC_PHYS_ADDR_INVALID 0xffff + +/* + * The maximum number of logical addresses one device can be assigned to. + * The CEC 2.0 spec allows for only 2 logical addresses at the moment. The + * Analog Devices CEC hardware supports 3. So let's go wild and go for 4. + */ +#define CEC_MAX_LOG_ADDRS 4 + +/* The logical addresses defined by CEC 2.0 */ +#define CEC_LOG_ADDR_TV 0 +#define CEC_LOG_ADDR_RECORD_1 1 +#define CEC_LOG_ADDR_RECORD_2 2 +#define CEC_LOG_ADDR_TUNER_1 3 +#define CEC_LOG_ADDR_PLAYBACK_1 4 +#define CEC_LOG_ADDR_AUDIOSYSTEM 5 +#define CEC_LOG_ADDR_TUNER_2 6 +#define CEC_LOG_ADDR_TUNER_3 7 +#define CEC_LOG_ADDR_PLAYBACK_2 8 +#define CEC_LOG_ADDR_RECORD_3 9 +#define CEC_LOG_ADDR_TUNER_4 10 +#define CEC_LOG_ADDR_PLAYBACK_3 11 +#define CEC_LOG_ADDR_BACKUP_1 12 +#define CEC_LOG_ADDR_BACKUP_2 13 +#define CEC_LOG_ADDR_SPECIFIC 14 +#define CEC_LOG_ADDR_UNREGISTERED 15 /* as initiator address */ +#define CEC_LOG_ADDR_BROADCAST 15 /* ad destination address */ + +/* The logical address types that the CEC device wants to claim */ +#define CEC_LOG_ADDR_TYPE_TV 0 +#define CEC_LOG_ADDR_TYPE_RECORD 1 +#define CEC_LOG_ADDR_TYPE_TUNER 2 +#define CEC_LOG_ADDR_TYPE_PLAYBACK 3 +#define CEC_LOG_ADDR_TYPE_AUDIOSYSTEM 4 +#define CEC_LOG_ADDR_TYPE_SPECIFIC 5 +#define CEC_LOG_ADDR_TYPE_UNREGISTERED 6 +/* + * Switches should use UNREGISTERED. + * Processors should use SPECIFIC. + */ + +#define CEC_LOG_ADDR_MASK_TV (1 << CEC_LOG_ADDR_TV) +#define CEC_LOG_ADDR_MASK_RECORD ((1 << CEC_LOG_ADDR_RECORD_1) | \ + (1 << CEC_LOG_ADDR_RECORD_2) | \ + (1 << CEC_LOG_ADDR_RECORD_3)) +#define CEC_LOG_ADDR_MASK_TUNER ((1 << CEC_LOG_ADDR_TUNER_1) | \ + (1 << CEC_LOG_ADDR_TUNER_2) | \ + (1 << CEC_LOG_ADDR_TUNER_3) | \ + (1 << CEC_LOG_ADDR_TUNER_4)) +#define CEC_LOG_ADDR_MASK_PLAYBACK ((1 << CEC_LOG_ADDR_PLAYBACK_1) | \ + (1 << CEC_LOG_ADDR_PLAYBACK_2) | \ + (1 << CEC_LOG_ADDR_PLAYBACK_3)) +#define CEC_LOG_ADDR_MASK_AUDIOSYSTEM (1 << CEC_LOG_ADDR_AUDIOSYSTEM) +#define CEC_LOG_ADDR_MASK_BACKUP ((1 << CEC_LOG_ADDR_BACKUP_1) | \ + (1 << CEC_LOG_ADDR_BACKUP_2)) +#define CEC_LOG_ADDR_MASK_SPECIFIC (1 << CEC_LOG_ADDR_SPECIFIC) +#define CEC_LOG_ADDR_MASK_UNREGISTERED (1 << CEC_LOG_ADDR_UNREGISTERED) + +static inline bool cec_has_tv(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_TV; +} + +static inline bool cec_has_record(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_RECORD; +} + +static inline bool cec_has_tuner(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_TUNER; +} + +static inline bool cec_has_playback(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_PLAYBACK; +} + +static inline bool cec_has_audiosystem(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_AUDIOSYSTEM; +} + +static inline bool cec_has_backup(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_BACKUP; +} + +static inline bool cec_has_specific(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_SPECIFIC; +} + +static inline bool cec_is_unregistered(__u16 log_addr_mask) +{ + return log_addr_mask & CEC_LOG_ADDR_MASK_UNREGISTERED; +} + +static inline bool cec_is_unconfigured(__u16 log_addr_mask) +{ + return log_addr_mask == 0; +} + +/* + * Use this if there is no vendor ID (CEC_G_VENDOR_ID) or if the vendor ID + * should be disabled (CEC_S_VENDOR_ID) + */ +#define CEC_VENDOR_ID_NONE 0xffffffff + +/* The message handling modes */ +/* Modes for initiator */ +#define CEC_MODE_NO_INITIATOR (0x0 << 0) +#define CEC_MODE_INITIATOR (0x1 << 0) +#define CEC_MODE_EXCL_INITIATOR (0x2 << 0) +#define CEC_MODE_INITIATOR_MSK 0x0f + +/* Modes for follower */ +#define CEC_MODE_NO_FOLLOWER (0x0 << 4) +#define CEC_MODE_FOLLOWER (0x1 << 4) +#define CEC_MODE_EXCL_FOLLOWER (0x2 << 4) +#define CEC_MODE_EXCL_FOLLOWER_PASSTHRU (0x3 << 4) +#define CEC_MODE_MONITOR (0xe << 4) +#define CEC_MODE_MONITOR_ALL (0xf << 4) +#define CEC_MODE_FOLLOWER_MSK 0xf0 + +/* Userspace has to configure the physical address */ +#define CEC_CAP_PHYS_ADDR (1 << 0) +/* Userspace has to configure the logical addresses */ +#define CEC_CAP_LOG_ADDRS (1 << 1) +/* Userspace can transmit messages (and thus become follower as well) */ +#define CEC_CAP_TRANSMIT (1 << 2) +/* + * Passthrough all messages instead of processing them. + */ +#define CEC_CAP_PASSTHROUGH (1 << 3) +/* Supports remote control */ +#define CEC_CAP_RC (1 << 4) +/* Hardware can monitor all messages, not just directed and broadcast. */ +#define CEC_CAP_MONITOR_ALL (1 << 5) + +/** + * struct cec_caps - CEC capabilities structure. + * @driver: name of the CEC device driver. + * @name: name of the CEC device. @driver + @name must be unique. + * @available_log_addrs: number of available logical addresses. + * @capabilities: capabilities of the CEC adapter. + * @version: version of the CEC adapter framework. + */ +struct cec_caps { + char driver[32]; + char name[32]; + __u32 available_log_addrs; + __u32 capabilities; + __u32 version; +}; + +/** + * struct cec_log_addrs - CEC logical addresses structure. + * @log_addr: the claimed logical addresses. Set by the driver. + * @log_addr_mask: current logical address mask. Set by the driver. + * @cec_version: the CEC version that the adapter should implement. Set by the + * caller. + * @num_log_addrs: how many logical addresses should be claimed. Set by the + * caller. + * @vendor_id: the vendor ID of the device. Set by the caller. + * @flags: set to 0. + * @osd_name: the OSD name of the device. Set by the caller. + * @primary_device_type: the primary device type for each logical address. + * Set by the caller. + * @log_addr_type: the logical address types. Set by the caller. + * @all_device_types: CEC 2.0: all device types represented by the logical + * address. Set by the caller. + * @features: CEC 2.0: The logical address features. Set by the caller. + */ +struct cec_log_addrs { + __u8 log_addr[CEC_MAX_LOG_ADDRS]; + __u16 log_addr_mask; + __u8 cec_version; + __u8 num_log_addrs; + __u32 vendor_id; + __u32 flags; + char osd_name[15]; + __u8 primary_device_type[CEC_MAX_LOG_ADDRS]; + __u8 log_addr_type[CEC_MAX_LOG_ADDRS]; + + /* CEC 2.0 */ + __u8 all_device_types[CEC_MAX_LOG_ADDRS]; + __u8 features[CEC_MAX_LOG_ADDRS][12]; +}; + +/* Events */ + +/* Event that occurs when the adapter state changes */ +#define CEC_EVENT_STATE_CHANGE 1 +/* + * This event is sent when messages are lost because the application + * didn't empty the message queue in time + */ +#define CEC_EVENT_LOST_MSGS 2 + +#define CEC_EVENT_FL_INITIAL_STATE (1 << 0) + +/** + * struct cec_event_state_change - used when the CEC adapter changes state. + * @phys_addr: the current physical address + * @log_addr_mask: the current logical address mask + */ +struct cec_event_state_change { + __u16 phys_addr; + __u16 log_addr_mask; +}; + +/** + * struct cec_event_lost_msgs - tells you how many messages were lost due. + * @lost_msgs: how many messages were lost. + */ +struct cec_event_lost_msgs { + __u32 lost_msgs; +}; + +/** + * struct cec_event - CEC event structure + * @ts: the timestamp of when the event was sent. + * @event: the event. + * array. + * @state_change: the event payload for CEC_EVENT_STATE_CHANGE. + * @lost_msgs: the event payload for CEC_EVENT_LOST_MSGS. + * @raw: array to pad the union. + */ +struct cec_event { + __u64 ts; + __u32 event; + __u32 flags; + union { + struct cec_event_state_change state_change; + struct cec_event_lost_msgs lost_msgs; + __u32 raw[16]; + }; +}; + +/* ioctls */ + +/* Adapter capabilities */ +#define CEC_ADAP_G_CAPS _IOWR('a', 0, struct cec_caps) + +/* + * phys_addr is either 0 (if this is the CEC root device) + * or a valid physical address obtained from the sink's EDID + * as read by this CEC device (if this is a source device) + * or a physical address obtained and modified from a sink + * EDID and used for a sink CEC device. + * If nothing is connected, then phys_addr is 0xffff. + * See HDMI 1.4b, section 8.7 (Physical Address). + * + * The CEC_ADAP_S_PHYS_ADDR ioctl may not be available if that is handled + * internally. + */ +#define CEC_ADAP_G_PHYS_ADDR _IOR('a', 1, __u16) +#define CEC_ADAP_S_PHYS_ADDR _IOW('a', 2, __u16) + +/* + * Configure the CEC adapter. It sets the device type and which + * logical types it will try to claim. It will return which + * logical addresses it could actually claim. + * An error is returned if the adapter is disabled or if there + * is no physical address assigned. + */ + +#define CEC_ADAP_G_LOG_ADDRS _IOR('a', 3, struct cec_log_addrs) +#define CEC_ADAP_S_LOG_ADDRS _IOWR('a', 4, struct cec_log_addrs) + +/* Transmit/receive a CEC command */ +#define CEC_TRANSMIT _IOWR('a', 5, struct cec_msg) +#define CEC_RECEIVE _IOWR('a', 6, struct cec_msg) + +/* Dequeue CEC events */ +#define CEC_DQEVENT _IOWR('a', 7, struct cec_event) + +/* + * Get and set the message handling mode for this filehandle. + */ +#define CEC_G_MODE _IOR('a', 8, __u32) +#define CEC_S_MODE _IOW('a', 9, __u32) + +/* + * The remainder of this header defines all CEC messages and operands. + * The format matters since it the cec-ctl utility parses it to generate + * code for implementing all these messages. + * + * Comments ending with 'Feature' group messages for each feature. + * If messages are part of multiple features, then the "Has also" + * comment is used to list the previously defined messages that are + * supported by the feature. + * + * Before operands are defined a comment is added that gives the + * name of the operand and in brackets the variable name of the + * corresponding argument in the cec-funcs.h function. + */ + +/* Messages */ + +/* One Touch Play Feature */ +#define CEC_MSG_ACTIVE_SOURCE 0x82 +#define CEC_MSG_IMAGE_VIEW_ON 0x04 +#define CEC_MSG_TEXT_VIEW_ON 0x0d + + +/* Routing Control Feature */ + +/* + * Has also: + * CEC_MSG_ACTIVE_SOURCE + */ + +#define CEC_MSG_INACTIVE_SOURCE 0x9d +#define CEC_MSG_REQUEST_ACTIVE_SOURCE 0x85 +#define CEC_MSG_ROUTING_CHANGE 0x80 +#define CEC_MSG_ROUTING_INFORMATION 0x81 +#define CEC_MSG_SET_STREAM_PATH 0x86 + + +/* Standby Feature */ +#define CEC_MSG_STANDBY 0x36 + + +/* One Touch Record Feature */ +#define CEC_MSG_RECORD_OFF 0x0b +#define CEC_MSG_RECORD_ON 0x09 +/* Record Source Type Operand (rec_src_type) */ +#define CEC_OP_RECORD_SRC_OWN 1 +#define CEC_OP_RECORD_SRC_DIGITAL 2 +#define CEC_OP_RECORD_SRC_ANALOG 3 +#define CEC_OP_RECORD_SRC_EXT_PLUG 4 +#define CEC_OP_RECORD_SRC_EXT_PHYS_ADDR 5 +/* Service Identification Method Operand (service_id_method) */ +#define CEC_OP_SERVICE_ID_METHOD_BY_DIG_ID 0 +#define CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL 1 +/* Digital Service Broadcast System Operand (dig_bcast_system) */ +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_GEN 0x00 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN 0x01 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_GEN 0x02 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_BS 0x08 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_CS 0x09 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ARIB_T 0x0a +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE 0x10 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT 0x11 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T 0x12 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_C 0x18 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S 0x19 +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_S2 0x1a +#define CEC_OP_DIG_SERVICE_BCAST_SYSTEM_DVB_T 0x1b +/* Analogue Broadcast Type Operand (ana_bcast_type) */ +#define CEC_OP_ANA_BCAST_TYPE_CABLE 0 +#define CEC_OP_ANA_BCAST_TYPE_SATELLITE 1 +#define CEC_OP_ANA_BCAST_TYPE_TERRESTRIAL 2 +/* Broadcast System Operand (bcast_system) */ +#define CEC_OP_BCAST_SYSTEM_PAL_BG 0x00 +#define CEC_OP_BCAST_SYSTEM_SECAM_LQ 0x01 /* SECAM L' */ +#define CEC_OP_BCAST_SYSTEM_PAL_M 0x02 +#define CEC_OP_BCAST_SYSTEM_NTSC_M 0x03 +#define CEC_OP_BCAST_SYSTEM_PAL_I 0x04 +#define CEC_OP_BCAST_SYSTEM_SECAM_DK 0x05 +#define CEC_OP_BCAST_SYSTEM_SECAM_BG 0x06 +#define CEC_OP_BCAST_SYSTEM_SECAM_L 0x07 +#define CEC_OP_BCAST_SYSTEM_PAL_DK 0x08 +#define CEC_OP_BCAST_SYSTEM_OTHER 0x1f +/* Channel Number Format Operand (channel_number_fmt) */ +#define CEC_OP_CHANNEL_NUMBER_FMT_1_PART 0x01 +#define CEC_OP_CHANNEL_NUMBER_FMT_2_PART 0x02 + +#define CEC_MSG_RECORD_STATUS 0x0a +/* Record Status Operand (rec_status) */ +#define CEC_OP_RECORD_STATUS_CUR_SRC 0x01 +#define CEC_OP_RECORD_STATUS_DIG_SERVICE 0x02 +#define CEC_OP_RECORD_STATUS_ANA_SERVICE 0x03 +#define CEC_OP_RECORD_STATUS_EXT_INPUT 0x04 +#define CEC_OP_RECORD_STATUS_NO_DIG_SERVICE 0x05 +#define CEC_OP_RECORD_STATUS_NO_ANA_SERVICE 0x06 +#define CEC_OP_RECORD_STATUS_NO_SERVICE 0x07 +#define CEC_OP_RECORD_STATUS_INVALID_EXT_PLUG 0x09 +#define CEC_OP_RECORD_STATUS_INVALID_EXT_PHYS_ADDR 0x0a +#define CEC_OP_RECORD_STATUS_UNSUP_CA 0x0b +#define CEC_OP_RECORD_STATUS_NO_CA_ENTITLEMENTS 0x0c +#define CEC_OP_RECORD_STATUS_CANT_COPY_SRC 0x0d +#define CEC_OP_RECORD_STATUS_NO_MORE_COPIES 0x0e +#define CEC_OP_RECORD_STATUS_NO_MEDIA 0x10 +#define CEC_OP_RECORD_STATUS_PLAYING 0x11 +#define CEC_OP_RECORD_STATUS_ALREADY_RECORDING 0x12 +#define CEC_OP_RECORD_STATUS_MEDIA_PROT 0x13 +#define CEC_OP_RECORD_STATUS_NO_SIGNAL 0x14 +#define CEC_OP_RECORD_STATUS_MEDIA_PROBLEM 0x15 +#define CEC_OP_RECORD_STATUS_NO_SPACE 0x16 +#define CEC_OP_RECORD_STATUS_PARENTAL_LOCK 0x17 +#define CEC_OP_RECORD_STATUS_TERMINATED_OK 0x1a +#define CEC_OP_RECORD_STATUS_ALREADY_TERM 0x1b +#define CEC_OP_RECORD_STATUS_OTHER 0x1f + +#define CEC_MSG_RECORD_TV_SCREEN 0x0f + + +/* Timer Programming Feature */ +#define CEC_MSG_CLEAR_ANALOGUE_TIMER 0x33 +/* Recording Sequence Operand (recording_seq) */ +#define CEC_OP_REC_SEQ_SUNDAY 0x01 +#define CEC_OP_REC_SEQ_MONDAY 0x02 +#define CEC_OP_REC_SEQ_TUESDAY 0x04 +#define CEC_OP_REC_SEQ_WEDNESDAY 0x08 +#define CEC_OP_REC_SEQ_THURSDAY 0x10 +#define CEC_OP_REC_SEQ_FRIDAY 0x20 +#define CEC_OP_REC_SEQ_SATERDAY 0x40 +#define CEC_OP_REC_SEQ_ONCE_ONLY 0x00 + +#define CEC_MSG_CLEAR_DIGITAL_TIMER 0x99 + +#define CEC_MSG_CLEAR_EXT_TIMER 0xa1 +/* External Source Specifier Operand (ext_src_spec) */ +#define CEC_OP_EXT_SRC_PLUG 0x04 +#define CEC_OP_EXT_SRC_PHYS_ADDR 0x05 + +#define CEC_MSG_SET_ANALOGUE_TIMER 0x34 +#define CEC_MSG_SET_DIGITAL_TIMER 0x97 +#define CEC_MSG_SET_EXT_TIMER 0xa2 + +#define CEC_MSG_SET_TIMER_PROGRAM_TITLE 0x67 +#define CEC_MSG_TIMER_CLEARED_STATUS 0x43 +/* Timer Cleared Status Data Operand (timer_cleared_status) */ +#define CEC_OP_TIMER_CLR_STAT_RECORDING 0x00 +#define CEC_OP_TIMER_CLR_STAT_NO_MATCHING 0x01 +#define CEC_OP_TIMER_CLR_STAT_NO_INFO 0x02 +#define CEC_OP_TIMER_CLR_STAT_CLEARED 0x80 + +#define CEC_MSG_TIMER_STATUS 0x35 +/* Timer Overlap Warning Operand (timer_overlap_warning) */ +#define CEC_OP_TIMER_OVERLAP_WARNING_NO_OVERLAP 0 +#define CEC_OP_TIMER_OVERLAP_WARNING_OVERLAP 1 +/* Media Info Operand (media_info) */ +#define CEC_OP_MEDIA_INFO_UNPROT_MEDIA 0 +#define CEC_OP_MEDIA_INFO_PROT_MEDIA 1 +#define CEC_OP_MEDIA_INFO_NO_MEDIA 2 +/* Programmed Indicator Operand (prog_indicator) */ +#define CEC_OP_PROG_IND_NOT_PROGRAMMED 0 +#define CEC_OP_PROG_IND_PROGRAMMED 1 +/* Programmed Info Operand (prog_info) */ +#define CEC_OP_PROG_INFO_ENOUGH_SPACE 0x08 +#define CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE 0x09 +#define CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE 0x0b +#define CEC_OP_PROG_INFO_NONE_AVAILABLE 0x0a +/* Not Programmed Error Info Operand (prog_error) */ +#define CEC_OP_PROG_ERROR_NO_FREE_TIMER 0x01 +#define CEC_OP_PROG_ERROR_DATE_OUT_OF_RANGE 0x02 +#define CEC_OP_PROG_ERROR_REC_SEQ_ERROR 0x03 +#define CEC_OP_PROG_ERROR_INV_EXT_PLUG 0x04 +#define CEC_OP_PROG_ERROR_INV_EXT_PHYS_ADDR 0x05 +#define CEC_OP_PROG_ERROR_CA_UNSUPP 0x06 +#define CEC_OP_PROG_ERROR_INSUF_CA_ENTITLEMENTS 0x07 +#define CEC_OP_PROG_ERROR_RESOLUTION_UNSUPP 0x08 +#define CEC_OP_PROG_ERROR_PARENTAL_LOCK 0x09 +#define CEC_OP_PROG_ERROR_CLOCK_FAILURE 0x0a +#define CEC_OP_PROG_ERROR_DUPLICATE 0x0e + + +/* System Information Feature */ +#define CEC_MSG_CEC_VERSION 0x9e +/* CEC Version Operand (cec_version) */ +#define CEC_OP_CEC_VERSION_1_3A 4 +#define CEC_OP_CEC_VERSION_1_4 5 +#define CEC_OP_CEC_VERSION_2_0 6 + +#define CEC_MSG_GET_CEC_VERSION 0x9f +#define CEC_MSG_GIVE_PHYSICAL_ADDR 0x83 +#define CEC_MSG_GET_MENU_LANGUAGE 0x91 +#define CEC_MSG_REPORT_PHYSICAL_ADDR 0x84 +/* Primary Device Type Operand (prim_devtype) */ +#define CEC_OP_PRIM_DEVTYPE_TV 0 +#define CEC_OP_PRIM_DEVTYPE_RECORD 1 +#define CEC_OP_PRIM_DEVTYPE_TUNER 3 +#define CEC_OP_PRIM_DEVTYPE_PLAYBACK 4 +#define CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM 5 +#define CEC_OP_PRIM_DEVTYPE_SWITCH 6 +#define CEC_OP_PRIM_DEVTYPE_PROCESSOR 7 + +#define CEC_MSG_SET_MENU_LANGUAGE 0x32 +#define CEC_MSG_REPORT_FEATURES 0xa6 /* HDMI 2.0 */ +/* All Device Types Operand (all_device_types) */ +#define CEC_OP_ALL_DEVTYPE_TV 0x80 +#define CEC_OP_ALL_DEVTYPE_RECORD 0x40 +#define CEC_OP_ALL_DEVTYPE_TUNER 0x20 +#define CEC_OP_ALL_DEVTYPE_PLAYBACK 0x10 +#define CEC_OP_ALL_DEVTYPE_AUDIOSYSTEM 0x08 +#define CEC_OP_ALL_DEVTYPE_SWITCH 0x04 +/* + * And if you wondering what happened to PROCESSOR devices: those should + * be mapped to a SWITCH. + */ + +/* Valid for RC Profile and Device Feature operands */ +#define CEC_OP_FEAT_EXT 0x80 /* Extension bit */ +/* RC Profile Operand (rc_profile) */ +#define CEC_OP_FEAT_RC_TV_PROFILE_NONE 0x00 +#define CEC_OP_FEAT_RC_TV_PROFILE_1 0x02 +#define CEC_OP_FEAT_RC_TV_PROFILE_2 0x06 +#define CEC_OP_FEAT_RC_TV_PROFILE_3 0x0a +#define CEC_OP_FEAT_RC_TV_PROFILE_4 0x0e +#define CEC_OP_FEAT_RC_SRC_HAS_DEV_ROOT_MENU 0x50 +#define CEC_OP_FEAT_RC_SRC_HAS_DEV_SETUP_MENU 0x48 +#define CEC_OP_FEAT_RC_SRC_HAS_CONTENTS_MENU 0x44 +#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_TOP_MENU 0x42 +#define CEC_OP_FEAT_RC_SRC_HAS_MEDIA_CONTEXT_MENU 0x41 +/* Device Feature Operand (dev_features) */ +#define CEC_OP_FEAT_DEV_HAS_RECORD_TV_SCREEN 0x40 +#define CEC_OP_FEAT_DEV_HAS_SET_OSD_STRING 0x20 +#define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL 0x10 +#define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE 0x08 +#define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX 0x04 +#define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX 0x02 + +#define CEC_MSG_GIVE_FEATURES 0xa5 /* HDMI 2.0 */ + + +/* Deck Control Feature */ +#define CEC_MSG_DECK_CONTROL 0x42 +/* Deck Control Mode Operand (deck_control_mode) */ +#define CEC_OP_DECK_CTL_MODE_SKIP_FWD 1 +#define CEC_OP_DECK_CTL_MODE_SKIP_REV 2 +#define CEC_OP_DECK_CTL_MODE_STOP 3 +#define CEC_OP_DECK_CTL_MODE_EJECT 4 + +#define CEC_MSG_DECK_STATUS 0x1b +/* Deck Info Operand (deck_info) */ +#define CEC_OP_DECK_INFO_PLAY 0x11 +#define CEC_OP_DECK_INFO_RECORD 0x12 +#define CEC_OP_DECK_INFO_PLAY_REV 0x13 +#define CEC_OP_DECK_INFO_STILL 0x14 +#define CEC_OP_DECK_INFO_SLOW 0x15 +#define CEC_OP_DECK_INFO_SLOW_REV 0x16 +#define CEC_OP_DECK_INFO_FAST_FWD 0x17 +#define CEC_OP_DECK_INFO_FAST_REV 0x18 +#define CEC_OP_DECK_INFO_NO_MEDIA 0x19 +#define CEC_OP_DECK_INFO_STOP 0x1a +#define CEC_OP_DECK_INFO_SKIP_FWD 0x1b +#define CEC_OP_DECK_INFO_SKIP_REV 0x1c +#define CEC_OP_DECK_INFO_INDEX_SEARCH_FWD 0x1d +#define CEC_OP_DECK_INFO_INDEX_SEARCH_REV 0x1e +#define CEC_OP_DECK_INFO_OTHER 0x1f + +#define CEC_MSG_GIVE_DECK_STATUS 0x1a +/* Status Request Operand (status_req) */ +#define CEC_OP_STATUS_REQ_ON 1 +#define CEC_OP_STATUS_REQ_OFF 2 +#define CEC_OP_STATUS_REQ_ONCE 3 + +#define CEC_MSG_PLAY 0x41 +/* Play Mode Operand (play_mode) */ +#define CEC_OP_PLAY_MODE_PLAY_FWD 0x24 +#define CEC_OP_PLAY_MODE_PLAY_REV 0x20 +#define CEC_OP_PLAY_MODE_PLAY_STILL 0x25 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MIN 0x05 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MED 0x06 +#define CEC_OP_PLAY_MODE_PLAY_FAST_FWD_MAX 0x07 +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MIN 0x09 +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MED 0x0a +#define CEC_OP_PLAY_MODE_PLAY_FAST_REV_MAX 0x0b +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MIN 0x15 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MED 0x16 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_FWD_MAX 0x17 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MIN 0x19 +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MED 0x1a +#define CEC_OP_PLAY_MODE_PLAY_SLOW_REV_MAX 0x1b + + +/* Tuner Control Feature */ +#define CEC_MSG_GIVE_TUNER_DEVICE_STATUS 0x08 +#define CEC_MSG_SELECT_ANALOGUE_SERVICE 0x92 +#define CEC_MSG_SELECT_DIGITAL_SERVICE 0x93 +#define CEC_MSG_TUNER_DEVICE_STATUS 0x07 +/* Recording Flag Operand (rec_flag) */ +#define CEC_OP_REC_FLAG_USED 0 +#define CEC_OP_REC_FLAG_NOT_USED 1 +/* Tuner Display Info Operand (tuner_display_info) */ +#define CEC_OP_TUNER_DISPLAY_INFO_DIGITAL 0 +#define CEC_OP_TUNER_DISPLAY_INFO_NONE 1 +#define CEC_OP_TUNER_DISPLAY_INFO_ANALOGUE 2 + +#define CEC_MSG_TUNER_STEP_DECREMENT 0x06 +#define CEC_MSG_TUNER_STEP_INCREMENT 0x05 + + +/* Vendor Specific Commands Feature */ + +/* + * Has also: + * CEC_MSG_CEC_VERSION + * CEC_MSG_GET_CEC_VERSION + */ +#define CEC_MSG_DEVICE_VENDOR_ID 0x87 +#define CEC_MSG_GIVE_DEVICE_VENDOR_ID 0x8c +#define CEC_MSG_VENDOR_COMMAND 0x89 +#define CEC_MSG_VENDOR_COMMAND_WITH_ID 0xa0 +#define CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN 0x8a +#define CEC_MSG_VENDOR_REMOTE_BUTTON_UP 0x8b + + +/* OSD Display Feature */ +#define CEC_MSG_SET_OSD_STRING 0x64 +/* Display Control Operand (disp_ctl) */ +#define CEC_OP_DISP_CTL_DEFAULT 0x00 +#define CEC_OP_DISP_CTL_UNTIL_CLEARED 0x40 +#define CEC_OP_DISP_CTL_CLEAR 0x80 + + +/* Device OSD Transfer Feature */ +#define CEC_MSG_GIVE_OSD_NAME 0x46 +#define CEC_MSG_SET_OSD_NAME 0x47 + + +/* Device Menu Control Feature */ +#define CEC_MSG_MENU_REQUEST 0x8d +/* Menu Request Type Operand (menu_req) */ +#define CEC_OP_MENU_REQUEST_ACTIVATE 0x00 +#define CEC_OP_MENU_REQUEST_DEACTIVATE 0x01 +#define CEC_OP_MENU_REQUEST_QUERY 0x02 + +#define CEC_MSG_MENU_STATUS 0x8e +/* Menu State Operand (menu_state) */ +#define CEC_OP_MENU_STATE_ACTIVATED 0x00 +#define CEC_OP_MENU_STATE_DEACTIVATED 0x01 + +#define CEC_MSG_USER_CONTROL_PRESSED 0x44 +/* UI Broadcast Type Operand (ui_bcast_type) */ +#define CEC_OP_UI_BCAST_TYPE_TOGGLE_ALL 0x00 +#define CEC_OP_UI_BCAST_TYPE_TOGGLE_DIG_ANA 0x01 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE 0x10 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_T 0x20 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_CABLE 0x30 +#define CEC_OP_UI_BCAST_TYPE_ANALOGUE_SAT 0x40 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL 0x50 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_T 0x60 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_CABLE 0x70 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_SAT 0x80 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT 0x90 +#define CEC_OP_UI_BCAST_TYPE_DIGITAL_COM_SAT2 0x91 +#define CEC_OP_UI_BCAST_TYPE_IP 0xa0 +/* UI Sound Presentation Control Operand (ui_snd_pres_ctl) */ +#define CEC_OP_UI_SND_PRES_CTL_DUAL_MONO 0x10 +#define CEC_OP_UI_SND_PRES_CTL_KARAOKE 0x20 +#define CEC_OP_UI_SND_PRES_CTL_DOWNMIX 0x80 +#define CEC_OP_UI_SND_PRES_CTL_REVERB 0x90 +#define CEC_OP_UI_SND_PRES_CTL_EQUALIZER 0xa0 +#define CEC_OP_UI_SND_PRES_CTL_BASS_UP 0xb1 +#define CEC_OP_UI_SND_PRES_CTL_BASS_NEUTRAL 0xb2 +#define CEC_OP_UI_SND_PRES_CTL_BASS_DOWN 0xb3 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_UP 0xc1 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_NEUTRAL 0xc2 +#define CEC_OP_UI_SND_PRES_CTL_TREBLE_DOWN 0xc3 + +#define CEC_MSG_USER_CONTROL_RELEASED 0x45 + + +/* Remote Control Passthrough Feature */ + +/* + * Has also: + * CEC_MSG_USER_CONTROL_PRESSED + * CEC_MSG_USER_CONTROL_RELEASED + */ + + +/* Power Status Feature */ +#define CEC_MSG_GIVE_DEVICE_POWER_STATUS 0x8f +#define CEC_MSG_REPORT_POWER_STATUS 0x90 +/* Power Status Operand (pwr_state) */ +#define CEC_OP_POWER_STATUS_ON 0 +#define CEC_OP_POWER_STATUS_STANDBY 1 +#define CEC_OP_POWER_STATUS_TO_ON 2 +#define CEC_OP_POWER_STATUS_TO_STANDBY 3 + + +/* General Protocol Messages */ +#define CEC_MSG_FEATURE_ABORT 0x00 +/* Abort Reason Operand (reason) */ +#define CEC_OP_ABORT_UNRECOGNIZED_OP 0 +#define CEC_OP_ABORT_INCORRECT_MODE 1 +#define CEC_OP_ABORT_NO_SOURCE 2 +#define CEC_OP_ABORT_INVALID_OP 3 +#define CEC_OP_ABORT_REFUSED 4 +#define CEC_OP_ABORT_UNDETERMINED 5 + +#define CEC_MSG_ABORT 0xff + + +/* System Audio Control Feature */ + +/* + * Has also: + * CEC_MSG_USER_CONTROL_PRESSED + * CEC_MSG_USER_CONTROL_RELEASED + */ +#define CEC_MSG_GIVE_AUDIO_STATUS 0x71 +#define CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS 0x7d +#define CEC_MSG_REPORT_AUDIO_STATUS 0x7a +/* Audio Mute Status Operand (aud_mute_status) */ +#define CEC_OP_AUD_MUTE_STATUS_OFF 0 +#define CEC_OP_AUD_MUTE_STATUS_ON 1 + +#define CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR 0xa3 +#define CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR 0xa4 +#define CEC_MSG_SET_SYSTEM_AUDIO_MODE 0x72 +/* System Audio Status Operand (sys_aud_status) */ +#define CEC_OP_SYS_AUD_STATUS_OFF 0 +#define CEC_OP_SYS_AUD_STATUS_ON 1 + +#define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST 0x70 +#define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS 0x7e +/* Audio Format ID Operand (audio_format_id) */ +#define CEC_OP_AUD_FMT_ID_CEA861 0 +#define CEC_OP_AUD_FMT_ID_CEA861_CXT 1 + + +/* Audio Rate Control Feature */ +#define CEC_MSG_SET_AUDIO_RATE 0x9a +/* Audio Rate Operand (audio_rate) */ +#define CEC_OP_AUD_RATE_OFF 0 +#define CEC_OP_AUD_RATE_WIDE_STD 1 +#define CEC_OP_AUD_RATE_WIDE_FAST 2 +#define CEC_OP_AUD_RATE_WIDE_SLOW 3 +#define CEC_OP_AUD_RATE_NARROW_STD 4 +#define CEC_OP_AUD_RATE_NARROW_FAST 5 +#define CEC_OP_AUD_RATE_NARROW_SLOW 6 + + +/* Audio Return Channel Control Feature */ +#define CEC_MSG_INITIATE_ARC 0xc0 +#define CEC_MSG_REPORT_ARC_INITIATED 0xc1 +#define CEC_MSG_REPORT_ARC_TERMINATED 0xc2 +#define CEC_MSG_REQUEST_ARC_INITIATION 0xc3 +#define CEC_MSG_REQUEST_ARC_TERMINATION 0xc4 +#define CEC_MSG_TERMINATE_ARC 0xc5 + + +/* Dynamic Audio Lipsync Feature */ +/* Only for CEC 2.0 and up */ +#define CEC_MSG_REQUEST_CURRENT_LATENCY 0xa7 +#define CEC_MSG_REPORT_CURRENT_LATENCY 0xa8 +/* Low Latency Mode Operand (low_latency_mode) */ +#define CEC_OP_LOW_LATENCY_MODE_OFF 0 +#define CEC_OP_LOW_LATENCY_MODE_ON 1 +/* Audio Output Compensated Operand (audio_out_compensated) */ +#define CEC_OP_AUD_OUT_COMPENSATED_NA 0 +#define CEC_OP_AUD_OUT_COMPENSATED_DELAY 1 +#define CEC_OP_AUD_OUT_COMPENSATED_NO_DELAY 2 +#define CEC_OP_AUD_OUT_COMPENSATED_PARTIAL_DELAY 3 + + +/* Capability Discovery and Control Feature */ +#define CEC_MSG_CDC_MESSAGE 0xf8 +/* Ethernet-over-HDMI: nobody ever does this... */ +#define CEC_MSG_CDC_HEC_INQUIRE_STATE 0x00 +#define CEC_MSG_CDC_HEC_REPORT_STATE 0x01 +/* HEC Functionality State Operand (hec_func_state) */ +#define CEC_OP_HEC_FUNC_STATE_NOT_SUPPORTED 0 +#define CEC_OP_HEC_FUNC_STATE_INACTIVE 1 +#define CEC_OP_HEC_FUNC_STATE_ACTIVE 2 +#define CEC_OP_HEC_FUNC_STATE_ACTIVATION_FIELD 3 +/* Host Functionality State Operand (host_func_state) */ +#define CEC_OP_HOST_FUNC_STATE_NOT_SUPPORTED 0 +#define CEC_OP_HOST_FUNC_STATE_INACTIVE 1 +#define CEC_OP_HOST_FUNC_STATE_ACTIVE 2 +/* ENC Functionality State Operand (enc_func_state) */ +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_NOT_SUPPORTED 0 +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_INACTIVE 1 +#define CEC_OP_ENC_FUNC_STATE_EXT_CON_ACTIVE 2 +/* CDC Error Code Operand (cdc_errcode) */ +#define CEC_OP_CDC_ERROR_CODE_NONE 0 +#define CEC_OP_CDC_ERROR_CODE_CAP_UNSUPPORTED 1 +#define CEC_OP_CDC_ERROR_CODE_WRONG_STATE 2 +#define CEC_OP_CDC_ERROR_CODE_OTHER 3 +/* HEC Support Operand (hec_support) */ +#define CEC_OP_HEC_SUPPORT_NO 0 +#define CEC_OP_HEC_SUPPORT_YES 1 +/* HEC Activation Operand (hec_activation) */ +#define CEC_OP_HEC_ACTIVATION_ON 0 +#define CEC_OP_HEC_ACTIVATION_OFF 1 + +#define CEC_MSG_CDC_HEC_SET_STATE_ADJACENT 0x02 +#define CEC_MSG_CDC_HEC_SET_STATE 0x03 +/* HEC Set State Operand (hec_set_state) */ +#define CEC_OP_HEC_SET_STATE_DEACTIVATE 0 +#define CEC_OP_HEC_SET_STATE_ACTIVATE 1 + +#define CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION 0x04 +#define CEC_MSG_CDC_HEC_NOTIFY_ALIVE 0x05 +#define CEC_MSG_CDC_HEC_DISCOVER 0x06 +/* Hotplug Detect messages */ +#define CEC_MSG_CDC_HPD_SET_STATE 0x10 +/* HPD State Operand (hpd_state) */ +#define CEC_OP_HPD_STATE_CP_EDID_DISABLE 0 +#define CEC_OP_HPD_STATE_CP_EDID_ENABLE 1 +#define CEC_OP_HPD_STATE_CP_EDID_DISABLE_ENABLE 2 +#define CEC_OP_HPD_STATE_EDID_DISABLE 3 +#define CEC_OP_HPD_STATE_EDID_ENABLE 4 +#define CEC_OP_HPD_STATE_EDID_DISABLE_ENABLE 5 +#define CEC_MSG_CDC_HPD_REPORT_STATE 0x11 +/* HPD Error Code Operand (hpd_error) */ +#define CEC_OP_HPD_ERROR_NONE 0 +#define CEC_OP_HPD_ERROR_INITIATOR_NOT_CAPABLE 1 +#define CEC_OP_HPD_ERROR_INITIATOR_WRONG_STATE 2 +#define CEC_OP_HPD_ERROR_OTHER 3 +#define CEC_OP_HPD_ERROR_NONE_NO_VIDEO 4 + +#endif -- cgit v1.2.3 From 50f7d5a65e5a31e92a9d46663770cd9509f939a2 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 17 Jun 2016 09:20:52 -0300 Subject: [media] cec-funcs.h: static inlines to pack/unpack CEC messages This public header contains static inlines to pack and unpack CEC messages. It is for use in both the kernel and in userspace. Since the CEC framework will initially be in staging this header is not yet in include/uapi. Once the framework is moved out of staging this header should be moved to uapi at the same time. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 1881 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1881 insertions(+) create mode 100644 include/linux/cec-funcs.h (limited to 'include') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h new file mode 100644 index 000000000000..8ee1029b9b74 --- /dev/null +++ b/include/linux/cec-funcs.h @@ -0,0 +1,1881 @@ +/* + * cec - HDMI Consumer Electronics Control message functions + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/* + * Note: this framework is still in staging and it is likely the API + * will change before it goes out of staging. + * + * Once it is moved out of staging this header will move to uapi. + */ +#ifndef _CEC_UAPI_FUNCS_H +#define _CEC_UAPI_FUNCS_H + +#include + +/* One Touch Play Feature */ +static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_active_source(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_image_view_on(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_IMAGE_VIEW_ON; +} + +static inline void cec_msg_text_view_on(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TEXT_VIEW_ON; +} + + +/* Routing Control Feature */ +static inline void cec_msg_inactive_source(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_INACTIVE_SOURCE; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_inactive_source(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_request_active_source(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; + msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; +} + +static inline void cec_msg_routing_information(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_routing_information(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_routing_change(struct cec_msg *msg, + bool reply, + __u16 orig_phys_addr, + __u16 new_phys_addr) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_ROUTING_CHANGE; + msg->msg[2] = orig_phys_addr >> 8; + msg->msg[3] = orig_phys_addr & 0xff; + msg->msg[4] = new_phys_addr >> 8; + msg->msg[5] = new_phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_ROUTING_INFORMATION : 0; +} + +static inline void cec_ops_routing_change(const struct cec_msg *msg, + __u16 *orig_phys_addr, + __u16 *new_phys_addr) +{ + *orig_phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *new_phys_addr = (msg->msg[4] << 8) | msg->msg[5]; +} + +static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_SET_STREAM_PATH; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; +} + +static inline void cec_ops_set_stream_path(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + + +/* Standby Feature */ +static inline void cec_msg_standby(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_STANDBY; +} + + +/* One Touch Record Feature */ +static inline void cec_msg_record_off(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_RECORD_OFF; +} + +struct cec_op_arib_data { + __u16 transport_id; + __u16 service_id; + __u16 orig_network_id; +}; + +struct cec_op_atsc_data { + __u16 transport_id; + __u16 program_number; +}; + +struct cec_op_dvb_data { + __u16 transport_id; + __u16 service_id; + __u16 orig_network_id; +}; + +struct cec_op_channel_data { + __u8 channel_number_fmt; + __u16 major; + __u16 minor; +}; + +struct cec_op_digital_service_id { + __u8 service_id_method; + __u8 dig_bcast_system; + union { + struct cec_op_arib_data arib; + struct cec_op_atsc_data atsc; + struct cec_op_dvb_data dvb; + struct cec_op_channel_data channel; + }; +}; + +struct cec_op_record_src { + __u8 type; + union { + struct cec_op_digital_service_id digital; + struct { + __u8 ana_bcast_type; + __u16 ana_freq; + __u8 bcast_system; + } analog; + struct { + __u8 plug; + } ext_plug; + struct { + __u16 phys_addr; + } ext_phys_addr; + }; +}; + +static inline void cec_set_digital_service_id(__u8 *msg, + const struct cec_op_digital_service_id *digital) +{ + *msg++ = (digital->service_id_method << 7) | digital->dig_bcast_system; + if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { + *msg++ = (digital->channel.channel_number_fmt << 2) | + (digital->channel.major >> 8); + *msg++ = digital->channel.major && 0xff; + *msg++ = digital->channel.minor >> 8; + *msg++ = digital->channel.minor & 0xff; + *msg++ = 0; + *msg++ = 0; + return; + } + switch (digital->dig_bcast_system) { + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_GEN: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_CABLE: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_SAT: + case CEC_OP_DIG_SERVICE_BCAST_SYSTEM_ATSC_T: + *msg++ = digital->atsc.transport_id >> 8; + *msg++ = digital->atsc.transport_id & 0xff; + *msg++ = digital->atsc.program_number >> 8; + *msg++ = digital->atsc.program_number & 0xff; + *msg++ = 0; + *msg++ = 0; + break; + default: + *msg++ = digital->dvb.transport_id >> 8; + *msg++ = digital->dvb.transport_id & 0xff; + *msg++ = digital->dvb.service_id >> 8; + *msg++ = digital->dvb.service_id & 0xff; + *msg++ = digital->dvb.orig_network_id >> 8; + *msg++ = digital->dvb.orig_network_id & 0xff; + break; + } +} + +static inline void cec_get_digital_service_id(const __u8 *msg, + struct cec_op_digital_service_id *digital) +{ + digital->service_id_method = msg[0] >> 7; + digital->dig_bcast_system = msg[0] & 0x7f; + if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) { + digital->channel.channel_number_fmt = msg[1] >> 2; + digital->channel.major = ((msg[1] & 3) << 6) | msg[2]; + digital->channel.minor = (msg[3] << 8) | msg[4]; + return; + } + digital->dvb.transport_id = (msg[1] << 8) | msg[2]; + digital->dvb.service_id = (msg[3] << 8) | msg[4]; + digital->dvb.orig_network_id = (msg[5] << 8) | msg[6]; +} + +static inline void cec_msg_record_on_own(struct cec_msg *msg) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_OWN; +} + +static inline void cec_msg_record_on_digital(struct cec_msg *msg, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 10; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_DIGITAL; + cec_set_digital_service_id(msg->msg + 3, digital); +} + +static inline void cec_msg_record_on_analog(struct cec_msg *msg, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 7; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_ANALOG; + msg->msg[3] = ana_bcast_type; + msg->msg[4] = ana_freq >> 8; + msg->msg[5] = ana_freq & 0xff; + msg->msg[6] = bcast_system; +} + +static inline void cec_msg_record_on_plug(struct cec_msg *msg, + __u8 plug) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PLUG; + msg->msg[3] = plug; +} + +static inline void cec_msg_record_on_phys_addr(struct cec_msg *msg, + __u16 phys_addr) +{ + msg->len = 5; + msg->msg[1] = CEC_MSG_RECORD_ON; + msg->msg[2] = CEC_OP_RECORD_SRC_EXT_PHYS_ADDR; + msg->msg[3] = phys_addr >> 8; + msg->msg[4] = phys_addr & 0xff; +} + +static inline void cec_msg_record_on(struct cec_msg *msg, + const struct cec_op_record_src *rec_src) +{ + switch (rec_src->type) { + case CEC_OP_RECORD_SRC_OWN: + cec_msg_record_on_own(msg); + break; + case CEC_OP_RECORD_SRC_DIGITAL: + cec_msg_record_on_digital(msg, &rec_src->digital); + break; + case CEC_OP_RECORD_SRC_ANALOG: + cec_msg_record_on_analog(msg, + rec_src->analog.ana_bcast_type, + rec_src->analog.ana_freq, + rec_src->analog.bcast_system); + break; + case CEC_OP_RECORD_SRC_EXT_PLUG: + cec_msg_record_on_plug(msg, rec_src->ext_plug.plug); + break; + case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: + cec_msg_record_on_phys_addr(msg, + rec_src->ext_phys_addr.phys_addr); + break; + } +} + +static inline void cec_ops_record_on(const struct cec_msg *msg, + struct cec_op_record_src *rec_src) +{ + rec_src->type = msg->msg[2]; + switch (rec_src->type) { + case CEC_OP_RECORD_SRC_OWN: + break; + case CEC_OP_RECORD_SRC_DIGITAL: + cec_get_digital_service_id(msg->msg + 3, &rec_src->digital); + break; + case CEC_OP_RECORD_SRC_ANALOG: + rec_src->analog.ana_bcast_type = msg->msg[3]; + rec_src->analog.ana_freq = + (msg->msg[4] << 8) | msg->msg[5]; + rec_src->analog.bcast_system = msg->msg[6]; + break; + case CEC_OP_RECORD_SRC_EXT_PLUG: + rec_src->ext_plug.plug = msg->msg[3]; + break; + case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: + rec_src->ext_phys_addr.phys_addr = + (msg->msg[3] << 8) | msg->msg[4]; + break; + } +} + +static inline void cec_msg_record_status(struct cec_msg *msg, __u8 rec_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_RECORD_STATUS; + msg->msg[2] = rec_status; +} + +static inline void cec_ops_record_status(const struct cec_msg *msg, + __u8 *rec_status) +{ + *rec_status = msg->msg[2]; +} + +static inline void cec_msg_record_tv_screen(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_RECORD_TV_SCREEN; + msg->reply = reply ? CEC_MSG_RECORD_ON : 0; +} + + +/* Timer Programming Feature */ +static inline void cec_msg_timer_status(struct cec_msg *msg, + __u8 timer_overlap_warning, + __u8 media_info, + __u8 prog_info, + __u8 prog_error, + __u8 duration_hr, + __u8 duration_min) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_TIMER_STATUS; + msg->msg[2] = (timer_overlap_warning << 7) | + (media_info << 5) | + (prog_info ? 0x10 : 0) | + (prog_info ? prog_info : prog_error); + if (prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || + prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || + prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { + msg->len += 2; + msg->msg[3] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[4] = ((duration_min / 10) << 4) | (duration_min % 10); + } +} + +static inline void cec_ops_timer_status(struct cec_msg *msg, + __u8 *timer_overlap_warning, + __u8 *media_info, + __u8 *prog_info, + __u8 *prog_error, + __u8 *duration_hr, + __u8 *duration_min) +{ + *timer_overlap_warning = msg->msg[2] >> 7; + *media_info = (msg->msg[2] >> 5) & 3; + if (msg->msg[2] & 0x10) { + *prog_info = msg->msg[2] & 0xf; + *prog_error = 0; + } else { + *prog_info = 0; + *prog_error = msg->msg[2] & 0xf; + } + if (*prog_info == CEC_OP_PROG_INFO_NOT_ENOUGH_SPACE || + *prog_info == CEC_OP_PROG_INFO_MIGHT_NOT_BE_ENOUGH_SPACE || + *prog_error == CEC_OP_PROG_ERROR_DUPLICATE) { + *duration_hr = (msg->msg[3] >> 4) * 10 + (msg->msg[3] & 0xf); + *duration_min = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + } else { + *duration_hr = *duration_min = 0; + } +} + +static inline void cec_msg_timer_cleared_status(struct cec_msg *msg, + __u8 timer_cleared_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_TIMER_CLEARED_STATUS; + msg->msg[2] = timer_cleared_status; +} + +static inline void cec_ops_timer_cleared_status(struct cec_msg *msg, + __u8 *timer_cleared_status) +{ + *timer_cleared_status = msg->msg[2]; +} + +static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_CLEAR_ANALOGUE_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ana_bcast_type; + msg->msg[10] = ana_freq >> 8; + msg->msg[11] = ana_freq & 0xff; + msg->msg[12] = bcast_system; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; +} + +static inline void cec_ops_clear_analogue_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ana_bcast_type = msg->msg[9]; + *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; + *bcast_system = msg->msg[12]; +} + +static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 16; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; + msg->msg[1] = CEC_MSG_CLEAR_DIGITAL_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + cec_set_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_ops_clear_digital_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + struct cec_op_digital_service_id *digital) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + cec_get_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ext_src_spec, + __u8 plug, + __u16 phys_addr) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_CLEAR_EXT_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ext_src_spec; + msg->msg[10] = plug; + msg->msg[11] = phys_addr >> 8; + msg->msg[12] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; +} + +static inline void cec_ops_clear_ext_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ext_src_spec, + __u8 *plug, + __u16 *phys_addr) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ext_src_spec = msg->msg[9]; + *plug = msg->msg[10]; + *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; +} + +static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_SET_ANALOGUE_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ana_bcast_type; + msg->msg[10] = ana_freq >> 8; + msg->msg[11] = ana_freq & 0xff; + msg->msg[12] = bcast_system; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; +} + +static inline void cec_ops_set_analogue_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ana_bcast_type = msg->msg[9]; + *ana_freq = (msg->msg[10] << 8) | msg->msg[11]; + *bcast_system = msg->msg[12]; +} + +static inline void cec_msg_set_digital_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 16; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; + msg->msg[1] = CEC_MSG_SET_DIGITAL_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + cec_set_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_ops_set_digital_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + struct cec_op_digital_service_id *digital) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + cec_get_digital_service_id(msg->msg + 9, digital); +} + +static inline void cec_msg_set_ext_timer(struct cec_msg *msg, + bool reply, + __u8 day, + __u8 month, + __u8 start_hr, + __u8 start_min, + __u8 duration_hr, + __u8 duration_min, + __u8 recording_seq, + __u8 ext_src_spec, + __u8 plug, + __u16 phys_addr) +{ + msg->len = 13; + msg->msg[1] = CEC_MSG_SET_EXT_TIMER; + msg->msg[2] = day; + msg->msg[3] = month; + /* Hours and minutes are in BCD format */ + msg->msg[4] = ((start_hr / 10) << 4) | (start_hr % 10); + msg->msg[5] = ((start_min / 10) << 4) | (start_min % 10); + msg->msg[6] = ((duration_hr / 10) << 4) | (duration_hr % 10); + msg->msg[7] = ((duration_min / 10) << 4) | (duration_min % 10); + msg->msg[8] = recording_seq; + msg->msg[9] = ext_src_spec; + msg->msg[10] = plug; + msg->msg[11] = phys_addr >> 8; + msg->msg[12] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; +} + +static inline void cec_ops_set_ext_timer(struct cec_msg *msg, + __u8 *day, + __u8 *month, + __u8 *start_hr, + __u8 *start_min, + __u8 *duration_hr, + __u8 *duration_min, + __u8 *recording_seq, + __u8 *ext_src_spec, + __u8 *plug, + __u16 *phys_addr) +{ + *day = msg->msg[2]; + *month = msg->msg[3]; + /* Hours and minutes are in BCD format */ + *start_hr = (msg->msg[4] >> 4) * 10 + (msg->msg[4] & 0xf); + *start_min = (msg->msg[5] >> 4) * 10 + (msg->msg[5] & 0xf); + *duration_hr = (msg->msg[6] >> 4) * 10 + (msg->msg[6] & 0xf); + *duration_min = (msg->msg[7] >> 4) * 10 + (msg->msg[7] & 0xf); + *recording_seq = msg->msg[8]; + *ext_src_spec = msg->msg[9]; + *plug = msg->msg[10]; + *phys_addr = (msg->msg[11] << 8) | msg->msg[12]; +} + +static inline void cec_msg_set_timer_program_title(struct cec_msg *msg, + const char *prog_title) +{ + unsigned int len = strlen(prog_title); + + if (len > 14) + len = 14; + msg->len = 2 + len; + msg->msg[1] = CEC_MSG_SET_TIMER_PROGRAM_TITLE; + memcpy(msg->msg + 2, prog_title, len); +} + +static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg, + char *prog_title) +{ + unsigned int len = msg->len - 2; + + if (len > 14) + len = 14; + memcpy(prog_title, msg->msg + 2, len); + prog_title[len] = '\0'; +} + +/* System Information Feature */ +static inline void cec_msg_cec_version(struct cec_msg *msg, __u8 cec_version) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_CEC_VERSION; + msg->msg[2] = cec_version; +} + +static inline void cec_ops_cec_version(const struct cec_msg *msg, + __u8 *cec_version) +{ + *cec_version = msg->msg[2]; +} + +static inline void cec_msg_get_cec_version(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GET_CEC_VERSION; + msg->reply = reply ? CEC_MSG_CEC_VERSION : 0; +} + +static inline void cec_msg_report_physical_addr(struct cec_msg *msg, + __u16 phys_addr, __u8 prim_devtype) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->msg[4] = prim_devtype; +} + +static inline void cec_ops_report_physical_addr(const struct cec_msg *msg, + __u16 *phys_addr, __u8 *prim_devtype) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *prim_devtype = msg->msg[4]; +} + +static inline void cec_msg_give_physical_addr(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_PHYSICAL_ADDR; + msg->reply = reply ? CEC_MSG_REPORT_PHYSICAL_ADDR : 0; +} + +static inline void cec_msg_set_menu_language(struct cec_msg *msg, + const char *language) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; + memcpy(msg->msg + 2, language, 3); +} + +static inline void cec_ops_set_menu_language(struct cec_msg *msg, + char *language) +{ + memcpy(language, msg->msg + 2, 3); + language[3] = '\0'; +} + +static inline void cec_msg_get_menu_language(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GET_MENU_LANGUAGE; + msg->reply = reply ? CEC_MSG_SET_MENU_LANGUAGE : 0; +} + +/* + * Assumes a single RC Profile byte and a single Device Features byte, + * i.e. no extended features are supported by this helper function. + * + * As of CEC 2.0 no extended features are defined, should those be added + * in the future, then this function needs to be adapted or a new function + * should be added. + */ +static inline void cec_msg_report_features(struct cec_msg *msg, + __u8 cec_version, __u8 all_device_types, + __u8 rc_profile, __u8 dev_features) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_FEATURES; + msg->msg[2] = cec_version; + msg->msg[3] = all_device_types; + msg->msg[4] = rc_profile; + msg->msg[5] = dev_features; +} + +static inline void cec_ops_report_features(const struct cec_msg *msg, + __u8 *cec_version, __u8 *all_device_types, + const __u8 **rc_profile, const __u8 **dev_features) +{ + const __u8 *p = &msg->msg[4]; + + *cec_version = msg->msg[2]; + *all_device_types = msg->msg[3]; + *rc_profile = p; + while (p < &msg->msg[14] && (*p & CEC_OP_FEAT_EXT)) + p++; + if (!(*p & CEC_OP_FEAT_EXT)) { + *dev_features = p + 1; + while (p < &msg->msg[15] && (*p & CEC_OP_FEAT_EXT)) + p++; + } + if (*p & CEC_OP_FEAT_EXT) + *rc_profile = *dev_features = NULL; +} + +static inline void cec_msg_give_features(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_FEATURES; + msg->reply = reply ? CEC_MSG_REPORT_FEATURES : 0; +} + +/* Deck Control Feature */ +static inline void cec_msg_deck_control(struct cec_msg *msg, + __u8 deck_control_mode) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_DECK_CONTROL; + msg->msg[2] = deck_control_mode; +} + +static inline void cec_ops_deck_control(struct cec_msg *msg, + __u8 *deck_control_mode) +{ + *deck_control_mode = msg->msg[2]; +} + +static inline void cec_msg_deck_status(struct cec_msg *msg, + __u8 deck_info) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_DECK_STATUS; + msg->msg[2] = deck_info; +} + +static inline void cec_ops_deck_status(struct cec_msg *msg, + __u8 *deck_info) +{ + *deck_info = msg->msg[2]; +} + +static inline void cec_msg_give_deck_status(struct cec_msg *msg, + bool reply, + __u8 status_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_GIVE_DECK_STATUS; + msg->msg[2] = status_req; + msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; +} + +static inline void cec_ops_give_deck_status(struct cec_msg *msg, + __u8 *status_req) +{ + *status_req = msg->msg[2]; +} + +static inline void cec_msg_play(struct cec_msg *msg, + __u8 play_mode) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_PLAY; + msg->msg[2] = play_mode; +} + +static inline void cec_ops_play(struct cec_msg *msg, + __u8 *play_mode) +{ + *play_mode = msg->msg[2]; +} + + +/* Tuner Control Feature */ +struct cec_op_tuner_device_info { + __u8 rec_flag; + __u8 tuner_display_info; + bool is_analog; + union { + struct cec_op_digital_service_id digital; + struct { + __u8 ana_bcast_type; + __u16 ana_freq; + __u8 bcast_system; + } analog; + }; +}; + +static inline void cec_msg_tuner_device_status_analog(struct cec_msg *msg, + __u8 rec_flag, + __u8 tuner_display_info, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 7; + msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; + msg->msg[2] = (rec_flag << 7) | tuner_display_info; + msg->msg[3] = ana_bcast_type; + msg->msg[4] = ana_freq >> 8; + msg->msg[5] = ana_freq & 0xff; + msg->msg[6] = bcast_system; +} + +static inline void cec_msg_tuner_device_status_digital(struct cec_msg *msg, + __u8 rec_flag, __u8 tuner_display_info, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 10; + msg->msg[1] = CEC_MSG_TUNER_DEVICE_STATUS; + msg->msg[2] = (rec_flag << 7) | tuner_display_info; + cec_set_digital_service_id(msg->msg + 3, digital); +} + +static inline void cec_msg_tuner_device_status(struct cec_msg *msg, + const struct cec_op_tuner_device_info *tuner_dev_info) +{ + if (tuner_dev_info->is_analog) + cec_msg_tuner_device_status_analog(msg, + tuner_dev_info->rec_flag, + tuner_dev_info->tuner_display_info, + tuner_dev_info->analog.ana_bcast_type, + tuner_dev_info->analog.ana_freq, + tuner_dev_info->analog.bcast_system); + else + cec_msg_tuner_device_status_digital(msg, + tuner_dev_info->rec_flag, + tuner_dev_info->tuner_display_info, + &tuner_dev_info->digital); +} + +static inline void cec_ops_tuner_device_status(struct cec_msg *msg, + struct cec_op_tuner_device_info *tuner_dev_info) +{ + tuner_dev_info->is_analog = msg->len < 10; + tuner_dev_info->rec_flag = msg->msg[2] >> 7; + tuner_dev_info->tuner_display_info = msg->msg[2] & 0x7f; + if (tuner_dev_info->is_analog) { + tuner_dev_info->analog.ana_bcast_type = msg->msg[3]; + tuner_dev_info->analog.ana_freq = (msg->msg[4] << 8) | msg->msg[5]; + tuner_dev_info->analog.bcast_system = msg->msg[6]; + return; + } + cec_get_digital_service_id(msg->msg + 3, &tuner_dev_info->digital); +} + +static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, + bool reply, + __u8 status_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_GIVE_TUNER_DEVICE_STATUS; + msg->msg[2] = status_req; + msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; +} + +static inline void cec_ops_give_tuner_device_status(struct cec_msg *msg, + __u8 *status_req) +{ + *status_req = msg->msg[2]; +} + +static inline void cec_msg_select_analogue_service(struct cec_msg *msg, + __u8 ana_bcast_type, + __u16 ana_freq, + __u8 bcast_system) +{ + msg->len = 6; + msg->msg[1] = CEC_MSG_SELECT_ANALOGUE_SERVICE; + msg->msg[2] = ana_bcast_type; + msg->msg[3] = ana_freq >> 8; + msg->msg[4] = ana_freq & 0xff; + msg->msg[5] = bcast_system; +} + +static inline void cec_ops_select_analogue_service(struct cec_msg *msg, + __u8 *ana_bcast_type, + __u16 *ana_freq, + __u8 *bcast_system) +{ + *ana_bcast_type = msg->msg[2]; + *ana_freq = (msg->msg[3] << 8) | msg->msg[4]; + *bcast_system = msg->msg[5]; +} + +static inline void cec_msg_select_digital_service(struct cec_msg *msg, + const struct cec_op_digital_service_id *digital) +{ + msg->len = 9; + msg->msg[1] = CEC_MSG_SELECT_DIGITAL_SERVICE; + cec_set_digital_service_id(msg->msg + 2, digital); +} + +static inline void cec_ops_select_digital_service(struct cec_msg *msg, + struct cec_op_digital_service_id *digital) +{ + cec_get_digital_service_id(msg->msg + 2, digital); +} + +static inline void cec_msg_tuner_step_decrement(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TUNER_STEP_DECREMENT; +} + +static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TUNER_STEP_INCREMENT; +} + + +/* Vendor Specific Commands Feature */ +static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; + msg->msg[2] = vendor_id >> 16; + msg->msg[3] = (vendor_id >> 8) & 0xff; + msg->msg[4] = vendor_id & 0xff; +} + +static inline void cec_ops_device_vendor_id(const struct cec_msg *msg, + __u32 *vendor_id) +{ + *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4]; +} + +static inline void cec_msg_give_device_vendor_id(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_DEVICE_VENDOR_ID; + msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0; +} + +static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_UP; +} + + +/* OSD Display Feature */ +static inline void cec_msg_set_osd_string(struct cec_msg *msg, + __u8 disp_ctl, + const char *osd) +{ + unsigned int len = strlen(osd); + + if (len > 13) + len = 13; + msg->len = 3 + len; + msg->msg[1] = CEC_MSG_SET_OSD_STRING; + msg->msg[2] = disp_ctl; + memcpy(msg->msg + 3, osd, len); +} + +static inline void cec_ops_set_osd_string(const struct cec_msg *msg, + __u8 *disp_ctl, + char *osd) +{ + unsigned int len = msg->len - 3; + + *disp_ctl = msg->msg[2]; + if (len > 13) + len = 13; + memcpy(osd, msg->msg + 3, len); + osd[len] = '\0'; +} + + +/* Device OSD Transfer Feature */ +static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name) +{ + unsigned int len = strlen(name); + + if (len > 14) + len = 14; + msg->len = 2 + len; + msg->msg[1] = CEC_MSG_SET_OSD_NAME; + memcpy(msg->msg + 2, name, len); +} + +static inline void cec_ops_set_osd_name(const struct cec_msg *msg, + char *name) +{ + unsigned int len = msg->len - 2; + + if (len > 14) + len = 14; + memcpy(name, msg->msg + 2, len); + name[len] = '\0'; +} + +static inline void cec_msg_give_osd_name(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_OSD_NAME; + msg->reply = reply ? CEC_MSG_SET_OSD_NAME : 0; +} + + +/* Device Menu Control Feature */ +static inline void cec_msg_menu_status(struct cec_msg *msg, + __u8 menu_state) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_MENU_STATUS; + msg->msg[2] = menu_state; +} + +static inline void cec_ops_menu_status(struct cec_msg *msg, + __u8 *menu_state) +{ + *menu_state = msg->msg[2]; +} + +static inline void cec_msg_menu_request(struct cec_msg *msg, + bool reply, + __u8 menu_req) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_MENU_REQUEST; + msg->msg[2] = menu_req; + msg->reply = reply ? CEC_MSG_MENU_STATUS : 0; +} + +static inline void cec_ops_menu_request(struct cec_msg *msg, + __u8 *menu_req) +{ + *menu_req = msg->msg[2]; +} + +struct cec_op_ui_command { + __u8 ui_cmd; + bool has_opt_arg; + union { + struct cec_op_channel_data channel_identifier; + __u8 ui_broadcast_type; + __u8 ui_sound_presentation_control; + __u8 play_mode; + __u8 ui_function_media; + __u8 ui_function_select_av_input; + __u8 ui_function_select_audio_input; + }; +}; + +static inline void cec_msg_user_control_pressed(struct cec_msg *msg, + const struct cec_op_ui_command *ui_cmd) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_USER_CONTROL_PRESSED; + msg->msg[2] = ui_cmd->ui_cmd; + if (!ui_cmd->has_opt_arg) + return; + switch (ui_cmd->ui_cmd) { + case 0x56: + case 0x57: + case 0x60: + case 0x68: + case 0x69: + case 0x6a: + /* The optional operand is one byte for all these ui commands */ + msg->len++; + msg->msg[3] = ui_cmd->play_mode; + break; + case 0x67: + msg->len += 4; + msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) | + (ui_cmd->channel_identifier.major >> 8); + msg->msg[4] = ui_cmd->channel_identifier.major && 0xff; + msg->msg[5] = ui_cmd->channel_identifier.minor >> 8; + msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff; + break; + } +} + +static inline void cec_ops_user_control_pressed(struct cec_msg *msg, + struct cec_op_ui_command *ui_cmd) +{ + ui_cmd->ui_cmd = msg->msg[2]; + ui_cmd->has_opt_arg = false; + if (msg->len == 3) + return; + switch (ui_cmd->ui_cmd) { + case 0x56: + case 0x57: + case 0x60: + case 0x68: + case 0x69: + case 0x6a: + /* The optional operand is one byte for all these ui commands */ + ui_cmd->play_mode = msg->msg[3]; + ui_cmd->has_opt_arg = true; + break; + case 0x67: + if (msg->len < 7) + break; + ui_cmd->has_opt_arg = true; + ui_cmd->channel_identifier.channel_number_fmt = msg->msg[3] >> 2; + ui_cmd->channel_identifier.major = ((msg->msg[3] & 3) << 6) | msg->msg[4]; + ui_cmd->channel_identifier.minor = (msg->msg[5] << 8) | msg->msg[6]; + break; + } +} + +static inline void cec_msg_user_control_released(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_USER_CONTROL_RELEASED; +} + +/* Remote Control Passthrough Feature */ + +/* Power Status Feature */ +static inline void cec_msg_report_power_status(struct cec_msg *msg, + __u8 pwr_state) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_REPORT_POWER_STATUS; + msg->msg[2] = pwr_state; +} + +static inline void cec_ops_report_power_status(const struct cec_msg *msg, + __u8 *pwr_state) +{ + *pwr_state = msg->msg[2]; +} + +static inline void cec_msg_give_device_power_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_DEVICE_POWER_STATUS; + msg->reply = reply ? CEC_MSG_REPORT_POWER_STATUS : 0; +} + +/* General Protocol Messages */ +static inline void cec_msg_feature_abort(struct cec_msg *msg, + __u8 abort_msg, __u8 reason) +{ + msg->len = 4; + msg->msg[1] = CEC_MSG_FEATURE_ABORT; + msg->msg[2] = abort_msg; + msg->msg[3] = reason; +} + +static inline void cec_ops_feature_abort(const struct cec_msg *msg, + __u8 *abort_msg, __u8 *reason) +{ + *abort_msg = msg->msg[2]; + *reason = msg->msg[3]; +} + +/* This changes the current message into a feature abort message */ +static inline void cec_msg_reply_feature_abort(struct cec_msg *msg, __u8 reason) +{ + cec_msg_set_reply_to(msg, msg); + msg->len = 4; + msg->msg[2] = msg->msg[1]; + msg->msg[3] = reason; + msg->msg[1] = CEC_MSG_FEATURE_ABORT; +} + +static inline void cec_msg_abort(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_ABORT; +} + + +/* System Audio Control Feature */ +static inline void cec_msg_report_audio_status(struct cec_msg *msg, + __u8 aud_mute_status, + __u8 aud_vol_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_REPORT_AUDIO_STATUS; + msg->msg[2] = (aud_mute_status << 7) | (aud_vol_status & 0x7f); +} + +static inline void cec_ops_report_audio_status(const struct cec_msg *msg, + __u8 *aud_mute_status, + __u8 *aud_vol_status) +{ + *aud_mute_status = msg->msg[2] >> 7; + *aud_vol_status = msg->msg[2] & 0x7f; +} + +static inline void cec_msg_give_audio_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_AUDIO_STATUS; + msg->reply = reply ? CEC_MSG_REPORT_AUDIO_STATUS : 0; +} + +static inline void cec_msg_set_system_audio_mode(struct cec_msg *msg, + __u8 sys_aud_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_SYSTEM_AUDIO_MODE; + msg->msg[2] = sys_aud_status; +} + +static inline void cec_ops_set_system_audio_mode(const struct cec_msg *msg, + __u8 *sys_aud_status) +{ + *sys_aud_status = msg->msg[2]; +} + +static inline void cec_msg_system_audio_mode_request(struct cec_msg *msg, + bool reply, + __u16 phys_addr) +{ + msg->len = phys_addr == 0xffff ? 2 : 4; + msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_SET_SYSTEM_AUDIO_MODE : 0; + +} + +static inline void cec_ops_system_audio_mode_request(const struct cec_msg *msg, + __u16 *phys_addr) +{ + if (msg->len < 4) + *phys_addr = 0xffff; + else + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_system_audio_mode_status(struct cec_msg *msg, + __u8 sys_aud_status) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SYSTEM_AUDIO_MODE_STATUS; + msg->msg[2] = sys_aud_status; +} + +static inline void cec_ops_system_audio_mode_status(const struct cec_msg *msg, + __u8 *sys_aud_status) +{ + *sys_aud_status = msg->msg[2]; +} + +static inline void cec_msg_give_system_audio_mode_status(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS; + msg->reply = reply ? CEC_MSG_SYSTEM_AUDIO_MODE_STATUS : 0; +} + +static inline void cec_msg_report_short_audio_descriptor(struct cec_msg *msg, + __u8 num_descriptors, + const __u32 *descriptors) +{ + unsigned int i; + + if (num_descriptors > 4) + num_descriptors = 4; + msg->len = 2 + num_descriptors * 3; + msg->msg[1] = CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR; + for (i = 0; i < num_descriptors; i++) { + msg->msg[2 + i * 3] = (descriptors[i] >> 16) & 0xff; + msg->msg[3 + i * 3] = (descriptors[i] >> 8) & 0xff; + msg->msg[4 + i * 3] = descriptors[i] & 0xff; + } +} + +static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *msg, + __u8 *num_descriptors, + __u32 *descriptors) +{ + unsigned int i; + + *num_descriptors = (msg->len - 2) / 3; + if (*num_descriptors > 4) + *num_descriptors = 4; + for (i = 0; i < *num_descriptors; i++) + descriptors[i] = (msg->msg[2 + i * 3] << 16) | + (msg->msg[3 + i * 3] << 8) | + msg->msg[4 + i * 3]; +} + +static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, + __u8 num_descriptors, + const __u8 *audio_format_id, + const __u8 *audio_format_code) +{ + unsigned int i; + + if (num_descriptors > 4) + num_descriptors = 4; + msg->len = 2 + num_descriptors; + msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR; + for (i = 0; i < num_descriptors; i++) + msg->msg[2 + i] = (audio_format_id[i] << 6) | + (audio_format_code[i] & 0x3f); +} + +static inline void cec_ops_request_short_audio_descriptor(const struct cec_msg *msg, + __u8 *num_descriptors, + __u8 *audio_format_id, + __u8 *audio_format_code) +{ + unsigned int i; + + *num_descriptors = msg->len - 2; + if (*num_descriptors > 4) + *num_descriptors = 4; + for (i = 0; i < *num_descriptors; i++) { + audio_format_id[i] = msg->msg[2 + i] >> 6; + audio_format_code[i] = msg->msg[2 + i] & 0x3f; + } +} + + +/* Audio Rate Control Feature */ +static inline void cec_msg_set_audio_rate(struct cec_msg *msg, + __u8 audio_rate) +{ + msg->len = 3; + msg->msg[1] = CEC_MSG_SET_AUDIO_RATE; + msg->msg[2] = audio_rate; +} + +static inline void cec_ops_set_audio_rate(const struct cec_msg *msg, + __u8 *audio_rate) +{ + *audio_rate = msg->msg[2]; +} + + +/* Audio Return Channel Control Feature */ +static inline void cec_msg_report_arc_initiated(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REPORT_ARC_INITIATED; +} + +static inline void cec_msg_initiate_arc(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_INITIATE_ARC; + msg->reply = reply ? CEC_MSG_REPORT_ARC_INITIATED : 0; +} + +static inline void cec_msg_request_arc_initiation(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REQUEST_ARC_INITIATION; + msg->reply = reply ? CEC_MSG_INITIATE_ARC : 0; +} + +static inline void cec_msg_report_arc_terminated(struct cec_msg *msg) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REPORT_ARC_TERMINATED; +} + +static inline void cec_msg_terminate_arc(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_TERMINATE_ARC; + msg->reply = reply ? CEC_MSG_REPORT_ARC_TERMINATED : 0; +} + +static inline void cec_msg_request_arc_termination(struct cec_msg *msg, + bool reply) +{ + msg->len = 2; + msg->msg[1] = CEC_MSG_REQUEST_ARC_TERMINATION; + msg->reply = reply ? CEC_MSG_TERMINATE_ARC : 0; +} + + +/* Dynamic Audio Lipsync Feature */ +/* Only for CEC 2.0 and up */ +static inline void cec_msg_report_current_latency(struct cec_msg *msg, + __u16 phys_addr, + __u8 video_latency, + __u8 low_latency_mode, + __u8 audio_out_compensated, + __u8 audio_out_delay) +{ + msg->len = 7; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->msg[4] = video_latency; + msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated; + msg->msg[6] = audio_out_delay; +} + +static inline void cec_ops_report_current_latency(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *video_latency, + __u8 *low_latency_mode, + __u8 *audio_out_compensated, + __u8 *audio_out_delay) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *video_latency = msg->msg[4]; + *low_latency_mode = (msg->msg[5] >> 2) & 1; + *audio_out_compensated = msg->msg[5] & 3; + *audio_out_delay = msg->msg[6]; +} + +static inline void cec_msg_request_current_latency(struct cec_msg *msg, + bool reply, + __u16 phys_addr) +{ + msg->len = 4; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; + msg->msg[2] = phys_addr >> 8; + msg->msg[3] = phys_addr & 0xff; + msg->reply = reply ? CEC_MSG_REPORT_CURRENT_LATENCY : 0; +} + +static inline void cec_ops_request_current_latency(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + + +/* Capability Discovery and Control Feature */ +static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2) +{ + msg->len = 9; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; +} + +static inline void cec_ops_cdc_hec_inquire_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; +} + +static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, + __u16 target_phys_addr, + __u8 hec_func_state, + __u8 host_func_state, + __u8 enc_func_state, + __u8 cdc_errcode, + __u8 has_field, + __u16 hec_field) +{ + msg->len = has_field ? 10 : 8; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; + msg->msg[5] = target_phys_addr >> 8; + msg->msg[6] = target_phys_addr & 0xff; + msg->msg[7] = (hec_func_state << 6) | + (host_func_state << 4) | + (enc_func_state << 2) | + cdc_errcode; + if (has_field) { + msg->msg[8] = hec_field >> 8; + msg->msg[9] = hec_field & 0xff; + } +} + +static inline void cec_ops_cdc_hec_report_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *target_phys_addr, + __u8 *hec_func_state, + __u8 *host_func_state, + __u8 *enc_func_state, + __u8 *cdc_errcode, + __u8 *has_field, + __u16 *hec_field) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *target_phys_addr = (msg->msg[5] << 8) | msg->msg[6]; + *hec_func_state = msg->msg[7] >> 6; + *host_func_state = (msg->msg[7] >> 4) & 3; + *enc_func_state = (msg->msg[7] >> 4) & 3; + *cdc_errcode = msg->msg[7] & 3; + *has_field = msg->len >= 10; + *hec_field = *has_field ? ((msg->msg[8] << 8) | msg->msg[9]) : 0; +} + +static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2, + __u8 hec_set_state, + __u16 phys_addr3, + __u16 phys_addr4, + __u16 phys_addr5) +{ + msg->len = 10; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; + msg->msg[9] = hec_set_state; + if (phys_addr3 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr3 >> 8; + msg->msg[msg->len++] = phys_addr3 & 0xff; + if (phys_addr4 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr4 >> 8; + msg->msg[msg->len++] = phys_addr4 & 0xff; + if (phys_addr5 != CEC_PHYS_ADDR_INVALID) { + msg->msg[msg->len++] = phys_addr5 >> 8; + msg->msg[msg->len++] = phys_addr5 & 0xff; + } + } + } +} + +static inline void cec_ops_cdc_hec_set_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2, + __u8 *hec_set_state, + __u16 *phys_addr3, + __u16 *phys_addr4, + __u16 *phys_addr5) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; + *hec_set_state = msg->msg[9]; + *phys_addr3 = *phys_addr4 = *phys_addr5 = CEC_PHYS_ADDR_INVALID; + if (msg->len >= 12) + *phys_addr3 = (msg->msg[10] << 8) | msg->msg[11]; + if (msg->len >= 14) + *phys_addr4 = (msg->msg[12] << 8) | msg->msg[13]; + if (msg->len >= 16) + *phys_addr5 = (msg->msg[14] << 8) | msg->msg[15]; +} + +static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, + __u16 phys_addr1, + __u8 hec_set_state) +{ + msg->len = 8; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = hec_set_state; +} + +static inline void cec_ops_cdc_hec_set_state_adjacent(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u8 *hec_set_state) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *hec_set_state = msg->msg[7]; +} + +static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, + __u16 phys_addr1, + __u16 phys_addr2, + __u16 phys_addr3) +{ + msg->len = 11; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; + msg->msg[5] = phys_addr1 >> 8; + msg->msg[6] = phys_addr1 & 0xff; + msg->msg[7] = phys_addr2 >> 8; + msg->msg[8] = phys_addr2 & 0xff; + msg->msg[9] = phys_addr3 >> 8; + msg->msg[10] = phys_addr3 & 0xff; +} + +static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *msg, + __u16 *phys_addr, + __u16 *phys_addr1, + __u16 *phys_addr2, + __u16 *phys_addr3) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *phys_addr1 = (msg->msg[5] << 8) | msg->msg[6]; + *phys_addr2 = (msg->msg[7] << 8) | msg->msg[8]; + *phys_addr3 = (msg->msg[9] << 8) | msg->msg[10]; +} + +static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; +} + +static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) +{ + msg->len = 5; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; +} + +static inline void cec_ops_cdc_hec_discover(const struct cec_msg *msg, + __u16 *phys_addr) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; +} + +static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, + __u8 input_port, + __u8 hpd_state) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; + msg->msg[5] = (input_port << 4) | hpd_state; +} + +static inline void cec_ops_cdc_hpd_set_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *input_port, + __u8 *hpd_state) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *input_port = msg->msg[5] >> 4; + *hpd_state = msg->msg[5] & 0xf; +} + +static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, + __u8 hpd_state, + __u8 hpd_error) +{ + msg->len = 6; + msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[1] = CEC_MSG_CDC_MESSAGE; + /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ + msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; + msg->msg[5] = (hpd_state << 4) | hpd_error; +} + +static inline void cec_ops_cdc_hpd_report_state(const struct cec_msg *msg, + __u16 *phys_addr, + __u8 *hpd_state, + __u8 *hpd_error) +{ + *phys_addr = (msg->msg[2] << 8) | msg->msg[3]; + *hpd_state = msg->msg[5] >> 4; + *hpd_error = msg->msg[5] & 0xf; +} + +#endif -- cgit v1.2.3 From a56960e8b406d36b612776c79134b954adc2ca18 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sat, 25 Jun 2016 09:43:58 -0300 Subject: [media] cec: add HDMI CEC framework (core) The added HDMI CEC framework provides a generic kernel interface for HDMI CEC devices. Note that the CEC framework is added to staging/media and that the cec.h and cec-funcs.h headers are not exported yet. While the kABI is mature, I would prefer to allow the uABI some more time before it is mainlined in case it needs more tweaks. This adds the cec-core.c, media/cec.h and cec-priv.h sources. Signed-off-by: Hans Verkuil [k.debski@samsung.com: Merged CEC Updates commit by Hans Verkuil] [k.debski@samsung.com: Merged Update author commit by Hans Verkuil] [k.debski@samsung.com: code cleanup and fixes] [k.debski@samsung.com: add missing CEC commands to match spec] [k.debski@samsung.com: add RC framework support] [k.debski@samsung.com: move and edit documentation] [k.debski@samsung.com: add vendor id reporting] [k.debski@samsung.com: reorder of API structs and add reserved fields] [k.debski@samsung.com: fix handling of events and fix 32/64bit timespec problem] [k.debski@samsung.com: add sequence number handling] [k.debski@samsung.com: add passthrough mode] [k.debski@samsung.com: fix CEC defines, add missing CEC 2.0 commands] Signed-off-by: Kamil Debski Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 232 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 232 insertions(+) create mode 100644 include/media/cec.h (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h new file mode 100644 index 000000000000..9a791c08a789 --- /dev/null +++ b/include/media/cec.h @@ -0,0 +1,232 @@ +/* + * cec - HDMI Consumer Electronics Control support header + * + * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _MEDIA_CEC_H +#define _MEDIA_CEC_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * struct cec_devnode - cec device node + * @dev: cec device + * @cdev: cec character device + * @parent: parent device + * @minor: device node minor number + * @registered: the device was correctly registered + * @unregistered: the device was unregistered + * @fhs_lock: lock to control access to the filehandle list + * @fhs: the list of open filehandles (cec_fh) + * + * This structure represents a cec-related device node. + * + * The @parent is a physical device. It must be set by core or device drivers + * before registering the node. + */ +struct cec_devnode { + /* sysfs */ + struct device dev; + struct cdev cdev; + struct device *parent; + + /* device info */ + int minor; + bool registered; + bool unregistered; + struct mutex fhs_lock; + struct list_head fhs; +}; + +struct cec_adapter; +struct cec_data; + +struct cec_data { + struct list_head list; + struct list_head xfer_list; + struct cec_adapter *adap; + struct cec_msg msg; + struct cec_fh *fh; + struct delayed_work work; + struct completion c; + u8 attempts; + bool new_initiator; + bool blocking; + bool completed; +}; + +struct cec_msg_entry { + struct list_head list; + struct cec_msg msg; +}; + +#define CEC_NUM_EVENTS CEC_EVENT_LOST_MSGS + +struct cec_fh { + struct list_head list; + struct list_head xfer_list; + struct cec_adapter *adap; + u8 mode_initiator; + u8 mode_follower; + + /* Events */ + wait_queue_head_t wait; + unsigned int pending_events; + struct cec_event events[CEC_NUM_EVENTS]; + struct mutex lock; + struct list_head msgs; /* queued messages */ + unsigned int queued_msgs; +}; + +#define CEC_SIGNAL_FREE_TIME_RETRY 3 +#define CEC_SIGNAL_FREE_TIME_NEW_INITIATOR 5 +#define CEC_SIGNAL_FREE_TIME_NEXT_XFER 7 + +/* The nominal data bit period is 2.4 ms */ +#define CEC_FREE_TIME_TO_USEC(ft) ((ft) * 2400) + +struct cec_adap_ops { + /* Low-level callbacks */ + int (*adap_enable)(struct cec_adapter *adap, bool enable); + int (*adap_monitor_all_enable)(struct cec_adapter *adap, bool enable); + int (*adap_log_addr)(struct cec_adapter *adap, u8 logical_addr); + int (*adap_transmit)(struct cec_adapter *adap, u8 attempts, + u32 signal_free_time, struct cec_msg *msg); + void (*adap_status)(struct cec_adapter *adap, struct seq_file *file); + + /* High-level CEC message callback */ + int (*received)(struct cec_adapter *adap, struct cec_msg *msg); +}; + +/* + * The minimum message length you can receive (excepting poll messages) is 2. + * With a transfer rate of at most 36 bytes per second this makes 18 messages + * per second worst case. + * + * We queue at most 3 seconds worth of messages. The CEC specification requires + * that messages are replied to within a second, so 3 seconds should give more + * than enough margin. Since most messages are actually more than 2 bytes, this + * is in practice a lot more than 3 seconds. + */ +#define CEC_MAX_MSG_QUEUE_SZ (18 * 3) + +struct cec_adapter { + struct module *owner; + char name[32]; + struct cec_devnode devnode; + struct mutex lock; + struct rc_dev *rc; + + struct list_head transmit_queue; + struct list_head wait_queue; + struct cec_data *transmitting; + + struct task_struct *kthread_config; + struct completion config_completion; + + struct task_struct *kthread; + wait_queue_head_t kthread_waitq; + wait_queue_head_t waitq; + + const struct cec_adap_ops *ops; + void *priv; + u32 capabilities; + u8 available_log_addrs; + + u16 phys_addr; + bool is_configuring; + bool is_configured; + u32 monitor_all_cnt; + u32 follower_cnt; + struct cec_fh *cec_follower; + struct cec_fh *cec_initiator; + bool passthrough; + struct cec_log_addrs log_addrs; + + struct dentry *cec_dir; + struct dentry *status_file; + + u16 phys_addrs[15]; + u32 sequence; + + char input_name[32]; + char input_phys[32]; + char input_drv[32]; +}; + +static inline bool cec_has_log_addr(const struct cec_adapter *adap, u8 log_addr) +{ + return adap->log_addrs.log_addr_mask & (1 << log_addr); +} + +static inline bool cec_is_sink(const struct cec_adapter *adap) +{ + return adap->phys_addr == 0; +} + +#if IS_ENABLED(CONFIG_MEDIA_CEC) +struct cec_adapter *cec_allocate_adapter(const struct cec_adap_ops *ops, + void *priv, const char *name, u32 caps, u8 available_las, + struct device *parent); +int cec_register_adapter(struct cec_adapter *adap); +void cec_unregister_adapter(struct cec_adapter *adap); +void cec_delete_adapter(struct cec_adapter *adap); + +int cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, + bool block); +void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, + bool block); +int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg, + bool block); + +/* Called by the adapter */ +void cec_transmit_done(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt, + u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt); +void cec_received_msg(struct cec_adapter *adap, struct cec_msg *msg); + +#else + +static inline int cec_register_adapter(struct cec_adapter *adap) +{ + return 0; +} + +static inline void cec_unregister_adapter(struct cec_adapter *adap) +{ +} + +static inline void cec_delete_adapter(struct cec_adapter *adap) +{ +} + +static inline void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, + bool block) +{ +} + +#endif + +#endif /* _MEDIA_CEC_H */ -- cgit v1.2.3 From 257d4eaed38c736da1654048e14ecd2b76bebf03 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 29 Jun 2015 04:55:35 -0300 Subject: [media] cec: adv7511: add cec support Add CEC support to the adv7511 driver. Signed-off-by: Hans Verkuil [k.debski@samsung.com: Merged changes from CEC Updates commit by Hans Verkuil] Signed-off-by: Kamil Debski Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/i2c/adv7511.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/i2c/adv7511.h b/include/media/i2c/adv7511.h index d83b91d80764..61c3d711cc69 100644 --- a/include/media/i2c/adv7511.h +++ b/include/media/i2c/adv7511.h @@ -32,11 +32,7 @@ struct adv7511_monitor_detect { struct adv7511_edid_detect { int present; int segment; -}; - -struct adv7511_cec_arg { - void *arg; - u32 f_flags; + uint16_t phys_addr; }; struct adv7511_platform_data { -- cgit v1.2.3 From 9828c2c6c1048c61034a8b94e6376aeff6d2284f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 28 Jun 2016 09:03:59 +0200 Subject: block: Convert fifo_time from ulong to u64 Currently rq->fifo_time is unsigned long but CFQ stores nanosecond timestamp in it which would overflow on 32-bit archs. Convert it to u64 to avoid the overflow. Since the rq->fifo_time is unioned with struct call_single_data(), this does not change the size of struct request in any way. We have to slightly fixup block/deadline-iosched.c so that comparison happens in the right types. Fixes: 9a7f38c42c2b92391d9dabaf9f51df7cfe5608e4 Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9746d223494c..d116d3b52c73 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -90,7 +90,7 @@ struct request { struct list_head queuelist; union { struct call_single_data csd; - unsigned long fifo_time; + u64 fifo_time; }; struct request_queue *q; -- cgit v1.2.3 From 79c8d083e226fbfc20d9e801352fccfa7b08a8b3 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 15 Jun 2016 20:27:58 -0300 Subject: [media] videodev2.h: Group YUV 3 planes formats together The formats are interleaved with the YUV packed and miscellaneous formats, making the result confusing especially with the YUV444 format being packed and not planar like YUV410 or YUV420. Move them to their own group as the 2 planes or 3 non-contiguous planes formats to clarify the header. Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 8f951917be74..50ff346c4118 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -504,22 +504,16 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_UV8 v4l2_fourcc('U', 'V', '8', ' ') /* 8 UV 4:4 */ /* Luminance+Chrominance formats */ -#define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y', 'V', 'U', '9') /* 9 YVU 4:1:0 */ -#define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y', 'V', '1', '2') /* 12 YVU 4:2:0 */ #define V4L2_PIX_FMT_YUYV v4l2_fourcc('Y', 'U', 'Y', 'V') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_YYUV v4l2_fourcc('Y', 'Y', 'U', 'V') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_YVYU v4l2_fourcc('Y', 'V', 'Y', 'U') /* 16 YVU 4:2:2 */ #define V4L2_PIX_FMT_UYVY v4l2_fourcc('U', 'Y', 'V', 'Y') /* 16 YUV 4:2:2 */ #define V4L2_PIX_FMT_VYUY v4l2_fourcc('V', 'Y', 'U', 'Y') /* 16 YUV 4:2:2 */ -#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16 YVU422 planar */ -#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 16 YVU411 planar */ #define V4L2_PIX_FMT_Y41P v4l2_fourcc('Y', '4', '1', 'P') /* 12 YUV 4:1:1 */ #define V4L2_PIX_FMT_YUV444 v4l2_fourcc('Y', '4', '4', '4') /* 16 xxxxyyyy uuuuvvvv */ #define V4L2_PIX_FMT_YUV555 v4l2_fourcc('Y', 'U', 'V', 'O') /* 16 YUV-5-5-5 */ #define V4L2_PIX_FMT_YUV565 v4l2_fourcc('Y', 'U', 'V', 'P') /* 16 YUV-5-6-5 */ #define V4L2_PIX_FMT_YUV32 v4l2_fourcc('Y', 'U', 'V', '4') /* 32 YUV-8-8-8-8 */ -#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ -#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* 8 8-bit color */ #define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ #define V4L2_PIX_FMT_M420 v4l2_fourcc('M', '4', '2', '0') /* 12 YUV 4:2:0 2 lines y, 1 line uv interleaved */ @@ -540,6 +534,14 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 macroblocks */ #define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 macroblocks */ +/* three planes - Y Cb, Cr */ +#define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ +#define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y', 'V', 'U', '9') /* 9 YVU 4:1:0 */ +#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 16 YVU411 planar */ +#define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ +#define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y', 'V', '1', '2') /* 12 YVU 4:2:0 */ +#define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16 YVU422 planar */ + /* three non contiguous planes - Y, Cb, Cr */ #define V4L2_PIX_FMT_YUV420M v4l2_fourcc('Y', 'M', '1', '2') /* 12 YUV420 planar */ #define V4L2_PIX_FMT_YVU420M v4l2_fourcc('Y', 'M', '2', '1') /* 12 YVU420 planar */ -- cgit v1.2.3 From ab46f6d24bf57ddac0f5abe2f546a78af57b476c Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 15 Jun 2016 20:35:36 -0300 Subject: [media] videodev2.h: Fix V4L2_PIX_FMT_YUV411P description YUV 4:1:1 uses 12 bits per pixel on average, not 16. Signed-off-by: Laurent Pinchart Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 50ff346c4118..724f43e69d03 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -537,7 +537,7 @@ struct v4l2_pix_format { /* three planes - Y Cb, Cr */ #define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ #define V4L2_PIX_FMT_YVU410 v4l2_fourcc('Y', 'V', 'U', '9') /* 9 YVU 4:1:0 */ -#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 16 YVU411 planar */ +#define V4L2_PIX_FMT_YUV411P v4l2_fourcc('4', '1', '1', 'P') /* 12 YVU411 planar */ #define V4L2_PIX_FMT_YUV420 v4l2_fourcc('Y', 'U', '1', '2') /* 12 YUV 4:2:0 */ #define V4L2_PIX_FMT_YVU420 v4l2_fourcc('Y', 'V', '1', '2') /* 12 YVU 4:2:0 */ #define V4L2_PIX_FMT_YUV422P v4l2_fourcc('4', '2', '2', 'P') /* 16 YVU422 planar */ -- cgit v1.2.3 From 1179aab13db3c6251484afe492c8dbd869ca8b05 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Mon, 15 Feb 2016 22:00:30 -0200 Subject: [media] media: Add video processing entity functions Add composer, pixel formatter, pixel encoding converter and scaler functions. Signed-off-by: Laurent Pinchart Acked-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index df59edee25d1..3136686c4bd0 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -94,6 +94,15 @@ struct media_device_info { #define MEDIA_ENT_F_AUDIO_PLAYBACK (MEDIA_ENT_F_BASE + 0x03002) #define MEDIA_ENT_F_AUDIO_MIXER (MEDIA_ENT_F_BASE + 0x03003) +/* + * Processing entities + */ +#define MEDIA_ENT_F_PROC_VIDEO_COMPOSER (MEDIA_ENT_F_BASE + 0x4001) +#define MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER (MEDIA_ENT_F_BASE + 0x4002) +#define MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV (MEDIA_ENT_F_BASE + 0x4003) +#define MEDIA_ENT_F_PROC_VIDEO_LUT (MEDIA_ENT_F_BASE + 0x4004) +#define MEDIA_ENT_F_PROC_VIDEO_SCALER (MEDIA_ENT_F_BASE + 0x4005) + /* * Connectors */ -- cgit v1.2.3 From eaa0b96bbb6586a95e66d3dedd974313d7b0d94f Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Tue, 1 Mar 2016 21:12:27 -0300 Subject: [media] media: Add video statistics computation functions The video statistics function describes entities such as video histogram engines or 3A statistics engines. Signed-off-by: Laurent Pinchart Acked-by: Hans Verkuil Acked-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/media.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h index 3136686c4bd0..7acf0f634f70 100644 --- a/include/uapi/linux/media.h +++ b/include/uapi/linux/media.h @@ -102,6 +102,7 @@ struct media_device_info { #define MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV (MEDIA_ENT_F_BASE + 0x4003) #define MEDIA_ENT_F_PROC_VIDEO_LUT (MEDIA_ENT_F_BASE + 0x4004) #define MEDIA_ENT_F_PROC_VIDEO_SCALER (MEDIA_ENT_F_BASE + 0x4005) +#define MEDIA_ENT_F_PROC_VIDEO_STATISTICS (MEDIA_ENT_F_BASE + 0x4006) /* * Connectors -- cgit v1.2.3 From 42e89bed23000c0bf985a741422ef943df0ee1e9 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Fri, 13 May 2016 13:52:11 -0300 Subject: [media] v4l: vsp1: lut: Expose configuration through a control Replace the custom ioctl with a V4L2 control in order to standardize the API. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/vsp1.h | 34 ---------------------------------- 1 file changed, 34 deletions(-) delete mode 100644 include/uapi/linux/vsp1.h (limited to 'include') diff --git a/include/uapi/linux/vsp1.h b/include/uapi/linux/vsp1.h deleted file mode 100644 index 9a823696d816..000000000000 --- a/include/uapi/linux/vsp1.h +++ /dev/null @@ -1,34 +0,0 @@ -/* - * vsp1.h - * - * Renesas R-Car VSP1 - User-space API - * - * Copyright (C) 2013 Renesas Corporation - * - * Contacts: Laurent Pinchart - * - * 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 __VSP1_USER_H__ -#define __VSP1_USER_H__ - -#include -#include - -/* - * Private IOCTLs - * - * VIDIOC_VSP1_LUT_CONFIG - Configure the lookup table - */ - -#define VIDIOC_VSP1_LUT_CONFIG \ - _IOWR('V', BASE_VIDIOC_PRIVATE + 1, struct vsp1_lut_config) - -struct vsp1_lut_config { - __u32 lut[256]; -}; - -#endif /* __VSP1_USER_H__ */ -- cgit v1.2.3 From cbf9077e586b9c0db1a1ce5690552ae268c15848 Mon Sep 17 00:00:00 2001 From: Chris Lapa Date: Fri, 24 Jun 2016 12:26:08 +1000 Subject: max8903: cleans up confusing relationship between dc_valid, dok and dcm. The max8903_charger.h file indicated that dcm and dok were not optional when dc_valid is set. It makes sense to have dok as a compulsory pin when dc_valid is given. However dcm can be optionally wired to a fixed level especially when the circuit is configured for dc power exclusively. The previous implementation already allowed for this somewhat, however no error was given if dok wasn't given whilst dc_valid was. The new implementation enforces dok presence when dc_valid is given. Whilst allowing dcm to be optional. Signed-off-by: Chris Lapa Reviewed-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- include/linux/power/max8903_charger.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/power/max8903_charger.h b/include/linux/power/max8903_charger.h index 24f51db8a83f..89d3f1cb3433 100644 --- a/include/linux/power/max8903_charger.h +++ b/include/linux/power/max8903_charger.h @@ -26,8 +26,8 @@ struct max8903_pdata { /* * GPIOs - * cen, chg, flt, and usus are optional. - * dok, dcm, and uok are not optional depending on the status of + * cen, chg, flt, dcm and usus are optional. + * dok and uok are not optional depending on the status of * dc_valid and usb_valid. */ int cen; /* Charger Enable input */ @@ -41,7 +41,7 @@ struct max8903_pdata { /* * DC(Adapter/TA) is wired * When dc_valid is true, - * dok and dcm should be valid. + * dok should be valid. * * At least one of dc_valid or usb_valid should be true. */ -- cgit v1.2.3 From e81b87d22a8fed6bac24197972c9c394a2b92b5d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 28 Jun 2016 13:25:04 +0200 Subject: clk: Provide notifier stubs when !COMMON_CLK The clk notifier symbols are hidden by COMMON_CLK. However on some platforms HAVE_CLK might be set while COMMON_CLK not which leads to compile test build errors like: $ make.cross ARCH=sh drivers/devfreq/tegra-devfreq.c: In function 'tegra_actmon_rate_notify_cb': >> drivers/devfreq/tegra-devfreq.c:391:16: error: 'POST_RATE_CHANGE' undeclared (first use in this function) if (action != POST_RATE_CHANGE) ^ drivers/devfreq/tegra-devfreq.c: In function 'tegra_devfreq_probe': >> drivers/devfreq/tegra-devfreq.c:654:8: error: implicit declaration of function 'clk_notifier_register' [-Werror=implicit-function-declaration] err = clk_notifier_register(tegra->emc_clock, &tegra->rate_change_nb); ^ Export the macros and data type declarations outside of COMMON_CLK ifdef and provide stubs to fix the compile testing. Reported-by: kbuild test robot Signed-off-by: Krzysztof Kozlowski Tested-by: Bartlomiej Zolnierkiewicz Signed-off-by: Stephen Boyd --- include/linux/clk.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/clk.h b/include/linux/clk.h index 0df4a51e1a78..a89ba4e7af7a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -20,8 +20,6 @@ struct device; struct clk; -#ifdef CONFIG_COMMON_CLK - /** * DOC: clk notifier callback types * @@ -78,6 +76,8 @@ struct clk_notifier_data { unsigned long new_rate; }; +#ifdef CONFIG_COMMON_CLK + /** * clk_notifier_register: register a clock rate-change notifier callback * @clk: clock whose rate we are interested in @@ -140,6 +140,18 @@ bool clk_is_match(const struct clk *p, const struct clk *q); #else +static inline int clk_notifier_register(struct clk *clk, + struct notifier_block *nb) +{ + return -ENOTSUPP; +} + +static inline int clk_notifier_unregister(struct clk *clk, + struct notifier_block *nb) +{ + return -ENOTSUPP; +} + static inline long clk_get_accuracy(struct clk *clk) { return -ENOTSUPP; -- cgit v1.2.3 From 7eb231c337e00735d4b553ed4ae7f9441598f028 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Fri, 17 Jun 2016 12:27:52 +0200 Subject: PM / Domains: Convert pm_genpd_init() to return an error code The are already cases when pm_genpd_init() can fail. Currently we hide the failures instead of propagating an error code, which is a better method. Moreover, to prepare for future changes like moving away from using a fixed array-size of the struct genpd_power_state, to instead dynamically allocate data for it, the pm_genpd_init() API needs to be able to return an error code, as allocation can fail. Current users of the pm_genpd_init() is thus requested to start dealing with error codes. In the transition phase, users will have to live with only error messages being printed to log. Signed-off-by: Ulf Hansson Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index dd5b0447d572..31fec858088c 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -127,8 +127,8 @@ extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *new_subdomain); extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, struct generic_pm_domain *target); -extern void pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off); +extern int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -163,9 +163,10 @@ static inline int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, { return -ENOSYS; } -static inline void pm_genpd_init(struct generic_pm_domain *genpd, - struct dev_power_governor *gov, bool is_off) +static inline int pm_genpd_init(struct generic_pm_domain *genpd, + struct dev_power_governor *gov, bool is_off) { + return -ENOSYS; } #endif -- cgit v1.2.3 From a99ab50dbbb1f982d076d19e0a9959fe2efa3126 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Tue, 28 Jun 2016 22:53:19 -0700 Subject: mfd: rn5t618: Add Ricoh RN5T567 PMIC support The Ricoh RN5T567 is from the same family as the Ricoh RN5T618 is, the differences are: + DCDC4 + Slightly different output voltage/currents + 32kHz Output - ADC/Charger capabilities Signed-off-by: Stefan Agner Reviewed-by: Marcel Ziswiler Acked-by: Rob Herring Signed-off-by: Lee Jones --- include/linux/mfd/rn5t618.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h index c72d5344f3b3..54179c2577ae 100644 --- a/include/linux/mfd/rn5t618.h +++ b/include/linux/mfd/rn5t618.h @@ -20,6 +20,7 @@ #define RN5T618_OTPVER 0x01 #define RN5T618_IODAC 0x02 #define RN5T618_VINDAC 0x03 +#define RN5T618_OUT32KEN 0x05 #define RN5T618_CPUCNT 0x06 #define RN5T618_PSWR 0x07 #define RN5T618_PONHIS 0x09 @@ -38,6 +39,7 @@ #define RN5T618_DC1_SLOT 0x16 #define RN5T618_DC2_SLOT 0x17 #define RN5T618_DC3_SLOT 0x18 +#define RN5T618_DC4_SLOT 0x19 #define RN5T618_LDO1_SLOT 0x1b #define RN5T618_LDO2_SLOT 0x1c #define RN5T618_LDO3_SLOT 0x1d @@ -54,12 +56,16 @@ #define RN5T618_DC2CTL2 0x2f #define RN5T618_DC3CTL 0x30 #define RN5T618_DC3CTL2 0x31 +#define RN5T618_DC4CTL 0x32 +#define RN5T618_DC4CTL2 0x33 #define RN5T618_DC1DAC 0x36 #define RN5T618_DC2DAC 0x37 #define RN5T618_DC3DAC 0x38 +#define RN5T618_DC4DAC 0x39 #define RN5T618_DC1DAC_SLP 0x3b #define RN5T618_DC2DAC_SLP 0x3c #define RN5T618_DC3DAC_SLP 0x3d +#define RN5T618_DC4DAC_SLP 0x3e #define RN5T618_DCIREN 0x40 #define RN5T618_DCIRQ 0x41 #define RN5T618_DCIRMON 0x42 @@ -221,8 +227,14 @@ enum { RN5T618_REG_NUM, }; +enum { + RN5T567 = 0, + RN5T618, +}; + struct rn5t618 { struct regmap *regmap; + long variant; }; #endif /* __LINUX_MFD_RN5T618_H */ -- cgit v1.2.3 From ed6d362d8dbc3494cd98cd771737ea8b1407ed61 Mon Sep 17 00:00:00 2001 From: Stefan Agner Date: Tue, 28 Jun 2016 22:53:20 -0700 Subject: regulator: rn5t618: Add RN5T567 PMIC support Extend the driver to support Ricoh RN5T567. Support the additional DCDC and slightly different voltage range of LDORTC1. Signed-off-by: Stefan Agner Reviewed-by: Marcel Ziswiler Acked-by: Mark Brown Signed-off-by: Lee Jones --- include/linux/mfd/rn5t618.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h index 54179c2577ae..cadc6543909d 100644 --- a/include/linux/mfd/rn5t618.h +++ b/include/linux/mfd/rn5t618.h @@ -217,6 +217,7 @@ enum { RN5T618_DCDC1, RN5T618_DCDC2, RN5T618_DCDC3, + RN5T618_DCDC4, RN5T618_LDO1, RN5T618_LDO2, RN5T618_LDO3, -- cgit v1.2.3 From 9787f5e28b50774f1d5672e33b277ba1e9aa0753 Mon Sep 17 00:00:00 2001 From: Thor Thayer Date: Thu, 2 Jun 2016 12:52:23 -0500 Subject: mfd: altr_a10sr: Add Altera Arria10 DevKit System Resource Chip Add support for the Altera Arria10 Development Kit System Resource chip which is implemented using a MAX5 as a external gpio extender with the regmap framework over a SPI bus. Signed-off-by: Thor Thayer Signed-off-by: Lee Jones --- include/linux/mfd/altera-a10sr.h | 85 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 85 insertions(+) create mode 100644 include/linux/mfd/altera-a10sr.h (limited to 'include') diff --git a/include/linux/mfd/altera-a10sr.h b/include/linux/mfd/altera-a10sr.h new file mode 100644 index 000000000000..45a5e6e7db54 --- /dev/null +++ b/include/linux/mfd/altera-a10sr.h @@ -0,0 +1,85 @@ +/* + * Copyright Intel Corporation (C) 2014-2016. All Rights Reserved + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + * + * Declarations for Altera Arria10 MAX5 System Resource Chip + * + * Adapted from DA9052 + */ + +#ifndef __MFD_ALTERA_A10SR_H +#define __MFD_ALTERA_A10SR_H + +#include +#include +#include +#include +#include + +/* Write registers are always on even addresses */ +#define WRITE_REG_MASK 0xFE +/* Odd registers are always on odd addresses */ +#define READ_REG_MASK 0x01 + +#define ALTR_A10SR_BITS_PER_REGISTER 8 +/* + * To find the correct register, we divide the input GPIO by + * the number of GPIO in each register. We then need to multiply + * by 2 because the reads are at odd addresses. + */ +#define ALTR_A10SR_REG_OFFSET(X) (((X) / ALTR_A10SR_BITS_PER_REGISTER) << 1) +#define ALTR_A10SR_REG_BIT(X) ((X) % ALTR_A10SR_BITS_PER_REGISTER) +#define ALTR_A10SR_REG_BIT_CHG(X, Y) ((X) << ALTR_A10SR_REG_BIT(Y)) +#define ALTR_A10SR_REG_BIT_MASK(X) (1 << ALTR_A10SR_REG_BIT(X)) + +/* Arria10 System Controller Register Defines */ +#define ALTR_A10SR_NOP 0x00 /* No Change */ +#define ALTR_A10SR_VERSION_READ 0x00 /* MAX5 Version Read */ + +#define ALTR_A10SR_LED_REG 0x02 /* LED - Upper 4 bits */ +/* LED register Bit Definitions */ +#define ALTR_A10SR_LED_VALID_SHIFT 4 /* LED - Upper 4 bits valid */ +#define ALTR_A10SR_OUT_VALID_RANGE_LO ALTR_A10SR_LED_VALID_SHIFT +#define ALTR_A10SR_OUT_VALID_RANGE_HI 7 + +#define ALTR_A10SR_PBDSW_REG 0x04 /* PB & DIP SW - Input only */ +#define ALTR_A10SR_PBDSW_IRQ_REG 0x06 /* PB & DIP SW Flag Clear */ +/* Pushbutton & DIP Switch Bit Definitions */ +#define ALTR_A10SR_IN_VALID_RANGE_LO 8 +#define ALTR_A10SR_IN_VALID_RANGE_HI 15 + +#define ALTR_A10SR_PWR_GOOD1_REG 0x08 /* Power Good1 Read */ +#define ALTR_A10SR_PWR_GOOD2_REG 0x0A /* Power Good2 Read */ +#define ALTR_A10SR_PWR_GOOD3_REG 0x0C /* Power Good3 Read */ +#define ALTR_A10SR_FMCAB_REG 0x0E /* FMCA/B & PCIe Pwr Enable */ +#define ALTR_A10SR_HPS_RST_REG 0x10 /* HPS Reset */ +#define ALTR_A10SR_USB_QSPI_REG 0x12 /* USB, BQSPI, FILE Reset */ +#define ALTR_A10SR_SFPA_REG 0x14 /* SFPA Control Reg */ +#define ALTR_A10SR_SFPB_REG 0x16 /* SFPB Control Reg */ +#define ALTR_A10SR_I2C_M_REG 0x18 /* I2C Master Select */ +#define ALTR_A10SR_WARM_RST_REG 0x1A /* HPS Warm Reset */ +#define ALTR_A10SR_WR_KEY_REG 0x1C /* HPS Warm Reset Key */ +#define ALTR_A10SR_PMBUS_REG 0x1E /* HPS PM Bus */ + +/** + * struct altr_a10sr - Altera Max5 MFD device private data structure + * @dev: : this device + * @regmap: the regmap assigned to the parent device. + */ +struct altr_a10sr { + struct device *dev; + struct regmap *regmap; +}; + +#endif /* __MFD_ALTERA_A10SR_H */ -- cgit v1.2.3 From 0d3a7cce3e8bc5c060b1f038984c10cb70289e1d Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Wed, 8 Jun 2016 10:54:35 -0500 Subject: mfd: ti_am335x_tscadc: Rename regmap_tscadc to regmap The regmap structure pointer is named regmap_tscadc, this is not consistent with other drivers and is redundant, it also contributes to several checkpatch warnings involving long lines. Rename this. Signed-off-by: Andrew F. Davis Signed-off-by: Lee Jones --- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 1fd50dcfe47c..2567a87872b0 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -153,7 +153,7 @@ struct ti_tscadc_dev { struct device *dev; - struct regmap *regmap_tscadc; + struct regmap *regmap; void __iomem *tscadc_base; int irq; int used_cells; /* 1-2 */ -- cgit v1.2.3 From 9e3d5c996b340c1572afabe5ff2f0dd8ced1583a Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 14 Jun 2016 15:43:31 -0700 Subject: mfd: hi655x-pmic: Rename some interrupt macro names Currently the hi655x-pmic driver has names for interrupt mask values, but not for the interrupt numbers themselves. So to allow for interrupt numbers to have sane names, rename the mask values with the _MASK postfix and use the existing names as the interrupt name Signed-off-by: John Stultz Signed-off-by: Lee Jones --- include/linux/mfd/hi655x-pmic.h | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h index dbbe9a644622..62f03c2b1bb0 100644 --- a/include/linux/mfd/hi655x-pmic.h +++ b/include/linux/mfd/hi655x-pmic.h @@ -34,14 +34,23 @@ #define PMU_VER_START 0x10 #define PMU_VER_END 0x38 -#define RESERVE_INT BIT(7) -#define PWRON_D20R_INT BIT(6) -#define PWRON_D20F_INT BIT(5) -#define PWRON_D4SR_INT BIT(4) -#define VSYS_6P0_D200UR_INT BIT(3) -#define VSYS_UV_D3R_INT BIT(2) -#define VSYS_2P5_R_INT BIT(1) -#define OTMP_D1R_INT BIT(0) +#define RESERVE_INT 7 +#define PWRON_D20R_INT 6 +#define PWRON_D20F_INT 5 +#define PWRON_D4SR_INT 4 +#define VSYS_6P0_D200UR_INT 3 +#define VSYS_UV_D3R_INT 2 +#define VSYS_2P5_R_INT 1 +#define OTMP_D1R_INT 0 + +#define RESERVE_INT_MASK BIT(RESERVE_INT) +#define PWRON_D20R_INT_MASK BIT(PWRON_D20R_INT) +#define PWRON_D20F_INT_MASK BIT(PWRON_D20F_INT) +#define PWRON_D4SR_INT_MASK BIT(PWRON_D4SR_INT) +#define VSYS_6P0_D200UR_INT_MASK BIT(VSYS_6P0_D200UR_INT) +#define VSYS_UV_D3R_INT_MASK BIT(VSYS_UV_D3R_INT) +#define VSYS_2P5_R_INT_MASK BIT(VSYS_2P5_R_INT) +#define OTMP_D1R_INT_MASK BIT(OTMP_D1R_INT) struct hi655x_pmic { struct resource *res; -- cgit v1.2.3 From 698adfc968f3625a50853157ee5dbd208b6408a8 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 13 Jun 2016 13:37:51 +0100 Subject: mfd: arizona: Remove some duplicate defines Some duplicate defines seem to have snuck into the registers file, this patch simply removes them. Signed-off-by: Charles Keepax Signed-off-by: Lee Jones --- include/linux/mfd/arizona/registers.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h index cd7e78eae006..0d06c5d0af93 100644 --- a/include/linux/mfd/arizona/registers.h +++ b/include/linux/mfd/arizona/registers.h @@ -856,12 +856,6 @@ #define ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE 0xB38 #define ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE 0xB40 #define ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE 0xB48 -#define ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE 0xB60 -#define ARIZONA_ISRC2INT2MIX_INPUT_1_SOURCE 0xB68 -#define ARIZONA_ISRC1INT3MIX_INPUT_1_SOURCE 0xB30 -#define ARIZONA_ISRC1INT4MIX_INPUT_1_SOURCE 0xB38 -#define ARIZONA_ISRC2DEC1MIX_INPUT_1_SOURCE 0xB40 -#define ARIZONA_ISRC2DEC2MIX_INPUT_1_SOURCE 0xB48 #define ARIZONA_ISRC2DEC3MIX_INPUT_1_SOURCE 0xB50 #define ARIZONA_ISRC2DEC4MIX_INPUT_1_SOURCE 0xB58 #define ARIZONA_ISRC2INT1MIX_INPUT_1_SOURCE 0xB60 -- cgit v1.2.3 From fc1882dcb5031953169a38260a0e653910825e46 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 25 May 2016 14:22:02 +0200 Subject: mfd: stmpe: Move platform data into MFD driver The STMPE platform data is only populated from the device tree in all existing users, so push the struct and make the OF case the norm. Signed-off-by: Linus Walleij Signed-off-by: Lee Jones --- include/linux/mfd/stmpe.h | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h index cb83883918a7..de748bc7525e 100644 --- a/include/linux/mfd/stmpe.h +++ b/include/linux/mfd/stmpe.h @@ -62,6 +62,7 @@ enum { struct stmpe_variant_info; struct stmpe_client_info; +struct stmpe_platform_data; /** * struct stmpe - STMPE MFD structure @@ -117,25 +118,4 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks); #define STMPE_GPIO_NOREQ_811_TOUCH (0xf0) -/** - * struct stmpe_platform_data - STMPE platform data - * @id: device id to distinguish between multiple STMPEs on the same board - * @blocks: bitmask of blocks to enable (use STMPE_BLOCK_*) - * @irq_trigger: IRQ trigger to use for the interrupt to the host - * @autosleep: bool to enable/disable stmpe autosleep - * @autosleep_timeout: inactivity timeout in milliseconds for autosleep - * @irq_over_gpio: true if gpio is used to get irq - * @irq_gpio: gpio number over which irq will be requested (significant only if - * irq_over_gpio is true) - */ -struct stmpe_platform_data { - int id; - unsigned int blocks; - unsigned int irq_trigger; - bool autosleep; - bool irq_over_gpio; - int irq_gpio; - int autosleep_timeout; -}; - #endif -- cgit v1.2.3 From 0a58da1e2f25f213fb72d7d6a18dff9562621215 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Mon, 20 Jun 2016 17:07:18 +0300 Subject: mfd: twl6040: Handle mclk used for HPPLL and optional internal clock source On some boards, like omap5-uevm the MCLK is gated by default and in order to be able to use the High performance modes of twl6040 it need to be enabled by SW. Add support for handling the MCLK source clock via CCF. At the same time lower the print priority of the notification that the 32K clock is not provided and it is not going to be handled by the driver. Signed-off-by: Peter Ujfalusi Acked-by: Rob Herring Signed-off-by: Lee Jones --- include/linux/mfd/twl6040.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h index 8e95cd87cd74..36795a1be479 100644 --- a/include/linux/mfd/twl6040.h +++ b/include/linux/mfd/twl6040.h @@ -226,6 +226,7 @@ struct twl6040 { struct regmap_irq_chip_data *irq_data; struct regulator_bulk_data supplies[2]; /* supplies for vio, v2v1 */ struct clk *clk32k; + struct clk *mclk; struct mutex mutex; struct mutex irq_mutex; struct mfd_cell cells[TWL6040_CELLS]; @@ -237,8 +238,8 @@ struct twl6040 { /* PLL configuration */ int pll; - unsigned int sysclk; - unsigned int mclk; + unsigned int sysclk_rate; + unsigned int mclk_rate; unsigned int irq; unsigned int irq_ready; -- 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 053239987f89f9a6299e78610bad010764bccd71 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 28 Jun 2016 16:10:33 +0200 Subject: soc: renesas: rcar-sysc: Move SYSC interrupt config to rcar-sysc driver On R-Car H1 and Gen2, the SYSC interrupt registers are always configured using hardcoded values in platform code. For R-Car Gen2, values are provided for H2 and M2-W only, other SoCs are not yet supported, and never will be. Move this configuration from SoC-specific platform code to the rcar_sysc_init() wrapper, so it can be skipped if the SYSC is configured from DT. This would be the case not only for H1, H2, and M2-W using a modern DTS, but also for other R-Car Gen2 SoCs not supported by the platform code, relying purely on DT. There is no longer a need to return the mapped register block, hence make the function return void. Signed-off-by: Geert Uytterhoeven Reviewed-by: Ulrich Hecht Signed-off-by: Simon Horman --- include/linux/soc/renesas/rcar-sysc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/soc/renesas/rcar-sysc.h b/include/linux/soc/renesas/rcar-sysc.h index 92fc613ab23d..7b8b280c181b 100644 --- a/include/linux/soc/renesas/rcar-sysc.h +++ b/include/linux/soc/renesas/rcar-sysc.h @@ -11,6 +11,6 @@ struct rcar_sysc_ch { int rcar_sysc_power_down(const struct rcar_sysc_ch *sysc_ch); int rcar_sysc_power_up(const struct rcar_sysc_ch *sysc_ch); -void __iomem *rcar_sysc_init(phys_addr_t base); +void rcar_sysc_init(phys_addr_t base, u32 syscier); #endif /* __LINUX_SOC_RENESAS_RCAR_SYSC_H__ */ -- cgit v1.2.3 From 7524c1cebc0a4e2ab186fcb5f87116f3d9018ee4 Mon Sep 17 00:00:00 2001 From: James Ban Date: Wed, 29 Jun 2016 16:49:32 +0900 Subject: regulator: da9211: add descriptions for da9212/da9214 This is a patch for adding description for da9212/da9214. Signed-off-by: James Ban Signed-off-by: Mark Brown --- include/linux/regulator/da9211.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h index a43a5ca1167b..80cb40b7c88d 100644 --- a/include/linux/regulator/da9211.h +++ b/include/linux/regulator/da9211.h @@ -1,5 +1,6 @@ /* - * da9211.h - Regulator device driver for DA9211/DA9213/DA9215 + * da9211.h - Regulator device driver for DA9211/DA9212 + * /DA9213/DA9214/DA9215 * Copyright (C) 2015 Dialog Semiconductor Ltd. * * This program is free software; you can redistribute it and/or @@ -22,7 +23,9 @@ enum da9211_chip_id { DA9211, + DA9212, DA9213, + DA9214, DA9215, }; -- cgit v1.2.3 From abd3147e69481caade441e8d8296fa3f541aea03 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 31 May 2016 09:00:14 +0000 Subject: ASoC: add new simple-card-utils.c Current ALSA SoC has simple-card driver which is supporting both platform and DT probe. Now, some sound cards driver are created based on simple-card. They have similar feature or function, but implemented separately on each drivers. This is a waste of code. OTOH, merging these driver into same driver is highly risk, because it will be very difficult to keep compatibility. More over, ALSA SoC want to have graph base of DT feature in the future. Maybe it want to use simple-card like feature / function. Because of these background, this patch creates simple-card helper utils, and provides common function to each drivers. 1st is asoc_simple_card_parse_daifmt() Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/sound/simple_card_utils.h (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h new file mode 100644 index 000000000000..7acc798016e0 --- /dev/null +++ b/include/sound/simple_card_utils.h @@ -0,0 +1,21 @@ +/* + * simple_card_core.h + * + * Copyright (c) 2016 Kuninori Morimoto + * + * 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 __SIMPLE_CARD_CORE_H +#define __SIMPLE_CARD_CORE_H + +#include + +int asoc_simple_card_parse_daifmt(struct device *dev, + struct device_node *node, + struct device_node *codec, + char *prefix, + unsigned int *retfmt); + +#endif /* __SIMPLE_CARD_CORE_H */ -- cgit v1.2.3 From 339d00cb173a5eb283d3b8d617fa97a3a46ada2f Mon Sep 17 00:00:00 2001 From: Xinliang Liu Date: Mon, 20 Jun 2016 11:50:05 +0800 Subject: arm64: dts: hi6220: Add media subsystem reset dts Add media subsystem reset dts support. Signed-off-by: Chen Feng Signed-off-by: Xinliang Liu Signed-off-by: Philipp Zabel --- include/dt-bindings/reset/hisi,hi6220-resets.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/reset/hisi,hi6220-resets.h b/include/dt-bindings/reset/hisi,hi6220-resets.h index ca08a7e5248e..322ec5335b65 100644 --- a/include/dt-bindings/reset/hisi,hi6220-resets.h +++ b/include/dt-bindings/reset/hisi,hi6220-resets.h @@ -64,4 +64,12 @@ #define PERIPH_RSDIST9_CARM_SOCDBG 0x507 #define PERIPH_RSDIST9_CARM_ETM 0x508 +#define MEDIA_G3D 0 +#define MEDIA_CODEC_VPU 2 +#define MEDIA_CODEC_JPEG 3 +#define MEDIA_ISP 4 +#define MEDIA_ADE 5 +#define MEDIA_MMU 6 +#define MEDIA_XG2RAM1 7 + #endif /*_DT_BINDINGS_RESET_CONTROLLER_HI6220*/ -- cgit v1.2.3 From a3828519c39aa9c85bae14bad2572d12dc0d1da6 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Mon, 27 Jun 2016 12:12:16 -0500 Subject: Documentation: dt: reset: Add TI syscon reset binding Add TI syscon reset controller binding. This will hook to the reset framework and use syscon/regmap to set reset bits. This allows reset control of individual SoC subsytems and devices with memory-mapped reset registers in a common register memory space. Signed-off-by: Andrew F. Davis Signed-off-by: Suman Anna Acked-by: Rob Herring Signed-off-by: Philipp Zabel --- include/dt-bindings/reset/ti-syscon.h | 38 +++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/dt-bindings/reset/ti-syscon.h (limited to 'include') diff --git a/include/dt-bindings/reset/ti-syscon.h b/include/dt-bindings/reset/ti-syscon.h new file mode 100644 index 000000000000..884fd91df8e9 --- /dev/null +++ b/include/dt-bindings/reset/ti-syscon.h @@ -0,0 +1,38 @@ +/* + * TI Syscon Reset definitions + * + * Copyright (C) 2015-2016 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __DT_BINDINGS_RESET_TI_SYSCON_H__ +#define __DT_BINDINGS_RESET_TI_SYSCON_H__ + +/* + * The reset does not support the feature and corresponding + * values are not valid + */ +#define ASSERT_NONE (1 << 0) +#define DEASSERT_NONE (1 << 1) +#define STATUS_NONE (1 << 2) + +/* When set this function is activated by setting(vs clearing) this bit */ +#define ASSERT_SET (1 << 3) +#define DEASSERT_SET (1 << 4) +#define STATUS_SET (1 << 5) + +/* The following are the inverse of the above and are added for consistency */ +#define ASSERT_CLEAR (0 << 3) +#define DEASSERT_CLEAR (0 << 4) +#define STATUS_CLEAR (0 << 5) + +#endif -- cgit v1.2.3 From a92e7c3d82a1313ab1954e5cdfd8f04efdb4ca78 Mon Sep 17 00:00:00 2001 From: Andi Shyti Date: Tue, 28 Jun 2016 11:41:12 +0900 Subject: spi: s3c64xx: consider the case when the CS line is not connected When the CS line is not connected, it is not needed to enable or disable the chip selection functionality from the s3c64xx devices in order to perform a transfer. Set the CS controller logically always enabled already during initialization (by writing '0' in the S3C64XX_SPI_SLAVE_SEL register) and never disable it. Signed-off-by: Andi Shyti Signed-off-by: Mark Brown --- include/linux/platform_data/spi-s3c64xx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index fb5625bcca9a..5c1e21c87270 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -38,6 +38,7 @@ struct s3c64xx_spi_csinfo { struct s3c64xx_spi_info { int src_clk_nr; int num_cs; + bool no_cs; int (*cfg_gpio)(void); dma_filter_fn filter; void *dma_tx; -- cgit v1.2.3 From 3fdd1526e6c5ceadd4e91906d223e2d382fb72ca Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Wed, 22 Jun 2016 22:22:19 +0300 Subject: ir-rx51: use PWM framework instead of OMAP dmtimer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert driver to use PWM framework instead of calling dmtimer functions directly for PWM timer. Remove paragraph about writing to the Free Software Foundation's mailing address while at it. Signed-off-by: Ivaylo Dimitrov Acked-by: Pali Rohár Signed-off-by: Tony Lindgren --- include/linux/platform_data/media/ir-rx51.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h index 3038120ca46e..6acf22d497f7 100644 --- a/include/linux/platform_data/media/ir-rx51.h +++ b/include/linux/platform_data/media/ir-rx51.h @@ -2,8 +2,6 @@ #define _LIRC_RX51_H struct lirc_rx51_platform_data { - int pwm_timer; - int(*set_max_mpu_wakeup_lat)(struct device *dev, long t); struct pwm_omap_dmtimer_pdata *dmtimer; }; -- cgit v1.2.3 From 79cdad3635b3a253d712aba115fa274ef94a8c6b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Wed, 22 Jun 2016 22:22:21 +0300 Subject: ir-rx51: use hrtimer instead of dmtimer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop dmtimer usage for pulse timer in favor of hrtimer. That allows removing PWM dmitimer platform data usage. Signed-off-by: Ivaylo Dimitrov Acked-by: Pali Rohár Signed-off-by: Tony Lindgren --- include/linux/platform_data/media/ir-rx51.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h index 6acf22d497f7..812d87307877 100644 --- a/include/linux/platform_data/media/ir-rx51.h +++ b/include/linux/platform_data/media/ir-rx51.h @@ -3,7 +3,6 @@ struct lirc_rx51_platform_data { int(*set_max_mpu_wakeup_lat)(struct device *dev, long t); - struct pwm_omap_dmtimer_pdata *dmtimer; }; #endif -- cgit v1.2.3 From 2d902671ce1cd98cdc88d78c481889a1b2996101 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 30 Jun 2016 08:53:27 +0200 Subject: vfs: merge .d_select_inode() into .d_real() The two methods essentially do the same: find the real dentry/inode belonging to an overlay dentry. The difference is in the usage: vfs_open() uses ->d_select_inode() and expects the function to perform copy-up if necessary based on the open flags argument. file_dentry() uses ->d_real() passing in the overlay dentry as well as the underlying inode. vfs_rename() uses ->d_select_inode() but passes zero flags. ->d_real() with a zero inode would have worked just as well here. This patch merges the functionality of ->d_select_inode() into ->d_real() by adding an 'open_flags' argument to the latter. [Al Viro] Make the signature of d_real() match that of ->d_real() again. And constify the inode argument, while we are at it. Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 28 ++++++++-------------------- include/linux/fs.h | 7 +------ 2 files changed, 9 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f53fa055021a..45b22de15ede 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -139,8 +139,7 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); - struct inode *(*d_select_inode)(struct dentry *, unsigned); - struct dentry *(*d_real)(struct dentry *, struct inode *); + struct dentry *(*d_real)(struct dentry *, const struct inode *, unsigned int); } ____cacheline_aligned; /* @@ -206,10 +205,8 @@ struct dentry_operations { #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ -#define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */ - -#define DCACHE_ENCRYPTED_WITH_KEY 0x04000000 /* dir is encrypted with a valid key */ -#define DCACHE_OP_REAL 0x08000000 +#define DCACHE_ENCRYPTED_WITH_KEY 0x02000000 /* dir is encrypted with a valid key */ +#define DCACHE_OP_REAL 0x04000000 #define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ #define DCACHE_DENTRY_CURSOR 0x20000000 @@ -557,25 +554,16 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } -static inline struct dentry *d_real(struct dentry *dentry) +static inline struct dentry *d_real(struct dentry *dentry, + const struct inode *inode, + unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, NULL); + return dentry->d_op->d_real(dentry, inode, flags); else return dentry; } -static inline struct inode *vfs_select_inode(struct dentry *dentry, - unsigned open_flags) -{ - struct inode *inode = d_inode(dentry); - - if (inode && unlikely(dentry->d_flags & DCACHE_OP_SELECT_INODE)) - inode = dentry->d_op->d_select_inode(dentry, open_flags); - - return inode; -} - /** * d_real_inode - Return the real inode * @dentry: The dentry to query @@ -585,7 +573,7 @@ static inline struct inode *vfs_select_inode(struct dentry *dentry, */ static inline struct inode *d_real_inode(struct dentry *dentry) { - return d_backing_inode(d_real(dentry)); + return d_backing_inode(d_real(dentry, NULL, 0)); } diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..bacc0733663c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1272,12 +1272,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - struct dentry *dentry = file->f_path.dentry; - - if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, file_inode(file)); - else - return dentry; + return d_real(file->f_path.dentry, file_inode(file), 0); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -- cgit v1.2.3 From e698b8a43659f9ece192fcab215abcadac8f88d7 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 30 Jun 2016 08:53:27 +0200 Subject: vfs: document ->d_real() Add missing documentation for the d_op->d_real() method and d_real() helper. Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 45b22de15ede..14df83609c7f 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -139,7 +139,8 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(struct dentry *, bool); - struct dentry *(*d_real)(struct dentry *, const struct inode *, unsigned int); + struct dentry *(*d_real)(struct dentry *, const struct inode *, + unsigned int); } ____cacheline_aligned; /* @@ -554,6 +555,17 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } +/** + * d_real - Return the real dentry + * @dentry: the dentry to query + * @inode: inode to select the dentry from multiple layers (can be NULL) + * @flags: open flags to control copy-up behavior + * + * If dentry is on an union/overlay, then return the underlying, real dentry. + * Otherwise return the dentry itself. + * + * See also: Documentation/filesystems/vfs.txt + */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode, unsigned int flags) -- cgit v1.2.3 From 6816a7ffce32e999601825ddfd887f36d3052932 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 28 Jun 2016 12:18:25 +0200 Subject: bpf, trace: add BPF_F_CURRENT_CPU flag for bpf_perf_event_read Follow-up commit to 1e33759c788c ("bpf, trace: add BPF_F_CURRENT_CPU flag for bpf_perf_event_output") to add the same functionality into bpf_perf_event_read() helper. The split of index into flags and index component is also safe here, since such large maps are rejected during map allocation time. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 406459b935a2..58df2da3e9bf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -347,7 +347,7 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK -- cgit v1.2.3 From 6578171a7ff0c31dc73258f93da7407510abf085 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 28 Jun 2016 12:18:27 +0200 Subject: bpf: add bpf_skb_change_proto helper This patch adds a minimal helper for doing the groundwork of changing the skb->protocol in a controlled way. Currently supported is v4 to v6 and vice versa transitions, which allows f.e. for a minimal, static nat64 implementation where applications in containers that still require IPv4 can be transparently operated in an IPv6-only environment. For example, host facing veth of the container can transparently do the transitions in a programmatic way with the help of clsact qdisc and cls_bpf. Idea is to separate concerns for keeping complexity of the helper lower, which means that the programs utilize bpf_skb_change_proto(), bpf_skb_store_bytes() and bpf_lX_csum_replace() to get the job done, instead of doing everything in a single helper (and thus partially duplicating helper functionality). Also, bpf_skb_change_proto() shouldn't need to deal with raw packet data as this is done by other helpers. bpf_skb_proto_6_to_4() and bpf_skb_proto_4_to_6() unclone the skb to operate on a private one, push or pop additionally required header space and migrate the gso/gro meta data from the shared info. We do mark the gso type as dodgy so that headers are checked and segs recalculated by the gso/gro engine. The gso_size target is adapted as well. The flags argument added is currently reserved and can be used for future extensions. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 58df2da3e9bf..66cd738a937a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -313,6 +313,20 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From d2485c4242a826fdf493fd3a27b8b792965b9b9e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 28 Jun 2016 12:18:28 +0200 Subject: bpf: add bpf_skb_change_type helper This work adds a helper for changing skb->pkt_type in a controlled way. We only allow a subset of possible values and can extend that in future should other use cases come up. Doing this as a helper has the advantage that errors can be handeled gracefully and thus helper kept extensible. It's a write counterpart to pkt_type member we can already read from struct __sk_buff context. Major use case is to change incoming skbs to PACKET_HOST in a programmatic way instead of having to recirculate via redirect(..., BPF_F_INGRESS), for example. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 66cd738a937a..be6ac1291680 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -327,6 +327,15 @@ enum bpf_func_id { */ BPF_FUNC_skb_change_proto, + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From e98e915e11ad1efb11147122bd4932ec6b3425da Mon Sep 17 00:00:00 2001 From: Masashi Honma Date: Wed, 22 Jun 2016 20:23:03 +0900 Subject: wireless: Use macro instead of number Use IEEE80211_MIN_ACTION_SIZE macro for robust management frame check. Signed-off-by: Masashi Honma Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b118744d3382..1daebb307e6e 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2464,7 +2464,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) */ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) { - if (skb->len < 25) + if (skb->len < IEEE80211_MIN_ACTION_SIZE) return false; return _ieee80211_is_robust_mgmt_frame((void *)skb->data); } -- cgit v1.2.3 From 46f6b06050b736dab4d41494dae27b883cddc365 Mon Sep 17 00:00:00 2001 From: Masashi Honma Date: Wed, 22 Jun 2016 19:55:20 +0900 Subject: mac80211: Encrypt "Group addressed privacy" action frames Previously, the action frames to group address was not encrypted. But [1] "Table 8-38 Category values" indicates "Mesh" and "Multihop" category action frames should be encrypted (Group addressed privacy == yes). And the encyption key should be MGTK ([1] 10.13 Group addressed robust management frame procedures). So this patch modifies the code to make it suitable for spec. [1] IEEE Std 802.11-2012 Signed-off-by: Masashi Honma Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 1daebb307e6e..a80516fd65c8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -19,6 +19,7 @@ #include #include +#include #include #include @@ -2486,6 +2487,35 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC; } +/** + * _ieee80211_is_group_privacy_action - check if frame is a group addressed + * privacy action frame + * @hdr: the frame + */ +static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) +{ + struct ieee80211_mgmt *mgmt = (void *)hdr; + + if (!ieee80211_is_action(hdr->frame_control) || + !is_multicast_ether_addr(hdr->addr1)) + return false; + + return mgmt->u.action.category == WLAN_CATEGORY_MESH_ACTION || + mgmt->u.action.category == WLAN_CATEGORY_MULTIHOP_ACTION; +} + +/** + * ieee80211_is_group_privacy_action - check if frame is a group addressed + * privacy action frame + * @skb: the skb containing the frame, length will be checked + */ +static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) +{ + if (skb->len < IEEE80211_MIN_ACTION_SIZE) + return false; + return _ieee80211_is_group_privacy_action((void *)skb->data); +} + /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs -- cgit v1.2.3 From 80e73cc563c4359be809a03bcb8e7e28141a813a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 28 Jun 2016 16:57:05 +0200 Subject: net: rtnetlink: add support for the IFLA_STATS_LINK_XSTATS_SLAVE attribute This patch adds support for the IFLA_STATS_LINK_XSTATS_SLAVE attribute which allows to export per-slave statistics if the master device supports the linkxstats callback. The attribute is passed down to the linkxstats callback and it is up to the callback user to use it (an example has been added to the only current user - the bridge). This allows us to query only specific slaves of master devices like bridge ports and export only what we're interested in instead of having to dump all ports and searching only for a single one. This will be used to export per-port IGMP/MLD stats and also per-port vlan stats in the future, possibly other statistics as well. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 5 +++-- include/uapi/linux/if_link.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 006a7b81d758..4113916cc1bb 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -98,10 +98,11 @@ struct rtnl_link_ops { const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); - size_t (*get_linkxstats_size)(const struct net_device *dev); + size_t (*get_linkxstats_size)(const struct net_device *dev, + int attr); int (*fill_linkxstats)(struct sk_buff *skb, const struct net_device *dev, - int *prividx); + int *prividx, int attr); }; int __rtnl_link_register(struct rtnl_link_ops *ops); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index bb36bd5675a7..db2458ade81c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -822,6 +822,7 @@ enum { IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ IFLA_STATS_LINK_64, IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, __IFLA_STATS_MAX, }; -- cgit v1.2.3 From 1080ab95e3c7bdd77870e209aff83c763fdcf439 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 28 Jun 2016 16:57:06 +0200 Subject: net: bridge: add support for IGMP/MLD stats and export them via netlink This patch adds stats support for the currently used IGMP/MLD types by the bridge. The stats are per-port (plus one stat per-bridge) and per-direction (RX/TX). The stats are exported via netlink via the new linkxstats API (RTM_GETSTATS). In order to minimize the performance impact, a new option is used to enable/disable the stats - multicast_stats_enabled, similar to the recent vlan stats. Also in order to avoid multiple IGMP/MLD type lookups and checks, we make use of the current "igmp" member of the bridge private skb->cb region to record the type on Rx (both host-generated and external packets pass by multicast_rcv()). We can do that since the igmp member was used as a boolean and all the valid IGMP/MLD types are positive values. The normal bridge fast-path is not affected at all, the only affected paths are the flooding ones and since we make use of the IGMP/MLD type, we can quickly determine if the packet should be counted using cache-hot data (cb's igmp member). We add counters for: * IGMP Queries * IGMP Leaves * IGMP v1/v2/v3 reports * MLD Queries * MLD Leaves * MLD v1/v2 reports These are invaluable when monitoring or debugging complex multicast setups with bridges. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/if_link.h | 1 + 2 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 397d503fdedb..8304fe6f0561 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -247,8 +247,34 @@ enum { enum { BRIDGE_XSTATS_UNSPEC, BRIDGE_XSTATS_VLAN, + BRIDGE_XSTATS_MCAST, + BRIDGE_XSTATS_PAD, __BRIDGE_XSTATS_MAX }; #define BRIDGE_XSTATS_MAX (__BRIDGE_XSTATS_MAX - 1) +enum { + BR_MCAST_DIR_RX, + BR_MCAST_DIR_TX, + BR_MCAST_DIR_SIZE +}; + +/* IGMP/MLD statistics */ +struct br_mcast_stats { + __u64 igmp_queries[BR_MCAST_DIR_SIZE]; + __u64 igmp_leaves[BR_MCAST_DIR_SIZE]; + __u64 igmp_v1reports[BR_MCAST_DIR_SIZE]; + __u64 igmp_v2reports[BR_MCAST_DIR_SIZE]; + __u64 igmp_v3reports[BR_MCAST_DIR_SIZE]; + __u64 igmp_parse_errors; + + __u64 mld_queries[BR_MCAST_DIR_SIZE]; + __u64 mld_leaves[BR_MCAST_DIR_SIZE]; + __u64 mld_v1reports[BR_MCAST_DIR_SIZE]; + __u64 mld_v2reports[BR_MCAST_DIR_SIZE]; + __u64 mld_parse_errors; + + __u64 mcast_bytes[BR_MCAST_DIR_SIZE]; + __u64 mcast_packets[BR_MCAST_DIR_SIZE]; +}; #endif /* _UAPI_LINUX_IF_BRIDGE_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index db2458ade81c..4285ac31e865 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -273,6 +273,7 @@ enum { IFLA_BR_VLAN_DEFAULT_PVID, IFLA_BR_PAD, IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, __IFLA_BR_MAX, }; -- cgit v1.2.3 From 8582f6d158c8824042432f581d49ef478d5cb238 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 29 Jun 2016 16:11:32 +0200 Subject: soc/tegra: Stub out PCIe IRQ workaround on 64-bit ARM The PCIe host controller found on Tegra20 has a hardware bug that causes PCIe interrupts to get lost when LP2 is enabled. Stub out the workaround on 64-bit ARM because none of the more recent Tegra SoC generations seem to have this bug anymore. Signed-off-by: Thierry Reding --- include/soc/tegra/cpuidle.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/soc/tegra/cpuidle.h b/include/soc/tegra/cpuidle.h index ea04f4225638..1fae9c7800d1 100644 --- a/include/soc/tegra/cpuidle.h +++ b/include/soc/tegra/cpuidle.h @@ -14,7 +14,7 @@ #ifndef __SOC_TEGRA_CPUIDLE_H__ #define __SOC_TEGRA_CPUIDLE_H__ -#ifdef CONFIG_CPU_IDLE +#if defined(CONFIG_ARM) && defined(CONFIG_CPU_IDLE) void tegra_cpuidle_pcie_irqs_in_use(void); #else static inline void tegra_cpuidle_pcie_irqs_in_use(void) -- cgit v1.2.3 From b1ed4c4fa9a5ccf325184fd90edc50978ef6e33a Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 27 Jun 2016 15:33:56 -0700 Subject: tcp: add an ability to dump and restore window parameters We found that sometimes a restored tcp socket doesn't work. A reason of this bug is incorrect window parameters and in this case tcp_acceptable_seq() returns tcp_wnd_end(tp) instead of tp->snd_nxt. The other side drops packets with this seq, because seq is less than tp->rcv_nxt ( tcp_sequence() ). Data from a send queue is sent only if there is enough space in a window, so when we restore unacked data, we need to expand a window to fit this data. This was in a first version of this patch: "tcp: extend window to fit all restored unacked data in a send queue" Then Alexey recommended me to restore window parameters instead of adjusted them according with data in a sent queue. This sounds resonable. rcv_wnd has to be restored, because it was reported to another side and the offered window is never shrunk. One of reasons why we need to restore snd_wnd was described above. Cc: Pavel Emelyanov Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 53e8e3fe6b1b..482898fc433a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -115,12 +115,22 @@ enum { #define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ #define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ #define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ +#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ struct tcp_repair_opt { __u32 opt_code; __u32 opt_val; }; +struct tcp_repair_window { + __u32 snd_wl1; + __u32 snd_wnd; + __u32 max_window; + + __u32 rcv_wnd; + __u32 rcv_wup; +}; + enum { TCP_NO_QUEUE, TCP_RECV_QUEUE, -- cgit v1.2.3 From 2631b79f6cb8b634fe41b77de9c4add0ec6b3cae Mon Sep 17 00:00:00 2001 From: "Seymour, Shane M" Date: Tue, 28 Jun 2016 23:06:48 +0000 Subject: tcp: increase size at which tcp_bound_to_half_wnd bounds to > TCP_MSS_DEFAULT In previous commit 01f83d69844d307be2aa6fea88b0e8fe5cbdb2f4 the following comments were added: "When peer uses tiny windows, there is no use in packetizing to sub-MSS pieces for the sake of SWS or making sure there are enough packets in the pipe for fast recovery." The test should be > TCP_MSS_DEFAULT not >= 512. This allows low end devices that send an MSS of 536 (TCP_MSS_DEFAULT) to see better network performance by sending it 536 bytes of data at a time instead of bounding to half window size (268). Other network stacks work this way, e.g. HP-UX. Signed-off-by: Shane Seymour Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a79894b66726..d825858fe4f1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -589,7 +589,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) * On the other hand, for extremely large MSS devices, handling * smaller than MSS windows in this way does make sense. */ - if (tp->max_window >= 512) + if (tp->max_window > TCP_MSS_DEFAULT) cutoff = (tp->max_window >> 1); else cutoff = tp->max_window; -- cgit v1.2.3 From ab714aff4f744f52f0beae93ed441f2f5585eb7a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 30 Jun 2016 11:39:38 -0400 Subject: jbd2: move lockdep tracking to journal_s Currently lockdep map is tracked in each journal handle. To be able to expand lockdep support to cover also other cases where we depend on transaction commit and where handle is not available, move lockdep map into struct journal_s. Since this makes the lockdep map shared for all handles, we have to use rwsem_acquire_read() for acquisitions now. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index efb232c5f668..3d210cbe4e1b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -491,10 +491,6 @@ struct jbd2_journal_handle unsigned long h_start_jiffies; unsigned int h_requested_credits; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map h_lockdep_map; -#endif }; @@ -793,6 +789,7 @@ jbd2_time_diff(unsigned long start, unsigned long end) * @j_proc_entry: procfs entry for the jbd statistics directory * @j_stats: Overall statistics * @j_private: An opaque pointer to fs-private information. + * @j_trans_commit_map: Lockdep entity to track transaction commit dependencies */ struct journal_s @@ -1035,6 +1032,18 @@ struct journal_s /* Precomputed journal UUID checksum for seeding other checksums */ __u32 j_csum_seed; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Lockdep entity to track transaction commit dependencies. Handles + * hold this "lock" for read, when we wait for commit, we acquire the + * "lock" for writing. This matches the properties of jbd2 journalling + * where the running transaction has to wait for all handles to be + * dropped to commit that transaction and also acquiring a handle may + * require transaction commit to finish. + */ + struct lockdep_map j_trans_commit_map; +#endif }; /* journal feature predicate functions */ -- cgit v1.2.3 From 1eaa566d368b214d99cbb973647c1b0b8102a9ae Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 30 Jun 2016 11:40:54 -0400 Subject: jbd2: track more dependencies on transaction commit So far we were tracking only dependency on transaction commit due to starting a new handle (which may require commit to start a new transaction). Now add tracking also for other cases where we wait for transaction commit. This way lockdep can catch deadlocks e. g. because we call jbd2_journal_stop() for a synchronous handle with some locks held which rank below transaction start. Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 3d210cbe4e1b..dfaa1f4dcb0c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1046,6 +1046,12 @@ struct journal_s #endif }; +#define jbd2_might_wait_for_commit(j) \ + do { \ + rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ + rwsem_release(&j->j_trans_commit_map, 1, _THIS_IP_); \ + } while (0) + /* journal feature predicate functions */ #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ static inline bool jbd2_has_feature_##name(journal_t *j) \ -- 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 --- include/linux/iio/iio.h | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'include') 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 6fb924dc9c482557ebd41f6c6a5fde34210a2e08 Mon Sep 17 00:00:00 2001 From: Zhangfei Gao Date: Wed, 29 Jun 2016 17:48:44 -0700 Subject: clk: hi6220: Add RTC clock for pl031 Adds clk support for the pl031 RTC on hi6220 Cc: Michael Turquette Cc: Stephen Boyd Cc: Rob Herring Cc: Pawel Moll Cc: Wei Xu Cc: Guodong Xu Signed-off-by: Zhangfei Gao [jstultz: Forward ported, tweaked commit description] Signed-off-by: John Stultz Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/hi6220-clock.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/clock/hi6220-clock.h b/include/dt-bindings/clock/hi6220-clock.h index 70ee3833a7a0..6b03c84f4278 100644 --- a/include/dt-bindings/clock/hi6220-clock.h +++ b/include/dt-bindings/clock/hi6220-clock.h @@ -55,8 +55,9 @@ #define HI6220_TIMER7_PCLK 34 #define HI6220_TIMER8_PCLK 35 #define HI6220_UART0_PCLK 36 - -#define HI6220_AO_NR_CLKS 37 +#define HI6220_RTC0_PCLK 37 +#define HI6220_RTC1_PCLK 38 +#define HI6220_AO_NR_CLKS 39 /* clk in Hi6220 systrl */ /* gate clock */ -- cgit v1.2.3 From 5c6e5b60aae4347223f176966455010a5715b863 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Jun 2016 14:13:12 -0400 Subject: NFS: Fix an Oops in the pNFS files and flexfiles connection setup to the DS Chris Worley reports: RIP: 0010:[] [] rpc_new_client+0x2a0/0x2e0 [sunrpc] RSP: 0018:ffff880158f6f548 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880234f8bc00 RCX: 000000000000ea60 RDX: 0000000000074cc0 RSI: 000000000000ea60 RDI: ffff880234f8bcf0 RBP: ffff880158f6f588 R08: 000000000001ac80 R09: ffff880237003300 R10: ffff880201171000 R11: ffffea0000d75200 R12: ffffffffa03afc60 R13: ffff880230c18800 R14: 0000000000000000 R15: ffff880158f6f680 FS: 00007f0e32673740(0000) GS:ffff88023fc40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000008 CR3: 0000000234886000 CR4: 00000000001406e0 Stack: ffffffffa047a680 0000000000000000 ffff880158f6f598 ffff880158f6f680 ffff880158f6f680 ffff880234d11d00 ffff88023357f800 ffff880158f6f7d0 ffff880158f6f5b8 ffffffffa024660a ffff880158f6f5b8 ffffffffa02492ec Call Trace: [] rpc_create_xprt+0x1a/0xb0 [sunrpc] [] ? xprt_create_transport+0x13c/0x240 [sunrpc] [] rpc_create+0xc6/0x1a0 [sunrpc] [] nfs_create_rpc_client+0xf5/0x140 [nfs] [] nfs_init_client+0x3a/0xd0 [nfs] [] nfs_get_client+0x25f/0x310 [nfs] [] ? rpc_ntop+0xe8/0x100 [sunrpc] [] nfs3_set_ds_client+0xcc/0x100 [nfsv3] [] nfs4_pnfs_ds_connect+0x120/0x400 [nfsv4] [] nfs4_ff_layout_prepare_ds+0xe7/0x330 [nfs_layout_flexfiles] [] ff_layout_pg_init_write+0xcb/0x280 [nfs_layout_flexfiles] [] __nfs_pageio_add_request+0x12c/0x490 [nfs] [] nfs_pageio_add_request+0xc2/0x2a0 [nfs] [] ? nfs_pageio_init+0x75/0x120 [nfs] [] nfs_do_writepage+0x120/0x270 [nfs] [] nfs_writepage_locked+0x61/0xc0 [nfs] [] ? __percpu_counter_add+0x55/0x70 [] nfs_wb_single_page+0xef/0x1c0 [nfs] [] ? __dec_zone_page_state+0x33/0x40 [] nfs_launder_page+0x41/0x90 [nfs] [] invalidate_inode_pages2_range+0x340/0x3a0 [] invalidate_inode_pages2+0x17/0x20 [] nfs_release+0x9e/0xb0 [nfs] [] ? nfs_open+0x60/0x60 [nfs] [] nfs_file_release+0x3d/0x60 [nfs] [] __fput+0xdc/0x1e0 [] ____fput+0xe/0x10 [] task_work_run+0xc4/0xe0 [] do_exit+0x2e8/0xb30 [] ? do_audit_syscall_entry+0x6c/0x70 [] ? __audit_syscall_exit+0x1e6/0x280 [] do_group_exit+0x3f/0xa0 [] SyS_exit_group+0x14/0x20 [] system_call_fastpath+0x12/0x71 Which seems to be due to a call to utsname() when in a task exit context in order to determine the hostname to set in rpc_new_client(). In reality, what we want here is not the hostname of the current task, but the hostname that was used to set up the metadata server. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c304a11b5b1a..82b81a1c2438 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1596,9 +1596,8 @@ struct nfs_rpc_ops { int (*have_delegation)(struct inode *, fmode_t); int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); - struct nfs_client * - (*init_client) (struct nfs_client *, const struct rpc_timeout *, - const char *); + struct nfs_client *(*init_client) (struct nfs_client *, + const struct nfs_client_initdata *); void (*free_client) (struct nfs_client *); struct nfs_server *(*create_server)(struct nfs_mount_info *, struct nfs_subversion *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, -- cgit v1.2.3 From 52445637371e5a30c0320eae75970c28f982d914 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 22 May 2016 14:33:35 +0900 Subject: clk: fixed-rate: add clk_hw_unregister_fixed_rate() This will be used to migrate to the clk_hw APIs. Signed-off-by: Masahiro Yamada Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 0c72204c75fc..94e00fe976f5 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -293,6 +293,7 @@ void clk_unregister_fixed_rate(struct clk *clk); struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned long fixed_rate, unsigned long fixed_accuracy); +void clk_hw_unregister_fixed_rate(struct clk_hw *hw); void of_fixed_clk_setup(struct device_node *np); -- cgit v1.2.3 From 37b11804ed1725dc2ea97be2236150210a69e9d5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 27 Jun 2016 15:52:48 -0500 Subject: userns: Handle -1 in k[ug]id_has_mapping when !CONFIG_USER_NS Refuse to admit any user namespace has a mapping of the INVALID_UID and the INVALID_GID when !CONFIG_USER_NS. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/uidgid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 03835522dfcb..25e9d9216340 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -177,12 +177,12 @@ static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { - return true; + return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { - return true; + return gid_valid(gid); } #endif /* CONFIG_USER_NS */ -- cgit v1.2.3 From 0d4d717f25834134bb6f43284f84c8ccee5bbf2a Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 27 Jun 2016 16:04:06 -0500 Subject: vfs: Verify acls are valid within superblock's s_user_ns. Update posix_acl_valid to verify that an acl is within a user namespace. Update the callers of posix_acl_valid to pass in an appropriate user namespace. For posix_acl_xattr_set and v9fs_xattr_set_acl pass in inode->i_sb->s_user_ns to posix_acl_valid. For md_unpack_acl pass in &init_user_ns as no inode or superblock is in sight. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/posix_acl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 5b5a80cc5926..1af6438fde3e 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -81,7 +81,7 @@ posix_acl_release(struct posix_acl *acl) extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); -extern int posix_acl_valid(const struct posix_acl *); +extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); -- cgit v1.2.3 From 19689e38eca5d7b32755182d4e62efd7a5376c45 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 27 Jun 2016 18:51:53 +0200 Subject: tcp: md5: use kmalloc() backed scratch areas Some arches have virtually mapped kernel stacks, or will soon have. tcp_md5_hash_header() uses an automatic variable to copy tcp header before mangling th->check and calling crypto function, which might be problematic on such arches. David says that using percpu storage is also problematic on non SMP builds. Just use kmalloc() to allocate scratch areas. Signed-off-by: Eric Dumazet Reported-by: Andy Lutomirski Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d825858fe4f1..c00e7d51bb18 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1384,7 +1384,7 @@ union tcp_md5sum_block { /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { struct ahash_request *md5_req; - union tcp_md5sum_block md5_blk; + void *scratch; }; /* - functions */ @@ -1420,7 +1420,6 @@ static inline void tcp_put_md5sig_pool(void) local_bh_enable(); } -int tcp_md5_hash_header(struct tcp_md5sig_pool *, const struct tcphdr *); int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff *, unsigned int header_len); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, -- cgit v1.2.3 From 6edaa5307f3f51e4e56dc4c63f68a69d88c6ddf5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 15 Jun 2016 15:18:26 +0200 Subject: KVM: remove kvm_guest_enter/exit wrappers Use the functions from context_tracking.h directly. Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: H. Peter Anvin Cc: Ingo Molnar Cc: Thomas Gleixner Reviewed-by: Rik van Riel Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ffff40522688..66b2f6159aad 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -875,28 +875,6 @@ static inline void kvm_iommu_unmap_pages(struct kvm *kvm, } #endif -/* must be called with irqs disabled */ -static inline void __kvm_guest_enter(void) -{ - guest_enter_irqoff(); -} - -/* must be called with irqs disabled */ -static inline void __kvm_guest_exit(void) -{ - guest_exit_irqoff(); -} - -static inline void kvm_guest_enter(void) -{ - guest_enter(); -} - -static inline void kvm_guest_exit(void) -{ - guest_exit(); -} - /* * search_memslots() and __gfn_to_memslot() are here because they are * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c. -- cgit v1.2.3 From 982fb490c298896d15e9323a882f34a57c11ff56 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 30 Jun 2016 14:45:31 +0800 Subject: ptr_ring: support zero length ring Sometimes, we need zero length ring. But current code will crash since we don't do any check before accessing the ring. This patch fixes this. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 562a65e8bcc0..d78b8b89c707 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -102,7 +102,7 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r) */ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr) { - if (r->queue[r->producer]) + if (unlikely(!r->size) || r->queue[r->producer]) return -ENOSPC; r->queue[r->producer++] = ptr; @@ -164,7 +164,9 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { - return r->queue[r->consumer]; + if (likely(r->size)) + return r->queue[r->consumer]; + return NULL; } /* Note: callers invoking this in a loop must use a compiler barrier, -- cgit v1.2.3 From fd68adec9de3104c236ffbcb3bd829d3e635a444 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 30 Jun 2016 14:45:32 +0800 Subject: skb_array: minor tweak Signed-off-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/skb_array.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index 678bfbf78ac4..2dd0d1e4ee7e 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -151,12 +151,12 @@ static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_init(&a->ring, size, gfp); } -void __skb_array_destroy_skb(void *ptr) +static void __skb_array_destroy_skb(void *ptr) { kfree_skb(ptr); } -int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) +static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -- cgit v1.2.3 From 59e6ae53248a72d83cec77dd704b6990b2394479 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 30 Jun 2016 14:45:33 +0800 Subject: ptr_ring: support resizing multiple queues Sometimes, we need support resizing multiple queues at once. This is because it was not easy to recover to recover from a partial failure of multiple queues resizing. Signed-off-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 71 ++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 62 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index d78b8b89c707..2052011bf9fb 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -349,20 +349,14 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } -static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, - void (*destroy)(void *)) +static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, + int size, gfp_t gfp, + void (*destroy)(void *)) { - unsigned long flags; int producer = 0; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); void **old; void *ptr; - if (!queue) - return -ENOMEM; - - spin_lock_irqsave(&(r)->producer_lock, flags); - while ((ptr = ptr_ring_consume(r))) if (producer < size) queue[producer++] = ptr; @@ -375,6 +369,23 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, old = r->queue; r->queue = queue; + return old; +} + +static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, + void (*destroy)(void *)) +{ + unsigned long flags; + void **queue = __ptr_ring_init_queue_alloc(size, gfp); + void **old; + + if (!queue) + return -ENOMEM; + + spin_lock_irqsave(&(r)->producer_lock, flags); + + old = __ptr_ring_swap_queue(r, queue, size, gfp, destroy); + spin_unlock_irqrestore(&(r)->producer_lock, flags); kfree(old); @@ -382,6 +393,48 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, return 0; } +static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, + int size, + gfp_t gfp, void (*destroy)(void *)) +{ + unsigned long flags; + void ***queues; + int i; + + queues = kmalloc(nrings * sizeof *queues, gfp); + if (!queues) + goto noqueues; + + for (i = 0; i < nrings; ++i) { + queues[i] = __ptr_ring_init_queue_alloc(size, gfp); + if (!queues[i]) + goto nomem; + } + + for (i = 0; i < nrings; ++i) { + spin_lock_irqsave(&(rings[i])->producer_lock, flags); + queues[i] = __ptr_ring_swap_queue(rings[i], queues[i], + size, gfp, destroy); + spin_unlock_irqrestore(&(rings[i])->producer_lock, flags); + } + + for (i = 0; i < nrings; ++i) + kfree(queues[i]); + + kfree(queues); + + return 0; + +nomem: + while (--i >= 0) + kfree(queues[i]); + + kfree(queues); + +noqueues: + return -ENOMEM; +} + static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { void *ptr; -- cgit v1.2.3 From bf900b3dbefee49855c17aa09fb4245346a78fb3 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 30 Jun 2016 14:45:34 +0800 Subject: skb_array: add wrappers for resizing Signed-off-by: Michael S. Tsirkin Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/skb_array.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index 2dd0d1e4ee7e..f4dfade428f0 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -161,6 +161,15 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } +static inline int skb_array_resize_multiple(struct skb_array **rings, + int nrings, int size, gfp_t gfp) +{ + BUILD_BUG_ON(offsetof(struct skb_array, ring)); + return ptr_ring_resize_multiple((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); +} + static inline void skb_array_cleanup(struct skb_array *a) { ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb); -- cgit v1.2.3 From 08294a26e15d7baf1e14ee569e9f2bc82a7ae768 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 30 Jun 2016 14:45:35 +0800 Subject: net: introduce NETDEV_CHANGE_TX_QUEUE_LEN This patch introduces a new event - NETDEV_CHANGE_TX_QUEUE_LEN, this will be triggered when tx_queue_len. It could be used by net device who want to do some processing at that time. An example is tun who may want to resize tx array when tx_queue_len is changed. Cc: John Fastabend Signed-off-by: Jason Wang Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e84d9d23c2d5..7dc2ec74122a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2237,6 +2237,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B #define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C +#define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 1576d98605998fb59d121a39581129e134217182 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 30 Jun 2016 14:45:36 +0800 Subject: tun: switch to use skb array for tx We used to queue tx packets in sk_receive_queue, this is less efficient since it requires spinlocks to synchronize between producer and consumer. This patch tries to address this by: - switch from sk_receive_queue to a skb_array, and resize it when tx_queue_len was changed. - introduce a new proto_ops peek_len which was used for peeking the skb length. - implement a tun version of peek_len for vhost_net to use and convert vhost_net to use peek_len if possible. Pktgen test shows about 15.3% improvement on guest receiving pps for small buffers: Before: ~1300000pps After : ~1500000pps Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/net.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 25aa03b51c4e..b9f0ff4d489c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -185,6 +185,7 @@ struct proto_ops { ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); + int (*peek_len)(struct socket *sock); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- cgit v1.2.3 From 4ae89ad92477219b504a49966ee010fe8dcb85af Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 24 Jun 2016 11:32:26 -0700 Subject: etherdevice.h & bridge: netfilter: Add and use ether_addr_equal_masked There are code duplications of a masked ethernet address comparison here so make it a separate function instead. Miscellanea: o Neaten alignment of FWINV macro uses to make it clearer for the reader Signed-off-by: Joe Perches Acked-by: David S. Miller Signed-off-by: Pablo Neira Ayuso --- include/linux/etherdevice.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 37ff4a6faa9a..6fec9e81bd70 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -373,6 +373,29 @@ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) #endif } +/** + * ether_addr_equal_masked - Compare two Ethernet addresses with a mask + * @addr1: Pointer to a six-byte array containing the 1st Ethernet address + * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address + * @mask: Pointer to a six-byte array containing the Ethernet address bitmask + * + * Compare two Ethernet addresses with a mask, returns true if for every bit + * set in the bitmask the equivalent bits in the ethernet addresses are equal. + * Using a mask with all bits set is a slower ether_addr_equal. + */ +static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, + const u8 *mask) +{ + int i; + + for (i = 0; i < ETH_ALEN; i++) { + if ((addr1[i] ^ addr2[i]) & mask[i]) + return false; + } + + return true; +} + /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure -- cgit v1.2.3 From cecdef3656956b0978bf86ecd1ce0542d2c61e97 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 30 Jun 2016 06:02:46 +0000 Subject: ASoC: simple-card: use asoc_simple_card_parse_daifmt() We can use simpel utils asoc_simple_card_parse_daifmt(). Let's use it Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card.h | 11 +---------- include/sound/simple_card_utils.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h index 0399352f3a62..a6a2e1547092 100644 --- a/include/sound/simple_card.h +++ b/include/sound/simple_card.h @@ -13,16 +13,7 @@ #define __SIMPLE_CARD_H #include - -struct asoc_simple_dai { - const char *name; - unsigned int sysclk; - int slots; - int slot_width; - unsigned int tx_slot_mask; - unsigned int rx_slot_mask; - struct clk *clk; -}; +#include struct asoc_simple_card_info { const char *name; diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 7acc798016e0..50aa7b22a94c 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -12,6 +12,16 @@ #include +struct asoc_simple_dai { + const char *name; + unsigned int sysclk; + int slots; + int slot_width; + unsigned int tx_slot_mask; + unsigned int rx_slot_mask; + struct clk *clk; +}; + int asoc_simple_card_parse_daifmt(struct device *dev, struct device_node *node, struct device_node *codec, -- cgit v1.2.3 From 32f27c745c26ff4b6351bce265cba049a2c74de5 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 29 Jun 2016 18:04:13 +0800 Subject: crypto: api - Add crypto_inst_setname This patch adds the helper crypto_inst_setname because the current helper crypto_alloc_instance2 is no longer useful given that we now look up the algorithm after we allocate the instance object. Signed-off-by: Herbert Xu --- include/crypto/algapi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index eeafd21afb44..0483f652ac27 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -244,6 +244,8 @@ static inline struct crypto_alg *crypto_attr_alg(struct rtattr *rta, } int crypto_attr_u32(struct rtattr *rta, u32 *num); +int crypto_inst_setname(struct crypto_instance *inst, const char *name, + struct crypto_alg *alg); void *crypto_alloc_instance2(const char *name, struct crypto_alg *alg, unsigned int head); struct crypto_instance *crypto_alloc_instance(const char *name, -- cgit v1.2.3 From 9b45b7bba3d22de52e09df63c50f390a193a3f53 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 29 Jun 2016 19:32:21 +0800 Subject: crypto: rsa - Generate fixed-length output Every implementation of RSA that we have naturally generates output with leading zeroes. The one and only user of RSA, pkcs1pad wants to have those leading zeroes in place, in fact because they are currently absent it has to write those zeroes itself. So we shouldn't be stripping leading zeroes in the first place. In fact this patch makes rsa-generic produce output with fixed length so that pkcs1pad does not need to do any extra work. This patch also changes DH to use the new interface. Signed-off-by: Herbert Xu --- include/linux/mpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mpi.h b/include/linux/mpi.h index f219559e5e80..1cc5ffb769af 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -80,7 +80,7 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign); int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes, int *sign); void *mpi_get_secure_buffer(MPI a, unsigned *nbytes, int *sign); -int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned *nbytes, +int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes, int *sign); #define log_mpidump g10_log_mpidump -- cgit v1.2.3 From 1aacde3d22c42281236155c1ef6d7a5aa32a826b Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 30 Jun 2016 17:24:43 +0200 Subject: bpf: generally move prog destruction to RCU deferral Jann Horn reported following analysis that could potentially result in a very hard to trigger (if not impossible) UAF race, to quote his event timeline: - Set up a process with threads T1, T2 and T3 - Let T1 set up a socket filter F1 that invokes another filter F2 through a BPF map [tail call] - Let T1 trigger the socket filter via a unix domain socket write, don't wait for completion - Let T2 call PERF_EVENT_IOC_SET_BPF with F2, don't wait for completion - Now T2 should be behind bpf_prog_get(), but before bpf_prog_put() - Let T3 close the file descriptor for F2, dropping the reference count of F2 to 2 - At this point, T1 should have looked up F2 from the map, but not finished executing it - Let T3 remove F2 from the BPF map, dropping the reference count of F2 to 1 - Now T2 should call bpf_prog_put() (wrong BPF program type), dropping the reference count of F2 to 0 and scheduling bpf_prog_free_deferred() via schedule_work() - At this point, the BPF program could be freed - BPF execution is still running in a freed BPF program While at PERF_EVENT_IOC_SET_BPF time it's only guaranteed that the perf event fd we're doing the syscall on doesn't disappear from underneath us for whole syscall time, it may not be the case for the bpf fd used as an argument only after we did the put. It needs to be a valid fd pointing to a BPF program at the time of the call to make the bpf_prog_get() and while T2 gets preempted, F2 must have dropped reference to 1 on the other CPU. The fput() from the close() in T3 should also add additionally delay to the reference drop via exit_task_work() when bpf_prog_release() gets called as well as scheduling bpf_prog_free_deferred(). That said, it makes nevertheless sense to move the BPF prog destruction generally after RCU grace period to guarantee that such scenario above, but also others as recently fixed in ceb56070359b ("bpf, perf: delay release of BPF prog after grace period") with regards to tail calls won't happen. Integrating bpf_prog_free_deferred() directly into the RCU callback is not allowed since the invocation might happen from either softirq or process context, so we're not permitted to block. Reviewing all bpf_prog_put() invocations from eBPF side (note, cBPF -> eBPF progs don't use this for their destruction) with call_rcu() look good to me. Since we don't know whether at the time of attaching the program, we're already part of a tail call map, we need to use RCU variant. However, due to this, there won't be severely more stress on the RCU callback queue: situations with above bpf_prog_get() and bpf_prog_put() combo in practice normally won't lead to releases, but even if they would, enough effort/ cycles have to be put into loading a BPF program into the kernel already. Reported-by: Jann Horn Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8411032ac90d..749549888b86 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -220,7 +220,6 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -281,10 +280,6 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd) static inline void bpf_prog_put(struct bpf_prog *prog) { } - -static inline void bpf_prog_put_rcu(struct bpf_prog *prog) -{ -} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ -- cgit v1.2.3 From 113214be7f6c98dd6d0435e4765aea8dea91662c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 30 Jun 2016 17:24:44 +0200 Subject: bpf: refactor bpf_prog_get and type check into helper Since bpf_prog_get() and program type check is used in a couple of places, refactor this into a small helper function that we can make use of. Since the non RO prog->aux part is not used in performance critical paths and a program destruction via RCU is rather very unlikley when doing the put, we shouldn't have an issue just doing the bpf_prog_get() + prog->type != type check, but actually not taking the ref at all (due to being in fdget() / fdput() section of the bpf fd) is even cleaner and makes the diff smaller as well, so just go for that. Callsites are changed to make use of the new helper where possible. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 749549888b86..b3336b4f5d04 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -218,6 +218,7 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); +struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); @@ -277,6 +278,12 @@ static inline struct bpf_prog *bpf_prog_get(u32 ufd) return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, + enum bpf_prog_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void bpf_prog_put(struct bpf_prog *prog) { } -- cgit v1.2.3 From db1bb44c4c7e8d49ed674dc59e5222d99c698088 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:44 -0400 Subject: SUNRPC: Don't allocate a full sockaddr_storage for tracing We're always tracing IPv4 or IPv6 addresses, so we can save a lot of space on the ringbuffer by allocating the correct sockaddr size. Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Fixes: 83a712e0afef "sunrpc: add some tracepoints around ..." Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 47 +++++++++++++++++++++++++++++++------------ 1 file changed, 34 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 003dca933803..5664ca07c9c7 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -529,20 +529,27 @@ TRACE_EVENT(svc_xprt_do_enqueue, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) - __field_struct(struct sockaddr_storage, ss) __field(int, pid) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( __entry->xprt = xprt; - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); __entry->pid = rqst? rqst->rq_task->pid : 0; - __entry->flags = xprt ? xprt->xpt_flags : 0; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->pid, show_svc_xprt_flags(__entry->flags)) ); @@ -553,18 +560,25 @@ TRACE_EVENT(svc_xprt_dequeue, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) - __field_struct(struct sockaddr_storage, ss) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( - __entry->xprt = xprt, - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); - __entry->flags = xprt ? xprt->xpt_flags : 0; + __entry->xprt = xprt; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, show_svc_xprt_flags(__entry->flags)) ); @@ -592,19 +606,26 @@ TRACE_EVENT(svc_handle_xprt, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) __field(int, len) - __field_struct(struct sockaddr_storage, ss) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( __entry->xprt = xprt; - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); __entry->len = len; - __entry->flags = xprt ? xprt->xpt_flags : 0; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->len, show_svc_xprt_flags(__entry->flags)) ); #endif /* _TRACE_SUNRPC_H */ -- cgit v1.2.3 From 1f3fe7ebf6136c341012db9f554d4caa566fcbaa Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 30 Jun 2016 10:28:42 -0700 Subject: cgroup: Add cgroup_get_from_fd Add a helper function to get a cgroup2 from a fd. It will be stored in a bpf array (BPF_MAP_TYPE_CGROUP_ARRAY) which will be introduced in the later patch. Signed-off-by: Martin KaFai Lau Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Tejun Heo Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/cgroup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index a20320c666fd..984f73b719a9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -87,6 +87,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); +struct cgroup *cgroup_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); -- cgit v1.2.3 From 4ed8ec521ed57c4e207ad464ca0388776de74d4b Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 30 Jun 2016 10:28:43 -0700 Subject: cgroup: bpf: Add BPF_MAP_TYPE_CGROUP_ARRAY Add a BPF_MAP_TYPE_CGROUP_ARRAY and its bpf_map_ops's implementations. To update an element, the caller is expected to obtain a cgroup2 backed fd by open(cgroup2_dir) and then update the array with that fd. Signed-off-by: Martin KaFai Lau Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Tejun Heo Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index be6ac1291680..26c04be32003 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { -- cgit v1.2.3 From 4a482f34afcc162d8456f449b137ec2a95be60d8 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 30 Jun 2016 10:28:44 -0700 Subject: cgroup: bpf: Add bpf_skb_in_cgroup_proto Adds a bpf helper, bpf_skb_in_cgroup, to decide if a skb->sk belongs to a descendant of a cgroup2. It is similar to the feature added in netfilter: commit c38c4597e4bf ("netfilter: implement xt_cgroup cgroup2 path match") The user is expected to populate a BPF_MAP_TYPE_CGROUP_ARRAY which will be used by the bpf_skb_in_cgroup. Modifications to the bpf verifier is to ensure BPF_MAP_TYPE_CGROUP_ARRAY and bpf_skb_in_cgroup() are always used together. Signed-off-by: Martin KaFai Lau Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Tejun Heo Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 26c04be32003..f44504d875e2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -337,6 +337,17 @@ enum bpf_func_id { */ BPF_FUNC_skb_change_type, + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From e380538529e83c5d3fd27e8cbfcc1f9799cb6bbb Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Wed, 22 Jun 2016 11:45:52 -0400 Subject: power_supply: fix return value of get_property power_supply_get_property() should ideally return -EAGAIN if it is called while the power_supply is being registered. There was no way previously to determine if use_cnt == 0 meant that the power_supply wasn't fully registered yet, or if it had already been unregistered. Add a new boolean to the power_supply struct to simply show if registration is completed. Lastly, modify the check in power_supply_show_property() to also ignore -EAGAIN when so it doesn't complain about not returning the property. Signed-off-by: Rhyland Klein Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 751061790626..3965503315ef 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -248,6 +248,7 @@ struct power_supply { struct delayed_work deferred_register_work; spinlock_t changed_lock; bool changed; + bool initialized; atomic_t use_cnt; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; -- cgit v1.2.3 From a4b3518d146f150d633f7dc815bb8ee2fbc162e9 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Thu, 30 Jun 2016 17:31:13 +0800 Subject: clk: core: support clocks which requires parents enable (part 1) On Freescale i.MX7D platform, all clocks operations, including enable/disable, rate change and re-parent, requires its parent clock enable. Current clock core can not support it well. This patch introduce a new flag CLK_OPS_PARENT_ENABLE to handle this special case in clock core that enable its parent clock firstly for each operation and disable it later after operation complete. The patch part 1 fixes the possible disabling clocks while its parent is off during kernel booting phase in clk_disable_unused_subtree(). Before the completion of kernel booting, clock tree is still not built completely, there may be a case that the child clock is on but its parent is off which could be caused by either HW initial reset state or bootloader initialization. Taking bootloader as an example, we may enable all clocks in HW by default. And during kernel booting time, the parent clock could be disabled in its driver probe due to calling clk_prepare_enable and clk_disable_unprepare. Because it's child clock is only enabled in HW while its SW usecount in clock tree is still 0, so clk_disable of parent clock will gate the parent clock in both HW and SW usecount ultimately. Then there will be a child clock is still on in HW but its parent is already off. Later in clk_disable_unused(), this clock disable accessing while its parent off will cause system hang due to the limitation of HW which must require its parent on. This patch simply enables the parent clock first before disabling if flag CLK_OPS_PARENT_ENABLE is set in clk_disable_unused_subtree(). This is a simple solution and only affects booting time. After kernel booting up the clock tree is already created, there will be no case that child is off but its parent is off. So no need do this checking for normal clk_disable() later. Cc: Michael Turquette Cc: Stephen Boyd Cc: Shawn Guo Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index eeb2e69ee727..a39c0c530778 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -33,6 +33,8 @@ #define CLK_RECALC_NEW_RATES BIT(9) /* recalc rates after notifications */ #define CLK_SET_RATE_UNGATE BIT(10) /* clock needs to run to set rate */ #define CLK_IS_CRITICAL BIT(11) /* do not gate, ever */ +/* parents need enable during gate/ungate, set rate and re-parent */ +#define CLK_OPS_PARENT_ENABLE BIT(12) struct clk; struct clk_hw; -- 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 --- include/linux/extcon/extcon-adc-jack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') 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 acbc2004d7129a1ecf02414c1da8808bdc06d5a2 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Fri, 1 Jul 2016 14:50:58 +0300 Subject: net/mlx5: Introduce offloads steering namespace Add a new namespace (MLX5_FLOW_NAMESPACE_OFFLOADS) to be populated with flow steering rules that deal with rules that have have to be executed before the EN NIC steering rules are matched. The namespace is located after the bypass name-space and before the kernel name-space. Therefore, it precedes the HW processing done for rules set for the kernel NIC name-space. Under SRIOV, it would allow us to match on e-switch missed packet and forward them to the relevant VF representor TIR. Signed-off-by: Or Gerlitz Signed-off-by: Amir Vadai Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 4b7a107d9c19..6ad111938709 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -54,6 +54,7 @@ static inline void build_leftovers_ft_param(int *priority, enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, + MLX5_FLOW_NAMESPACE_OFFLOADS, MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, -- cgit v1.2.3 From 08f4b5918b2d6b491f0403cc1886f5cdccef89bb Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Fri, 1 Jul 2016 14:51:01 +0300 Subject: net/devlink: Add E-Switch mode control Add the commands to set and show the mode of SRIOV E-Switch, two modes are supported: * legacy: operating in the "old" L2 based mode (DMAC --> VF vport) * switchdev: the E-Switch is referred to as whitebox switch configured using standard tools such as tc, bridge, openvswitch etc. To allow working with the tools, for each VF, a VF representor netdevice is created by the E-Switch manager vendor device driver instance (e.g PF). Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/devlink.h | 3 +++ include/uapi/linux/devlink.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 1d45b61cb320..c99ffe8cef3c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -90,6 +90,9 @@ struct devlink_ops { u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); + + int (*eswitch_mode_get)(struct devlink *devlink, u16 *p_mode); + int (*eswitch_mode_set)(struct devlink *devlink, u16 mode); }; static inline void *devlink_priv(struct devlink *devlink) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ba0073b26fa6..915bfa74458c 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -57,6 +57,8 @@ enum devlink_command { DEVLINK_CMD_SB_OCC_SNAPSHOT, DEVLINK_CMD_SB_OCC_MAX_CLEAR, + DEVLINK_CMD_ESWITCH_MODE_GET, + DEVLINK_CMD_ESWITCH_MODE_SET, /* add new commands above here */ __DEVLINK_CMD_MAX, @@ -95,6 +97,11 @@ enum devlink_sb_threshold_type { #define DEVLINK_SB_THRESHOLD_TO_ALPHA_MAX 20 +enum devlink_eswitch_mode { + DEVLINK_ESWITCH_MODE_LEGACY, + DEVLINK_ESWITCH_MODE_SWITCHDEV, +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -125,6 +132,7 @@ enum devlink_attr { DEVLINK_ATTR_SB_TC_INDEX, /* u16 */ DEVLINK_ATTR_SB_OCC_CUR, /* u32 */ DEVLINK_ATTR_SB_OCC_MAX, /* u32 */ + DEVLINK_ATTR_ESWITCH_MODE, /* u16 */ /* add new attributes above here, update the policy in devlink.c */ -- cgit v1.2.3 From b50d292b4399f4eb11e82d0430aacf62dd5d5365 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Fri, 1 Jul 2016 14:51:04 +0300 Subject: net/mlx5e: Create NIC global resources only once To allow creating more than one netdev over the same PCI function, we change the driver such that global NIC resources are created once and later be shared amongst all the mlx5e netdevs running over that port. Move the CQ UAR, PD (pdn), Transport Domain (tdn), MKey resources from being kept in the mlx5e priv part to a new resources structure (mlx5e_resources) placed under the mlx5_core device. This patch doesn't add any new functionality. Signed-off-by: Hadar Hen Zion Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 46260fdc5305..e22b3456b2ee 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -578,6 +578,18 @@ enum mlx5_pci_status { MLX5_PCI_STATUS_ENABLED, }; +struct mlx5_td { + struct list_head tirs_list; + u32 tdn; +}; + +struct mlx5e_resources { + struct mlx5_uar cq_uar; + u32 pdn; + struct mlx5_td td; + struct mlx5_core_mkey mkey; +}; + struct mlx5_core_dev { struct pci_dev *pdev; /* sync pci state */ @@ -602,6 +614,7 @@ struct mlx5_core_dev { struct mlx5_profile *profile; atomic_t num_qps; u32 issi; + struct mlx5e_resources mlx5e_res; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif -- 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 --- include/linux/iio/common/st_sensors.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') 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 e192be9d9a30555aae2ca1dc3aad37cba484cd4a Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 12 Jun 2016 18:13:36 -0400 Subject: random: replace non-blocking pool with a Chacha20-based CRNG The CRNG is faster, and we don't pretend to track entropy usage in the CRNG any more. Signed-off-by: Theodore Ts'o --- include/crypto/chacha20.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h index 274bbaeeed0f..20d20f681a72 100644 --- a/include/crypto/chacha20.h +++ b/include/crypto/chacha20.h @@ -16,6 +16,7 @@ struct chacha20_ctx { u32 key[8]; }; +void chacha20_block(u32 *state, void *stream); void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv); int crypto_chacha20_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keysize); -- cgit v1.2.3 From c37a2dfa67f7920b14ea77dc9f9f9660f7a1f6dd Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 24 Jun 2016 13:25:22 -0700 Subject: netfilter: Convert FWINV<[foo]> macros and uses to NF_INVF netfilter uses multiple FWINV #defines with identical form that hide a specific structure variable and dereference it with a invflags member. $ git grep "#define FWINV" include/linux/netfilter_bridge/ebtables.h:#define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) net/bridge/netfilter/ebtables.c:#define FWINV2(bool, invflg) ((bool) ^ !!(e->invflags & invflg)) net/ipv4/netfilter/arp_tables.c:#define FWINV(bool, invflg) ((bool) ^ !!(arpinfo->invflags & (invflg))) net/ipv4/netfilter/ip_tables.c:#define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg))) net/ipv6/netfilter/ip6_tables.c:#define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg))) net/netfilter/xt_tcpudp.c:#define FWINVTCP(bool, invflg) ((bool) ^ !!(tcpinfo->invflags & (invflg))) Consolidate these macros into a single NF_INVF macro. Miscellanea: o Neaten the alignment around these uses o A few lines are > 80 columns for intelligibility Signed-off-by: Joe Perches Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 4 ++++ include/linux/netfilter_bridge/ebtables.h | 2 -- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index dc4f58a3cdcc..e94e81ab2b58 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -6,6 +6,10 @@ #include #include +/* Test a struct->invflags and a boolean for inequality */ +#define NF_INVF(ptr, flag, boolean) \ + ((boolean) ^ !!((ptr)->invflags & (flag))) + /** * struct xt_action_param - parameters for matches/targets * diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2ea517c7c6b9..984b2112c77b 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -115,8 +115,6 @@ extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); -/* Used in the kernel match() functions */ -#define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ #define BASE_CHAIN (par->hook_mask & (1 << NF_BR_NUMHOOKS)) -- cgit v1.2.3 From 50926d82fa271fa76d5717b546a66f7b5703ff05 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 28 May 2016 11:27:11 +0100 Subject: KVM: arm/arm64: The GIC is dead, long live the GIC I don't think any single piece of the KVM/ARM code ever generated as much hatred as the GIC emulation. It was written by someone who had zero experience in modeling hardware (me), was riddled with design flaws, should have been scrapped and rewritten from scratch long before having a remote chance of reaching mainline, and yet we supported it for a good three years. No need to mention the names of those who suffered, the git log is singing their praises. Thankfully, we now have a much more maintainable implementation, and we can safely put the grumpy old GIC to rest. Fellow hackers, please raise your glass in memory of the GIC: The GIC is dead, long live the GIC! Signed-off-by: Marc Zyngier Signed-off-by: Christoffer Dall --- include/kvm/arm_vgic.h | 381 ++++++++++++++++-------------------------------- include/kvm/vgic/vgic.h | 246 ------------------------------- 2 files changed, 126 insertions(+), 501 deletions(-) delete mode 100644 include/kvm/vgic/vgic.h (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index da0a524802cb..12640378db98 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -1,6 +1,5 @@ /* - * Copyright (C) 2012 ARM Ltd. - * Author: Marc Zyngier + * Copyright (C) 2015, 2016 ARM Ltd. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -12,16 +11,10 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program. If not, see . */ - -#ifndef __ASM_ARM_KVM_VGIC_H -#define __ASM_ARM_KVM_VGIC_H - -#ifdef CONFIG_KVM_NEW_VGIC -#include -#else +#ifndef __KVM_ARM_VGIC_H +#define __KVM_ARM_VGIC_H #include #include @@ -29,248 +22,130 @@ #include #include #include -#include -#define VGIC_NR_IRQS_LEGACY 256 +#define VGIC_V3_MAX_CPUS 255 +#define VGIC_V2_MAX_CPUS 8 +#define VGIC_NR_IRQS_LEGACY 256 #define VGIC_NR_SGIS 16 #define VGIC_NR_PPIS 16 #define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS) +#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1) +#define VGIC_MAX_SPI 1019 +#define VGIC_MAX_RESERVED 1023 +#define VGIC_MIN_LPI 8192 -#define VGIC_V2_MAX_LRS (1 << 6) -#define VGIC_V3_MAX_LRS 16 -#define VGIC_MAX_IRQS 1024 -#define VGIC_V2_MAX_CPUS 8 -#define VGIC_V3_MAX_CPUS 255 - -#if (VGIC_NR_IRQS_LEGACY & 31) -#error "VGIC_NR_IRQS must be a multiple of 32" -#endif +enum vgic_type { + VGIC_V2, /* Good ol' GICv2 */ + VGIC_V3, /* New fancy GICv3 */ +}; -#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS) -#error "VGIC_NR_IRQS must be <= 1024" -#endif +/* same for all guests, as depending only on the _host's_ GIC model */ +struct vgic_global { + /* type of the host GIC */ + enum vgic_type type; -/* - * The GIC distributor registers describing interrupts have two parts: - * - 32 per-CPU interrupts (SGI + PPI) - * - a bunch of shared interrupts (SPI) - */ -struct vgic_bitmap { - /* - * - One UL per VCPU for private interrupts (assumes UL is at - * least 32 bits) - * - As many UL as necessary for shared interrupts. - * - * The private interrupts are accessed via the "private" - * field, one UL per vcpu (the state for vcpu n is in - * private[n]). The shared interrupts are accessed via the - * "shared" pointer (IRQn state is at bit n-32 in the bitmap). - */ - unsigned long *private; - unsigned long *shared; -}; + /* Physical address of vgic virtual cpu interface */ + phys_addr_t vcpu_base; -struct vgic_bytemap { - /* - * - 8 u32 per VCPU for private interrupts - * - As many u32 as necessary for shared interrupts. - * - * The private interrupts are accessed via the "private" - * field, (the state for vcpu n is in private[n*8] to - * private[n*8 + 7]). The shared interrupts are accessed via - * the "shared" pointer (IRQn state is at byte (n-32)%4 of the - * shared[(n-32)/4] word). - */ - u32 *private; - u32 *shared; -}; + /* virtual control interface mapping */ + void __iomem *vctrl_base; -struct kvm_vcpu; + /* Number of implemented list registers */ + int nr_lr; -enum vgic_type { - VGIC_V2, /* Good ol' GICv2 */ - VGIC_V3, /* New fancy GICv3 */ -}; + /* Maintenance IRQ number */ + unsigned int maint_irq; -#define LR_STATE_PENDING (1 << 0) -#define LR_STATE_ACTIVE (1 << 1) -#define LR_STATE_MASK (3 << 0) -#define LR_EOI_INT (1 << 2) -#define LR_HW (1 << 3) + /* maximum number of VCPUs allowed (GICv2 limits us to 8) */ + int max_gic_vcpus; -struct vgic_lr { - unsigned irq:10; - union { - unsigned hwirq:10; - unsigned source:3; - }; - unsigned state:4; + /* Only needed for the legacy KVM_CREATE_IRQCHIP */ + bool can_emulate_gicv2; }; -struct vgic_vmcr { - u32 ctlr; - u32 abpr; - u32 bpr; - u32 pmr; -}; +extern struct vgic_global kvm_vgic_global_state; -struct vgic_ops { - struct vgic_lr (*get_lr)(const struct kvm_vcpu *, int); - void (*set_lr)(struct kvm_vcpu *, int, struct vgic_lr); - u64 (*get_elrsr)(const struct kvm_vcpu *vcpu); - u64 (*get_eisr)(const struct kvm_vcpu *vcpu); - void (*clear_eisr)(struct kvm_vcpu *vcpu); - u32 (*get_interrupt_status)(const struct kvm_vcpu *vcpu); - void (*enable_underflow)(struct kvm_vcpu *vcpu); - void (*disable_underflow)(struct kvm_vcpu *vcpu); - void (*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); - void (*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr); - void (*enable)(struct kvm_vcpu *vcpu); -}; +#define VGIC_V2_MAX_LRS (1 << 6) +#define VGIC_V3_MAX_LRS 16 +#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) -struct vgic_params { - /* vgic type */ - enum vgic_type type; - /* Physical address of vgic virtual cpu interface */ - phys_addr_t vcpu_base; - /* Number of list registers */ - u32 nr_lr; - /* Interrupt number */ - unsigned int maint_irq; - /* Virtual control interface base address */ - void __iomem *vctrl_base; - int max_gic_vcpus; - /* Only needed for the legacy KVM_CREATE_IRQCHIP */ - bool can_emulate_gicv2; +enum vgic_irq_config { + VGIC_CONFIG_EDGE = 0, + VGIC_CONFIG_LEVEL }; -struct vgic_vm_ops { - bool (*queue_sgi)(struct kvm_vcpu *, int irq); - void (*add_sgi_source)(struct kvm_vcpu *, int irq, int source); - int (*init_model)(struct kvm *); - int (*map_resources)(struct kvm *, const struct vgic_params *); +struct vgic_irq { + spinlock_t irq_lock; /* Protects the content of the struct */ + struct list_head ap_list; + + struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU + * SPIs and LPIs: The VCPU whose ap_list + * this is queued on. + */ + + struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should + * be sent to, as a result of the + * targets reg (v2) or the + * affinity reg (v3). + */ + + u32 intid; /* Guest visible INTID */ + bool pending; + bool line_level; /* Level only */ + bool soft_pending; /* Level only */ + bool active; /* not used for LPIs */ + bool enabled; + bool hw; /* Tied to HW IRQ */ + u32 hwintid; /* HW INTID number */ + union { + u8 targets; /* GICv2 target VCPUs mask */ + u32 mpidr; /* GICv3 target VCPU */ + }; + u8 source; /* GICv2 SGIs only */ + u8 priority; + enum vgic_irq_config config; /* Level or edge */ }; +struct vgic_register_region; + struct vgic_io_device { - gpa_t addr; - int len; - const struct vgic_io_range *reg_ranges; + gpa_t base_addr; struct kvm_vcpu *redist_vcpu; + const struct vgic_register_region *regions; + int nr_regions; struct kvm_io_device dev; }; -struct irq_phys_map { - u32 virt_irq; - u32 phys_irq; -}; - -struct irq_phys_map_entry { - struct list_head entry; - struct rcu_head rcu; - struct irq_phys_map map; -}; - struct vgic_dist { - spinlock_t lock; bool in_kernel; bool ready; + bool initialized; /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */ u32 vgic_model; - int nr_cpus; - int nr_irqs; + int nr_spis; + /* TODO: Consider moving to global state */ /* Virtual control interface mapping */ void __iomem *vctrl_base; - /* Distributor and vcpu interface mapping in the guest */ - phys_addr_t vgic_dist_base; - /* GICv2 and GICv3 use different mapped register blocks */ + /* base addresses in guest physical address space: */ + gpa_t vgic_dist_base; /* distributor */ union { - phys_addr_t vgic_cpu_base; - phys_addr_t vgic_redist_base; + /* either a GICv2 CPU interface */ + gpa_t vgic_cpu_base; + /* or a number of GICv3 redistributor regions */ + gpa_t vgic_redist_base; }; - /* Distributor enabled */ - u32 enabled; - - /* Interrupt enabled (one bit per IRQ) */ - struct vgic_bitmap irq_enabled; - - /* Level-triggered interrupt external input is asserted */ - struct vgic_bitmap irq_level; - - /* - * Interrupt state is pending on the distributor - */ - struct vgic_bitmap irq_pending; - - /* - * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered - * interrupts. Essentially holds the state of the flip-flop in - * Figure 4-10 on page 4-101 in ARM IHI 0048B.b. - * Once set, it is only cleared for level-triggered interrupts on - * guest ACKs (when we queue it) or writes to GICD_ICPENDRn. - */ - struct vgic_bitmap irq_soft_pend; - - /* Level-triggered interrupt queued on VCPU interface */ - struct vgic_bitmap irq_queued; - - /* Interrupt was active when unqueue from VCPU interface */ - struct vgic_bitmap irq_active; + /* distributor enabled */ + bool enabled; - /* Interrupt priority. Not used yet. */ - struct vgic_bytemap irq_priority; + struct vgic_irq *spis; - /* Level/edge triggered */ - struct vgic_bitmap irq_cfg; - - /* - * Source CPU per SGI and target CPU: - * - * Each byte represent a SGI observable on a VCPU, each bit of - * this byte indicating if the corresponding VCPU has - * generated this interrupt. This is a GICv2 feature only. - * - * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are - * the SGIs observable on VCPUn. - */ - u8 *irq_sgi_sources; - - /* - * Target CPU for each SPI: - * - * Array of available SPI, each byte indicating the target - * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32]. - */ - u8 *irq_spi_cpu; - - /* - * Reverse lookup of irq_spi_cpu for faster compute pending: - * - * Array of bitmaps, one per VCPU, describing if IRQn is - * routed to a particular VCPU. - */ - struct vgic_bitmap *irq_spi_target; - - /* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */ - u32 *irq_spi_mpidr; - - /* Bitmap indicating which CPU has something pending */ - unsigned long *irq_pending_on_cpu; - - /* Bitmap indicating which CPU has active IRQs */ - unsigned long *irq_active_on_cpu; - - struct vgic_vm_ops vm_ops; struct vgic_io_device dist_iodev; struct vgic_io_device *redist_iodevs; - - /* Virtual irq to hwirq mapping */ - spinlock_t irq_phys_map_lock; - struct list_head irq_phys_map_list; }; struct vgic_v2_cpu_if { @@ -298,78 +173,74 @@ struct vgic_v3_cpu_if { }; struct vgic_cpu { - /* Pending/active/both interrupts on this VCPU */ - DECLARE_BITMAP(pending_percpu, VGIC_NR_PRIVATE_IRQS); - DECLARE_BITMAP(active_percpu, VGIC_NR_PRIVATE_IRQS); - DECLARE_BITMAP(pend_act_percpu, VGIC_NR_PRIVATE_IRQS); - - /* Pending/active/both shared interrupts, dynamically sized */ - unsigned long *pending_shared; - unsigned long *active_shared; - unsigned long *pend_act_shared; - /* CPU vif control registers for world switch */ union { struct vgic_v2_cpu_if vgic_v2; struct vgic_v3_cpu_if vgic_v3; }; - /* Protected by the distributor's irq_phys_map_lock */ - struct list_head irq_phys_map_list; - - u64 live_lrs; -}; + unsigned int used_lrs; + struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS]; -#define LR_EMPTY 0xff + spinlock_t ap_list_lock; /* Protects the ap_list */ -#define INT_STATUS_EOI (1 << 0) -#define INT_STATUS_UNDERFLOW (1 << 1) + /* + * List of IRQs that this VCPU should consider because they are either + * Active or Pending (hence the name; AP list), or because they recently + * were one of the two and need to be migrated off this list to another + * VCPU. + */ + struct list_head ap_list_head; -struct kvm; -struct kvm_vcpu; + u64 live_lrs; +}; int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); -int kvm_vgic_hyp_init(void); -int kvm_vgic_map_resources(struct kvm *kvm); -int kvm_vgic_get_max_vcpus(void); void kvm_vgic_early_init(struct kvm *kvm); int kvm_vgic_create(struct kvm *kvm, u32 type); void kvm_vgic_destroy(struct kvm *kvm); void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu); void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); -void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); -void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); -int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, +int kvm_vgic_map_resources(struct kvm *kvm); +int kvm_vgic_hyp_init(void); + +int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, bool level); -int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, - unsigned int virt_irq, bool level); -void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); -int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); -int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq); +int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid, + bool level); +int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq); bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq); +int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); + #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) -#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus)) +#define vgic_initialized(k) ((k)->arch.vgic.initialized) #define vgic_ready(k) ((k)->arch.vgic.ready) #define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \ - ((i) < (k)->arch.vgic.nr_irqs)) + ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) + +bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu); +void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); +void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); -int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info, - const struct vgic_ops **ops, - const struct vgic_params **params); #ifdef CONFIG_KVM_ARM_VGIC_V3 -int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info, - const struct vgic_ops **ops, - const struct vgic_params **params); +void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); #else -static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info, - const struct vgic_ops **ops, - const struct vgic_params **params) +static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg) { - return -ENODEV; } #endif -#endif /* old VGIC include */ -#endif +/** + * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW + * + * The host's GIC naturally limits the maximum amount of VCPUs a guest + * can use. + */ +static inline int kvm_vgic_get_max_vcpus(void) +{ + return kvm_vgic_global_state.max_gic_vcpus; +} + +#endif /* __KVM_ARM_VGIC_H */ diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h deleted file mode 100644 index 3fbd175265ae..000000000000 --- a/include/kvm/vgic/vgic.h +++ /dev/null @@ -1,246 +0,0 @@ -/* - * Copyright (C) 2015, 2016 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - */ -#ifndef __ASM_ARM_KVM_VGIC_VGIC_H -#define __ASM_ARM_KVM_VGIC_VGIC_H - -#include -#include -#include -#include -#include -#include - -#define VGIC_V3_MAX_CPUS 255 -#define VGIC_V2_MAX_CPUS 8 -#define VGIC_NR_IRQS_LEGACY 256 -#define VGIC_NR_SGIS 16 -#define VGIC_NR_PPIS 16 -#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS) -#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1) -#define VGIC_MAX_SPI 1019 -#define VGIC_MAX_RESERVED 1023 -#define VGIC_MIN_LPI 8192 - -enum vgic_type { - VGIC_V2, /* Good ol' GICv2 */ - VGIC_V3, /* New fancy GICv3 */ -}; - -/* same for all guests, as depending only on the _host's_ GIC model */ -struct vgic_global { - /* type of the host GIC */ - enum vgic_type type; - - /* Physical address of vgic virtual cpu interface */ - phys_addr_t vcpu_base; - - /* virtual control interface mapping */ - void __iomem *vctrl_base; - - /* Number of implemented list registers */ - int nr_lr; - - /* Maintenance IRQ number */ - unsigned int maint_irq; - - /* maximum number of VCPUs allowed (GICv2 limits us to 8) */ - int max_gic_vcpus; - - /* Only needed for the legacy KVM_CREATE_IRQCHIP */ - bool can_emulate_gicv2; -}; - -extern struct vgic_global kvm_vgic_global_state; - -#define VGIC_V2_MAX_LRS (1 << 6) -#define VGIC_V3_MAX_LRS 16 -#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) - -enum vgic_irq_config { - VGIC_CONFIG_EDGE = 0, - VGIC_CONFIG_LEVEL -}; - -struct vgic_irq { - spinlock_t irq_lock; /* Protects the content of the struct */ - struct list_head ap_list; - - struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU - * SPIs and LPIs: The VCPU whose ap_list - * this is queued on. - */ - - struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should - * be sent to, as a result of the - * targets reg (v2) or the - * affinity reg (v3). - */ - - u32 intid; /* Guest visible INTID */ - bool pending; - bool line_level; /* Level only */ - bool soft_pending; /* Level only */ - bool active; /* not used for LPIs */ - bool enabled; - bool hw; /* Tied to HW IRQ */ - u32 hwintid; /* HW INTID number */ - union { - u8 targets; /* GICv2 target VCPUs mask */ - u32 mpidr; /* GICv3 target VCPU */ - }; - u8 source; /* GICv2 SGIs only */ - u8 priority; - enum vgic_irq_config config; /* Level or edge */ -}; - -struct vgic_register_region; - -struct vgic_io_device { - gpa_t base_addr; - struct kvm_vcpu *redist_vcpu; - const struct vgic_register_region *regions; - int nr_regions; - struct kvm_io_device dev; -}; - -struct vgic_dist { - bool in_kernel; - bool ready; - bool initialized; - - /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */ - u32 vgic_model; - - int nr_spis; - - /* TODO: Consider moving to global state */ - /* Virtual control interface mapping */ - void __iomem *vctrl_base; - - /* base addresses in guest physical address space: */ - gpa_t vgic_dist_base; /* distributor */ - union { - /* either a GICv2 CPU interface */ - gpa_t vgic_cpu_base; - /* or a number of GICv3 redistributor regions */ - gpa_t vgic_redist_base; - }; - - /* distributor enabled */ - bool enabled; - - struct vgic_irq *spis; - - struct vgic_io_device dist_iodev; - struct vgic_io_device *redist_iodevs; -}; - -struct vgic_v2_cpu_if { - u32 vgic_hcr; - u32 vgic_vmcr; - u32 vgic_misr; /* Saved only */ - u64 vgic_eisr; /* Saved only */ - u64 vgic_elrsr; /* Saved only */ - u32 vgic_apr; - u32 vgic_lr[VGIC_V2_MAX_LRS]; -}; - -struct vgic_v3_cpu_if { -#ifdef CONFIG_KVM_ARM_VGIC_V3 - u32 vgic_hcr; - u32 vgic_vmcr; - u32 vgic_sre; /* Restored only, change ignored */ - u32 vgic_misr; /* Saved only */ - u32 vgic_eisr; /* Saved only */ - u32 vgic_elrsr; /* Saved only */ - u32 vgic_ap0r[4]; - u32 vgic_ap1r[4]; - u64 vgic_lr[VGIC_V3_MAX_LRS]; -#endif -}; - -struct vgic_cpu { - /* CPU vif control registers for world switch */ - union { - struct vgic_v2_cpu_if vgic_v2; - struct vgic_v3_cpu_if vgic_v3; - }; - - unsigned int used_lrs; - struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS]; - - spinlock_t ap_list_lock; /* Protects the ap_list */ - - /* - * List of IRQs that this VCPU should consider because they are either - * Active or Pending (hence the name; AP list), or because they recently - * were one of the two and need to be migrated off this list to another - * VCPU. - */ - struct list_head ap_list_head; - - u64 live_lrs; -}; - -int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); -void kvm_vgic_early_init(struct kvm *kvm); -int kvm_vgic_create(struct kvm *kvm, u32 type); -void kvm_vgic_destroy(struct kvm *kvm); -void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu); -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); -int kvm_vgic_map_resources(struct kvm *kvm); -int kvm_vgic_hyp_init(void); - -int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, - bool level); -int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid, - bool level); -int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq); -int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq); -bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq); - -int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); - -#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) -#define vgic_initialized(k) ((k)->arch.vgic.initialized) -#define vgic_ready(k) ((k)->arch.vgic.ready) -#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \ - ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) - -bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu); -void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); -void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); - -#ifdef CONFIG_KVM_ARM_VGIC_V3 -void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg); -#else -static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg) -{ -} -#endif - -/** - * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW - * - * The host's GIC naturally limits the maximum amount of VCPUs a guest - * can use. - */ -static inline int kvm_vgic_get_max_vcpus(void) -{ - return kvm_vgic_global_state.max_gic_vcpus; -} - -#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */ -- cgit v1.2.3 From f86dec94e3a86c992a637df1c301a4df25a85801 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Fri, 15 Apr 2016 18:14:25 +0200 Subject: NFC: hci: delete unused nfc_llc_get_rx_head_tail_room() It used to be EXPORTed, but then EXPORT usage was cleaned up (in 2012), without noticing that the function has no users at all (and curiously, never had any users). Delete it. While at it, remove non-static "inline" hints on nearby functions: these hints don't work across compilation units anyway, and these functions are not used in their .c file, thus they are never inlined. IOW: "inline" here does not help in any way. Signed-off-by: Denys Vlasenko CC: Samuel Ortiz CC: Christophe Ricard CC: linux-wireless@vger.kernel.org CC: linux-kernel@vger.kernel.org Signed-off-by: Samuel Ortiz --- include/net/nfc/llc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/nfc/llc.h b/include/net/nfc/llc.h index c25fbdee0d61..7ecb45757897 100644 --- a/include/net/nfc/llc.h +++ b/include/net/nfc/llc.h @@ -37,10 +37,6 @@ struct nfc_llc *nfc_llc_allocate(const char *name, struct nfc_hci_dev *hdev, int tx_tailroom, llc_failure_t llc_failure); void nfc_llc_free(struct nfc_llc *llc); -void nfc_llc_get_rx_head_tail_room(struct nfc_llc *llc, int *rx_headroom, - int *rx_tailroom); - - int nfc_llc_start(struct nfc_llc *llc); int nfc_llc_stop(struct nfc_llc *llc); void nfc_llc_rcv_from_drv(struct nfc_llc *llc, struct sk_buff *skb); -- 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 ++---- 1 file changed, 2 insertions(+), 4 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, -- 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 +++++++ 1 file changed, 7 insertions(+) (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) -- 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 --- include/linux/irq.h | 4 ++-- include/linux/irqdomain.h | 9 ++++++--- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') 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, -- 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 ++ 1 file changed, 2 insertions(+) (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 */ -- 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 ++++++++ 1 file changed, 8 insertions(+) (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 */ /* -- cgit v1.2.3 From 7854a44526de84142e367f08288c9f3a33c4c8ee Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Tue, 7 Jun 2016 16:21:52 +0200 Subject: NFC: digital: Add a delay between poll cycles This replaces the polling work struct with a delayed work struct and add a 10 ms delay between 2 poll cycles. This avoids to flood the device with 'switch off'/'switch on' commands. Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/net/nfc/digital.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index 0ae101eef0f4..506e3f6eabef 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -220,7 +220,7 @@ struct nfc_digital_dev { struct list_head cmd_queue; struct mutex cmd_lock; - struct work_struct poll_work; + struct delayed_work poll_work; u8 curr_protocol; u8 curr_rf_tech; -- cgit v1.2.3 From 09748a22f4ab7b0ab5a83c432f6e18f65f18e09b Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 9 May 2016 18:41:08 +0200 Subject: batman-adv: add generic netlink family for batman-adv debugfs is currently severely broken virtually everywhere in the kernel where files are dynamically added and removed (see http://lkml.iu.edu/hypermail/linux/kernel/1506.1/02196.html for some details). In addition to that, debugfs is not namespace-aware. Instead of adding new debugfs entries, the whole infrastructure should be moved to netlink. This will fix the long standing problem of large buffers for debug tables and hard to parse text files. Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: Strip down patch to only add genl family, add missing kerneldoc] Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 53 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) create mode 100644 include/uapi/linux/batman_adv.h (limited to 'include') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h new file mode 100644 index 000000000000..79f797281b87 --- /dev/null +++ b/include/uapi/linux/batman_adv.h @@ -0,0 +1,53 @@ +/* Copyright (C) 2016 B.A.T.M.A.N. contributors: + * + * Matthias Schiffer + * + * Permission to use, copy, modify, and/or distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ + +#ifndef _UAPI_LINUX_BATMAN_ADV_H_ +#define _UAPI_LINUX_BATMAN_ADV_H_ + +#define BATADV_NL_NAME "batadv" + +/** + * enum batadv_nl_attrs - batman-adv netlink attributes + * + * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors + * @__BATADV_ATTR_AFTER_LAST: internal use + * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available + * @BATADV_ATTR_MAX: highest attribute number currently defined + */ +enum batadv_nl_attrs { + BATADV_ATTR_UNSPEC, + /* add attributes above here, update the policy in netlink.c */ + __BATADV_ATTR_AFTER_LAST, + NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, + BATADV_ATTR_MAX = __BATADV_ATTR_AFTER_LAST - 1 +}; + +/** + * enum batadv_nl_commands - supported batman-adv netlink commands + * + * @BATADV_CMD_UNSPEC: unspecified command to catch errors + * @__BATADV_CMD_AFTER_LAST: internal use + * @BATADV_CMD_MAX: highest used command number + */ +enum batadv_nl_commands { + BATADV_CMD_UNSPEC, + /* add new commands above here */ + __BATADV_CMD_AFTER_LAST, + BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 +}; + +#endif /* _UAPI_LINUX_BATMAN_ADV_H_ */ -- cgit v1.2.3 From 5da0aef5e93591b373010c10f374c4161b37728c Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 9 May 2016 18:41:09 +0200 Subject: batman-adv: add netlink command to query generic mesh information files BATADV_CMD_GET_MESH_INFO is used to query basic information about a batman-adv softif (name, index and MAC address for both the softif and the primary hardif; routing algorithm; batman-adv version). Signed-off-by: Matthias Schiffer Signed-off-by: Andrew Lunn [sven.eckelmann@open-mesh.com: Reduce the number of changes to BATADV_CMD_GET_MESH_INFO, add missing kerneldoc, add policy for attributes] Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 79f797281b87..c39623c7109e 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -24,12 +24,28 @@ * enum batadv_nl_attrs - batman-adv netlink attributes * * @BATADV_ATTR_UNSPEC: unspecified attribute to catch errors + * @BATADV_ATTR_VERSION: batman-adv version string + * @BATADV_ATTR_ALGO_NAME: name of routing algorithm + * @BATADV_ATTR_MESH_IFINDEX: index of the batman-adv interface + * @BATADV_ATTR_MESH_IFNAME: name of the batman-adv interface + * @BATADV_ATTR_MESH_ADDRESS: mac address of the batman-adv interface + * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface + * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface + * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined */ enum batadv_nl_attrs { BATADV_ATTR_UNSPEC, + BATADV_ATTR_VERSION, + BATADV_ATTR_ALGO_NAME, + BATADV_ATTR_MESH_IFINDEX, + BATADV_ATTR_MESH_IFNAME, + BATADV_ATTR_MESH_ADDRESS, + BATADV_ATTR_HARD_IFINDEX, + BATADV_ATTR_HARD_IFNAME, + BATADV_ATTR_HARD_ADDRESS, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -40,11 +56,13 @@ enum batadv_nl_attrs { * enum batadv_nl_commands - supported batman-adv netlink commands * * @BATADV_CMD_UNSPEC: unspecified command to catch errors + * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ enum batadv_nl_commands { BATADV_CMD_UNSPEC, + BATADV_CMD_GET_MESH_INFO, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 -- cgit v1.2.3 From 33a3bb4a3345bb511f9c69c913da95d4693e2a4e Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Thu, 5 May 2016 13:09:43 +0200 Subject: batman-adv: throughput meter implementation The throughput meter module is a simple, kernel-space replacement for throughtput measurements tool like iperf and netperf. It is intended to approximate TCP behaviour. It is invoked through batctl: the protocol is connection oriented, with cumulative acknowledgment and a dynamic-size sliding window. The test *can* be interrupted by batctl. A receiver side timeout avoids unlimited waitings for sender packets: after one second of inactivity, the receiver abort the ongoing test. Based on a prototype from Edo Monticelli Signed-off-by: Antonio Quartulli Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batman_adv.h | 43 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index c39623c7109e..0fbf6fd4711b 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -20,6 +20,8 @@ #define BATADV_NL_NAME "batadv" +#define BATADV_NL_MCAST_GROUP_TPMETER "tpmeter" + /** * enum batadv_nl_attrs - batman-adv netlink attributes * @@ -32,6 +34,12 @@ * @BATADV_ATTR_HARD_IFINDEX: index of the non-batman-adv interface * @BATADV_ATTR_HARD_IFNAME: name of the non-batman-adv interface * @BATADV_ATTR_HARD_ADDRESS: mac address of the non-batman-adv interface + * @BATADV_ATTR_ORIG_ADDRESS: originator mac address + * @BATADV_ATTR_TPMETER_RESULT: result of run (see batadv_tp_meter_status) + * @BATADV_ATTR_TPMETER_TEST_TIME: time (msec) the run took + * @BATADV_ATTR_TPMETER_BYTES: amount of acked bytes during run + * @BATADV_ATTR_TPMETER_COOKIE: session cookie to match tp_meter session + * @BATADV_ATTR_PAD: attribute used for padding for 64-bit alignment * @__BATADV_ATTR_AFTER_LAST: internal use * @NUM_BATADV_ATTR: total number of batadv_nl_attrs available * @BATADV_ATTR_MAX: highest attribute number currently defined @@ -46,6 +54,12 @@ enum batadv_nl_attrs { BATADV_ATTR_HARD_IFINDEX, BATADV_ATTR_HARD_IFNAME, BATADV_ATTR_HARD_ADDRESS, + BATADV_ATTR_ORIG_ADDRESS, + BATADV_ATTR_TPMETER_RESULT, + BATADV_ATTR_TPMETER_TEST_TIME, + BATADV_ATTR_TPMETER_BYTES, + BATADV_ATTR_TPMETER_COOKIE, + BATADV_ATTR_PAD, /* add attributes above here, update the policy in netlink.c */ __BATADV_ATTR_AFTER_LAST, NUM_BATADV_ATTR = __BATADV_ATTR_AFTER_LAST, @@ -57,15 +71,44 @@ enum batadv_nl_attrs { * * @BATADV_CMD_UNSPEC: unspecified command to catch errors * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv device + * @BATADV_CMD_TP_METER: Start a tp meter session + * @BATADV_CMD_TP_METER_CANCEL: Cancel a tp meter session * @__BATADV_CMD_AFTER_LAST: internal use * @BATADV_CMD_MAX: highest used command number */ enum batadv_nl_commands { BATADV_CMD_UNSPEC, BATADV_CMD_GET_MESH_INFO, + BATADV_CMD_TP_METER, + BATADV_CMD_TP_METER_CANCEL, /* add new commands above here */ __BATADV_CMD_AFTER_LAST, BATADV_CMD_MAX = __BATADV_CMD_AFTER_LAST - 1 }; +/** + * enum batadv_tp_meter_reason - reason of a tp meter test run stop + * @BATADV_TP_REASON_COMPLETE: sender finished tp run + * @BATADV_TP_REASON_CANCEL: sender was stopped during run + * @BATADV_TP_REASON_DST_UNREACHABLE: receiver could not be reached or didn't + * answer + * @BATADV_TP_REASON_RESEND_LIMIT: (unused) sender retry reached limit + * @BATADV_TP_REASON_ALREADY_ONGOING: test to or from the same node already + * ongoing + * @BATADV_TP_REASON_MEMORY_ERROR: test was stopped due to low memory + * @BATADV_TP_REASON_CANT_SEND: failed to send via outgoing interface + * @BATADV_TP_REASON_TOO_MANY: too many ongoing sessions + */ +enum batadv_tp_meter_reason { + BATADV_TP_REASON_COMPLETE = 3, + BATADV_TP_REASON_CANCEL = 4, + /* error status >= 128 */ + BATADV_TP_REASON_DST_UNREACHABLE = 128, + BATADV_TP_REASON_RESEND_LIMIT = 129, + BATADV_TP_REASON_ALREADY_ONGOING = 130, + BATADV_TP_REASON_MEMORY_ERROR = 131, + BATADV_TP_REASON_CANT_SEND = 132, + BATADV_TP_REASON_TOO_MANY = 133, +}; + #endif /* _UAPI_LINUX_BATMAN_ADV_H_ */ -- 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 --- include/linux/phy/phy.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') 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 8b10cab64c134ffbffac96edd1899d303d3afcac Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 2 Jul 2016 06:43:14 -0400 Subject: net: simplify and make pkt_type_ok() available for other users Suggested-by: Daniel Borkmann Signed-off-by: Jamal Hadi Salim Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dc0fca747c5e..638b0e004310 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include #include /* The interface for checksum offload between the stack and networking drivers @@ -881,6 +882,15 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb) return (struct rtable *)skb_dst(skb); } +/* For mangling skb->pkt_type from user space side from applications + * such as nft, tc, etc, we only allow a conservative subset of + * possible pkt_types to be set. +*/ +static inline bool skb_pkt_type_ok(u32 ptype) +{ + return ptype <= PACKET_OTHERHOST; +} + void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_tx_error(struct sk_buff *skb); -- cgit v1.2.3 From ff202ee1ed8f032f05b80b541664cf02e75d7080 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 2 Jul 2016 06:43:15 -0400 Subject: net sched actions: skbedit add support for mod-ing skb pkt_type Extremely useful for setting packet type to host so i dont have to modify the dst mac address using pedit (which requires that i know the mac address) Example usage: tc filter add dev eth0 parent ffff: protocol ip pref 9 u32 \ match ip src 5.5.5.5/32 \ flowid 1:5 action skbedit ptype host This will tag all packets incoming from 5.5.5.5 with type PACKET_HOST Signed-off-by: Jamal Hadi Salim Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/net/tc_act/tc_skbedit.h | 10 +++++----- include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index b496d5ad7d42..d01a5d40cfb5 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -24,11 +24,11 @@ struct tcf_skbedit { struct tcf_common common; - u32 flags; - u32 priority; - u32 mark; - u16 queue_mapping; - /* XXX: 16-bit pad here? */ + u32 flags; + u32 priority; + u32 mark; + u16 queue_mapping; + u16 ptype; }; #define to_skbedit(a) \ container_of(a->priv, struct tcf_skbedit, common) diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index fecb5cc48c40..a4d00c608d8f 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -27,6 +27,7 @@ #define SKBEDIT_F_PRIORITY 0x1 #define SKBEDIT_F_QUEUE_MAPPING 0x2 #define SKBEDIT_F_MARK 0x4 +#define SKBEDIT_F_PTYPE 0x8 struct tc_skbedit { tc_gen; @@ -40,6 +41,7 @@ enum { TCA_SKBEDIT_QUEUE_MAPPING, TCA_SKBEDIT_MARK, TCA_SKBEDIT_PAD, + TCA_SKBEDIT_PTYPE, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) -- cgit v1.2.3 From 13c5c240f789bbd2bcacb14a23771491485ae61f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 3 Jul 2016 01:28:47 +0200 Subject: bpf: add bpf_get_hash_recalc helper If skb_clear_hash() was invoked due to mangling of relevant headers and BPF program needs skb->hash later on, we can add a helper to trigger hash recalculation via bpf_get_hash_recalc(). The helper will return the newly retrieved hash directly, but later access can also be done via skb context again through skb->hash directly (inline) without needing to call the helper once more. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f44504d875e2..c14ca1cd6297 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -348,6 +348,15 @@ enum bpf_func_id { * < 0 error */ BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From 7ce856aaaf13a5dc969ac5f998e5daaf1abe4cd2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 4 Jul 2016 08:23:12 +0200 Subject: mlxsw: spectrum: Add couple of lower device helper functions Add functions that iterate over lower devices and find port device. As a dependency add netdev_for_each_all_lower_dev and netdev_for_each_all_lower_dev_rcu macro with netdev_all_lower_get_next and netdev_all_lower_get_next_rcu shelpers. Also, add functions to return mlxsw struct according to lower device found and mlxsw_port struct with a reference to lower device. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dc2ec74122a..0c6ee2c5099f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3804,12 +3804,30 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); + #define netdev_for_each_lower_dev(dev, ldev, iter) \ for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) +struct net_device *netdev_all_lower_get_next(struct net_device *dev, + struct list_head **iter); +struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, + struct list_head **iter); + +#define netdev_for_each_all_lower_dev(dev, ldev, iter) \ + for (iter = (dev)->all_adj_list.lower.next, \ + ldev = netdev_all_lower_get_next(dev, &(iter)); \ + ldev; \ + ldev = netdev_all_lower_get_next(dev, &(iter))) + +#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \ + for (iter = (dev)->all_adj_list.lower.next, \ + ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \ + ldev; \ + ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) + void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); -- cgit v1.2.3 From c5bb17302e734967822be559cf661704b707b4ed Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 4 Jul 2016 17:23:05 +0300 Subject: net/mlx5: Refactor mlx5_add_flow_rule Reduce the set of arguments passed to mlx5_add_flow_rule by introducing flow_spec structure. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6ad111938709..d22fe7e5a39a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -68,6 +68,12 @@ struct mlx5_flow_group; struct mlx5_flow_rule; struct mlx5_flow_namespace; +struct mlx5_flow_spec { + u8 match_criteria_enable; + u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; + u32 match_value[MLX5_ST_SZ_DW(fte_match_param)]; +}; + struct mlx5_flow_destination { enum mlx5_flow_destination_type type; union { @@ -116,9 +122,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); */ struct mlx5_flow_rule * mlx5_add_flow_rule(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, + struct mlx5_flow_spec *spec, u32 action, u32 flow_tag, struct mlx5_flow_destination *dest); -- cgit v1.2.3 From fba53f7b571925b8a0d59d460ad6de1fda928a3e Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 4 Jul 2016 17:23:06 +0300 Subject: net/mlx5: Introduce mlx5_flow_steering structure Instead of having all steering private name spaces and steering module fields flat in mlx5_core_priv, we wrap them in mlx5_flow_steering for better modularity and API exposure. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e22b3456b2ee..f21c45941887 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,14 +550,10 @@ struct mlx5_priv { struct list_head ctx_list; spinlock_t ctx_lock; + struct mlx5_flow_steering *steering; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; unsigned long pci_dev_data; - struct mlx5_flow_root_namespace *root_ns; - struct mlx5_flow_root_namespace *fdb_root_ns; - struct mlx5_flow_root_namespace *esw_egress_root_ns; - struct mlx5_flow_root_namespace *esw_ingress_root_ns; - struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; }; -- cgit v1.2.3 From 6dc6071cfcde6cf687f8d288c9cef9ee6ee24dc7 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 4 Jul 2016 17:23:08 +0300 Subject: net/mlx5e: Add ethtool flow steering support Implement etrhtool set_rxnfc callback to support ethtool flow spec direct steering. This patch adds only the support of ether flow type spec. L3/L4 flow specs support will be added in downstream patches. Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index d22fe7e5a39a..e036d6030867 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -55,6 +55,7 @@ static inline void build_leftovers_ft_param(int *priority, enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, MLX5_FLOW_NAMESPACE_OFFLOADS, + MLX5_FLOW_NAMESPACE_ETHTOOL, MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, -- cgit v1.2.3 From a5d5639f812f24f10c7affaf0d537c204fdea986 Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Mon, 27 Jun 2016 09:18:03 +0530 Subject: ASoC: dapm: Export snd_soc_dapm_new_control This is useful outside the core, when one dapm element is added at a time. Signed-off-by: Subhransu S. Prusty Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- include/sound/soc-dapm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 3101d53468aa..0efeb38ae059 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -382,6 +382,9 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol, int snd_soc_dapm_new_controls(struct snd_soc_dapm_context *dapm, const struct snd_soc_dapm_widget *widget, int num); +struct snd_soc_dapm_widget *snd_soc_dapm_new_control( + struct snd_soc_dapm_context *dapm, + const struct snd_soc_dapm_widget *widget); int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm, struct snd_soc_dai *dai); int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card); -- cgit v1.2.3 From fd1e71e2481445e6a771b9dbd827523337353a3c Mon Sep 17 00:00:00 2001 From: Alexandre TORGUE Date: Tue, 5 Jul 2016 15:40:15 +0200 Subject: includes: dt-bindings: Add STM32F746 pinctrl DT bindings Signed-off-by: Maxime Coquelin Signed-off-by: Alexandre TORGUE Signed-off-by: Linus Walleij --- include/dt-bindings/pinctrl/stm32f746-pinfunc.h | 1324 +++++++++++++++++++++++ 1 file changed, 1324 insertions(+) create mode 100644 include/dt-bindings/pinctrl/stm32f746-pinfunc.h (limited to 'include') diff --git a/include/dt-bindings/pinctrl/stm32f746-pinfunc.h b/include/dt-bindings/pinctrl/stm32f746-pinfunc.h new file mode 100644 index 000000000000..6348c6a830e9 --- /dev/null +++ b/include/dt-bindings/pinctrl/stm32f746-pinfunc.h @@ -0,0 +1,1324 @@ +#ifndef _DT_BINDINGS_STM32F746_PINFUNC_H +#define _DT_BINDINGS_STM32F746_PINFUNC_H + +#define STM32F746_PA0_FUNC_GPIO 0x0 +#define STM32F746_PA0_FUNC_TIM2_CH1_TIM2_ETR 0x2 +#define STM32F746_PA0_FUNC_TIM5_CH1 0x3 +#define STM32F746_PA0_FUNC_TIM8_ETR 0x4 +#define STM32F746_PA0_FUNC_USART2_CTS 0x8 +#define STM32F746_PA0_FUNC_UART4_TX 0x9 +#define STM32F746_PA0_FUNC_SAI2_SD_B 0xb +#define STM32F746_PA0_FUNC_ETH_MII_CRS 0xc +#define STM32F746_PA0_FUNC_EVENTOUT 0x10 +#define STM32F746_PA0_FUNC_ANALOG 0x11 + +#define STM32F746_PA1_FUNC_GPIO 0x100 +#define STM32F746_PA1_FUNC_TIM2_CH2 0x102 +#define STM32F746_PA1_FUNC_TIM5_CH2 0x103 +#define STM32F746_PA1_FUNC_USART2_RTS 0x108 +#define STM32F746_PA1_FUNC_UART4_RX 0x109 +#define STM32F746_PA1_FUNC_QUADSPI_BK1_IO3 0x10a +#define STM32F746_PA1_FUNC_SAI2_MCLK_B 0x10b +#define STM32F746_PA1_FUNC_ETH_MII_RX_CLK_ETH_RMII_REF_CLK 0x10c +#define STM32F746_PA1_FUNC_LCD_R2 0x10f +#define STM32F746_PA1_FUNC_EVENTOUT 0x110 +#define STM32F746_PA1_FUNC_ANALOG 0x111 + +#define STM32F746_PA2_FUNC_GPIO 0x200 +#define STM32F746_PA2_FUNC_TIM2_CH3 0x202 +#define STM32F746_PA2_FUNC_TIM5_CH3 0x203 +#define STM32F746_PA2_FUNC_TIM9_CH1 0x204 +#define STM32F746_PA2_FUNC_USART2_TX 0x208 +#define STM32F746_PA2_FUNC_SAI2_SCK_B 0x209 +#define STM32F746_PA2_FUNC_ETH_MDIO 0x20c +#define STM32F746_PA2_FUNC_LCD_R1 0x20f +#define STM32F746_PA2_FUNC_EVENTOUT 0x210 +#define STM32F746_PA2_FUNC_ANALOG 0x211 + +#define STM32F746_PA3_FUNC_GPIO 0x300 +#define STM32F746_PA3_FUNC_TIM2_CH4 0x302 +#define STM32F746_PA3_FUNC_TIM5_CH4 0x303 +#define STM32F746_PA3_FUNC_TIM9_CH2 0x304 +#define STM32F746_PA3_FUNC_USART2_RX 0x308 +#define STM32F746_PA3_FUNC_OTG_HS_ULPI_D0 0x30b +#define STM32F746_PA3_FUNC_ETH_MII_COL 0x30c +#define STM32F746_PA3_FUNC_LCD_B5 0x30f +#define STM32F746_PA3_FUNC_EVENTOUT 0x310 +#define STM32F746_PA3_FUNC_ANALOG 0x311 + +#define STM32F746_PA4_FUNC_GPIO 0x400 +#define STM32F746_PA4_FUNC_SPI1_NSS_I2S1_WS 0x406 +#define STM32F746_PA4_FUNC_SPI3_NSS_I2S3_WS 0x407 +#define STM32F746_PA4_FUNC_USART2_CK 0x408 +#define STM32F746_PA4_FUNC_OTG_HS_SOF 0x40d +#define STM32F746_PA4_FUNC_DCMI_HSYNC 0x40e +#define STM32F746_PA4_FUNC_LCD_VSYNC 0x40f +#define STM32F746_PA4_FUNC_EVENTOUT 0x410 +#define STM32F746_PA4_FUNC_ANALOG 0x411 + +#define STM32F746_PA5_FUNC_GPIO 0x500 +#define STM32F746_PA5_FUNC_TIM2_CH1_TIM2_ETR 0x502 +#define STM32F746_PA5_FUNC_TIM8_CH1N 0x504 +#define STM32F746_PA5_FUNC_SPI1_SCK_I2S1_CK 0x506 +#define STM32F746_PA5_FUNC_OTG_HS_ULPI_CK 0x50b +#define STM32F746_PA5_FUNC_LCD_R4 0x50f +#define STM32F746_PA5_FUNC_EVENTOUT 0x510 +#define STM32F746_PA5_FUNC_ANALOG 0x511 + +#define STM32F746_PA6_FUNC_GPIO 0x600 +#define STM32F746_PA6_FUNC_TIM1_BKIN 0x602 +#define STM32F746_PA6_FUNC_TIM3_CH1 0x603 +#define STM32F746_PA6_FUNC_TIM8_BKIN 0x604 +#define STM32F746_PA6_FUNC_SPI1_MISO 0x606 +#define STM32F746_PA6_FUNC_TIM13_CH1 0x60a +#define STM32F746_PA6_FUNC_DCMI_PIXCLK 0x60e +#define STM32F746_PA6_FUNC_LCD_G2 0x60f +#define STM32F746_PA6_FUNC_EVENTOUT 0x610 +#define STM32F746_PA6_FUNC_ANALOG 0x611 + +#define STM32F746_PA7_FUNC_GPIO 0x700 +#define STM32F746_PA7_FUNC_TIM1_CH1N 0x702 +#define STM32F746_PA7_FUNC_TIM3_CH2 0x703 +#define STM32F746_PA7_FUNC_TIM8_CH1N 0x704 +#define STM32F746_PA7_FUNC_SPI1_MOSI_I2S1_SD 0x706 +#define STM32F746_PA7_FUNC_TIM14_CH1 0x70a +#define STM32F746_PA7_FUNC_ETH_MII_RX_DV_ETH_RMII_CRS_DV 0x70c +#define STM32F746_PA7_FUNC_FMC_SDNWE 0x70d +#define STM32F746_PA7_FUNC_EVENTOUT 0x710 +#define STM32F746_PA7_FUNC_ANALOG 0x711 + +#define STM32F746_PA8_FUNC_GPIO 0x800 +#define STM32F746_PA8_FUNC_MCO1 0x801 +#define STM32F746_PA8_FUNC_TIM1_CH1 0x802 +#define STM32F746_PA8_FUNC_TIM8_BKIN2 0x804 +#define STM32F746_PA8_FUNC_I2C3_SCL 0x805 +#define STM32F746_PA8_FUNC_USART1_CK 0x808 +#define STM32F746_PA8_FUNC_OTG_FS_SOF 0x80b +#define STM32F746_PA8_FUNC_LCD_R6 0x80f +#define STM32F746_PA8_FUNC_EVENTOUT 0x810 +#define STM32F746_PA8_FUNC_ANALOG 0x811 + +#define STM32F746_PA9_FUNC_GPIO 0x900 +#define STM32F746_PA9_FUNC_TIM1_CH2 0x902 +#define STM32F746_PA9_FUNC_I2C3_SMBA 0x905 +#define STM32F746_PA9_FUNC_SPI2_SCK_I2S2_CK 0x906 +#define STM32F746_PA9_FUNC_USART1_TX 0x908 +#define STM32F746_PA9_FUNC_DCMI_D0 0x90e +#define STM32F746_PA9_FUNC_EVENTOUT 0x910 +#define STM32F746_PA9_FUNC_ANALOG 0x911 + +#define STM32F746_PA10_FUNC_GPIO 0xa00 +#define STM32F746_PA10_FUNC_TIM1_CH3 0xa02 +#define STM32F746_PA10_FUNC_USART1_RX 0xa08 +#define STM32F746_PA10_FUNC_OTG_FS_ID 0xa0b +#define STM32F746_PA10_FUNC_DCMI_D1 0xa0e +#define STM32F746_PA10_FUNC_EVENTOUT 0xa10 +#define STM32F746_PA10_FUNC_ANALOG 0xa11 + +#define STM32F746_PA11_FUNC_GPIO 0xb00 +#define STM32F746_PA11_FUNC_TIM1_CH4 0xb02 +#define STM32F746_PA11_FUNC_USART1_CTS 0xb08 +#define STM32F746_PA11_FUNC_CAN1_RX 0xb0a +#define STM32F746_PA11_FUNC_OTG_FS_DM 0xb0b +#define STM32F746_PA11_FUNC_LCD_R4 0xb0f +#define STM32F746_PA11_FUNC_EVENTOUT 0xb10 +#define STM32F746_PA11_FUNC_ANALOG 0xb11 + +#define STM32F746_PA12_FUNC_GPIO 0xc00 +#define STM32F746_PA12_FUNC_TIM1_ETR 0xc02 +#define STM32F746_PA12_FUNC_USART1_RTS 0xc08 +#define STM32F746_PA12_FUNC_SAI2_FS_B 0xc09 +#define STM32F746_PA12_FUNC_CAN1_TX 0xc0a +#define STM32F746_PA12_FUNC_OTG_FS_DP 0xc0b +#define STM32F746_PA12_FUNC_LCD_R5 0xc0f +#define STM32F746_PA12_FUNC_EVENTOUT 0xc10 +#define STM32F746_PA12_FUNC_ANALOG 0xc11 + +#define STM32F746_PA13_FUNC_GPIO 0xd00 +#define STM32F746_PA13_FUNC_JTMS_SWDIO 0xd01 +#define STM32F746_PA13_FUNC_EVENTOUT 0xd10 +#define STM32F746_PA13_FUNC_ANALOG 0xd11 + +#define STM32F746_PA14_FUNC_GPIO 0xe00 +#define STM32F746_PA14_FUNC_JTCK_SWCLK 0xe01 +#define STM32F746_PA14_FUNC_EVENTOUT 0xe10 +#define STM32F746_PA14_FUNC_ANALOG 0xe11 + +#define STM32F746_PA15_FUNC_GPIO 0xf00 +#define STM32F746_PA15_FUNC_JTDI 0xf01 +#define STM32F746_PA15_FUNC_TIM2_CH1_TIM2_ETR 0xf02 +#define STM32F746_PA15_FUNC_HDMI_CEC 0xf05 +#define STM32F746_PA15_FUNC_SPI1_NSS_I2S1_WS 0xf06 +#define STM32F746_PA15_FUNC_SPI3_NSS_I2S3_WS 0xf07 +#define STM32F746_PA15_FUNC_UART4_RTS 0xf09 +#define STM32F746_PA15_FUNC_EVENTOUT 0xf10 +#define STM32F746_PA15_FUNC_ANALOG 0xf11 + + +#define STM32F746_PB0_FUNC_GPIO 0x1000 +#define STM32F746_PB0_FUNC_TIM1_CH2N 0x1002 +#define STM32F746_PB0_FUNC_TIM3_CH3 0x1003 +#define STM32F746_PB0_FUNC_TIM8_CH2N 0x1004 +#define STM32F746_PB0_FUNC_UART4_CTS 0x1009 +#define STM32F746_PB0_FUNC_LCD_R3 0x100a +#define STM32F746_PB0_FUNC_OTG_HS_ULPI_D1 0x100b +#define STM32F746_PB0_FUNC_ETH_MII_RXD2 0x100c +#define STM32F746_PB0_FUNC_EVENTOUT 0x1010 +#define STM32F746_PB0_FUNC_ANALOG 0x1011 + +#define STM32F746_PB1_FUNC_GPIO 0x1100 +#define STM32F746_PB1_FUNC_TIM1_CH3N 0x1102 +#define STM32F746_PB1_FUNC_TIM3_CH4 0x1103 +#define STM32F746_PB1_FUNC_TIM8_CH3N 0x1104 +#define STM32F746_PB1_FUNC_LCD_R6 0x110a +#define STM32F746_PB1_FUNC_OTG_HS_ULPI_D2 0x110b +#define STM32F746_PB1_FUNC_ETH_MII_RXD3 0x110c +#define STM32F746_PB1_FUNC_EVENTOUT 0x1110 +#define STM32F746_PB1_FUNC_ANALOG 0x1111 + +#define STM32F746_PB2_FUNC_GPIO 0x1200 +#define STM32F746_PB2_FUNC_SAI1_SD_A 0x1207 +#define STM32F746_PB2_FUNC_SPI3_MOSI_I2S3_SD 0x1208 +#define STM32F746_PB2_FUNC_QUADSPI_CLK 0x120a +#define STM32F746_PB2_FUNC_EVENTOUT 0x1210 +#define STM32F746_PB2_FUNC_ANALOG 0x1211 + +#define STM32F746_PB3_FUNC_GPIO 0x1300 +#define STM32F746_PB3_FUNC_JTDO_TRACESWO 0x1301 +#define STM32F746_PB3_FUNC_TIM2_CH2 0x1302 +#define STM32F746_PB3_FUNC_SPI1_SCK_I2S1_CK 0x1306 +#define STM32F746_PB3_FUNC_SPI3_SCK_I2S3_CK 0x1307 +#define STM32F746_PB3_FUNC_EVENTOUT 0x1310 +#define STM32F746_PB3_FUNC_ANALOG 0x1311 + +#define STM32F746_PB4_FUNC_GPIO 0x1400 +#define STM32F746_PB4_FUNC_NJTRST 0x1401 +#define STM32F746_PB4_FUNC_TIM3_CH1 0x1403 +#define STM32F746_PB4_FUNC_SPI1_MISO 0x1406 +#define STM32F746_PB4_FUNC_SPI3_MISO 0x1407 +#define STM32F746_PB4_FUNC_SPI2_NSS_I2S2_WS 0x1408 +#define STM32F746_PB4_FUNC_EVENTOUT 0x1410 +#define STM32F746_PB4_FUNC_ANALOG 0x1411 + +#define STM32F746_PB5_FUNC_GPIO 0x1500 +#define STM32F746_PB5_FUNC_TIM3_CH2 0x1503 +#define STM32F746_PB5_FUNC_I2C1_SMBA 0x1505 +#define STM32F746_PB5_FUNC_SPI1_MOSI_I2S1_SD 0x1506 +#define STM32F746_PB5_FUNC_SPI3_MOSI_I2S3_SD 0x1507 +#define STM32F746_PB5_FUNC_CAN2_RX 0x150a +#define STM32F746_PB5_FUNC_OTG_HS_ULPI_D7 0x150b +#define STM32F746_PB5_FUNC_ETH_PPS_OUT 0x150c +#define STM32F746_PB5_FUNC_FMC_SDCKE1 0x150d +#define STM32F746_PB5_FUNC_DCMI_D10 0x150e +#define STM32F746_PB5_FUNC_EVENTOUT 0x1510 +#define STM32F746_PB5_FUNC_ANALOG 0x1511 + +#define STM32F746_PB6_FUNC_GPIO 0x1600 +#define STM32F746_PB6_FUNC_TIM4_CH1 0x1603 +#define STM32F746_PB6_FUNC_HDMI_CEC 0x1604 +#define STM32F746_PB6_FUNC_I2C1_SCL 0x1605 +#define STM32F746_PB6_FUNC_USART1_TX 0x1608 +#define STM32F746_PB6_FUNC_CAN2_TX 0x160a +#define STM32F746_PB6_FUNC_QUADSPI_BK1_NCS 0x160b +#define STM32F746_PB6_FUNC_FMC_SDNE1 0x160d +#define STM32F746_PB6_FUNC_DCMI_D5 0x160e +#define STM32F746_PB6_FUNC_EVENTOUT 0x1610 +#define STM32F746_PB6_FUNC_ANALOG 0x1611 + +#define STM32F746_PB7_FUNC_GPIO 0x1700 +#define STM32F746_PB7_FUNC_TIM4_CH2 0x1703 +#define STM32F746_PB7_FUNC_I2C1_SDA 0x1705 +#define STM32F746_PB7_FUNC_USART1_RX 0x1708 +#define STM32F746_PB7_FUNC_FMC_NL 0x170d +#define STM32F746_PB7_FUNC_DCMI_VSYNC 0x170e +#define STM32F746_PB7_FUNC_EVENTOUT 0x1710 +#define STM32F746_PB7_FUNC_ANALOG 0x1711 + +#define STM32F746_PB8_FUNC_GPIO 0x1800 +#define STM32F746_PB8_FUNC_TIM4_CH3 0x1803 +#define STM32F746_PB8_FUNC_TIM10_CH1 0x1804 +#define STM32F746_PB8_FUNC_I2C1_SCL 0x1805 +#define STM32F746_PB8_FUNC_CAN1_RX 0x180a +#define STM32F746_PB8_FUNC_ETH_MII_TXD3 0x180c +#define STM32F746_PB8_FUNC_SDMMC1_D4 0x180d +#define STM32F746_PB8_FUNC_DCMI_D6 0x180e +#define STM32F746_PB8_FUNC_LCD_B6 0x180f +#define STM32F746_PB8_FUNC_EVENTOUT 0x1810 +#define STM32F746_PB8_FUNC_ANALOG 0x1811 + +#define STM32F746_PB9_FUNC_GPIO 0x1900 +#define STM32F746_PB9_FUNC_TIM4_CH4 0x1903 +#define STM32F746_PB9_FUNC_TIM11_CH1 0x1904 +#define STM32F746_PB9_FUNC_I2C1_SDA 0x1905 +#define STM32F746_PB9_FUNC_SPI2_NSS_I2S2_WS 0x1906 +#define STM32F746_PB9_FUNC_CAN1_TX 0x190a +#define STM32F746_PB9_FUNC_SDMMC1_D5 0x190d +#define STM32F746_PB9_FUNC_DCMI_D7 0x190e +#define STM32F746_PB9_FUNC_LCD_B7 0x190f +#define STM32F746_PB9_FUNC_EVENTOUT 0x1910 +#define STM32F746_PB9_FUNC_ANALOG 0x1911 + +#define STM32F746_PB10_FUNC_GPIO 0x1a00 +#define STM32F746_PB10_FUNC_TIM2_CH3 0x1a02 +#define STM32F746_PB10_FUNC_I2C2_SCL 0x1a05 +#define STM32F746_PB10_FUNC_SPI2_SCK_I2S2_CK 0x1a06 +#define STM32F746_PB10_FUNC_USART3_TX 0x1a08 +#define STM32F746_PB10_FUNC_OTG_HS_ULPI_D3 0x1a0b +#define STM32F746_PB10_FUNC_ETH_MII_RX_ER 0x1a0c +#define STM32F746_PB10_FUNC_LCD_G4 0x1a0f +#define STM32F746_PB10_FUNC_EVENTOUT 0x1a10 +#define STM32F746_PB10_FUNC_ANALOG 0x1a11 + +#define STM32F746_PB11_FUNC_GPIO 0x1b00 +#define STM32F746_PB11_FUNC_TIM2_CH4 0x1b02 +#define STM32F746_PB11_FUNC_I2C2_SDA 0x1b05 +#define STM32F746_PB11_FUNC_USART3_RX 0x1b08 +#define STM32F746_PB11_FUNC_OTG_HS_ULPI_D4 0x1b0b +#define STM32F746_PB11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN 0x1b0c +#define STM32F746_PB11_FUNC_LCD_G5 0x1b0f +#define STM32F746_PB11_FUNC_EVENTOUT 0x1b10 +#define STM32F746_PB11_FUNC_ANALOG 0x1b11 + +#define STM32F746_PB12_FUNC_GPIO 0x1c00 +#define STM32F746_PB12_FUNC_TIM1_BKIN 0x1c02 +#define STM32F746_PB12_FUNC_I2C2_SMBA 0x1c05 +#define STM32F746_PB12_FUNC_SPI2_NSS_I2S2_WS 0x1c06 +#define STM32F746_PB12_FUNC_USART3_CK 0x1c08 +#define STM32F746_PB12_FUNC_CAN2_RX 0x1c0a +#define STM32F746_PB12_FUNC_OTG_HS_ULPI_D5 0x1c0b +#define STM32F746_PB12_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0 0x1c0c +#define STM32F746_PB12_FUNC_OTG_HS_ID 0x1c0d +#define STM32F746_PB12_FUNC_EVENTOUT 0x1c10 +#define STM32F746_PB12_FUNC_ANALOG 0x1c11 + +#define STM32F746_PB13_FUNC_GPIO 0x1d00 +#define STM32F746_PB13_FUNC_TIM1_CH1N 0x1d02 +#define STM32F746_PB13_FUNC_SPI2_SCK_I2S2_CK 0x1d06 +#define STM32F746_PB13_FUNC_USART3_CTS 0x1d08 +#define STM32F746_PB13_FUNC_CAN2_TX 0x1d0a +#define STM32F746_PB13_FUNC_OTG_HS_ULPI_D6 0x1d0b +#define STM32F746_PB13_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1 0x1d0c +#define STM32F746_PB13_FUNC_EVENTOUT 0x1d10 +#define STM32F746_PB13_FUNC_ANALOG 0x1d11 + +#define STM32F746_PB14_FUNC_GPIO 0x1e00 +#define STM32F746_PB14_FUNC_TIM1_CH2N 0x1e02 +#define STM32F746_PB14_FUNC_TIM8_CH2N 0x1e04 +#define STM32F746_PB14_FUNC_SPI2_MISO 0x1e06 +#define STM32F746_PB14_FUNC_USART3_RTS 0x1e08 +#define STM32F746_PB14_FUNC_TIM12_CH1 0x1e0a +#define STM32F746_PB14_FUNC_OTG_HS_DM 0x1e0d +#define STM32F746_PB14_FUNC_EVENTOUT 0x1e10 +#define STM32F746_PB14_FUNC_ANALOG 0x1e11 + +#define STM32F746_PB15_FUNC_GPIO 0x1f00 +#define STM32F746_PB15_FUNC_RTC_REFIN 0x1f01 +#define STM32F746_PB15_FUNC_TIM1_CH3N 0x1f02 +#define STM32F746_PB15_FUNC_TIM8_CH3N 0x1f04 +#define STM32F746_PB15_FUNC_SPI2_MOSI_I2S2_SD 0x1f06 +#define STM32F746_PB15_FUNC_TIM12_CH2 0x1f0a +#define STM32F746_PB15_FUNC_OTG_HS_DP 0x1f0d +#define STM32F746_PB15_FUNC_EVENTOUT 0x1f10 +#define STM32F746_PB15_FUNC_ANALOG 0x1f11 + + +#define STM32F746_PC0_FUNC_GPIO 0x2000 +#define STM32F746_PC0_FUNC_SAI2_FS_B 0x2009 +#define STM32F746_PC0_FUNC_OTG_HS_ULPI_STP 0x200b +#define STM32F746_PC0_FUNC_FMC_SDNWE 0x200d +#define STM32F746_PC0_FUNC_LCD_R5 0x200f +#define STM32F746_PC0_FUNC_EVENTOUT 0x2010 +#define STM32F746_PC0_FUNC_ANALOG 0x2011 + +#define STM32F746_PC1_FUNC_GPIO 0x2100 +#define STM32F746_PC1_FUNC_TRACED0 0x2101 +#define STM32F746_PC1_FUNC_SPI2_MOSI_I2S2_SD 0x2106 +#define STM32F746_PC1_FUNC_SAI1_SD_A 0x2107 +#define STM32F746_PC1_FUNC_ETH_MDC 0x210c +#define STM32F746_PC1_FUNC_EVENTOUT 0x2110 +#define STM32F746_PC1_FUNC_ANALOG 0x2111 + +#define STM32F746_PC2_FUNC_GPIO 0x2200 +#define STM32F746_PC2_FUNC_SPI2_MISO 0x2206 +#define STM32F746_PC2_FUNC_OTG_HS_ULPI_DIR 0x220b +#define STM32F746_PC2_FUNC_ETH_MII_TXD2 0x220c +#define STM32F746_PC2_FUNC_FMC_SDNE0 0x220d +#define STM32F746_PC2_FUNC_EVENTOUT 0x2210 +#define STM32F746_PC2_FUNC_ANALOG 0x2211 + +#define STM32F746_PC3_FUNC_GPIO 0x2300 +#define STM32F746_PC3_FUNC_SPI2_MOSI_I2S2_SD 0x2306 +#define STM32F746_PC3_FUNC_OTG_HS_ULPI_NXT 0x230b +#define STM32F746_PC3_FUNC_ETH_MII_TX_CLK 0x230c +#define STM32F746_PC3_FUNC_FMC_SDCKE0 0x230d +#define STM32F746_PC3_FUNC_EVENTOUT 0x2310 +#define STM32F746_PC3_FUNC_ANALOG 0x2311 + +#define STM32F746_PC4_FUNC_GPIO 0x2400 +#define STM32F746_PC4_FUNC_I2S1_MCK 0x2406 +#define STM32F746_PC4_FUNC_SPDIFRX_IN2 0x2409 +#define STM32F746_PC4_FUNC_ETH_MII_RXD0_ETH_RMII_RXD0 0x240c +#define STM32F746_PC4_FUNC_FMC_SDNE0 0x240d +#define STM32F746_PC4_FUNC_EVENTOUT 0x2410 +#define STM32F746_PC4_FUNC_ANALOG 0x2411 + +#define STM32F746_PC5_FUNC_GPIO 0x2500 +#define STM32F746_PC5_FUNC_SPDIFRX_IN3 0x2509 +#define STM32F746_PC5_FUNC_ETH_MII_RXD1_ETH_RMII_RXD1 0x250c +#define STM32F746_PC5_FUNC_FMC_SDCKE0 0x250d +#define STM32F746_PC5_FUNC_EVENTOUT 0x2510 +#define STM32F746_PC5_FUNC_ANALOG 0x2511 + +#define STM32F746_PC6_FUNC_GPIO 0x2600 +#define STM32F746_PC6_FUNC_TIM3_CH1 0x2603 +#define STM32F746_PC6_FUNC_TIM8_CH1 0x2604 +#define STM32F746_PC6_FUNC_I2S2_MCK 0x2606 +#define STM32F746_PC6_FUNC_USART6_TX 0x2609 +#define STM32F746_PC6_FUNC_SDMMC1_D6 0x260d +#define STM32F746_PC6_FUNC_DCMI_D0 0x260e +#define STM32F746_PC6_FUNC_LCD_HSYNC 0x260f +#define STM32F746_PC6_FUNC_EVENTOUT 0x2610 +#define STM32F746_PC6_FUNC_ANALOG 0x2611 + +#define STM32F746_PC7_FUNC_GPIO 0x2700 +#define STM32F746_PC7_FUNC_TIM3_CH2 0x2703 +#define STM32F746_PC7_FUNC_TIM8_CH2 0x2704 +#define STM32F746_PC7_FUNC_I2S3_MCK 0x2707 +#define STM32F746_PC7_FUNC_USART6_RX 0x2709 +#define STM32F746_PC7_FUNC_SDMMC1_D7 0x270d +#define STM32F746_PC7_FUNC_DCMI_D1 0x270e +#define STM32F746_PC7_FUNC_LCD_G6 0x270f +#define STM32F746_PC7_FUNC_EVENTOUT 0x2710 +#define STM32F746_PC7_FUNC_ANALOG 0x2711 + +#define STM32F746_PC8_FUNC_GPIO 0x2800 +#define STM32F746_PC8_FUNC_TRACED1 0x2801 +#define STM32F746_PC8_FUNC_TIM3_CH3 0x2803 +#define STM32F746_PC8_FUNC_TIM8_CH3 0x2804 +#define STM32F746_PC8_FUNC_UART5_RTS 0x2808 +#define STM32F746_PC8_FUNC_USART6_CK 0x2809 +#define STM32F746_PC8_FUNC_SDMMC1_D0 0x280d +#define STM32F746_PC8_FUNC_DCMI_D2 0x280e +#define STM32F746_PC8_FUNC_EVENTOUT 0x2810 +#define STM32F746_PC8_FUNC_ANALOG 0x2811 + +#define STM32F746_PC9_FUNC_GPIO 0x2900 +#define STM32F746_PC9_FUNC_MCO2 0x2901 +#define STM32F746_PC9_FUNC_TIM3_CH4 0x2903 +#define STM32F746_PC9_FUNC_TIM8_CH4 0x2904 +#define STM32F746_PC9_FUNC_I2C3_SDA 0x2905 +#define STM32F746_PC9_FUNC_I2S_CKIN 0x2906 +#define STM32F746_PC9_FUNC_UART5_CTS 0x2908 +#define STM32F746_PC9_FUNC_QUADSPI_BK1_IO0 0x290a +#define STM32F746_PC9_FUNC_SDMMC1_D1 0x290d +#define STM32F746_PC9_FUNC_DCMI_D3 0x290e +#define STM32F746_PC9_FUNC_EVENTOUT 0x2910 +#define STM32F746_PC9_FUNC_ANALOG 0x2911 + +#define STM32F746_PC10_FUNC_GPIO 0x2a00 +#define STM32F746_PC10_FUNC_SPI3_SCK_I2S3_CK 0x2a07 +#define STM32F746_PC10_FUNC_USART3_TX 0x2a08 +#define STM32F746_PC10_FUNC_UART4_TX 0x2a09 +#define STM32F746_PC10_FUNC_QUADSPI_BK1_IO1 0x2a0a +#define STM32F746_PC10_FUNC_SDMMC1_D2 0x2a0d +#define STM32F746_PC10_FUNC_DCMI_D8 0x2a0e +#define STM32F746_PC10_FUNC_LCD_R2 0x2a0f +#define STM32F746_PC10_FUNC_EVENTOUT 0x2a10 +#define STM32F746_PC10_FUNC_ANALOG 0x2a11 + +#define STM32F746_PC11_FUNC_GPIO 0x2b00 +#define STM32F746_PC11_FUNC_SPI3_MISO 0x2b07 +#define STM32F746_PC11_FUNC_USART3_RX 0x2b08 +#define STM32F746_PC11_FUNC_UART4_RX 0x2b09 +#define STM32F746_PC11_FUNC_QUADSPI_BK2_NCS 0x2b0a +#define STM32F746_PC11_FUNC_SDMMC1_D3 0x2b0d +#define STM32F746_PC11_FUNC_DCMI_D4 0x2b0e +#define STM32F746_PC11_FUNC_EVENTOUT 0x2b10 +#define STM32F746_PC11_FUNC_ANALOG 0x2b11 + +#define STM32F746_PC12_FUNC_GPIO 0x2c00 +#define STM32F746_PC12_FUNC_TRACED3 0x2c01 +#define STM32F746_PC12_FUNC_SPI3_MOSI_I2S3_SD 0x2c07 +#define STM32F746_PC12_FUNC_USART3_CK 0x2c08 +#define STM32F746_PC12_FUNC_UART5_TX 0x2c09 +#define STM32F746_PC12_FUNC_SDMMC1_CK 0x2c0d +#define STM32F746_PC12_FUNC_DCMI_D9 0x2c0e +#define STM32F746_PC12_FUNC_EVENTOUT 0x2c10 +#define STM32F746_PC12_FUNC_ANALOG 0x2c11 + +#define STM32F746_PC13_FUNC_GPIO 0x2d00 +#define STM32F746_PC13_FUNC_EVENTOUT 0x2d10 +#define STM32F746_PC13_FUNC_ANALOG 0x2d11 + +#define STM32F746_PC14_FUNC_GPIO 0x2e00 +#define STM32F746_PC14_FUNC_EVENTOUT 0x2e10 +#define STM32F746_PC14_FUNC_ANALOG 0x2e11 + +#define STM32F746_PC15_FUNC_GPIO 0x2f00 +#define STM32F746_PC15_FUNC_EVENTOUT 0x2f10 +#define STM32F746_PC15_FUNC_ANALOG 0x2f11 + + +#define STM32F746_PD0_FUNC_GPIO 0x3000 +#define STM32F746_PD0_FUNC_CAN1_RX 0x300a +#define STM32F746_PD0_FUNC_FMC_D2 0x300d +#define STM32F746_PD0_FUNC_EVENTOUT 0x3010 +#define STM32F746_PD0_FUNC_ANALOG 0x3011 + +#define STM32F746_PD1_FUNC_GPIO 0x3100 +#define STM32F746_PD1_FUNC_CAN1_TX 0x310a +#define STM32F746_PD1_FUNC_FMC_D3 0x310d +#define STM32F746_PD1_FUNC_EVENTOUT 0x3110 +#define STM32F746_PD1_FUNC_ANALOG 0x3111 + +#define STM32F746_PD2_FUNC_GPIO 0x3200 +#define STM32F746_PD2_FUNC_TRACED2 0x3201 +#define STM32F746_PD2_FUNC_TIM3_ETR 0x3203 +#define STM32F746_PD2_FUNC_UART5_RX 0x3209 +#define STM32F746_PD2_FUNC_SDMMC1_CMD 0x320d +#define STM32F746_PD2_FUNC_DCMI_D11 0x320e +#define STM32F746_PD2_FUNC_EVENTOUT 0x3210 +#define STM32F746_PD2_FUNC_ANALOG 0x3211 + +#define STM32F746_PD3_FUNC_GPIO 0x3300 +#define STM32F746_PD3_FUNC_SPI2_SCK_I2S2_CK 0x3306 +#define STM32F746_PD3_FUNC_USART2_CTS 0x3308 +#define STM32F746_PD3_FUNC_FMC_CLK 0x330d +#define STM32F746_PD3_FUNC_DCMI_D5 0x330e +#define STM32F746_PD3_FUNC_LCD_G7 0x330f +#define STM32F746_PD3_FUNC_EVENTOUT 0x3310 +#define STM32F746_PD3_FUNC_ANALOG 0x3311 + +#define STM32F746_PD4_FUNC_GPIO 0x3400 +#define STM32F746_PD4_FUNC_USART2_RTS 0x3408 +#define STM32F746_PD4_FUNC_FMC_NOE 0x340d +#define STM32F746_PD4_FUNC_EVENTOUT 0x3410 +#define STM32F746_PD4_FUNC_ANALOG 0x3411 + +#define STM32F746_PD5_FUNC_GPIO 0x3500 +#define STM32F746_PD5_FUNC_USART2_TX 0x3508 +#define STM32F746_PD5_FUNC_FMC_NWE 0x350d +#define STM32F746_PD5_FUNC_EVENTOUT 0x3510 +#define STM32F746_PD5_FUNC_ANALOG 0x3511 + +#define STM32F746_PD6_FUNC_GPIO 0x3600 +#define STM32F746_PD6_FUNC_SPI3_MOSI_I2S3_SD 0x3606 +#define STM32F746_PD6_FUNC_SAI1_SD_A 0x3607 +#define STM32F746_PD6_FUNC_USART2_RX 0x3608 +#define STM32F746_PD6_FUNC_FMC_NWAIT 0x360d +#define STM32F746_PD6_FUNC_DCMI_D10 0x360e +#define STM32F746_PD6_FUNC_LCD_B2 0x360f +#define STM32F746_PD6_FUNC_EVENTOUT 0x3610 +#define STM32F746_PD6_FUNC_ANALOG 0x3611 + +#define STM32F746_PD7_FUNC_GPIO 0x3700 +#define STM32F746_PD7_FUNC_USART2_CK 0x3708 +#define STM32F746_PD7_FUNC_SPDIFRX_IN0 0x3709 +#define STM32F746_PD7_FUNC_FMC_NE1 0x370d +#define STM32F746_PD7_FUNC_EVENTOUT 0x3710 +#define STM32F746_PD7_FUNC_ANALOG 0x3711 + +#define STM32F746_PD8_FUNC_GPIO 0x3800 +#define STM32F746_PD8_FUNC_USART3_TX 0x3808 +#define STM32F746_PD8_FUNC_SPDIFRX_IN1 0x3809 +#define STM32F746_PD8_FUNC_FMC_D13 0x380d +#define STM32F746_PD8_FUNC_EVENTOUT 0x3810 +#define STM32F746_PD8_FUNC_ANALOG 0x3811 + +#define STM32F746_PD9_FUNC_GPIO 0x3900 +#define STM32F746_PD9_FUNC_USART3_RX 0x3908 +#define STM32F746_PD9_FUNC_FMC_D14 0x390d +#define STM32F746_PD9_FUNC_EVENTOUT 0x3910 +#define STM32F746_PD9_FUNC_ANALOG 0x3911 + +#define STM32F746_PD10_FUNC_GPIO 0x3a00 +#define STM32F746_PD10_FUNC_USART3_CK 0x3a08 +#define STM32F746_PD10_FUNC_FMC_D15 0x3a0d +#define STM32F746_PD10_FUNC_LCD_B3 0x3a0f +#define STM32F746_PD10_FUNC_EVENTOUT 0x3a10 +#define STM32F746_PD10_FUNC_ANALOG 0x3a11 + +#define STM32F746_PD11_FUNC_GPIO 0x3b00 +#define STM32F746_PD11_FUNC_I2C4_SMBA 0x3b05 +#define STM32F746_PD11_FUNC_USART3_CTS 0x3b08 +#define STM32F746_PD11_FUNC_QUADSPI_BK1_IO0 0x3b0a +#define STM32F746_PD11_FUNC_SAI2_SD_A 0x3b0b +#define STM32F746_PD11_FUNC_FMC_A16_FMC_CLE 0x3b0d +#define STM32F746_PD11_FUNC_EVENTOUT 0x3b10 +#define STM32F746_PD11_FUNC_ANALOG 0x3b11 + +#define STM32F746_PD12_FUNC_GPIO 0x3c00 +#define STM32F746_PD12_FUNC_TIM4_CH1 0x3c03 +#define STM32F746_PD12_FUNC_LPTIM1_IN1 0x3c04 +#define STM32F746_PD12_FUNC_I2C4_SCL 0x3c05 +#define STM32F746_PD12_FUNC_USART3_RTS 0x3c08 +#define STM32F746_PD12_FUNC_QUADSPI_BK1_IO1 0x3c0a +#define STM32F746_PD12_FUNC_SAI2_FS_A 0x3c0b +#define STM32F746_PD12_FUNC_FMC_A17_FMC_ALE 0x3c0d +#define STM32F746_PD12_FUNC_EVENTOUT 0x3c10 +#define STM32F746_PD12_FUNC_ANALOG 0x3c11 + +#define STM32F746_PD13_FUNC_GPIO 0x3d00 +#define STM32F746_PD13_FUNC_TIM4_CH2 0x3d03 +#define STM32F746_PD13_FUNC_LPTIM1_OUT 0x3d04 +#define STM32F746_PD13_FUNC_I2C4_SDA 0x3d05 +#define STM32F746_PD13_FUNC_QUADSPI_BK1_IO3 0x3d0a +#define STM32F746_PD13_FUNC_SAI2_SCK_A 0x3d0b +#define STM32F746_PD13_FUNC_FMC_A18 0x3d0d +#define STM32F746_PD13_FUNC_EVENTOUT 0x3d10 +#define STM32F746_PD13_FUNC_ANALOG 0x3d11 + +#define STM32F746_PD14_FUNC_GPIO 0x3e00 +#define STM32F746_PD14_FUNC_TIM4_CH3 0x3e03 +#define STM32F746_PD14_FUNC_UART8_CTS 0x3e09 +#define STM32F746_PD14_FUNC_FMC_D0 0x3e0d +#define STM32F746_PD14_FUNC_EVENTOUT 0x3e10 +#define STM32F746_PD14_FUNC_ANALOG 0x3e11 + +#define STM32F746_PD15_FUNC_GPIO 0x3f00 +#define STM32F746_PD15_FUNC_TIM4_CH4 0x3f03 +#define STM32F746_PD15_FUNC_UART8_RTS 0x3f09 +#define STM32F746_PD15_FUNC_FMC_D1 0x3f0d +#define STM32F746_PD15_FUNC_EVENTOUT 0x3f10 +#define STM32F746_PD15_FUNC_ANALOG 0x3f11 + + +#define STM32F746_PE0_FUNC_GPIO 0x4000 +#define STM32F746_PE0_FUNC_TIM4_ETR 0x4003 +#define STM32F746_PE0_FUNC_LPTIM1_ETR 0x4004 +#define STM32F746_PE0_FUNC_UART8_RX 0x4009 +#define STM32F746_PE0_FUNC_SAI2_MCLK_A 0x400b +#define STM32F746_PE0_FUNC_FMC_NBL0 0x400d +#define STM32F746_PE0_FUNC_DCMI_D2 0x400e +#define STM32F746_PE0_FUNC_EVENTOUT 0x4010 +#define STM32F746_PE0_FUNC_ANALOG 0x4011 + +#define STM32F746_PE1_FUNC_GPIO 0x4100 +#define STM32F746_PE1_FUNC_LPTIM1_IN2 0x4104 +#define STM32F746_PE1_FUNC_UART8_TX 0x4109 +#define STM32F746_PE1_FUNC_FMC_NBL1 0x410d +#define STM32F746_PE1_FUNC_DCMI_D3 0x410e +#define STM32F746_PE1_FUNC_EVENTOUT 0x4110 +#define STM32F746_PE1_FUNC_ANALOG 0x4111 + +#define STM32F746_PE2_FUNC_GPIO 0x4200 +#define STM32F746_PE2_FUNC_TRACECLK 0x4201 +#define STM32F746_PE2_FUNC_SPI4_SCK 0x4206 +#define STM32F746_PE2_FUNC_SAI1_MCLK_A 0x4207 +#define STM32F746_PE2_FUNC_QUADSPI_BK1_IO2 0x420a +#define STM32F746_PE2_FUNC_ETH_MII_TXD3 0x420c +#define STM32F746_PE2_FUNC_FMC_A23 0x420d +#define STM32F746_PE2_FUNC_EVENTOUT 0x4210 +#define STM32F746_PE2_FUNC_ANALOG 0x4211 + +#define STM32F746_PE3_FUNC_GPIO 0x4300 +#define STM32F746_PE3_FUNC_TRACED0 0x4301 +#define STM32F746_PE3_FUNC_SAI1_SD_B 0x4307 +#define STM32F746_PE3_FUNC_FMC_A19 0x430d +#define STM32F746_PE3_FUNC_EVENTOUT 0x4310 +#define STM32F746_PE3_FUNC_ANALOG 0x4311 + +#define STM32F746_PE4_FUNC_GPIO 0x4400 +#define STM32F746_PE4_FUNC_TRACED1 0x4401 +#define STM32F746_PE4_FUNC_SPI4_NSS 0x4406 +#define STM32F746_PE4_FUNC_SAI1_FS_A 0x4407 +#define STM32F746_PE4_FUNC_FMC_A20 0x440d +#define STM32F746_PE4_FUNC_DCMI_D4 0x440e +#define STM32F746_PE4_FUNC_LCD_B0 0x440f +#define STM32F746_PE4_FUNC_EVENTOUT 0x4410 +#define STM32F746_PE4_FUNC_ANALOG 0x4411 + +#define STM32F746_PE5_FUNC_GPIO 0x4500 +#define STM32F746_PE5_FUNC_TRACED2 0x4501 +#define STM32F746_PE5_FUNC_TIM9_CH1 0x4504 +#define STM32F746_PE5_FUNC_SPI4_MISO 0x4506 +#define STM32F746_PE5_FUNC_SAI1_SCK_A 0x4507 +#define STM32F746_PE5_FUNC_FMC_A21 0x450d +#define STM32F746_PE5_FUNC_DCMI_D6 0x450e +#define STM32F746_PE5_FUNC_LCD_G0 0x450f +#define STM32F746_PE5_FUNC_EVENTOUT 0x4510 +#define STM32F746_PE5_FUNC_ANALOG 0x4511 + +#define STM32F746_PE6_FUNC_GPIO 0x4600 +#define STM32F746_PE6_FUNC_TRACED3 0x4601 +#define STM32F746_PE6_FUNC_TIM1_BKIN2 0x4602 +#define STM32F746_PE6_FUNC_TIM9_CH2 0x4604 +#define STM32F746_PE6_FUNC_SPI4_MOSI 0x4606 +#define STM32F746_PE6_FUNC_SAI1_SD_A 0x4607 +#define STM32F746_PE6_FUNC_SAI2_MCLK_B 0x460b +#define STM32F746_PE6_FUNC_FMC_A22 0x460d +#define STM32F746_PE6_FUNC_DCMI_D7 0x460e +#define STM32F746_PE6_FUNC_LCD_G1 0x460f +#define STM32F746_PE6_FUNC_EVENTOUT 0x4610 +#define STM32F746_PE6_FUNC_ANALOG 0x4611 + +#define STM32F746_PE7_FUNC_GPIO 0x4700 +#define STM32F746_PE7_FUNC_TIM1_ETR 0x4702 +#define STM32F746_PE7_FUNC_UART7_RX 0x4709 +#define STM32F746_PE7_FUNC_QUADSPI_BK2_IO0 0x470b +#define STM32F746_PE7_FUNC_FMC_D4 0x470d +#define STM32F746_PE7_FUNC_EVENTOUT 0x4710 +#define STM32F746_PE7_FUNC_ANALOG 0x4711 + +#define STM32F746_PE8_FUNC_GPIO 0x4800 +#define STM32F746_PE8_FUNC_TIM1_CH1N 0x4802 +#define STM32F746_PE8_FUNC_UART7_TX 0x4809 +#define STM32F746_PE8_FUNC_QUADSPI_BK2_IO1 0x480b +#define STM32F746_PE8_FUNC_FMC_D5 0x480d +#define STM32F746_PE8_FUNC_EVENTOUT 0x4810 +#define STM32F746_PE8_FUNC_ANALOG 0x4811 + +#define STM32F746_PE9_FUNC_GPIO 0x4900 +#define STM32F746_PE9_FUNC_TIM1_CH1 0x4902 +#define STM32F746_PE9_FUNC_UART7_RTS 0x4909 +#define STM32F746_PE9_FUNC_QUADSPI_BK2_IO2 0x490b +#define STM32F746_PE9_FUNC_FMC_D6 0x490d +#define STM32F746_PE9_FUNC_EVENTOUT 0x4910 +#define STM32F746_PE9_FUNC_ANALOG 0x4911 + +#define STM32F746_PE10_FUNC_GPIO 0x4a00 +#define STM32F746_PE10_FUNC_TIM1_CH2N 0x4a02 +#define STM32F746_PE10_FUNC_UART7_CTS 0x4a09 +#define STM32F746_PE10_FUNC_QUADSPI_BK2_IO3 0x4a0b +#define STM32F746_PE10_FUNC_FMC_D7 0x4a0d +#define STM32F746_PE10_FUNC_EVENTOUT 0x4a10 +#define STM32F746_PE10_FUNC_ANALOG 0x4a11 + +#define STM32F746_PE11_FUNC_GPIO 0x4b00 +#define STM32F746_PE11_FUNC_TIM1_CH2 0x4b02 +#define STM32F746_PE11_FUNC_SPI4_NSS 0x4b06 +#define STM32F746_PE11_FUNC_SAI2_SD_B 0x4b0b +#define STM32F746_PE11_FUNC_FMC_D8 0x4b0d +#define STM32F746_PE11_FUNC_LCD_G3 0x4b0f +#define STM32F746_PE11_FUNC_EVENTOUT 0x4b10 +#define STM32F746_PE11_FUNC_ANALOG 0x4b11 + +#define STM32F746_PE12_FUNC_GPIO 0x4c00 +#define STM32F746_PE12_FUNC_TIM1_CH3N 0x4c02 +#define STM32F746_PE12_FUNC_SPI4_SCK 0x4c06 +#define STM32F746_PE12_FUNC_SAI2_SCK_B 0x4c0b +#define STM32F746_PE12_FUNC_FMC_D9 0x4c0d +#define STM32F746_PE12_FUNC_LCD_B4 0x4c0f +#define STM32F746_PE12_FUNC_EVENTOUT 0x4c10 +#define STM32F746_PE12_FUNC_ANALOG 0x4c11 + +#define STM32F746_PE13_FUNC_GPIO 0x4d00 +#define STM32F746_PE13_FUNC_TIM1_CH3 0x4d02 +#define STM32F746_PE13_FUNC_SPI4_MISO 0x4d06 +#define STM32F746_PE13_FUNC_SAI2_FS_B 0x4d0b +#define STM32F746_PE13_FUNC_FMC_D10 0x4d0d +#define STM32F746_PE13_FUNC_LCD_DE 0x4d0f +#define STM32F746_PE13_FUNC_EVENTOUT 0x4d10 +#define STM32F746_PE13_FUNC_ANALOG 0x4d11 + +#define STM32F746_PE14_FUNC_GPIO 0x4e00 +#define STM32F746_PE14_FUNC_TIM1_CH4 0x4e02 +#define STM32F746_PE14_FUNC_SPI4_MOSI 0x4e06 +#define STM32F746_PE14_FUNC_SAI2_MCLK_B 0x4e0b +#define STM32F746_PE14_FUNC_FMC_D11 0x4e0d +#define STM32F746_PE14_FUNC_LCD_CLK 0x4e0f +#define STM32F746_PE14_FUNC_EVENTOUT 0x4e10 +#define STM32F746_PE14_FUNC_ANALOG 0x4e11 + +#define STM32F746_PE15_FUNC_GPIO 0x4f00 +#define STM32F746_PE15_FUNC_TIM1_BKIN 0x4f02 +#define STM32F746_PE15_FUNC_FMC_D12 0x4f0d +#define STM32F746_PE15_FUNC_LCD_R7 0x4f0f +#define STM32F746_PE15_FUNC_EVENTOUT 0x4f10 +#define STM32F746_PE15_FUNC_ANALOG 0x4f11 + + +#define STM32F746_PF0_FUNC_GPIO 0x5000 +#define STM32F746_PF0_FUNC_I2C2_SDA 0x5005 +#define STM32F746_PF0_FUNC_FMC_A0 0x500d +#define STM32F746_PF0_FUNC_EVENTOUT 0x5010 +#define STM32F746_PF0_FUNC_ANALOG 0x5011 + +#define STM32F746_PF1_FUNC_GPIO 0x5100 +#define STM32F746_PF1_FUNC_I2C2_SCL 0x5105 +#define STM32F746_PF1_FUNC_FMC_A1 0x510d +#define STM32F746_PF1_FUNC_EVENTOUT 0x5110 +#define STM32F746_PF1_FUNC_ANALOG 0x5111 + +#define STM32F746_PF2_FUNC_GPIO 0x5200 +#define STM32F746_PF2_FUNC_I2C2_SMBA 0x5205 +#define STM32F746_PF2_FUNC_FMC_A2 0x520d +#define STM32F746_PF2_FUNC_EVENTOUT 0x5210 +#define STM32F746_PF2_FUNC_ANALOG 0x5211 + +#define STM32F746_PF3_FUNC_GPIO 0x5300 +#define STM32F746_PF3_FUNC_FMC_A3 0x530d +#define STM32F746_PF3_FUNC_EVENTOUT 0x5310 +#define STM32F746_PF3_FUNC_ANALOG 0x5311 + +#define STM32F746_PF4_FUNC_GPIO 0x5400 +#define STM32F746_PF4_FUNC_FMC_A4 0x540d +#define STM32F746_PF4_FUNC_EVENTOUT 0x5410 +#define STM32F746_PF4_FUNC_ANALOG 0x5411 + +#define STM32F746_PF5_FUNC_GPIO 0x5500 +#define STM32F746_PF5_FUNC_FMC_A5 0x550d +#define STM32F746_PF5_FUNC_EVENTOUT 0x5510 +#define STM32F746_PF5_FUNC_ANALOG 0x5511 + +#define STM32F746_PF6_FUNC_GPIO 0x5600 +#define STM32F746_PF6_FUNC_TIM10_CH1 0x5604 +#define STM32F746_PF6_FUNC_SPI5_NSS 0x5606 +#define STM32F746_PF6_FUNC_SAI1_SD_B 0x5607 +#define STM32F746_PF6_FUNC_UART7_RX 0x5609 +#define STM32F746_PF6_FUNC_QUADSPI_BK1_IO3 0x560a +#define STM32F746_PF6_FUNC_EVENTOUT 0x5610 +#define STM32F746_PF6_FUNC_ANALOG 0x5611 + +#define STM32F746_PF7_FUNC_GPIO 0x5700 +#define STM32F746_PF7_FUNC_TIM11_CH1 0x5704 +#define STM32F746_PF7_FUNC_SPI5_SCK 0x5706 +#define STM32F746_PF7_FUNC_SAI1_MCLK_B 0x5707 +#define STM32F746_PF7_FUNC_UART7_TX 0x5709 +#define STM32F746_PF7_FUNC_QUADSPI_BK1_IO2 0x570a +#define STM32F746_PF7_FUNC_EVENTOUT 0x5710 +#define STM32F746_PF7_FUNC_ANALOG 0x5711 + +#define STM32F746_PF8_FUNC_GPIO 0x5800 +#define STM32F746_PF8_FUNC_SPI5_MISO 0x5806 +#define STM32F746_PF8_FUNC_SAI1_SCK_B 0x5807 +#define STM32F746_PF8_FUNC_UART7_RTS 0x5809 +#define STM32F746_PF8_FUNC_TIM13_CH1 0x580a +#define STM32F746_PF8_FUNC_QUADSPI_BK1_IO0 0x580b +#define STM32F746_PF8_FUNC_EVENTOUT 0x5810 +#define STM32F746_PF8_FUNC_ANALOG 0x5811 + +#define STM32F746_PF9_FUNC_GPIO 0x5900 +#define STM32F746_PF9_FUNC_SPI5_MOSI 0x5906 +#define STM32F746_PF9_FUNC_SAI1_FS_B 0x5907 +#define STM32F746_PF9_FUNC_UART7_CTS 0x5909 +#define STM32F746_PF9_FUNC_TIM14_CH1 0x590a +#define STM32F746_PF9_FUNC_QUADSPI_BK1_IO1 0x590b +#define STM32F746_PF9_FUNC_EVENTOUT 0x5910 +#define STM32F746_PF9_FUNC_ANALOG 0x5911 + +#define STM32F746_PF10_FUNC_GPIO 0x5a00 +#define STM32F746_PF10_FUNC_DCMI_D11 0x5a0e +#define STM32F746_PF10_FUNC_LCD_DE 0x5a0f +#define STM32F746_PF10_FUNC_EVENTOUT 0x5a10 +#define STM32F746_PF10_FUNC_ANALOG 0x5a11 + +#define STM32F746_PF11_FUNC_GPIO 0x5b00 +#define STM32F746_PF11_FUNC_SPI5_MOSI 0x5b06 +#define STM32F746_PF11_FUNC_SAI2_SD_B 0x5b0b +#define STM32F746_PF11_FUNC_FMC_SDNRAS 0x5b0d +#define STM32F746_PF11_FUNC_DCMI_D12 0x5b0e +#define STM32F746_PF11_FUNC_EVENTOUT 0x5b10 +#define STM32F746_PF11_FUNC_ANALOG 0x5b11 + +#define STM32F746_PF12_FUNC_GPIO 0x5c00 +#define STM32F746_PF12_FUNC_FMC_A6 0x5c0d +#define STM32F746_PF12_FUNC_EVENTOUT 0x5c10 +#define STM32F746_PF12_FUNC_ANALOG 0x5c11 + +#define STM32F746_PF13_FUNC_GPIO 0x5d00 +#define STM32F746_PF13_FUNC_I2C4_SMBA 0x5d05 +#define STM32F746_PF13_FUNC_FMC_A7 0x5d0d +#define STM32F746_PF13_FUNC_EVENTOUT 0x5d10 +#define STM32F746_PF13_FUNC_ANALOG 0x5d11 + +#define STM32F746_PF14_FUNC_GPIO 0x5e00 +#define STM32F746_PF14_FUNC_I2C4_SCL 0x5e05 +#define STM32F746_PF14_FUNC_FMC_A8 0x5e0d +#define STM32F746_PF14_FUNC_EVENTOUT 0x5e10 +#define STM32F746_PF14_FUNC_ANALOG 0x5e11 + +#define STM32F746_PF15_FUNC_GPIO 0x5f00 +#define STM32F746_PF15_FUNC_I2C4_SDA 0x5f05 +#define STM32F746_PF15_FUNC_FMC_A9 0x5f0d +#define STM32F746_PF15_FUNC_EVENTOUT 0x5f10 +#define STM32F746_PF15_FUNC_ANALOG 0x5f11 + + +#define STM32F746_PG0_FUNC_GPIO 0x6000 +#define STM32F746_PG0_FUNC_FMC_A10 0x600d +#define STM32F746_PG0_FUNC_EVENTOUT 0x6010 +#define STM32F746_PG0_FUNC_ANALOG 0x6011 + +#define STM32F746_PG1_FUNC_GPIO 0x6100 +#define STM32F746_PG1_FUNC_FMC_A11 0x610d +#define STM32F746_PG1_FUNC_EVENTOUT 0x6110 +#define STM32F746_PG1_FUNC_ANALOG 0x6111 + +#define STM32F746_PG2_FUNC_GPIO 0x6200 +#define STM32F746_PG2_FUNC_FMC_A12 0x620d +#define STM32F746_PG2_FUNC_EVENTOUT 0x6210 +#define STM32F746_PG2_FUNC_ANALOG 0x6211 + +#define STM32F746_PG3_FUNC_GPIO 0x6300 +#define STM32F746_PG3_FUNC_FMC_A13 0x630d +#define STM32F746_PG3_FUNC_EVENTOUT 0x6310 +#define STM32F746_PG3_FUNC_ANALOG 0x6311 + +#define STM32F746_PG4_FUNC_GPIO 0x6400 +#define STM32F746_PG4_FUNC_FMC_A14_FMC_BA0 0x640d +#define STM32F746_PG4_FUNC_EVENTOUT 0x6410 +#define STM32F746_PG4_FUNC_ANALOG 0x6411 + +#define STM32F746_PG5_FUNC_GPIO 0x6500 +#define STM32F746_PG5_FUNC_FMC_A15_FMC_BA1 0x650d +#define STM32F746_PG5_FUNC_EVENTOUT 0x6510 +#define STM32F746_PG5_FUNC_ANALOG 0x6511 + +#define STM32F746_PG6_FUNC_GPIO 0x6600 +#define STM32F746_PG6_FUNC_DCMI_D12 0x660e +#define STM32F746_PG6_FUNC_LCD_R7 0x660f +#define STM32F746_PG6_FUNC_EVENTOUT 0x6610 +#define STM32F746_PG6_FUNC_ANALOG 0x6611 + +#define STM32F746_PG7_FUNC_GPIO 0x6700 +#define STM32F746_PG7_FUNC_USART6_CK 0x6709 +#define STM32F746_PG7_FUNC_FMC_INT 0x670d +#define STM32F746_PG7_FUNC_DCMI_D13 0x670e +#define STM32F746_PG7_FUNC_LCD_CLK 0x670f +#define STM32F746_PG7_FUNC_EVENTOUT 0x6710 +#define STM32F746_PG7_FUNC_ANALOG 0x6711 + +#define STM32F746_PG8_FUNC_GPIO 0x6800 +#define STM32F746_PG8_FUNC_SPI6_NSS 0x6806 +#define STM32F746_PG8_FUNC_SPDIFRX_IN2 0x6808 +#define STM32F746_PG8_FUNC_USART6_RTS 0x6809 +#define STM32F746_PG8_FUNC_ETH_PPS_OUT 0x680c +#define STM32F746_PG8_FUNC_FMC_SDCLK 0x680d +#define STM32F746_PG8_FUNC_EVENTOUT 0x6810 +#define STM32F746_PG8_FUNC_ANALOG 0x6811 + +#define STM32F746_PG9_FUNC_GPIO 0x6900 +#define STM32F746_PG9_FUNC_SPDIFRX_IN3 0x6908 +#define STM32F746_PG9_FUNC_USART6_RX 0x6909 +#define STM32F746_PG9_FUNC_QUADSPI_BK2_IO2 0x690a +#define STM32F746_PG9_FUNC_SAI2_FS_B 0x690b +#define STM32F746_PG9_FUNC_FMC_NE2_FMC_NCE 0x690d +#define STM32F746_PG9_FUNC_DCMI_VSYNC 0x690e +#define STM32F746_PG9_FUNC_EVENTOUT 0x6910 +#define STM32F746_PG9_FUNC_ANALOG 0x6911 + +#define STM32F746_PG10_FUNC_GPIO 0x6a00 +#define STM32F746_PG10_FUNC_LCD_G3 0x6a0a +#define STM32F746_PG10_FUNC_SAI2_SD_B 0x6a0b +#define STM32F746_PG10_FUNC_FMC_NE3 0x6a0d +#define STM32F746_PG10_FUNC_DCMI_D2 0x6a0e +#define STM32F746_PG10_FUNC_LCD_B2 0x6a0f +#define STM32F746_PG10_FUNC_EVENTOUT 0x6a10 +#define STM32F746_PG10_FUNC_ANALOG 0x6a11 + +#define STM32F746_PG11_FUNC_GPIO 0x6b00 +#define STM32F746_PG11_FUNC_SPDIFRX_IN0 0x6b08 +#define STM32F746_PG11_FUNC_ETH_MII_TX_EN_ETH_RMII_TX_EN 0x6b0c +#define STM32F746_PG11_FUNC_DCMI_D3 0x6b0e +#define STM32F746_PG11_FUNC_LCD_B3 0x6b0f +#define STM32F746_PG11_FUNC_EVENTOUT 0x6b10 +#define STM32F746_PG11_FUNC_ANALOG 0x6b11 + +#define STM32F746_PG12_FUNC_GPIO 0x6c00 +#define STM32F746_PG12_FUNC_LPTIM1_IN1 0x6c04 +#define STM32F746_PG12_FUNC_SPI6_MISO 0x6c06 +#define STM32F746_PG12_FUNC_SPDIFRX_IN1 0x6c08 +#define STM32F746_PG12_FUNC_USART6_RTS 0x6c09 +#define STM32F746_PG12_FUNC_LCD_B4 0x6c0a +#define STM32F746_PG12_FUNC_FMC_NE4 0x6c0d +#define STM32F746_PG12_FUNC_LCD_B1 0x6c0f +#define STM32F746_PG12_FUNC_EVENTOUT 0x6c10 +#define STM32F746_PG12_FUNC_ANALOG 0x6c11 + +#define STM32F746_PG13_FUNC_GPIO 0x6d00 +#define STM32F746_PG13_FUNC_TRACED0 0x6d01 +#define STM32F746_PG13_FUNC_LPTIM1_OUT 0x6d04 +#define STM32F746_PG13_FUNC_SPI6_SCK 0x6d06 +#define STM32F746_PG13_FUNC_USART6_CTS 0x6d09 +#define STM32F746_PG13_FUNC_ETH_MII_TXD0_ETH_RMII_TXD0 0x6d0c +#define STM32F746_PG13_FUNC_FMC_A24 0x6d0d +#define STM32F746_PG13_FUNC_LCD_R0 0x6d0f +#define STM32F746_PG13_FUNC_EVENTOUT 0x6d10 +#define STM32F746_PG13_FUNC_ANALOG 0x6d11 + +#define STM32F746_PG14_FUNC_GPIO 0x6e00 +#define STM32F746_PG14_FUNC_TRACED1 0x6e01 +#define STM32F746_PG14_FUNC_LPTIM1_ETR 0x6e04 +#define STM32F746_PG14_FUNC_SPI6_MOSI 0x6e06 +#define STM32F746_PG14_FUNC_USART6_TX 0x6e09 +#define STM32F746_PG14_FUNC_QUADSPI_BK2_IO3 0x6e0a +#define STM32F746_PG14_FUNC_ETH_MII_TXD1_ETH_RMII_TXD1 0x6e0c +#define STM32F746_PG14_FUNC_FMC_A25 0x6e0d +#define STM32F746_PG14_FUNC_LCD_B0 0x6e0f +#define STM32F746_PG14_FUNC_EVENTOUT 0x6e10 +#define STM32F746_PG14_FUNC_ANALOG 0x6e11 + +#define STM32F746_PG15_FUNC_GPIO 0x6f00 +#define STM32F746_PG15_FUNC_USART6_CTS 0x6f09 +#define STM32F746_PG15_FUNC_FMC_SDNCAS 0x6f0d +#define STM32F746_PG15_FUNC_DCMI_D13 0x6f0e +#define STM32F746_PG15_FUNC_EVENTOUT 0x6f10 +#define STM32F746_PG15_FUNC_ANALOG 0x6f11 + + +#define STM32F746_PH0_FUNC_GPIO 0x7000 +#define STM32F746_PH0_FUNC_EVENTOUT 0x7010 +#define STM32F746_PH0_FUNC_ANALOG 0x7011 + +#define STM32F746_PH1_FUNC_GPIO 0x7100 +#define STM32F746_PH1_FUNC_EVENTOUT 0x7110 +#define STM32F746_PH1_FUNC_ANALOG 0x7111 + +#define STM32F746_PH2_FUNC_GPIO 0x7200 +#define STM32F746_PH2_FUNC_LPTIM1_IN2 0x7204 +#define STM32F746_PH2_FUNC_QUADSPI_BK2_IO0 0x720a +#define STM32F746_PH2_FUNC_SAI2_SCK_B 0x720b +#define STM32F746_PH2_FUNC_ETH_MII_CRS 0x720c +#define STM32F746_PH2_FUNC_FMC_SDCKE0 0x720d +#define STM32F746_PH2_FUNC_LCD_R0 0x720f +#define STM32F746_PH2_FUNC_EVENTOUT 0x7210 +#define STM32F746_PH2_FUNC_ANALOG 0x7211 + +#define STM32F746_PH3_FUNC_GPIO 0x7300 +#define STM32F746_PH3_FUNC_QUADSPI_BK2_IO1 0x730a +#define STM32F746_PH3_FUNC_SAI2_MCLK_B 0x730b +#define STM32F746_PH3_FUNC_ETH_MII_COL 0x730c +#define STM32F746_PH3_FUNC_FMC_SDNE0 0x730d +#define STM32F746_PH3_FUNC_LCD_R1 0x730f +#define STM32F746_PH3_FUNC_EVENTOUT 0x7310 +#define STM32F746_PH3_FUNC_ANALOG 0x7311 + +#define STM32F746_PH4_FUNC_GPIO 0x7400 +#define STM32F746_PH4_FUNC_I2C2_SCL 0x7405 +#define STM32F746_PH4_FUNC_OTG_HS_ULPI_NXT 0x740b +#define STM32F746_PH4_FUNC_EVENTOUT 0x7410 +#define STM32F746_PH4_FUNC_ANALOG 0x7411 + +#define STM32F746_PH5_FUNC_GPIO 0x7500 +#define STM32F746_PH5_FUNC_I2C2_SDA 0x7505 +#define STM32F746_PH5_FUNC_SPI5_NSS 0x7506 +#define STM32F746_PH5_FUNC_FMC_SDNWE 0x750d +#define STM32F746_PH5_FUNC_EVENTOUT 0x7510 +#define STM32F746_PH5_FUNC_ANALOG 0x7511 + +#define STM32F746_PH6_FUNC_GPIO 0x7600 +#define STM32F746_PH6_FUNC_I2C2_SMBA 0x7605 +#define STM32F746_PH6_FUNC_SPI5_SCK 0x7606 +#define STM32F746_PH6_FUNC_TIM12_CH1 0x760a +#define STM32F746_PH6_FUNC_ETH_MII_RXD2 0x760c +#define STM32F746_PH6_FUNC_FMC_SDNE1 0x760d +#define STM32F746_PH6_FUNC_DCMI_D8 0x760e +#define STM32F746_PH6_FUNC_EVENTOUT 0x7610 +#define STM32F746_PH6_FUNC_ANALOG 0x7611 + +#define STM32F746_PH7_FUNC_GPIO 0x7700 +#define STM32F746_PH7_FUNC_I2C3_SCL 0x7705 +#define STM32F746_PH7_FUNC_SPI5_MISO 0x7706 +#define STM32F746_PH7_FUNC_ETH_MII_RXD3 0x770c +#define STM32F746_PH7_FUNC_FMC_SDCKE1 0x770d +#define STM32F746_PH7_FUNC_DCMI_D9 0x770e +#define STM32F746_PH7_FUNC_EVENTOUT 0x7710 +#define STM32F746_PH7_FUNC_ANALOG 0x7711 + +#define STM32F746_PH8_FUNC_GPIO 0x7800 +#define STM32F746_PH8_FUNC_I2C3_SDA 0x7805 +#define STM32F746_PH8_FUNC_FMC_D16 0x780d +#define STM32F746_PH8_FUNC_DCMI_HSYNC 0x780e +#define STM32F746_PH8_FUNC_LCD_R2 0x780f +#define STM32F746_PH8_FUNC_EVENTOUT 0x7810 +#define STM32F746_PH8_FUNC_ANALOG 0x7811 + +#define STM32F746_PH9_FUNC_GPIO 0x7900 +#define STM32F746_PH9_FUNC_I2C3_SMBA 0x7905 +#define STM32F746_PH9_FUNC_TIM12_CH2 0x790a +#define STM32F746_PH9_FUNC_FMC_D17 0x790d +#define STM32F746_PH9_FUNC_DCMI_D0 0x790e +#define STM32F746_PH9_FUNC_LCD_R3 0x790f +#define STM32F746_PH9_FUNC_EVENTOUT 0x7910 +#define STM32F746_PH9_FUNC_ANALOG 0x7911 + +#define STM32F746_PH10_FUNC_GPIO 0x7a00 +#define STM32F746_PH10_FUNC_TIM5_CH1 0x7a03 +#define STM32F746_PH10_FUNC_I2C4_SMBA 0x7a05 +#define STM32F746_PH10_FUNC_FMC_D18 0x7a0d +#define STM32F746_PH10_FUNC_DCMI_D1 0x7a0e +#define STM32F746_PH10_FUNC_LCD_R4 0x7a0f +#define STM32F746_PH10_FUNC_EVENTOUT 0x7a10 +#define STM32F746_PH10_FUNC_ANALOG 0x7a11 + +#define STM32F746_PH11_FUNC_GPIO 0x7b00 +#define STM32F746_PH11_FUNC_TIM5_CH2 0x7b03 +#define STM32F746_PH11_FUNC_I2C4_SCL 0x7b05 +#define STM32F746_PH11_FUNC_FMC_D19 0x7b0d +#define STM32F746_PH11_FUNC_DCMI_D2 0x7b0e +#define STM32F746_PH11_FUNC_LCD_R5 0x7b0f +#define STM32F746_PH11_FUNC_EVENTOUT 0x7b10 +#define STM32F746_PH11_FUNC_ANALOG 0x7b11 + +#define STM32F746_PH12_FUNC_GPIO 0x7c00 +#define STM32F746_PH12_FUNC_TIM5_CH3 0x7c03 +#define STM32F746_PH12_FUNC_I2C4_SDA 0x7c05 +#define STM32F746_PH12_FUNC_FMC_D20 0x7c0d +#define STM32F746_PH12_FUNC_DCMI_D3 0x7c0e +#define STM32F746_PH12_FUNC_LCD_R6 0x7c0f +#define STM32F746_PH12_FUNC_EVENTOUT 0x7c10 +#define STM32F746_PH12_FUNC_ANALOG 0x7c11 + +#define STM32F746_PH13_FUNC_GPIO 0x7d00 +#define STM32F746_PH13_FUNC_TIM8_CH1N 0x7d04 +#define STM32F746_PH13_FUNC_CAN1_TX 0x7d0a +#define STM32F746_PH13_FUNC_FMC_D21 0x7d0d +#define STM32F746_PH13_FUNC_LCD_G2 0x7d0f +#define STM32F746_PH13_FUNC_EVENTOUT 0x7d10 +#define STM32F746_PH13_FUNC_ANALOG 0x7d11 + +#define STM32F746_PH14_FUNC_GPIO 0x7e00 +#define STM32F746_PH14_FUNC_TIM8_CH2N 0x7e04 +#define STM32F746_PH14_FUNC_FMC_D22 0x7e0d +#define STM32F746_PH14_FUNC_DCMI_D4 0x7e0e +#define STM32F746_PH14_FUNC_LCD_G3 0x7e0f +#define STM32F746_PH14_FUNC_EVENTOUT 0x7e10 +#define STM32F746_PH14_FUNC_ANALOG 0x7e11 + +#define STM32F746_PH15_FUNC_GPIO 0x7f00 +#define STM32F746_PH15_FUNC_TIM8_CH3N 0x7f04 +#define STM32F746_PH15_FUNC_FMC_D23 0x7f0d +#define STM32F746_PH15_FUNC_DCMI_D11 0x7f0e +#define STM32F746_PH15_FUNC_LCD_G4 0x7f0f +#define STM32F746_PH15_FUNC_EVENTOUT 0x7f10 +#define STM32F746_PH15_FUNC_ANALOG 0x7f11 + + +#define STM32F746_PI0_FUNC_GPIO 0x8000 +#define STM32F746_PI0_FUNC_TIM5_CH4 0x8003 +#define STM32F746_PI0_FUNC_SPI2_NSS_I2S2_WS 0x8006 +#define STM32F746_PI0_FUNC_FMC_D24 0x800d +#define STM32F746_PI0_FUNC_DCMI_D13 0x800e +#define STM32F746_PI0_FUNC_LCD_G5 0x800f +#define STM32F746_PI0_FUNC_EVENTOUT 0x8010 +#define STM32F746_PI0_FUNC_ANALOG 0x8011 + +#define STM32F746_PI1_FUNC_GPIO 0x8100 +#define STM32F746_PI1_FUNC_TIM8_BKIN2 0x8104 +#define STM32F746_PI1_FUNC_SPI2_SCK_I2S2_CK 0x8106 +#define STM32F746_PI1_FUNC_FMC_D25 0x810d +#define STM32F746_PI1_FUNC_DCMI_D8 0x810e +#define STM32F746_PI1_FUNC_LCD_G6 0x810f +#define STM32F746_PI1_FUNC_EVENTOUT 0x8110 +#define STM32F746_PI1_FUNC_ANALOG 0x8111 + +#define STM32F746_PI2_FUNC_GPIO 0x8200 +#define STM32F746_PI2_FUNC_TIM8_CH4 0x8204 +#define STM32F746_PI2_FUNC_SPI2_MISO 0x8206 +#define STM32F746_PI2_FUNC_FMC_D26 0x820d +#define STM32F746_PI2_FUNC_DCMI_D9 0x820e +#define STM32F746_PI2_FUNC_LCD_G7 0x820f +#define STM32F746_PI2_FUNC_EVENTOUT 0x8210 +#define STM32F746_PI2_FUNC_ANALOG 0x8211 + +#define STM32F746_PI3_FUNC_GPIO 0x8300 +#define STM32F746_PI3_FUNC_TIM8_ETR 0x8304 +#define STM32F746_PI3_FUNC_SPI2_MOSI_I2S2_SD 0x8306 +#define STM32F746_PI3_FUNC_FMC_D27 0x830d +#define STM32F746_PI3_FUNC_DCMI_D10 0x830e +#define STM32F746_PI3_FUNC_EVENTOUT 0x8310 +#define STM32F746_PI3_FUNC_ANALOG 0x8311 + +#define STM32F746_PI4_FUNC_GPIO 0x8400 +#define STM32F746_PI4_FUNC_TIM8_BKIN 0x8404 +#define STM32F746_PI4_FUNC_SAI2_MCLK_A 0x840b +#define STM32F746_PI4_FUNC_FMC_NBL2 0x840d +#define STM32F746_PI4_FUNC_DCMI_D5 0x840e +#define STM32F746_PI4_FUNC_LCD_B4 0x840f +#define STM32F746_PI4_FUNC_EVENTOUT 0x8410 +#define STM32F746_PI4_FUNC_ANALOG 0x8411 + +#define STM32F746_PI5_FUNC_GPIO 0x8500 +#define STM32F746_PI5_FUNC_TIM8_CH1 0x8504 +#define STM32F746_PI5_FUNC_SAI2_SCK_A 0x850b +#define STM32F746_PI5_FUNC_FMC_NBL3 0x850d +#define STM32F746_PI5_FUNC_DCMI_VSYNC 0x850e +#define STM32F746_PI5_FUNC_LCD_B5 0x850f +#define STM32F746_PI5_FUNC_EVENTOUT 0x8510 +#define STM32F746_PI5_FUNC_ANALOG 0x8511 + +#define STM32F746_PI6_FUNC_GPIO 0x8600 +#define STM32F746_PI6_FUNC_TIM8_CH2 0x8604 +#define STM32F746_PI6_FUNC_SAI2_SD_A 0x860b +#define STM32F746_PI6_FUNC_FMC_D28 0x860d +#define STM32F746_PI6_FUNC_DCMI_D6 0x860e +#define STM32F746_PI6_FUNC_LCD_B6 0x860f +#define STM32F746_PI6_FUNC_EVENTOUT 0x8610 +#define STM32F746_PI6_FUNC_ANALOG 0x8611 + +#define STM32F746_PI7_FUNC_GPIO 0x8700 +#define STM32F746_PI7_FUNC_TIM8_CH3 0x8704 +#define STM32F746_PI7_FUNC_SAI2_FS_A 0x870b +#define STM32F746_PI7_FUNC_FMC_D29 0x870d +#define STM32F746_PI7_FUNC_DCMI_D7 0x870e +#define STM32F746_PI7_FUNC_LCD_B7 0x870f +#define STM32F746_PI7_FUNC_EVENTOUT 0x8710 +#define STM32F746_PI7_FUNC_ANALOG 0x8711 + +#define STM32F746_PI8_FUNC_GPIO 0x8800 +#define STM32F746_PI8_FUNC_EVENTOUT 0x8810 +#define STM32F746_PI8_FUNC_ANALOG 0x8811 + +#define STM32F746_PI9_FUNC_GPIO 0x8900 +#define STM32F746_PI9_FUNC_CAN1_RX 0x890a +#define STM32F746_PI9_FUNC_FMC_D30 0x890d +#define STM32F746_PI9_FUNC_LCD_VSYNC 0x890f +#define STM32F746_PI9_FUNC_EVENTOUT 0x8910 +#define STM32F746_PI9_FUNC_ANALOG 0x8911 + +#define STM32F746_PI10_FUNC_GPIO 0x8a00 +#define STM32F746_PI10_FUNC_ETH_MII_RX_ER 0x8a0c +#define STM32F746_PI10_FUNC_FMC_D31 0x8a0d +#define STM32F746_PI10_FUNC_LCD_HSYNC 0x8a0f +#define STM32F746_PI10_FUNC_EVENTOUT 0x8a10 +#define STM32F746_PI10_FUNC_ANALOG 0x8a11 + +#define STM32F746_PI11_FUNC_GPIO 0x8b00 +#define STM32F746_PI11_FUNC_OTG_HS_ULPI_DIR 0x8b0b +#define STM32F746_PI11_FUNC_EVENTOUT 0x8b10 +#define STM32F746_PI11_FUNC_ANALOG 0x8b11 + +#define STM32F746_PI12_FUNC_GPIO 0x8c00 +#define STM32F746_PI12_FUNC_LCD_HSYNC 0x8c0f +#define STM32F746_PI12_FUNC_EVENTOUT 0x8c10 +#define STM32F746_PI12_FUNC_ANALOG 0x8c11 + +#define STM32F746_PI13_FUNC_GPIO 0x8d00 +#define STM32F746_PI13_FUNC_LCD_VSYNC 0x8d0f +#define STM32F746_PI13_FUNC_EVENTOUT 0x8d10 +#define STM32F746_PI13_FUNC_ANALOG 0x8d11 + +#define STM32F746_PI14_FUNC_GPIO 0x8e00 +#define STM32F746_PI14_FUNC_LCD_CLK 0x8e0f +#define STM32F746_PI14_FUNC_EVENTOUT 0x8e10 +#define STM32F746_PI14_FUNC_ANALOG 0x8e11 + +#define STM32F746_PI15_FUNC_GPIO 0x8f00 +#define STM32F746_PI15_FUNC_LCD_R0 0x8f0f +#define STM32F746_PI15_FUNC_EVENTOUT 0x8f10 +#define STM32F746_PI15_FUNC_ANALOG 0x8f11 + + +#define STM32F746_PJ0_FUNC_GPIO 0x9000 +#define STM32F746_PJ0_FUNC_LCD_R1 0x900f +#define STM32F746_PJ0_FUNC_EVENTOUT 0x9010 +#define STM32F746_PJ0_FUNC_ANALOG 0x9011 + +#define STM32F746_PJ1_FUNC_GPIO 0x9100 +#define STM32F746_PJ1_FUNC_LCD_R2 0x910f +#define STM32F746_PJ1_FUNC_EVENTOUT 0x9110 +#define STM32F746_PJ1_FUNC_ANALOG 0x9111 + +#define STM32F746_PJ2_FUNC_GPIO 0x9200 +#define STM32F746_PJ2_FUNC_LCD_R3 0x920f +#define STM32F746_PJ2_FUNC_EVENTOUT 0x9210 +#define STM32F746_PJ2_FUNC_ANALOG 0x9211 + +#define STM32F746_PJ3_FUNC_GPIO 0x9300 +#define STM32F746_PJ3_FUNC_LCD_R4 0x930f +#define STM32F746_PJ3_FUNC_EVENTOUT 0x9310 +#define STM32F746_PJ3_FUNC_ANALOG 0x9311 + +#define STM32F746_PJ4_FUNC_GPIO 0x9400 +#define STM32F746_PJ4_FUNC_LCD_R5 0x940f +#define STM32F746_PJ4_FUNC_EVENTOUT 0x9410 +#define STM32F746_PJ4_FUNC_ANALOG 0x9411 + +#define STM32F746_PJ5_FUNC_GPIO 0x9500 +#define STM32F746_PJ5_FUNC_LCD_R6 0x950f +#define STM32F746_PJ5_FUNC_EVENTOUT 0x9510 +#define STM32F746_PJ5_FUNC_ANALOG 0x9511 + +#define STM32F746_PJ6_FUNC_GPIO 0x9600 +#define STM32F746_PJ6_FUNC_LCD_R7 0x960f +#define STM32F746_PJ6_FUNC_EVENTOUT 0x9610 +#define STM32F746_PJ6_FUNC_ANALOG 0x9611 + +#define STM32F746_PJ7_FUNC_GPIO 0x9700 +#define STM32F746_PJ7_FUNC_LCD_G0 0x970f +#define STM32F746_PJ7_FUNC_EVENTOUT 0x9710 +#define STM32F746_PJ7_FUNC_ANALOG 0x9711 + +#define STM32F746_PJ8_FUNC_GPIO 0x9800 +#define STM32F746_PJ8_FUNC_LCD_G1 0x980f +#define STM32F746_PJ8_FUNC_EVENTOUT 0x9810 +#define STM32F746_PJ8_FUNC_ANALOG 0x9811 + +#define STM32F746_PJ9_FUNC_GPIO 0x9900 +#define STM32F746_PJ9_FUNC_LCD_G2 0x990f +#define STM32F746_PJ9_FUNC_EVENTOUT 0x9910 +#define STM32F746_PJ9_FUNC_ANALOG 0x9911 + +#define STM32F746_PJ10_FUNC_GPIO 0x9a00 +#define STM32F746_PJ10_FUNC_LCD_G3 0x9a0f +#define STM32F746_PJ10_FUNC_EVENTOUT 0x9a10 +#define STM32F746_PJ10_FUNC_ANALOG 0x9a11 + +#define STM32F746_PJ11_FUNC_GPIO 0x9b00 +#define STM32F746_PJ11_FUNC_LCD_G4 0x9b0f +#define STM32F746_PJ11_FUNC_EVENTOUT 0x9b10 +#define STM32F746_PJ11_FUNC_ANALOG 0x9b11 + +#define STM32F746_PJ12_FUNC_GPIO 0x9c00 +#define STM32F746_PJ12_FUNC_LCD_B0 0x9c0f +#define STM32F746_PJ12_FUNC_EVENTOUT 0x9c10 +#define STM32F746_PJ12_FUNC_ANALOG 0x9c11 + +#define STM32F746_PJ13_FUNC_GPIO 0x9d00 +#define STM32F746_PJ13_FUNC_LCD_B1 0x9d0f +#define STM32F746_PJ13_FUNC_EVENTOUT 0x9d10 +#define STM32F746_PJ13_FUNC_ANALOG 0x9d11 + +#define STM32F746_PJ14_FUNC_GPIO 0x9e00 +#define STM32F746_PJ14_FUNC_LCD_B2 0x9e0f +#define STM32F746_PJ14_FUNC_EVENTOUT 0x9e10 +#define STM32F746_PJ14_FUNC_ANALOG 0x9e11 + +#define STM32F746_PJ15_FUNC_GPIO 0x9f00 +#define STM32F746_PJ15_FUNC_LCD_B3 0x9f0f +#define STM32F746_PJ15_FUNC_EVENTOUT 0x9f10 +#define STM32F746_PJ15_FUNC_ANALOG 0x9f11 + + +#define STM32F746_PK0_FUNC_GPIO 0xa000 +#define STM32F746_PK0_FUNC_LCD_G5 0xa00f +#define STM32F746_PK0_FUNC_EVENTOUT 0xa010 +#define STM32F746_PK0_FUNC_ANALOG 0xa011 + +#define STM32F746_PK1_FUNC_GPIO 0xa100 +#define STM32F746_PK1_FUNC_LCD_G6 0xa10f +#define STM32F746_PK1_FUNC_EVENTOUT 0xa110 +#define STM32F746_PK1_FUNC_ANALOG 0xa111 + +#define STM32F746_PK2_FUNC_GPIO 0xa200 +#define STM32F746_PK2_FUNC_LCD_G7 0xa20f +#define STM32F746_PK2_FUNC_EVENTOUT 0xa210 +#define STM32F746_PK2_FUNC_ANALOG 0xa211 + +#define STM32F746_PK3_FUNC_GPIO 0xa300 +#define STM32F746_PK3_FUNC_LCD_B4 0xa30f +#define STM32F746_PK3_FUNC_EVENTOUT 0xa310 +#define STM32F746_PK3_FUNC_ANALOG 0xa311 + +#define STM32F746_PK4_FUNC_GPIO 0xa400 +#define STM32F746_PK4_FUNC_LCD_B5 0xa40f +#define STM32F746_PK4_FUNC_EVENTOUT 0xa410 +#define STM32F746_PK4_FUNC_ANALOG 0xa411 + +#define STM32F746_PK5_FUNC_GPIO 0xa500 +#define STM32F746_PK5_FUNC_LCD_B6 0xa50f +#define STM32F746_PK5_FUNC_EVENTOUT 0xa510 +#define STM32F746_PK5_FUNC_ANALOG 0xa511 + +#define STM32F746_PK6_FUNC_GPIO 0xa600 +#define STM32F746_PK6_FUNC_LCD_B7 0xa60f +#define STM32F746_PK6_FUNC_EVENTOUT 0xa610 +#define STM32F746_PK6_FUNC_ANALOG 0xa611 + +#define STM32F746_PK7_FUNC_GPIO 0xa700 +#define STM32F746_PK7_FUNC_LCD_DE 0xa70f +#define STM32F746_PK7_FUNC_EVENTOUT 0xa710 +#define STM32F746_PK7_FUNC_ANALOG 0xa711 + +#endif /* _DT_BINDINGS_STM32F746_PINFUNC_H */ -- cgit v1.2.3 From 8be0b84e58a9b07c314f920792926c5c5a53d3da Mon Sep 17 00:00:00 2001 From: Salvatore Benedetto Date: Mon, 4 Jul 2016 17:21:38 +0100 Subject: crypto: rsa - Store rest of the private key components When parsing a private key, store all non-optional fields. These are required for enabling CRT mode for decrypt and verify Signed-off-by: Salvatore Benedetto Signed-off-by: Herbert Xu --- include/crypto/internal/rsa.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/crypto/internal/rsa.h b/include/crypto/internal/rsa.h index d6c042a2ee52..9e8f1590de98 100644 --- a/include/crypto/internal/rsa.h +++ b/include/crypto/internal/rsa.h @@ -19,17 +19,37 @@ * @n : RSA modulus raw byte stream * @e : RSA public exponent raw byte stream * @d : RSA private exponent raw byte stream + * @p : RSA prime factor p of n raw byte stream + * @q : RSA prime factor q of n raw byte stream + * @dp : RSA exponent d mod (p - 1) raw byte stream + * @dq : RSA exponent d mod (q - 1) raw byte stream + * @qinv : RSA CRT coefficient q^(-1) mod p raw byte stream * @n_sz : length in bytes of RSA modulus n * @e_sz : length in bytes of RSA public exponent * @d_sz : length in bytes of RSA private exponent + * @p_sz : length in bytes of p field + * @q_sz : length in bytes of q field + * @dp_sz : length in bytes of dp field + * @dq_sz : length in bytes of dq field + * @qinv_sz : length in bytes of qinv field */ struct rsa_key { const u8 *n; const u8 *e; const u8 *d; + const u8 *p; + const u8 *q; + const u8 *dp; + const u8 *dq; + const u8 *qinv; size_t n_sz; size_t e_sz; size_t d_sz; + size_t p_sz; + size_t q_sz; + size_t dp_sz; + size_t dq_sz; + size_t qinv_sz; }; int rsa_parse_pub_key(struct rsa_key *rsa_key, const void *key, -- cgit v1.2.3 From 503eebc265dcf5c512454fd5a6b6673ea4f1d7f2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 5 Jul 2016 11:27:37 +0200 Subject: net: add dev arg to ndo_neigh_construct/destroy As the following patch will allow upper devices to follow the call down lower devices, we need to add dev here and not rely on n->dev. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0c6ee2c5099f..91af73c9dd51 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1209,8 +1209,10 @@ struct net_device_ops { netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); - int (*ndo_neigh_construct)(struct neighbour *n); - void (*ndo_neigh_destroy)(struct neighbour *n); + int (*ndo_neigh_construct)(struct net_device *dev, + struct neighbour *n); + void (*ndo_neigh_destroy)(struct net_device *dev, + struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], -- cgit v1.2.3 From 18bfb924f0005a728caadd90ba755b2a660bf441 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 5 Jul 2016 11:27:38 +0200 Subject: net: introduce default neigh_construct/destroy ndo calls for L2 upper devices L2 upper device needs to propagate neigh_construct/destroy calls down to lower devices. Do this by defining default ndo functions and use them in team, bond, bridge and vlan. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 91af73c9dd51..49736a31acaa 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3845,6 +3845,10 @@ void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); +int netdev_default_l2upper_neigh_construct(struct net_device *dev, + struct neighbour *n); +void netdev_default_l2upper_neigh_destroy(struct net_device *dev, + struct neighbour *n); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 -- cgit v1.2.3 From 2a4501ae18b52fcdf553404286e6cefabd1d17ec Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 5 Jul 2016 11:27:42 +0200 Subject: neigh: Send a notification when DELAY_PROBE_TIME changes When the data plane is offloaded the traffic doesn't go through the networking stack. Therefore, after first resolving a neighbour the NUD state machine will transition it from REACHABLE to STALE until it's finally deleted by the garbage collector. To prevent such situations the offloading driver should notify the NUD state machine on any neighbours that were recently used. The driver's polling interval should be set so that the NUD state machine can function as if the traffic wasn't offloaded. Currently, there are no in-tree drivers that can report confirmation for a neighbour, but only 'used' indication. Therefore, the polling interval should be set according to DELAY_FIRST_PROBE_TIME, as a neighbour will transition from REACHABLE state to DELAY (instead of STALE) if "a packet was sent within the last DELAY_FIRST_PROBE_TIME seconds" (RFC 4861). Send a netevent whenever the DELAY_FIRST_PROBE_TIME changes - either via netlink or sysctl - so that offloading drivers can correctly set their polling interval. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/netevent.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netevent.h b/include/net/netevent.h index d8bbb38584b6..f440df172b56 100644 --- a/include/net/netevent.h +++ b/include/net/netevent.h @@ -24,6 +24,7 @@ struct netevent_redirect { enum netevent_notif_type { NETEVENT_NEIGH_UPDATE = 1, /* arg is struct neighbour ptr */ NETEVENT_REDIRECT, /* arg is struct netevent_redirect ptr */ + NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */ }; int register_netevent_notifier(struct notifier_block *nb); -- cgit v1.2.3 From 1f5bd336b9150560458b03460cbcfcfbcf8995b1 Mon Sep 17 00:00:00 2001 From: Ming Lin Date: Mon, 13 Jun 2016 16:45:21 +0200 Subject: blk-mq: add blk_mq_alloc_request_hctx For some protocols like NVMe over Fabrics we need to be able to send initialization commands to a specific queue. Based on an earlier patch from Christoph Hellwig . Signed-off-by: Ming Lin [hch: disallow sleeping allocation, req_op fixes] Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2498fdf3a503..cbfd8ca5f13e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -196,6 +196,8 @@ enum { struct request *blk_mq_alloc_request(struct request_queue *q, int rw, unsigned int flags); +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op, + unsigned int flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags); -- cgit v1.2.3 From eb793e2c9286cca415423edff4942e4ba28e3cd4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 13 Jun 2016 16:45:25 +0200 Subject: nvme.h: add NVMe over Fabrics definitions The NVMe over Fabrics specification defines a protocol interface and related extensions to NVMe that enable operation over network protocols. The NVMe over Fabrics specification has an NVMe Transport binding for each NVMe Transport. This patch adds the fabrics related definitions: - fabric specific command set and error codes - transport addressing and binding definitions - fabrics sgl extensions - controller identification fabrics enhancements - discovery log page definition Signed-off-by: Armen Baloyan Signed-off-by: James Smart Signed-off-by: Jay Freyensee Signed-off-by: Ming Lin Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 337 ++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 318 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index dc815cc6718d..75250303bcb3 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -16,6 +16,78 @@ #define _LINUX_NVME_H #include +#include + +/* NQN names in commands fields specified one size */ +#define NVMF_NQN_FIELD_LEN 256 + +/* However the max length of a qualified name is another size */ +#define NVMF_NQN_SIZE 223 + +#define NVMF_TRSVCID_SIZE 32 +#define NVMF_TRADDR_SIZE 256 +#define NVMF_TSAS_SIZE 256 + +#define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" + +#define NVME_RDMA_IP_PORT 4420 + +enum nvme_subsys_type { + NVME_NQN_DISC = 1, /* Discovery type target subsystem */ + NVME_NQN_NVME = 2, /* NVME type target subsystem */ +}; + +/* Address Family codes for Discovery Log Page entry ADRFAM field */ +enum { + NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ + NVMF_ADDR_FAMILY_IP4 = 1, /* IP4 */ + NVMF_ADDR_FAMILY_IP6 = 2, /* IP6 */ + NVMF_ADDR_FAMILY_IB = 3, /* InfiniBand */ + NVMF_ADDR_FAMILY_FC = 4, /* Fibre Channel */ +}; + +/* Transport Type codes for Discovery Log Page entry TRTYPE field */ +enum { + NVMF_TRTYPE_RDMA = 1, /* RDMA */ + NVMF_TRTYPE_FC = 2, /* Fibre Channel */ + NVMF_TRTYPE_LOOP = 254, /* Reserved for host usage */ + NVMF_TRTYPE_MAX, +}; + +/* Transport Requirements codes for Discovery Log Page entry TREQ field */ +enum { + NVMF_TREQ_NOT_SPECIFIED = 0, /* Not specified */ + NVMF_TREQ_REQUIRED = 1, /* Required */ + NVMF_TREQ_NOT_REQUIRED = 2, /* Not Required */ +}; + +/* RDMA QP Service Type codes for Discovery Log Page entry TSAS + * RDMA_QPTYPE field + */ +enum { + NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */ + NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */ +}; + +/* RDMA QP Service Type codes for Discovery Log Page entry TSAS + * RDMA_QPTYPE field + */ +enum { + NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */ + NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */ + NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */ + NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */ + NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */ +}; + +/* RDMA Connection Management Service Type codes for Discovery Log Page + * entry TSAS RDMA_CMS field + */ +enum { + NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */ +}; + +#define NVMF_AQ_DEPTH 32 enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -117,7 +189,8 @@ struct nvme_id_ctrl { __le32 rtd3r; __le32 rtd3e; __le32 oaes; - __u8 rsvd96[160]; + __le32 ctratt; + __u8 rsvd100[156]; __le16 oacs; __u8 acl; __u8 aerl; @@ -132,7 +205,7 @@ struct nvme_id_ctrl { __u8 rsvd270[242]; __u8 sqes; __u8 cqes; - __u8 rsvd514[2]; + __le16 maxcmd; __le32 nn; __le16 oncs; __le16 fuses; @@ -145,7 +218,15 @@ struct nvme_id_ctrl { __le16 acwu; __u8 rsvd534[2]; __le32 sgls; - __u8 rsvd540[1508]; + __u8 rsvd540[228]; + char subnqn[256]; + __u8 rsvd1024[768]; + __le32 ioccsz; + __le32 iorcsz; + __le16 icdoff; + __u8 ctrattr; + __u8 msdbd; + __u8 rsvd1804[244]; struct nvme_id_power_state psd[32]; __u8 vs[1024]; }; @@ -306,6 +387,61 @@ enum nvme_opcode { nvme_cmd_resv_release = 0x15, }; +/* + * Descriptor subtype - lower 4 bits of nvme_(keyed_)sgl_desc identifier + * + * @NVME_SGL_FMT_ADDRESS: absolute address of the data block + * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation + * request subtype + */ +enum { + NVME_SGL_FMT_ADDRESS = 0x00, + NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_INVALIDATE = 0x0f, +}; + +/* + * Descriptor type - upper 4 bits of nvme_(keyed_)sgl_desc identifier + * + * For struct nvme_sgl_desc: + * @NVME_SGL_FMT_DATA_DESC: data block descriptor + * @NVME_SGL_FMT_SEG_DESC: sgl segment descriptor + * @NVME_SGL_FMT_LAST_SEG_DESC: last sgl segment descriptor + * + * For struct nvme_keyed_sgl_desc: + * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + */ +enum { + NVME_SGL_FMT_DATA_DESC = 0x00, + NVME_SGL_FMT_SEG_DESC = 0x02, + NVME_SGL_FMT_LAST_SEG_DESC = 0x03, + NVME_KEY_SGL_FMT_DATA_DESC = 0x04, +}; + +struct nvme_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +struct nvme_keyed_sgl_desc { + __le64 addr; + __u8 length[3]; + __u8 key[4]; + __u8 type; +}; + +union nvme_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct nvme_sgl_desc sgl; + struct nvme_keyed_sgl_desc ksgl; +}; + /* * Lowest two bits of our flags field (FUSE field in the spec): * @@ -336,8 +472,7 @@ struct nvme_common_command { __le32 nsid; __le32 cdw2[2]; __le64 metadata; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 cdw10[6]; }; @@ -348,8 +483,7 @@ struct nvme_rw_command { __le32 nsid; __u64 rsvd2; __le64 metadata; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le64 slba; __le16 length; __le16 control; @@ -389,8 +523,7 @@ struct nvme_dsm_cmd { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 nr; __le32 attributes; __u32 rsvd12[4]; @@ -454,6 +587,7 @@ enum { NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), NVME_FWACT_REPL_ACTV = (1 << 3), @@ -466,8 +600,7 @@ struct nvme_identify { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 cns; __u32 rsvd11[5]; }; @@ -478,8 +611,7 @@ struct nvme_features { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 fid; __le32 dword11; __u32 rsvd12[4]; @@ -538,8 +670,7 @@ struct nvme_download_firmware { __u8 flags; __u16 command_id; __u32 rsvd1[5]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 numd; __le32 offset; __u32 rsvd12[4]; @@ -561,8 +692,7 @@ struct nvme_get_log_page_command { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __u8 lid; __u8 rsvd10; __le16 numdl; @@ -573,6 +703,126 @@ struct nvme_get_log_page_command { __u32 rsvd14[2]; }; +/* + * Fabrics subcommands. + */ +enum nvmf_fabrics_opcode { + nvme_fabrics_command = 0x7f, +}; + +enum nvmf_capsule_command { + nvme_fabrics_type_property_set = 0x00, + nvme_fabrics_type_connect = 0x01, + nvme_fabrics_type_property_get = 0x04, +}; + +struct nvmf_common_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 ts[24]; +}; + +/* + * The legal cntlid range a NVMe Target will provide. + * Note that cntlid of value 0 is considered illegal in the fabrics world. + * Devices based on earlier specs did not have the subsystem concept; + * therefore, those devices had their cntlid value set to 0 as a result. + */ +#define NVME_CNTLID_MIN 1 +#define NVME_CNTLID_MAX 0xffef +#define NVME_CNTLID_DYNAMIC 0xffff + +#define MAX_DISC_LOGS 255 + +/* Discovery log page entry */ +struct nvmf_disc_rsp_page_entry { + __u8 trtype; + __u8 adrfam; + __u8 nqntype; + __u8 treq; + __le16 portid; + __le16 cntlid; + __le16 asqsz; + __u8 resv8[22]; + char trsvcid[NVMF_TRSVCID_SIZE]; + __u8 resv64[192]; + char subnqn[NVMF_NQN_FIELD_LEN]; + char traddr[NVMF_TRADDR_SIZE]; + union tsas { + char common[NVMF_TSAS_SIZE]; + struct rdma { + __u8 qptype; + __u8 prtype; + __u8 cms; + __u8 resv3[5]; + __u16 pkey; + __u8 resv10[246]; + } rdma; + } tsas; +}; + +/* Discovery log page header */ +struct nvmf_disc_rsp_page_hdr { + __le64 genctr; + __le64 numrec; + __le16 recfmt; + __u8 resv14[1006]; + struct nvmf_disc_rsp_page_entry entries[0]; +}; + +struct nvmf_connect_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __le16 recfmt; + __le16 qid; + __le16 sqsize; + __u8 cattr; + __u8 resv3; + __le32 kato; + __u8 resv4[12]; +}; + +struct nvmf_connect_data { + uuid_le hostid; + __le16 cntlid; + char resv4[238]; + char subsysnqn[NVMF_NQN_FIELD_LEN]; + char hostnqn[NVMF_NQN_FIELD_LEN]; + char resv5[256]; +}; + +struct nvmf_property_set_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 attrib; + __u8 resv3[3]; + __le32 offset; + __le64 value; + __u8 resv4[8]; +}; + +struct nvmf_property_get_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 attrib; + __u8 resv3[3]; + __le32 offset; + __u8 resv4[16]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -587,15 +837,29 @@ struct nvme_command { struct nvme_dsm_cmd dsm; struct nvme_abort_cmd abort; struct nvme_get_log_page_command get_log_page; + struct nvmf_common_command fabrics; + struct nvmf_connect_command connect; + struct nvmf_property_set_command prop_set; + struct nvmf_property_get_command prop_get; }; }; static inline bool nvme_is_write(struct nvme_command *cmd) { + /* + * What a mess... + * + * Why can't we simply have a Fabrics In and Fabrics out command? + */ + if (unlikely(cmd->common.opcode == nvme_fabrics_command)) + return cmd->fabrics.opcode & 1; return cmd->common.opcode & 1; } enum { + /* + * Generic Command Status: + */ NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, NVME_SC_INVALID_FIELD = 0x2, @@ -614,10 +878,18 @@ enum { NVME_SC_SGL_INVALID_DATA = 0xf, NVME_SC_SGL_INVALID_METADATA = 0x10, NVME_SC_SGL_INVALID_TYPE = 0x11, + + NVME_SC_SGL_INVALID_OFFSET = 0x16, + NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, NVME_SC_RESERVATION_CONFLICT = 0x83, + + /* + * Command Specific Status: + */ NVME_SC_CQ_INVALID = 0x100, NVME_SC_QID_INVALID = 0x101, NVME_SC_QUEUE_SIZE = 0x102, @@ -635,9 +907,29 @@ enum { NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, NVME_SC_FEATURE_NOT_PER_NS = 0x10f, NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, + + /* + * I/O Command Set Specific - NVM commands: + */ NVME_SC_BAD_ATTRIBUTES = 0x180, NVME_SC_INVALID_PI = 0x181, NVME_SC_READ_ONLY = 0x182, + + /* + * I/O Command Set Specific - Fabrics commands: + */ + NVME_SC_CONNECT_FORMAT = 0x180, + NVME_SC_CONNECT_CTRL_BUSY = 0x181, + NVME_SC_CONNECT_INVALID_PARAM = 0x182, + NVME_SC_CONNECT_RESTART_DISC = 0x183, + NVME_SC_CONNECT_INVALID_HOST = 0x184, + + NVME_SC_DISCOVERY_RESTART = 0x190, + NVME_SC_AUTH_REQUIRED = 0x191, + + /* + * Media and Data Integrity Errors: + */ NVME_SC_WRITE_FAULT = 0x280, NVME_SC_READ_ERROR = 0x281, NVME_SC_GUARD_CHECK = 0x282, @@ -645,12 +937,19 @@ enum { NVME_SC_REFTAG_CHECK = 0x284, NVME_SC_COMPARE_FAILED = 0x285, NVME_SC_ACCESS_DENIED = 0x286, + NVME_SC_DNR = 0x4000, }; struct nvme_completion { - __le32 result; /* Used by admin commands to return data */ - __u32 rsvd; + /* + * Used by Admin and Fabrics commands to return data: + */ + union { + __le16 result16; + __le32 result; + __le64 result64; + }; __le16 sq_head; /* how much of this queue may be reclaimed */ __le16 sq_id; /* submission queue that generated this entry */ __u16 command_id; /* of the command which completed */ -- cgit v1.2.3 From 7b89eae29eec4dd9259acd82ed57bec8d9e430ca Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Mon, 13 Jun 2016 16:45:27 +0200 Subject: nvme.h: Add keep-alive opcode and identify controller attribute KAS: keep-alive support and granularity of kato in units of 100 ms nvme_admin_keep_alive opcode: 0x18 Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- include/linux/nvme.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 75250303bcb3..d8b37bab2887 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -202,7 +202,9 @@ struct nvme_id_ctrl { __u8 apsta; __le16 wctemp; __le16 cctemp; - __u8 rsvd270[242]; + __u8 rsvd270[50]; + __le16 kas; + __u8 rsvd322[190]; __u8 sqes; __u8 cqes; __le16 maxcmd; @@ -556,6 +558,7 @@ enum nvme_admin_opcode { nvme_admin_async_event = 0x0c, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_keep_alive = 0x18, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, nvme_admin_security_recv = 0x82, @@ -580,6 +583,7 @@ enum { NVME_FEAT_WRITE_ATOMIC = 0x0a, NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_AUTO_PST = 0x0c, + NVME_FEAT_KATO = 0x0f, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, -- cgit v1.2.3 From 0bd23d09b874e53bd1a2fe2296030aa2720d7b08 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 29 Jun 2016 14:54:46 -0500 Subject: vfs: Don't modify inodes with a uid or gid unknown to the vfs When a filesystem outside of init_user_ns is mounted it could have uids and gids stored in it that do not map to init_user_ns. The plan is to allow those filesystems to set i_uid to INVALID_UID and i_gid to INVALID_GID for unmapped uids and gids and then to handle that strange case in the vfs to ensure there is consistent robust handling of the weirdness. Upon a careful review of the vfs and filesystems about the only case where there is any possibility of confusion or trouble is when the inode is written back to disk. In that case filesystems typically read the inode->i_uid and inode->i_gid and write them to disk even when just an inode timestamp is being updated. Which leads to a rule that is very simple to implement and understand inodes whose i_uid or i_gid is not valid may not be written. In dealing with access times this means treat those inodes as if the inode flag S_NOATIME was set. Reads of the inodes appear safe and useful, but any write or modification is disallowed. The only inode write that is allowed is a chown that sets the uid and gid on the inode to valid values. After such a chown the inode is normal and may be treated as such. Denying all writes to inodes with uids or gids unknown to the vfs also prevents several oddball cases where corruption would have occurred because the vfs does not have complete information. One problem case that is prevented is attempting to use the gid of a directory for new inodes where the directories sgid bit is set but the directories gid is not mapped. Another problem case avoided is attempting to update the evm hash after setxattr, removexattr, and setattr. As the evm hash includeds the inode->i_uid or inode->i_gid not knowning the uid or gid prevents a correct evm hash from being computed. evm hash verification also fails when i_uid or i_gid is unknown but that is essentially harmless as it does not cause filesystem corruption. Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 375e37f42cdf..cb25ceb6d1ef 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1874,6 +1874,11 @@ struct super_operations { #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) +static inline bool HAS_UNMAPPED_ID(struct inode *inode) +{ + return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); +} + /* * Inode state bits. Protected by inode->i_lock * -- cgit v1.2.3 From d49d37624a1931c2f3b5d0cbe95bd5181cbdc279 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 30 Jun 2016 16:31:01 -0500 Subject: quota: Ensure qids map to the filesystem Introduce the helper qid_has_mapping and use it to ensure that the quota system only considers qids that map to the filesystems s_user_ns. In practice for quota supporting filesystems today this is the exact same check as qid_valid. As only 0xffffffff aka (qid_t)-1 does not map into init_user_ns. Replace the qid_valid calls with qid_has_mapping as values come in from userspace. This is harmless today and it prepares the quota system to work on filesystems with quotas but mounted by unprivileged users. Call qid_has_mapping from dqget. This ensures the passed in qid has a prepresentation on the underlying filesystem. Previously this was unnecessary as filesystesm never had qids that could not map. With the introduction of filesystems outside of s_user_ns this will not remain true. All of this ensures the quota code never has to deal with qids that don't map to the underlying filesystem. Cc: Jan Kara Acked-by: Seth Forshee Signed-off-by: "Eric W. Biederman" --- include/linux/quota.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/quota.h b/include/linux/quota.h index 9dfb6bce8c9e..1db16ee39b31 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -179,6 +179,16 @@ static inline struct kqid make_kqid_projid(kprojid_t projid) return kqid; } +/** + * qid_has_mapping - Report if a qid maps into a user namespace. + * @ns: The user namespace to see if a value maps into. + * @qid: The kernel internal quota identifier to test. + */ +static inline bool qid_has_mapping(struct user_namespace *ns, struct kqid qid) +{ + return from_kqid(ns, qid) != (qid_t) -1; +} + extern spinlock_t dq_data_lock; -- cgit v1.2.3 From 81754357770ebd900801231e7bc8d151ddc00498 Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Thu, 11 Dec 2014 10:15:45 -0600 Subject: fs: Update i_[ug]id_(read|write) to translate relative to s_user_ns For filesystems mounted from a user namespace on-disk ids should be translated relative to s_users_ns rather than init_user_ns. When an id in the filesystem doesn't exist in s_user_ns the associated id in the inode will be set to INVALID_[UG]ID, which turns these into de facto "nobody" ids. This actually maps pretty well into the way most code already works, and those places where it didn't were fixed in previous patches. Moving forward vfs code needs to be careful to handle instances where ids in inodes may be invalid. Signed-off-by: Seth Forshee Signed-off-by: Eric W. Biederman --- include/linux/fs.h | 50 +++++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index cb25ceb6d1ef..8aa9b72e0bc5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -831,31 +831,6 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) #endif } -/* Helper functions so that in most cases filesystems will - * not need to deal directly with kuid_t and kgid_t and can - * instead deal with the raw numeric values that are stored - * in the filesystem. - */ -static inline uid_t i_uid_read(const struct inode *inode) -{ - return from_kuid(&init_user_ns, inode->i_uid); -} - -static inline gid_t i_gid_read(const struct inode *inode) -{ - return from_kgid(&init_user_ns, inode->i_gid); -} - -static inline void i_uid_write(struct inode *inode, uid_t uid) -{ - inode->i_uid = make_kuid(&init_user_ns, uid); -} - -static inline void i_gid_write(struct inode *inode, gid_t gid) -{ - inode->i_gid = make_kgid(&init_user_ns, gid); -} - static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); @@ -1461,6 +1436,31 @@ struct super_block { struct list_head s_inodes; /* all inodes */ }; +/* Helper functions so that in most cases filesystems will + * not need to deal directly with kuid_t and kgid_t and can + * instead deal with the raw numeric values that are stored + * in the filesystem. + */ +static inline uid_t i_uid_read(const struct inode *inode) +{ + return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); +} + +static inline gid_t i_gid_read(const struct inode *inode) +{ + return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); +} + +static inline void i_uid_write(struct inode *inode, uid_t uid) +{ + inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); +} + +static inline void i_gid_write(struct inode *inode, gid_t gid) +{ + inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); +} + extern struct timespec current_fs_time(struct super_block *sb); /* -- cgit v1.2.3 From a4a551b8f1d4c4ebffd0f49dfef44df3128546f8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 29 Jun 2016 19:56:48 +0900 Subject: ftrace: Reduce size of function graph entries Currently ftrace_graph_ent{,_entry} and ftrace_graph_ret{,_entry} struct can have padding bytes at the end due to alignment in 64-bit data type. As these data are recorded so frequently, those paddings waste non-negligible space. As the ring buffer maintains alignment properly for each architecture, just to remove the extra padding using 'packed' attribute. ftrace_graph_ent_entry: 24 -> 20 ftrace_graph_ret_entry: 48 -> 44 Also I moved the 'overrun' field in struct ftrace_graph_ret to minimize the padding in the middle. Tested on x86_64 only. Link: http://lkml.kernel.org/r/1467197808-13578-1-git-send-email-namhyung@kernel.org Cc: Ingo Molnar Cc: linux-arch@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 66a36a815f0a..7d565afe35d2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -754,23 +754,27 @@ static inline void ftrace_init(void) { } /* * Structure that defines an entry function trace. + * It's already packed but the attribute "packed" is needed + * to remove extra padding at the end. */ struct ftrace_graph_ent { unsigned long func; /* Current function */ int depth; -}; +} __packed; /* * Structure that defines a return function trace. + * It's already packed but the attribute "packed" is needed + * to remove extra padding at the end. */ struct ftrace_graph_ret { unsigned long func; /* Current function */ - unsigned long long calltime; - unsigned long long rettime; /* Number of functions that overran the depth limit for current task */ unsigned long overrun; + unsigned long long calltime; + unsigned long long rettime; int depth; -}; +} __packed; /* Type of the callback handlers for tracing function graph*/ typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */ -- cgit v1.2.3 From a5864c999de6703f7ce908f72337568520c6cad3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 3 Jun 2016 17:07:19 -0400 Subject: NFS: Do not serialise O_DIRECT reads and writes Allow dio requests to be scheduled in parallel, but ensuring that they do not conflict with buffered I/O. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 120dd04b553c..225d17d35277 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -210,6 +210,7 @@ struct nfs_inode { #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ +#define NFS_INO_ODIRECT (12) /* I/O setting is O_DIRECT */ static inline struct nfs_inode *NFS_I(const struct inode *inode) { -- cgit v1.2.3 From be527494e02b89e03485955b30de6c1e976a07eb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 22 Jun 2016 08:19:36 -0400 Subject: NFS: Remove unused function nfs_revalidate_mapping_protected() Clean up... Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 225d17d35277..810124b33327 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -351,7 +351,6 @@ extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *ino extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_revalidate_mapping_rcu(struct inode *inode); -extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, -- cgit v1.2.3 From 243848fc018cb98c2a70c39fe1f93eb266c79835 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:19 +0800 Subject: xen/grant-table: Move xlated_setup_gnttab_pages to common place Move xlated_setup_gnttab_pages to common place, so it can be reused by ARM to setup grant table. Rename it to xen_xlate_map_ballooned_pages. Signed-off-by: Shannon Zhao Reviewed-by: Stefano Stabellini Reviewed-by: Julien Grall Tested-by: Julien Grall --- include/xen/xen-ops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 86abe07b20ec..072be1c29917 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -85,6 +85,8 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma, struct page **pages); int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, int nr, struct page **pages); +int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr, + unsigned long nr_grant_frames); bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); -- cgit v1.2.3 From 712a5b77cb5a1d3028a8c202f4f839802a03f19f Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:22 +0800 Subject: xen: memory : Add new XENMAPSPACE type XENMAPSPACE_dev_mmio Add a new type of Xen map space for Dom0 to map device's MMIO region. Signed-off-by: Shannon Zhao Reviewed-by: Julien Grall Tested-by: Julien Grall --- include/xen/interface/memory.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/xen/interface/memory.h b/include/xen/interface/memory.h index 2ecfe4f700d9..9aa8988cb340 100644 --- a/include/xen/interface/memory.h +++ b/include/xen/interface/memory.h @@ -160,6 +160,7 @@ DEFINE_GUEST_HANDLE_STRUCT(xen_machphys_mapping_t); #define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom, * XENMEM_add_to_physmap_range only. */ +#define XENMAPSPACE_dev_mmio 5 /* device mmio region */ /* * Sets the GPFN at which a particular page appears in the specified guest's -- cgit v1.2.3 From b6f0bcc23fa9cb32752cbf263d4014a21f132f92 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:25 +0800 Subject: Xen: public/hvm: sync changes of HVM_PARAM_CALLBACK_VIA ABI from Xen Sync the changes of HVM_PARAM_CALLBACK_VIA ABI introduced by Xen commit (public/hvm: export the HVM_PARAM_CALLBACK_VIA ABI in the API). Signed-off-by: Shannon Zhao Acked-by: Stefano Stabellini Tested-by: Julien Grall --- include/xen/interface/hvm/params.h | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h index a6c79911e729..70ad20834e13 100644 --- a/include/xen/interface/hvm/params.h +++ b/include/xen/interface/hvm/params.h @@ -27,16 +27,31 @@ * Parameter space for HVMOP_{set,get}_param. */ +#define HVM_PARAM_CALLBACK_IRQ 0 /* * How should CPU0 event-channel notifications be delivered? - * val[63:56] == 0: val[55:0] is a delivery GSI (Global System Interrupt). - * val[63:56] == 1: val[55:0] is a delivery PCI INTx line, as follows: - * Domain = val[47:32], Bus = val[31:16], - * DevFn = val[15: 8], IntX = val[ 1: 0] - * val[63:56] == 2: val[7:0] is a vector number. + * * If val == 0 then CPU0 event-channel notifications are not delivered. + * If val != 0, val[63:56] encodes the type, as follows: + */ + +#define HVM_PARAM_CALLBACK_TYPE_GSI 0 +/* + * val[55:0] is a delivery GSI. GSI 0 cannot be used, as it aliases val == 0, + * and disables all notifications. + */ + +#define HVM_PARAM_CALLBACK_TYPE_PCI_INTX 1 +/* + * val[55:0] is a delivery PCI INTx line: + * Domain = val[47:32], Bus = val[31:16] DevFn = val[15:8], IntX = val[1:0] + */ + +#define HVM_PARAM_CALLBACK_TYPE_VECTOR 2 +/* + * val[7:0] is a vector number. Check for XENFEAT_hvm_callback_vector to know + * if this delivery method is available. */ -#define HVM_PARAM_CALLBACK_IRQ 0 #define HVM_PARAM_STORE_PFN 1 #define HVM_PARAM_STORE_EVTCHN 2 -- cgit v1.2.3 From 383ff518a79fe3dcece579b9d30be77b219d10f8 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:26 +0800 Subject: xen/hvm/params: Add a new delivery type for event-channel in HVM_PARAM_CALLBACK_IRQ This new delivery type which is for ARM shares the same value with HVM_PARAM_CALLBACK_TYPE_VECTOR which is for x86. val[15:8] is flag: val[7:0] is a PPI. To the flag, bit 8 stands the interrupt mode is edge(1) or level(0) and bit 9 stands the interrupt polarity is active low(1) or high(0). Signed-off-by: Shannon Zhao Acked-by: Stefano Stabellini Reviewed-by: Julien Grall Tested-by: Julien Grall --- include/xen/interface/hvm/params.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h index 70ad20834e13..4d61fc58d99d 100644 --- a/include/xen/interface/hvm/params.h +++ b/include/xen/interface/hvm/params.h @@ -47,11 +47,24 @@ * Domain = val[47:32], Bus = val[31:16] DevFn = val[15:8], IntX = val[1:0] */ +#if defined(__i386__) || defined(__x86_64__) #define HVM_PARAM_CALLBACK_TYPE_VECTOR 2 /* * val[7:0] is a vector number. Check for XENFEAT_hvm_callback_vector to know * if this delivery method is available. */ +#elif defined(__arm__) || defined(__aarch64__) +#define HVM_PARAM_CALLBACK_TYPE_PPI 2 +/* + * val[55:16] needs to be zero. + * val[15:8] is interrupt flag of the PPI used by event-channel: + * bit 8: the PPI is edge(1) or level(0) triggered + * bit 9: the PPI is active low(1) or high(0) + * val[7:0] is a PPI number used by event-channel. + * This is only used by ARM/ARM64 and masking/eoi the interrupt associated to + * the notification is handled by the interrupt controller. + */ +#endif #define HVM_PARAM_STORE_PFN 1 #define HVM_PARAM_STORE_EVTCHN 2 -- cgit v1.2.3 From a62ed500307bfaf4c1a818b69f7c1e7df1039a16 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:31 +0800 Subject: XEN: EFI: Move x86 specific codes to architecture directory Move x86 specific codes to architecture directory and export those EFI runtime service functions. This will be useful for initializing runtime service on ARM later. Signed-off-by: Shannon Zhao Reviewed-by: Stefano Stabellini Tested-by: Julien Grall Signed-off-by: Stefano Stabellini --- include/xen/xen-ops.h | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 072be1c29917..3491582bf50a 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -90,14 +90,28 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr, bool xen_running_on_version_or_later(unsigned int major, unsigned int minor); -#ifdef CONFIG_XEN_EFI -extern efi_system_table_t *xen_efi_probe(void); -#else -static inline efi_system_table_t __init *xen_efi_probe(void) -{ - return NULL; -} -#endif +efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc); +efi_status_t xen_efi_set_time(efi_time_t *tm); +efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, + efi_time_t *tm); +efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm); +efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, + void *data); +efi_status_t xen_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, efi_guid_t *vendor); +efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data); +efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size); +efi_status_t xen_efi_get_next_high_mono_count(u32 *count); +efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list); +efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, + int *reset_type); #ifdef CONFIG_PREEMPT -- cgit v1.2.3 From 9c6098685a1d5df72da61ff7838ebb1524796869 Mon Sep 17 00:00:00 2001 From: Shannon Zhao Date: Thu, 7 Apr 2016 20:03:33 +0800 Subject: FDT: Add a helper to get the subnode by given name Sometimes it needs to check if there is a subnode of given node in FDT by given name. Introduce this helper to get the subnode if it exists. CC: Rob Herring Signed-off-by: Shannon Zhao Acked-by: Stefano Stabellini Acked-by: Rob Herring Tested-by: Julien Grall --- include/linux/of_fdt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 901ec01c9fba..26c3302ae58f 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -53,6 +53,8 @@ extern char __dtb_end[]; extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, int depth, void *data), void *data); +extern int of_get_flat_dt_subnode_by_name(unsigned long node, + const char *uname); extern const void *of_get_flat_dt_prop(unsigned long node, const char *name, int *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); -- cgit v1.2.3 From ecb23dc6f2eff0ce64dd60351a81f376f13b12cc Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 20 May 2016 09:26:48 +0200 Subject: xen: add steal_clock support on x86 The pv_time_ops structure contains a function pointer for the "steal_clock" functionality used only by KVM and Xen on ARM. Xen on x86 uses its own mechanism to account for the "stolen" time a thread wasn't able to run due to hypervisor scheduling. Add support in Xen arch independent time handling for this feature by moving it out of the arm arch into drivers/xen and remove the x86 Xen hack. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Reviewed-by: Stefano Stabellini Signed-off-by: David Vrabel --- include/linux/kernel_stat.h | 1 - include/xen/xen-ops.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 25a822f6f000..44fda64ad434 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -92,7 +92,6 @@ static inline void account_process_tick(struct task_struct *tsk, int user) extern void account_process_tick(struct task_struct *, int user); #endif -extern void account_steal_ticks(unsigned long ticks); extern void account_idle_ticks(unsigned long ticks); #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 3491582bf50a..355275bad2cf 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -21,6 +21,7 @@ void xen_resume_notifier_unregister(struct notifier_block *nb); bool xen_vcpu_stolen(int vcpu); void xen_setup_runstate_info(int cpu); +void xen_time_setup_guest(void); void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); int xen_setup_shutdown_event(void); -- cgit v1.2.3 From 7ba8dba95cb227eb6c270b1aa77f942e45f5e47c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 6 Jul 2016 07:00:28 +0200 Subject: xen: update xen headers Update some Xen headers to be able to use new functionality. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Reviewed-by: Stefano Stabellini Signed-off-by: David Vrabel --- include/xen/interface/vcpu.h | 24 +++++++++++++++--------- include/xen/interface/xen.h | 17 ++++++++++++++++- 2 files changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/xen/interface/vcpu.h b/include/xen/interface/vcpu.h index b05288ce3991..98188c87f5c1 100644 --- a/include/xen/interface/vcpu.h +++ b/include/xen/interface/vcpu.h @@ -75,15 +75,21 @@ */ #define VCPUOP_get_runstate_info 4 struct vcpu_runstate_info { - /* VCPU's current state (RUNSTATE_*). */ - int state; - /* When was current state entered (system time, ns)? */ - uint64_t state_entry_time; - /* - * Time spent in each RUNSTATE_* (ns). The sum of these times is - * guaranteed not to drift from system time. - */ - uint64_t time[4]; + /* VCPU's current state (RUNSTATE_*). */ + int state; + /* When was current state entered (system time, ns)? */ + uint64_t state_entry_time; + /* + * Update indicator set in state_entry_time: + * When activated via VMASST_TYPE_runstate_update_flag, set during + * updates in guest memory mapped copy of vcpu_runstate_info. + */ +#define XEN_RUNSTATE_UPDATE (1ULL << 63) + /* + * Time spent in each RUNSTATE_* (ns). The sum of these times is + * guaranteed not to drift from system time. + */ + uint64_t time[4]; }; DEFINE_GUEST_HANDLE_STRUCT(vcpu_runstate_info); diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h index d1331121c0bd..1b0d189cd3d3 100644 --- a/include/xen/interface/xen.h +++ b/include/xen/interface/xen.h @@ -413,7 +413,22 @@ DEFINE_GUEST_HANDLE_STRUCT(mmuext_op); /* x86/PAE guests: support PDPTs above 4GB. */ #define VMASST_TYPE_pae_extended_cr3 3 -#define MAX_VMASST_TYPE 3 +/* + * x86 guests: Sane behaviour for virtual iopl + * - virtual iopl updated from do_iret() hypercalls. + * - virtual iopl reported in bounce frames. + * - guest kernels assumed to be level 0 for the purpose of iopl checks. + */ +#define VMASST_TYPE_architectural_iopl 4 + +/* + * All guests: activate update indicator in vcpu_runstate_info + * Enable setting the XEN_RUNSTATE_UPDATE flag in guest memory mapped + * vcpu_runstate_info during updates of the runstate information. + */ +#define VMASST_TYPE_runstate_update_flag 5 + +#define MAX_VMASST_TYPE 5 #ifndef __ASSEMBLY__ -- cgit v1.2.3 From c1adf20052d80f776849fa2c1acb472cdeb7786c Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 1 Jul 2016 07:53:51 +0100 Subject: Introduce rb_replace_node_rcu() Implement an RCU-safe variant of rb_replace_node() and rearrange rb_replace_node() to do things in the same order. Signed-off-by: David Howells Acked-by: Peter Zijlstra (Intel) --- include/linux/rbtree.h | 2 ++ include/linux/rbtree_augmented.h | 13 +++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index b6900099ea81..e585018498d5 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -76,6 +76,8 @@ extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); +extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, + struct rb_root *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 14d7b831b63a..d076183e49be 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -130,6 +130,19 @@ __rb_change_child(struct rb_node *old, struct rb_node *new, WRITE_ONCE(root->rb_node, new); } +static inline void +__rb_change_child_rcu(struct rb_node *old, struct rb_node *new, + struct rb_node *parent, struct rb_root *root) +{ + if (parent) { + if (parent->rb_left == old) + rcu_assign_pointer(parent->rb_left, new); + else + rcu_assign_pointer(parent->rb_right, new); + } else + rcu_assign_pointer(root->rb_node, new); +} + extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); -- cgit v1.2.3 From 995f1405610bd8446c5be37d2ffc031a7729e406 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 1 Jul 2016 13:44:53 -0700 Subject: rcu: Suppress sparse warnings for rcu_dereference_raw() Data structures that are used both with and without RCU protection are difficult to write in a sparse-clean manner. If you mark the relevant pointers with __rcu, sparse will complain about all non-RCU uses, but if you don't mark those pointers, sparse will complain about all RCU uses. This commit therefore suppresses sparse warnings for rcu_dereference_raw(), allowing mixed-protection data structures to avoid these warnings. Reported-by: David Howells Signed-off-by: Paul E. McKenney Signed-off-by: David Howells --- include/linux/rcupdate.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5f1533e3d032..85830e6c797b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -611,6 +611,12 @@ static inline void rcu_preempt_sleep_check(void) rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) +#define rcu_dereference_raw(p) \ +({ \ + /* Dependency order vs. p above. */ \ + typeof(p) ________p1 = lockless_dereference(p); \ + ((typeof(*p) __force __kernel *)(________p1)); \ +}) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable @@ -729,8 +735,6 @@ static inline void rcu_preempt_sleep_check(void) __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) -#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/ - /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. -- cgit v1.2.3 From c6e6a0c8be575c830a97b1942dabeab70f423fe0 Mon Sep 17 00:00:00 2001 From: Aviya Erenfeld Date: Tue, 5 Jul 2016 15:23:08 +0300 Subject: nl80211: Add API to support VHT MU-MIMO air sniffer add API to support VHT MU-MIMO air sniffer. in MU-MIMO there are parallel frames on the air while the HW has only one RX. add the capability to sniff one of the MU-MIMO parallel frames by giving the sniffer additional information so it'll know which of the parallel frames it shall follow. Add attribute - NL80211_ATTR_MU_MIMO_GROUP_DATA - for getting a MU-MIMO groupID in order to monitor packets from that group using VHT MU-MIMO. And add attribute -NL80211_ATTR_MU_MIMO_FOLLOW_ADDR - for passing MAC address to monitor mode. that option will be used by VHT MU-MIMO air sniffer to follow a station according to it's MAC address using VHT MU-MIMO. Signed-off-by: Aviya Erenfeld Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 10 ++++++++-- include/uapi/linux/nl80211.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7bbb00d8b2cd..fa4f0f793817 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -330,6 +330,9 @@ struct ieee80211_supported_band { * in a separate chapter. */ +#define VHT_MUMIMO_GROUPS_DATA_LEN (WLAN_MEMBERSHIP_LEN +\ + WLAN_USER_POSITION_LEN) + /** * struct vif_params - describes virtual interface parameters * @use_4addr: use 4-address frames @@ -339,10 +342,13 @@ struct ieee80211_supported_band { * This feature is only fully supported by drivers that enable the * %NL80211_FEATURE_MAC_ON_CREATE flag. Others may support creating ** only p2p devices with specified MAC. + * @vht_mumimo_groups: MU-MIMO groupID. used for monitoring only + * packets belonging to that MU-MIMO groupID. */ struct vif_params { - int use_4addr; - u8 macaddr[ETH_ALEN]; + int use_4addr; + u8 macaddr[ETH_ALEN]; + u8 vht_mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN]; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 53c8278827a0..1d7da7888dcf 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1829,6 +1829,25 @@ enum nl80211_commands { * %NL80211_ATTR_EXT_CAPA_MASK, to specify the extended capabilities per * interface type. * + * @NL80211_ATTR_MU_MIMO_GROUP_DATA: array of 24 bytes that defines a MU-MIMO + * groupID for monitor mode. + * The first 8 bytes are a mask that defines the membership in each + * group (there are 64 groups, group 0 and 63 are reserved), + * each bit represents a group and set to 1 for being a member in + * that group and 0 for not being a member. + * The remaining 16 bytes define the position in each group: 2 bits for + * each group. + * (smaller group numbers represented on most significant bits and bigger + * group numbers on least significant bits.) + * This attribute is used only if all interfaces are in monitor mode. + * Set this attribute in order to monitor packets using the given MU-MIMO + * groupID data. + * to turn off that feature set all the bits of the groupID to zero. + * @NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR: mac address for the sniffer to follow + * when using MU-MIMO air sniffer. + * to turn that feature off set an invalid mac address + * (e.g. FF:FF:FF:FF:FF:FF) + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2213,6 +2232,9 @@ enum nl80211_attrs { NL80211_ATTR_IFTYPE_EXT_CAPA, + NL80211_ATTR_MU_MIMO_GROUP_DATA, + NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4479,6 +4501,12 @@ enum nl80211_feature_flags { * %NL80211_CMD_ASSOCIATE and %NL80211_CMD_CONNECT requests, which will set * the ASSOC_REQ_USE_RRM flag in the association request even if * NL80211_FEATURE_QUIET is not advertized. + * @NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER: This device supports MU-MIMO air + * sniffer which means that it can be configured to hear packets from + * certain groups which can be configured by the + * %NL80211_ATTR_MU_MIMO_GROUP_DATA attribute, + * or can be configured to follow a station by configuring the + * %NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR attribute. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4486,6 +4514,7 @@ enum nl80211_feature_flags { enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_VHT_IBSS, NL80211_EXT_FEATURE_RRM, + NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 1d76250bd34af86c6498fc51e50cab3bfbbeceaa Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Tue, 5 Jul 2016 17:10:13 +0300 Subject: nl80211: support beacon report scanning Beacon report radio measurement requires reporting observed BSSs on the channels specified in the beacon request. If the measurement mode is set to passive or active, it requires actually performing a scan (passive or active, accordingly), and reporting the time that the scan was started and the time each beacon/probe was received (both in terms of TSF of the BSS of the requesting AP). If the request mode is table, this information is optional. In addition, the radio measurement request specifies the channel dwell time for the measurement. In order to use scan for beacon report when the mode is active or passive, add a parameter to scan request that specifies the channel dwell time, and add scan start time and beacon received time to scan results information. Supporting beacon report is required for Multi Band Operation (MBO). Signed-off-by: Assaf Krauss Signed-off-by: David Spinadel Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 40 +++++++++++++++++++++++++++++++++++----- include/uapi/linux/nl80211.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fa4f0f793817..e2658e392a1f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1423,6 +1423,21 @@ struct cfg80211_ssid { u8 ssid_len; }; +/** + * struct cfg80211_scan_info - information about completed scan + * @scan_start_tsf: scan start time in terms of the TSF of the BSS that the + * wireless device that requested the scan is connected to. If this + * information is not available, this field is left zero. + * @tsf_bssid: the BSSID according to which %scan_start_tsf is set. + * @aborted: set to true if the scan was aborted for any reason, + * userspace will be notified of that + */ +struct cfg80211_scan_info { + u64 scan_start_tsf; + u8 tsf_bssid[ETH_ALEN] __aligned(2); + bool aborted; +}; + /** * struct cfg80211_scan_request - scan request description * @@ -1433,12 +1448,17 @@ struct cfg80211_ssid { * @scan_width: channel width for scanning * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets + * @duration: how long to listen on each channel, in TUs. If + * %duration_mandatory is not set, this is the maximum dwell time and + * the actual dwell time may be shorter. + * @duration_mandatory: if set, the scan duration must be as specified by the + * %duration field. * @flags: bit field of flags controlling operation * @rates: bitmap of rates to advertise for each band * @wiphy: the wiphy this was for * @scan_start: time (in jiffies) when the scan started * @wdev: the wireless device to scan for - * @aborted: (internal) scan request was notified as aborted + * @info: (internal) information about completed scan * @notified: (internal) scan request was notified as done or aborted * @no_cck: used to send probe requests at non CCK rate in 2GHz band * @mac_addr: MAC address used with randomisation @@ -1454,6 +1474,8 @@ struct cfg80211_scan_request { enum nl80211_bss_scan_width scan_width; const u8 *ie; size_t ie_len; + u16 duration; + bool duration_mandatory; u32 flags; u32 rates[NUM_NL80211_BANDS]; @@ -1467,7 +1489,8 @@ struct cfg80211_scan_request { /* internal */ struct wiphy *wiphy; unsigned long scan_start; - bool aborted, notified; + struct cfg80211_scan_info info; + bool notified; bool no_cck; /* keep last */ @@ -1600,12 +1623,19 @@ enum cfg80211_signal_type { * buffered on the device) and be accurate to about 10ms. * If the frame isn't buffered, just passing the return value of * ktime_get_boot_ns() is likely appropriate. + * @parent_tsf: the time at the start of reception of the first octet of the + * timestamp field of the frame. The time is the TSF of the BSS specified + * by %parent_bssid. + * @parent_bssid: the BSS according to which %parent_tsf is set. This is set to + * the BSS that requested the scan in which the beacon/probe was received. */ struct cfg80211_inform_bss { struct ieee80211_channel *chan; enum nl80211_bss_scan_width scan_width; s32 signal; u64 boottime_ns; + u64 parent_tsf; + u8 parent_bssid[ETH_ALEN] __aligned(2); }; /** @@ -4067,10 +4097,10 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * cfg80211_scan_done - notify that scan finished * * @request: the corresponding scan request - * @aborted: set to true if the scan was aborted for any reason, - * userspace will be notified of that + * @info: information about the completed scan */ -void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted); +void cfg80211_scan_done(struct cfg80211_scan_request *request, + struct cfg80211_scan_info *info); /** * cfg80211_sched_scan_results - notify that new scan results are available diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1d7da7888dcf..b39ccab45333 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1848,6 +1848,22 @@ enum nl80211_commands { * to turn that feature off set an invalid mac address * (e.g. FF:FF:FF:FF:FF:FF) * + * @NL80211_ATTR_SCAN_START_TIME_TSF: The time at which the scan was actually + * started (u64). The time is the TSF of the BSS the interface that + * requested the scan is connected to (if available, otherwise this + * attribute must not be included). + * @NL80211_ATTR_SCAN_START_TIME_TSF_BSSID: The BSS according to which + * %NL80211_ATTR_SCAN_START_TIME_TSF is set. + * @NL80211_ATTR_MEASUREMENT_DURATION: measurement duration in TUs (u16). If + * %NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY is not set, this is the + * maximum measurement duration allowed. This attribute is used with + * measurement requests. It can also be used with %NL80211_CMD_TRIGGER_SCAN + * if the scan is used for beacon report radio measurement. + * @NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY: flag attribute that indicates + * that the duration specified with %NL80211_ATTR_MEASUREMENT_DURATION is + * mandatory. If this flag is not set, the duration is the maximum duration + * and the actual measurement duration may be shorter. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2235,6 +2251,11 @@ enum nl80211_attrs { NL80211_ATTR_MU_MIMO_GROUP_DATA, NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR, + NL80211_ATTR_SCAN_START_TIME_TSF, + NL80211_ATTR_SCAN_START_TIME_TSF_BSSID, + NL80211_ATTR_MEASUREMENT_DURATION, + NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3496,6 +3517,12 @@ enum nl80211_bss_scan_width { * was last updated by a received frame. The value is expected to be * accurate to about 10ms. (u64, nanoseconds) * @NL80211_BSS_PAD: attribute used for padding for 64-bit alignment + * @NL80211_BSS_PARENT_TSF: the time at the start of reception of the first + * octet of the timestamp field of the last beacon/probe received for + * this BSS. The time is the TSF of the BSS specified by + * @NL80211_BSS_PARENT_BSSID. (u64). + * @NL80211_BSS_PARENT_BSSID: the BSS according to which @NL80211_BSS_PARENT_TSF + * is set. * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -3517,6 +3544,8 @@ enum nl80211_bss { NL80211_BSS_PRESP_DATA, NL80211_BSS_LAST_SEEN_BOOTTIME, NL80211_BSS_PAD, + NL80211_BSS_PARENT_TSF, + NL80211_BSS_PARENT_BSSID, /* keep last */ __NL80211_BSS_AFTER_LAST, @@ -4507,6 +4536,16 @@ enum nl80211_feature_flags { * %NL80211_ATTR_MU_MIMO_GROUP_DATA attribute, * or can be configured to follow a station by configuring the * %NL80211_ATTR_MU_MIMO_FOLLOW_MAC_ADDR attribute. + * @NL80211_EXT_FEATURE_SCAN_START_TIME: This driver includes the actual + * time the scan started in scan results event. The time is the TSF of + * the BSS that the interface that requested the scan is connected to + * (if available). + * @NL80211_EXT_FEATURE_BSS_PARENT_TSF: Per BSS, this driver reports the + * time the last beacon/probe was received. The time is the TSF of the + * BSS that the interface that requested the scan is connected to + * (if available). + * @NL80211_EXT_FEATURE_SET_SCAN_DWELL: This driver supports configuration of + * channel dwell time. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4515,6 +4554,9 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_VHT_IBSS, NL80211_EXT_FEATURE_RRM, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER, + NL80211_EXT_FEATURE_SCAN_START_TIME, + NL80211_EXT_FEATURE_BSS_PARENT_TSF, + NL80211_EXT_FEATURE_SET_SCAN_DWELL, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 7947d3e075cde1a18e538f2dafbc850aa356ff79 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Tue, 5 Jul 2016 15:23:12 +0300 Subject: mac80211: Add support for beacon report radio measurement Add the following to support beacon report radio measurement with the measurement mode field set to passive or active: 1. Propagate the required scan duration to the device 2. Report the scan start time (in terms of TSF) 3. Report each BSS's detection time (also in terms of TSF) TSF times refer to the BSS that the interface that requested the scan is connected to. Signed-off-by: Assaf Krauss Signed-off-by: Avraham Stern [changed ath9k/10k, at76c59x-usb, iwlegacy, wl1251 and wlcore to match the new API] Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- include/net/mac80211.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a52009ffc19f..b4faadbb4e01 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4697,9 +4697,10 @@ void ieee80211_wake_queues(struct ieee80211_hw *hw); * any context, including hardirq context. * * @hw: the hardware that finished the scan - * @aborted: set to true if scan was aborted + * @info: information about the completed scan */ -void ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted); +void ieee80211_scan_completed(struct ieee80211_hw *hw, + struct cfg80211_scan_info *info); /** * ieee80211_sched_scan_results - got results from scheduled scan -- cgit v1.2.3 From 7d27a0ba7adc8ef30c2aae7592fce4c162aee4df Mon Sep 17 00:00:00 2001 From: Masashi Honma Date: Fri, 1 Jul 2016 10:19:34 +0900 Subject: cfg80211: Add mesh peer AID setting API Previously, mesh power management functionality works only with kernel MPM. Because user space MPM did not report mesh peer AID to kernel, the kernel could not identify the bit in TIM element. So this patch adds mesh peer AID setting API. Signed-off-by: Masashi Honma Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e2658e392a1f..9c23f4d33e06 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -780,6 +780,7 @@ enum station_parameters_apply_mask { * (bitmask of BIT(NL80211_STA_FLAG_...)) * @listen_interval: listen interval or -1 for no change * @aid: AID or zero for no change + * @peer_aid: mesh peer AID or zero for no change * @plink_action: plink action to take * @plink_state: set the peer link state for a station * @ht_capa: HT capabilities of station @@ -811,6 +812,7 @@ struct station_parameters { u32 sta_modify_mask; int listen_interval; u16 aid; + u16 peer_aid; u8 supported_rates_len; u8 plink_action; u8 plink_state; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index b39ccab45333..220694151434 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1864,6 +1864,9 @@ enum nl80211_commands { * mandatory. If this flag is not set, the duration is the maximum duration * and the actual measurement duration may be shorter. * + * @NL80211_ATTR_MESH_PEER_AID: Association ID for the mesh peer (u16). This is + * used to pull the stored data for mesh peer in power save state. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2256,6 +2259,8 @@ enum nl80211_attrs { NL80211_ATTR_MEASUREMENT_DURATION, NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY, + NL80211_ATTR_MESH_PEER_AID, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From da0c6dc00c69d0adaae99c3b3d2ea0c869a3fb35 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 27 Jun 2016 16:04:07 +0530 Subject: cpufreq: Handle sorted frequency tables more efficiently cpufreq drivers aren't required to provide a sorted frequency table today, and even the ones which provide a sorted table aren't handled efficiently by cpufreq core. This patch adds infrastructure to verify if the freq-table provided by the drivers is sorted or not, and use efficient helpers if they are sorted. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 234 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 231 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c378776628b4..c6410b1b2490 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -36,6 +36,12 @@ struct cpufreq_governor; +enum cpufreq_table_sorting { + CPUFREQ_TABLE_UNSORTED, + CPUFREQ_TABLE_SORTED_ASCENDING, + CPUFREQ_TABLE_SORTED_DESCENDING +}; + struct cpufreq_freqs { unsigned int cpu; /* cpu nr */ unsigned int old; @@ -87,6 +93,7 @@ struct cpufreq_policy { struct cpufreq_user_policy user_policy; struct cpufreq_frequency_table *freq_table; + enum cpufreq_table_sorting freq_table_sorted; struct list_head policy_list; struct kobject kobj; @@ -597,9 +604,9 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy); -int cpufreq_frequency_table_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation); +int cpufreq_table_index_unsorted(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation); int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy, unsigned int freq); @@ -610,6 +617,227 @@ int cpufreq_boost_trigger_state(int state); int cpufreq_boost_enabled(void); int cpufreq_enable_boost_support(void); bool policy_has_boost_freq(struct cpufreq_policy *policy); + +/* Find lowest freq at or above target in a table in ascending order */ +static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq >= target_freq) + return i; + + best = i; + } + + return best; +} + +/* Find lowest freq at or above target in a table in descending order */ +static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq == target_freq) + return i; + + if (freq > target_freq) { + best = i; + continue; + } + + /* No freq found above target_freq */ + if (best == -1) + return i; + + return best; + } + + return best; +} + +/* Works only on sorted freq-tables */ +static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + target_freq = clamp_val(target_freq, policy->min, policy->max); + + if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) + return cpufreq_table_find_index_al(policy, target_freq); + else + return cpufreq_table_find_index_dl(policy, target_freq); +} + +/* Find highest freq at or below target in a table in ascending order */ +static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq == target_freq) + return i; + + if (freq < target_freq) { + best = i; + continue; + } + + /* No freq found below target_freq */ + if (best == -1) + return i; + + return best; + } + + return best; +} + +/* Find highest freq at or below target in a table in descending order */ +static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq <= target_freq) + return i; + + best = i; + } + + return best; +} + +/* Works only on sorted freq-tables */ +static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + target_freq = clamp_val(target_freq, policy->min, policy->max); + + if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) + return cpufreq_table_find_index_ah(policy, target_freq); + else + return cpufreq_table_find_index_dh(policy, target_freq); +} + +/* Find closest freq to target in a table in ascending order */ +static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq == target_freq) + return i; + + if (freq < target_freq) { + best = i; + continue; + } + + /* No freq found below target_freq */ + if (best == -1) + return i; + + /* Choose the closest freq */ + if (target_freq - table[best].frequency > freq - target_freq) + return i; + + return best; + } + + return best; +} + +/* Find closest freq to target in a table in descending order */ +static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + struct cpufreq_frequency_table *table = policy->freq_table; + unsigned int freq; + int i, best = -1; + + for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) { + freq = table[i].frequency; + + if (freq == target_freq) + return i; + + if (freq > target_freq) { + best = i; + continue; + } + + /* No freq found above target_freq */ + if (best == -1) + return i; + + /* Choose the closest freq */ + if (table[best].frequency - target_freq > target_freq - freq) + return i; + + return best; + } + + return best; +} + +/* Works only on sorted freq-tables */ +static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + target_freq = clamp_val(target_freq, policy->min, policy->max); + + if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) + return cpufreq_table_find_index_ac(policy, target_freq); + else + return cpufreq_table_find_index_dc(policy, target_freq); +} + +static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED)) + return cpufreq_table_index_unsorted(policy, target_freq, + relation); + + switch (relation) { + case CPUFREQ_RELATION_L: + return cpufreq_table_find_index_l(policy, target_freq); + case CPUFREQ_RELATION_H: + return cpufreq_table_find_index_h(policy, target_freq); + case CPUFREQ_RELATION_C: + return cpufreq_table_find_index_c(policy, target_freq); + default: + pr_err("%s: Invalid relation: %d\n", __func__, relation); + return -EINVAL; + } +} #else static inline int cpufreq_boost_trigger_state(int state) { -- cgit v1.2.3 From 054e2730088a9c9340b5bc6927000f5c14a8b6d7 Mon Sep 17 00:00:00 2001 From: Sylvain Lemieux Date: Fri, 3 Jun 2016 15:34:35 -0400 Subject: clk: lpc32xx: allow peripheral clock selection in device tree This patch add the support to select the peripheral clock (PERIPH) as a parent clock source using the "assigned-clock-parents" parameter in the device tree. Signed-off-by: Sylvain Lemieux Acked-by: Vladimir Zapolskiy Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/1464982475-24738-1-git-send-email-slemieux.tyco@gmail.com --- include/dt-bindings/clock/lpc32xx-clock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/lpc32xx-clock.h b/include/dt-bindings/clock/lpc32xx-clock.h index d41b6fea1450..e624d3a52798 100644 --- a/include/dt-bindings/clock/lpc32xx-clock.h +++ b/include/dt-bindings/clock/lpc32xx-clock.h @@ -48,6 +48,7 @@ #define LPC32XX_CLK_PWM2 33 #define LPC32XX_CLK_ADC 34 #define LPC32XX_CLK_HCLK_PLL 35 +#define LPC32XX_CLK_PERIPH 36 /* LPC32XX USB clocks */ #define LPC32XX_USB_CLK_I2C 1 -- 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 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 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: -- 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 --- 1 file changed, 3 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: -- 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 ++ 1 file changed, 2 insertions(+) (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 }, \ -- 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 --- include/linux/timer.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') 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: -- cgit v1.2.3 From 529435e8188674fa1071235f50e6fbbbe020c93f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Thu, 7 Jul 2016 09:54:08 +0200 Subject: lightnvm: add media manager mark_blk helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Expose media manager mark_blk() to targets, as done for the rest of the media manager callback functions. Signed-off-by: Javier González Updated description Signed-off-by: Matias Bjørling Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ef2c7d2e76c4..9c56148d6f63 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -532,6 +532,8 @@ extern int nvm_register(struct request_queue *, char *, struct nvm_dev_ops *); extern void nvm_unregister(char *); +void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type); + extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); -- cgit v1.2.3 From 5389a1dfb39786df08d4f6a482bd2734b1b50e33 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Thu, 7 Jul 2016 09:54:09 +0200 Subject: lightnvm: initialize ppa_addr in dev_to_generic_addr() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ->reserved bit is not initialized when allocated on stack. This may lead targets to misinterpret the PPA as cached. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 9c56148d6f63..cee4c8de34d5 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -385,6 +385,7 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, { struct ppa_addr l; + l.ppa = 0; /* * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. */ -- cgit v1.2.3 From 077d2389994197277f4f7662b13d11b2f67646a7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 7 Jul 2016 09:54:14 +0200 Subject: lightnvm: remove open/close statistics for gennvm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The responsibility of the media manager is not to keep track of open/closed blocks. This is better maintained within a target, that already manages this information on writes. Remove the statistics and merge the states NVM_BLK_ST_OPEN and NVM_BLK_ST_CLOSED. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index cee4c8de34d5..8b51d5767331 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -269,24 +269,15 @@ struct nvm_lun { int lun_id; int chnl_id; - /* It is up to the target to mark blocks as closed. If the target does - * not do it, all blocks are marked as open, and nr_open_blocks - * represents the number of blocks in use - */ - unsigned int nr_open_blocks; /* Number of used, writable blocks */ - unsigned int nr_closed_blocks; /* Number of used, read-only blocks */ - unsigned int nr_free_blocks; /* Number of unused blocks */ - unsigned int nr_bad_blocks; /* Number of bad blocks */ - spinlock_t lock; + unsigned int nr_free_blocks; /* Number of unused blocks */ struct nvm_block *blocks; }; enum { NVM_BLK_ST_FREE = 0x1, /* Free block */ - NVM_BLK_ST_OPEN = 0x2, /* Open block - read-write */ - NVM_BLK_ST_CLOSED = 0x4, /* Closed block - read-only */ + NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ NVM_BLK_ST_BAD = 0x8, /* Bad block */ }; -- cgit v1.2.3 From b76eb20bb0c6f4f9c2e1ad493f73c52817b8aaff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 7 Jul 2016 09:54:16 +0200 Subject: lightnvm: move target mgmt into media mgr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To enable persistent block management to easily control creation and removal of targets, we move target management into the media manager. The LightNVM core continues to maintain which target types are registered, while the media manager now keeps track of its initialized targets. Two new callbacks for the media manager are introduced. create_tgt and remove_tgt. Note that remove_tgt returns 0 on successfully removing a target, and returns 1 if the target was not found. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 8b51d5767331..d619f6dde7df 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -1,7 +1,9 @@ #ifndef NVM_H #define NVM_H +#include #include +#include enum { NVM_IO_OK = 0, @@ -447,6 +449,8 @@ struct nvm_tgt_type { struct list_head list; }; +extern struct nvm_tgt_type *nvm_find_target_type(const char *, int); + extern int nvm_register_tgt_type(struct nvm_tgt_type *); extern void nvm_unregister_tgt_type(struct nvm_tgt_type *); @@ -455,6 +459,9 @@ extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); typedef int (nvmm_register_fn)(struct nvm_dev *); typedef void (nvmm_unregister_fn)(struct nvm_dev *); + +typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); +typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, struct nvm_lun *, unsigned long); typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); @@ -480,6 +487,9 @@ struct nvmm_type { nvmm_register_fn *register_mgr; nvmm_unregister_fn *unregister_mgr; + nvmm_create_tgt_fn *create_tgt; + nvmm_remove_tgt_fn *remove_tgt; + /* Block administration callbacks */ nvmm_get_blk_fn *get_blk_unlocked; nvmm_put_blk_fn *put_blk_unlocked; -- cgit v1.2.3 From 41285fad511a2c3746bee7ccb3b2f21b70305c14 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 7 Jul 2016 09:54:19 +0200 Subject: lightnvm: remove _unlocked variant of [get/put]_blk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The [get/put]_blk API enables targets to get ownership of blocks at runtime. This information is currently not recorded on disk, and the information is therefore lost on power failure. To restore the metadata, the [get/put]_blk must persist its metadata. In that case, we need to control the outer lock, so that we can disable them while updating the on-disk metadata. Fortunately, the _unlocked versions can be removed, which allows us to move the lock into the [get/put]_blk functions. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d619f6dde7df..e9836cfb6fde 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -491,8 +491,6 @@ struct nvmm_type { nvmm_remove_tgt_fn *remove_tgt; /* Block administration callbacks */ - nvmm_get_blk_fn *get_blk_unlocked; - nvmm_put_blk_fn *put_blk_unlocked; nvmm_get_blk_fn *get_blk; nvmm_put_blk_fn *put_blk; nvmm_open_blk_fn *open_blk; @@ -522,10 +520,6 @@ struct nvmm_type { extern int nvm_register_mgr(struct nvmm_type *); extern void nvm_unregister_mgr(struct nvmm_type *); -extern struct nvm_block *nvm_get_blk_unlocked(struct nvm_dev *, - struct nvm_lun *, unsigned long); -extern void nvm_put_blk_unlocked(struct nvm_dev *, struct nvm_block *); - extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *, unsigned long); extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *); -- cgit v1.2.3 From 8680f165eaa56cc9812d7d9b4903f449df0f6a45 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 7 Jul 2016 09:54:22 +0200 Subject: lightnvm: make ppa_list const in nvm_set_rqd_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The passed by reference ppa list in nvm_set_rqd_list() is updated when multiple planes are available. In that case, each PPA plane is incremented when the device side PPA list is created. This prevents the caller to rely on the PPA list to be unmodified after a call. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index e9836cfb6fde..ba78b8306674 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -534,7 +534,7 @@ extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, - struct ppa_addr *, int, int); + const struct ppa_addr *, int, int); extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int); extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *); -- cgit v1.2.3 From c83f8effefa46c15f2fd43de598d9839d0056096 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:52 -0400 Subject: Btrfs: add tracepoint for adding block groups I'm writing a tool to visualize the enospc system inside btrfs, I need this tracepoint in order to keep track of the block groups in the system. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index e90e82ad6875..985e01b6c849 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -440,6 +440,46 @@ TRACE_EVENT(btrfs_sync_fs, TP_printk("wait = %d", __entry->wait) ); +TRACE_EVENT(btrfs_add_block_group, + + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_block_group_cache *block_group, int create), + + TP_ARGS(fs_info, block_group, create), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, offset ) + __field( u64, size ) + __field( u64, flags ) + __field( u64, bytes_used ) + __field( u64, bytes_super ) + __field( int, create ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->offset = block_group->key.objectid; + __entry->size = block_group->key.offset; + __entry->flags = block_group->flags; + __entry->bytes_used = + btrfs_block_group_used(&block_group->item); + __entry->bytes_super = block_group->bytes_super; + __entry->create = create; + ), + + TP_printk("%pU: block_group offset = %llu, size = %llu, " + "flags = %llu(%s), bytes_used = %llu, bytes_super = %llu, " + "create = %d", __entry->fsid, + (unsigned long long)__entry->offset, + (unsigned long long)__entry->size, + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->bytes_used, + (unsigned long long)__entry->bytes_super, __entry->create) +); + #define show_ref_action(action) \ __print_symbolic(action, \ { BTRFS_ADD_DELAYED_REF, "ADD_DELAYED_REF" }, \ -- cgit v1.2.3 From f376df2b7da3a40f62f861a65efdd8c29fa1b877 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:56 -0400 Subject: Btrfs: add tracepoints for flush events We want to track when we're triggering flushing from our reservation code and what flushing is being done when we start flushing. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 82 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 985e01b6c849..226c7f283247 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -784,6 +784,88 @@ TRACE_EVENT(btrfs_space_reservation, __entry->bytes) ); +#define show_flush_action(action) \ + __print_symbolic(action, \ + { BTRFS_RESERVE_NO_FLUSH, "BTRFS_RESERVE_NO_FLUSH"}, \ + { BTRFS_RESERVE_FLUSH_LIMIT, "BTRFS_RESERVE_FLUSH_LIMIT"}, \ + { BTRFS_RESERVE_FLUSH_ALL, "BTRFS_RESERVE_FLUSH_ALL"}) + +TRACE_EVENT(btrfs_trigger_flush, + + TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, + int flush, char *reason), + + TP_ARGS(fs_info, flags, bytes, flush, reason), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, flags ) + __field( u64, bytes ) + __field( int, flush ) + __string( reason, reason ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->flags = flags; + __entry->bytes = bytes; + __entry->flush = flush; + __assign_str(reason, reason) + ), + + TP_printk("%pU: %s: flush = %d(%s), flags = %llu(%s), bytes = %llu", + __entry->fsid, __get_str(reason), __entry->flush, + show_flush_action(__entry->flush), + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->bytes) +); + +#define show_flush_state(state) \ + __print_symbolic(state, \ + { FLUSH_DELAYED_ITEMS_NR, "FLUSH_DELAYED_ITEMS_NR"}, \ + { FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS"}, \ + { FLUSH_DELALLOC, "FLUSH_DELALLOC"}, \ + { FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT"}, \ + { ALLOC_CHUNK, "ALLOC_CHUNK"}, \ + { COMMIT_TRANS, "COMMIT_TRANS"}) + +TRACE_EVENT(btrfs_flush_space, + + TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 num_bytes, + u64 orig_bytes, int state, int ret), + + TP_ARGS(fs_info, flags, num_bytes, orig_bytes, state, ret), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, flags ) + __field( u64, num_bytes ) + __field( u64, orig_bytes ) + __field( int, state ) + __field( int, ret ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->flags = flags; + __entry->num_bytes = num_bytes; + __entry->orig_bytes = orig_bytes; + __entry->state = state; + __entry->ret = ret; + ), + + TP_printk("%pU: state = %d(%s), flags = %llu(%s), num_bytes = %llu, " + "orig_bytes = %llu, ret = %d", __entry->fsid, __entry->state, + show_flush_state(__entry->state), + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->num_bytes, + (unsigned long long)__entry->orig_bytes, __entry->ret) +); + DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_PROTO(struct btrfs_root *root, u64 start, u64 len), -- cgit v1.2.3 From dce3afa5932776f7b925249fbef435c265014f91 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:57 -0400 Subject: Btrfs: add fsid to some tracepoints When tracing enospc problems on a box with multiple file systems mounted I need to be able to differentiate between the two file systems. Most of the important trace points I'm looking at already have an fsid, but the reserved extent trace points do not, so add that to make it possible to figure out which trace point belongs to which file system. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 226c7f283247..5b81ef304388 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -873,18 +873,21 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_ARGS(root, start, len), TP_STRUCT__entry( - __field( u64, root_objectid ) - __field( u64, start ) - __field( u64, len ) + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, root_objectid ) + __field( u64, start ) + __field( u64, len ) ), TP_fast_assign( + memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); __entry->root_objectid = root->root_key.objectid; __entry->start = start; __entry->len = len; ), - TP_printk("root = %llu(%s), start = %llu, len = %llu", + TP_printk("%pU: root = %llu(%s), start = %llu, len = %llu", + __entry->fsid, show_root_type(__entry->root_objectid), (unsigned long long)__entry->start, (unsigned long long)__entry->len) @@ -941,6 +944,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, TP_ARGS(root, block_group, start, len), TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) __field( u64, root_objectid ) __field( u64, bg_objectid ) __field( u64, flags ) @@ -949,6 +953,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, ), TP_fast_assign( + memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); __entry->root_objectid = root->root_key.objectid; __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; @@ -956,8 +961,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __entry->len = len; ), - TP_printk("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " - "start = %Lu, len = %Lu", + TP_printk("%pU: root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " + "start = %Lu, len = %Lu", __entry->fsid, show_root_type(__entry->root_objectid), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), -- cgit v1.2.3 From 29b9aa0aa3837c93ecd804dd3ada39b8cc75607d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 6 Jun 2016 17:42:38 -0700 Subject: libnvdimm: introduce devm_nvdimm_memremap(), convert nfit_spa_map() users In preparation for generically mapping flush hint addresses for both the BLK and PMEM use case, provide a generic / reference counted mapping api. Given the fact that a dimm may belong to multiple regions (PMEM and BLK), the flush hint addresses need to be held valid as long as any region associated with the dimm is active. This is similar to the existing BLK-region case where multiple BLK-regions may share an aperture mapping. Up-level this shared / reference-counted mapping capability from the nfit driver to a core nvdimm capability. This eliminates the need for the nd_blk_region.disable() callback. Note that the removal of nfit_spa_map() and related infrastructure is deferred to a later patch. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 0c3c30cbbea5..18c3cc48a970 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -99,6 +99,15 @@ struct nd_region_desc { unsigned long flags; }; +struct device; +void *devm_nvdimm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags); +static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, + resource_size_t offset, size_t size) +{ + return (void __iomem *) devm_nvdimm_memremap(dev, offset, size, 0); +} + struct nvdimm_bus; struct module; struct device; -- cgit v1.2.3 From e16fb2e6355c1c1b41623af9e01ada196e2af098 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Wed, 6 Jul 2016 20:38:37 -0700 Subject: clk: gxbb: expose CLKID_MMC_PCLK The MMC_PCLK is needed for the SD/eMMC driver, expose to DT (and comment out in clk driver) Signed-off-by: Kevin Hilman Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20160707033837.20029-1-khilman@baylibre.com --- include/dt-bindings/clock/gxbb-clkc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h index f889d80246cb..5eb69ec74f6b 100644 --- a/include/dt-bindings/clock/gxbb-clkc.h +++ b/include/dt-bindings/clock/gxbb-clkc.h @@ -8,5 +8,6 @@ #define CLKID_CPUCLK 1 #define CLKID_CLK81 12 #define CLKID_ETH 36 +#define CLKID_MMC_PCLK 66 #endif /* __GXBB_CLKC_H */ -- 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 aece0c3fe1f06962a591268b8c236df0ae5d9e4e Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sat, 18 Jun 2016 10:45:33 +0200 Subject: nl802154: move PAD to right position The PAD define should be above the experimental support. We don't care about if we break userspace in experimental stuff but PAD is part of the existing UAPI. Cc: Nicolas Dichtel Acked-by: Nicolas Dichtel Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/nl802154.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/nl802154.h b/include/net/nl802154.h index fcab4de49951..7aad2fdfd16a 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -124,6 +124,8 @@ enum nl802154_attrs { NL802154_ATTR_ACKREQ_DEFAULT, + NL802154_ATTR_PAD, + /* add attributes here, update the policy in nl802154.c */ #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL @@ -138,8 +140,6 @@ enum nl802154_attrs { NL802154_ATTR_SEC_KEY, #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ - NL802154_ATTR_PAD, - __NL802154_ATTR_AFTER_LAST, NL802154_ATTR_MAX = __NL802154_ATTR_AFTER_LAST - 1 }; -- cgit v1.2.3 From 66e5c2672cd11b9310008099faf6a4ffb9dfb6d0 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Sat, 18 Jun 2016 10:45:34 +0200 Subject: ieee802154: add netns support This patch adds netns support for 802.15.4 subsystem. Most parts are copy&pasted from wireless subsystem, it has the identically userspace API. Cc: Nicolas Dichtel Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/cfg802154.h | 13 +++++++++++++ include/net/nl802154.h | 5 +++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 171cd76558fb..795ca4008f72 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -219,9 +219,22 @@ struct wpan_phy { struct device dev; + /* the network namespace this phy lives in currently */ + possible_net_t _net; + char priv[0] __aligned(NETDEV_ALIGN); }; +static inline struct net *wpan_phy_net(struct wpan_phy *wpan_phy) +{ + return read_pnet(&wpan_phy->_net); +} + +static inline void wpan_phy_net_set(struct wpan_phy *wpan_phy, struct net *net) +{ + write_pnet(&wpan_phy->_net, net); +} + struct ieee802154_addr { u8 mode; __le16 pan_id; diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 7aad2fdfd16a..ddcee128f5d9 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -54,6 +54,8 @@ enum nl802154_commands { NL802154_CMD_SET_ACKREQ_DEFAULT, + NL802154_CMD_SET_WPAN_PHY_NETNS, + /* add new commands above here */ #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL @@ -126,6 +128,9 @@ enum nl802154_attrs { NL802154_ATTR_PAD, + NL802154_ATTR_PID, + NL802154_ATTR_NETNS_FD, + /* add attributes here, update the policy in nl802154.c */ #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL -- cgit v1.2.3 From 9cc577dd25b9762df7f353658426bb2e048c480a Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 6 Jul 2016 23:32:24 +0200 Subject: ieee802154: add ieee802154_skb_dst_pan helper This patch adds ieee802154_skb_dst_pan function to get the pointer address of the destination pan id at skb mac pointer. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 16 ++++++++++++++++ include/net/mac802154.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index acedbb68a5a3..91f4665fea63 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -31,6 +31,8 @@ #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 #define IEEE802154_MAX_AUTH_TAG_LEN 16 +#define IEEE802154_FC_LEN 2 +#define IEEE802154_SEQ_LEN 1 /* General MAC frame format: * 2 bytes: Frame Control @@ -221,9 +223,14 @@ enum { #define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_SECEN 0x0004 #define IEEE802154_FCTL_INTRA_PAN 0x0040 +#define IEEE802154_FCTL_DADDR 0x0c00 #define IEEE802154_FTYPE_DATA 0x0001 +#define IEEE802154_FCTL_ADDR_NONE 0x0000 +#define IEEE802154_FCTL_DADDR_SHORT 0x0800 +#define IEEE802154_FCTL_DADDR_EXTENDED 0x0c00 + /* * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder @@ -261,6 +268,15 @@ static inline bool ieee802154_is_intra_pan(__le16 fc) return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); } +/* + * ieee802154_daddr_mode - get daddr mode from fc + * @fc: frame control bytes in little-endian byteorder + */ +static inline __le16 ieee802154_daddr_mode(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_DADDR); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: diff --git a/include/net/mac802154.h b/include/net/mac802154.h index e465c8551ac3..b3f7cd868fe9 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -257,6 +257,35 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) return get_unaligned_le16(skb_mac_header(skb)); } +/** + * ieee802154_skb_dst_pan - get the pointer to destination pan field + * @fc: mac header frame control field + * @skb: skb where the destination pan pointer will be get from + */ +static inline unsigned char *ieee802154_skb_dst_pan(__le16 fc, + const struct sk_buff *skb) +{ + unsigned char *dst_pan; + + switch (ieee802154_daddr_mode(fc)) { + case cpu_to_le16(IEEE802154_FCTL_ADDR_NONE): + dst_pan = NULL; + break; + case cpu_to_le16(IEEE802154_FCTL_DADDR_SHORT): + case cpu_to_le16(IEEE802154_FCTL_DADDR_EXTENDED): + dst_pan = skb_mac_header(skb) + + IEEE802154_FC_LEN + + IEEE802154_SEQ_LEN; + break; + default: + WARN_ONCE(1, "invalid addr mode detected"); + dst_pan = NULL; + break; + } + + return dst_pan; +} + /** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer -- cgit v1.2.3 From 19580cc1ed299c736b56b45c7576b477f185f8f5 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 6 Jul 2016 23:32:25 +0200 Subject: ieee802154: add ieee802154_skb_src_pan helper This patch adds ieee802154_skb_src_pan function to get the pointer address of the source pan id at skb mac pointer. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/linux/ieee802154.h | 13 ++++++++++ include/net/mac802154.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 91f4665fea63..ddb890174a0e 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -50,6 +50,7 @@ #define IEEE802154_EXTENDED_ADDR_LEN 8 #define IEEE802154_SHORT_ADDR_LEN 2 +#define IEEE802154_PAN_ID_LEN 2 #define IEEE802154_LIFS_PERIOD 40 #define IEEE802154_SIFS_PERIOD 12 @@ -224,12 +225,15 @@ enum { #define IEEE802154_FCTL_SECEN 0x0004 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FCTL_DADDR 0x0c00 +#define IEEE802154_FCTL_SADDR 0xc000 #define IEEE802154_FTYPE_DATA 0x0001 #define IEEE802154_FCTL_ADDR_NONE 0x0000 #define IEEE802154_FCTL_DADDR_SHORT 0x0800 #define IEEE802154_FCTL_DADDR_EXTENDED 0x0c00 +#define IEEE802154_FCTL_SADDR_SHORT 0x8000 +#define IEEE802154_FCTL_SADDR_EXTENDED 0xc000 /* * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA @@ -277,6 +281,15 @@ static inline __le16 ieee802154_daddr_mode(__le16 fc) return fc & cpu_to_le16(IEEE802154_FCTL_DADDR); } +/* + * ieee802154_saddr_mode - get saddr mode from fc + * @fc: frame control bytes in little-endian byteorder + */ +static inline __le16 ieee802154_saddr_mode(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_SADDR); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: diff --git a/include/net/mac802154.h b/include/net/mac802154.h index b3f7cd868fe9..ec01b35bc969 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -286,6 +286,65 @@ static inline unsigned char *ieee802154_skb_dst_pan(__le16 fc, return dst_pan; } +/** + * ieee802154_skb_src_pan - get the pointer to source pan field + * @fc: mac header frame control field + * @skb: skb where the source pan pointer will be get from + */ +static inline unsigned char *ieee802154_skb_src_pan(__le16 fc, + const struct sk_buff *skb) +{ + unsigned char *src_pan; + + switch (ieee802154_saddr_mode(fc)) { + case cpu_to_le16(IEEE802154_FCTL_ADDR_NONE): + src_pan = NULL; + break; + case cpu_to_le16(IEEE802154_FCTL_SADDR_SHORT): + case cpu_to_le16(IEEE802154_FCTL_SADDR_EXTENDED): + /* if intra-pan and source addr mode is non none, + * then source pan id is equal destination pan id. + */ + if (ieee802154_is_intra_pan(fc)) { + src_pan = ieee802154_skb_dst_pan(fc, skb); + break; + } + + switch (ieee802154_daddr_mode(fc)) { + case cpu_to_le16(IEEE802154_FCTL_ADDR_NONE): + src_pan = skb_mac_header(skb) + + IEEE802154_FC_LEN + + IEEE802154_SEQ_LEN; + break; + case cpu_to_le16(IEEE802154_FCTL_DADDR_SHORT): + src_pan = skb_mac_header(skb) + + IEEE802154_FC_LEN + + IEEE802154_SEQ_LEN + + IEEE802154_PAN_ID_LEN + + IEEE802154_SHORT_ADDR_LEN; + break; + case cpu_to_le16(IEEE802154_FCTL_DADDR_EXTENDED): + src_pan = skb_mac_header(skb) + + IEEE802154_FC_LEN + + IEEE802154_SEQ_LEN + + IEEE802154_PAN_ID_LEN + + IEEE802154_EXTENDED_ADDR_LEN; + break; + default: + WARN_ONCE(1, "invalid addr mode detected"); + src_pan = NULL; + break; + } + break; + default: + WARN_ONCE(1, "invalid addr mode detected"); + src_pan = NULL; + break; + } + + return src_pan; +} + /** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer -- cgit v1.2.3 From 0ea0b9af9b7599ada307258dc841f4300873e8a1 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 6 Jul 2016 23:32:26 +0200 Subject: ieee802154: 6lowpan: fix intra pan id check The RIOT-OS stack does send intra-pan frames but don't set the intra pan flag inside the mac header. It seems this is valid frame addressing but inefficient. Anyway this patch adds a new function for intra pan addressing, doesn't matter if intra pan flag or source and destination are the same. The newly introduction function will be used to check on intra pan addressing for 6lowpan. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index ec01b35bc969..d757edd0b0b7 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -345,6 +345,25 @@ static inline unsigned char *ieee802154_skb_src_pan(__le16 fc, return src_pan; } +/** + * ieee802154_skb_is_intra_pan_addressing - checks whenever the mac addressing + * is an intra pan communication + * @fc: mac header frame control field + * @skb: skb where the source and destination pan should be get from + */ +static inline bool ieee802154_skb_is_intra_pan_addressing(__le16 fc, + const struct sk_buff *skb) +{ + unsigned char *dst_pan = ieee802154_skb_dst_pan(fc, skb), + *src_pan = ieee802154_skb_src_pan(fc, skb); + + /* if one is NULL is no intra pan addressing */ + if (!dst_pan || !src_pan) + return false; + + return !memcmp(dst_pan, src_pan, IEEE802154_PAN_ID_LEN); +} + /** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer -- cgit v1.2.3 From aaa7088eb29a0ffe6cf8d8a443695df41e5a62f3 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 6 Jul 2016 23:32:27 +0200 Subject: ieee802154: fix skb get fc on big endian This patch fixes ieee802154_get_fc_from_skb function on big endian machines. The function get_unaligned_le16 converts the byte order to host byte order but we want to keep the byte order like in mac header. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index d757edd0b0b7..bb7bfecc5ab3 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -247,6 +247,8 @@ struct ieee802154_ops { */ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) { + __le16 fc; + /* check if we can fc at skb_mac_header of sk buffer */ if (unlikely(!skb_mac_header_was_set(skb) || (skb_tail_pointer(skb) - skb_mac_header(skb)) < 2)) { @@ -254,7 +256,8 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) return cpu_to_le16(0); } - return get_unaligned_le16(skb_mac_header(skb)); + memcpy(&fc, skb_mac_header(skb), IEEE802154_FC_LEN); + return fc; } /** -- cgit v1.2.3 From 048e7f7e66a8693fe1707997bffd19d08cde08f5 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Wed, 6 Jul 2016 23:32:30 +0200 Subject: ieee802154: cleanup WARN_ON for fc fetch This patch cleanups the WARN_ON which occurs when the sk buffer has insufficient buffer space by moving the WARN_ON into if condition. Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- include/net/mac802154.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac802154.h b/include/net/mac802154.h index bb7bfecc5ab3..286824acd008 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -250,11 +250,10 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) __le16 fc; /* check if we can fc at skb_mac_header of sk buffer */ - if (unlikely(!skb_mac_header_was_set(skb) || - (skb_tail_pointer(skb) - skb_mac_header(skb)) < 2)) { - WARN_ON(1); + if (WARN_ON(!skb_mac_header_was_set(skb) || + (skb_tail_pointer(skb) - + skb_mac_header(skb)) < IEEE802154_FC_LEN)) return cpu_to_le16(0); - } memcpy(&fc, skb_mac_header(skb), IEEE802154_FC_LEN); return fc; -- 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 --- include/linux/mm_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') 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 { -- 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 3467f0d433016c45d1851f3587d32816b7b2ffb0 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Thu, 23 Jun 2016 16:57:09 +0200 Subject: ath9k: Allow configuration of LED polarity in platform data. Some devices running OpenWrt need this and it makes sense to add this to ath9k_platform_data as the next patches will add a devicetree (boolean) property for it as well. Suggested-by: Vittorio Gambaletta Signed-off-by: Martin Blumenstingl Signed-off-by: Kalle Valo --- include/linux/ath9k_platform.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h index e66153d60bd5..76860a461ed2 100644 --- a/include/linux/ath9k_platform.h +++ b/include/linux/ath9k_platform.h @@ -40,6 +40,7 @@ struct ath9k_platform_data { bool tx_gain_buffalo; bool disable_2ghz; bool disable_5ghz; + bool led_active_high; int (*get_mac_revision)(void); int (*external_reset)(void); -- cgit v1.2.3 From d4a5f6d71e8bd32f268e738ed39b31a15334cdf7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 27 Jun 2016 00:03:00 +0200 Subject: rtc: ds1286: move header to linux/rtc Move ds1286.h to rtc specific folder. Signed-off-by: Alexandre Belloni --- include/linux/ds1286.h | 52 ---------------------------------------------- include/linux/rtc/ds1286.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+), 52 deletions(-) delete mode 100644 include/linux/ds1286.h create mode 100644 include/linux/rtc/ds1286.h (limited to 'include') diff --git a/include/linux/ds1286.h b/include/linux/ds1286.h deleted file mode 100644 index 45ea0aa0aeb9..000000000000 --- a/include/linux/ds1286.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright (C) 1998, 1999, 2003 Ralf Baechle - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ -#ifndef __LINUX_DS1286_H -#define __LINUX_DS1286_H - -/********************************************************************** - * register summary - **********************************************************************/ -#define RTC_HUNDREDTH_SECOND 0 -#define RTC_SECONDS 1 -#define RTC_MINUTES 2 -#define RTC_MINUTES_ALARM 3 -#define RTC_HOURS 4 -#define RTC_HOURS_ALARM 5 -#define RTC_DAY 6 -#define RTC_DAY_ALARM 7 -#define RTC_DATE 8 -#define RTC_MONTH 9 -#define RTC_YEAR 10 -#define RTC_CMD 11 -#define RTC_WHSEC 12 -#define RTC_WSEC 13 -#define RTC_UNUSED 14 - -/* RTC_*_alarm is always true if 2 MSBs are set */ -# define RTC_ALARM_DONT_CARE 0xC0 - - -/* - * Bits in the month register - */ -#define RTC_EOSC 0x80 -#define RTC_ESQW 0x40 - -/* - * Bits in the Command register - */ -#define RTC_TDF 0x01 -#define RTC_WAF 0x02 -#define RTC_TDM 0x04 -#define RTC_WAM 0x08 -#define RTC_PU_LVL 0x10 -#define RTC_IBH_LO 0x20 -#define RTC_IPSW 0x40 -#define RTC_TE 0x80 - -#endif /* __LINUX_DS1286_H */ diff --git a/include/linux/rtc/ds1286.h b/include/linux/rtc/ds1286.h new file mode 100644 index 000000000000..45ea0aa0aeb9 --- /dev/null +++ b/include/linux/rtc/ds1286.h @@ -0,0 +1,52 @@ +/* + * Copyright (C) 1998, 1999, 2003 Ralf Baechle + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#ifndef __LINUX_DS1286_H +#define __LINUX_DS1286_H + +/********************************************************************** + * register summary + **********************************************************************/ +#define RTC_HUNDREDTH_SECOND 0 +#define RTC_SECONDS 1 +#define RTC_MINUTES 2 +#define RTC_MINUTES_ALARM 3 +#define RTC_HOURS 4 +#define RTC_HOURS_ALARM 5 +#define RTC_DAY 6 +#define RTC_DAY_ALARM 7 +#define RTC_DATE 8 +#define RTC_MONTH 9 +#define RTC_YEAR 10 +#define RTC_CMD 11 +#define RTC_WHSEC 12 +#define RTC_WSEC 13 +#define RTC_UNUSED 14 + +/* RTC_*_alarm is always true if 2 MSBs are set */ +# define RTC_ALARM_DONT_CARE 0xC0 + + +/* + * Bits in the month register + */ +#define RTC_EOSC 0x80 +#define RTC_ESQW 0x40 + +/* + * Bits in the Command register + */ +#define RTC_TDF 0x01 +#define RTC_WAF 0x02 +#define RTC_TDM 0x04 +#define RTC_WAM 0x08 +#define RTC_PU_LVL 0x10 +#define RTC_IBH_LO 0x20 +#define RTC_IPSW 0x40 +#define RTC_TE 0x80 + +#endif /* __LINUX_DS1286_H */ -- cgit v1.2.3 From 486cf9899e311838b6ab95d19ff87c4da44d6508 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 6 Jul 2016 21:55:48 +0900 Subject: blk-mq: Introduce blk_mq_reinit_tagset The new nvme-rdma driver will need to reinitialize all the tags as part of the error recovery procedure (realloc the tag memory region). Add a helper in blk-mq for it that can iterate over all requests in a tagset to make this easier. Signed-off-by: Sagi Grimberg Tested-by: Ming Lin Reviewed-by: Stephen Bates Signed-off-by: Christoph Hellwig Reviewed-by: Steve Wise Tested-by: Steve Wise Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index cbfd8ca5f13e..e43bbffb5b7a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -96,6 +96,7 @@ typedef int (init_request_fn)(void *, struct request *, unsigned int, unsigned int, unsigned int); typedef void (exit_request_fn)(void *, struct request *, unsigned int, unsigned int); +typedef int (reinit_request_fn)(void *, struct request *); typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); @@ -145,6 +146,7 @@ struct blk_mq_ops { */ init_request_fn *init_request; exit_request_fn *exit_request; + reinit_request_fn *reinit_request; }; enum { @@ -245,6 +247,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); +int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); -- cgit v1.2.3 From 931a6de4d734de6142142c82555e3f017adcb9f0 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 6 Jul 2016 21:55:50 +0900 Subject: nvme-rdma.h: Add includes for nvme rdma_cm negotiation NVMe over Fabrics RDMA transport defines a connection establishment protocol over the RDMA connection manager. This header will be used by both the host and target drivers to negotiate the connection establishment parameters. Signed-off-by: Jay Freyensee Signed-off-by: Ming Lin Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Reviewed-by: Steve Wise Tested-by: Steve Wise Signed-off-by: Jens Axboe --- include/linux/nvme-rdma.h | 71 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 include/linux/nvme-rdma.h (limited to 'include') diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h new file mode 100644 index 000000000000..bf240a3cbf99 --- /dev/null +++ b/include/linux/nvme-rdma.h @@ -0,0 +1,71 @@ +/* + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _LINUX_NVME_RDMA_H +#define _LINUX_NVME_RDMA_H + +enum nvme_rdma_cm_fmt { + NVME_RDMA_CM_FMT_1_0 = 0x0, +}; + +enum nvme_rdma_cm_status { + NVME_RDMA_CM_INVALID_LEN = 0x01, + NVME_RDMA_CM_INVALID_RECFMT = 0x02, + NVME_RDMA_CM_INVALID_QID = 0x03, + NVME_RDMA_CM_INVALID_HSQSIZE = 0x04, + NVME_RDMA_CM_INVALID_HRQSIZE = 0x05, + NVME_RDMA_CM_NO_RSC = 0x06, + NVME_RDMA_CM_INVALID_IRD = 0x07, + NVME_RDMA_CM_INVALID_ORD = 0x08, +}; + +/** + * struct nvme_rdma_cm_req - rdma connect request + * + * @recfmt: format of the RDMA Private Data + * @qid: queue Identifier for the Admin or I/O Queue + * @hrqsize: host receive queue size to be created + * @hsqsize: host send queue size to be created + */ +struct nvme_rdma_cm_req { + __le16 recfmt; + __le16 qid; + __le16 hrqsize; + __le16 hsqsize; + u8 rsvd[24]; +}; + +/** + * struct nvme_rdma_cm_rep - rdma connect reply + * + * @recfmt: format of the RDMA Private Data + * @crqsize: controller receive queue size + */ +struct nvme_rdma_cm_rep { + __le16 recfmt; + __le16 crqsize; + u8 rsvd[28]; +}; + +/** + * struct nvme_rdma_cm_rej - rdma connect reject + * + * @recfmt: format of the RDMA Private Data + * @fsts: error status for the associated connect request + */ +struct nvme_rdma_cm_rej { + __le16 recfmt; + __le16 sts; +}; + +#endif /* _LINUX_NVME_RDMA_H */ -- cgit v1.2.3 From a6a0dbbcfa469cf3e5c4d9522106c0b7b9e9e373 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 14 Jun 2016 11:13:09 +0200 Subject: pwm: Add a helper to prepare a new PWM state The pwm_init_state() helper prepares a new state object containing the current PWM state except for the polarity and period fields which are set to the reference values (those in struct pwm_args). This is particularly useful for PWM users who want to apply a new duty- cycle expressed relatively to the reference period without changing the enable state. Signed-off-by: Boris Brezillon Tested-by: Heiko Stuebner Signed-off-by: Thierry Reding --- include/linux/pwm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 17018f3c066e..a100f6e80738 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -147,6 +147,39 @@ static inline void pwm_get_args(const struct pwm_device *pwm, *args = pwm->args; } +/** + * pwm_init_state() - prepare a new state to be applied with pwm_apply_state() + * @pwm: PWM device + * @state: state to fill with the prepared PWM state + * + * This functions prepares a state that can later be tweaked and applied + * to the PWM device with pwm_apply_state(). This is a convenient function + * that first retrieves the current PWM state and the replaces the period + * and polarity fields with the reference values defined in pwm->args. + * Once the function returns, you can adjust the ->enabled and ->duty_cycle + * fields according to your needs before calling pwm_apply_state(). + * + * ->duty_cycle is initially set to zero to avoid cases where the current + * ->duty_cycle value exceed the pwm_args->period one, which would trigger + * an error if the user calls pwm_apply_state() without adjusting ->duty_cycle + * first. + */ +static inline void pwm_init_state(const struct pwm_device *pwm, + struct pwm_state *state) +{ + struct pwm_args args; + + /* First get the current state. */ + pwm_get_state(pwm, state); + + /* Then fill it with the reference config */ + pwm_get_args(pwm, &args); + + state->period = args.period; + state->polarity = args.polarity; + state->duty_cycle = 0; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM -- cgit v1.2.3 From f6f3bddf7b2b994a927808fcc5a3d07069c35956 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 14 Jun 2016 11:13:10 +0200 Subject: pwm: Add relative duty cycle manipulation helpers The PWM framework expects PWM users to configure the duty cycle in nano- seconds, but many users want to express the duty cycle relatively to the period value (i.e. duty_cycle = 33% of the period). Add the pwm_{get,set}_relative_duty_cycle() helpers to ease this kind of conversion. Signed-off-by: Boris Brezillon Tested-by: Heiko Stuebner Signed-off-by: Thierry Reding --- include/linux/pwm.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index a100f6e80738..fd1092729ed6 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -180,6 +180,61 @@ static inline void pwm_init_state(const struct pwm_device *pwm, state->duty_cycle = 0; } +/** + * pwm_get_relative_duty_cycle() - Get a relative duty cycle value + * @state: PWM state to extract the duty cycle from + * @scale: target scale of the relative duty cycle + * + * This functions converts the absolute duty cycle stored in @state (expressed + * in nanosecond) into a value relative to the period. + * + * For example if you want to get the duty_cycle expressed in percent, call: + * + * pwm_get_state(pwm, &state); + * duty = pwm_get_relative_duty_cycle(&state, 100); + */ +static inline unsigned int +pwm_get_relative_duty_cycle(const struct pwm_state *state, unsigned int scale) +{ + if (!state->period) + return 0; + + return DIV_ROUND_CLOSEST_ULL((u64)state->duty_cycle * scale, + state->period); +} + +/** + * pwm_set_relative_duty_cycle() - Set a relative duty cycle value + * @state: PWM state to fill + * @duty_cycle: relative duty cycle value + * @scale: scale in which @duty_cycle is expressed + * + * This functions converts a relative into an absolute duty cycle (expressed + * in nanoseconds), and puts the result in state->duty_cycle. + * + * For example if you want to configure a 50% duty cycle, call: + * + * pwm_init_state(pwm, &state); + * pwm_set_relative_duty_cycle(&state, 50, 100); + * pwm_apply_state(pwm, &state); + * + * This functions returns -EINVAL if @duty_cycle and/or @scale are + * inconsistent (@scale == 0 or @duty_cycle > @scale). + */ +static inline int +pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, + unsigned int scale) +{ + if (!scale || duty_cycle > scale) + return -EINVAL; + + state->duty_cycle = DIV_ROUND_CLOSEST_ULL((u64)duty_cycle * + state->period, + scale); + + return 0; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM -- cgit v1.2.3 From 2b77487f2e8ff7e6496a7f5a08839de9bbb39ab3 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Jun 2016 15:49:53 +0200 Subject: pwm: Remove gratuitous blank line Commit 5ec803edcb70 ("pwm: Add core infrastructure to allow atomic updates") introduced this double blank line by mistake. Signed-off-by: Thierry Reding --- include/linux/pwm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index fd1092729ed6..83d8bcb7e1de 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -408,7 +408,6 @@ static inline void pwm_disable(struct pwm_device *pwm) pwm_apply_state(pwm, &state); } - /* PWM provider APIs */ int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); -- cgit v1.2.3 From d16e832da23edff951015f108525ef31ae8dea37 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 15 Apr 2016 09:15:05 -0300 Subject: [media] vb2: move dma_attrs to vb2_queue Make the dma attributes struct part of vb2_queue. This greatly simplifies the remainder of the patch series since the dma_contig alloc context is now (as before) just a struct device pointer. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Cc: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-core.h | 7 ++++--- include/media/videobuf2-dma-contig.h | 9 +-------- 2 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 88e3ab496e8f..444ef3b9d39f 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -27,7 +27,6 @@ enum vb2_memory { VB2_MEMORY_DMABUF = 4, }; -struct vb2_alloc_ctx; struct vb2_fileio_data; struct vb2_threadio_data; @@ -93,8 +92,8 @@ struct vb2_threadio_data; * unmap_dmabuf. */ struct vb2_mem_ops { - void *(*alloc)(void *alloc_ctx, unsigned long size, - enum dma_data_direction dma_dir, + void *(*alloc)(void *alloc_ctx, const struct dma_attrs *attrs, + unsigned long size, enum dma_data_direction dma_dir, gfp_t gfp_flags); void (*put)(void *buf_priv); struct dma_buf *(*get_dmabuf)(void *buf_priv, unsigned long flags); @@ -401,6 +400,7 @@ struct vb2_buf_ops { * caller. For example, for V4L2, it should match * the V4L2_BUF_TYPE_* in include/uapi/linux/videodev2.h * @io_modes: supported io methods (see vb2_io_modes enum) + * @dma_attrs: DMA attributes to use for the DMA. May be NULL. * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver @@ -467,6 +467,7 @@ struct vb2_buf_ops { struct vb2_queue { unsigned int type; unsigned int io_modes; + const struct dma_attrs *dma_attrs; unsigned fileio_read_once:1; unsigned fileio_write_immediately:1; unsigned allow_zero_bytesused:1; diff --git a/include/media/videobuf2-dma-contig.h b/include/media/videobuf2-dma-contig.h index f7dc8401817e..5bdd4a4072e5 100644 --- a/include/media/videobuf2-dma-contig.h +++ b/include/media/videobuf2-dma-contig.h @@ -26,14 +26,7 @@ vb2_dma_contig_plane_dma_addr(struct vb2_buffer *vb, unsigned int plane_no) return *addr; } -void *vb2_dma_contig_init_ctx_attrs(struct device *dev, - struct dma_attrs *attrs); - -static inline void *vb2_dma_contig_init_ctx(struct device *dev) -{ - return vb2_dma_contig_init_ctx_attrs(dev, NULL); -} - +void *vb2_dma_contig_init_ctx(struct device *dev); void vb2_dma_contig_cleanup_ctx(void *alloc_ctx); int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size); void vb2_dma_contig_clear_max_seg_size(struct device *dev); -- cgit v1.2.3 From 20be7ab8dba68072b34ae2285c282290b2344339 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 16 Dec 2015 08:30:43 -0200 Subject: [media] vb2: add a dev field to use for the default allocation context The allocation context is nothing more than a per-plane device pointer to use when allocating buffers. So just provide a dev pointer in vb2_queue for that purpose and drivers can skip allocating/releasing/filling in the allocation context unless they require different per-plane device pointers as used by some Samsung SoCs. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Cc: Sakari Ailus Cc: Florian Echtler Cc: Federico Vaga Cc: "Lad, Prabhakar" Cc: Scott Jiang Acked-by: Philipp Zabel Cc: Fabien Dessenne Acked-by: Benoit Parrot Cc: Mikhail Ulyanov Cc: Guennadi Liakhovetski Cc: Jonathan Corbet Cc: Ludovic Desroches Cc: Sergei Shtylyov Cc: Kyungmin Park Cc: Sylwester Nawrocki Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 444ef3b9d39f..d38668c2ea06 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -400,6 +400,8 @@ struct vb2_buf_ops { * caller. For example, for V4L2, it should match * the V4L2_BUF_TYPE_* in include/uapi/linux/videodev2.h * @io_modes: supported io methods (see vb2_io_modes enum) + * @dev: device to use for the default allocation context if the driver + * doesn't fill in the @alloc_ctx array. * @dma_attrs: DMA attributes to use for the DMA. May be NULL. * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call @@ -467,6 +469,7 @@ struct vb2_buf_ops { struct vb2_queue { unsigned int type; unsigned int io_modes; + struct device *dev; const struct dma_attrs *dma_attrs; unsigned fileio_read_once:1; unsigned fileio_write_immediately:1; -- cgit v1.2.3 From 53ddcc683faef8c730c7162fa1ef2261a385d16d Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 15 Feb 2016 13:09:10 -0200 Subject: [media] media/platform: convert drivers to use the new vb2_queue dev field Stop using alloc_ctx and just fill in the device pointer. Signed-off-by: Hans Verkuil Acked-by: Lad, Prabhakar Cc: Scott Jiang Acked-by: Philipp Zabel Signed-off-by: Mauro Carvalho Chehab --- include/media/davinci/vpbe_display.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/davinci/vpbe_display.h b/include/media/davinci/vpbe_display.h index e14a9370b67e..12783fd823f8 100644 --- a/include/media/davinci/vpbe_display.h +++ b/include/media/davinci/vpbe_display.h @@ -81,8 +81,6 @@ struct vpbe_layer { * Buffer queue used in video-buf */ struct vb2_queue buffer_queue; - /* allocator-specific contexts for each plane */ - struct vb2_alloc_ctx *alloc_ctx; /* Queue of filled frames */ struct list_head dma_queue; /* Used in video-buf */ -- cgit v1.2.3 From 36c0f8b32c4bd4f668cedfba6d97afaa84f055fb Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 15 Apr 2016 09:15:05 -0300 Subject: [media] vb2: replace void *alloc_ctxs by struct device *alloc_devs Make this a proper typed array. Drop the old allocate context code since that is no longer used. Note that the memops functions now get a struct device pointer instead of the struct device ** that was there initially (actually a void pointer to a struct containing only a struct device pointer). This code is now a lot cleaner. Signed-off-by: Hans Verkuil Reviewed-by: Laurent Pinchart Cc: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- include/media/videobuf2-core.h | 18 +++++++++--------- include/media/videobuf2-dma-contig.h | 2 -- include/media/videobuf2-dma-sg.h | 3 --- 3 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index d38668c2ea06..bea81c9e3758 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -56,7 +56,7 @@ struct vb2_threadio_data; * @put_userptr: inform the allocator that a USERPTR buffer will no longer * be used. * @attach_dmabuf: attach a shared struct dma_buf for a hardware operation; - * used for DMABUF memory types; alloc_ctx is the alloc context + * used for DMABUF memory types; dev is the alloc device * dbuf is the shared dma_buf; returns NULL on failure; * allocator private per-buffer structure on success; * this needs to be used for further accesses to the buffer. @@ -92,13 +92,13 @@ struct vb2_threadio_data; * unmap_dmabuf. */ struct vb2_mem_ops { - void *(*alloc)(void *alloc_ctx, const struct dma_attrs *attrs, + void *(*alloc)(struct device *dev, const struct dma_attrs *attrs, unsigned long size, enum dma_data_direction dma_dir, gfp_t gfp_flags); void (*put)(void *buf_priv); struct dma_buf *(*get_dmabuf)(void *buf_priv, unsigned long flags); - void *(*get_userptr)(void *alloc_ctx, unsigned long vaddr, + void *(*get_userptr)(struct device *dev, unsigned long vaddr, unsigned long size, enum dma_data_direction dma_dir); void (*put_userptr)(void *buf_priv); @@ -106,7 +106,7 @@ struct vb2_mem_ops { void (*prepare)(void *buf_priv); void (*finish)(void *buf_priv); - void *(*attach_dmabuf)(void *alloc_ctx, struct dma_buf *dbuf, + void *(*attach_dmabuf)(struct device *dev, struct dma_buf *dbuf, unsigned long size, enum dma_data_direction dma_dir); void (*detach_dmabuf)(void *buf_priv); @@ -281,7 +281,7 @@ struct vb2_buffer { * in *num_buffers, the required number of planes per * buffer in *num_planes, the size of each plane should be * set in the sizes[] array and optional per-plane - * allocator specific context in the alloc_ctxs[] array. + * allocator specific device in the alloc_devs[] array. * When called from VIDIOC_REQBUFS, *num_planes == 0, the * driver has to use the currently configured format to * determine the plane sizes and *num_buffers is the total @@ -355,7 +355,7 @@ struct vb2_buffer { struct vb2_ops { int (*queue_setup)(struct vb2_queue *q, unsigned int *num_buffers, unsigned int *num_planes, - unsigned int sizes[], void *alloc_ctxs[]); + unsigned int sizes[], struct device *alloc_devs[]); void (*wait_prepare)(struct vb2_queue *q); void (*wait_finish)(struct vb2_queue *q); @@ -401,7 +401,7 @@ struct vb2_buf_ops { * the V4L2_BUF_TYPE_* in include/uapi/linux/videodev2.h * @io_modes: supported io methods (see vb2_io_modes enum) * @dev: device to use for the default allocation context if the driver - * doesn't fill in the @alloc_ctx array. + * doesn't fill in the @alloc_devs array. * @dma_attrs: DMA attributes to use for the DMA. May be NULL. * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call @@ -449,7 +449,7 @@ struct vb2_buf_ops { * @done_list: list of buffers ready to be dequeued to userspace * @done_lock: lock to protect done_list list * @done_wq: waitqueue for processes waiting for buffers ready to be dequeued - * @alloc_ctx: memory type/allocator-specific contexts for each plane + * @alloc_devs: memory type/allocator-specific per-plane device * @streaming: current streaming state * @start_streaming_called: start_streaming() was called successfully and we * started streaming. @@ -503,7 +503,7 @@ struct vb2_queue { spinlock_t done_lock; wait_queue_head_t done_wq; - void *alloc_ctx[VB2_MAX_PLANES]; + struct device *alloc_devs[VB2_MAX_PLANES]; unsigned int streaming:1; unsigned int start_streaming_called:1; diff --git a/include/media/videobuf2-dma-contig.h b/include/media/videobuf2-dma-contig.h index 5bdd4a4072e5..df2aabee3401 100644 --- a/include/media/videobuf2-dma-contig.h +++ b/include/media/videobuf2-dma-contig.h @@ -26,8 +26,6 @@ vb2_dma_contig_plane_dma_addr(struct vb2_buffer *vb, unsigned int plane_no) return *addr; } -void *vb2_dma_contig_init_ctx(struct device *dev); -void vb2_dma_contig_cleanup_ctx(void *alloc_ctx); int vb2_dma_contig_set_max_seg_size(struct device *dev, unsigned int size); void vb2_dma_contig_clear_max_seg_size(struct device *dev); diff --git a/include/media/videobuf2-dma-sg.h b/include/media/videobuf2-dma-sg.h index 8d1083f83c3d..52afa0e2bb17 100644 --- a/include/media/videobuf2-dma-sg.h +++ b/include/media/videobuf2-dma-sg.h @@ -21,9 +21,6 @@ static inline struct sg_table *vb2_dma_sg_plane_desc( return (struct sg_table *)vb2_plane_cookie(vb, plane_no); } -void *vb2_dma_sg_init_ctx(struct device *dev); -void vb2_dma_sg_cleanup_ctx(void *alloc_ctx); - extern const struct vb2_mem_ops vb2_dma_sg_memops; #endif -- cgit v1.2.3 From 10c7e20b2ff3caa5a8c0e7d60aef5a9c86e60ce8 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Fri, 8 Jul 2016 19:13:08 +0300 Subject: ACPI / scan: fix enumeration (visited) flags for bus rescans If the ACPI tables change as a result of a dinamically loaded table and a bus rescan is required the enumeration/visited flag are not consistent. I2C/SPI are not directly enumerated in acpi_bus_attach(), however the visited flag is set. This makes it impossible to check if an ACPI device has already been enumerated by the I2C and SPI subsystems. To fix this issue we only set the visited flags if the device is not I2C or SPI. With this change we also need to remove setting visited to false from acpi_bus_attach(), otherwise if we rescan already enumerated I2C/SPI devices we try to re-enumerate them. Note that I2C/SPI devices can be enumerated either via a scan handler (when using PRP0001) or via regular device_attach(). In either case the flow goes through acpi_default_enumeration() which makes it the ideal place to mark the ACPI device as enumerated. Signed-off-by: Octavian Purdila Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ef2ad26abede..db680e8788c4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -531,6 +531,16 @@ void acpi_walk_dep_device_list(acpi_handle handle); struct platform_device *acpi_create_platform_device(struct acpi_device *); #define ACPI_PTR(_ptr) (_ptr) +static inline void acpi_device_set_enumerated(struct acpi_device *adev) +{ + adev->flags.visited = true; +} + +static inline void acpi_device_clear_enumerated(struct acpi_device *adev) +{ + adev->flags.visited = false; +} + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -676,6 +686,14 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) #define ACPI_PTR(_ptr) (NULL) +static inline void acpi_device_set_enumerated(struct acpi_device *adev) +{ +} + +static inline void acpi_device_clear_enumerated(struct acpi_device *adev) +{ +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI -- cgit v1.2.3 From 68bdb6773289f8c9a36633f9f6525b127c093258 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Fri, 8 Jul 2016 19:13:09 +0300 Subject: ACPI: add support for ACPI reconfiguration notifiers Add support for ACPI reconfiguration notifiers to allow subsystems to react to changes in the ACPI tables that happen after the initial enumeration. This is similar with the way dynamic device tree notifications work. The reconfigure notifications supported for now are device add and device remove. Since ACPICA allows only one table notification handler, this patch makes the table notifier function generic and moves it out of the sysfs specific code. Signed-off-by: Octavian Purdila Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index db680e8788c4..8b48de17e388 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -541,6 +541,14 @@ static inline void acpi_device_clear_enumerated(struct acpi_device *adev) adev->flags.visited = false; } +enum acpi_reconfig_event { + ACPI_RECONFIG_DEVICE_ADD = 0, + ACPI_RECONFIG_DEVICE_REMOVE, +}; + +int acpi_reconfig_notifier_register(struct notifier_block *nb); +int acpi_reconfig_notifier_unregister(struct notifier_block *nb); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -694,6 +702,16 @@ static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } +static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) +{ + return -EINVAL; +} + +static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) +{ + return -EINVAL; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI -- cgit v1.2.3 From 12655445a2adc292db3352bbe80e43bd243517aa Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 30 Jun 2016 07:01:41 -0300 Subject: [media] cec.h/cec-funcs.h: add option to use BSD license Like the videodev2.h and other headers, explicitly allow these headers to be used with the BSD license. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 16 ++++++++++++++++ include/linux/cec.h | 16 ++++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 8ee1029b9b74..19486009693a 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -7,6 +7,22 @@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation; version 2 of the License. * + * Alternatively you can redistribute this file under the terms of the + * BSD license as stated below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * 3. The names of its contributors may not be used to endorse or promote + * products derived from this software without specific prior written + * permission. + * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND diff --git a/include/linux/cec.h b/include/linux/cec.h index 40924e79465d..6678afe26844 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -7,6 +7,22 @@ * it under the terms of the GNU General Public License as published by * the Free Software Foundation; version 2 of the License. * + * Alternatively you can redistribute this file under the terms of the + * BSD license as stated below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * 3. The names of its contributors may not be used to endorse or promote + * products derived from this software without specific prior written + * permission. + * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND -- cgit v1.2.3 From 0cb1f1e44cf5b013dd0991f509e332ac77ce2ddd Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 6 Jul 2016 05:49:26 -0300 Subject: [media] cec-funcs.h: add length checks Add msg->len sanity checks to fix static checker warning: include/linux/cec-funcs.h:1154 cec_ops_set_osd_string() warn: setting length 'msg->len - 3' to negative one Signed-off-by: Hans Verkuil Reported-by: Dan Carpenter Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 19486009693a..8d217ce53034 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -788,7 +788,7 @@ static inline void cec_msg_set_timer_program_title(struct cec_msg *msg, static inline void cec_ops_set_timer_program_title(const struct cec_msg *msg, char *prog_title) { - unsigned int len = msg->len - 2; + unsigned int len = msg->len > 2 ? msg->len - 2 : 0; if (len > 14) len = 14; @@ -1167,7 +1167,7 @@ static inline void cec_ops_set_osd_string(const struct cec_msg *msg, __u8 *disp_ctl, char *osd) { - unsigned int len = msg->len - 3; + unsigned int len = msg->len > 3 ? msg->len - 3 : 0; *disp_ctl = msg->msg[2]; if (len > 13) @@ -1192,7 +1192,7 @@ static inline void cec_msg_set_osd_name(struct cec_msg *msg, const char *name) static inline void cec_ops_set_osd_name(const struct cec_msg *msg, char *name) { - unsigned int len = msg->len - 2; + unsigned int len = msg->len > 2 ? msg->len - 2 : 0; if (len > 14) len = 14; -- cgit v1.2.3 From 0c1f8569942695b7a2735301efe45ecd69e2a41f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 8 Jul 2016 05:36:26 -0300 Subject: [media] cec-funcs.h: add missing const modifier The cec_ops_* functions never touch cec_msg, so mark it as const. This was done for some of the cec_ops_ functions, but not all. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 8d217ce53034..455f9df86c43 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -420,7 +420,7 @@ static inline void cec_msg_timer_status(struct cec_msg *msg, } } -static inline void cec_ops_timer_status(struct cec_msg *msg, +static inline void cec_ops_timer_status(const struct cec_msg *msg, __u8 *timer_overlap_warning, __u8 *media_info, __u8 *prog_info, @@ -455,7 +455,7 @@ static inline void cec_msg_timer_cleared_status(struct cec_msg *msg, msg->msg[2] = timer_cleared_status; } -static inline void cec_ops_timer_cleared_status(struct cec_msg *msg, +static inline void cec_ops_timer_cleared_status(const struct cec_msg *msg, __u8 *timer_cleared_status) { *timer_cleared_status = msg->msg[2]; @@ -491,7 +491,7 @@ static inline void cec_msg_clear_analogue_timer(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; } -static inline void cec_ops_clear_analogue_timer(struct cec_msg *msg, +static inline void cec_ops_clear_analogue_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -541,7 +541,7 @@ static inline void cec_msg_clear_digital_timer(struct cec_msg *msg, cec_set_digital_service_id(msg->msg + 9, digital); } -static inline void cec_ops_clear_digital_timer(struct cec_msg *msg, +static inline void cec_ops_clear_digital_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -592,7 +592,7 @@ static inline void cec_msg_clear_ext_timer(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_TIMER_CLEARED_STATUS : 0; } -static inline void cec_ops_clear_ext_timer(struct cec_msg *msg, +static inline void cec_ops_clear_ext_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -647,7 +647,7 @@ static inline void cec_msg_set_analogue_timer(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; } -static inline void cec_ops_set_analogue_timer(struct cec_msg *msg, +static inline void cec_ops_set_analogue_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -697,7 +697,7 @@ static inline void cec_msg_set_digital_timer(struct cec_msg *msg, cec_set_digital_service_id(msg->msg + 9, digital); } -static inline void cec_ops_set_digital_timer(struct cec_msg *msg, +static inline void cec_ops_set_digital_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -748,7 +748,7 @@ static inline void cec_msg_set_ext_timer(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_TIMER_STATUS : 0; } -static inline void cec_ops_set_ext_timer(struct cec_msg *msg, +static inline void cec_ops_set_ext_timer(const struct cec_msg *msg, __u8 *day, __u8 *month, __u8 *start_hr, @@ -853,7 +853,7 @@ static inline void cec_msg_set_menu_language(struct cec_msg *msg, memcpy(msg->msg + 2, language, 3); } -static inline void cec_ops_set_menu_language(struct cec_msg *msg, +static inline void cec_ops_set_menu_language(const struct cec_msg *msg, char *language) { memcpy(language, msg->msg + 2, 3); @@ -926,7 +926,7 @@ static inline void cec_msg_deck_control(struct cec_msg *msg, msg->msg[2] = deck_control_mode; } -static inline void cec_ops_deck_control(struct cec_msg *msg, +static inline void cec_ops_deck_control(const struct cec_msg *msg, __u8 *deck_control_mode) { *deck_control_mode = msg->msg[2]; @@ -940,7 +940,7 @@ static inline void cec_msg_deck_status(struct cec_msg *msg, msg->msg[2] = deck_info; } -static inline void cec_ops_deck_status(struct cec_msg *msg, +static inline void cec_ops_deck_status(const struct cec_msg *msg, __u8 *deck_info) { *deck_info = msg->msg[2]; @@ -956,7 +956,7 @@ static inline void cec_msg_give_deck_status(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_DECK_STATUS : 0; } -static inline void cec_ops_give_deck_status(struct cec_msg *msg, +static inline void cec_ops_give_deck_status(const struct cec_msg *msg, __u8 *status_req) { *status_req = msg->msg[2]; @@ -970,7 +970,7 @@ static inline void cec_msg_play(struct cec_msg *msg, msg->msg[2] = play_mode; } -static inline void cec_ops_play(struct cec_msg *msg, +static inline void cec_ops_play(const struct cec_msg *msg, __u8 *play_mode) { *play_mode = msg->msg[2]; @@ -1035,7 +1035,7 @@ static inline void cec_msg_tuner_device_status(struct cec_msg *msg, &tuner_dev_info->digital); } -static inline void cec_ops_tuner_device_status(struct cec_msg *msg, +static inline void cec_ops_tuner_device_status(const struct cec_msg *msg, struct cec_op_tuner_device_info *tuner_dev_info) { tuner_dev_info->is_analog = msg->len < 10; @@ -1060,7 +1060,7 @@ static inline void cec_msg_give_tuner_device_status(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_TUNER_DEVICE_STATUS : 0; } -static inline void cec_ops_give_tuner_device_status(struct cec_msg *msg, +static inline void cec_ops_give_tuner_device_status(const struct cec_msg *msg, __u8 *status_req) { *status_req = msg->msg[2]; @@ -1079,7 +1079,7 @@ static inline void cec_msg_select_analogue_service(struct cec_msg *msg, msg->msg[5] = bcast_system; } -static inline void cec_ops_select_analogue_service(struct cec_msg *msg, +static inline void cec_ops_select_analogue_service(const struct cec_msg *msg, __u8 *ana_bcast_type, __u16 *ana_freq, __u8 *bcast_system) @@ -1097,7 +1097,7 @@ static inline void cec_msg_select_digital_service(struct cec_msg *msg, cec_set_digital_service_id(msg->msg + 2, digital); } -static inline void cec_ops_select_digital_service(struct cec_msg *msg, +static inline void cec_ops_select_digital_service(const struct cec_msg *msg, struct cec_op_digital_service_id *digital) { cec_get_digital_service_id(msg->msg + 2, digital); @@ -1218,7 +1218,7 @@ static inline void cec_msg_menu_status(struct cec_msg *msg, msg->msg[2] = menu_state; } -static inline void cec_ops_menu_status(struct cec_msg *msg, +static inline void cec_ops_menu_status(const struct cec_msg *msg, __u8 *menu_state) { *menu_state = msg->msg[2]; @@ -1234,7 +1234,7 @@ static inline void cec_msg_menu_request(struct cec_msg *msg, msg->reply = reply ? CEC_MSG_MENU_STATUS : 0; } -static inline void cec_ops_menu_request(struct cec_msg *msg, +static inline void cec_ops_menu_request(const struct cec_msg *msg, __u8 *menu_req) { *menu_req = msg->msg[2]; @@ -1284,7 +1284,7 @@ static inline void cec_msg_user_control_pressed(struct cec_msg *msg, } } -static inline void cec_ops_user_control_pressed(struct cec_msg *msg, +static inline void cec_ops_user_control_pressed(const struct cec_msg *msg, struct cec_op_ui_command *ui_cmd) { ui_cmd->ui_cmd = msg->msg[2]; -- cgit v1.2.3 From 9ad52b4db79d168867a2ca105eca00fb9cb28fe5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 8 Jul 2016 05:52:34 -0300 Subject: [media] cec-funcs.h: add missing 'reply' for short audio descriptor The cec_msg_request_short_audio_descriptor function was missing the reply argument. That's needed if you want the framework to wait for the reply message. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec-funcs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cec-funcs.h b/include/linux/cec-funcs.h index 455f9df86c43..82c3d3b7269d 100644 --- a/include/linux/cec-funcs.h +++ b/include/linux/cec-funcs.h @@ -1494,6 +1494,7 @@ static inline void cec_ops_report_short_audio_descriptor(const struct cec_msg *m } static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, + bool reply, __u8 num_descriptors, const __u8 *audio_format_id, const __u8 *audio_format_code) @@ -1504,6 +1505,7 @@ static inline void cec_msg_request_short_audio_descriptor(struct cec_msg *msg, num_descriptors = 4; msg->len = 2 + num_descriptors; msg->msg[1] = CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR; + msg->reply = reply ? CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR : 0; for (i = 0; i < num_descriptors; i++) msg->msg[2 + i] = (audio_format_id[i] << 6) | (audio_format_code[i] & 0x3f); -- cgit v1.2.3 From 0577e4853bfb4c65f620fa56d3157692df7f766e Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Wed, 29 Jun 2016 21:05:34 +0200 Subject: clk: sunxi-ng: Add H3 clocks Add the list of clocks and resets found in the H3 CCU. Signed-off-by: Maxime Ripard Signed-off-by: Michael Turquette Link: lkml.kernel.org/r/20160629190535.11855-14-maxime.ripard@free-electrons.com --- include/dt-bindings/clock/sun8i-h3-ccu.h | 145 +++++++++++++++++++++++++++++++ include/dt-bindings/reset/sun8i-h3-ccu.h | 103 ++++++++++++++++++++++ 2 files changed, 248 insertions(+) create mode 100644 include/dt-bindings/clock/sun8i-h3-ccu.h create mode 100644 include/dt-bindings/reset/sun8i-h3-ccu.h (limited to 'include') diff --git a/include/dt-bindings/clock/sun8i-h3-ccu.h b/include/dt-bindings/clock/sun8i-h3-ccu.h new file mode 100644 index 000000000000..efb7ba2bd515 --- /dev/null +++ b/include/dt-bindings/clock/sun8i-h3-ccu.h @@ -0,0 +1,145 @@ +/* + * Copyright (C) 2016 Maxime Ripard + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef _DT_BINDINGS_CLK_SUN8I_H3_H_ +#define _DT_BINDINGS_CLK_SUN8I_H3_H_ + +#define CLK_CPUX 14 + +#define CLK_BUS_CE 20 +#define CLK_BUS_DMA 21 +#define CLK_BUS_MMC0 22 +#define CLK_BUS_MMC1 23 +#define CLK_BUS_MMC2 24 +#define CLK_BUS_NAND 25 +#define CLK_BUS_DRAM 26 +#define CLK_BUS_EMAC 27 +#define CLK_BUS_TS 28 +#define CLK_BUS_HSTIMER 29 +#define CLK_BUS_SPI0 30 +#define CLK_BUS_SPI1 31 +#define CLK_BUS_OTG 32 +#define CLK_BUS_EHCI0 33 +#define CLK_BUS_EHCI1 34 +#define CLK_BUS_EHCI2 35 +#define CLK_BUS_EHCI3 36 +#define CLK_BUS_OHCI0 37 +#define CLK_BUS_OHCI1 38 +#define CLK_BUS_OHCI2 39 +#define CLK_BUS_OHCI3 40 +#define CLK_BUS_VE 41 +#define CLK_BUS_TCON0 42 +#define CLK_BUS_TCON1 43 +#define CLK_BUS_DEINTERLACE 44 +#define CLK_BUS_CSI 45 +#define CLK_BUS_TVE 46 +#define CLK_BUS_HDMI 47 +#define CLK_BUS_DE 48 +#define CLK_BUS_GPU 49 +#define CLK_BUS_MSGBOX 50 +#define CLK_BUS_SPINLOCK 51 +#define CLK_BUS_CODEC 52 +#define CLK_BUS_SPDIF 53 +#define CLK_BUS_PIO 54 +#define CLK_BUS_THS 55 +#define CLK_BUS_I2S0 56 +#define CLK_BUS_I2S1 57 +#define CLK_BUS_I2S2 58 +#define CLK_BUS_I2C0 59 +#define CLK_BUS_I2C1 60 +#define CLK_BUS_I2C2 61 +#define CLK_BUS_UART0 62 +#define CLK_BUS_UART1 63 +#define CLK_BUS_UART2 64 +#define CLK_BUS_UART3 65 +#define CLK_BUS_SCR 66 +#define CLK_BUS_EPHY 67 +#define CLK_BUS_DBG 68 + +#define CLK_THS 69 +#define CLK_NAND 70 +#define CLK_MMC0 71 +#define CLK_MMC0_SAMPLE 72 +#define CLK_MMC0_OUTPUT 73 +#define CLK_MMC1 74 +#define CLK_MMC1_SAMPLE 75 +#define CLK_MMC1_OUTPUT 76 +#define CLK_MMC2 77 +#define CLK_MMC2_SAMPLE 78 +#define CLK_MMC2_OUTPUT 79 +#define CLK_TS 80 +#define CLK_CE 81 +#define CLK_SPI0 82 +#define CLK_SPI1 83 +#define CLK_I2S0 84 +#define CLK_I2S1 85 +#define CLK_I2S2 86 +#define CLK_SPDIF 87 +#define CLK_USB_PHY0 88 +#define CLK_USB_PHY1 89 +#define CLK_USB_PHY2 90 +#define CLK_USB_PHY3 91 +#define CLK_USB_OHCI0 92 +#define CLK_USB_OHCI1 93 +#define CLK_USB_OHCI2 94 +#define CLK_USB_OHCI3 95 + +#define CLK_DRAM_VE 97 +#define CLK_DRAM_CSI 98 +#define CLK_DRAM_DEINTERLACE 99 +#define CLK_DRAM_TS 100 +#define CLK_DE 101 +#define CLK_TCON0 102 +#define CLK_TVE 103 +#define CLK_DEINTERLACE 104 +#define CLK_CSI_MISC 105 +#define CLK_CSI_SCLK 106 +#define CLK_CSI_MCLK 107 +#define CLK_VE 108 +#define CLK_AC_DIG 109 +#define CLK_AVS 110 +#define CLK_HDMI 111 +#define CLK_HDMI_DDC 112 + +#define CLK_GPU 114 + +#endif /* _DT_BINDINGS_CLK_SUN8I_H3_H_ */ diff --git a/include/dt-bindings/reset/sun8i-h3-ccu.h b/include/dt-bindings/reset/sun8i-h3-ccu.h new file mode 100644 index 000000000000..6b7af80c26ec --- /dev/null +++ b/include/dt-bindings/reset/sun8i-h3-ccu.h @@ -0,0 +1,103 @@ +/* + * Copyright (C) 2016 Maxime Ripard + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, + * copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following + * conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES + * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT + * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, + * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef _DT_BINDINGS_RST_SUN8I_H3_H_ +#define _DT_BINDINGS_RST_SUN8I_H3_H_ + +#define RST_USB_PHY0 0 +#define RST_USB_PHY1 1 +#define RST_USB_PHY2 2 +#define RST_USB_PHY3 3 + +#define RST_MBUS 4 + +#define RST_BUS_CE 5 +#define RST_BUS_DMA 6 +#define RST_BUS_MMC0 7 +#define RST_BUS_MMC1 8 +#define RST_BUS_MMC2 9 +#define RST_BUS_NAND 10 +#define RST_BUS_DRAM 11 +#define RST_BUS_EMAC 12 +#define RST_BUS_TS 13 +#define RST_BUS_HSTIMER 14 +#define RST_BUS_SPI0 15 +#define RST_BUS_SPI1 16 +#define RST_BUS_OTG 17 +#define RST_BUS_EHCI0 18 +#define RST_BUS_EHCI1 19 +#define RST_BUS_EHCI2 20 +#define RST_BUS_EHCI3 21 +#define RST_BUS_OHCI0 22 +#define RST_BUS_OHCI1 23 +#define RST_BUS_OHCI2 24 +#define RST_BUS_OHCI3 25 +#define RST_BUS_VE 26 +#define RST_BUS_TCON0 27 +#define RST_BUS_TCON1 28 +#define RST_BUS_DEINTERLACE 29 +#define RST_BUS_CSI 30 +#define RST_BUS_TVE 31 +#define RST_BUS_HDMI0 32 +#define RST_BUS_HDMI1 33 +#define RST_BUS_DE 34 +#define RST_BUS_GPU 35 +#define RST_BUS_MSGBOX 36 +#define RST_BUS_SPINLOCK 37 +#define RST_BUS_DBG 38 +#define RST_BUS_EPHY 39 +#define RST_BUS_CODEC 40 +#define RST_BUS_SPDIF 41 +#define RST_BUS_THS 42 +#define RST_BUS_I2S0 43 +#define RST_BUS_I2S1 44 +#define RST_BUS_I2S2 45 +#define RST_BUS_I2C0 46 +#define RST_BUS_I2C1 47 +#define RST_BUS_I2C2 48 +#define RST_BUS_UART0 49 +#define RST_BUS_UART1 50 +#define RST_BUS_UART2 51 +#define RST_BUS_UART3 52 +#define RST_BUS_SCR 53 + +#endif /* _DT_BINDINGS_RST_SUN8I_H3_H_ */ -- cgit v1.2.3 From d390238c4fba7c87a3bcd859ce3373c864eb7b02 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 6 Jul 2016 20:03:54 -0400 Subject: net: dsa: initialize the routing table The routing table of every switch in a tree is currently initialized to all zeros. This is an issue since 0 is a valid port number. Add a DSA_RTABLE_NONE=-1 constant to initialize the signed values of the routing table pointing to other switches. This fixes the device mapping of the mv88e6xxx driver where the port pointing to the switch itself and to non-existent switches was wrongly configured to be 0. It is now set to the expected 0xf value. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 20b3087ad193..52ab18bc2b0d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -32,6 +32,8 @@ enum dsa_tag_protocol { #define DSA_MAX_SWITCHES 4 #define DSA_MAX_PORTS 12 +#define DSA_RTABLE_NONE -1 + struct dsa_chip_data { /* * How to access the switch configuration registers. -- cgit v1.2.3 From 606274c5abd8e245add01bc7145a8cbb92b69ba8 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 6 Jul 2016 22:38:36 -0700 Subject: bpf: introduce bpf_get_current_task() helper over time there were multiple requests to access different data structures and fields of task_struct current, so finally add the helper to access 'current' as-is. Tracing bpf programs will do the rest of walking the pointers via bpf_probe_read(). Note that current can be null and bpf program has to deal it with, but even dumb passing null into bpf_probe_read() is still safe. Suggested-by: Brendan Gregg Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c14ca1cd6297..262a7e883b19 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -357,6 +357,13 @@ enum bpf_func_id { */ BPF_FUNC_get_hash_recalc, + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From cd9b518b98d3e989f523e63b2ffda78467a3679e Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 27 Jun 2016 00:03:03 +0200 Subject: rtc: v3020: move rtc-v3020.h to platform_data rtc-v3020.h belongs to include/linux/platform_data/ Acked-by: Robert Jarzmik Signed-off-by: Alexandre Belloni --- include/linux/platform_data/rtc-v3020.h | 41 +++++++++++++++++++++++++++++++++ include/linux/rtc-v3020.h | 41 --------------------------------- 2 files changed, 41 insertions(+), 41 deletions(-) create mode 100644 include/linux/platform_data/rtc-v3020.h delete mode 100644 include/linux/rtc-v3020.h (limited to 'include') diff --git a/include/linux/platform_data/rtc-v3020.h b/include/linux/platform_data/rtc-v3020.h new file mode 100644 index 000000000000..e55d82cebf80 --- /dev/null +++ b/include/linux/platform_data/rtc-v3020.h @@ -0,0 +1,41 @@ +/* + * v3020.h - Registers definition and platform data structure for the v3020 RTC. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2006, 8D Technologies inc. + */ +#ifndef __LINUX_V3020_H +#define __LINUX_V3020_H + +/* The v3020 has only one data pin but which one + * is used depends on the board. */ +struct v3020_platform_data { + int leftshift; /* (1<<(leftshift)) & readl() */ + + unsigned int use_gpio:1; + unsigned int gpio_cs; + unsigned int gpio_wr; + unsigned int gpio_rd; + unsigned int gpio_io; +}; + +#define V3020_STATUS_0 0x00 +#define V3020_STATUS_1 0x01 +#define V3020_SECONDS 0x02 +#define V3020_MINUTES 0x03 +#define V3020_HOURS 0x04 +#define V3020_MONTH_DAY 0x05 +#define V3020_MONTH 0x06 +#define V3020_YEAR 0x07 +#define V3020_WEEK_DAY 0x08 +#define V3020_WEEK 0x09 + +#define V3020_IS_COMMAND(val) ((val)>=0x0E) + +#define V3020_CMD_RAM2CLOCK 0x0E +#define V3020_CMD_CLOCK2RAM 0x0F + +#endif /* __LINUX_V3020_H */ diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h deleted file mode 100644 index e55d82cebf80..000000000000 --- a/include/linux/rtc-v3020.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * v3020.h - Registers definition and platform data structure for the v3020 RTC. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006, 8D Technologies inc. - */ -#ifndef __LINUX_V3020_H -#define __LINUX_V3020_H - -/* The v3020 has only one data pin but which one - * is used depends on the board. */ -struct v3020_platform_data { - int leftshift; /* (1<<(leftshift)) & readl() */ - - unsigned int use_gpio:1; - unsigned int gpio_cs; - unsigned int gpio_wr; - unsigned int gpio_rd; - unsigned int gpio_io; -}; - -#define V3020_STATUS_0 0x00 -#define V3020_STATUS_1 0x01 -#define V3020_SECONDS 0x02 -#define V3020_MINUTES 0x03 -#define V3020_HOURS 0x04 -#define V3020_MONTH_DAY 0x05 -#define V3020_MONTH 0x06 -#define V3020_YEAR 0x07 -#define V3020_WEEK_DAY 0x08 -#define V3020_WEEK 0x09 - -#define V3020_IS_COMMAND(val) ((val)>=0x0E) - -#define V3020_CMD_RAM2CLOCK 0x0E -#define V3020_CMD_CLOCK2RAM 0x0F - -#endif /* __LINUX_V3020_H */ -- cgit v1.2.3 From a4d020e97d8e65d57061677c15c89e99609d0b37 Mon Sep 17 00:00:00 2001 From: Jonathan McDowell Date: Fri, 20 May 2016 12:08:35 -0300 Subject: [media] Convert Wideview WT220 DVB USB driver to rc-core Converts the dtt200u DVB USB driver over to the rc-core infrastructure for its handling of IR remotes. This device can receive generic NEC / NEC Extended signals and the switch to the newer core enables the easy use of tools such as ir-keytable to modify the active key map. Signed-off-by: Jonathan McDowell Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 6e6557dbeb9f..a459129dd554 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -136,6 +136,7 @@ void rc_map_init(void); #define RC_MAP_DM1105_NEC "rc-dm1105-nec" #define RC_MAP_DNTV_LIVE_DVBT_PRO "rc-dntv-live-dvbt-pro" #define RC_MAP_DNTV_LIVE_DVB_T "rc-dntv-live-dvb-t" +#define RC_MAP_DTT200U "rc-dtt200u" #define RC_MAP_DVBSKY "rc-dvbsky" #define RC_MAP_EMPTY "rc-empty" #define RC_MAP_EM_TERRATEC "rc-em-terratec" -- cgit v1.2.3 From ca8bee5dde1f02c2dbe8c8453dce27f2dfafb21c Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Tue, 5 Jul 2016 14:30:14 +0200 Subject: Bluetooth: Rename HCI_BREDR into HCI_PRIMARY The HCI_BREDR naming is confusing since it actually stands for Primary Bluetooth Controller. Which is a term that has been used in the latest standard. However from a legacy point of view there only really have been Basic Rate (BR) and Enhanced Data Rate (EDR). Recent versions of Bluetooth introduced Low Energy (LE) and made this terminology a little bit confused since Dual Mode Controllers include BR/EDR and LE. To simplify this the name HCI_PRIMARY stands for the Primary Controller which can be a single mode or dual mode controller. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index eefcf3e96421..a3f86de6f100 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -65,7 +65,7 @@ #define HCI_I2C 8 /* HCI controller types */ -#define HCI_BREDR 0x00 +#define HCI_PRIMARY 0x00 #define HCI_AMP 0x01 /* First BR/EDR Controller shall have ID = 0 */ -- cgit v1.2.3 From a65056ecf4b48be0d0284a7b6a57b6dace10b843 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 6 Jul 2016 12:12:21 -0700 Subject: net: bridge: extend MLD/IGMP query stats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As was suggested this patch adds support for the different versions of MLD and IGMP query types. Since the user visible structure is still in net-next we can augment it instead of adding netlink attributes. The distinction between the different IGMP/MLD query types is done as suggested in Section 7.1, RFC 3376 [1] and Section 8.1, RFC 3810 [2] based on query payload size and code for IGMP. Since all IGMP packets go through multicast_rcv() and it uses ip_mc_check_igmp/ipv6_mc_check_mld we can be sure that at least the ip/ipv6 header can be directly used. [1] https://tools.ietf.org/html/rfc3376#section-7 [2] https://tools.ietf.org/html/rfc3810#section-8.1 Suggested-by: Linus Lüssing Signed-off-by: Nikolay Aleksandrov Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 8304fe6f0561..c186f64fffca 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -261,14 +261,17 @@ enum { /* IGMP/MLD statistics */ struct br_mcast_stats { - __u64 igmp_queries[BR_MCAST_DIR_SIZE]; + __u64 igmp_v1queries[BR_MCAST_DIR_SIZE]; + __u64 igmp_v2queries[BR_MCAST_DIR_SIZE]; + __u64 igmp_v3queries[BR_MCAST_DIR_SIZE]; __u64 igmp_leaves[BR_MCAST_DIR_SIZE]; __u64 igmp_v1reports[BR_MCAST_DIR_SIZE]; __u64 igmp_v2reports[BR_MCAST_DIR_SIZE]; __u64 igmp_v3reports[BR_MCAST_DIR_SIZE]; __u64 igmp_parse_errors; - __u64 mld_queries[BR_MCAST_DIR_SIZE]; + __u64 mld_v1queries[BR_MCAST_DIR_SIZE]; + __u64 mld_v2queries[BR_MCAST_DIR_SIZE]; __u64 mld_leaves[BR_MCAST_DIR_SIZE]; __u64 mld_v1reports[BR_MCAST_DIR_SIZE]; __u64 mld_v2reports[BR_MCAST_DIR_SIZE]; -- cgit v1.2.3 From 1db19db7f5ff4ddd3b1b6dd2092a87298ee5bd0b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 7 Jul 2016 18:01:32 +0200 Subject: net: tracepoint napi:napi_poll add work and budget An important information for the napi_poll tracepoint is knowing the work done (packets processed) by the napi_poll() call. Add both the work done and budget, as they are related. Handle trace_napi_poll() param change in dropwatch/drop_monitor and in python perf script netdev-times.py in backward compat way, as python fortunately supports optional parameter handling. Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/trace/events/napi.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 8fe1e93f531d..118ed7767639 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -12,22 +12,27 @@ TRACE_EVENT(napi_poll, - TP_PROTO(struct napi_struct *napi), + TP_PROTO(struct napi_struct *napi, int work, int budget), - TP_ARGS(napi), + TP_ARGS(napi, work, budget), TP_STRUCT__entry( __field( struct napi_struct *, napi) + __field( int, work) + __field( int, budget) __string( dev_name, napi->dev ? napi->dev->name : NO_DEV) ), TP_fast_assign( __entry->napi = napi; + __entry->work = work; + __entry->budget = budget; __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); ), - TP_printk("napi poll on napi struct %p for device %s", - __entry->napi, __get_str(dev_name)) + TP_printk("napi poll on napi struct %p for device %s work %d budget %d", + __entry->napi, __get_str(dev_name), + __entry->work, __entry->budget) ); #undef NO_DEV -- 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 --- include/linux/context_tracking.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') 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 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 --- include/linux/nmi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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; -- cgit v1.2.3 From 1d984c2e03c1fb21539a9f50627e312788512013 Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Fri, 8 Jul 2016 15:52:39 +0200 Subject: NFC: digital: Fix handling of saved PDU sk_buff pointers This patch fixes the way an I-PDU is saved in case it needs to be sent again. It is now copied using pskb_copy() and not simply referenced using skb_get() since it could be modified by the driver. digital_in_send_saved_skb() and digital_tg_send_saved_skb() still get a reference on the saved skb which is re-sent but release it if the send operation fails. That way the caller doesn't have to take care about skb ref in case of error. RTOX supervisor PDU must not be saved as this can override a previously saved I-PDU that should be re-sent later on. Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/net/nfc/digital.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index 506e3f6eabef..f9a4e4771861 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -237,7 +237,6 @@ struct nfc_digital_dev { int nack_count; struct sk_buff *saved_skb; - unsigned int saved_skb_len; u16 target_fsc; -- cgit v1.2.3 From 1a09c56f545c8ff8d338a38c7c40d79f4165a94c Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Fri, 8 Jul 2016 15:52:45 +0200 Subject: NFC: digital: Add support for NFC DEP Response Waiting Time When sending an ATR_REQ, the initiator must wait for the ATR_RES at least 'RWT(nfcdep,activation) + dRWT(nfcdep)' and no more than 'RWT(nfcdep,activation) + dRWT(nfcdep) + dT(nfcdep,initiator)'. This gives a timeout value between 1237 ms and 1337 ms. This patch defines DIGITAL_ATR_RES_RWT to 1337 used for the timeout value of ATR_REQ command. For other DEP PDUs, the initiator must wait between 'RWT + dRWT(nfcdep)' and 'RWT + dRWT(nfcdep) + dT(nfcdep,initiator)' where RWT is given by the following formula: '(256 * 16 / f(c)) * 2^wt' where wt is the value of the TO field in the ATR_RES response and is in the range between 0 and 14. This patch declares a mapping table for wt values and gives RWT max values between 100 ms and 5049 ms. This patch also defines DIGITAL_ATR_RES_TO_WT, the maximum wt value in target mode, to 8. Signed-off-by: Thierry Escande Signed-off-by: Samuel Ortiz --- include/net/nfc/digital.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h index f9a4e4771861..74fa7eb94e72 100644 --- a/include/net/nfc/digital.h +++ b/include/net/nfc/digital.h @@ -226,6 +226,7 @@ struct nfc_digital_dev { u8 curr_rf_tech; u8 curr_nfc_dep_pni; u8 did; + u16 dep_rwt; u8 local_payload_max; u8 remote_payload_max; -- cgit v1.2.3 From 64b87639c9cbeb03e26bc65528416c961b1dde96 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sun, 3 Jul 2016 13:18:43 +0800 Subject: netfilter: conntrack: fix race between nf_conntrack proc read and hash resize MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we do "cat /proc/net/nf_conntrack", and meanwhile resize the conntrack hash table via /sys/module/nf_conntrack/parameters/hashsize, race will happen, because reader can observe a newly allocated hash but the old size (or vice versa). So oops will happen like follows： BUG: unable to handle kernel NULL pointer dereference at 0000000000000017 IP: [] seq_print_acct+0x11/0x50 [nf_conntrack] Call Trace: [] ? ct_seq_show+0x14e/0x340 [nf_conntrack] [] seq_read+0x2cc/0x390 [] proc_reg_read+0x42/0x70 [] __vfs_read+0x37/0x130 [] ? security_file_permission+0xa0/0xc0 [] vfs_read+0x95/0x140 [] SyS_read+0x55/0xc0 [] entry_SYSCALL_64_fastpath+0x1a/0xa4 It is very easy to reproduce this kernel crash. 1. open one shell and input the following cmds: while : ; do echo $RANDOM > /sys/module/nf_conntrack/parameters/hashsize done 2. open more shells and input the following cmds: while : ; do cat /proc/net/nf_conntrack done 3. just wait a monent, oops will happen soon. The solution in this patch is based on Florian's Commit 5e3c61f98175 ("netfilter: conntrack: fix lookup race during hash resize"). And add a wrapper function nf_conntrack_get_ht to get hash and hsize suggested by Florian Westphal. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 3e2f3328945c..79d7ac5c9740 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -51,6 +51,8 @@ bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); +void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize); + /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, -- cgit v1.2.3 From 242922a027176cd260c5adce4ba6bbfa3a05190c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 3 Jul 2016 20:44:01 +0200 Subject: netfilter: conntrack: simplify early_drop We don't need to acquire the bucket lock during early drop, we can use lockless traveral just like ____nf_conntrack_find. The timer deletion serves as synchronization point, if another cpu attempts to evict same entry, only one will succeed with timer deletion. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5d3397f34583..2a5133e214c9 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -301,6 +301,7 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl); #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) +#define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) #define MODULE_ALIAS_NFCT_HELPER(helper) \ MODULE_ALIAS("nfct-helper-" helper) -- cgit v1.2.3 From 7c9664351980aaa6a4b8837a314360b3a4ad382a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 5 Jul 2016 12:07:23 +0200 Subject: netfilter: move nat hlist_head to nf_conn The nat extension structure is 32bytes in size on x86_64: struct nf_conn_nat { struct hlist_node bysource; /* 0 16 */ struct nf_conn * ct; /* 16 8 */ union nf_conntrack_nat_help help; /* 24 4 */ int masq_index; /* 28 4 */ /* size: 32, cachelines: 1, members: 4 */ /* last cacheline: 32 bytes */ }; The hlist is needed to quickly check for possible tuple collisions when installing a new nat binding. Storing this in the extension area has two drawbacks: 1. We need ct backpointer to get the conntrack struct from the extension. 2. When reallocation of extension area occurs we need to fixup the bysource hash head via hlist_replace_rcu. We can avoid both by placing the hlist_head in nf_conn and place nf_conn in the bysource hash rather than the extenstion. We can also remove the ->move support; no other extension needs it. Moving the entire nat extension into nf_conn would be possible as well but then we have to add yet another callback for deletion from the bysource hash table rather than just using nat extension ->destroy hook for this. nf_conn size doesn't increase due to aligment, followup patch replaces hlist_node with single pointer. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 +++ include/net/netfilter/nf_conntrack_extend.h | 3 --- include/net/netfilter/nf_nat.h | 2 -- 3 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 2a5133e214c9..e5135d8728b4 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -117,6 +117,9 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; +#if IS_ENABLED(CONFIG_NF_NAT) + struct hlist_node nat_bysource; +#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index b925395fa5ed..1c3035dda31f 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -99,9 +99,6 @@ void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id, struct nf_ct_ext_type { /* Destroys relationships (can be NULL). */ void (*destroy)(struct nf_conn *ct); - /* Called when realloacted (can be NULL). - Contents has already been moved. */ - void (*move)(void *new, void *old); enum nf_ct_ext_id id; diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 344b1ab19220..02515f7ed4cc 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -29,8 +29,6 @@ struct nf_conn; /* The structure embedded in the conntrack structure. */ struct nf_conn_nat { - struct hlist_node bysource; - struct nf_conn *ct; union nf_conntrack_nat_help help; #if IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV4) || \ IS_ENABLED(CONFIG_NF_NAT_MASQUERADE_IPV6) -- cgit v1.2.3 From 870190a9ec9075205c0fa795a09fa931694a3ff1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 5 Jul 2016 12:07:24 +0200 Subject: netfilter: nat: convert nat bysrc hash to rhashtable It did use a fixed-size bucket list plus single lock to protect add/del. Unlike the main conntrack table we only need to add and remove keys. Convert it to rhashtable to get table autosizing and per-bucket locking. The maximum number of entries is -- as before -- tied to the number of conntracks so we do not need another upperlimit. The change does not handle rhashtable_remove_fast error, only possible "error" is -ENOENT, and that is something that can happen legitimetely, e.g. because nat module was inserted at a later time and no src manip took place yet. Tested with http-client-benchmark + httpterm with DNAT and SNAT rules in place. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 3 ++- include/net/netfilter/nf_nat.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e5135d8728b4..a08825b7e955 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -118,7 +119,7 @@ struct nf_conn { struct nf_ct_ext *ext; #if IS_ENABLED(CONFIG_NF_NAT) - struct hlist_node nat_bysource; + struct rhash_head nat_bysource; #endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 02515f7ed4cc..c327a431a6f3 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -1,5 +1,6 @@ #ifndef _NF_NAT_H #define _NF_NAT_H +#include #include #include #include -- cgit v1.2.3 From d51ed8367bcbbb06f4f4986d1ef7dc2480bed1ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 8 Jul 2016 13:08:50 +0200 Subject: netfilter: constify arg to is_dying/confirmed Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a08825b7e955..1e04911b78ea 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -270,12 +270,12 @@ static inline int nf_ct_is_template(const struct nf_conn *ct) } /* It's confirmed if it is, or has been in the hash table. */ -static inline int nf_ct_is_confirmed(struct nf_conn *ct) +static inline int nf_ct_is_confirmed(const struct nf_conn *ct) { return test_bit(IPS_CONFIRMED_BIT, &ct->status); } -static inline int nf_ct_is_dying(struct nf_conn *ct) +static inline int nf_ct_is_dying(const struct nf_conn *ct) { return test_bit(IPS_DYING_BIT, &ct->status); } -- cgit v1.2.3 From 42a55769132fdf4f44bac1471b371d7f80bcde35 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 8 Jul 2016 14:41:49 +0200 Subject: netfilter: nf_tables: get rid of possible_net_t from set and basechain We can pass the netns pointer as parameter to the functions that need to gain access to it. From basechains, I didn't find any client for this field anymore so let's remove this too. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 30c1d9489ae2..f2f13399ce44 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -236,7 +236,8 @@ struct nft_expr; * @features: features supported by the implementation */ struct nft_set_ops { - bool (*lookup)(const struct nft_set *set, + bool (*lookup)(const struct net *net, + const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, @@ -248,11 +249,14 @@ struct nft_set_ops { struct nft_regs *regs, const struct nft_set_ext **ext); - int (*insert)(const struct nft_set *set, + int (*insert)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); - void (*activate)(const struct nft_set *set, + void (*activate)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); - void * (*deactivate)(const struct nft_set *set, + void * (*deactivate)(const struct net *net, + const struct nft_set *set, const struct nft_set_elem *elem); void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); @@ -295,7 +299,6 @@ void nft_unregister_set(struct nft_set_ops *ops); * @udlen: user data length * @udata: user data * @ops: set ops - * @pnet: network namespace * @flags: set flags * @genmask: generation mask * @klen: key length @@ -318,7 +321,6 @@ struct nft_set { unsigned char *udata; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - possible_net_t pnet; u16 flags:14, genmask:2; u8 klen; @@ -804,7 +806,6 @@ struct nft_stats { * struct nft_base_chain - nf_tables base chain * * @ops: netfilter hook ops - * @pnet: net namespace that this chain belongs to * @type: chain type * @policy: default policy * @stats: per-cpu chain stats @@ -813,7 +814,6 @@ struct nft_stats { */ struct nft_base_chain { struct nf_hook_ops ops[NFT_HOOK_OPS_MAX]; - possible_net_t pnet; const struct nf_chain_type *type; u8 policy; u8 flags; @@ -1009,10 +1009,11 @@ static inline bool nft_set_elem_active(const struct nft_set_ext *ext, return !(ext->genmask & genmask); } -static inline void nft_set_elem_change_active(const struct nft_set *set, +static inline void nft_set_elem_change_active(const struct net *net, + const struct nft_set *set, struct nft_set_ext *ext) { - ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet)); + ext->genmask ^= nft_genmask_next(net); } /* -- cgit v1.2.3 From d55f09abe24b4dfadab246b6f217da547361cdb6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 11 Jul 2016 09:45:32 -0300 Subject: [media] lirc.h: remove several unused ioctls While reviewing the documentation gaps on LIRC, it was noticed that several ioctls aren't used by any LIRC drivers (nor at staging or mainstream). It doesn't make sense to document them, as they're not used anywhere. So, let's remove those from the lirc header. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/lirc.h | 39 ++------------------------------------- 1 file changed, 2 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/lirc.h b/include/uapi/linux/lirc.h index 4b3ab2966b5a..991ab4570b8e 100644 --- a/include/uapi/linux/lirc.h +++ b/include/uapi/linux/lirc.h @@ -90,20 +90,11 @@ #define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) #define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) -#define LIRC_GET_SEND_CARRIER _IOR('i', 0x00000003, __u32) -#define LIRC_GET_REC_CARRIER _IOR('i', 0x00000004, __u32) -#define LIRC_GET_SEND_DUTY_CYCLE _IOR('i', 0x00000005, __u32) -#define LIRC_GET_REC_DUTY_CYCLE _IOR('i', 0x00000006, __u32) #define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) #define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) #define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) -#define LIRC_GET_MIN_FILTER_PULSE _IOR('i', 0x0000000a, __u32) -#define LIRC_GET_MAX_FILTER_PULSE _IOR('i', 0x0000000b, __u32) -#define LIRC_GET_MIN_FILTER_SPACE _IOR('i', 0x0000000c, __u32) -#define LIRC_GET_MAX_FILTER_SPACE _IOR('i', 0x0000000d, __u32) - /* code length in bits, currently only for LIRC_MODE_LIRCCODE */ #define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) @@ -113,7 +104,6 @@ #define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) #define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) #define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) -#define LIRC_SET_REC_DUTY_CYCLE _IOW('i', 0x00000016, __u32) #define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) /* @@ -126,22 +116,6 @@ /* 1 enables, 0 disables timeout reports in MODE2 */ #define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) -/* - * pulses shorter than this are filtered out by hardware (software - * emulation in lirc_dev?) - */ -#define LIRC_SET_REC_FILTER_PULSE _IOW('i', 0x0000001a, __u32) -/* - * spaces shorter than this are filtered out by hardware (software - * emulation in lirc_dev?) - */ -#define LIRC_SET_REC_FILTER_SPACE _IOW('i', 0x0000001b, __u32) -/* - * if filter cannot be set independently for pulse/space, this should - * be used - */ -#define LIRC_SET_REC_FILTER _IOW('i', 0x0000001c, __u32) - /* * if enabled from the next key press on the driver will send * LIRC_MODE2_FREQUENCY packets @@ -149,20 +123,11 @@ #define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) /* - * to set a range use - * LIRC_SET_REC_DUTY_CYCLE_RANGE/LIRC_SET_REC_CARRIER_RANGE with the - * lower bound first and later - * LIRC_SET_REC_DUTY_CYCLE/LIRC_SET_REC_CARRIER with the upper bound + * to set a range use LIRC_SET_REC_CARRIER_RANGE with the + * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound */ - -#define LIRC_SET_REC_DUTY_CYCLE_RANGE _IOW('i', 0x0000001e, __u32) #define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) -#define LIRC_NOTIFY_DECODE _IO('i', 0x00000020) - -#define LIRC_SETUP_START _IO('i', 0x00000021) -#define LIRC_SETUP_END _IO('i', 0x00000022) - #define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) #endif -- cgit v1.2.3 From fce7b5ae1273a27db341d5dfd51a8ca6ef4caa95 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 21 Jun 2016 16:16:18 +0100 Subject: bus: mvebu-mbus: fix __iomem on register pointers The save_cpu_target functions should take "u32 __iomem *", not a plain "u32 *" as it is passed to register access functions. Fix the following warnings by adding the annotation: drivers/bus/mvebu-mbus.c:739:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:739:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:739:17: got unsigned int [usertype] * drivers/bus/mvebu-mbus.c:741:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:741:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:741:17: got unsigned int [usertype] * drivers/bus/mvebu-mbus.c:742:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:742:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:742:17: got unsigned int [usertype] * drivers/bus/mvebu-mbus.c:744:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:744:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:744:17: got unsigned int [usertype] * drivers/bus/mvebu-mbus.c:790:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:790:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:790:17: got unsigned int [usertype] * drivers/bus/mvebu-mbus.c:792:17: warning: incorrect type in argument 2 (different address spaces) drivers/bus/mvebu-mbus.c:792:17: expected void volatile [noderef] *addr drivers/bus/mvebu-mbus.c:792:17: got unsigned int [usertype] * Signed-off-by: Ben Dooks Acked-by: Arnd Bergmann Signed-off-by: Gregory CLEMENT --- include/linux/mbus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mbus.h b/include/linux/mbus.h index ea34a867caa0..d610232762e3 100644 --- a/include/linux/mbus.h +++ b/include/linux/mbus.h @@ -66,7 +66,7 @@ static inline const struct mbus_dram_target_info *mv_mbus_dram_info_nooverlap(vo } #endif -int mvebu_mbus_save_cpu_target(u32 *store_addr); +int mvebu_mbus_save_cpu_target(u32 __iomem *store_addr); void mvebu_mbus_get_pcie_mem_aperture(struct resource *res); void mvebu_mbus_get_pcie_io_aperture(struct resource *res); int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr); -- cgit v1.2.3 From 65b80179f9b8171b74625febf3457f41e792fa23 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:55:06 -0400 Subject: xprtrdma: No direct data placement with krb5i and krb5p Direct data placement is not allowed when using flavors that guarantee integrity or privacy. When such security flavors are in effect, don't allow the use of Read and Write chunks for moving individual data items. All messages larger than the inline threshold are sent via Long Call or Long Reply. On my systems (CX-3 Pro on FDR), for small I/O operations, the use of Long messages adds only around 5 usecs of latency in each direction. Note that when integrity or encryption is used, the host CPU touches every byte in these messages. Even if it could be used, data movement offload doesn't buy much in this case. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- include/linux/sunrpc/auth.h | 3 +++ include/linux/sunrpc/gss_api.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 899791573a40..3a40287b4d27 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -107,6 +107,9 @@ struct rpc_auth { /* per-flavor data */ }; +/* rpc_auth au_flags */ +#define RPCAUTH_AUTH_DATATOUCH 0x00000002 + struct rpc_auth_create_args { rpc_authflavor_t pseudoflavor; const char *target_name; diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 1f911ccb2a75..68ec78c1aa48 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -73,6 +73,7 @@ u32 gss_delete_sec_context( rpc_authflavor_t gss_svc_to_pseudoflavor(struct gss_api_mech *, u32 qop, u32 service); u32 gss_pseudoflavor_to_service(struct gss_api_mech *, u32 pseudoflavor); +bool gss_pseudoflavor_to_datatouch(struct gss_api_mech *, u32 pseudoflavor); char *gss_service_to_auth_domain_name(struct gss_api_mech *, u32 service); struct pf_desc { @@ -81,6 +82,7 @@ struct pf_desc { u32 service; char *name; char *auth_domain_name; + bool datatouch; }; /* Different mechanisms (e.g., krb5 or spkm3) may implement gss-api, and -- cgit v1.2.3 From 28aa4c26fce2202db8d42ae76b639ca1d9a23d25 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 9 Jul 2016 19:47:40 +0800 Subject: sctp: add SCTP_PR_SUPPORTED on sctp sockopt According to section 4.5 of rfc7496, prsctp_enable should be per asoc. We will add prsctp_enable to both asoc and ep, and replace the places where it used net.sctp->prsctp_enable with asoc->prsctp_enable. ep->prsctp_enable will be initialized with net.sctp->prsctp_enable, and asoc->prsctp_enable will be initialized with ep->prsctp_enable. We can also modify it's value through sockopt SCTP_PR_SUPPORTED. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 6 ++++-- include/uapi/linux/sctp.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 83c5ec58b93a..07115ca9de4d 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1256,7 +1256,8 @@ struct sctp_endpoint { /* SCTP-AUTH: endpoint shared keys */ struct list_head endpoint_shared_keys; __u16 active_key_id; - __u8 auth_enable; + __u8 auth_enable:1, + prsctp_enable:1; }; /* Recover the outter endpoint structure. */ @@ -1848,7 +1849,8 @@ struct sctp_association { __u16 active_key_id; __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ - temp:1; /* Is it a temporary association? */ + temp:1, /* Is it a temporary association? */ + prsctp_enable:1; struct sctp_priv_assoc_stats stats; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index ce70fe6b45df..aa08906f292d 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -112,6 +112,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ #define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ #define SCTP_GET_ASSOC_STATS 112 /* Read only */ +#define SCTP_PR_SUPPORTED 113 /* These are bit fields for msghdr->msg_flags. See section 5.1. */ /* On user space Linux, these live in as an enum. */ -- cgit v1.2.3 From f959fb442c35f4b61fea341401b8463dd0a1b959 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 9 Jul 2016 19:47:41 +0800 Subject: sctp: add SCTP_DEFAULT_PRINFO into sctp sockopt This patch adds SCTP_DEFAULT_PRINFO to sctp sockopt. It is used to set/get sctp Partially Reliable Policies' default params, which includes 3 policies (ttl, rtx, prio) and their values. Still, if we set policy params in sndinfo, we will use the params of sndinfo against chunks, instead of the default params. In this patch, we will use 5-8bit of sp/asoc->default_flags to store prsctp policies, and reuse asoc->default_timetolive to store their values. It means if we enable and set prsctp policy, prior ttl timeout in sctp will not work any more. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index aa08906f292d..984cf2e9a61d 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -113,6 +113,29 @@ typedef __s32 sctp_assoc_t; #define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ #define SCTP_GET_ASSOC_STATS 112 /* Read only */ #define SCTP_PR_SUPPORTED 113 +#define SCTP_DEFAULT_PRINFO 114 + +/* PR-SCTP policies */ +#define SCTP_PR_SCTP_NONE 0x0000 +#define SCTP_PR_SCTP_TTL 0x0010 +#define SCTP_PR_SCTP_RTX 0x0020 +#define SCTP_PR_SCTP_PRIO 0x0030 +#define SCTP_PR_SCTP_MAX SCTP_PR_SCTP_PRIO +#define SCTP_PR_SCTP_MASK 0x0030 + +#define __SCTP_PR_INDEX(x) ((x >> 4) - 1) +#define SCTP_PR_INDEX(x) __SCTP_PR_INDEX(SCTP_PR_SCTP_ ## x) + +#define SCTP_PR_POLICY(x) ((x) & SCTP_PR_SCTP_MASK) +#define SCTP_PR_SET_POLICY(flags, x) \ + do { \ + flags &= ~SCTP_PR_SCTP_MASK; \ + flags |= x; \ + } while (0) + +#define SCTP_PR_TTL_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_TTL) +#define SCTP_PR_RTX_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_RTX) +#define SCTP_PR_PRIO_ENABLED(x) (SCTP_PR_POLICY(x) == SCTP_PR_SCTP_PRIO) /* These are bit fields for msghdr->msg_flags. See section 5.1. */ /* On user space Linux, these live in as an enum. */ @@ -903,4 +926,10 @@ struct sctp_paddrthlds { __u16 spt_pathpfthld; }; +struct sctp_default_prinfo { + sctp_assoc_t pr_assoc_id; + __u32 pr_value; + __u16 pr_policy; +}; + #endif /* _UAPI_SCTP_H */ -- cgit v1.2.3 From 826d253d57b11f69add81c8086d2e7f1dce5ec77 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 9 Jul 2016 19:47:42 +0800 Subject: sctp: add SCTP_PR_ASSOC_STATUS on sctp sockopt This patch adds SCTP_PR_ASSOC_STATUS to sctp sockopt, which is used to dump the prsctp statistics info from the asoc. The prsctp statistics includes abandoned_sent/unsent from the asoc. abandoned_sent is the count of the packets we drop packets from retransmit/transmited queue, and abandoned_unsent is the count of the packets we drop from out_queue according to the policy. Note: another option for prsctp statistics dump described in rfc is SCTP_PR_STREAM_STATUS, which is used to dump the prsctp statistics info from each stream. But by now, linux doesn't yet have per stream statistics info, it needs rfc6525 to be implemented. As the prsctp statistics for each stream has to be based on per stream statistics, we will delay it until rfc6525 is done in linux. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +++ include/uapi/linux/sctp.h | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 07115ca9de4d..d8e464aacb20 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1853,6 +1853,9 @@ struct sctp_association { prsctp_enable:1; struct sctp_priv_assoc_stats stats; + + __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; + __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; }; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 984cf2e9a61d..d304f4c9792c 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -114,6 +114,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_GET_ASSOC_STATS 112 /* Read only */ #define SCTP_PR_SUPPORTED 113 #define SCTP_DEFAULT_PRINFO 114 +#define SCTP_PR_ASSOC_STATUS 115 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -926,6 +927,17 @@ struct sctp_paddrthlds { __u16 spt_pathpfthld; }; +/* + * Socket Option for Getting the Association/Stream-Specific PR-SCTP Status + */ +struct sctp_prstatus { + sctp_assoc_t sprstat_assoc_id; + __u16 sprstat_sid; + __u16 sprstat_policy; + __u64 sprstat_abandoned_unsent; + __u64 sprstat_abandoned_sent; +}; + struct sctp_default_prinfo { sctp_assoc_t pr_assoc_id; __u32 pr_value; -- cgit v1.2.3 From a6c2f792873aff332a4689717c3cd6104f46684c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 9 Jul 2016 19:47:43 +0800 Subject: sctp: implement prsctp TTL policy prsctp TTL policy is a policy to abandon chunks when they expire at the specific time in local stack. It's similar with expires_at in struct sctp_datamsg. This patch uses sinfo->sinfo_timetolive to set the specific time for TTL policy. sinfo->sinfo_timetolive is also used for msg->expires_at. So if prsctp_enable or TTL policy is not enabled, msg->expires_at still works as before. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d8e464aacb20..6bcda715008e 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -602,6 +602,16 @@ struct sctp_chunk { /* This needs to be recoverable for SCTP_SEND_FAILED events. */ struct sctp_sndrcvinfo sinfo; + /* We use this field to record param for prsctp policies, + * for TTL policy, it is the time_to_drop of this chunk, + * for RTX policy, it is the max_sent_count of this chunk, + * for PRIO policy, it is the priority of this chunk. + */ + unsigned long prsctp_param; + + /* How many times this chunk have been sent, for prsctp RTX policy */ + int sent_count; + /* Which association does this belong to? */ struct sctp_association *asoc; -- cgit v1.2.3 From 8dbdf1f5b09cb22560e7c7173b52fe3c631046bd Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 9 Jul 2016 19:47:45 +0800 Subject: sctp: implement prsctp PRIO policy prsctp PRIO policy is a policy to abandon lower priority chunks when asoc doesn't have enough snd buffer, so that the current chunk with higher priority can be queued successfully. Similar to TTL/RTX policy, we will set the priority of the chunk to prsctp_param with sinfo->sinfo_timetolive in sctp_set_prsctp_policy(). So if PRIO policy is enabled, msg->expire_at won't work. asoc->sent_cnt_removable will record how many chunks can be checked to remove. If priority policy is enabled, when the chunk is queued into the out_queue, we will increase sent_cnt_removable. When the chunk is moved to abandon_queue or dequeue and free, we will decrease sent_cnt_removable. In sctp_sendmsg, we will check if there is enough snd buffer for current msg and if sent_cnt_removable is not 0. Then try to abandon chunks in sctp_prune_prsctp when sendmsg from the retransmit/transmited queue, and free chunks from out_queue in right order until the abandon+free size > msg_len - sctp_wfree. For the abandon size, we have to wait until it sends FORWARD TSN, receives the sack and the chunks are really freed. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6bcda715008e..8626bdd3249a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1084,6 +1084,8 @@ void sctp_retransmit(struct sctp_outq *, struct sctp_transport *, sctp_retransmit_reason_t); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); int sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); +void sctp_prsctp_prune(struct sctp_association *asoc, + struct sctp_sndrcvinfo *sinfo, int msg_len); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { @@ -1864,6 +1866,8 @@ struct sctp_association { struct sctp_priv_assoc_stats stats; + int sent_cnt_removable; + __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; }; -- cgit v1.2.3 From a8a6d2e04c4ffda055db70814c50bd106e44730f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 7 Jun 2016 16:38:04 -0700 Subject: libnvdimm, nfit: remove nfit_spa_map() infrastructure Now that all shared mappings are handled by devm_nvdimm_memremap() we no longer need nfit_spa_map() nor do we need to trigger a callback to the bus provider at region disable time. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 18c3cc48a970..1050f9aa3a3e 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -114,7 +114,6 @@ struct device; struct nd_blk_region; struct nd_blk_region_desc { int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - void (*disable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, void *iobuf, u64 len, int rw); struct nd_region_desc ndr_desc; -- cgit v1.2.3 From e5ae3b252c6732f838f5695170bbf2ea9fb5b9ff Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 7 Jun 2016 17:00:04 -0700 Subject: libnvdimm, nfit: move flush hint mapping to region-device driver-data In preparation for triggering flushes of a DIMM's writes-posted-queue (WPQ) via the pmem driver move mapping of flush hint addresses to the region driver. Since this uses devm_nvdimm_memremap() the flush addresses will remain mapped while any region to which the dimm belongs is active. We need to communicate more information to the nvdimm core to facilitate this mapping, namely each dimm object now carries an array of flush hint address resources. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 1050f9aa3a3e..815b9b430ead 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -52,6 +52,7 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct nd_namespace_label; struct nvdimm_drvdata; + struct nd_mapping { struct nvdimm *nvdimm; struct nd_namespace_label **labels; @@ -142,7 +143,8 @@ unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm); void *nvdimm_provider_data(struct nvdimm *nvdimm); struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, const struct attribute_group **groups, unsigned long flags, - unsigned long cmd_mask); + unsigned long cmd_mask, int num_flush, + struct resource *flush_wpq); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, -- cgit v1.2.3 From f284a4f23752d0334e482d04e0a584d19c9c8cd0 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 7 Jul 2016 19:44:50 -0700 Subject: libnvdimm: introduce nvdimm_flush() and nvdimm_has_flush() nvdimm_flush() is a replacement for the x86 'pcommit' instruction. It is an optional write flushing mechanism that an nvdimm bus can provide for the pmem driver to consume. In the case of the NFIT nvdimm-bus-provider nvdimm_flush() is implemented as a series of flush-hint-address [1] writes to each dimm in the interleave set (region) that backs the namespace. The nvdimm_has_flush() routine relies on platform firmware to describe the flushing capabilities of a platform. It uses the heuristic of whether an nvdimm bus provider provides flush address data to return a ternary result: 1: flush addresses defined 0: dimm topology described without flush addresses (assume ADR) -errno: no topology information, unable to determine flush mechanism The pmem driver is expected to take the following actions on this ternary result: 1: nvdimm_flush() in response to REQ_FUA / REQ_FLUSH and shutdown 0: do not set, WC or FUA on the queue, take no further action -errno: warn and then operate as if nvdimm_has_flush() returned '0' The caveat of this heuristic is that it can not distinguish the "dimm does not have flush address" case from the "platform firmware is broken and failed to describe a flush address". Given we are already explicitly trusting the NFIT there's not much more we can do beyond blacklisting broken firmwares if they are ever encountered. Cc: Ross Zwisler Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 815b9b430ead..d37fda6dd64c 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -166,4 +166,6 @@ struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); +void nvdimm_flush(struct nd_region *nd_region); +int nvdimm_has_flush(struct nd_region *nd_region); #endif /* __LIBNVDIMM_H__ */ -- cgit v1.2.3 From 4e657946cbf68998b51b331375a1209e90792fe4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 18 Mar 2016 16:53:31 +0100 Subject: mfd: db8500 stop passing around platform data Except for the constant DB8500_PRCMU_FW_VERSION_OFFSET number, nothing is ever passed through the platform data and used in a driver, so we can simply stop passing it around. Acked-by: Lee Jones Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/mfd/abx500/ab8500-sysctrl.h | 6 ------ include/linux/mfd/dbx500-prcmu.h | 10 ---------- 2 files changed, 16 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/abx500/ab8500-sysctrl.h b/include/linux/mfd/abx500/ab8500-sysctrl.h index 689312745b2f..01024d1aed0e 100644 --- a/include/linux/mfd/abx500/ab8500-sysctrl.h +++ b/include/linux/mfd/abx500/ab8500-sysctrl.h @@ -37,12 +37,6 @@ static inline int ab8500_sysctrl_clear(u16 reg, u8 bits) return ab8500_sysctrl_write(reg, bits, 0); } -/* Configuration data for SysClkReq1RfClkBuf - SysClkReq8RfClkBuf */ -struct ab8500_sysctrl_platform_data { - u8 initial_req_buf_config[8]; - u16 (*reboot_reason_code)(const char *cmd); -}; - /* Registers */ #define AB8500_TURNONSTATUS 0x100 #define AB8500_RESETSTATUS 0x101 diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index bf5109d38a26..5d374601404c 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -178,16 +178,6 @@ enum ddr_pwrst { #define DB8500_PRCMU_LEGACY_OFFSET 0xDD4 -struct prcmu_pdata -{ - bool enable_set_ddr_opp; - bool enable_ape_opp_100_voltage; - struct ab8500_platform_data *ab_platdata; - u32 version_offset; - u32 legacy_offset; - u32 adt_offset; -}; - #define PRCMU_FW_PROJECT_U8500 2 #define PRCMU_FW_PROJECT_U8400 3 #define PRCMU_FW_PROJECT_U9500 4 /* Customer specific */ -- cgit v1.2.3 From 269f1aac1410d27959bd073a089eb85eed55c8a1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Jun 2016 22:47:53 +0200 Subject: ARM: ux500: use CLK_OF_DECLARE() The ux500 DT support predates the CLK_OF_DECLARE macro and calls directly into the clk driver from platform code. Converting this to CLK_OF_DECLARE makes the code much nicer and similar to how modern platforms do it today. It also removes the last user of cpu_is_u8500_family() etc. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/platform_data/clk-ux500.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/platform_data/clk-ux500.h (limited to 'include') diff --git a/include/linux/platform_data/clk-ux500.h b/include/linux/platform_data/clk-ux500.h deleted file mode 100644 index 3af0da1f3be5..000000000000 --- a/include/linux/platform_data/clk-ux500.h +++ /dev/null @@ -1,17 +0,0 @@ -/* - * Clock definitions for ux500 platforms - * - * Copyright (C) 2012 ST-Ericsson SA - * Author: Ulf Hansson - * - * License terms: GNU General Public License (GPL) version 2 - */ - -#ifndef __CLK_UX500_H -#define __CLK_UX500_H - -void u8500_clk_init(void); -void u9540_clk_init(void); -void u8540_clk_init(void); - -#endif /* __CLK_UX500_H */ -- cgit v1.2.3 From 6cb4f8dd1044849047023b76567231f41eb64c9e Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Tue, 7 Jun 2016 13:19:00 +0200 Subject: ARM: sti: stih407-family: Supply defines for CLOCKGEN A0 There are 2 LMI clocks generated by CLOCKGEN A0. We wish to control them individually and need to use these indexes to do so. Signed-off-by: Lee Jones --- include/dt-bindings/clock/stih407-clks.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/dt-bindings/clock/stih407-clks.h b/include/dt-bindings/clock/stih407-clks.h index 7af2b717b3b2..082edd9badfa 100644 --- a/include/dt-bindings/clock/stih407-clks.h +++ b/include/dt-bindings/clock/stih407-clks.h @@ -5,6 +5,10 @@ #ifndef _DT_BINDINGS_CLK_STIH407 #define _DT_BINDINGS_CLK_STIH407 +/* CLOCKGEN A0 */ +#define CLK_IC_LMI0 0 +#define CLK_IC_LMI1 1 + /* CLOCKGEN C0 */ #define CLK_ICN_GPU 0 #define CLK_FDMA 1 -- cgit v1.2.3 From f04f2d0e3e9137ec33c24daac686629927b3c839 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sun, 3 Jul 2016 09:02:01 -0300 Subject: [media] v4l2-subdev.h: remove the control subdev ops These are no longer used (finally!), so remove them. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ctrls.h | 10 ---------- include/media/v4l2-subdev.h | 21 --------------------- 2 files changed, 31 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 5c2ed0cfb841..8b59336b2217 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -903,16 +903,6 @@ int v4l2_try_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls * int v4l2_s_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *c); -/* Helpers for subdevices. If the associated ctrl_handler == NULL then they - will all return -EINVAL. */ -int v4l2_subdev_queryctrl(struct v4l2_subdev *sd, struct v4l2_queryctrl *qc); -int v4l2_subdev_querymenu(struct v4l2_subdev *sd, struct v4l2_querymenu *qm); -int v4l2_subdev_g_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs); -int v4l2_subdev_try_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs); -int v4l2_subdev_s_ext_ctrls(struct v4l2_subdev *sd, struct v4l2_ext_controls *cs); -int v4l2_subdev_g_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl); -int v4l2_subdev_s_ctrl(struct v4l2_subdev *sd, struct v4l2_control *ctrl); - /* Can be used as a subscribe_event function that just subscribes control events. */ int v4l2_ctrl_subdev_subscribe_event(struct v4l2_subdev *sd, struct v4l2_fh *fh, diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 32fc7a4beb5e..c672efc4f87b 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -143,20 +143,6 @@ struct v4l2_subdev_io_pin_config { * @s_gpio: set GPIO pins. Very simple right now, might need to be extended with * a direction argument if needed. * - * @queryctrl: callback for VIDIOC_QUERYCTL ioctl handler code. - * - * @g_ctrl: callback for VIDIOC_G_CTRL ioctl handler code. - * - * @s_ctrl: callback for VIDIOC_S_CTRL ioctl handler code. - * - * @g_ext_ctrls: callback for VIDIOC_G_EXT_CTRLS ioctl handler code. - * - * @s_ext_ctrls: callback for VIDIOC_S_EXT_CTRLS ioctl handler code. - * - * @try_ext_ctrls: callback for VIDIOC_TRY_EXT_CTRLS ioctl handler code. - * - * @querymenu: callback for VIDIOC_QUERYMENU ioctl handler code. - * * @ioctl: called at the end of ioctl() syscall handler at the V4L2 core. * used to provide support for private ioctls used on the driver. * @@ -190,13 +176,6 @@ struct v4l2_subdev_core_ops { int (*load_fw)(struct v4l2_subdev *sd); int (*reset)(struct v4l2_subdev *sd, u32 val); int (*s_gpio)(struct v4l2_subdev *sd, u32 val); - int (*queryctrl)(struct v4l2_subdev *sd, struct v4l2_queryctrl *qc); - int (*g_ctrl)(struct v4l2_subdev *sd, struct v4l2_control *ctrl); - int (*s_ctrl)(struct v4l2_subdev *sd, struct v4l2_control *ctrl); - int (*g_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls); - int (*s_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls); - int (*try_ext_ctrls)(struct v4l2_subdev *sd, struct v4l2_ext_controls *ctrls); - int (*querymenu)(struct v4l2_subdev *sd, struct v4l2_querymenu *qm); long (*ioctl)(struct v4l2_subdev *sd, unsigned int cmd, void *arg); #ifdef CONFIG_COMPAT long (*compat_ioctl32)(struct v4l2_subdev *sd, unsigned int cmd, -- cgit v1.2.3 From 0c12735e8abf4734b011aec979092db5e63556b0 Mon Sep 17 00:00:00 2001 From: Tom Yan Date: Tue, 12 Jul 2016 21:37:02 +0800 Subject: libata-scsi: fix SET FEATURES "filtering" for ata_msense_caching() Without this fix, the DRA bit of the caching mode page would not be updated when the read look-ahead feature is toggled (e.g. with `smartctl --set`), but will only be until, for example, the write cache feature is touched. Signed-off-by: Tom Yan Signed-off-by: Tejun Heo --- include/linux/ata.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 99346be5a7ca..2d6879392ae3 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -409,6 +409,9 @@ enum { SETFEATURES_WC_ON = 0x02, /* Enable write cache */ SETFEATURES_WC_OFF = 0x82, /* Disable write cache */ + SETFEATURES_RA_ON = 0xaa, /* Enable read look-ahead */ + SETFEATURES_RA_OFF = 0x55, /* Disable read look-ahead */ + /* Enable/Disable Automatic Acoustic Management */ SETFEATURES_AAM_ON = 0x42, SETFEATURES_AAM_OFF = 0xC2, -- cgit v1.2.3 From 8842316bbdcbe7862c0b05839efec5ec4fc73f93 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 28 Jun 2016 11:54:59 -0300 Subject: [media] adv7604/adv7842: drop unused op_656_range and alt_data_sat fields These platform_data fields are no longer needed, drop them. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/i2c/adv7604.h | 2 -- include/media/i2c/adv7842.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/include/media/i2c/adv7604.h b/include/media/i2c/adv7604.h index a913859bfd30..2e6857dee0cc 100644 --- a/include/media/i2c/adv7604.h +++ b/include/media/i2c/adv7604.h @@ -121,8 +121,6 @@ struct adv76xx_platform_data { /* IO register 0x02 */ unsigned alt_gamma:1; - unsigned op_656_range:1; - unsigned alt_data_sat:1; /* IO register 0x05 */ unsigned blank_data:1; diff --git a/include/media/i2c/adv7842.h b/include/media/i2c/adv7842.h index bc249709bf35..7f53ada9bdf1 100644 --- a/include/media/i2c/adv7842.h +++ b/include/media/i2c/adv7842.h @@ -165,8 +165,6 @@ struct adv7842_platform_data { /* IO register 0x02 */ unsigned alt_gamma:1; - unsigned op_656_range:1; - unsigned alt_data_sat:1; /* IO register 0x05 */ unsigned blank_data:1; -- cgit v1.2.3 From c624b5de5037fab77c75db8272befb2df52a968f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sun, 10 Jul 2016 07:08:58 -0300 Subject: [media] input: serio - add new protocol for the Pulse-Eight USB-CEC Adapter This is for the new pulse8-cec staging driver. Signed-off-by: Hans Verkuil Acked-by: Dmitry Torokhov Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/serio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/serio.h b/include/uapi/linux/serio.h index c2ea1698257f..f2447a83ac8d 100644 --- a/include/uapi/linux/serio.h +++ b/include/uapi/linux/serio.h @@ -78,5 +78,6 @@ #define SERIO_TSC40 0x3d #define SERIO_WACOM_IV 0x3e #define SERIO_EGALAX 0x3f +#define SERIO_PULSE8_CEC 0x40 #endif /* _UAPI_SERIO_H */ -- cgit v1.2.3 From 2983860c766870b701c4a34f435c1e18db086244 Mon Sep 17 00:00:00 2001 From: Tom Yan Date: Wed, 13 Jul 2016 04:31:23 +0800 Subject: libata-scsi: avoid repeated calculation of number of TRIM ranges Currently libata statically allows only 1-block (512-byte) payload for each TRIM command. Each payload can carry 64 TRIM ranges since each range requires 8 bytes. It is silly to keep doing the calculation (512 / 8) in different places. Hence, define the new ATA_MAX_TRIM_RNUM for the result. Signed-off-by: Tom Yan Signed-off-by: Tejun Heo --- include/linux/ata.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 2d6879392ae3..d20b1ee127b0 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -48,6 +48,7 @@ enum { ATA_MAX_SECTORS_1024 = 1024, ATA_MAX_SECTORS_LBA48 = 65535,/* TODO: 65536? */ ATA_MAX_SECTORS_TAPE = 65535, + ATA_MAX_TRIM_RNUM = 64, /* 512-byte payload / (6-byte LBA + 2-byte range per entry) */ ATA_ID_WORDS = 256, ATA_ID_CONFIG = 0, @@ -1069,12 +1070,12 @@ static inline void ata_id_to_hd_driveid(u16 *id) * TO NV CACHE PINNED SET. */ static inline unsigned ata_set_lba_range_entries(void *_buffer, - unsigned buf_size, u64 sector, unsigned long count) + unsigned num, u64 sector, unsigned long count) { __le64 *buffer = _buffer; unsigned i = 0, used_bytes; - while (i < buf_size / 8 ) { /* 6-byte LBA + 2-byte range per entry */ + while (i < num) { u64 entry = sector | ((u64)(count > 0xffff ? 0xffff : count) << 48); buffer[i++] = __cpu_to_le64(entry); -- cgit v1.2.3 From e5224f0fe2acddbc2fa9b419d8867ced7f5381fc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 Jul 2016 18:05:03 +0200 Subject: devlink: add hardware messages tracing facility Define a tracepoint and allow user to trace messages going to and from hardware associated with devlink instance. Signed-off-by: Jiri Pirko Acked-by: Steven Rostedt Signed-off-by: David S. Miller --- include/trace/events/devlink.h | 68 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) create mode 100644 include/trace/events/devlink.h (limited to 'include') diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h new file mode 100644 index 000000000000..333c32ac9bfa --- /dev/null +++ b/include/trace/events/devlink.h @@ -0,0 +1,68 @@ +#if IS_ENABLED(CONFIG_NET_DEVLINK) + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM devlink + +#if !defined(_TRACE_DEVLINK_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_DEVLINK_H + +#include +#include +#include + +/* + * Tracepoint for devlink hardware message: + */ +TRACE_EVENT(devlink_hwmsg, + TP_PROTO(const struct devlink *devlink, bool incoming, + unsigned long type, const u8 *buf, size_t len), + + TP_ARGS(devlink, incoming, type, buf, len), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(owner_name, devlink->dev->driver->owner->name) + __field(bool, incoming) + __field(unsigned long, type) + __dynamic_array(u8, buf, len) + __field(size_t, len) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(owner_name, devlink->dev->driver->owner->name); + __entry->incoming = incoming; + __entry->type = type; + memcpy(__get_dynamic_array(buf), buf, len); + __entry->len = len; + ), + + TP_printk("bus_name=%s dev_name=%s owner_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%lu", + __get_str(bus_name), __get_str(dev_name), + __get_str(owner_name), __entry->incoming, __entry->type, + (int) __entry->len, __get_dynamic_array(buf), __entry->len) +); + +#endif /* _TRACE_DEVLINK_H */ + +/* This part must be outside protection */ +#include + +#else /* CONFIG_NET_DEVLINK */ + +#if !defined(_TRACE_DEVLINK_H) +#define _TRACE_DEVLINK_H + +#include + +static inline void trace_devlink_hwmsg(const struct devlink *devlink, + bool incoming, unsigned long type, + const u8 *buf, size_t len) +{ +} + +#endif /* _TRACE_DEVLINK_H */ + +#endif -- cgit v1.2.3 From 476f848aaee466fd5d74f123fa652e757f2baeba Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 9 Jul 2016 00:12:52 -0700 Subject: libnvdimm, pmem: flush posted-write queues on shutdown Commit writes to media on system shutdown or pmem driver unload. Signed-off-by: Dan Williams --- include/linux/nd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nd.h b/include/linux/nd.h index aee2761d294c..1ecd64643512 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -26,6 +26,7 @@ struct nd_device_driver { unsigned long type; int (*probe)(struct device *dev); int (*remove)(struct device *dev); + void (*shutdown)(struct device *dev); void (*notify)(struct device *dev, enum nvdimm_event event); }; -- cgit v1.2.3 From 7c8a6a71904d57ae5fb24140f9661ec22ca9ee85 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 1 Jun 2016 23:07:43 -0700 Subject: pmem: kill wmb_pmem() All users have been replaced with flushing in the pmem driver. Cc: Ross Zwisler Signed-off-by: Dan Williams --- include/linux/pmem.h | 47 ++++------------------------------------------- 1 file changed, 4 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/pmem.h b/include/linux/pmem.h index 57d146fe44dd..9e3ea94b8157 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -26,16 +26,6 @@ * calling these symbols with arch_has_pmem_api() and redirect to the * implementation in asm/pmem.h. */ -static inline bool __arch_has_wmb_pmem(void) -{ - return false; -} - -static inline void arch_wmb_pmem(void) -{ - BUG(); -} - static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) { @@ -101,20 +91,6 @@ static inline int memcpy_from_pmem(void *dst, void __pmem const *src, return default_memcpy_from_pmem(dst, src, size); } -/** - * arch_has_wmb_pmem - true if wmb_pmem() ensures durability - * - * For a given cpu implementation within an architecture it is possible - * that wmb_pmem() resolves to a nop. In the case this returns - * false, pmem api users are unable to ensure durability and may want to - * fall back to a different data consistency model, or otherwise notify - * the user. - */ -static inline bool arch_has_wmb_pmem(void) -{ - return arch_has_pmem_api() && __arch_has_wmb_pmem(); -} - /* * These defaults seek to offer decent performance and minimize the * window between i/o completion and writes being durable on media. @@ -152,7 +128,7 @@ static inline void default_clear_pmem(void __pmem *addr, size_t size) * being effectively evicted from, or never written to, the processor * cache hierarchy after the copy completes. After memcpy_to_pmem() * data may still reside in cpu or platform buffers, so this operation - * must be followed by a wmb_pmem(). + * must be followed by a blkdev_issue_flush() on the pmem block device. */ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) { @@ -162,21 +138,6 @@ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) default_memcpy_to_pmem(dst, src, n); } -/** - * wmb_pmem - synchronize writes to persistent memory - * - * After a series of memcpy_to_pmem() operations this drains data from - * cpu write buffers and any platform (memory controller) buffers to - * ensure that written data is durable on persistent memory media. - */ -static inline void wmb_pmem(void) -{ - if (arch_has_wmb_pmem()) - arch_wmb_pmem(); - else - wmb(); -} - /** * copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -184,7 +145,7 @@ static inline void wmb_pmem(void) * @i: iterator with source data * * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. - * This function requires explicit ordering with a wmb_pmem() call. + * See blkdev_issue_flush() note for memcpy_to_pmem(). */ static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, struct iov_iter *i) @@ -200,7 +161,7 @@ static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, * @size: number of bytes to zero * * Write zeros into the memory range starting at 'addr' for 'size' bytes. - * This function requires explicit ordering with a wmb_pmem() call. + * See blkdev_issue_flush() note for memcpy_to_pmem(). */ static inline void clear_pmem(void __pmem *addr, size_t size) { @@ -230,7 +191,7 @@ static inline void invalidate_pmem(void __pmem *addr, size_t size) * @size: number of bytes to write back * * Write back the processor cache range starting at 'addr' for 'size' bytes. - * This function requires explicit ordering with a wmb_pmem() call. + * See blkdev_issue_flush() note for memcpy_to_pmem(). */ static inline void wb_cache_pmem(void __pmem *addr, size_t size) { -- cgit v1.2.3 From 7a9eb20666317794d0279843fbd091af93907780 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 3 Jun 2016 18:06:47 -0700 Subject: pmem: kill __pmem address space The __pmem address space was meant to annotate codepaths that touch persistent memory and need to coordinate a call to wmb_pmem(). Now that wmb_pmem() is gone, there is little need to keep this annotation. Cc: Christoph Hellwig Cc: Ross Zwisler Signed-off-by: Dan Williams --- include/linux/blkdev.h | 6 ++--- include/linux/compiler.h | 2 -- include/linux/nd.h | 2 +- include/linux/pmem.h | 70 ++++++++++++------------------------------------ 4 files changed, 21 insertions(+), 59 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3d9cf326574f..fde908b2836b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1659,7 +1659,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, */ struct blk_dax_ctl { sector_t sector; - void __pmem *addr; + void *addr; long size; pfn_t pfn; }; @@ -1670,8 +1670,8 @@ struct block_device_operations { int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - long (*direct_access)(struct block_device *, sector_t, void __pmem **, - pfn_t *, long); + long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, + long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 793c0829e3a3..b966974938ed 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -17,7 +17,6 @@ # define __release(x) __context__(x,-1) # define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0) # define __percpu __attribute__((noderef, address_space(3))) -# define __pmem __attribute__((noderef, address_space(5))) #ifdef CONFIG_SPARSE_RCU_POINTER # define __rcu __attribute__((noderef, address_space(4))) #else /* CONFIG_SPARSE_RCU_POINTER */ @@ -45,7 +44,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); # define __cond_lock(x,c) (c) # define __percpu # define __rcu -# define __pmem # define __private # define ACCESS_PRIVATE(p, member) ((p)->member) #endif /* __CHECKER__ */ diff --git a/include/linux/nd.h b/include/linux/nd.h index 1ecd64643512..f1ea426d6a5e 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -68,7 +68,7 @@ struct nd_namespace_io { struct nd_namespace_common common; struct resource res; resource_size_t size; - void __pmem *addr; + void *addr; struct badblocks bb; }; diff --git a/include/linux/pmem.h b/include/linux/pmem.h index 9e3ea94b8157..e856c2cb0fe8 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -26,37 +26,35 @@ * calling these symbols with arch_has_pmem_api() and redirect to the * implementation in asm/pmem.h. */ -static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, - size_t n) +static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) { BUG(); } -static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src, - size_t n) +static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) { BUG(); return -EFAULT; } -static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, +static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, struct iov_iter *i) { BUG(); return 0; } -static inline void arch_clear_pmem(void __pmem *addr, size_t size) +static inline void arch_clear_pmem(void *addr, size_t size) { BUG(); } -static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size) +static inline void arch_wb_cache_pmem(void *addr, size_t size) { BUG(); } -static inline void arch_invalidate_pmem(void __pmem *addr, size_t size) +static inline void arch_invalidate_pmem(void *addr, size_t size) { BUG(); } @@ -67,13 +65,6 @@ static inline bool arch_has_pmem_api(void) return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API); } -static inline int default_memcpy_from_pmem(void *dst, void __pmem const *src, - size_t size) -{ - memcpy(dst, (void __force *) src, size); - return 0; -} - /* * memcpy_from_pmem - read from persistent memory with error handling * @dst: destination buffer @@ -82,40 +73,13 @@ static inline int default_memcpy_from_pmem(void *dst, void __pmem const *src, * * Returns 0 on success negative error code on failure. */ -static inline int memcpy_from_pmem(void *dst, void __pmem const *src, - size_t size) +static inline int memcpy_from_pmem(void *dst, void const *src, size_t size) { if (arch_has_pmem_api()) return arch_memcpy_from_pmem(dst, src, size); else - return default_memcpy_from_pmem(dst, src, size); -} - -/* - * These defaults seek to offer decent performance and minimize the - * window between i/o completion and writes being durable on media. - * However, it is undefined / architecture specific whether - * ARCH_MEMREMAP_PMEM + default_memcpy_to_pmem is sufficient for - * making data durable relative to i/o completion. - */ -static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src, - size_t size) -{ - memcpy((void __force *) dst, src, size); -} - -static inline size_t default_copy_from_iter_pmem(void __pmem *addr, - size_t bytes, struct iov_iter *i) -{ - return copy_from_iter_nocache((void __force *)addr, bytes, i); -} - -static inline void default_clear_pmem(void __pmem *addr, size_t size) -{ - if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0) - clear_page((void __force *)addr); - else - memset((void __force *)addr, 0, size); + memcpy(dst, src, size); + return 0; } /** @@ -130,12 +94,12 @@ static inline void default_clear_pmem(void __pmem *addr, size_t size) * data may still reside in cpu or platform buffers, so this operation * must be followed by a blkdev_issue_flush() on the pmem block device. */ -static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) +static inline void memcpy_to_pmem(void *dst, const void *src, size_t n) { if (arch_has_pmem_api()) arch_memcpy_to_pmem(dst, src, n); else - default_memcpy_to_pmem(dst, src, n); + memcpy(dst, src, n); } /** @@ -147,12 +111,12 @@ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. * See blkdev_issue_flush() note for memcpy_to_pmem(). */ -static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, +static inline size_t copy_from_iter_pmem(void *addr, size_t bytes, struct iov_iter *i) { if (arch_has_pmem_api()) return arch_copy_from_iter_pmem(addr, bytes, i); - return default_copy_from_iter_pmem(addr, bytes, i); + return copy_from_iter_nocache(addr, bytes, i); } /** @@ -163,12 +127,12 @@ static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, * Write zeros into the memory range starting at 'addr' for 'size' bytes. * See blkdev_issue_flush() note for memcpy_to_pmem(). */ -static inline void clear_pmem(void __pmem *addr, size_t size) +static inline void clear_pmem(void *addr, size_t size) { if (arch_has_pmem_api()) arch_clear_pmem(addr, size); else - default_clear_pmem(addr, size); + memset(addr, 0, size); } /** @@ -179,7 +143,7 @@ static inline void clear_pmem(void __pmem *addr, size_t size) * For platforms that support clearing poison this flushes any poisoned * ranges out of the cache */ -static inline void invalidate_pmem(void __pmem *addr, size_t size) +static inline void invalidate_pmem(void *addr, size_t size) { if (arch_has_pmem_api()) arch_invalidate_pmem(addr, size); @@ -193,7 +157,7 @@ static inline void invalidate_pmem(void __pmem *addr, size_t size) * Write back the processor cache range starting at 'addr' for 'size' bytes. * See blkdev_issue_flush() note for memcpy_to_pmem(). */ -static inline void wb_cache_pmem(void __pmem *addr, size_t size) +static inline void wb_cache_pmem(void *addr, size_t size) { if (arch_has_pmem_api()) arch_wb_cache_pmem(addr, size); -- cgit v1.2.3 From 4b9bc86d5a999e344098303882d6395d39e36c13 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 12 Apr 2016 17:16:54 +0200 Subject: fcoe: convert to kworker The driver creates its own per-CPU threads which are updated based on CPU hotplug events. It is also possible to use kworkers and remove some of the kthread infrastrucure. The code checked ->thread to decide if there is an active per-CPU thread. By using the kworker infrastructure this is no longer possible (or required). The thread pointer is saved in `kthread' instead of `thread' so anything trying to use thread is caught by the compiler. Currently only the bnx2fc driver is using struct fcoe_percpu_s and the kthread member. After a CPU went offline, we may still enqueue items on the "offline" CPU. This isn't much of a problem. The work will be done on a random CPU. The allocated crc_eof_page page won't be cleaned up. It is probably expected that the CPU comes up at some point so it should not be a problem. The crc_eof_page memory is released of course once the module is removed. This patch was only compile-tested due to -ENODEV. Cc: Vasu Dev Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Christoph Hellwig Cc: fcoe-devel@open-fcoe.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Sebastian Andrzej Siewior Tested-by: Johannes Thumshirn Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/libfcoe.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index de7e3ee60f0c..c6fbbb6581d3 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -319,14 +319,16 @@ struct fcoe_transport { /** * struct fcoe_percpu_s - The context for FCoE receive thread(s) - * @thread: The thread context + * @kthread: The thread context (used by bnx2fc) + * @work: The work item (used by fcoe) * @fcoe_rx_list: The queue of pending packets to process * @page: The memory page for calculating frame trailer CRCs * @crc_eof_offset: The offset into the CRC page pointing to available * memory for a new trailer */ struct fcoe_percpu_s { - struct task_struct *thread; + struct task_struct *kthread; + struct work_struct work; struct sk_buff_head fcoe_rx_list; struct page *crc_eof_page; int crc_eof_offset; -- cgit v1.2.3 From 160b925163c0aabc2c2fbb7d58a75e38b7cd6a17 Mon Sep 17 00:00:00 2001 From: Szymon Janc Date: Tue, 12 Jul 2016 02:12:16 +0200 Subject: Bluetooth: Add Authentication Failed reason to Disconnected Mgmt event If link is disconnected due to Authentication Failure (PIN or Key Missing status) userspace will be notified about this with proper error code. Many LE profiles define "PIN or Key Missing" status as indication of remote lost bond so this allows userspace to take action on this. @ Device Connected: 88:63:DF:88:0E:83 (1) flags 0x0000 02 01 1a 05 03 0a 18 0d 18 0b 09 48 65 61 72 74 ...........Heart 20 52 61 74 65 Rate > HCI Event: Command Status (0x0f) plen 4 LE Read Remote Used Features (0x08|0x0016) ncmd 1 Status: Success (0x00) > ACL Data RX: Handle 3585 flags 0x02 dlen 11 ATT: Read By Group Type Request (0x10) len 6 Handle range: 0x0001-0xffff Attribute group type: Primary Service (0x2800) > HCI Event: LE Meta Event (0x3e) plen 12 LE Read Remote Used Features (0x04) Status: Success (0x00) Handle: 3585 Features: 0x01 0x00 0x00 0x00 0x00 0x00 0x00 0x00 LE Encryption < HCI Command: LE Start Encryption (0x08|0x0019) plen 28 Handle: 3585 Random number: 0x0000000000000000 Encrypted diversifier: 0x0000 Long term key: 26201cd479a0921b6f949f0b1fa8dc82 > HCI Event: Command Status (0x0f) plen 4 LE Start Encryption (0x08|0x0019) ncmd 1 Status: Success (0x00) > HCI Event: Encryption Change (0x08) plen 4 Status: PIN or Key Missing (0x06) Handle: 3585 Encryption: Disabled (0x00) < HCI Command: Disconnect (0x01|0x0006) plen 3 Handle: 3585 Reason: Authentication Failure (0x05) > HCI Event: Command Status (0x0f) plen 4 Disconnect (0x01|0x0006) ncmd 1 Status: Success (0x00) > HCI Event: Disconnect Complete (0x05) plen 4 Status: Success (0x00) Handle: 3585 Reason: Connection Terminated By Local Host (0x16) @ Device Disconnected: 88:63:DF:88:0E:83 (1) reason 4 @ Device Connected: C4:43:8F:A3:4D:83 (0) flags 0x0000 08 09 4e 65 78 75 73 20 35 ..Nexus 5 > HCI Event: Command Status (0x0f) plen 4 Authentication Requested (0x01|0x0011) ncmd 1 Status: Success (0x00) > HCI Event: Link Key Request (0x17) plen 6 Address: C4:43:8F:A3:4D:83 (LG Electronics) < HCI Command: Link Key Request Reply (0x01|0x000b) plen 22 Address: C4:43:8F:A3:4D:83 (LG Electronics) Link key: 080812e4aa97a863d11826f71f65a933 > HCI Event: Command Complete (0x0e) plen 10 Link Key Request Reply (0x01|0x000b) ncmd 1 Status: Success (0x00) Address: C4:43:8F:A3:4D:83 (LG Electronics) > HCI Event: Auth Complete (0x06) plen 3 Status: PIN or Key Missing (0x06) Handle: 75 @ Authentication Failed: C4:43:8F:A3:4D:83 (0) status 0x05 < HCI Command: Disconnect (0x01|0x0006) plen 3 Handle: 75 Reason: Remote User Terminated Connection (0x13) > HCI Event: Command Status (0x0f) plen 4 Disconnect (0x01|0x0006) ncmd 1 Status: Success (0x00) > HCI Event: Disconnect Complete (0x05) plen 4 Status: Success (0x00) Handle: 75 Reason: Connection Terminated By Local Host (0x16) @ Device Disconnected: C4:43:8F:A3:4D:83 (0) reason 4 Signed-off-by: Szymon Janc Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/mgmt.h | 1 + 3 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a3f86de6f100..003b25283407 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -445,6 +445,7 @@ enum { /* ---- HCI Error Codes ---- */ #define HCI_ERROR_UNKNOWN_CONN_ID 0x02 #define HCI_ERROR_AUTH_FAILURE 0x05 +#define HCI_ERROR_PIN_OR_KEY_MISSING 0x06 #define HCI_ERROR_MEMORY_EXCEEDED 0x07 #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index dc71473462ac..77d7fe115a0d 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -654,6 +654,7 @@ enum { HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, + HCI_CONN_AUTH_FAILURE, }; static inline bool hci_conn_ssp_enabled(struct hci_conn *conn) diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index ea73e0826aa7..7647964b1efa 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -645,6 +645,7 @@ struct mgmt_ev_device_connected { #define MGMT_DEV_DISCONN_TIMEOUT 0x01 #define MGMT_DEV_DISCONN_LOCAL_HOST 0x02 #define MGMT_DEV_DISCONN_REMOTE 0x03 +#define MGMT_DEV_DISCONN_AUTH_FAILURE 0x04 #define MGMT_EV_DEVICE_DISCONNECTED 0x000C struct mgmt_ev_device_disconnected { -- 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 --- include/linux/sfi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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 33b21a6b203f70e2012b02753134e59c3ab38779 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 5 Jul 2016 13:07:53 +0200 Subject: iommu: Add apply_dm_region call-back to iommu-ops This new call-back will be used by the iommu driver to do reserve the given dm_region in its iova space before the mapping is created. The call-back is temporary until the dma-ops implementation is part of the common iommu code. Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 664683aedcce..a35fb8b42e1a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -152,6 +152,7 @@ struct iommu_dm_region { * @domain_set_attr: Change domain attributes * @get_dm_regions: Request list of direct mapping requirements for a device * @put_dm_regions: Free list of direct mapping requirements for a device + * @apply_dm_region: Temporary helper call-back for iova reserved ranges * @domain_window_enable: Configure and enable a particular window for a domain * @domain_window_disable: Disable a particular window for a domain * @domain_set_windows: Set the number of windows for a domain @@ -186,6 +187,8 @@ struct iommu_ops { /* Request/Free a list of direct mapping requirements for a device */ void (*get_dm_regions)(struct device *dev, struct list_head *list); void (*put_dm_regions)(struct device *dev, struct list_head *list); + void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain, + struct iommu_dm_region *region); /* Window handling functions */ int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr, -- cgit v1.2.3 From 980e0b36b55985dd0a37acd25d29c8f21482db32 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Tue, 12 Jul 2016 11:10:42 -0300 Subject: [media] cec: split the timestamp into an rx and tx timestamp When transmitting a message and waiting for a reply it would be good to know the time between when the message was transmitted and when the reply arrived. With only one timestamp field it was set to when the reply arrived and the original transmit time was overwritten. Just taking the timestamp in userspace right before CEC_TRANSMIT is called is not reliable, since the actual transmit can be delayed if the CEC bus is busy. Only the driver can fill this in accurately. So split up the ts field into an rx_ts and a tx_ts. Also move the status fields to after the 'reply' field: they were placed in a strange position and make much more sense when grouped with the other status-related fields. This patch also makes sure that the timestamp is taken as soon as possible. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/cec.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/cec.h b/include/linux/cec.h index 6678afe26844..b3e22893a002 100644 --- a/include/linux/cec.h +++ b/include/linux/cec.h @@ -48,9 +48,10 @@ /** * struct cec_msg - CEC message structure. - * @ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the - * driver. It is set when the message transmission has finished - * and it is set when a message was received. + * @tx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the + * driver when the message transmission has finished. + * @rx_ts: Timestamp in nanoseconds using CLOCK_MONOTONIC. Set by the + * driver when the message was received. * @len: Length in bytes of the message. * @timeout: The timeout (in ms) that is used to timeout CEC_RECEIVE. * Set to 0 if you want to wait forever. This timeout can also be @@ -61,8 +62,6 @@ * sent. This can be used to track replies to previously sent * messages. * @flags: Set to 0. - * @rx_status: The message receive status bits. Set by the driver. - * @tx_status: The message transmit status bits. Set by the driver. * @msg: The message payload. * @reply: This field is ignored with CEC_RECEIVE and is only used by * CEC_TRANSMIT. If non-zero, then wait for a reply with this @@ -80,6 +79,8 @@ * broadcast, then -EINVAL is returned. * if reply is non-zero, then timeout is set to 1000 (the required * maximum response time). + * @rx_status: The message receive status bits. Set by the driver. + * @tx_status: The message transmit status bits. Set by the driver. * @tx_arb_lost_cnt: The number of 'Arbitration Lost' events. Set by the driver. * @tx_nack_cnt: The number of 'Not Acknowledged' events. Set by the driver. * @tx_low_drive_cnt: The number of 'Low Drive Detected' events. Set by the @@ -87,15 +88,16 @@ * @tx_error_cnt: The number of 'Error' events. Set by the driver. */ struct cec_msg { - __u64 ts; + __u64 tx_ts; + __u64 rx_ts; __u32 len; __u32 timeout; __u32 sequence; __u32 flags; - __u8 rx_status; - __u8 tx_status; __u8 msg[CEC_MAX_MSG_SIZE]; __u8 reply; + __u8 rx_status; + __u8 tx_status; __u8 tx_arb_lost_cnt; __u8 tx_nack_cnt; __u8 tx_low_drive_cnt; -- cgit v1.2.3 From d8d29138b17c9965484427b34cf8046601aef8c4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 2 Jun 2016 16:31:03 +1000 Subject: sunrpc: remove 'inuse' flag from struct cache_detail. This field is not currently in use. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ed03c9f7f908..62a60eeacb0a 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -78,8 +78,6 @@ struct cache_detail { struct hlist_head * hash_table; rwlock_t hash_lock; - atomic_t inuse; /* active user-space update or lookup */ - char *name; void (*cache_put)(struct kref *); -- cgit v1.2.3 From 1adf0c5a4451a100cd9253c1d6e3ca77f4a5a98b Mon Sep 17 00:00:00 2001 From: Andrew Elble Date: Wed, 15 Jun 2016 12:52:07 -0400 Subject: nfs/nfsd: Move useful bitfield ops to a commonly accessible place So these may be used in nfsd as well Signed-off-by: Andrew Elble Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 11 +++++++++++ include/linux/nfs_xdr.h | 11 ----------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index bfed6b367350..c6564ada9beb 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -643,4 +643,15 @@ enum pnfs_update_layout_reason { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, }; +#define NFS4_OP_MAP_NUM_LONGS \ + DIV_ROUND_UP(LAST_NFS4_OP, 8 * sizeof(unsigned long)) +#define NFS4_OP_MAP_NUM_WORDS \ + (NFS4_OP_MAP_NUM_LONGS * sizeof(unsigned long) / sizeof(u32)) +struct nfs4_op_map { + union { + unsigned long longs[NFS4_OP_MAP_NUM_LONGS]; + u32 words[NFS4_OP_MAP_NUM_WORDS]; + } u; +}; + #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c304a11b5b1a..e66abc2d1f88 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1185,17 +1185,6 @@ struct pnfs_ds_commit_info { struct pnfs_commit_bucket *buckets; }; -#define NFS4_OP_MAP_NUM_LONGS \ - DIV_ROUND_UP(LAST_NFS4_OP, 8 * sizeof(unsigned long)) -#define NFS4_OP_MAP_NUM_WORDS \ - (NFS4_OP_MAP_NUM_LONGS * sizeof(unsigned long) / sizeof(u32)) -struct nfs4_op_map { - union { - unsigned long longs[NFS4_OP_MAP_NUM_LONGS]; - u32 words[NFS4_OP_MAP_NUM_WORDS]; - } u; -}; - struct nfs41_state_protection { u32 how; struct nfs4_op_map enforce; -- cgit v1.2.3 From 82ea2d7615309d755579d609ad9c11daea25d0cc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:45 -0400 Subject: SUNRPC: Add a tracepoint for server socket out-of-space conditions Add a tracepoint to track when the processing of incoming RPC data gets deferred due to out-of-space issues on the outgoing transport. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 5664ca07c9c7..b014207a95a8 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -553,7 +553,7 @@ TRACE_EVENT(svc_xprt_do_enqueue, __entry->pid, show_svc_xprt_flags(__entry->flags)) ); -TRACE_EVENT(svc_xprt_dequeue, +DECLARE_EVENT_CLASS(svc_xprt_event, TP_PROTO(struct svc_xprt *xprt), TP_ARGS(xprt), @@ -582,6 +582,14 @@ TRACE_EVENT(svc_xprt_dequeue, show_svc_xprt_flags(__entry->flags)) ); +DEFINE_EVENT(svc_xprt_event, svc_xprt_dequeue, + TP_PROTO(struct svc_xprt *xprt), + TP_ARGS(xprt)); + +DEFINE_EVENT(svc_xprt_event, svc_xprt_no_write_space, + TP_PROTO(struct svc_xprt *xprt), + TP_ARGS(xprt)); + TRACE_EVENT(svc_wake_up, TP_PROTO(int pid), -- cgit v1.2.3 From 104f6351f7dc0036575b4e47765d6d39c757c066 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:46 -0400 Subject: SUNRPC: Add tracepoints for dropped and deferred requests Dropping and/or deferring requests has an impact on performance. Let's make sure we can trace those events. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 61 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'include') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index b014207a95a8..8a707f8a41c3 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -473,6 +473,39 @@ TRACE_EVENT(svc_recv, show_rqstp_flags(__entry->flags)) ); +DECLARE_EVENT_CLASS(svc_rqst_event, + + TP_PROTO(struct svc_rqst *rqst), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + __field(__be32, xid) + __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, rqst->rq_addrlen) + ), + + TP_fast_assign( + __entry->xid = rqst->rq_xid; + __entry->flags = rqst->rq_flags; + memcpy(__get_dynamic_array(addr), + &rqst->rq_addr, rqst->rq_addrlen); + ), + + TP_printk("addr=%pIScp rq_xid=0x%x flags=%s", + (struct sockaddr *)__get_dynamic_array(addr), + be32_to_cpu(__entry->xid), + show_rqstp_flags(__entry->flags)) +); + +DEFINE_EVENT(svc_rqst_event, svc_defer, + TP_PROTO(struct svc_rqst *rqst), + TP_ARGS(rqst)); + +DEFINE_EVENT(svc_rqst_event, svc_drop, + TP_PROTO(struct svc_rqst *rqst), + TP_ARGS(rqst)); + DECLARE_EVENT_CLASS(svc_rqst_status, TP_PROTO(struct svc_rqst *rqst, int status), @@ -636,6 +669,34 @@ TRACE_EVENT(svc_handle_xprt, (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->len, show_svc_xprt_flags(__entry->flags)) ); + + +DECLARE_EVENT_CLASS(svc_deferred_event, + TP_PROTO(struct svc_deferred_req *dr), + + TP_ARGS(dr), + + TP_STRUCT__entry( + __field(__be32, xid) + __dynamic_array(unsigned char, addr, dr->addrlen) + ), + + TP_fast_assign( + __entry->xid = *(__be32 *)(dr->args + (dr->xprt_hlen>>2)); + memcpy(__get_dynamic_array(addr), &dr->addr, dr->addrlen); + ), + + TP_printk("addr=%pIScp xid=0x%x", + (struct sockaddr *)__get_dynamic_array(addr), + be32_to_cpu(__entry->xid)) +); + +DEFINE_EVENT(svc_deferred_event, svc_drop_deferred, + TP_PROTO(struct svc_deferred_req *dr), + TP_ARGS(dr)); +DEFINE_EVENT(svc_deferred_event, svc_revisit_deferred, + TP_PROTO(struct svc_deferred_req *dr), + TP_ARGS(dr)); #endif /* _TRACE_SUNRPC_H */ #include -- cgit v1.2.3 From ff3ac5c3dc2323ba54c3d9ef30ef4942a71b251d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:50 -0400 Subject: SUNRPC: Add a server side per-connection limit Allow the user to limit the number of requests serviced through a single connection, to help prevent faster clients from starving slower clients. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + include/linux/sunrpc/svc_xprt.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 7ca44fb5b675..7321ae933867 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -268,6 +268,7 @@ struct svc_rqst { * cache pages */ #define RQ_VICTIM (5) /* about to be shut down */ #define RQ_BUSY (6) /* request is busy */ +#define RQ_DATA (7) /* request has data */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 79ba50856707..ad899ffed3be 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -69,6 +69,7 @@ struct svc_xprt { struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ + atomic_t xpt_nr_rqsts; /* Number of requests */ struct mutex xpt_mutex; /* to serialize sending data */ spinlock_t xpt_lock; /* protects sk_deferred * and xpt_auth_cache */ -- cgit v1.2.3 From f4a4906e563522aa2eab61cf080460d13b85725c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:52 -0400 Subject: SUNRPC: Remove unused callback xpo_adjust_wspace() Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ad899ffed3be..ab02a457da1f 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -25,7 +25,6 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); int (*xpo_secure_port)(struct svc_rqst *); - void (*xpo_adjust_wspace)(struct svc_xprt *); }; struct svc_xprt_class { -- cgit v1.2.3 From 83510e5f57111ad3b09d0187c822841f0a3ece4c Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Wed, 13 Jul 2016 11:11:36 -0700 Subject: Input: fix a double word "is is" in include/linux/input.h This patch fix a double word "is is" found in in Documentation/DocBook/device-drivers.xml. It is because the file was created from comments in sources, so I have to fix the double words in include/linux/input.h Signed-off-by: Masanari Iida Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 1e967694e9a5..a65e3b24fb18 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -95,7 +95,7 @@ struct input_value { * @grab: input handle that currently has the device grabbed (via * EVIOCGRAB ioctl). When a handle grabs a device it becomes sole * recipient for all input events coming from the device - * @event_lock: this spinlock is is taken when input core receives + * @event_lock: this spinlock is taken when input core receives * and processes a new event for the device (in input_event()). * Code that accesses and/or modifies parameters of a device * (such as keymap or absmin, absmax, absfuzz, etc.) after device -- cgit v1.2.3 From 9e238323799fb8c2add2b1de9a22edd4d4e51e30 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 13 Jul 2016 15:08:55 -0300 Subject: sctp: allow others to use sctp_input_cb We process input path in other files too and having access to it is nice, so move it to a header where it's shared. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 8626bdd3249a..966c3a40039c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -59,6 +59,7 @@ #include /* We need tq_struct. */ #include /* We need sctp* header structs. */ #include /* We need auth specific structs */ +#include /* For inet_skb_parm */ /* A convenience structure for handling sockaddr structures. * We should wean ourselves off this. @@ -1092,6 +1093,20 @@ static inline void sctp_outq_cork(struct sctp_outq *q) q->cork = 1; } +/* SCTP skb control block. + * sctp_input_cb is currently used on rx and sock rx queue + */ +struct sctp_input_cb { + union { + struct inet_skb_parm h4; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_skb_parm h6; +#endif + } header; + struct sctp_chunk *chunk; +}; +#define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) + /* These bind address data fields common between endpoints and associations */ struct sctp_bind_addr { -- cgit v1.2.3 From f5d258e60722142e88cb6f0f337d78bca67cf973 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 13 Jul 2016 15:08:56 -0300 Subject: sctp: reorder sctp_ulpevent and shrink msg_flags The next patch needs 8 bytes in there. sctp_ulpevent has a hole due to bad alignment; msg_flags is using 4 bytes while it actually uses only 2, so we shrink it, and iif member (4 bytes) which can be easily fetched from another place once the next patch is there, so we remove it and thus creating space for 8 bytes. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/ulpevent.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index cccdcfd14973..aa342645dbce 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -48,15 +48,15 @@ */ struct sctp_ulpevent { struct sctp_association *asoc; - __u16 stream; - __u16 ssn; - __u16 flags; + unsigned int rmem_len; __u32 ppid; __u32 tsn; __u32 cumtsn; - int msg_flags; int iif; - unsigned int rmem_len; + __u16 stream; + __u16 ssn; + __u16 flags; + __u16 msg_flags; }; /* Retrieve the skb this event sits inside of. */ -- cgit v1.2.3 From 1f45f78f8e511203f03138f2ccde3d2cf90d2cbf Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 13 Jul 2016 15:08:57 -0300 Subject: sctp: allow GSO frags to access the chunk too SCTP will try to access original IP headers on sctp_recvmsg in order to copy the addresses used. There are also other places that do similar access to IP or even SCTP headers. But after 90017accff61 ("sctp: Add GSO support") they aren't always there because they are only present in the header skb. SCTP handles the queueing of incoming data by cloning the incoming skb and limiting to only the relevant payload. This clone has its cb updated to something different and it's then queued on socket rx queue. Thus we need to fix this in two moments. For rx path, not related to socket queue yet, this patch uses a partially copied sctp_input_cb to such GSO frags. This restores the ability to access the headers for this part of the code. Regarding the socket rx queue, it removes iif member from sctp_event and also add a chunk pointer on it. With these changes we're always able to reach the headers again. The biggest change here is that now the sctp_chunk struct and the original skb are only freed after the application consumed the buffer. Note however that the original payload was already like this due to the skb cloning. For iif, SCTP's IPv4 code doesn't use it, so no change is necessary. IPv6 now can fetch it directly from original's IPv6 CB as the original skb is still accessible. In the future we probably can simplify sctp_v*_skb_iif() stuff, as sctp_v4_skb_iif() was called but it's return value not used, and now it's not even called, but such cleanup is out of scope for this change. Fixes: 90017accff61 ("sctp: Add GSO support") Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 7 +++++++ include/net/sctp/ulpevent.h | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 966c3a40039c..f6f201de6fa4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1107,6 +1107,13 @@ struct sctp_input_cb { }; #define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) +static inline const struct sk_buff *sctp_gso_headskb(const struct sk_buff *skb) +{ + const struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; + + return chunk->head_skb ? : skb; +} + /* These bind address data fields common between endpoints and associations */ struct sctp_bind_addr { diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index aa342645dbce..2c098cd7e7e2 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -48,11 +48,11 @@ */ struct sctp_ulpevent { struct sctp_association *asoc; + struct sctp_chunk *chunk; unsigned int rmem_len; __u32 ppid; __u32 tsn; __u32 cumtsn; - int iif; __u16 stream; __u16 ssn; __u16 flags; -- cgit v1.2.3 From e7487c86dc5c4a528a7dbd9dc14f453a0de61a84 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 13 Jul 2016 15:08:58 -0300 Subject: sctp: avoid identifying address family many times for a chunk Identifying address family operations during rx path is not something expensive but it's ugly to the eye to have it done multiple times, specially when we already validated it during initial rx processing. This patch takes advantage of the now shared sctp_input_cb and make the pointer to the operations readily available. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f6f201de6fa4..ce93c4b10d26 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1104,6 +1104,7 @@ struct sctp_input_cb { #endif } header; struct sctp_chunk *chunk; + struct sctp_af *af; }; #define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) -- cgit v1.2.3 From 6a551c113252ca05d0f4ca307aa6d7118d0a5e45 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 4 Jul 2016 10:29:18 +0200 Subject: fc_fip: Update to latest FC-BB-6 draft Update to latest FC-BB-6 draft to include FIP VN2VN VLAN notifications and additional flags. Signed-off-by: Hannes Reinecke Acked-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/fc/fc_fip.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/fc/fc_fip.h b/include/scsi/fc/fc_fip.h index ae25d4ab2548..9710254fd98c 100644 --- a/include/scsi/fc/fc_fip.h +++ b/include/scsi/fc/fc_fip.h @@ -22,7 +22,7 @@ /* * This version is based on: * http://www.t11.org/ftp/t11/pub/fc/bb-5/08-543v1.pdf - * and T11 FC-BB-6 10-019v4.pdf (June 2010 VN2VN proposal) + * and T11 FC-BB-6 13-091v5.pdf (December 2013 VN2VN proposal) */ #define FIP_DEF_PRI 128 /* default selection priority */ @@ -109,8 +109,9 @@ enum fip_reset_subcode { * Subcodes for FIP_OP_VLAN. */ enum fip_vlan_subcode { - FIP_SC_VL_REQ = 1, /* request */ - FIP_SC_VL_REP = 2, /* reply */ + FIP_SC_VL_REQ = 1, /* vlan request */ + FIP_SC_VL_NOTE = 2, /* vlan notification */ + FIP_SC_VL_VN2VN_NOTE = 3, /* VN2VN vlan notification */ }; /* @@ -130,6 +131,8 @@ enum fip_vn2vn_subcode { enum fip_flag { FIP_FL_FPMA = 0x8000, /* supports FPMA fabric-provided MACs */ FIP_FL_SPMA = 0x4000, /* supports SPMA server-provided MACs */ + FIP_FL_FCF = 0x0020, /* originated from a controlling FCF */ + FIP_FL_FDF = 0x0010, /* originated from an FDF */ FIP_FL_REC_OR_P2P = 0x0008, /* configured addr or point-to-point */ FIP_FL_AVAIL = 0x0004, /* available for FLOGI/ELP */ FIP_FL_SOL = 0x0002, /* this is a solicited message */ @@ -161,7 +164,9 @@ enum fip_desc_type { FIP_DT_VLAN = 14, /* vlan number */ FIP_DT_FC4F = 15, /* FC-4 features */ FIP_DT_LIMIT, /* max defined desc_type + 1 */ - FIP_DT_VENDOR_BASE = 128, /* first vendor-specific desc_type */ + FIP_DT_NON_CRITICAL = 128, /* First non-critical descriptor */ + FIP_DT_CLR_VLINKS = 128, /* Clear virtual links reason code */ + FIP_DT_VENDOR_BASE = 241, /* first vendor-specific desc_type */ }; /* @@ -258,6 +263,14 @@ enum fip_fka_flags { /* FIP_DT_FKA flags */ +/* + * FIP_DT_VLAN descriptor + */ +struct fip_vlan_desc { + struct fip_desc fd_desc; + __be16 fd_vlan; /* Note: highest 4 bytes are unused */ +} __attribute__((packed)); + /* * FIP_DT_FC4F - FC-4 features. */ -- cgit v1.2.3 From 1917d42d14b744e7298872138dd281376a83a3fe Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 4 Jul 2016 10:29:19 +0200 Subject: fcoe: use enum for fip_mode The FIP mode is independent on the FIP state machine, so use a separate enum for that instead of overloading it with state machine values. Signed-off-by: Hannes Reinecke Acked-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/libfcoe.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index c6fbbb6581d3..bcc5c3e82977 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -78,10 +78,12 @@ enum fip_state { * The mode is the state that is to be entered after link up. * It must not change after fcoe_ctlr_init() sets it. */ -#define FIP_MODE_AUTO FIP_ST_AUTO -#define FIP_MODE_NON_FIP FIP_ST_NON_FIP -#define FIP_MODE_FABRIC FIP_ST_ENABLED -#define FIP_MODE_VN2VN FIP_ST_VNMP_START +enum fip_mode { + FIP_MODE_AUTO = FIP_ST_AUTO, + FIP_MODE_NON_FIP, + FIP_MODE_FABRIC, + FIP_MODE_VN2VN, +}; /** * struct fcoe_ctlr - FCoE Controller and FIP state @@ -124,7 +126,7 @@ enum fip_state { */ struct fcoe_ctlr { enum fip_state state; - enum fip_state mode; + enum fip_mode mode; struct fc_lport *lp; struct fcoe_fcf *sel_fcf; struct list_head fcfs; @@ -311,7 +313,7 @@ struct fcoe_transport { struct list_head list; bool (*match) (struct net_device *device); int (*alloc) (struct net_device *device); - int (*create) (struct net_device *device, enum fip_state fip_mode); + int (*create) (struct net_device *device, enum fip_mode fip_mode); int (*destroy) (struct net_device *device); int (*enable) (struct net_device *device); int (*disable) (struct net_device *device); -- cgit v1.2.3 From 68350a886e7df0269a14af888dd68be2ba9203ca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 Jul 2016 13:34:55 +0900 Subject: scsi: remove current_cmnd field from struct scsi_device The field is only used by the 53c700 driver, so move it into the driver-private device data instead of having it in the common structure. Signed-off-by: Christoph Hellwig Reviewed-by: Tomas Henzl Reviewed-by: Ewan D. Milne Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index a6c346df290d..8a9563144890 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -94,7 +94,6 @@ struct scsi_device { spinlock_t list_lock; struct list_head cmd_list; /* queue of in use SCSI Command structures */ struct list_head starved_entry; - struct scsi_cmnd *current_cmnd; /* currently active command */ unsigned short queue_depth; /* How deep of a queue we want */ unsigned short max_queue_depth; /* max queue depth */ unsigned short last_queue_full_depth; /* These two are used by */ -- cgit v1.2.3 From c63cf538eb4bf6a5ffd3750366d8d56f023645a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Tue, 12 Jul 2016 22:09:26 +0200 Subject: KVM: pass struct kvm to kvm_set_routing_entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Arch-specific code will use it. Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 66b2f6159aad..60d339faa94c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1011,7 +1011,8 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); -int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); void kvm_free_irq_routing(struct kvm *kvm); -- cgit v1.2.3 From 3713131345fbea291cbd859d248e06ed77815962 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Tue, 12 Jul 2016 22:09:27 +0200 Subject: KVM: x86: add KVM_CAP_X2APIC_API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM_CAP_X2APIC_API is a capability for features related to x2APIC enablement. KVM_X2APIC_API_32BIT_FORMAT feature can be enabled to extend APIC ID in get/set ioctl and MSI addresses to 32 bits. Both are needed to support x2APIC. The feature has to be enableable and disabled by default, because get/set ioctl shifted and truncated APIC ID to 8 bits by using a non-standard protocol inspired by xAPIC and the change is not backward-compatible. Changes to MSI addresses follow the format used by interrupt remapping unit. The upper address word, that used to be 0, contains upper 24 bits of the LAPIC address in its upper 24 bits. Lower 8 bits are reserved as 0. Using the upper address word is not backward-compatible either as we didn't check that userspace zeroed the word. Reserved bits are still not explicitly checked, but non-zero data will affect LAPIC addresses, which will cause a bug. Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- include/trace/events/kvm.h | 5 +++-- include/uapi/linux/kvm.h | 3 +++ 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index f28292d73ddb..8ade3eb6c640 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -151,8 +151,9 @@ TRACE_EVENT(kvm_msi_set_irq, __entry->data = data; ), - TP_printk("dst %u vec %u (%s|%s|%s%s)", - (u8)(__entry->address >> 12), (u8)__entry->data, + TP_printk("dst %llx vec %u (%s|%s|%s%s)", + (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), + (u8)__entry->data, __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), (__entry->address & (1<<2)) ? "logical" : "physical", (__entry->data & (1<<15)) ? "level" : "edge", diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 05ebf475104c..f704403e19a0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -866,6 +866,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_ARM_PMU_V3 126 #define KVM_CAP_VCPU_ATTRIBUTES 127 #define KVM_CAP_MAX_VCPU_ID 128 +#define KVM_CAP_X2APIC_API 129 #ifdef KVM_CAP_IRQ_ROUTING @@ -1313,4 +1314,6 @@ struct kvm_assigned_msix_entry { __u16 padding[3]; }; +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From c519265f2aa348b2f1b9ecf8fbe20bb7c0fb102e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= Date: Tue, 12 Jul 2016 22:09:28 +0200 Subject: KVM: x86: add a flag to disable KVM x2apic broadcast quirk MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK as a feature flag to KVM_CAP_X2APIC_API. The quirk made KVM interpret 0xff as a broadcast even in x2APIC mode. The enableable capability is needed in order to support standard x2APIC and remain backward compatible. Signed-off-by: Radim Krčmář [Expand kvm_apic_mda comment. - Paolo] Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f704403e19a0..4f8030e5b05d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1315,5 +1315,6 @@ struct kvm_assigned_msix_entry { }; #define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From 07d36c9e84002678d75b97d2361eb6302a718359 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:03 +0000 Subject: x86/vdso: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Acked-by: Andy Lutomirski Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153332.987560239@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 386374d19987..fe056408335e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -14,6 +14,7 @@ enum cpuhp_state { CPUHP_TEARDOWN_CPU, CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, + CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 93131f7a9b5c261f9995b4a6cbd7dbbec1351d2f Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:04 +0000 Subject: irqchip/gic: Convert to hotplug state machine More or less straightforward, although this driver sports some very interesting SMP setup code. Regarding the callback ordering, this deleted comment is interesting: ... the GIC needs to be up before the ARM generic timers. That comment is half baken as the same requirement is true for perf. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Jason Cooper Cc: Linus Torvalds Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.069777215@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index fe056408335e..edc8adf26410 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -9,6 +9,7 @@ enum cpuhp_state { CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, CPUHP_AP_SCHED_STARTING, + CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 6670a6d864653859229d2e921ea193a4a677dfea Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:05 +0000 Subject: irqchip/gicv3: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Jason Cooper Cc: Linus Torvalds Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.163186301@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index edc8adf26410..d6e4a06d5020 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -10,6 +10,7 @@ enum cpuhp_state { CPUHP_AP_OFFLINE, CPUHP_AP_SCHED_STARTING, CPUHP_AP_IRQ_GIC_STARTING, + CPUHP_AP_IRQ_GICV3_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 6c034d1736384c23ea97509e36e84f35f4a9b23c Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:06 +0000 Subject: irqchip/hip04: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Jason Cooper Cc: Linus Torvalds Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.244546182@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d6e4a06d5020..62ab4ff98521 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -11,6 +11,7 @@ enum cpuhp_state { CPUHP_AP_SCHED_STARTING, CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_IRQ_GICV3_STARTING, + CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From cb5ff2d245c1023f1004eca73038b2cae87bcc6a Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:07 +0000 Subject: irqchip/armada-370-xp: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Acked-by: Jason Cooper Cc: Linus Torvalds Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.330661455@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 62ab4ff98521..3a08ab962346 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -12,6 +12,8 @@ enum cpuhp_state { CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_IRQ_GICV3_STARTING, CPUHP_AP_IRQ_HIP04_STARTING, + CPUHP_AP_IRQ_ARMADA_XP_STARTING, + CPUHP_AP_IRQ_ARMADA_CASC_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 7ca04bc277431a271061dd85f98b6da4171ad2e4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:07 +0000 Subject: irqchip/bcm2836: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Acked-by: Jason Cooper Cc: Linus Torvalds Cc: Marc Zyngier Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.416260485@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3a08ab962346..420cfcf78908 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -14,6 +14,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_HIP04_STARTING, CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_ARMADA_CASC_STARTING, + CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 7fbbaebf8cd18cca58e84837fd80c07ea8d8bd56 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:08 +0000 Subject: ARM/mvebu: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Andrew Lunn Cc: Gregory Clement Cc: Jason Cooper Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russell King Cc: Sebastian Hesselbarth Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.503198935@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 420cfcf78908..d769ec941fd3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -15,6 +15,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_ARMADA_CASC_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, + CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 00e16c3d68fce504e880f59c9bdf23b2a4759d6d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:09 +0000 Subject: perf/core: Convert to hotplug state machine Actually a nice symmetric startup/teardown pair which fits properly into the state machine concept. In the long run we should be able to invoke the startup callback for the boot CPU via the state machine and get rid of the init function which invokes it on the boot CPU. Note: This comes actually before the perf hardware callbacks. In the notifier model the hardware callbacks have a higher priority than the core callback. But that's solely for CPU offline so that hardware migration of events happens before the core is notified about the outgoing CPU. With the symetric state array model we have the following ordering: UP: core -> hardware DOWN: hardware -> core Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.587514098@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ include/linux/perf_event.h | 9 +++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d769ec941fd3..067082e3fd41 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -4,6 +4,7 @@ enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, + CPUHP_PERF_PREPARE, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -22,6 +23,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_IDLE, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, + CPUHP_AP_PERF_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1a827cecd62f..9abeb6948e70 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1354,4 +1354,13 @@ _name##_show(struct device *dev, \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) +/* Performance counter hotplug functions */ +#ifdef CONFIG_PERF_EVENTS +int perf_event_init_cpu(unsigned int cpu); +int perf_event_exit_cpu(unsigned int cpu); +#else +#define perf_event_init_cpu NULL +#define perf_event_exit_cpu NULL +#endif + #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From 95ca792c7582fde2c435f84cbe872616e3c951f6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:10 +0000 Subject: perf/x86: Convert the core to the hotplug state machine Replace the perf_notifier() install mechanism, which invokes magically the callback on the current CPU. Convert the hardware specific callbacks which are invoked from the x86 perf core to return proper error codes instead of totally pointless NOTIFY_BAD return values. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Adam Borowski Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.670720553@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 067082e3fd41..858915f40fb3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -5,6 +5,7 @@ enum cpuhp_state { CPUHP_OFFLINE, CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, + CPUHP_PERF_X86_PREPARE, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -17,6 +18,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_CASC_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, + CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, @@ -24,6 +26,7 @@ enum cpuhp_state { CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_PERF_ONLINE, + CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 1a246b9f58c6149b5a5bec081418b8ed890e0dfe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:12 +0000 Subject: perf/x86/intel/uncore: Convert to hotplug state machine Convert the notifiers to state machine states and let the core code do the setup for the already online CPUs. This notifier has a completely undocumented ordering requirement versus perf hardcoded in the notifier priority. This odering is only required for CPU down, so that hardware migration happens before the core is notified about the outgoing CPU. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.752695801@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 858915f40fb3..6f91e94c9cc9 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -6,6 +6,7 @@ enum cpuhp_state { CPUHP_CREATE_THREADS, CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, + CPUHP_PERF_X86_UNCORE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -18,6 +19,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_CASC_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, + CPUHP_AP_PERF_X86_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, @@ -27,6 +29,7 @@ enum cpuhp_state { CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, + CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 96b2bd3866a0b045330e420a2f1829ff2a3399bc Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:13 +0000 Subject: perf/x86/amd/uncore: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Chen Yucong Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.839150380@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6f91e94c9cc9..569d057cc7d5 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -7,6 +7,7 @@ enum cpuhp_state { CPUHP_PERF_PREPARE, CPUHP_PERF_X86_PREPARE, CPUHP_PERF_X86_UNCORE_PREP, + CPUHP_PERF_X86_AMD_UNCORE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -20,6 +21,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_UNCORE_STARTING, + CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, @@ -30,6 +32,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, + CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 9744f7b7b37e78d7f18050856e626aea33058787 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:14 +0000 Subject: perf/x86/amd/ibs: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Chen Yucong Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153333.921401190@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 569d057cc7d5..46720197b307 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -23,6 +23,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_UNCORE_STARTING, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, + CPUHP_AP_PERF_X86_AMD_IBS_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 8b5b773d6245138c461b3a3e242339fa50fa9c58 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:15 +0000 Subject: perf/x86/intel/rapl: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Dave Hansen Cc: Huang Rui Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Srinivas Pandruvada Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.008808086@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 46720197b307..06d77fd0fda3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -8,6 +8,7 @@ enum cpuhp_state { CPUHP_PERF_X86_PREPARE, CPUHP_PERF_X86_UNCORE_PREP, CPUHP_PERF_X86_AMD_UNCORE_PREP, + CPUHP_PERF_X86_RAPL_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -34,6 +35,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, + CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From f07048270423622a2428a9b90929c76e92777caa Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:16 +0000 Subject: perf/x86/intel/cqm: Convert Intel CQM to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Olsa Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Tony Luck Cc: Vikas Shivappa Cc: Vince Weaver Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.096956222@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 06d77fd0fda3..f9399eeba263 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -25,6 +25,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_PERF_X86_AMD_IBS_STARTING, + CPUHP_AP_PERF_X86_CQM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, @@ -36,6 +37,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_PERF_X86_RAPL_ONLINE, + CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 77c34ef1c3194bfac65883af75baf7dec9fa0d77 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:18 +0000 Subject: perf/x86/intel/cstate: Convert Intel CSTATE to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Dave Hansen Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: kbuild test robot Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.184061086@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f9399eeba263..68f4495f4988 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -26,6 +26,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_STARTING, CPUHP_AP_PERF_X86_AMD_IBS_STARTING, CPUHP_AP_PERF_X86_CQM_STARTING, + CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, @@ -38,6 +39,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_X86_CQM_ONLINE, + CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From a409f5ee2937cb15b4af485fa98b90946d9bea3a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:19 +0000 Subject: blackfin/perf: Convert hotplug notifier to state machine Install the callback via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Miao Cc: adi-buildroot-devel@lists.sourceforge.net Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.265797537@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 68f4495f4988..d54973e62366 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -9,6 +9,7 @@ enum cpuhp_state { CPUHP_PERF_X86_UNCORE_PREP, CPUHP_PERF_X86_AMD_UNCORE_PREP, CPUHP_PERF_X86_RAPL_PREP, + CPUHP_PERF_BFIN, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, -- cgit v1.2.3 From 57ecde42cc7493fb74029918d0a8f97aec854876 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:20 +0000 Subject: powerpc/perf: Convert book3s notifier to state machine callbacks Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Anshuman Khandual Cc: Benjamin Herrenschmidt Cc: Linus Torvalds Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Cc: linuxppc-dev@lists.ozlabs.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.345786236@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d54973e62366..b265e992a481 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -10,6 +10,7 @@ enum cpuhp_state { CPUHP_PERF_X86_AMD_UNCORE_PREP, CPUHP_PERF_X86_RAPL_PREP, CPUHP_PERF_BFIN, + CPUHP_PERF_POWER, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, -- cgit v1.2.3 From 4f0f8217e69a0f6ff727913aa49cb64632ff7b6a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:21 +0000 Subject: s390/perf: Convert the hotplug notifier to state machine callbacks (Counter) Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Adam Buchbinder Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Peter Zijlstra Cc: Sukadev Bhattiprolu Cc: linux-s390@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.436370635@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b265e992a481..d4e09cb0c100 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -42,6 +42,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, + CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From e3d617fe6ac7294974fc513dc5e4d8ada8080fd1 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:22 +0000 Subject: s390/perf: Convert the hotplug notifier to state machine callbacks (Sampling) Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Christian Borntraeger Cc: Heiko Carstens Cc: Hendrik Brueckner Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-s390@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.518084858@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d4e09cb0c100..fea66667d190 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -43,6 +43,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, + CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From e3cfce17d309a3c914e36ac4b4b26c30045d4274 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:23 +0000 Subject: sh/perf: Convert the hotplug notifiers to state machine callbacks Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rich Felker Cc: Yoshinori Sato Cc: linux-sh@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.597790464@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index fea66667d190..16ab41779ca7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -11,6 +11,7 @@ enum cpuhp_state { CPUHP_PERF_X86_RAPL_PREP, CPUHP_PERF_BFIN, CPUHP_PERF_POWER, + CPUHP_PERF_SUPERH, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, -- cgit v1.2.3 From 28c94843bb873196f704e9a26775b117a32a31ad Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:24 +0000 Subject: bus/arm-cci: Convert to hotplug statemachine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Andrzej Hajda Cc: Linus Torvalds Cc: Mark Rutland Cc: Olof Johansson Cc: Pawel Moll Cc: Peter Zijlstra Cc: Punit Agrawal Cc: Suzuki K Poulose Cc: Suzuki K. Poulose Cc: Thomas Gleixner Cc: Will Deacon Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.679142601@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 16ab41779ca7..0f2f727594fa 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -45,6 +45,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, + CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From fdc15a36d84eeb52f58b907f03fd8f77f5648235 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:25 +0000 Subject: bus/arm-ccn: Convert to hotplug statemachine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Arnd Bergmann Cc: Dan Carpenter Cc: Linus Torvalds Cc: Pawel Moll Cc: Peter Zijlstra Cc: Suzuki K Poulose Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.768498577@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0f2f727594fa..2ee3c0edcc2d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -46,6 +46,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, + CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, -- cgit v1.2.3 From 25a77b55e74c46c79f838a97e782a45c33588ca6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:26 +0000 Subject: xtensa/perf: Convert the hotplug notifier to state machine callbacks Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Chris Zankel Cc: Linus Torvalds Cc: Max Filippov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-xtensa@linux-xtensa.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153334.852575891@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2ee3c0edcc2d..f187c46eb7a1 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -30,6 +30,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_AMD_IBS_STARTING, CPUHP_AP_PERF_X86_CQM_STARTING, CPUHP_AP_PERF_X86_CSTATE_STARTING, + CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 89ab9cb16931873ec600a909b3a38436352e629a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:28 +0000 Subject: perf/core: Remove perf CPU notifier code All users converted to state machine callbacks. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Nicolas Iooss Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.115333381@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 2 -- include/linux/perf_event.h | 35 ----------------------------------- 2 files changed, 37 deletions(-) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 21597dcac0e2..ca2dd865a34e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -59,8 +59,6 @@ struct notifier_block; * CPU notifier priorities. */ enum { - CPU_PRI_PERF = 20, - /* bring up workqueues before normal notifiers and down after */ CPU_PRI_WORKQUEUE_UP = 5, CPU_PRI_WORKQUEUE_DOWN = -5, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 9abeb6948e70..ddd3dab0f39e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1285,41 +1285,6 @@ static inline void perf_restore_debug_store(void) { } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) -/* - * This has to have a higher priority than migration_notifier in sched/core.c. - */ -#define perf_cpu_notifier(fn) \ -do { \ - static struct notifier_block fn##_nb = \ - { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ - unsigned long cpu = smp_processor_id(); \ - unsigned long flags; \ - \ - cpu_notifier_register_begin(); \ - fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ - (void *)(unsigned long)cpu); \ - local_irq_save(flags); \ - fn(&fn##_nb, (unsigned long)CPU_STARTING, \ - (void *)(unsigned long)cpu); \ - local_irq_restore(flags); \ - fn(&fn##_nb, (unsigned long)CPU_ONLINE, \ - (void *)(unsigned long)cpu); \ - __register_cpu_notifier(&fn##_nb); \ - cpu_notifier_register_done(); \ -} while (0) - -/* - * Bare-bones version of perf_cpu_notifier(), which doesn't invoke the - * callback for already online CPUs. - */ -#define __perf_cpu_notifier(fn) \ -do { \ - static struct notifier_block fn##_nb = \ - { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ - \ - __register_cpu_notifier(&fn##_nb); \ -} while (0) - struct perf_pmu_events_attr { struct device_attribute attr; u64 id; -- cgit v1.2.3 From c6a84daa3498f269e3b506757506f762b6f56080 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Wed, 13 Jul 2016 17:16:28 +0000 Subject: perf/x86/amd/power: Convert the hotplug notifier to state machine Install the callbacks via the state machine. Signed-off-by: Anna-Maria Gleixner Cc: Borislav Petkov Cc: Huang Rui Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.027571056@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f187c46eb7a1..acfeda137df8 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -41,6 +41,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, + CPUHP_AP_PERF_X86_AMD_POWER_ONLINE, CPUHP_AP_PERF_X86_RAPL_ONLINE, CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, -- cgit v1.2.3 From 7ee681b25284782ecf380bf5ccf55f13c52fd0ce Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:29 +0000 Subject: workqueue: Convert to state machine callbacks Get rid of the prio ordering of the separate notifiers and use a proper state callback pair. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Tejun Heo Cc: Andrew Morton Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Nicolas Iooss Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Rusty Russell Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.197083890@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 9 --------- include/linux/cpuhotplug.h | 2 ++ include/linux/workqueue.h | 6 ++++++ 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index ca2dd865a34e..797d9c8e9a1b 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -55,15 +55,6 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; -/* - * CPU notifier priorities. - */ -enum { - /* bring up workqueues before normal notifiers and down after */ - CPU_PRI_WORKQUEUE_UP = 5, - CPU_PRI_WORKQUEUE_DOWN = -5, -}; - #define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ #define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ #define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index acfeda137df8..60557a9e783d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -12,6 +12,7 @@ enum cpuhp_state { CPUHP_PERF_BFIN, CPUHP_PERF_POWER, CPUHP_PERF_SUPERH, + CPUHP_WORKQUEUE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, @@ -49,6 +50,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ca73c503b92a..26cc1df280d6 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -625,4 +625,10 @@ void wq_watchdog_touch(int cpu); static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ +#ifdef CONFIG_SMP +int workqueue_prepare_cpu(unsigned int cpu); +int workqueue_online_cpu(unsigned int cpu); +int workqueue_offline_cpu(unsigned int cpu); +#endif + #endif -- cgit v1.2.3 From 48d7f6c715782a6f6d4a5535f1233b764ce6b6f2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:30 +0000 Subject: x86/hpet: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: Jan Beulich Cc: Jiang Liu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Viresh Kumar Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.279718463@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 60557a9e783d..7449081ff412 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -12,6 +12,7 @@ enum cpuhp_state { CPUHP_PERF_BFIN, CPUHP_PERF_POWER, CPUHP_PERF_SUPERH, + CPUHP_X86_HPET_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, @@ -54,6 +55,7 @@ enum cpuhp_state { CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; -- 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 ++ 1 file changed, 2 insertions(+) (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) /* -- 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 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 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); -- 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 ----------- 1 file changed, 11 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 -- 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 4e56f858bdde5cbfb70f61baddfaa56a8ed851bf Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:01 +1000 Subject: cxl: Add cxl_slot_is_supported API This extends the check that the adapter is in a CAPI capable slot so that it may be called by external users in the kernel API. This will be used by the upcoming Mellanox CX4 support, which needs to know ahead of time if the card can be switched to cxl mode so that it can leave it in PCI mode if it is not. This API takes a parameter to check if CAPP DMA mode is supported, which it currently only allows on P8NVL systems, since that mode currently has issues accessing memory < 4GB on P8, and we cannot realistically avoid that. This API does not currently check if a CAPP unit is available (i.e. not already assigned to another PHB) on P8. Doing so would be racy since it is assigned on a first come first serve basis, and so long as CAPP DMA mode is not supported on P8 we don't need this, since the only anticipated user of this API requires CAPP DMA mode. Cc: Philippe Bergheaud Signed-off-by: Ian Munsie Reviewed-by: Andrew Donnellan Reviewed-by: Frederic Barrat Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index b6d040f31f76..dd9eebba3bb6 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -24,6 +24,21 @@ * generic PCI API. This API is agnostic to the actual AFU. */ +#define CXL_SLOT_FLAG_DMA 0x1 + +/* + * Checks if the given card is in a cxl capable slot. Pass CXL_SLOT_FLAG_DMA if + * the card requires CAPP DMA mode to also check if the system supports it. + * This is intended to be used by bi-modal devices to determine if they can use + * cxl mode or if they should continue running in PCI mode. + * + * Note that this only checks if the slot is cxl capable - it does not + * currently check if the CAPP is currently available for chips where it can be + * assigned to different PHBs on a first come first serve basis (i.e. P8) + */ +bool cxl_slot_is_supported(struct pci_dev *dev, int flags); + + /* Get the AFU associated with a pci_dev */ struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev); -- cgit v1.2.3 From 62ccf2d2efefa01d0eb92cd6ecbb45ea0499fb1c Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:03 +1000 Subject: cxl: Move cxl_afu_get / cxl_afu_put to base The Mellanox CX4 uses a model where the AFU is one physical function of the device, and is used by other peer physical functions of the same device. This will require those other devices to grab a reference on the AFU when they are initialised to make sure that it does not go away during their lifetime. Move the AFU refcount functions to base.c so they can be called from the PHB code. Signed-off-by: Ian Munsie Reviewed-by: Andrew Donnellan Reviewed-by: Frederic Barrat Signed-off-by: Michael Ellerman --- include/misc/cxl-base.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/misc/cxl-base.h b/include/misc/cxl-base.h index 5ae962512fb8..f53808fa638a 100644 --- a/include/misc/cxl-base.h +++ b/include/misc/cxl-base.h @@ -36,11 +36,15 @@ static inline void cxl_ctx_put(void) atomic_dec(&cxl_use_count); } +struct cxl_afu *cxl_afu_get(struct cxl_afu *afu); +void cxl_afu_put(struct cxl_afu *afu); void cxl_slbia(struct mm_struct *mm); #else /* CONFIG_CXL_BASE */ static inline bool cxl_ctx_in_use(void) { return false; } +static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu) { return NULL; } +static inline void cxl_afu_put(struct cxl_afu *afu) {} static inline void cxl_slbia(struct mm_struct *mm) {} #endif /* CONFIG_CXL_BASE */ -- cgit v1.2.3 From a19bd79e31769626d288cc016e21a31b6f47bf6f Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:04 +1000 Subject: cxl: Allow a default context to be associated with an external pci_dev The cxl kernel API has a concept of a default context associated with each PCI device under the virtual PHB. The Mellanox CX4 will also use the cxl kernel API, but it does not use a virtual PHB - rather, the AFU appears as a physical function as a peer to the networking functions. In order to allow the kernel API to work with those networking functions, we will need to associate a default context with them as well. To this end, refactor the corresponding code to do this in vphb.c and export it so that it can be called from the PHB code. Signed-off-by: Ian Munsie Reviewed-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- include/misc/cxl-base.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/misc/cxl-base.h b/include/misc/cxl-base.h index f53808fa638a..bb7e629ae492 100644 --- a/include/misc/cxl-base.h +++ b/include/misc/cxl-base.h @@ -10,6 +10,8 @@ #ifndef _MISC_CXL_BASE_H #define _MISC_CXL_BASE_H +#include + #ifdef CONFIG_CXL_BASE #define CXL_IRQ_RANGES 4 @@ -39,6 +41,8 @@ static inline void cxl_ctx_put(void) struct cxl_afu *cxl_afu_get(struct cxl_afu *afu); void cxl_afu_put(struct cxl_afu *afu); void cxl_slbia(struct mm_struct *mm); +bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu); +void cxl_pci_disable_device(struct pci_dev *dev); #else /* CONFIG_CXL_BASE */ @@ -46,6 +50,8 @@ static inline bool cxl_ctx_in_use(void) { return false; } static inline struct cxl_afu *cxl_afu_get(struct cxl_afu *afu) { return NULL; } static inline void cxl_afu_put(struct cxl_afu *afu) {} static inline void cxl_slbia(struct mm_struct *mm) {} +static inline bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu) { return false; } +static inline void cxl_pci_disable_device(struct pci_dev *dev) {} #endif /* CONFIG_CXL_BASE */ -- cgit v1.2.3 From 79384e4b71240abf50c375eea56060b0d79c242a Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:08 +1000 Subject: cxl: Add kernel APIs to get & set the max irqs per context These APIs will be used by the Mellanox CX4 support. While they function standalone to configure existing behaviour, their primary purpose is to allow the Mellanox driver to inform the cxl driver of a hardware limitation, which will be used in a future patch. Signed-off-by: Ian Munsie Reviewed-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index dd9eebba3bb6..fc07ed47c2d8 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -166,6 +166,16 @@ void cxl_psa_unmap(void __iomem *addr); /* Get the process element for this context */ int cxl_process_element(struct cxl_context *ctx); +/* + * Limit the number of interrupts that a single context can allocate via + * cxl_start_work. If using the api with a real phb, this may be used to + * request that additional default contexts be created when allocating + * interrupts via pci_enable_msix_range. These will be set to the same running + * state as the default context, and if that is running it will reuse the + * parameters previously passed to cxl_start_context for the default context. + */ +int cxl_set_max_irqs_per_process(struct pci_dev *dev, int irqs); +int cxl_get_max_irqs_per_process(struct pci_dev *dev); /* * These calls allow drivers to create their own file descriptors and make them -- cgit v1.2.3 From cbce0917e2e47d4bf5aa3b5fd6b1247f33e1a126 Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:09 +1000 Subject: cxl: Add preliminary workaround for CX4 interrupt limitation The Mellanox CX4 has a hardware limitation where only 4 bits of the AFU interrupt number can be passed to the XSL when sending an interrupt, limiting it to only 15 interrupts per context (AFU interrupt number 0 is invalid). In order to overcome this, we will allocate additional contexts linked to the default context as extra address space for the extra interrupts - this will be implemented in the next patch. This patch adds the preliminary support to allow this, by way of adding a linked list in the context structure that we use to keep track of the contexts dedicated to interrupts, and an API to simultaneously iterate over the related context structures, AFU interrupt numbers and hardware interrupt numbers. The point of using a single API to iterate these is to hide some of the details of the iteration from external code, and to reduce the number of APIs that need to be exported via base.c to allow built in code to call. Signed-off-by: Ian Munsie Reviewed-by: Frederic Barrat Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index fc07ed47c2d8..6c52cbcdfd79 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -177,6 +177,15 @@ int cxl_process_element(struct cxl_context *ctx); int cxl_set_max_irqs_per_process(struct pci_dev *dev, int irqs); int cxl_get_max_irqs_per_process(struct pci_dev *dev); +/* + * Use to simultaneously iterate over hardware interrupt numbers, contexts and + * afu interrupt numbers allocated for the device via pci_enable_msix_range and + * is a useful convenience function when working with hardware that has + * limitations on the number of interrupts per process. *ctx and *afu_irq + * should be NULL and 0 to start the iteration. + */ +int cxl_next_msi_hwirq(struct pci_dev *pdev, struct cxl_context **ctx, int *afu_irq); + /* * These calls allow drivers to create their own file descriptors and make them * identical to the cxl file descriptor user API. An example use case: -- cgit v1.2.3 From a2f67d5ee8d950caaa7a6144cf0bfb256500b73e Mon Sep 17 00:00:00 2001 From: Ian Munsie Date: Thu, 14 Jul 2016 07:17:10 +1000 Subject: cxl: Add support for interrupts on the Mellanox CX4 The Mellanox CX4 in cxl mode uses a hybrid interrupt model, where interrupts are routed from the networking hardware to the XSL using the MSIX table, and from there will be transformed back into an MSIX interrupt using the cxl style interrupts (i.e. using IVTE entries and ranges to map a PE and AFU interrupt number to an MSIX address). We want to hide the implementation details of cxl interrupts as much as possible. To this end, we use a special version of the MSI setup & teardown routines in the PHB while in cxl mode to allocate the cxl interrupts and configure the IVTE entries in the process element. This function does not configure the MSIX table - the CX4 card uses a custom format in that table and it would not be appropriate to fill that out in generic code. The rest of the functionality is similar to the "Full MSI-X mode" described in the CAIA, and this could be easily extended to support other adapters that use that mode in the future. The interrupts will be associated with the default context. If the maximum number of interrupts per context has been limited (e.g. by the mlx5 driver), it will automatically allocate additional kernel contexts to associate extra interrupts as required. These contexts will be started using the same WED that was used to start the default context. Signed-off-by: Ian Munsie Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- include/misc/cxl-base.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/misc/cxl-base.h b/include/misc/cxl-base.h index bb7e629ae492..b2ebc91fe09a 100644 --- a/include/misc/cxl-base.h +++ b/include/misc/cxl-base.h @@ -43,6 +43,8 @@ void cxl_afu_put(struct cxl_afu *afu); void cxl_slbia(struct mm_struct *mm); bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu); void cxl_pci_disable_device(struct pci_dev *dev); +int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); +void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev); #else /* CONFIG_CXL_BASE */ @@ -52,6 +54,8 @@ static inline void cxl_afu_put(struct cxl_afu *afu) {} static inline void cxl_slbia(struct mm_struct *mm) {} static inline bool cxl_pci_associate_default_context(struct pci_dev *dev, struct cxl_afu *afu) { return false; } static inline void cxl_pci_disable_device(struct pci_dev *dev) {} +static inline int cxl_cx4_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { return -ENODEV; } +static inline void cxl_cx4_teardown_msi_irqs(struct pci_dev *pdev) {} #endif /* CONFIG_CXL_BASE */ -- cgit v1.2.3 From b0b5e5918ad1babfd1d43d98c7281926a7b57b9f Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Thu, 14 Jul 2016 07:17:14 +1000 Subject: cxl: Add cxl_check_and_switch_mode() API to switch bi-modal cards Add a new API, cxl_check_and_switch_mode() to allow for switching of bi-modal CAPI cards, such as the Mellanox CX-4 network card. When a driver requests to switch a card to CAPI mode, use PCI hotplug infrastructure to remove all PCI devices underneath the slot. We then write an updated mode control register to the CAPI VSEC, hot reset the card, and reprobe the card. As the card may present a different set of PCI devices after the mode switch, use the infrastructure provided by the pnv_php driver and the OPAL PCI slot management facilities to ensure that: * the old devices are removed from both the OPAL and Linux device trees * the new devices are probed by OPAL and added to the OPAL device tree * the new devices are added to the Linux device tree and probed through the regular PCI device probe path As such, introduce a new option, CONFIG_CXL_BIMODAL, with a dependency on the pnv_php driver. Refactor existing code that touches the mode control register in the regular single mode case into a new function, setup_cxl_protocol_area(). Co-authored-by: Ian Munsie Cc: Gavin Shan Signed-off-by: Andrew Donnellan Signed-off-by: Ian Munsie Reviewed-by: Gavin Shan Signed-off-by: Michael Ellerman --- include/misc/cxl.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/misc/cxl.h b/include/misc/cxl.h index 6c52cbcdfd79..480d50a0b8ba 100644 --- a/include/misc/cxl.h +++ b/include/misc/cxl.h @@ -39,6 +39,31 @@ bool cxl_slot_is_supported(struct pci_dev *dev, int flags); +#define CXL_BIMODE_CXL 1 +#define CXL_BIMODE_PCI 2 + +/* + * Check the mode that the given bi-modal CXL adapter is currently in and + * change it if necessary. This does not apply to AFU drivers. + * + * If the mode matches the requested mode this function will return 0 - if the + * driver was expecting the generic CXL driver to have bound to the adapter and + * it gets this return value it should fail the probe function to give the CXL + * driver a chance to probe it. + * + * If the mode does not match it will start a background task to unplug the + * device from Linux and switch its mode, and will return -EBUSY. At this + * point the calling driver should make sure it has released the device and + * fail its probe function. + * + * The offset of the CXL VSEC can be provided to this function. If 0 is passed, + * this function will search for a CXL VSEC with ID 0x1280 and return -ENODEV + * if it is not found. + */ +#ifdef CONFIG_CXL_BIMODAL +int cxl_check_and_switch_mode(struct pci_dev *dev, int mode, int vsec); +#endif + /* Get the AFU associated with a pci_dev */ struct cxl_afu *cxl_pci_to_afu(struct pci_dev *dev); -- cgit v1.2.3 From 55d38d060e999ca1a3ea6eb132105a0301e4cd04 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Mon, 6 Jun 2016 14:26:22 +0300 Subject: i2c: core: Add function for finding the bus speed from ACPI ACPI 5 specification doesn't have property for the I2C bus speed but I2cSerialBus resource descriptors which define each controller-slave connection define the maximum speed supported by that connection. Thus finding the maximum safe speed for the bus is to walk all I2cSerialBus resources that are associated to I2C controller and use the speed of slowest connection. Add function i2c_acpi_find_bus_speed() to the i2c-core that adapter drivers can call prior registering itself to core. This implies two-step walk through the I2cSerialBus resources: call to i2c_acpi_find_bus_speed() does the first scan and finds the safe bus speed that adapter drivers can set up. Adapter driver registration does the second scan when i2c-core creates the I2C slaves by calling the i2c_acpi_register_devices(). In that way the bus speed is set in case slave device probe gets called during registration and does communication. Implement this by reusing the existing ACPI I2C walk routines in the i2c-core. Extend them so that slowest connection speed is saved during the walk and I2C slaves are registered only when calling through the i2c_acpi_register_devices() with the i2c_adapter pointer. Signed-off-by: Jarkko Nikula Reviewed-by: Andy Shevchenko Acked-by: Mika Westerberg Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index fffdc270ca18..5cde08719fb6 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -766,4 +766,13 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node } #endif /* CONFIG_OF */ +#if IS_ENABLED(CONFIG_ACPI) +u32 i2c_acpi_find_bus_speed(struct device *dev); +#else +static inline u32 i2c_acpi_find_bus_speed(struct device *dev) +{ + return 0; +} +#endif /* CONFIG_ACPI */ + #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From b1c04e80c6da5f5d3d4778ede23c59666135fdeb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 14 Jul 2016 09:05:42 +0900 Subject: libata: return boolean values from ata_is_* This way we don't have to worry about the exact bit postition of the test to leak out and any crazy propagation effects in the callers. Suggested-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/libata.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index d15c19e331d1..4e5a09c6dc10 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1063,32 +1063,32 @@ static inline unsigned int ata_prot_flags(u8 prot) return 0; } -static inline int ata_is_atapi(u8 prot) +static inline bool ata_is_atapi(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; } -static inline int ata_is_nodata(u8 prot) +static inline bool ata_is_nodata(u8 prot) { return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); } -static inline int ata_is_pio(u8 prot) +static inline bool ata_is_pio(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; } -static inline int ata_is_dma(u8 prot) +static inline bool ata_is_dma(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; } -static inline int ata_is_ncq(u8 prot) +static inline bool ata_is_ncq(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; } -static inline int ata_is_data(u8 prot) +static inline bool ata_is_data(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; } @@ -1407,7 +1407,7 @@ static inline bool sata_pmp_attached(struct ata_port *ap) return ap->nr_pmp_links != 0; } -static inline int ata_is_host_link(const struct ata_link *link) +static inline bool ata_is_host_link(const struct ata_link *link) { return link == &link->ap->link || link == link->ap->slave_link; } @@ -1422,7 +1422,7 @@ static inline bool sata_pmp_attached(struct ata_port *ap) return false; } -static inline int ata_is_host_link(const struct ata_link *link) +static inline bool ata_is_host_link(const struct ata_link *link) { return 1; } -- cgit v1.2.3 From 29cc6679076a00a6ce193004dcf2d14ae7c428a5 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 14 Jul 2016 10:32:37 +0300 Subject: net/mlx5: Store counters in rbtree instead of list In order to use bulk counters, we need to have counters sorted by id. Signed-off-by: Amir Vadai Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 81e8396574f4..a041b99fceac 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -469,7 +469,7 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct list_head list; + struct rb_root counters; struct list_head addlist; /* protect addlist add/splice operations */ spinlock_t addlist_lock; -- cgit v1.2.3 From a351a1b03bf169f77891060be30036ef71cbe618 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Thu, 14 Jul 2016 10:32:38 +0300 Subject: net/mlx5: Introduce bulk reading of flow counters This commit utilize the ability of ConnectX-4 to bulk read flow counters. Few bulk counter queries could be done instead of issuing thousands of firmware commands per second to get statistics of all flows set to HW, such as those programmed when we offload tc filters. Counters are stored sorted by hardware id, and queried in blocks (id + number of counters). Due to hardware requirement, start of block and number of counters in a block must be four aligned. Reviewed-by: Or Gerlitz Signed-off-by: Amir Vadai Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 152421cc6f44..d671e4e8e7db 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -893,7 +893,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_330[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_at_340[0x20]; + u8 reserved_at_340[0x8]; + u8 log_max_flow_counter_bulk[0x8]; + u8 max_flow_counter[0x10]; + u8 reserved_at_360[0x3]; u8 log_max_rq[0x5]; @@ -980,7 +983,8 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 reserved_at_0[0x10]; + u8 clear[0x1]; + u8 num_of_counters[0xf]; u8 flow_counter_id[0x10]; u8 reserved_at_20[0x20]; -- cgit v1.2.3 From 8438884d4ab423161b974854ebb90c08219dd678 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 14 Jul 2016 10:32:43 +0300 Subject: net/switchdev: Export the same parent ID service function This helper serves to know if two switchdev port netdevices belong to the same HW ASIC, e.g to figure out if forwarding offload is possible between them. Signed-off-by: Or Gerlitz Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/net/switchdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 985619a59323..9023e3e3be0b 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -227,6 +227,8 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); +bool switchdev_port_same_parent_id(struct net_device *a, + struct net_device *b); #else static inline void switchdev_deferred_process(void) @@ -351,6 +353,12 @@ static inline void switchdev_port_fwd_mark_set(struct net_device *dev, { } +static inline bool switchdev_port_same_parent_id(struct net_device *a, + struct net_device *b) +{ + return false; +} + #endif #endif /* _LINUX_SWITCHDEV_H_ */ -- cgit v1.2.3 From e0c3f92a08f3e0a95024d0d032564fdc1ee96f54 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 12 Jul 2016 00:52:43 +0300 Subject: ARM: dts: r8a7792: remove ADSP clock Simon Horman told me that R8A7792 has ADSP clock based on an incorrect table in the most recent R-Car gen2 manual. But when I received that manual I discovered that this is false: R8A7792 is the only Gen 2 SoC that doesn't have ADSP at all. Accordingly remove the ADSP clock from DT for the r8a7792. Signed-off-by: Sergei Shtylyov Reviewed-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- include/dt-bindings/clock/r8a7792-clock.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/r8a7792-clock.h b/include/dt-bindings/clock/r8a7792-clock.h index 89a5155913f6..9a8b392ceb00 100644 --- a/include/dt-bindings/clock/r8a7792-clock.h +++ b/include/dt-bindings/clock/r8a7792-clock.h @@ -18,7 +18,6 @@ #define R8A7792_CLK_LB 4 #define R8A7792_CLK_QSPI 5 #define R8A7792_CLK_Z 6 -#define R8A7792_CLK_ADSP 7 /* MSTP0 */ #define R8A7792_CLK_MSIOF0 0 -- cgit v1.2.3 From 0e1824c98a0ffd7fd9ffb2a3da01ec49ff1348a2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 14 Jul 2016 11:37:28 +0200 Subject: tracing: change owner name to driver name for devlink hwmsg tracepoint Turned on that driver->owner which is struct module is not available when modules are disabled. Better to depend on a driver name which is always available. Reported-by: Randy Dunlap Fixes: e5224f0fe2 ("devlink: add hardware messages tracing facility") Signed-off-by: Jiri Pirko Acked-by: Randy Dunlap Acked-by: Steven Rostedt Signed-off-by: David S. Miller --- include/trace/events/devlink.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 333c32ac9bfa..77dce71df42a 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -22,7 +22,7 @@ TRACE_EVENT(devlink_hwmsg, TP_STRUCT__entry( __string(bus_name, devlink->dev->bus->name) __string(dev_name, dev_name(devlink->dev)) - __string(owner_name, devlink->dev->driver->owner->name) + __string(driver_name, devlink->dev->driver->name) __field(bool, incoming) __field(unsigned long, type) __dynamic_array(u8, buf, len) @@ -32,16 +32,16 @@ TRACE_EVENT(devlink_hwmsg, TP_fast_assign( __assign_str(bus_name, devlink->dev->bus->name); __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(owner_name, devlink->dev->driver->owner->name); + __assign_str(driver_name, devlink->dev->driver->name); __entry->incoming = incoming; __entry->type = type; memcpy(__get_dynamic_array(buf), buf, len); __entry->len = len; ), - TP_printk("bus_name=%s dev_name=%s owner_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%lu", + TP_printk("bus_name=%s dev_name=%s driver_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%lu", __get_str(bus_name), __get_str(dev_name), - __get_str(owner_name), __entry->incoming, __entry->type, + __get_str(driver_name), __entry->incoming, __entry->type, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); -- cgit v1.2.3 From caeccd5180930eb8586771bb1935f4f2e456a8e8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Jul 2016 11:37:29 +0200 Subject: devlink: fix trace format string Including devlink.h on ARM and probably other 32-bit architectures results in a harmless warning: In file included from ../include/trace/define_trace.h:95:0, from ../include/trace/events/devlink.h:51, from ../net/core/devlink.c:30: include/trace/events/devlink.h: In function 'trace_raw_output_devlink_hwmsg': include/trace/events/devlink.h:42:12: error: format '%lu' expects argument of type 'long unsigned int', but argument 10 has type 'size_t {aka unsigned int}' [-Werror=format=] The correct format string for 'size_t' is %zu, not %lu, this works on all architectures. Signed-off-by: Arnd Bergmann Fixes: e5224f0fe2ac ("devlink: add hardware messages tracing facility") Signed-off-by: Jiri Pirko Acked-by: Randy Dunlap Signed-off-by: David S. Miller --- include/trace/events/devlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 77dce71df42a..09f1df228f2c 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -39,7 +39,7 @@ TRACE_EVENT(devlink_hwmsg, __entry->len = len; ), - TP_printk("bus_name=%s dev_name=%s driver_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%lu", + TP_printk("bus_name=%s dev_name=%s driver_name=%s incoming=%d type=%lu buf=0x[%*phD] len=%zu", __get_str(bus_name), __get_str(dev_name), __get_str(driver_name), __entry->incoming, __entry->type, (int) __entry->len, __get_dynamic_array(buf), __entry->len) -- cgit v1.2.3 From 251a5fd64b720a0646eddb8c54f5e9ddba066e72 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:33 +0000 Subject: x86/kvm/kvmclock: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. We assumed that the priority ordering was ment to invoke the online callback as the last step. In the original code this also invoked the down prepare callback as the last step. With the symmetric state machine the down prepare callback is now the first step. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Acked-by: Paolo Bonzini Cc: Gleb Natapov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.542880859@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7449081ff412..8c190a85af6e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -56,6 +56,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, + CPUHP_AP_X86_KVM_CLK_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; -- cgit v1.2.3 From 148b9e2abea6f50e4620e4ac0683b4913c4364c0 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:34 +0000 Subject: x86/apb_timer: Convert to hotplug state machine Install the callbacks via the state machine. There is no setup just one teardown callback. Remove the silly comment about the workqueue up dependency. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.625342983@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8c190a85af6e..3e719ba44fbe 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -13,6 +13,7 @@ enum cpuhp_state { CPUHP_PERF_POWER, CPUHP_PERF_SUPERH, CPUHP_X86_HPET_DEAD, + CPUHP_X86_APB_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, -- cgit v1.2.3 From e5b61bafe70477e05e1dce0d6ca4ec181e23cb2a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:35 +0000 Subject: arm: Convert VFP hotplug notifiers to state machine Straight forward conversion plus commentary why code which is executed in hotplug callbacks needs to be invoked before installing them. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russell King Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.713612993@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3e719ba44fbe..4c63cb30aee6 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -34,6 +34,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_STARTING, CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, + CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 7d88eb695a1f5f67820e02999b949d5cfa080442 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:36 +0000 Subject: arm/perf: Convert to hotplug state machine Straight forward conversion w/o bells and whistles. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Cc: Mark Rutland Cc: Peter Zijlstra Cc: Will Deacon Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.794097159@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + include/linux/perf/arm_pmu.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4c63cb30aee6..a5b6a6526af8 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -35,6 +35,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_ARM_VFP_STARTING, + CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index d28ac05c7f92..e6ed34eb2b2b 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -109,7 +109,6 @@ struct arm_pmu { DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; - struct notifier_block hotplug_nb; struct notifier_block cpu_pm_nb; }; -- cgit v1.2.3 From 8c18b2d2d0881b116ea52498c6d624c0a71e1fdc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:16:37 +0000 Subject: virt: Convert kvm hotplug to state machine Install the callbacks via the state machine. The core won't invoke the callbacks on already online CPUs. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Paolo Bonzini Cc: Gleb Natapov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Radim Krcmar Cc: kvm@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153335.886159080@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a5b6a6526af8..5423997c94f7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -36,6 +36,7 @@ enum cpuhp_state { CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 7e86e8bd8dd67649d176e08d8dfb90039f0a1e98 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:39 +0000 Subject: clocksource/arm_arch_timer: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.048259040@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5423997c94f7..f0524cd70e9b 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -36,6 +36,7 @@ enum cpuhp_state { CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 00c1d17aab513d3b8117fb84644eba39434b33e4 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:41 +0000 Subject: clocksource/dummy_timer: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.130385842@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f0524cd70e9b..81035613a836 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -37,6 +37,7 @@ enum cpuhp_state { CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, + CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 31e8e5db8849e4c7084dd5bce7b7d96d2fb14b8b Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:42 +0000 Subject: clocksource/metag: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: James Hogan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-metag@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.215137642@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 81035613a836..afba3b19006c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -38,6 +38,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, + CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From b04041655d0cf84b77802cb0b4517e672df04f01 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:43 +0000 Subject: clocksource/qcom-timer: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.295486558@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index afba3b19006c..d74d15a028e4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -39,6 +39,7 @@ enum cpuhp_state { CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_METAG_TIMER_STARTING, + CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 2dab90932fd08f101a45acc0495ccd77b869da5d Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:44 +0000 Subject: clocksource/mips-gic: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.380737946@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d74d15a028e4..456e3d93272c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -40,6 +40,7 @@ enum cpuhp_state { CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, + CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 911a359de96d5e9d24f50c74a48c6f3cf061539a Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:45 +0000 Subject: leds/trigger/cpu: Convert to hotplug state machine This is a straightforward conversion. We place this callback last in the list so that the LED illuminates only after a successful bring up sequence. ( NOTE: The patch adds a FIXME question about the callback used, this question should probably be revisited later on.) Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Jacek Anaszewski Cc: Linus Torvalds Cc: Linus Walleij Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Richard Purdie Cc: Thomas Gleixner Cc: linux-leds@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.465496902@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 456e3d93272c..24f56e290003 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -42,6 +42,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, + CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 42ec50b5f257b19bd5653c40933b0803d5c4179a Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:46 +0000 Subject: arm/kvm/vgic: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. The VGIC callback is run after KVM's main callback since it reflects the makefile order. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Christoffer Dall Cc: Gleb Natapov Cc: Linus Torvalds Cc: Marc Zyngier Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: kvmarm@lists.cs.columbia.edu Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.546953286@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 24f56e290003..ff37caccafce 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -42,6 +42,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, + CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From b3c9950a5c75983c0a2fcc93760f53ba52da3c85 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:47 +0000 Subject: arm/kvm/arch_timer: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Christoffer Dall Cc: Gleb Natapov Cc: Linus Torvalds Cc: Marc Zyngier Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: kvmarm@lists.cs.columbia.edu Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.634155707@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ff37caccafce..88986c979b0f 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -43,6 +43,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, + CPUHP_AP_KVM_ARM_TIMER_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 04d045a681122c806e4f17754ed48e2b19af5d80 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:49 +0000 Subject: metag/perf: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: James Hogan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-metag@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.717395164@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 88986c979b0f..990052c9a2f8 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -34,6 +34,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_STARTING, CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, + CPUHP_AP_PERF_METAG_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, -- cgit v1.2.3 From 9eeb2264775f0b60fcff3d186bf54c90b0191650 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:50 +0000 Subject: arm/l2c: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Brad Mouring Cc: Linus Torvalds Cc: Linus Walleij Cc: Marek Szyprowski Cc: Peter Zijlstra Cc: Rob Herring Cc: Russell King Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.801270887@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 990052c9a2f8..2057e64e4876 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -37,6 +37,7 @@ enum cpuhp_state { CPUHP_AP_PERF_METAG_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_METAG_TIMER_STARTING, -- cgit v1.2.3 From 26b8768868c090151aa8c337773d429e0d5ca727 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:51 +0000 Subject: arm/twd: Convert to hotplug state machine Install the callbacks via the state machine. The callbacks won't be invoked on already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Eric Anholt Cc: Felipe Balbi Cc: Heiko Stuebner Cc: Linus Torvalds Cc: Marc Gonzalez Cc: Peter Zijlstra Cc: Russell King Cc: Thomas Gleixner Cc: Vineet Gupta Cc: Viresh Kumar Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153336.881124821@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 2057e64e4876..ad48881ba02d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -40,6 +40,7 @@ enum cpuhp_state { CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, + CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, -- cgit v1.2.3 From 4761adb6f49048cddd65553a71ea2354b2a838be Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:52 +0000 Subject: arm/xen: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. The get_cpu() in xen_starting_cpu() boils down to preempt_disable() since we already know the CPU we run on. Disabling preemption shouldn't be required here from what I see since it we don't switch CPUs while invoking the function. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Reviewed-by: Stefano Stabellini Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Russell King Cc: Stefano Stabellini Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/20160713153336.971559670@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ad48881ba02d..4c02b52dc77f 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -47,6 +47,7 @@ enum cpuhp_state { CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_KVM_ARM_TIMER_STARTING, + CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 65264e3bc3d479a87a3a9dbc6f3daee6439ce5c0 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:53 +0000 Subject: MIPS/Loongson-3: Convert oprofile to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Ralf Baechle Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Robert Richter Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Cc: oprofile-list@lists.sf.net Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.054827168@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4c02b52dc77f..ad26e353a5c0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -35,6 +35,7 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CSTATE_STARTING, CPUHP_AP_PERF_XTENSA_STARTING, CPUHP_AP_PERF_METAG_STARTING, + CPUHP_AP_MIPS_OP_LOONGSON3_STARTING, CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, -- cgit v1.2.3 From 2b5283d12f678391616718229aeabeca47497db5 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:54 +0000 Subject: hwtracing/coresight-etm3x: Convert to hotplug state machine This driver has an asymmetry of ONLINE code without any corresponding tear down code. Otherwise, this is a straightforward conversion. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Acked-by: Mathieu Poirier Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.147128995@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ad26e353a5c0..576ad23dd50d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -49,6 +49,7 @@ enum cpuhp_state { CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_KVM_ARM_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, + CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 58eb457be0283d9bfc3024eeefea33715391443f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:55 +0000 Subject: hwtracing/coresight-etm4x: Convert to hotplug state machine This driver has an asymmetry of ONLINE code without any corresponding tear down code. Otherwise, this is a straightforward conversion. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Acked-by: Mathieu Poirier Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.228918408@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 576ad23dd50d..6cede6293806 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -50,6 +50,7 @@ enum cpuhp_state { CPUHP_AP_KVM_ARM_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, + CPUHP_AP_ARM_CORESIGHT4_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From 27c01a8c73e15b2135b96a1866e1dbeb797e4806 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:56 +0000 Subject: arm64/armv8 deprecated: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: James Morse Cc: Jisheng Zhang Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Shengjiu Wang Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.311115906@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6cede6293806..c5b96d0b6fbf 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -51,6 +51,7 @@ enum cpuhp_state { CPUHP_AP_ARM_XEN_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT4_STARTING, + CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, -- cgit v1.2.3 From ae6a8a2ed721ecdbc15d32b2089af5ed2190adc7 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:57 +0000 Subject: x86/tboot: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Gang Wei Cc: Linus Torvalds Cc: Ning Sun Cc: Peter Zijlstra Cc: Richard L Maliszewski Cc: Shane Wang Cc: Thomas Gleixner Cc: rt@linutronix.de Cc: tboot-devel@lists.sourceforge.net Link: http://lkml.kernel.org/r/20160713153337.400227322@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c5b96d0b6fbf..070cc7f28862 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -53,6 +53,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT4_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_LEDTRIG_STARTING, + CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, -- cgit v1.2.3 From 27590dc17b34aedc4f3e14bd107ee59b9db9b0a6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 15 Jul 2016 10:41:04 +0200 Subject: hrtimer: Convert to hotplug state machine Split out the clockevents callbacks instead of piggybacking them on hrtimers. This gets rid of a POST_DEAD user. See commit: 54e88fad223c ("sched: Make sure timers have migrated before killing the migration_thread") We just move the callback state to the proper place in the state machine. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Rusty Russell Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.485419196@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + include/linux/hrtimer.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 070cc7f28862..04ecc55009ed 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -15,6 +15,7 @@ enum cpuhp_state { CPUHP_X86_HPET_DEAD, CPUHP_X86_APB_DEAD, CPUHP_WORKQUEUE_PREP, + CPUHP_HRTIMERS_PREPARE, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index c98c6539e2c2..5e00f80b1535 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -494,4 +494,11 @@ extern void __init hrtimers_init(void); /* Show pending timers: */ extern void sysrq_timer_list_show(void); +int hrtimers_prepare_cpu(unsigned int cpu); +#ifdef CONFIG_HOTPLUG_CPU +int hrtimers_dead_cpu(unsigned int cpu); +#else +#define hrtimers_dead_cpu NULL +#endif + #endif -- cgit v1.2.3 From 24f73b99716a9cd8cbb345c41ced6b3b5ed94006 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:16:59 +0000 Subject: timers/core: Convert to hotplug state machine When tearing down, call timers_dead_cpu() before notify_dead(). There is a hidden dependency between: - timers - block multiqueue - rcutree If timers_dead_cpu() comes later than blk_mq_queue_reinit_notify() that latter function causes a RCU stall. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: John Stultz Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.566790058@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + include/linux/timer.h | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 04ecc55009ed..15d46d2a1d16 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -16,6 +16,7 @@ enum cpuhp_state { CPUHP_X86_APB_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_HRTIMERS_PREPARE, + CPUHP_TIMERS_DEAD, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, diff --git a/include/linux/timer.h b/include/linux/timer.h index 4419506b564e..51d601f192d4 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -273,4 +273,10 @@ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu); unsigned long round_jiffies_up(unsigned long j); unsigned long round_jiffies_up_relative(unsigned long j); +#ifdef CONFIG_HOTPLUG_CPU +int timers_dead_cpu(unsigned int cpu); +#else +#define timers_dead_cpu NULL +#endif + #endif -- cgit v1.2.3 From e722d8daafb974b9ad1bbaf42f384a5ea5929f5f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:16:59 +0000 Subject: profile: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. A lot of code is removed because the for-loop is used and create_hash_tables() is removed since its purpose is covered by the startup / teardown hooks. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Andrew Morton Cc: Arnd Bergmann Cc: Linus Torvalds Cc: Mel Gorman Cc: Michal Hocko Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.649867675@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 15d46d2a1d16..ace5ad0fc3ec 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -16,6 +16,7 @@ enum cpuhp_state { CPUHP_X86_APB_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_HRTIMERS_PREPARE, + CPUHP_PROFILE_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, -- cgit v1.2.3 From 6b2c28471de550308784560206c3365e5179d42f Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 13 Jul 2016 17:17:00 +0000 Subject: x86/x2apic: Convert to CPU hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Anna-Maria Gleixner Cc: Len Brown Cc: Linus Torvalds Cc: Mathias Krause Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.736898691@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ace5ad0fc3ec..78170827a776 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -17,6 +17,7 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_HRTIMERS_PREPARE, CPUHP_PROFILE_PREPARE, + CPUHP_X2APIC_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, -- cgit v1.2.3 From 31487f8328f20fdb302430b020a5d6e8446c1971 Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Wed, 13 Jul 2016 17:17:01 +0000 Subject: smp/cfd: Convert core to hotplug state machine Install the callbacks via the state machine. They are installed at runtime so smpcfd_prepare_cpu() needs to be invoked by the boot-CPU. Signed-off-by: Richard Weinberger [ Added the dropped CPU dying case back in. ] Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Mel Gorman Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.818376366@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 ++ include/linux/smp.h | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 78170827a776..b5cf01ace71b 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -18,6 +18,7 @@ enum cpuhp_state { CPUHP_HRTIMERS_PREPARE, CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, + CPUHP_SMPCFD_PREPARE, CPUHP_TIMERS_DEAD, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, @@ -57,6 +58,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT4_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_LEDTRIG_STARTING, + CPUHP_AP_SMPCFD_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_NOTIFY_STARTING, CPUHP_AP_ONLINE, diff --git a/include/linux/smp.h b/include/linux/smp.h index c4414074bd88..eccae4690f41 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -196,4 +196,9 @@ extern void arch_enable_nonboot_cpus_end(void); void smp_setup_processor_id(void); +/* SMP core functions */ +int smpcfd_prepare_cpu(unsigned int cpu); +int smpcfd_dead_cpu(unsigned int cpu); +int smpcfd_dying_cpu(unsigned int cpu); + #endif /* __LINUX_SMP_H */ -- cgit v1.2.3 From 15d7e3d349a329ad48a29c3a818eacd1c3f7e3ef Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Wed, 13 Jul 2016 17:17:02 +0000 Subject: KVM/arm/arm64/vgic-new: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Anna-Maria Gleixner Cc: Andre Przywara Cc: Christoffer Dall Cc: Eric Auger Cc: Linus Torvalds Cc: Marc Zyngier Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krcmar Cc: Thomas Gleixner Cc: kvm@vger.kernel.org Cc: kvmarm@lists.cs.columbia.edu Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.900484868@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b5cf01ace71b..544b5563720e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -51,6 +51,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, + CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, CPUHP_AP_KVM_ARM_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, -- cgit v1.2.3 From 4df8374254ea9294dfe4b8c447a1b7eddc543dbf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Jul 2016 17:17:03 +0000 Subject: rcu: Convert rcutree to hotplug state machine Straight forward conversion to the state machine. Though the question arises whether this needs really all these state transitions to work. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153337.982013161@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 3 +++ include/linux/rcutiny.h | 7 +++++++ include/linux/rcutree.h | 7 +++++++ 3 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 544b5563720e..201a2e23bc49 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -20,11 +20,13 @@ enum cpuhp_state { CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_TIMERS_DEAD, + CPUHP_RCUTREE_PREP, CPUHP_NOTIFY_PREPARE, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, CPUHP_AP_SCHED_STARTING, + CPUHP_AP_RCUTREE_DYING, CPUHP_AP_IRQ_GIC_STARTING, CPUHP_AP_IRQ_GICV3_STARTING, CPUHP_AP_IRQ_HIP04_STARTING, @@ -80,6 +82,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, + CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_NOTIFY_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 93aea75029fb..ac81e4063b40 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -243,4 +243,11 @@ static inline void rcu_all_qs(void) barrier(); /* Avoid RCU read-side critical sections leaking across. */ } +/* RCUtree hotplug events */ +#define rcutree_prepare_cpu NULL +#define rcutree_online_cpu NULL +#define rcutree_offline_cpu NULL +#define rcutree_dead_cpu NULL +#define rcutree_dying_cpu NULL + #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 5043cb823fb2..63a4e4cf40a5 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -111,4 +111,11 @@ bool rcu_is_watching(void); void rcu_all_qs(void); +/* RCUtree hotplug events */ +int rcutree_prepare_cpu(unsigned int cpu); +int rcutree_online_cpu(unsigned int cpu); +int rcutree_offline_cpu(unsigned int cpu); +int rcutree_dead_cpu(unsigned int cpu); +int rcutree_dying_cpu(unsigned int cpu); + #endif /* __LINUX_RCUTREE_H */ -- cgit v1.2.3 From b8a12296ac812f829bd9392346b01b1872d8118b Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:17:04 +0000 Subject: clocksource/arm_global_timer: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Maxime Coquelin Cc: Patrice Chotard Cc: Peter Zijlstra Cc: Srinivas Kandagatla Cc: Thomas Gleixner Cc: kernel@stlinux.com Cc: linux-arm-kernel@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153338.062741642@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 201a2e23bc49..d24b0fc2f88d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -47,6 +47,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, + CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_METAG_TIMER_STARTING, -- cgit v1.2.3 From d11b3a60fcc8c6e44dd370f1cf2738eb5bec7353 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:17:05 +0000 Subject: clocksource/exynos_mct: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Krzysztof Kozlowski Cc: Kukjin Kim Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-samsung-soc@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153338.147940411@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d24b0fc2f88d..7ad8a7e7806d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -49,6 +49,7 @@ enum cpuhp_state { CPUHP_AP_ARM_ARCH_TIMER_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_DUMMY_TIMER_STARTING, + CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, -- cgit v1.2.3 From 2c48fef74ca42d05c3efd4345b8a068ebf479a5f Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:17:06 +0000 Subject: clocksource/armada-370-xp: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153338.229913786@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 7ad8a7e7806d..ee7f750b1633 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -53,6 +53,7 @@ enum cpuhp_state { CPUHP_AP_ARM_TWD_STARTING, CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, + CPUHP_AP_ARMADA_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, -- cgit v1.2.3 From eb0a9d8c672dc01db41352afa646405d035ee7a4 Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 13 Jul 2016 17:17:07 +0000 Subject: clocksource/atlas7: Convert to hotplug state machine Install the callbacks via the state machine and let the core invoke the callbacks on the already online CPUs. Signed-off-by: Richard Cochran Signed-off-by: Anna-Maria Gleixner Reviewed-by: Sebastian Andrzej Siewior Cc: Barry Song Cc: Daniel Lezcano Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153338.310333816@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index ee7f750b1633..5ac59f7aafce 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -54,6 +54,7 @@ enum cpuhp_state { CPUHP_AP_METAG_TIMER_STARTING, CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_ARMADA_TIMER_STARTING, + CPUHP_AP_MARCO_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, -- cgit v1.2.3 From ecd8081f6fb9032c41e5c38885f06836da6ab455 Mon Sep 17 00:00:00 2001 From: Anna-Maria Gleixner Date: Wed, 13 Jul 2016 17:17:07 +0000 Subject: ARC/time: Convert to hotplug state machine Install the callbacks via the state machine. Signed-off-by: Anna-Maria Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vineet Gupta Cc: linux-snps-arc@lists.infradead.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160713153338.391826254@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5ac59f7aafce..09ef54bcba39 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -56,6 +56,7 @@ enum cpuhp_state { CPUHP_AP_ARMADA_TIMER_STARTING, CPUHP_AP_MARCO_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, + CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3 From 5b844b63ddfb65aef923eaabe0420196fd71dd13 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 14 Jul 2016 09:05:48 +0900 Subject: ata: Handle ATA NCQ NO-DATA commands correctly Add a new taskfile protocol ATA_PROT_NCQ_NODATA to handle ATA NCQ NO-DATA commands correctly. And fixup ata_scsi_zbc_out_xlat() to use it. Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/ata.h | 1 + include/linux/libata.h | 2 ++ include/trace/events/libata.h | 1 + 3 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index d20b1ee127b0..35857d1f15c8 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -530,6 +530,7 @@ enum ata_tf_protocols { ATA_PROT_PIO, /* PIO data xfer */ ATA_PROT_DMA, /* DMA */ ATA_PROT_NCQ, /* NCQ */ + ATA_PROT_NCQ_NODATA, /* NCQ no data */ ATAPI_PROT_NODATA, /* packet command, no data */ ATAPI_PROT_PIO, /* packet command, PIO data xfer*/ ATAPI_PROT_DMA, /* packet command with special DMA sauce */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 4e5a09c6dc10..1abd6690c776 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1053,6 +1053,8 @@ static inline unsigned int ata_prot_flags(u8 prot) return ATA_PROT_FLAG_DMA; case ATA_PROT_NCQ: return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; + case ATA_PROT_NCQ_NODATA: + return ATA_PROT_FLAG_NCQ; case ATAPI_PROT_NODATA: return ATA_PROT_FLAG_ATAPI; case ATAPI_PROT_PIO: diff --git a/include/trace/events/libata.h b/include/trace/events/libata.h index 75fff8696bae..2fbbf990e4b3 100644 --- a/include/trace/events/libata.h +++ b/include/trace/events/libata.h @@ -126,6 +126,7 @@ ata_protocol_name(ATA_PROT_PIO), \ ata_protocol_name(ATA_PROT_DMA), \ ata_protocol_name(ATA_PROT_NCQ), \ + ata_protocol_name(ATA_PROT_NCQ_NODATA), \ ata_protocol_name(ATAPI_PROT_NODATA), \ ata_protocol_name(ATAPI_PROT_PIO), \ ata_protocol_name(ATAPI_PROT_DMA)) -- cgit v1.2.3 From 08188ba8822163922e6b9c600095d21ce02f6a84 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 6 Jul 2016 16:19:41 +0200 Subject: regmap: add iopoll-like polling macro This patch adds a macro regmap_read_poll_timeout that works similar to the readx_poll_timeout defined in linux/iopoll.h, except that this can also return the error value returned by a failed regmap_read. Signed-off-by: Philipp Zabel Signed-off-by: Mark Brown --- include/linux/regmap.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 3dc08ce15426..26914dfcc9fc 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -95,6 +95,45 @@ struct reg_sequence { #define regmap_fields_force_update_bits(field, id, mask, val) \ regmap_fields_update_bits_base(field, id, mask, val, NULL, false, true) +/** + * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs + * @map: Regmap to read from + * @addr: Address to poll + * @val: Unsigned integer variable to read the value into + * @cond: Break condition (usually involving @val) + * @sleep_us: Maximum time to sleep between reads in us (0 + * tight-loops). Should be less than ~20ms since usleep_range + * is used (see Documentation/timers/timers-howto.txt). + * @timeout_us: Timeout in us, 0 means never timeout + * + * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. Must not be called + * from atomic context if sleep_us or timeout_us are used. + * + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + */ +#define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \ + int ret; \ + might_sleep_if(sleep_us); \ + for (;;) { \ + ret = regmap_read((map), (addr), &(val)); \ + if (ret) \ + break; \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \ + ret = regmap_read((map), (addr), &(val)); \ + break; \ + } \ + if (sleep_us) \ + usleep_range((sleep_us >> 2) + 1, sleep_us); \ + } \ + ret ?: ((cond) ? 0 : -ETIMEDOUT); \ +}) + #ifdef CONFIG_REGMAP enum regmap_endian { -- cgit v1.2.3 From 4f253cecf8cb59816d53267170440efa3e1df018 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 10 Jul 2016 13:34:38 -0300 Subject: [media] redrat3: make hardware timeout configurable Instead of hardcoding a timeout, let userspace change it dynamically by adding a s_timeout ops. Signed-off-by: Sean Young Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index b6586a91129c..324232cfc08d 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -119,6 +119,7 @@ enum rc_filter_type { * @s_carrier_report: enable carrier reports * @s_filter: set the scancode filter * @s_wakeup_filter: set the wakeup scancode filter + * @s_timeout: set hardware timeout in ns */ struct rc_dev { struct device dev; @@ -174,6 +175,8 @@ struct rc_dev { struct rc_scancode_filter *filter); int (*s_wakeup_filter)(struct rc_dev *dev, struct rc_scancode_filter *filter); + int (*s_timeout)(struct rc_dev *dev, + unsigned int timeout); }; #define to_rc_dev(d) container_of(d, struct rc_dev, dev) -- cgit v1.2.3 From 77501a79cec40eac65c59ee7af3f786c703ead9c Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Thu, 14 Jul 2016 16:29:43 +0200 Subject: net: phy: micrel: Add KSZ8041FTL fiber mode support We can't detect the FXEN (fiber mode) bootstrap pin, so configure it via a boolean device tree property "micrel,fiber-mode". If it is enabled, auto-negotiation is not supported. The only available modes are 100base-fx (full duplex and half duplex). Signed-off-by: Philipp Zabel Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 2e5b194b9b19..257173e0095e 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -37,6 +37,7 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 +#define MICREL_PHY_FXEN 0x00000002 #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC -- cgit v1.2.3 From 9aa9cc4221f5154ed93e999662ccfef7b6a82e3e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 13 Jul 2016 13:19:05 +0900 Subject: scsi: remove the disable_blk_mq host flag We've had scsi-mq for 2.5 years now, so we can remove the unused flag to disable the code on a per-host basis that was put in for unexpected emergencies during bringup. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- include/scsi/scsi_host.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 76e9d278c334..0dee7afa93d6 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -495,9 +495,6 @@ struct scsi_host_template { */ unsigned int cmd_size; struct scsi_host_cmd_pool *cmd_pool; - - /* temporary flag to disable blk-mq I/O path */ - bool disable_blk_mq; }; /* @@ -778,7 +775,8 @@ extern bool scsi_use_blk_mq; static inline bool shost_use_blk_mq(struct Scsi_Host *shost) { - return shost->use_blk_mq; + return scsi_use_blk_mq; + } extern int scsi_queue_work(struct Scsi_Host *, struct work_struct *); -- cgit v1.2.3 From 934de5f2eac35f34954166cdb47af3593451658a Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 1 Jul 2016 20:44:34 -0300 Subject: tracing: Use outer () on __get_str() definition __get_str(str)'s definition includes a (char *) operator overloading that is not protected with outer (). This patch adds () around __get_str()'s definition, enabling some code cleanup. Link: http://lkml.kernel.org/r/20ac1a10c2ec4ccd23e4a8ef34101fb6e4157d37.1467407618.git.bristot@redhat.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: Ingo Molnar Suggested-by: Steven Rostedt Reviewed-by: Steven Rostedt Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt --- include/trace/perf.h | 2 +- include/trace/trace_events.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/perf.h b/include/trace/perf.h index 88de5c205e86..04fe68bbe767 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -15,7 +15,7 @@ ((__entry->__data_loc_##field >> 16) & 0xffff) #undef __get_str -#define __get_str(field) (char *)__get_dynamic_array(field) +#define __get_str(field) ((char *)__get_dynamic_array(field)) #undef __get_bitmask #define __get_bitmask(field) (char *)__get_dynamic_array(field) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 80679a9fae65..467e12f780d8 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -256,7 +256,7 @@ TRACE_MAKE_SYSTEM_STR(); ((__entry->__data_loc_##field >> 16) & 0xffff) #undef __get_str -#define __get_str(field) (char *)__get_dynamic_array(field) +#define __get_str(field) ((char *)__get_dynamic_array(field)) #undef __get_bitmask #define __get_bitmask(field) \ -- cgit v1.2.3 From a17167ce1110e576f7032b98deeb6ec800f39c7a Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 1 Jul 2016 20:44:35 -0300 Subject: tracing, RAS: Cleanup on __get_str() usage __get_str(msg) does not need (char *) operator overloading to access mgs's elements anymore. This patch substitutes ((char *)__get_str(msg))[0] usage to __get_str(msg)[0]. It is just a code cleanup, no changes on tracepoint ABI. Link: http://lkml.kernel.org/r/6f2db5be7705da2cb483923320c91283d7c712a7.1467407618.git.bristot@redhat.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: Ingo Molnar Reviewed-by: Steven Rostedt Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt --- include/ras/ras_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1443d79e4fe6..1791a12cfa85 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -147,7 +147,7 @@ TRACE_EVENT(mc_event, __entry->error_count, mc_event_error_type(__entry->error_type), __entry->error_count > 1 ? "s" : "", - ((char *)__get_str(msg))[0] ? " " : "", + __get_str(msg)[0] ? " " : "", __get_str(msg), __get_str(label), __entry->mc_index, @@ -157,7 +157,7 @@ TRACE_EVENT(mc_event, __entry->address, 1 << __entry->grain_bits, __entry->syndrome, - ((char *)__get_str(driver_detail))[0] ? " " : "", + __get_str(driver_detail)[0] ? " " : "", __get_str(driver_detail)) ); -- cgit v1.2.3 From 752d596b394c62f081393bbf53dff2a2c244632e Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 1 Jul 2016 20:44:36 -0300 Subject: tracing: Use __get_str() when manipulating strings Use __get_str(str) rather than __get_dynamic_array(str) when deadling with strings. It is just a code cleanup, no changes on tracepoint ABI. Link: http://lkml.kernel.org/r/ea260df91817411cca2a1f3db2abd88860094788.1467407618.git.bristot@redhat.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: Ingo Molnar Cc: linux-nfs@vger.kernel.org Suggested-by: Steven Rostedt Reviewed-by: Steven Rostedt Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt --- include/trace/events/printk.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/printk.h b/include/trace/events/printk.h index c008bc99f9fa..542a7558154a 100644 --- a/include/trace/events/printk.h +++ b/include/trace/events/printk.h @@ -16,8 +16,8 @@ TRACE_EVENT(console, ), TP_fast_assign( - memcpy(__get_dynamic_array(msg), text, len); - ((char *)__get_dynamic_array(msg))[len] = 0; + memcpy(__get_str(msg), text, len); + __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) -- cgit v1.2.3 From 78aebca2c955c1c5aeb48e12645e13fe3c3461f2 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 1 Jul 2016 20:44:37 -0300 Subject: printk, tracing: Avoiding unneeded blank lines Printk messages often finish with '\n' to cause a new line. But as each tracepoint is already printed in a new line, printk messages that finish with '\n' ends up adding a blank line to the trace output. For example: kworker/0:1-86 [000] d... 46.006949: console: [ 46.006946] usb 1-3: USB disconnect, device number 3 kworker/2:2-374 [002] d... 48.699342: console: [ 48.699339] usb 1-3: new high-speed USB device number 4 using ehci-pci kworker/2:2-374 [002] d... 49.041450: console: [ 49.041448] usb 1-3: New USB device found, idVendor=5986, idProduct=0 To avoid unneeded blank lines, this patch checks if the printk message finishes with '\n', if so, it cut is off the '\n' to avoid blank lines. In a patched kernel, the same messages are printed without extra blank lines. For example: kworker/0:4-185 [000] d... 23.641738: console: [ 23.641736] usb 1-3: USB disconnect, device number 3 kworker/0:4-185 [000] d... 24.918703: console: [ 24.918700] usb 1-3: new high-speed USB device number 4 using ehci-pci kworker/0:4-185 [000] d... 25.228308: console: [ 25.228306] usb 1-3: New USB device found, idVendor=5986, idProduct=02d5 Link: http://lkml.kernel.org/r/c350fb2521baaf681a1b4d67981ca0e900108e8e.1467407618.git.bristot@redhat.com Cc: Trond Myklebust Cc: Anna Schumaker Cc: Ingo Molnar Reviewed-by: Steven Rostedt Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt --- include/trace/events/printk.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/trace/events/printk.h b/include/trace/events/printk.h index 542a7558154a..f350170059c6 100644 --- a/include/trace/events/printk.h +++ b/include/trace/events/printk.h @@ -16,6 +16,14 @@ TRACE_EVENT(console, ), TP_fast_assign( + /* + * Each trace entry is printed in a new line. + * If the msg finishes with '\n', cut it off + * to avoid blank lines in the trace. + */ + if ((len > 0) && (text[len-1] == '\n')) + len -= 1; + memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), -- cgit v1.2.3 From b4219a898f487f454f4b58b0906d9e035ea58a12 Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Tue, 5 Jul 2016 13:53:04 +0800 Subject: ACPICA: Linux: Enable ACPI_MUTEX_DEBUG for Linux kernel This patch enables ACPI_MUTEX_DEBUG for Linux kernel so that the ACPICA lock order issues can be captured by ACPICA itself. Signed-off-by: Lv Zheng Signed-off-by: Rafael J. Wysocki --- include/acpi/platform/aclinux.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 45c2d6528829..93b61b1f2beb 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -73,6 +73,10 @@ #define ACPI_DEBUGGER #endif +#ifdef CONFIG_ACPI_DEBUG +#define ACPI_MUTEX_DEBUG +#endif + #include #include #include -- cgit v1.2.3 From 7e3f977edd0bd9ea6104156feba95bb5ae9bdd38 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 14 Jul 2016 18:08:03 +0200 Subject: perf, events: add non-linear data support for raw records This patch adds support for non-linear data on raw records. It extends raw records to have one or multiple fragments that will be written linearly into the ring slot, where each fragment can optionally have a custom callback handler to walk and extract complex, possibly non-linear data. If a callback handler is provided for a fragment, then the new __output_custom() will be used instead of __output_copy() for the perf_output_sample() part. perf_prepare_sample() does all the size calculation only once, so perf_output_sample() doesn't need to redo the same work anymore, meaning real_size and padding will be cached in the raw record. The raw record becomes 32 bytes in size without holes; to not increase it further and to avoid doing unnecessary recalculations in fast-path, we can reuse next pointer of the last fragment, idea here is borrowed from ZERO_OR_NULL_PTR(), which should keep the perf_output_sample() path for PERF_SAMPLE_RAW minimal. This facility is needed for BPF's event output helper as a first user that will, in a follow-up, add an additional perf_raw_frag to its perf_raw_record in order to be able to more efficiently dump skb context after a linear head meta data related to it. skbs can be non-linear and thus need a custom output function to dump buffers. Currently, the skb data needs to be copied twice; with the help of __output_custom() this work only needs to be done once. Future users could be things like XDP/BPF programs that work on different context though and would thus also have a different callback function. The few users of raw records are adapted to initialize their frag data from the raw record itself, no change in behavior for them. The code is based upon a PoC diff provided by Peter Zijlstra [1]. [1] http://thread.gmane.org/gmane.linux.network/421294 Suggested-by: Peter Zijlstra Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/perf_event.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1a827cecd62f..e79e6c6fed89 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -69,9 +69,22 @@ struct perf_callchain_entry_ctx { bool contexts_maxed; }; +typedef unsigned long (*perf_copy_f)(void *dst, const void *src, + unsigned long len); + +struct perf_raw_frag { + union { + struct perf_raw_frag *next; + unsigned long pad; + }; + perf_copy_f copy; + void *data; + u32 size; +} __packed; + struct perf_raw_record { + struct perf_raw_frag frag; u32 size; - void *data; }; /* @@ -1283,6 +1296,11 @@ extern void perf_restore_debug_store(void); static inline void perf_restore_debug_store(void) { } #endif +static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) +{ + return frag->pad < sizeof(u64); +} + #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) /* -- cgit v1.2.3 From 555c8a8623a3a87b3c990ba30b7fd2e5914e41d2 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 14 Jul 2016 18:08:05 +0200 Subject: bpf: avoid stack copy and use skb ctx for event output This work addresses a couple of issues bpf_skb_event_output() helper currently has: i) We need two copies instead of just a single one for the skb data when it should be part of a sample. The data can be non-linear and thus needs to be extracted via bpf_skb_load_bytes() helper first, and then copied once again into the ring buffer slot. ii) Since bpf_skb_load_bytes() currently needs to be used first, the helper needs to see a constant size on the passed stack buffer to make sure BPF verifier can do sanity checks on it during verification time. Thus, just passing skb->len (or any other non-constant value) wouldn't work, but changing bpf_skb_load_bytes() is also not the proper solution, since the two copies are generally still needed. iii) bpf_skb_load_bytes() is just for rather small buffers like headers, since they need to sit on the limited BPF stack anyway. Instead of working around in bpf_skb_load_bytes(), this work improves the bpf_skb_event_output() helper to address all 3 at once. We can make use of the passed in skb context that we have in the helper anyway, and use some of the reserved flag bits as a length argument. The helper will use the new __output_custom() facility from perf side with bpf_skb_copy() as callback helper to walk and extract the data. It will pass the data for setup to bpf_event_output(), which generates and pushes the raw record with an additional frag part. The linear data used in the first frag of the record serves as programmatically defined meta data passed along with the appended sample. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 ++++++- include/uapi/linux/bpf.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b3336b4f5d04..c13e92b00bf5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -209,7 +209,12 @@ u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); -const struct bpf_func_proto *bpf_get_event_output_proto(void); + +typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, + unsigned long len); + +u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, + void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 262a7e883b19..c4d922439d20 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -401,6 +401,8 @@ enum bpf_func_id { /* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure -- cgit v1.2.3 From ed7c9870c9bc6ca50dc0d271a301410bc894f4b9 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 15 Jul 2016 14:05:29 -0700 Subject: Input: of_touchscreen - add support for inverted / swapped axes Extend touchscreen_parse_properties() with support for the touchscreen-inverted-x/y and touchscreen-swapped-x-y properties and add touchscreen_set_mt_pos() and touchscreen_report_pos() helper functions for storing coordinates into a input_mt_pos struct, or directly reporting them, taking these properties into account. This commit also modifies the existing callers of touchscreen_parse_properties() to pass in NULL for the new third argument, keeping the existing behavior. Signed-off-by: Hans de Goede Signed-off-by: Dmitry Torokhov --- include/linux/input/touchscreen.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input/touchscreen.h b/include/linux/input/touchscreen.h index c91e1376132b..09d22ccb9e41 100644 --- a/include/linux/input/touchscreen.h +++ b/include/linux/input/touchscreen.h @@ -10,7 +10,26 @@ #define _TOUCHSCREEN_H struct input_dev; +struct input_mt_pos; -void touchscreen_parse_properties(struct input_dev *dev, bool multitouch); +struct touchscreen_properties { + unsigned int max_x; + unsigned int max_y; + bool invert_x; + bool invert_y; + bool swap_x_y; +}; + +void touchscreen_parse_properties(struct input_dev *input, bool multitouch, + struct touchscreen_properties *prop); + +void touchscreen_set_mt_pos(struct input_mt_pos *pos, + const struct touchscreen_properties *prop, + unsigned int x, unsigned int y); + +void touchscreen_report_pos(struct input_dev *input, + const struct touchscreen_properties *prop, + unsigned int x, unsigned int y, + bool multitouch); #endif -- cgit v1.2.3 From 02a198777e646a12a8aabae5639f1d33d81d79ef Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 15 Jul 2016 23:55:20 +0200 Subject: net: fixup for tracepoint napi:napi_poll The recent change to tracepoint napi:napi_poll changed the order of the parameters that perf scripts sees, the printk was correct. The problem was that the new parameters (work and budget) were pushed in front of dev_name. The new parameters obviously need to be appended to keep backward compatible. Fixes: 1db19db7f5ff ("net: tracepoint napi:napi_poll add work and budget") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/trace/events/napi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 118ed7767639..0b9e5136a2a3 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -18,16 +18,16 @@ TRACE_EVENT(napi_poll, TP_STRUCT__entry( __field( struct napi_struct *, napi) + __string( dev_name, napi->dev ? napi->dev->name : NO_DEV) __field( int, work) __field( int, budget) - __string( dev_name, napi->dev ? napi->dev->name : NO_DEV) ), TP_fast_assign( __entry->napi = napi; + __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); __entry->work = work; __entry->budget = budget; - __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); ), TP_printk("napi poll on napi struct %p for device %s work %d budget %d", -- cgit v1.2.3 From ca1d2e269f593b318a75f3ffb9befc1ec8b6f2fd Mon Sep 17 00:00:00 2001 From: Michael Turquette Date: Fri, 15 Jul 2016 19:13:36 -0700 Subject: Revert "clk: gxbb: expose CLKID_MMC_PCLK" This reverts commit e16fb2e6355c1c1b41623af9e01ada196e2af098. Updated documentation from the chip vendor reveals that this clock is not required for correct operation of the MMC controller. As such, do not expose it to DT. Signed-off-by: Michael Turquette --- include/dt-bindings/clock/gxbb-clkc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h index 5eb69ec74f6b..f889d80246cb 100644 --- a/include/dt-bindings/clock/gxbb-clkc.h +++ b/include/dt-bindings/clock/gxbb-clkc.h @@ -8,6 +8,5 @@ #define CLKID_CPUCLK 1 #define CLKID_CLK81 12 #define CLKID_ETH 36 -#define CLKID_MMC_PCLK 66 #endif /* __GXBB_CLKC_H */ -- cgit v1.2.3 From 1db3312e3ab1a776ae8f414640dd7c180ce38a75 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 11 Jul 2016 23:57:14 +0000 Subject: ASoC: simple-card-utils: add asoc_simple_card_set_dailink_name() Current simple-card is creating dai_link->name / dai_link->stream_name. These are based on CPU + Codec name, or "fe.CPU" or "be.Codec" if it was DPCM. This patch adds asoc_simple_card_set_dailink_name() and set dailink name as common method. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index 50aa7b22a94c..b88a8dcfe4ba 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -27,5 +27,8 @@ int asoc_simple_card_parse_daifmt(struct device *dev, struct device_node *codec, char *prefix, unsigned int *retfmt); +int asoc_simple_card_set_dailink_name(struct device *dev, + struct snd_soc_dai_link *dai_link, + const char *fmt, ...); #endif /* __SIMPLE_CARD_CORE_H */ -- cgit v1.2.3 From fc55c9b5a2ea794c4b6be937522bcfe98be4770a Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 11 Jul 2016 23:59:16 +0000 Subject: ASoC: simple-card-utils: add asoc_simple_card_parse_card_name() simple-card needs to get its card name. This patch makes this method simple style standard. Signed-off-by: Kuninori Morimoto Signed-off-by: Mark Brown --- include/sound/simple_card_utils.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h index b88a8dcfe4ba..86088aed9002 100644 --- a/include/sound/simple_card_utils.h +++ b/include/sound/simple_card_utils.h @@ -30,5 +30,7 @@ int asoc_simple_card_parse_daifmt(struct device *dev, int asoc_simple_card_set_dailink_name(struct device *dev, struct snd_soc_dai_link *dai_link, const char *fmt, ...); +int asoc_simple_card_parse_card_name(struct snd_soc_card *card, + char *prefix); #endif /* __SIMPLE_CARD_CORE_H */ -- cgit v1.2.3 From 43b9e127406079d187794a5140a2411fbc6df2df Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 14 Jul 2016 19:28:27 +0300 Subject: net: ipmr/ip6mr: add support for keeping an entry age In preparation for hardware offloading of ipmr/ip6mr we need an interface that allows to check (and later update) the age of entries. Relying on stats alone can show activity but not actual age of the entry, furthermore when there're tens of thousands of entries a lot of the hardware implementations only support "hit" bits which are cleared on read to denote that the entry was active and shouldn't be aged out, these can then be naturally translated into age timestamp and will be compatible with the software forwarding age. Using a lastuse entry doesn't affect performance because the members in that cache line are written to along with the age. Since all new users are encouraged to use ipmr via netlink, this is exported via the RTA_EXPIRES attribute. Also do a minor local variable declaration style adjustment - arrange them longest to shortest. Signed-off-by: Nikolay Aleksandrov CC: Roopa Prabhu CC: Shrijeet Mukherjee CC: Satish Ashok CC: Donald Sharp CC: David S. Miller CC: Alexey Kuznetsov CC: James Morris CC: Hideaki YOSHIFUJI CC: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/mroute.h | 1 + include/linux/mroute6.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index bf9b322cb0b0..d351fd3e1049 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -104,6 +104,7 @@ struct mfc_cache { unsigned long bytes; unsigned long pkt; unsigned long wrong_if; + unsigned long lastuse; unsigned char ttls[MAXVIFS]; /* TTL thresholds */ } res; } mfc_un; diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 66982e764051..3987b64040c5 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -92,6 +92,7 @@ struct mfc6_cache { unsigned long bytes; unsigned long pkt; unsigned long wrong_if; + unsigned long lastuse; unsigned char ttls[MAXMIFS]; /* TTL thresholds */ } res; } mfc_un; -- cgit v1.2.3 From b786241253041c13d94309ca4dace301833f63d1 Mon Sep 17 00:00:00 2001 From: Dongpo Li Date: Fri, 15 Jul 2016 16:26:34 +0800 Subject: of_mdio: Abstract a general interface for phy connect Abstract a general interface "of_phy_get_and_connect" for PHY connect. User will have no bother with getting "phy-mode" and "phy-handle" any more. Suggested-by: Arnd Bergmann Signed-off-by: Dongpo Li Reviewed-by: Jiancheng Xue Signed-off-by: David S. Miller --- include/linux/of_mdio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 4b04587d0441..2ab233661ae5 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -19,6 +19,9 @@ extern struct phy_device *of_phy_connect(struct net_device *dev, struct device_node *phy_np, void (*hndlr)(struct net_device *), u32 flags, phy_interface_t iface); +extern struct phy_device * +of_phy_get_and_connect(struct net_device *dev, struct device_node *np, + void (*hndlr)(struct net_device *)); struct phy_device *of_phy_attach(struct net_device *dev, struct device_node *phy_np, u32 flags, phy_interface_t iface); @@ -52,6 +55,13 @@ static inline struct phy_device *of_phy_connect(struct net_device *dev, return NULL; } +static inline struct phy_device * +of_phy_get_and_connect(struct net_device *dev, struct device_node *np, + void (*hndlr)(struct net_device *)) +{ + return NULL; +} + static inline struct phy_device *of_phy_attach(struct net_device *dev, struct device_node *phy_np, u32 flags, phy_interface_t iface) -- cgit v1.2.3 From d26a5d4350fd234c1f35d8b262527c8cb97c630d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 17 Jul 2016 07:20:06 -0300 Subject: [media] doc-rst: Convert media API to rst Move the contents of the media section at DocBooks/DocBook/device-drivers.tmpl to a new ReST book. For now, the contents is kept as-is. Next patches will fix the warnings and add cross-references that were removed due to the conversion. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 231 ------------------------------------------- 1 file changed, 231 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index f743ae2210ee..4605fee0c228 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -29,237 +29,6 @@ #include #include -/** - * DOC: Media Controller - * - * The media controller userspace API is documented in DocBook format in - * Documentation/DocBook/media/v4l/media-controller.xml. This document focus - * on the kernel-side implementation of the media framework. - * - * * Abstract media device model: - * - * Discovering a device internal topology, and configuring it at runtime, is one - * of the goals of the media framework. To achieve this, hardware devices are - * modelled as an oriented graph of building blocks called entities connected - * through pads. - * - * An entity is a basic media hardware building block. It can correspond to - * a large variety of logical blocks such as physical hardware devices - * (CMOS sensor for instance), logical hardware devices (a building block - * in a System-on-Chip image processing pipeline), DMA channels or physical - * connectors. - * - * A pad is a connection endpoint through which an entity can interact with - * other entities. Data (not restricted to video) produced by an entity - * flows from the entity's output to one or more entity inputs. Pads should - * not be confused with physical pins at chip boundaries. - * - * A link is a point-to-point oriented connection between two pads, either - * on the same entity or on different entities. Data flows from a source - * pad to a sink pad. - * - * - * * Media device: - * - * A media device is represented by a struct &media_device instance, defined in - * include/media/media-device.h. Allocation of the structure is handled by the - * media device driver, usually by embedding the &media_device instance in a - * larger driver-specific structure. - * - * Drivers register media device instances by calling - * __media_device_register() via the macro media_device_register() - * and unregistered by calling - * media_device_unregister(). - * - * * Entities, pads and links: - * - * - Entities - * - * Entities are represented by a struct &media_entity instance, defined in - * include/media/media-entity.h. The structure is usually embedded into a - * higher-level structure, such as a v4l2_subdev or video_device instance, - * although drivers can allocate entities directly. - * - * Drivers initialize entity pads by calling - * media_entity_pads_init(). - * - * Drivers register entities with a media device by calling - * media_device_register_entity() - * and unregistred by calling - * media_device_unregister_entity(). - * - * - Interfaces - * - * Interfaces are represented by a struct &media_interface instance, defined in - * include/media/media-entity.h. Currently, only one type of interface is - * defined: a device node. Such interfaces are represented by a struct - * &media_intf_devnode. - * - * Drivers initialize and create device node interfaces by calling - * media_devnode_create() - * and remove them by calling: - * media_devnode_remove(). - * - * - Pads - * - * Pads are represented by a struct &media_pad instance, defined in - * include/media/media-entity.h. Each entity stores its pads in a pads array - * managed by the entity driver. Drivers usually embed the array in a - * driver-specific structure. - * - * Pads are identified by their entity and their 0-based index in the pads - * array. - * Both information are stored in the &media_pad structure, making the - * &media_pad pointer the canonical way to store and pass link references. - * - * Pads have flags that describe the pad capabilities and state. - * - * %MEDIA_PAD_FL_SINK indicates that the pad supports sinking data. - * %MEDIA_PAD_FL_SOURCE indicates that the pad supports sourcing data. - * - * NOTE: One and only one of %MEDIA_PAD_FL_SINK and %MEDIA_PAD_FL_SOURCE must - * be set for each pad. - * - * - Links - * - * Links are represented by a struct &media_link instance, defined in - * include/media/media-entity.h. There are two types of links: - * - * 1. pad to pad links: - * - * Associate two entities via their PADs. Each entity has a list that points - * to all links originating at or targeting any of its pads. - * A given link is thus stored twice, once in the source entity and once in - * the target entity. - * - * Drivers create pad to pad links by calling: - * media_create_pad_link() and remove with media_entity_remove_links(). - * - * 2. interface to entity links: - * - * Associate one interface to a Link. - * - * Drivers create interface to entity links by calling: - * media_create_intf_link() and remove with media_remove_intf_links(). - * - * NOTE: - * - * Links can only be created after having both ends already created. - * - * Links have flags that describe the link capabilities and state. The - * valid values are described at media_create_pad_link() and - * media_create_intf_link(). - * - * Graph traversal: - * - * The media framework provides APIs to iterate over entities in a graph. - * - * To iterate over all entities belonging to a media device, drivers can use - * the media_device_for_each_entity macro, defined in - * include/media/media-device.h. - * - * struct media_entity *entity; - * - * media_device_for_each_entity(entity, mdev) { - * // entity will point to each entity in turn - * ... - * } - * - * Drivers might also need to iterate over all entities in a graph that can be - * reached only through enabled links starting at a given entity. The media - * framework provides a depth-first graph traversal API for that purpose. - * - * Note that graphs with cycles (whether directed or undirected) are *NOT* - * supported by the graph traversal API. To prevent infinite loops, the graph - * traversal code limits the maximum depth to MEDIA_ENTITY_ENUM_MAX_DEPTH, - * currently defined as 16. - * - * Drivers initiate a graph traversal by calling - * media_entity_graph_walk_start() - * - * The graph structure, provided by the caller, is initialized to start graph - * traversal at the given entity. - * - * Drivers can then retrieve the next entity by calling - * media_entity_graph_walk_next() - * - * When the graph traversal is complete the function will return NULL. - * - * Graph traversal can be interrupted at any moment. No cleanup function call - * is required and the graph structure can be freed normally. - * - * Helper functions can be used to find a link between two given pads, or a pad - * connected to another pad through an enabled link - * media_entity_find_link() and media_entity_remote_pad() - * - * Use count and power handling: - * - * Due to the wide differences between drivers regarding power management - * needs, the media controller does not implement power management. However, - * the &media_entity structure includes a use_count field that media drivers - * can use to track the number of users of every entity for power management - * needs. - * - * The &media_entity.@use_count field is owned by media drivers and must not be - * touched by entity drivers. Access to the field must be protected by the - * &media_device.@graph_mutex lock. - * - * Links setup: - * - * Link properties can be modified at runtime by calling - * media_entity_setup_link() - * - * Pipelines and media streams: - * - * When starting streaming, drivers must notify all entities in the pipeline to - * prevent link states from being modified during streaming by calling - * media_entity_pipeline_start(). - * - * The function will mark all entities connected to the given entity through - * enabled links, either directly or indirectly, as streaming. - * - * The &media_pipeline instance pointed to by the pipe argument will be stored - * in every entity in the pipeline. Drivers should embed the &media_pipeline - * structure in higher-level pipeline structures and can then access the - * pipeline through the &media_entity pipe field. - * - * Calls to media_entity_pipeline_start() can be nested. The pipeline pointer - * must be identical for all nested calls to the function. - * - * media_entity_pipeline_start() may return an error. In that case, it will - * clean up any of the changes it did by itself. - * - * When stopping the stream, drivers must notify the entities with - * media_entity_pipeline_stop(). - * - * If multiple calls to media_entity_pipeline_start() have been made the same - * number of media_entity_pipeline_stop() calls are required to stop streaming. - * The &media_entity pipe field is reset to NULL on the last nested stop call. - * - * Link configuration will fail with -%EBUSY by default if either end of the - * link is a streaming entity. Links that can be modified while streaming must - * be marked with the %MEDIA_LNK_FL_DYNAMIC flag. - * - * If other operations need to be disallowed on streaming entities (such as - * changing entities configuration parameters) drivers can explicitly check the - * media_entity stream_count field to find out if an entity is streaming. This - * operation must be done with the media_device graph_mutex held. - * - * Link validation: - * - * Link validation is performed by media_entity_pipeline_start() for any - * entity which has sink pads in the pipeline. The - * &media_entity.@link_validate() callback is used for that purpose. In - * @link_validate() callback, entity driver should check that the properties of - * the source pad of the connected entity and its own sink pad match. It is up - * to the type of the entity (and in the end, the properties of the hardware) - * what matching actually means. - * - * Subsystems should facilitate link validation by providing subsystem specific - * helper functions to provide easy access for commonly needed information, and - * in the end provide a way to use driver-specific callbacks. - */ - struct ida; struct device; -- cgit v1.2.3 From 5b6137dc84f627e8497e554890ae02378c54f9f0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 17 Jul 2016 09:16:57 -0300 Subject: [media] doc-rst: Fix issues with RC documentation The kernel-doc script is now broken if it doesn't find all exported symbols documented. Signed-off-by: Mauro Carvalho Chehab --- include/media/lirc_dev.h | 2 +- include/media/rc-core.h | 45 +++++++++++++++++++++++++++++++++++++++++++-- include/media/rc-map.h | 17 ++++++++++++++++- 3 files changed, 60 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/lirc_dev.h b/include/media/lirc_dev.h index 0ab59a571fee..cec7d35602d1 100644 --- a/include/media/lirc_dev.h +++ b/include/media/lirc_dev.h @@ -140,7 +140,7 @@ static inline unsigned int lirc_buffer_write(struct lirc_buffer *buf, * second. * * @features: lirc compatible hardware features, like LIRC_MODE_RAW, - * LIRC_CAN_*, as defined at include/media/lirc.h. + * LIRC_CAN\_\*, as defined at include/media/lirc.h. * * @chunk_size: Size of each FIFO buffer. * diff --git a/include/media/rc-core.h b/include/media/rc-core.h index b6586a91129c..ff54a71f5cd2 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -29,9 +29,16 @@ do { \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) +/** + * enum rc_driver_type - type of the RC output + * + * @RC_DRIVER_SCANCODE: Driver or hardware generates a scancode + * @RC_DRIVER_IR_RAW: Driver or hardware generates pulse/space sequences. + * It needs a Infra-Red pulse/space decoder + */ enum rc_driver_type { - RC_DRIVER_SCANCODE = 0, /* Driver or hardware generates a scancode */ - RC_DRIVER_IR_RAW, /* Needs a Infra-Red pulse/space decoder */ + RC_DRIVER_SCANCODE = 0, + RC_DRIVER_IR_RAW, }; /** @@ -185,12 +192,46 @@ struct rc_dev { * Remote Controller, at sys/class/rc. */ +/** + * rc_allocate_device - Allocates a RC device + * + * returns a pointer to struct rc_dev. + */ struct rc_dev *rc_allocate_device(void); + +/** + * rc_free_device - Frees a RC device + * + * @dev: pointer to struct rc_dev. + */ void rc_free_device(struct rc_dev *dev); + +/** + * rc_register_device - Registers a RC device + * + * @dev: pointer to struct rc_dev. + */ int rc_register_device(struct rc_dev *dev); + +/** + * rc_unregister_device - Unregisters a RC device + * + * @dev: pointer to struct rc_dev. + */ void rc_unregister_device(struct rc_dev *dev); +/** + * rc_open - Opens a RC device + * + * @rdev: pointer to struct rc_dev. + */ int rc_open(struct rc_dev *rdev); + +/** + * rc_open - Closes a RC device + * + * @rdev: pointer to struct rc_dev. + */ void rc_close(struct rc_dev *rdev); void rc_repeat(struct rc_dev *dev); diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 6e6557dbeb9f..726bd9374fd2 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -98,10 +98,25 @@ struct rc_map_list { /* Routines from rc-map.c */ +/** + * rc_map_register() - Registers a Remote Controler scancode map + * + * @map: pointer to struct rc_map_list + */ int rc_map_register(struct rc_map_list *map); + +/** + * rc_map_unregister() - Unregisters a Remote Controler scancode map + * + * @map: pointer to struct rc_map_list + */ void rc_map_unregister(struct rc_map_list *map); + +/** + * rc_map_get - gets an RC map from its name + * @name: name of the RC scancode map + */ struct rc_map *rc_map_get(const char *name); -void rc_map_init(void); /* Names of the several keytables defined in-kernel */ -- cgit v1.2.3 From 89cb3ddbe7cc5ce49ffa814f30fb019fc531865d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 17 Jul 2016 08:44:08 -0300 Subject: [media] doc-rst: Fix conversion for v4l2 core functions The conversion from DocBook lead into some conversion issues, basically due to the lack of proper support at kernel-doc. So, address them: - Now, the C files with the exported symbols also need to be added. So, all headers need to be included twice: one to get the structs/enums/.. and another one for the functions; - Notes should use the ReST tag, as kernel-doc doesn't recognizes it anymore; - Identation needs to be fixed, as ReST uses it to identify when a format "tag" ends. - kernel-doc doesn't escape things like *pointer, so we need to manually add a escape char before it. - On some cases, kernel-doc conversion requires violating the 80-cols, as otherwise it won't properly parse the source code. Signed-off-by: Mauro Carvalho Chehab --- include/media/tuner-types.h | 8 ++++++-- include/media/tveeprom.h | 18 +++++++++++++++--- include/media/v4l2-mc.h | 13 ++++++++----- include/media/v4l2-subdev.h | 4 ++-- include/media/videobuf2-core.h | 30 ++++++++++++++++++------------ 5 files changed, 49 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/media/tuner-types.h b/include/media/tuner-types.h index 094e112cc325..aed539068d2d 100644 --- a/include/media/tuner-types.h +++ b/include/media/tuner-types.h @@ -35,8 +35,12 @@ enum param_type { * those ranges, as they're defined inside the driver. This is used by * analog tuners that are compatible with the "Philips way" to setup the * tuners. On those devices, the tuner set is done via 4 bytes: - * divider byte1 (DB1), divider byte 2 (DB2), Control byte (CB) and - * band switch byte (BB). + * + * #) divider byte1 (DB1) + * #) divider byte 2 (DB2) + * #) Control byte (CB) + * #) band switch byte (BB) + * * Some tuners also have an additional optional Auxiliary byte (AB). */ struct tuner_range { diff --git a/include/media/tveeprom.h b/include/media/tveeprom.h index 8be898739e0c..c56501ee0484 100644 --- a/include/media/tveeprom.h +++ b/include/media/tveeprom.h @@ -27,31 +27,43 @@ enum tveeprom_audio_processor { * struct tveeprom - Contains the fields parsed from Hauppauge eeproms * * @has_radio: 1 if the device has radio; 0 otherwise. + * * @has_ir: If has_ir == 0, then it is unknown what the IR * capabilities are. Otherwise: - * bit 0) 1 (= IR capabilities are known); - * bit 1) IR receiver present; - * bit 2) IR transmitter (blaster) present. + * bit 0) 1 (= IR capabilities are known); + * bit 1) IR receiver present; + * bit 2) IR transmitter (blaster) present. + * * @has_MAC_address: 0: no MAC, 1: MAC present, 2: unknown. * @tuner_type: type of the tuner (TUNER_*, as defined at * include/media/tuner.h). + * * @tuner_formats: Supported analog TV standards (V4L2_STD_*). * @tuner_hauppauge_model: Hauppauge's code for the device model number. * @tuner2_type: type of the second tuner (TUNER_*, as defined * at include/media/tuner.h). + * * @tuner2_formats: Tuner 2 supported analog TV standards * (V4L2_STD_*). + * * @tuner2_hauppauge_model: tuner 2 Hauppauge's code for the device model * number. + * * @audio_processor: analog audio decoder, as defined by enum * tveeprom_audio_processor. + * * @decoder_processor: Hauppauge's code for the decoder chipset. * Unused by the drivers, as they probe the * decoder based on the PCI or USB ID. + * * @model: Hauppauge's model number + * * @revision: Card revision number + * * @serial_number: Card's serial number + * * @rev_str: Card revision converted to number + * * @MAC_address: MAC address for the network interface */ struct tveeprom { diff --git a/include/media/v4l2-mc.h b/include/media/v4l2-mc.h index 7a8d6037a4bb..28c3f9d9c209 100644 --- a/include/media/v4l2-mc.h +++ b/include/media/v4l2-mc.h @@ -114,11 +114,14 @@ struct usb_device; * Add links between the entities commonly found on PC customer's hardware at * the V4L2 side: camera sensors, audio and video PLL-IF decoders, tuners, * analog TV decoder and I/O entities (video, VBI and Software Defined Radio). - * NOTE: webcams are modelled on a very simple way: the sensor is - * connected directly to the I/O entity. All dirty details, like - * scaler and crop HW are hidden. While such mapping is enough for v4l2 - * interface centric PC-consumer's hardware, V4L2 subdev centric camera - * hardware should not use this routine, as it will not build the right graph. + * + * .. note:: + * + * Webcams are modelled on a very simple way: the sensor is + * connected directly to the I/O entity. All dirty details, like + * scaler and crop HW are hidden. While such mapping is enough for v4l2 + * interface centric PC-consumer's hardware, V4L2 subdev centric camera + * hardware should not use this routine, as it will not build the right graph. */ int v4l2_mc_create_media_graph(struct media_device *mdev); diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 32fc7a4beb5e..4c880e86a1aa 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -225,7 +225,7 @@ struct v4l2_subdev_core_ops { * * @g_frequency: callback for VIDIOC_G_FREQUENCY ioctl handler code. * freq->type must be filled in. Normally done by video_ioctl2 - * or the bridge driver. + * or the bridge driver. * * @enum_freq_bands: callback for VIDIOC_ENUM_FREQ_BANDS ioctl handler code. * @@ -233,7 +233,7 @@ struct v4l2_subdev_core_ops { * * @s_tuner: callback for VIDIOC_S_TUNER ioctl handler code. vt->type must be * filled in. Normally done by video_ioctl2 or the - * bridge driver. + * bridge driver. * * @g_modulator: callback for VIDIOC_G_MODULATOR ioctl handler code. * diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 88e3ab496e8f..01cdd5bf90c8 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -86,11 +86,17 @@ struct vb2_threadio_data; * @mmap: setup a userspace mapping for a given memory buffer under * the provided virtual memory region. * - * Required ops for USERPTR types: get_userptr, put_userptr. - * Required ops for MMAP types: alloc, put, num_users, mmap. - * Required ops for read/write access types: alloc, put, num_users, vaddr. - * Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, map_dmabuf, - * unmap_dmabuf. + * Those operations are used by the videobuf2 core to implement the memory + * handling/memory allocators for each type of supported streaming I/O method. + * + * .. note:: + * #) Required ops for USERPTR types: get_userptr, put_userptr. + * + * #) Required ops for MMAP types: alloc, put, num_users, mmap. + * + * #) Required ops for read/write access types: alloc, put, num_users, vaddr. + * + * #) Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, map_dmabuf, unmap_dmabuf. */ struct vb2_mem_ops { void *(*alloc)(void *alloc_ctx, unsigned long size, @@ -279,19 +285,19 @@ struct vb2_buffer { * second time with the actually allocated number of * buffers to verify if that is OK. * The driver should return the required number of buffers - * in *num_buffers, the required number of planes per - * buffer in *num_planes, the size of each plane should be + * in \*num_buffers, the required number of planes per + * buffer in \*num_planes, the size of each plane should be * set in the sizes[] array and optional per-plane * allocator specific context in the alloc_ctxs[] array. - * When called from VIDIOC_REQBUFS, *num_planes == 0, the + * When called from VIDIOC_REQBUFS, \*num_planes == 0, the * driver has to use the currently configured format to - * determine the plane sizes and *num_buffers is the total + * determine the plane sizes and \*num_buffers is the total * number of buffers that are being allocated. When called - * from VIDIOC_CREATE_BUFS, *num_planes != 0 and it + * from VIDIOC_CREATE_BUFS, \*num_planes != 0 and it * describes the requested number of planes and sizes[] * contains the requested plane sizes. If either - * *num_planes or the requested sizes are invalid callback - * must return -EINVAL. In this case *num_buffers are + * \*num_planes or the requested sizes are invalid callback + * must return -EINVAL. In this case \*num_buffers are * being allocated additionally to q->num_buffers. * @wait_prepare: release any locks taken while calling vb2 functions; * it is called before an ioctl needs to wait for a new -- cgit v1.2.3 From 74604b7390af3afb1bcb055b87787b5cfabd03a0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sun, 17 Jul 2016 09:18:03 -0300 Subject: [media] doc-rst: Fix conversion for MC core functions There were lots of issues at the media controller side, after the conversion: - Some documentation at the header files weren't using the kernel-doc start block; - Now, the C files with the exported symbols also need to be added. So, all headers need to be included twice: one to get the structs/enums/.. and another one for the functions; - Notes should use the ReST tag, as kernel-doc doesn't recognizes it anymore; - Identation needs to be fixed, as ReST uses it to identify when a format "tag" ends. - Fix the cross-references at the media controller description. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-device.h | 24 +++++++------ include/media/media-entity.h | 83 ++++++++++++++++++++++++-------------------- 2 files changed, 58 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/media/media-device.h b/include/media/media-device.h index 4605fee0c228..28195242386c 100644 --- a/include/media/media-device.h +++ b/include/media/media-device.h @@ -242,13 +242,11 @@ void media_device_cleanup(struct media_device *mdev); * without breaking binary compatibility. The version major must be * incremented when binary compatibility is broken. * - * Notes: + * .. note:: * - * Upon successful registration a character device named media[0-9]+ is created. - * The device major and minor numbers are dynamic. The model name is exported as - * a sysfs attribute. + * #) Upon successful registration a character device named media[0-9]+ is created. The device major and minor numbers are dynamic. The model name is exported as a sysfs attribute. * - * Unregistering a media device that hasn't been registered is *NOT* safe. + * #) Unregistering a media device that hasn't been registered is **NOT** safe. * * Return: returns zero on success or a negative error code. */ @@ -296,14 +294,16 @@ void media_device_unregister(struct media_device *mdev); * This can be used to report the default audio and video devices or the * default camera sensor. * - * NOTE: Drivers should set the entity function before calling this function. - * Please notice that the values %MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN and - * %MEDIA_ENT_F_UNKNOWN should not be used by the drivers. + * .. note:: + * + * Drivers should set the entity function before calling this function. + * Please notice that the values %MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN and + * %MEDIA_ENT_F_UNKNOWN should not be used by the drivers. */ int __must_check media_device_register_entity(struct media_device *mdev, struct media_entity *entity); -/* +/** * media_device_unregister_entity() - unregisters a media entity. * * @entity: pointer to struct &media_entity to be unregistered @@ -317,8 +317,10 @@ int __must_check media_device_register_entity(struct media_device *mdev, * When a media device is unregistered, all its entities are unregistered * automatically. No manual entities unregistration is then required. * - * Note: the media_entity instance itself must be freed explicitly by - * the driver if required. + * .. note:: + * + * The media_entity instance itself must be freed explicitly by + * the driver if required. */ void media_device_unregister_entity(struct media_entity *entity); diff --git a/include/media/media-entity.h b/include/media/media-entity.h index cbb266f7f2b5..83877719bef4 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -104,7 +104,7 @@ struct media_entity_graph { int top; }; -/* +/** * struct media_pipeline - Media pipeline related information * * @streaming_count: Streaming start count - streaming stop count @@ -180,7 +180,7 @@ struct media_pad { * view. The media_entity_pipeline_start() function * validates all links by calling this operation. Optional. * - * Note: Those these callbacks are called with struct media_device.@graph_mutex + * .. note:: Those these callbacks are called with struct media_device.@graph_mutex * mutex held. */ struct media_entity_operations { @@ -602,19 +602,20 @@ static inline void media_entity_cleanup(struct media_entity *entity) {}; * @flags: Link flags, as defined in include/uapi/linux/media.h. * * Valid values for flags: - * A %MEDIA_LNK_FL_ENABLED flag indicates that the link is enabled and can be - * used to transfer media data. When two or more links target a sink pad, - * only one of them can be enabled at a time. * - * A %MEDIA_LNK_FL_IMMUTABLE flag indicates that the link enabled state can't - * be modified at runtime. If %MEDIA_LNK_FL_IMMUTABLE is set, then - * %MEDIA_LNK_FL_ENABLED must also be set since an immutable link is - * always enabled. + * - A %MEDIA_LNK_FL_ENABLED flag indicates that the link is enabled and can + * be used to transfer media data. When two or more links target a sink pad, + * only one of them can be enabled at a time. + * + * - A %MEDIA_LNK_FL_IMMUTABLE flag indicates that the link enabled state can't + * be modified at runtime. If %MEDIA_LNK_FL_IMMUTABLE is set, then + * %MEDIA_LNK_FL_ENABLED must also be set since an immutable link is + * always enabled. * - * NOTE: + * .. note:: * - * Before calling this function, media_entity_pads_init() and - * media_device_register_entity() should be called previously for both ends. + * Before calling this function, media_entity_pads_init() and + * media_device_register_entity() should be called previously for both ends. */ __must_check int media_create_pad_link(struct media_entity *source, u16 source_pad, struct media_entity *sink, @@ -641,6 +642,7 @@ __must_check int media_create_pad_link(struct media_entity *source, * and @sink are NULL. * * Valid values for flags: + * * A %MEDIA_LNK_FL_ENABLED flag indicates that the link is enabled and can be * used to transfer media data. If multiple links are created and this * flag is passed as an argument, only the first created link will have @@ -677,8 +679,10 @@ void __media_entity_remove_links(struct media_entity *entity); * * @entity: pointer to &media_entity * - * Note: this is called automatically when an entity is unregistered via - * media_device_register_entity(). + * .. note:: + * + * This is called automatically when an entity is unregistered via + * media_device_register_entity(). */ void media_entity_remove_links(struct media_entity *entity); @@ -728,9 +732,11 @@ int __media_entity_setup_link(struct media_link *link, u32 flags); * being enabled, the link_setup operation must return -EBUSY and can't * implicitly disable the first enabled link. * - * NOTE: the valid values of the flags for the link is the same as described - * on media_create_pad_link(), for pad to pad links or the same as described - * on media_create_intf_link(), for interface to entity links. + * .. note:: + * + * The valid values of the flags for the link is the same as described + * on media_create_pad_link(), for pad to pad links or the same as described + * on media_create_intf_link(), for interface to entity links. */ int media_entity_setup_link(struct media_link *link, u32 flags); @@ -844,7 +850,7 @@ __must_check int media_entity_pipeline_start(struct media_entity *entity, * @entity: Starting entity * @pipe: Media pipeline to be assigned to all entities in the pipeline. * - * Note: This is the non-locking version of media_entity_pipeline_start() + * ..note:: This is the non-locking version of media_entity_pipeline_start() */ __must_check int __media_entity_pipeline_start(struct media_entity *entity, struct media_pipeline *pipe); @@ -868,7 +874,7 @@ void media_entity_pipeline_stop(struct media_entity *entity); * * @entity: Starting entity * - * Note: This is the non-locking version of media_entity_pipeline_stop() + * .. note:: This is the non-locking version of media_entity_pipeline_stop() */ void __media_entity_pipeline_stop(struct media_entity *entity); @@ -909,20 +915,21 @@ struct media_link * * * * Valid values for flags: - * The %MEDIA_LNK_FL_ENABLED flag indicates that the interface is connected to - * the entity hardware. That's the default value for interfaces. An - * interface may be disabled if the hardware is busy due to the usage - * of some other interface that it is currently controlling the hardware. - * A typical example is an hybrid TV device that handle only one type of - * stream on a given time. So, when the digital TV is streaming, - * the V4L2 interfaces won't be enabled, as such device is not able to - * also stream analog TV or radio. * - * Note: + * - The %MEDIA_LNK_FL_ENABLED flag indicates that the interface is connected to + * the entity hardware. That's the default value for interfaces. An + * interface may be disabled if the hardware is busy due to the usage + * of some other interface that it is currently controlling the hardware. + * A typical example is an hybrid TV device that handle only one type of + * stream on a given time. So, when the digital TV is streaming, + * the V4L2 interfaces won't be enabled, as such device is not able to + * also stream analog TV or radio. + * + * .. note:: * - * Before calling this function, media_devnode_create() should be called for - * the interface and media_device_register_entity() should be called for the - * interface that will be part of the link. + * Before calling this function, media_devnode_create() should be called for + * the interface and media_device_register_entity() should be called for the + * interface that will be part of the link. */ __must_check media_create_intf_link(struct media_entity *entity, struct media_interface *intf, @@ -932,7 +939,7 @@ __must_check media_create_intf_link(struct media_entity *entity, * * @link: pointer to &media_link. * - * Note: this is an unlocked version of media_remove_intf_link() + * .. note:: This is an unlocked version of media_remove_intf_link() */ void __media_remove_intf_link(struct media_link *link); @@ -941,7 +948,7 @@ void __media_remove_intf_link(struct media_link *link); * * @link: pointer to &media_link. * - * Note: prefer to use this one, instead of __media_remove_intf_link() + * .. note:: Prefer to use this one, instead of __media_remove_intf_link() */ void media_remove_intf_link(struct media_link *link); @@ -950,7 +957,7 @@ void media_remove_intf_link(struct media_link *link); * * @intf: pointer to &media_interface * - * Note: this is an unlocked version of media_remove_intf_links(). + * .. note:: This is an unlocked version of media_remove_intf_links(). */ void __media_remove_intf_links(struct media_interface *intf); @@ -959,12 +966,12 @@ void __media_remove_intf_links(struct media_interface *intf); * * @intf: pointer to &media_interface * - * Notes: + * ..note:: * - * this is called automatically when an entity is unregistered via - * media_device_register_entity() and by media_devnode_remove(). + * - This is called automatically when an entity is unregistered via + * media_device_register_entity() and by media_devnode_remove(). * - * Prefer to use this one, instead of __media_remove_intf_links(). + * - Prefer to use this one, instead of __media_remove_intf_links(). */ void media_remove_intf_links(struct media_interface *intf); -- cgit v1.2.3 From a7284a82e826b88eb6264747cee57888d4076c48 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 6 Jun 2016 10:48:50 +0200 Subject: eeprom: at24: platform_data: use BIT() macro Use BIT() macro to replace the 0xXX constants in platform_data flags definitions. Signed-off-by: Bartosz Golaszewski Signed-off-by: Wolfram Sang --- include/linux/platform_data/at24.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h index be830b141d83..fcfdfe3c0e9c 100644 --- a/include/linux/platform_data/at24.h +++ b/include/linux/platform_data/at24.h @@ -10,6 +10,7 @@ #include #include +#include /** * struct at24_platform_data - data to set up at24 (generic eeprom) driver @@ -43,10 +44,10 @@ struct at24_platform_data { u32 byte_len; /* size (sum of all addr) */ u16 page_size; /* for writes */ u8 flags; -#define AT24_FLAG_ADDR16 0x80 /* address pointer is 16 bit */ -#define AT24_FLAG_READONLY 0x40 /* sysfs-entry will be read-only */ -#define AT24_FLAG_IRUGO 0x20 /* sysfs-entry will be world-readable */ -#define AT24_FLAG_TAKE8ADDR 0x10 /* take always 8 addresses (24c00) */ +#define AT24_FLAG_ADDR16 BIT(7) /* address pointer is 16 bit */ +#define AT24_FLAG_READONLY BIT(6) /* sysfs-entry will be read-only */ +#define AT24_FLAG_IRUGO BIT(5) /* sysfs-entry will be world-readable */ +#define AT24_FLAG_TAKE8ADDR BIT(4) /* take always 8 addresses (24c00) */ void (*setup)(struct nvmem_device *nvmem, void *context); void *context; -- cgit v1.2.3 From 818d0220d857cc92cb37600758c5b47c3df3782b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 6 Jun 2016 10:48:51 +0200 Subject: eeprom: at24: support reading the serial number for 24csxx The chips from the at24cs family have two memory areas - a regular read-write block and a read-only area containing the serial number. The latter is visible on a different slave address (the address of the rw memory block + 0x08). In order to access both blocks the user needs to instantiate a regular at24c device for the rw block address and a corresponding at24cs device on the serial number block address. Add a function that allows to access the serial number and assign it to at24->read_func if the chip allows serial number read operations and the driver was passed the relevant flag for this device. Signed-off-by: Bartosz Golaszewski Signed-off-by: Wolfram Sang --- include/linux/platform_data/at24.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h index fcfdfe3c0e9c..d59587473aed 100644 --- a/include/linux/platform_data/at24.h +++ b/include/linux/platform_data/at24.h @@ -48,6 +48,7 @@ struct at24_platform_data { #define AT24_FLAG_READONLY BIT(6) /* sysfs-entry will be read-only */ #define AT24_FLAG_IRUGO BIT(5) /* sysfs-entry will be world-readable */ #define AT24_FLAG_TAKE8ADDR BIT(4) /* take always 8 addresses (24c00) */ +#define AT24_FLAG_SERIAL BIT(3) /* factory-programmed serial number */ void (*setup)(struct nvmem_device *nvmem, void *context); void *context; -- cgit v1.2.3 From 0b813658c11532be90cbf5f579a8ba45a8cc9dbf Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 6 Jun 2016 10:48:54 +0200 Subject: eeprom: at24: add support for at24mac series Add a new read function to the at24 driver allowing to retrieve the factory-programmed mac address embedded in chips from the at24mac family. These chips can be instantiated similarily to the at24cs family, except that there's no way of having access to both the serial number and the mac address at the same time - the user must instantiate either an at24cs or at24mac device as both special memory areas are accessible on the same slave address. Signed-off-by: Bartosz Golaszewski Signed-off-by: Wolfram Sang --- include/linux/platform_data/at24.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/at24.h b/include/linux/platform_data/at24.h index d59587473aed..271a4e25af67 100644 --- a/include/linux/platform_data/at24.h +++ b/include/linux/platform_data/at24.h @@ -49,6 +49,7 @@ struct at24_platform_data { #define AT24_FLAG_IRUGO BIT(5) /* sysfs-entry will be world-readable */ #define AT24_FLAG_TAKE8ADDR BIT(4) /* take always 8 addresses (24c00) */ #define AT24_FLAG_SERIAL BIT(3) /* factory-programmed serial number */ +#define AT24_FLAG_MAC BIT(2) /* factory-programmed mac address */ void (*setup)(struct nvmem_device *nvmem, void *context); void *context; -- cgit v1.2.3 From 4360fa22ad5b48a1d1e10e31ffb383ed8c977435 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 6 Jun 2016 11:02:03 +0200 Subject: drivers: misc: ti-st: Use int instead of fuzzy char for callback status On mips and parisc: drivers/bluetooth/btwilink.c: In function 'ti_st_open': drivers/bluetooth/btwilink.c:174:21: warning: overflow in implicit constant conversion [-Woverflow] hst->reg_status = -EINPROGRESS; drivers/nfc/nfcwilink.c: In function 'nfcwilink_open': drivers/nfc/nfcwilink.c:396:31: warning: overflow in implicit constant conversion [-Woverflow] drv->st_register_cb_status = -EINPROGRESS; There are actually two issues: 1. Whether "char" is signed or unsigned depends on the architecture. As the completion callback data is used to pass a (negative) error code, it should always be signed. 2. EINPROGRESS is 150 on mips, 245 on parisc. Hence -EINPROGRESS doesn't fit in a signed 8-bit number. Change the callback status from "char" to "int" to fix these. Signed-off-by: Geert Uytterhoeven Acked-by: Mauro Carvalho Chehab Acked-by: Samuel Ortiz Signed-off-by: Marcel Holtmann --- include/linux/ti_wilink_st.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ti_wilink_st.h b/include/linux/ti_wilink_st.h index 0a0d56834c8e..f2293028ab9d 100644 --- a/include/linux/ti_wilink_st.h +++ b/include/linux/ti_wilink_st.h @@ -71,7 +71,7 @@ struct st_proto_s { enum proto_type type; long (*recv) (void *, struct sk_buff *); unsigned char (*match_packet) (const unsigned char *data); - void (*reg_complete_cb) (void *, char data); + void (*reg_complete_cb) (void *, int data); long (*write) (struct sk_buff *skb); void *priv_data; -- cgit v1.2.3 From 83fbae5a148cc1cd53e5be1a28edb3b6701b7af2 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Fri, 27 May 2016 17:33:54 +0200 Subject: watchdog: Add a device managed API for watchdog_register_device() This helps in reducing code in .remove callbacks and sometimes dropping .remove callbacks entirely. Signed-off-by: Neil Armstrong Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 51732d6c9555..6b75e38b683f 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -180,4 +180,7 @@ extern int watchdog_init_timeout(struct watchdog_device *wdd, extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); +/* devres register variant */ +int devm_watchdog_register_device(struct device *dev, struct watchdog_device *); + #endif /* ifndef _LINUX_WATCHDOG_H */ -- cgit v1.2.3 From f9f535c1b76128f94dae7a4bb41464aacd4c10ec Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 27 May 2016 14:19:06 -0700 Subject: watchdog: Improve description of min_hw_heartbeat_ms The description of min_hw_heartbeat_ms is misleading and needs some improvements. Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 6b75e38b683f..7047bc7f8106 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -66,7 +66,8 @@ struct watchdog_ops { * as configurable from user space. Only relevant if * max_hw_heartbeat_ms is not provided. * @min_hw_heartbeat_ms: - * Minimum time between heartbeats, in milli-seconds. + * Hardware limit for minimum time between heartbeats, + * in milli-seconds. * @max_hw_heartbeat_ms: * Hardware limit for maximum timeout, in milli-seconds. * Replaces max_timeout if specified. -- cgit v1.2.3 From f962fe32f2f85769cd835ddcecbff8c1d34cf561 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 17 Jul 2016 19:55:15 +0200 Subject: Bluetooth: Move hci_recv_frame and hci_recv_diag prototypes The protoypes for hci_recv_frame and hci_recv_diag are in the wrong location in the header file. Move them close to all the other hci_dev related exported functions. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 77d7fe115a0d..84d0273d826a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1022,6 +1022,8 @@ void hci_unregister_dev(struct hci_dev *hdev); int hci_suspend_dev(struct hci_dev *hdev); int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); +int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); +int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); @@ -1098,9 +1100,6 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance); void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb); -int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); -int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); - void hci_init_sysfs(struct hci_dev *hdev); void hci_conn_init_sysfs(struct hci_conn *conn); void hci_conn_add_sysfs(struct hci_conn *conn); -- cgit v1.2.3 From 5177a83827cd0b8cf6ce0391b00dd4417352d2f1 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sun, 17 Jul 2016 19:55:16 +0200 Subject: Bluetooth: Add debugfs fields for hardware and firmware info Some Bluetooth controllers allow for reading hardware and firmware related vendor specific infos. If they are available, then they can be exposed via debugfs now. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci_core.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 84d0273d826a..ee7fc47680a1 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -372,6 +372,8 @@ struct hci_dev { atomic_t promisc; + const char *hw_info; + const char *fw_info; struct dentry *debugfs; struct device dev; @@ -1024,6 +1026,8 @@ int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb); int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb); +void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...); +void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); int hci_dev_do_close(struct hci_dev *hdev); -- cgit v1.2.3 From d966c943e4dbb66e3afd9f300501c9f3b1c802fd Mon Sep 17 00:00:00 2001 From: Tony Makkiel Date: Mon, 11 Jul 2016 11:48:49 +0100 Subject: leds: LED driver for TI LP3952 6-Channel Color LED The chip can drive 2 sets of RGB leds. Controller can be controlled via PWM, I2C and audio synchronisation. This driver uses I2C to communicate with the chip. Datasheet: http://www.ti.com/lit/gpn/lp3952 Signed-off-by: Tony Makkiel Reviewed-by: Mika Westerberg Reviewed-by: Axel Lin Signed-off-by: Jacek Anaszewski --- include/linux/leds-lp3952.h | 125 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 125 insertions(+) create mode 100644 include/linux/leds-lp3952.h (limited to 'include') diff --git a/include/linux/leds-lp3952.h b/include/linux/leds-lp3952.h new file mode 100644 index 000000000000..49b37ed8d456 --- /dev/null +++ b/include/linux/leds-lp3952.h @@ -0,0 +1,125 @@ +/* + * LED driver for TI lp3952 controller + * + * Copyright (C) 2016, DAQRI, LLC. + * Author: Tony Makkiel + * + * 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 LEDS_LP3952_H_ +#define LEDS_LP3952_H_ + +#define LP3952_NAME "lp3952" +#define LP3952_CMD_REG_COUNT 8 +#define LP3952_BRIGHT_MAX 4 +#define LP3952_LABEL_MAX_LEN 15 + +#define LP3952_REG_LED_CTRL 0x00 +#define LP3952_REG_R1_BLNK_TIME_CTRL 0x01 +#define LP3952_REG_R1_BLNK_CYCLE_CTRL 0x02 +#define LP3952_REG_G1_BLNK_TIME_CTRL 0x03 +#define LP3952_REG_G1_BLNK_CYCLE_CTRL 0x04 +#define LP3952_REG_B1_BLNK_TIME_CTRL 0x05 +#define LP3952_REG_B1_BLNK_CYCLE_CTRL 0x06 +#define LP3952_REG_ENABLES 0x0B +#define LP3952_REG_PAT_GEN_CTRL 0x11 +#define LP3952_REG_RGB1_MAX_I_CTRL 0x12 +#define LP3952_REG_RGB2_MAX_I_CTRL 0x13 +#define LP3952_REG_CMD_0 0x50 +#define LP3952_REG_RESET 0x60 +#define REG_MAX LP3952_REG_RESET + +#define LP3952_PATRN_LOOP BIT(1) +#define LP3952_PATRN_GEN_EN BIT(2) +#define LP3952_INT_B00ST_LDR BIT(2) +#define LP3952_ACTIVE_MODE BIT(6) +#define LP3952_LED_MASK_ALL 0x3f + +/* Transition Time in ms */ +enum lp3952_tt { + TT0, + TT55, + TT110, + TT221, + TT422, + TT885, + TT1770, + TT3539 +}; + +/* Command Execution Time in ms */ +enum lp3952_cet { + CET197, + CET393, + CET590, + CET786, + CET1180, + CET1376, + CET1573, + CET1769, + CET1966, + CET2163, + CET2359, + CET2556, + CET2763, + CET2949, + CET3146 +}; + +/* Max Current in % */ +enum lp3952_colour_I_log_0 { + I0, + I7, + I14, + I21, + I32, + I46, + I71, + I100 +}; + +enum lp3952_leds { + LP3952_BLUE_2, + LP3952_GREEN_2, + LP3952_RED_2, + LP3952_BLUE_1, + LP3952_GREEN_1, + LP3952_RED_1, + LP3952_LED_ALL +}; + +struct lp3952_ctrl_hdl { + struct led_classdev cdev; + char name[LP3952_LABEL_MAX_LEN]; + enum lp3952_leds channel; + void *priv; +}; + +struct ptrn_gen_cmd { + union { + struct { + u16 tt:3; + u16 b:3; + u16 cet:4; + u16 g:3; + u16 r:3; + }; + struct { + u8 lsb; + u8 msb; + } bytes; + }; +} __packed; + +struct lp3952_led_array { + struct regmap *regmap; + struct i2c_client *client; + struct gpio_desc *enable_gpio; + struct lp3952_ctrl_hdl leds[LP3952_LED_ALL]; +}; + +#endif /* LEDS_LP3952_H_ */ -- cgit v1.2.3 From 4e6c3df4d729f85997cbf276bfa8ffd8579b8e77 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:31 +0800 Subject: crypto: skcipher - Add low-level skcipher interface This patch allows skcipher algorithms and instances to be created and registered with the crypto API. They are accessible through the top-level skcipher interface, along with ablkcipher/blkcipher algorithms and instances. This patch also introduces a new parameter called chunk size which is meant for ciphers such as CTR and CTS which ostensibly can handle arbitrary lengths, but still behave like block ciphers in that you can only process a partial block at the very end. For these ciphers the block size will continue to be set to 1 as it is now while the chunk size will be set to the underlying block size. Signed-off-by: Herbert Xu --- include/crypto/internal/skcipher.h | 87 +++++++++++++++++++++++++ include/crypto/skcipher.h | 130 +++++++++++++++++++++++++++++++++++++ include/linux/crypto.h | 1 + 3 files changed, 218 insertions(+) (limited to 'include') diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index 2cf7a61ece59..ce6619c339fe 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -19,12 +19,46 @@ struct rtattr; +struct skcipher_instance { + void (*free)(struct skcipher_instance *inst); + union { + struct { + char head[offsetof(struct skcipher_alg, base)]; + struct crypto_instance base; + } s; + struct skcipher_alg alg; + }; +}; + struct crypto_skcipher_spawn { struct crypto_spawn base; }; extern const struct crypto_type crypto_givcipher_type; +static inline struct crypto_instance *skcipher_crypto_instance( + struct skcipher_instance *inst) +{ + return &inst->s.base; +} + +static inline struct skcipher_instance *skcipher_alg_instance( + struct crypto_skcipher *skcipher) +{ + return container_of(crypto_skcipher_alg(skcipher), + struct skcipher_instance, alg); +} + +static inline void *skcipher_instance_ctx(struct skcipher_instance *inst) +{ + return crypto_instance_ctx(skcipher_crypto_instance(inst)); +} + +static inline void skcipher_request_complete(struct skcipher_request *req, int err) +{ + req->base.complete(&req->base, err); +} + static inline void crypto_set_skcipher_spawn( struct crypto_skcipher_spawn *spawn, struct crypto_instance *inst) { @@ -33,6 +67,8 @@ static inline void crypto_set_skcipher_spawn( int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name, u32 type, u32 mask); +int crypto_grab_skcipher2(struct crypto_skcipher_spawn *spawn, + const char *name, u32 type, u32 mask); struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask); @@ -47,6 +83,12 @@ static inline struct crypto_alg *crypto_skcipher_spawn_alg( return spawn->base.alg; } +static inline struct skcipher_alg *crypto_spawn_skcipher_alg( + struct crypto_skcipher_spawn *spawn) +{ + return container_of(spawn->base.alg, struct skcipher_alg, base); +} + static inline struct crypto_ablkcipher *crypto_spawn_skcipher( struct crypto_skcipher_spawn *spawn) { @@ -55,6 +97,25 @@ static inline struct crypto_ablkcipher *crypto_spawn_skcipher( crypto_skcipher_mask(0))); } +static inline struct crypto_skcipher *crypto_spawn_skcipher2( + struct crypto_skcipher_spawn *spawn) +{ + return crypto_spawn_tfm2(&spawn->base); +} + +static inline void crypto_skcipher_set_reqsize( + struct crypto_skcipher *skcipher, unsigned int reqsize) +{ + skcipher->reqsize = reqsize; +} + +int crypto_register_skcipher(struct skcipher_alg *alg); +void crypto_unregister_skcipher(struct skcipher_alg *alg); +int crypto_register_skciphers(struct skcipher_alg *algs, int count); +void crypto_unregister_skciphers(struct skcipher_alg *algs, int count); +int skcipher_register_instance(struct crypto_template *tmpl, + struct skcipher_instance *inst); + int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req); int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req); const char *crypto_default_geniv(const struct crypto_alg *alg); @@ -122,5 +183,31 @@ static inline u32 skcipher_request_flags(struct skcipher_request *req) return req->base.flags; } +static inline unsigned int crypto_skcipher_alg_min_keysize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blkcipher.min_keysize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_ablkcipher.min_keysize; + + return alg->min_keysize; +} + +static inline unsigned int crypto_skcipher_alg_max_keysize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blkcipher.max_keysize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_ablkcipher.max_keysize; + + return alg->max_keysize; +} + #endif /* _CRYPTO_INTERNAL_SKCIPHER_H */ diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 0f987f50bb52..a381f57ea695 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -65,6 +65,75 @@ struct crypto_skcipher { struct crypto_tfm base; }; +/** + * struct skcipher_alg - symmetric key cipher definition + * @min_keysize: Minimum key size supported by the transformation. This is the + * smallest key length supported by this transformation algorithm. + * This must be set to one of the pre-defined values as this is + * not hardware specific. Possible values for this field can be + * found via git grep "_MIN_KEY_SIZE" include/crypto/ + * @max_keysize: Maximum key size supported by the transformation. This is the + * largest key length supported by this transformation algorithm. + * This must be set to one of the pre-defined values as this is + * not hardware specific. Possible values for this field can be + * found via git grep "_MAX_KEY_SIZE" include/crypto/ + * @setkey: Set key for the transformation. This function is used to either + * program a supplied key into the hardware or store the key in the + * transformation context for programming it later. Note that this + * function does modify the transformation context. This function can + * be called multiple times during the existence of the transformation + * object, so one must make sure the key is properly reprogrammed into + * the hardware. This function is also responsible for checking the key + * length for validity. In case a software fallback was put in place in + * the @cra_init call, this function might need to use the fallback if + * the algorithm doesn't support all of the key sizes. + * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt + * the supplied scatterlist containing the blocks of data. The crypto + * API consumer is responsible for aligning the entries of the + * scatterlist properly and making sure the chunks are correctly + * sized. In case a software fallback was put in place in the + * @cra_init call, this function might need to use the fallback if + * the algorithm doesn't support all of the key sizes. In case the + * key was stored in transformation context, the key might need to be + * re-programmed into the hardware in this function. This function + * shall not modify the transformation context, as this function may + * be called in parallel with the same transformation object. + * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt + * and the conditions are exactly the same. + * @init: Initialize the cryptographic transformation object. This function + * is used to initialize the cryptographic transformation object. + * This function is called only once at the instantiation time, right + * after the transformation context was allocated. In case the + * cryptographic hardware has some special requirements which need to + * be handled by software, this function shall check for the precise + * requirement of the transformation and put any software fallbacks + * in place. + * @exit: Deinitialize the cryptographic transformation object. This is a + * counterpart to @init, used to remove various changes set in + * @init. + * @ivsize: IV size applicable for transformation. The consumer must provide an + * IV of exactly that size to perform the encrypt or decrypt operation. + * @chunksize: Equal to the block size except for stream ciphers such as + * CTR where it is set to the underlying block size. + * + * All fields except @ivsize are mandatory and must be filled. + */ +struct skcipher_alg { + int (*setkey)(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen); + int (*encrypt)(struct skcipher_request *req); + int (*decrypt)(struct skcipher_request *req); + int (*init)(struct crypto_skcipher *tfm); + void (*exit)(struct crypto_skcipher *tfm); + + unsigned int min_keysize; + unsigned int max_keysize; + unsigned int ivsize; + unsigned int chunksize; + + struct crypto_alg base; +}; + #define SKCIPHER_REQUEST_ON_STACK(name, tfm) \ char __##name##_desc[sizeof(struct skcipher_request) + \ crypto_skcipher_reqsize(tfm)] CRYPTO_MINALIGN_ATTR; \ @@ -231,12 +300,43 @@ static inline int crypto_has_skcipher(const char *alg_name, u32 type, crypto_skcipher_mask(mask)); } +/** + * crypto_has_skcipher2() - Search for the availability of an skcipher. + * @alg_name: is the cra_name / name or cra_driver_name / driver name of the + * skcipher + * @type: specifies the type of the skcipher + * @mask: specifies the mask for the skcipher + * + * Return: true when the skcipher is known to the kernel crypto API; false + * otherwise + */ +int crypto_has_skcipher2(const char *alg_name, u32 type, u32 mask); + static inline const char *crypto_skcipher_driver_name( struct crypto_skcipher *tfm) { return crypto_tfm_alg_driver_name(crypto_skcipher_tfm(tfm)); } +static inline struct skcipher_alg *crypto_skcipher_alg( + struct crypto_skcipher *tfm) +{ + return container_of(crypto_skcipher_tfm(tfm)->__crt_alg, + struct skcipher_alg, base); +} + +static inline unsigned int crypto_skcipher_alg_ivsize(struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blkcipher.ivsize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_ablkcipher.ivsize; + + return alg->ivsize; +} + /** * crypto_skcipher_ivsize() - obtain IV size * @tfm: cipher handle @@ -251,6 +351,36 @@ static inline unsigned int crypto_skcipher_ivsize(struct crypto_skcipher *tfm) return tfm->ivsize; } +static inline unsigned int crypto_skcipher_alg_chunksize( + struct skcipher_alg *alg) +{ + if ((alg->base.cra_flags & CRYPTO_ALG_TYPE_MASK) == + CRYPTO_ALG_TYPE_BLKCIPHER) + return alg->base.cra_blocksize; + + if (alg->base.cra_ablkcipher.encrypt) + return alg->base.cra_blocksize; + + return alg->chunksize; +} + +/** + * crypto_skcipher_chunksize() - obtain chunk size + * @tfm: cipher handle + * + * The block size is set to one for ciphers such as CTR. However, + * you still need to provide incremental updates in multiples of + * the underlying block size as the IV does not have sub-block + * granularity. This is known in this API as the chunk size. + * + * Return: chunk size in bytes + */ +static inline unsigned int crypto_skcipher_chunksize( + struct crypto_skcipher *tfm) +{ + return crypto_skcipher_alg_chunksize(crypto_skcipher_alg(tfm)); +} + /** * crypto_skcipher_blocksize() - obtain block size of cipher * @tfm: cipher handle diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 992cfc2e5df1..37a652d1639d 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -47,6 +47,7 @@ #define CRYPTO_ALG_TYPE_AEAD 0x00000003 #define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 +#define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_GIVCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_RNG 0x0000000c -- cgit v1.2.3 From a0129733a3f5eaa973c1ea76848d905b851548f1 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:32 +0800 Subject: crypto: null - Add new default null skcipher Current the default null skcipher is actually a crypto_blkcipher. This patch creates a synchronous crypto_skcipher version of the null cipher which unfortunately has to settle for the name skcipher2. Signed-off-by: Herbert Xu --- include/crypto/null.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/crypto/null.h b/include/crypto/null.h index 06dc30d9f56e..dda87cbb62b2 100644 --- a/include/crypto/null.h +++ b/include/crypto/null.h @@ -10,5 +10,7 @@ struct crypto_blkcipher *crypto_get_default_null_skcipher(void); void crypto_put_default_null_skcipher(void); +struct crypto_skcipher *crypto_get_default_null_skcipher2(void); +void crypto_put_default_null_skcipher2(void); #endif -- cgit v1.2.3 From 7a530aa9cf3f282b6b123b9296dfce80ed8f068e Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:33 +0800 Subject: crypto: aead - Add chunk size This patch adds a chunk size parameter to aead algorithms, just like the chunk size for skcipher algorithms. However, unlike skcipher we do not currently export this to AEAD users. It is only meant to be used by AEAD implementors for now. Signed-off-by: Herbert Xu --- include/crypto/aead.h | 12 +++++++----- include/crypto/internal/aead.h | 21 +++++++++++++++++++++ 2 files changed, 28 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/crypto/aead.h b/include/crypto/aead.h index 75174f80a106..12f84327ca36 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -112,11 +112,12 @@ struct aead_request { * supplied during the decryption operation. This function is also * responsible for checking the authentication tag size for * validity. - * @setkey: see struct ablkcipher_alg - * @encrypt: see struct ablkcipher_alg - * @decrypt: see struct ablkcipher_alg - * @geniv: see struct ablkcipher_alg - * @ivsize: see struct ablkcipher_alg + * @setkey: see struct skcipher_alg + * @encrypt: see struct skcipher_alg + * @decrypt: see struct skcipher_alg + * @geniv: see struct skcipher_alg + * @ivsize: see struct skcipher_alg + * @chunksize: see struct skcipher_alg * @init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right @@ -145,6 +146,7 @@ struct aead_alg { unsigned int ivsize; unsigned int maxauthsize; + unsigned int chunksize; struct crypto_alg base; }; diff --git a/include/crypto/internal/aead.h b/include/crypto/internal/aead.h index da3864991d4c..6ad8e31d3868 100644 --- a/include/crypto/internal/aead.h +++ b/include/crypto/internal/aead.h @@ -159,6 +159,27 @@ static inline struct aead_request *aead_get_backlog(struct aead_queue *queue) return req ? container_of(req, struct aead_request, base) : NULL; } +static inline unsigned int crypto_aead_alg_chunksize(struct aead_alg *alg) +{ + return alg->chunksize; +} + +/** + * crypto_aead_chunksize() - obtain chunk size + * @tfm: cipher handle + * + * The block size is set to one for ciphers such as CCM. However, + * you still need to provide incremental updates in multiples of + * the underlying block size as the IV does not have sub-block + * granularity. This is known in this API as the chunk size. + * + * Return: chunk size in bytes + */ +static inline unsigned int crypto_aead_chunksize(struct crypto_aead *tfm) +{ + return crypto_aead_alg_chunksize(crypto_aead_alg(tfm)); +} + int crypto_register_aead(struct aead_alg *alg); void crypto_unregister_aead(struct aead_alg *alg); int crypto_register_aeads(struct aead_alg *algs, int count); -- cgit v1.2.3 From ca0494c093371b1ca3cd4c8e14e1e7a19e6e21b6 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:42 +0800 Subject: crypto: aead - Add skcipher null for IV generators This patch adds an skcipher null object alongside the existing null blkcipher so that IV generators using it can switch over to skcipher. Signed-off-by: Herbert Xu --- include/crypto/internal/geniv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/crypto/internal/geniv.h b/include/crypto/internal/geniv.h index 59333635e712..e8447c9c14e6 100644 --- a/include/crypto/internal/geniv.h +++ b/include/crypto/internal/geniv.h @@ -21,6 +21,7 @@ struct aead_geniv_ctx { spinlock_t lock; struct crypto_aead *child; struct crypto_blkcipher *null; + struct crypto_skcipher *sknull; u8 salt[] __attribute__ ((aligned(__alignof__(u32)))); }; -- cgit v1.2.3 From da721302a78807e5da2902677fbe116fe052068f Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:46 +0800 Subject: crypto: aead - Remove blkcipher null for IV generators The blkcipher null object is no longer used and can now be removed. Signed-off-by: Herbert Xu --- include/crypto/internal/geniv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/crypto/internal/geniv.h b/include/crypto/internal/geniv.h index e8447c9c14e6..2bcfb931bc5b 100644 --- a/include/crypto/internal/geniv.h +++ b/include/crypto/internal/geniv.h @@ -20,7 +20,6 @@ struct aead_geniv_ctx { spinlock_t lock; struct crypto_aead *child; - struct crypto_blkcipher *null; struct crypto_skcipher *sknull; u8 salt[] __attribute__ ((aligned(__alignof__(u32)))); }; -- cgit v1.2.3 From 499a66e6b689b13d1a4108bec5d7dcdc829a27a8 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:47 +0800 Subject: crypto: null - Remove default null blkcipher The default null blkcipher is no longer used and can now be removed. Signed-off-by: Herbert Xu --- include/crypto/null.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/crypto/null.h b/include/crypto/null.h index dda87cbb62b2..3f0c59fb0a61 100644 --- a/include/crypto/null.h +++ b/include/crypto/null.h @@ -8,9 +8,17 @@ #define NULL_DIGEST_SIZE 0 #define NULL_IV_SIZE 0 -struct crypto_blkcipher *crypto_get_default_null_skcipher(void); +struct crypto_skcipher *crypto_get_default_null_skcipher(void); void crypto_put_default_null_skcipher(void); -struct crypto_skcipher *crypto_get_default_null_skcipher2(void); -void crypto_put_default_null_skcipher2(void); + +static inline struct crypto_skcipher *crypto_get_default_null_skcipher2(void) +{ + return crypto_get_default_null_skcipher(); +} + +static inline void crypto_put_default_null_skcipher2(void) +{ + crypto_put_default_null_skcipher(); +} #endif -- cgit v1.2.3 From 3a01d0ee2b991c8c267620e63a4ab47cd8c30cc4 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:50 +0800 Subject: crypto: skcipher - Remove top-level givcipher interface This patch removes the old crypto_grab_skcipher helper and replaces it with crypto_grab_skcipher2. As this is the final entry point into givcipher this patch also removes all traces of the top-level givcipher interface, including all implicit IV generators such as chainiv. The bottom-level givcipher interface remains until the drivers using it are converted. Signed-off-by: Herbert Xu --- include/crypto/internal/skcipher.h | 63 ++++++------------------------- include/crypto/skcipher.h | 76 -------------------------------------- include/linux/crypto.h | 19 ---------- 3 files changed, 12 insertions(+), 146 deletions(-) (limited to 'include') diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h index ce6619c339fe..a21a95e1a375 100644 --- a/include/crypto/internal/skcipher.h +++ b/include/crypto/internal/skcipher.h @@ -67,8 +67,12 @@ static inline void crypto_set_skcipher_spawn( int crypto_grab_skcipher(struct crypto_skcipher_spawn *spawn, const char *name, u32 type, u32 mask); -int crypto_grab_skcipher2(struct crypto_skcipher_spawn *spawn, - const char *name, u32 type, u32 mask); + +static inline int crypto_grab_skcipher2(struct crypto_skcipher_spawn *spawn, + const char *name, u32 type, u32 mask) +{ + return crypto_grab_skcipher(spawn, name, type, mask); +} struct crypto_alg *crypto_lookup_skcipher(const char *name, u32 type, u32 mask); @@ -77,30 +81,28 @@ static inline void crypto_drop_skcipher(struct crypto_skcipher_spawn *spawn) crypto_drop_spawn(&spawn->base); } -static inline struct crypto_alg *crypto_skcipher_spawn_alg( +static inline struct skcipher_alg *crypto_skcipher_spawn_alg( struct crypto_skcipher_spawn *spawn) { - return spawn->base.alg; + return container_of(spawn->base.alg, struct skcipher_alg, base); } static inline struct skcipher_alg *crypto_spawn_skcipher_alg( struct crypto_skcipher_spawn *spawn) { - return container_of(spawn->base.alg, struct skcipher_alg, base); + return crypto_skcipher_spawn_alg(spawn); } -static inline struct crypto_ablkcipher *crypto_spawn_skcipher( +static inline struct crypto_skcipher *crypto_spawn_skcipher( struct crypto_skcipher_spawn *spawn) { - return __crypto_ablkcipher_cast( - crypto_spawn_tfm(&spawn->base, crypto_skcipher_type(0), - crypto_skcipher_mask(0))); + return crypto_spawn_tfm2(&spawn->base); } static inline struct crypto_skcipher *crypto_spawn_skcipher2( struct crypto_skcipher_spawn *spawn) { - return crypto_spawn_tfm2(&spawn->base); + return crypto_spawn_skcipher(spawn); } static inline void crypto_skcipher_set_reqsize( @@ -116,53 +118,12 @@ void crypto_unregister_skciphers(struct skcipher_alg *algs, int count); int skcipher_register_instance(struct crypto_template *tmpl, struct skcipher_instance *inst); -int skcipher_null_givencrypt(struct skcipher_givcrypt_request *req); -int skcipher_null_givdecrypt(struct skcipher_givcrypt_request *req); -const char *crypto_default_geniv(const struct crypto_alg *alg); - -struct crypto_instance *skcipher_geniv_alloc(struct crypto_template *tmpl, - struct rtattr **tb, u32 type, - u32 mask); -void skcipher_geniv_free(struct crypto_instance *inst); -int skcipher_geniv_init(struct crypto_tfm *tfm); -void skcipher_geniv_exit(struct crypto_tfm *tfm); - -static inline struct crypto_ablkcipher *skcipher_geniv_cipher( - struct crypto_ablkcipher *geniv) -{ - return crypto_ablkcipher_crt(geniv)->base; -} - -static inline int skcipher_enqueue_givcrypt( - struct crypto_queue *queue, struct skcipher_givcrypt_request *request) -{ - return ablkcipher_enqueue_request(queue, &request->creq); -} - -static inline struct skcipher_givcrypt_request *skcipher_dequeue_givcrypt( - struct crypto_queue *queue) -{ - return skcipher_givcrypt_cast(crypto_dequeue_request(queue)); -} - -static inline void *skcipher_givcrypt_reqctx( - struct skcipher_givcrypt_request *req) -{ - return ablkcipher_request_ctx(&req->creq); -} - static inline void ablkcipher_request_complete(struct ablkcipher_request *req, int err) { req->base.complete(&req->base, err); } -static inline void skcipher_givcrypt_complete( - struct skcipher_givcrypt_request *req, int err) -{ - ablkcipher_request_complete(&req->creq, err); -} - static inline u32 ablkcipher_request_flags(struct ablkcipher_request *req) { return req->base.flags; diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index a381f57ea695..59c8f6c593e6 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -139,82 +139,6 @@ struct skcipher_alg { crypto_skcipher_reqsize(tfm)] CRYPTO_MINALIGN_ATTR; \ struct skcipher_request *name = (void *)__##name##_desc -static inline struct crypto_ablkcipher *skcipher_givcrypt_reqtfm( - struct skcipher_givcrypt_request *req) -{ - return crypto_ablkcipher_reqtfm(&req->creq); -} - -static inline int crypto_skcipher_givencrypt( - struct skcipher_givcrypt_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req)); - return crt->givencrypt(req); -}; - -static inline int crypto_skcipher_givdecrypt( - struct skcipher_givcrypt_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(skcipher_givcrypt_reqtfm(req)); - return crt->givdecrypt(req); -}; - -static inline void skcipher_givcrypt_set_tfm( - struct skcipher_givcrypt_request *req, struct crypto_ablkcipher *tfm) -{ - req->creq.base.tfm = crypto_ablkcipher_tfm(tfm); -} - -static inline struct skcipher_givcrypt_request *skcipher_givcrypt_cast( - struct crypto_async_request *req) -{ - return container_of(ablkcipher_request_cast(req), - struct skcipher_givcrypt_request, creq); -} - -static inline struct skcipher_givcrypt_request *skcipher_givcrypt_alloc( - struct crypto_ablkcipher *tfm, gfp_t gfp) -{ - struct skcipher_givcrypt_request *req; - - req = kmalloc(sizeof(struct skcipher_givcrypt_request) + - crypto_ablkcipher_reqsize(tfm), gfp); - - if (likely(req)) - skcipher_givcrypt_set_tfm(req, tfm); - - return req; -} - -static inline void skcipher_givcrypt_free(struct skcipher_givcrypt_request *req) -{ - kfree(req); -} - -static inline void skcipher_givcrypt_set_callback( - struct skcipher_givcrypt_request *req, u32 flags, - crypto_completion_t compl, void *data) -{ - ablkcipher_request_set_callback(&req->creq, flags, compl, data); -} - -static inline void skcipher_givcrypt_set_crypt( - struct skcipher_givcrypt_request *req, - struct scatterlist *src, struct scatterlist *dst, - unsigned int nbytes, void *iv) -{ - ablkcipher_request_set_crypt(&req->creq, src, dst, nbytes, iv); -} - -static inline void skcipher_givcrypt_set_giv( - struct skcipher_givcrypt_request *req, u8 *giv, u64 seq) -{ - req->giv = giv; - req->seq = seq; -} - /** * DOC: Symmetric Key Cipher API * diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 37a652d1639d..7cee5551625b 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -488,8 +488,6 @@ struct ablkcipher_tfm { unsigned int keylen); int (*encrypt)(struct ablkcipher_request *req); int (*decrypt)(struct ablkcipher_request *req); - int (*givencrypt)(struct skcipher_givcrypt_request *req); - int (*givdecrypt)(struct skcipher_givcrypt_request *req); struct crypto_ablkcipher *base; @@ -714,23 +712,6 @@ static inline u32 crypto_skcipher_mask(u32 mask) * state information is unused by the kernel crypto API. */ -/** - * crypto_alloc_ablkcipher() - allocate asynchronous block cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * ablkcipher cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for an ablkcipher. The returned struct - * crypto_ablkcipher is the cipher handle that is required for any subsequent - * API invocation for that ablkcipher. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -struct crypto_ablkcipher *crypto_alloc_ablkcipher(const char *alg_name, - u32 type, u32 mask); - static inline struct crypto_tfm *crypto_ablkcipher_tfm( struct crypto_ablkcipher *tfm) { -- cgit v1.2.3 From 5506f53c7cc17c4ad5e69e5512a35faf77182986 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:53 +0800 Subject: crypto: scatterwalk - Remove scatterwalk_bytes_sglen This patch removes the now unused scatterwalk_bytes_sglen. Anyone using this out-of-tree should switch over to sg_nents_for_len. Signed-off-by: Herbert Xu --- include/crypto/scatterwalk.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 35f99b68d037..7e1a33645eb5 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -92,8 +92,6 @@ void scatterwalk_done(struct scatter_walk *walk, int out, int more); void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes, int out); -int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes); - struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2], struct scatterlist *src, unsigned int len); -- cgit v1.2.3 From 4140139734459db4dffc50dad7b9e21ed79a8dd9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:17:56 +0800 Subject: crypto: api - Optimise away crypto_yield when hard preemption is on When hard preemption is enabled there is no need to explicitly call crypto_yield. This patch eliminates it if that is the case. Signed-off-by: Herbert Xu --- include/crypto/algapi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h index 0483f652ac27..8637cdfe382a 100644 --- a/include/crypto/algapi.h +++ b/include/crypto/algapi.h @@ -442,8 +442,10 @@ static inline int crypto_memneq(const void *a, const void *b, size_t size) static inline void crypto_yield(u32 flags) { +#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY) if (flags & CRYPTO_TFM_REQ_MAY_SLEEP) cond_resched(); +#endif } #endif /* _CRYPTO_ALGAPI_H */ -- cgit v1.2.3 From ac02725812cb3a814cfe1fdc2a8a59db073e7e66 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 12 Jul 2016 13:18:00 +0800 Subject: crypto: scatterwalk - Inline start/map/done This patch inlines the functions scatterwalk_start, scatterwalk_map and scatterwalk_done as they're all tiny and mostly used by the block cipher walker. Signed-off-by: Herbert Xu --- include/crypto/scatterwalk.h | 46 ++++++++++++++++++++++++++++++++++++++------ 1 file changed, 40 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 7e1a33645eb5..880e6be9e95e 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -16,14 +16,10 @@ #ifndef _CRYPTO_SCATTERWALK_H #define _CRYPTO_SCATTERWALK_H -#include #include -#include #include #include -#include #include -#include static inline void scatterwalk_crypto_chain(struct scatterlist *head, struct scatterlist *sg, @@ -83,11 +79,49 @@ static inline void scatterwalk_unmap(void *vaddr) kunmap_atomic(vaddr); } -void scatterwalk_start(struct scatter_walk *walk, struct scatterlist *sg); +static inline void scatterwalk_start(struct scatter_walk *walk, + struct scatterlist *sg) +{ + walk->sg = sg; + walk->offset = sg->offset; +} + +static inline void *scatterwalk_map(struct scatter_walk *walk) +{ + return kmap_atomic(scatterwalk_page(walk)) + + offset_in_page(walk->offset); +} + +static inline void scatterwalk_pagedone(struct scatter_walk *walk, int out, + unsigned int more) +{ + if (out) { + struct page *page; + + page = sg_page(walk->sg) + ((walk->offset - 1) >> PAGE_SHIFT); + /* Test ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE first as + * PageSlab cannot be optimised away per se due to + * use of volatile pointer. + */ + if (ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE && !PageSlab(page)) + flush_dcache_page(page); + } + + if (more && walk->offset >= walk->sg->offset + walk->sg->length) + scatterwalk_start(walk, sg_next(walk->sg)); +} + +static inline void scatterwalk_done(struct scatter_walk *walk, int out, + int more) +{ + if (!more || walk->offset >= walk->sg->offset + walk->sg->length || + !(walk->offset & (PAGE_SIZE - 1))) + scatterwalk_pagedone(walk, out, more); +} + void scatterwalk_copychunks(void *buf, struct scatter_walk *walk, size_t nbytes, int out); void *scatterwalk_map(struct scatter_walk *walk); -void scatterwalk_done(struct scatter_walk *walk, int out, int more); void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg, unsigned int start, unsigned int nbytes, int out); -- cgit v1.2.3 From 6502a34cfd6695929086187f63fe670cc3050e68 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 21 Jun 2016 14:19:51 +0200 Subject: KVM: s390: allow user space to handle instr 0x0000 We will use illegal instruction 0x0000 for handling 2 byte sw breakpoints from user space. As it can be enabled dynamically via a capability, let's move setting of ICTL_OPEREXC to the post creation step, so we avoid any races when enabling that capability just while adding new cpus. Acked-by: Janosch Frank Reviewed-by: Cornelia Huck Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4f8030e5b05d..70941f4ab6d8 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -867,6 +867,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_VCPU_ATTRIBUTES 127 #define KVM_CAP_MAX_VCPU_ID 128 #define KVM_CAP_X2APIC_API 129 +#define KVM_CAP_S390_USER_INSTR0 130 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 2fdf829236183e5be559a2b4d13c29926b79b2d4 Mon Sep 17 00:00:00 2001 From: Chen Zhong Date: Mon, 18 Jul 2016 14:40:51 +0200 Subject: regulator: mt6323: Add support for MT6323 regulator The MT6323 is a regulator found on boards based on MediaTek MT7623 and probably other SoCs. It is a so called pmic and connects as a slave to SoC using SPI, wrapped inside the pmic-wrapper. Signed-off-by: Chen Zhong Signed-off-by: John Crispin Signed-off-by: Mark Brown --- include/linux/regulator/mt6323-regulator.h | 52 ++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/regulator/mt6323-regulator.h (limited to 'include') diff --git a/include/linux/regulator/mt6323-regulator.h b/include/linux/regulator/mt6323-regulator.h new file mode 100644 index 000000000000..67011cd1ce55 --- /dev/null +++ b/include/linux/regulator/mt6323-regulator.h @@ -0,0 +1,52 @@ +/* + * Copyright (c) 2016 MediaTek Inc. + * Author: Chen Zhong + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_MT6323_H +#define __LINUX_REGULATOR_MT6323_H + +enum { + MT6323_ID_VPROC = 0, + MT6323_ID_VSYS, + MT6323_ID_VPA, + MT6323_ID_VTCXO, + MT6323_ID_VCN28, + MT6323_ID_VCN33_BT, + MT6323_ID_VCN33_WIFI, + MT6323_ID_VA, + MT6323_ID_VCAMA, + MT6323_ID_VIO28 = 9, + MT6323_ID_VUSB, + MT6323_ID_VMC, + MT6323_ID_VMCH, + MT6323_ID_VEMC3V3, + MT6323_ID_VGP1, + MT6323_ID_VGP2, + MT6323_ID_VGP3, + MT6323_ID_VCN18, + MT6323_ID_VSIM1, + MT6323_ID_VSIM2, + MT6323_ID_VRTC, + MT6323_ID_VCAMAF, + MT6323_ID_VIBR, + MT6323_ID_VRF18, + MT6323_ID_VM, + MT6323_ID_VIO18, + MT6323_ID_VCAMD, + MT6323_ID_VCAMIO, + MT6323_ID_RG_MAX, +}; + +#define MT6323_MAX_REGULATOR MT6323_ID_RG_MAX + +#endif /* __LINUX_REGULATOR_MT6323_H */ -- cgit v1.2.3 From 8f6cdc1c2eec20c3bbf3a83ad0e1db165f709917 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:22 +0100 Subject: KVM: arm/arm64: vgic: Move redistributor kvm_io_devices Logically a GICv3 redistributor is assigned to a (v)CPU, so we should aim to keep redistributor related variables out of our struct vgic_dist. Let's start by replacing the redistributor related kvm_io_device array with two members in our existing struct vgic_cpu, which are naturally per-VCPU and thus don't require any allocation / freeing. So apart from the better fit with the redistributor design this saves some code as well. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 12640378db98..5142e2ab9f5e 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -145,7 +145,6 @@ struct vgic_dist { struct vgic_irq *spis; struct vgic_io_device dist_iodev; - struct vgic_io_device *redist_iodevs; }; struct vgic_v2_cpu_if { @@ -193,6 +192,13 @@ struct vgic_cpu { struct list_head ap_list_head; u64 live_lrs; + + /* + * Members below are used with GICv3 emulation only and represent + * parts of the redistributor. + */ + struct vgic_io_device rd_iodev; + struct vgic_io_device sgi_iodev; }; int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); -- cgit v1.2.3 From 2b8ddd9337ee0d001b22507f95596648a1a90992 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:24 +0100 Subject: KVM: Extend struct kvm_msi to hold a 32-bit device ID The ARM GICv3 ITS MSI controller requires a device ID to be able to assign the proper interrupt vector. On real hardware, this ID is sampled from the bus. To be able to emulate an ITS controller, extend the KVM MSI interface to let userspace provide such a device ID. For PCI devices, the device ID is simply the 16-bit bus-device-function triplet, which should be easily available to the userland tool. Also there is a new KVM capability which advertises whether the current VM requires a device ID to be set along with the MSI data. This flag is still reported as not available everywhere, later we will enable it when ITS emulation is used. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Reviewed-by: Marc Zyngier Acked-by: Christoffer Dall Acked-by: Paolo Bonzini Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/uapi/linux/kvm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 05ebf475104c..7de96f5bb92c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -866,6 +866,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_ARM_PMU_V3 126 #define KVM_CAP_VCPU_ATTRIBUTES 127 #define KVM_CAP_MAX_VCPU_ID 128 +#define KVM_CAP_MSI_DEVID 129 #ifdef KVM_CAP_IRQ_ROUTING @@ -1024,12 +1025,14 @@ struct kvm_one_reg { __u64 addr; }; +#define KVM_MSI_VALID_DEVID (1U << 0) struct kvm_msi { __u32 address_lo; __u32 address_hi; __u32 data; __u32 flags; - __u8 pad[16]; + __u32 devid; + __u8 pad[12]; }; struct kvm_arm_device_addr { -- cgit v1.2.3 From 8a39d00670f0792c1186e442e1dd28fe0326f2ee Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:26 +0100 Subject: KVM: kvm_io_bus: Add kvm_io_bus_get_dev() call The kvm_io_bus framework is a nice place of holding information about various MMIO regions for kernel emulated devices. Add a call to retrieve the kvm_io_device structure which is associated with a certain MMIO address. This avoids to duplicate kvm_io_bus' knowledge of MMIO regions without having to fake MMIO calls if a user needs the device a certain MMIO address belongs to. This will be used by the ITS emulation to get the associated ITS device when someone triggers an MSI via an ioctl from userspace. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Reviewed-by: Marc Zyngier Acked-by: Christoffer Dall Acked-by: Paolo Bonzini Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0640ee92b978..614a98137c5f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -164,6 +164,8 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev); int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); +struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, + gpa_t addr); #ifdef CONFIG_KVM_ASYNC_PF struct kvm_async_pf { -- cgit v1.2.3 From 5dd4b924e390af426e424d5e52c1b4d1566af817 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:27 +0100 Subject: KVM: arm/arm64: vgic: Add refcounting for IRQs In the moment our struct vgic_irq's are statically allocated at guest creation time. So getting a pointer to an IRQ structure is trivial and safe. LPIs are more dynamic, they can be mapped and unmapped at any time during the guest's _runtime_. In preparation for supporting LPIs we introduce reference counting for those structures using the kernel's kref infrastructure. Since private IRQs and SPIs are statically allocated, we avoid actually refcounting them, since they would never be released anyway. But we take provisions to increase the refcount when an IRQ gets onto a VCPU list and decrease it when it gets removed. Also this introduces vgic_put_irq(), which wraps kref_put and hides the release function from the callers. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 5142e2ab9f5e..450b4dab9a9f 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -96,6 +96,7 @@ struct vgic_irq { bool active; /* not used for LPIs */ bool enabled; bool hw; /* Tied to HW IRQ */ + struct kref refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ union { u8 targets; /* GICv2 target VCPUs mask */ -- cgit v1.2.3 From 645b9e49a8c053182aae0765d797f557f7a67eda Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:28 +0100 Subject: irqchip/gic-v3: Refactor and add GICv3 definitions arm-gic-v3.h contains bit and register definitions for the GICv3 and ITS, at least for the bits the we currently care about. The ITS emulation needs more definitions, so add them and refactor the memory attribute #defines to be more universally usable. To avoid changing all users, we still provide some of the old definitons defined with the help of the new macros. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 180 ++++++++++++++++++++++++------------- 1 file changed, 120 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index bfbd707de390..9442be7f2461 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -112,34 +112,60 @@ #define GICR_WAKER_ProcessorSleep (1U << 1) #define GICR_WAKER_ChildrenAsleep (1U << 2) -#define GICR_PROPBASER_NonShareable (0U << 10) -#define GICR_PROPBASER_InnerShareable (1U << 10) -#define GICR_PROPBASER_OuterShareable (2U << 10) -#define GICR_PROPBASER_SHAREABILITY_MASK (3UL << 10) -#define GICR_PROPBASER_nCnB (0U << 7) -#define GICR_PROPBASER_nC (1U << 7) -#define GICR_PROPBASER_RaWt (2U << 7) -#define GICR_PROPBASER_RaWb (3U << 7) -#define GICR_PROPBASER_WaWt (4U << 7) -#define GICR_PROPBASER_WaWb (5U << 7) -#define GICR_PROPBASER_RaWaWt (6U << 7) -#define GICR_PROPBASER_RaWaWb (7U << 7) -#define GICR_PROPBASER_CACHEABILITY_MASK (7U << 7) -#define GICR_PROPBASER_IDBITS_MASK (0x1f) - -#define GICR_PENDBASER_NonShareable (0U << 10) -#define GICR_PENDBASER_InnerShareable (1U << 10) -#define GICR_PENDBASER_OuterShareable (2U << 10) -#define GICR_PENDBASER_SHAREABILITY_MASK (3UL << 10) -#define GICR_PENDBASER_nCnB (0U << 7) -#define GICR_PENDBASER_nC (1U << 7) -#define GICR_PENDBASER_RaWt (2U << 7) -#define GICR_PENDBASER_RaWb (3U << 7) -#define GICR_PENDBASER_WaWt (4U << 7) -#define GICR_PENDBASER_WaWb (5U << 7) -#define GICR_PENDBASER_RaWaWt (6U << 7) -#define GICR_PENDBASER_RaWaWb (7U << 7) -#define GICR_PENDBASER_CACHEABILITY_MASK (7U << 7) +#define GIC_BASER_CACHE_nCnB 0ULL +#define GIC_BASER_CACHE_SameAsInner 0ULL +#define GIC_BASER_CACHE_nC 1ULL +#define GIC_BASER_CACHE_RaWt 2ULL +#define GIC_BASER_CACHE_RaWb 3ULL +#define GIC_BASER_CACHE_WaWt 4ULL +#define GIC_BASER_CACHE_WaWb 5ULL +#define GIC_BASER_CACHE_RaWaWt 6ULL +#define GIC_BASER_CACHE_RaWaWb 7ULL +#define GIC_BASER_CACHE_MASK 7ULL +#define GIC_BASER_NonShareable 0ULL +#define GIC_BASER_InnerShareable 1ULL +#define GIC_BASER_OuterShareable 2ULL +#define GIC_BASER_SHAREABILITY_MASK 3ULL + +#define GIC_BASER_CACHEABILITY(reg, inner_outer, type) \ + (GIC_BASER_CACHE_##type << reg##_##inner_outer##_CACHEABILITY_SHIFT) + +#define GIC_BASER_SHAREABILITY(reg, type) \ + (GIC_BASER_##type << reg##_SHAREABILITY_SHIFT) + +#define GICR_PROPBASER_SHAREABILITY_SHIFT (10) +#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56) +#define GICR_PROPBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_PROPBASER, SHAREABILITY_MASK) +#define GICR_PROPBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, MASK) +#define GICR_PROPBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_PROPBASER, OUTER, MASK) +#define GICR_PROPBASER_CACHEABILITY_MASK GICR_PROPBASER_INNER_CACHEABILITY_MASK + +#define GICR_PROPBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable) +#define GICR_PROPBASER_nC GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC) +#define GICR_PROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb) +#define GICR_PROPBASER_IDBITS_MASK (0x1f) + +#define GICR_PENDBASER_SHAREABILITY_SHIFT (10) +#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT (56) +#define GICR_PENDBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_PENDBASER, SHAREABILITY_MASK) +#define GICR_PENDBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, MASK) +#define GICR_PENDBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, MASK) +#define GICR_PENDBASER_CACHEABILITY_MASK GICR_PENDBASER_INNER_CACHEABILITY_MASK + +#define GICR_PENDBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable) +#define GICR_PENDBASER_nC GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC) +#define GICR_PENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb) +#define GICR_PENDBASER_PTZ BIT_ULL(62) /* * Re-Distributor registers, offsets from SGI_base @@ -175,59 +201,74 @@ #define GITS_CWRITER 0x0088 #define GITS_CREADR 0x0090 #define GITS_BASER 0x0100 +#define GITS_IDREGS_BASE 0xffd0 +#define GITS_PIDR0 0xffe0 +#define GITS_PIDR1 0xffe4 #define GITS_PIDR2 GICR_PIDR2 +#define GITS_PIDR4 0xffd0 +#define GITS_CIDR0 0xfff0 +#define GITS_CIDR1 0xfff4 +#define GITS_CIDR2 0xfff8 +#define GITS_CIDR3 0xfffc #define GITS_TRANSLATER 0x10040 #define GITS_CTLR_ENABLE (1U << 0) #define GITS_CTLR_QUIESCENT (1U << 31) +#define GITS_TYPER_PLPIS (1UL << 0) +#define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) #define GITS_TYPER_PTA (1UL << 19) - -#define GITS_CBASER_VALID (1UL << 63) -#define GITS_CBASER_nCnB (0UL << 59) -#define GITS_CBASER_nC (1UL << 59) -#define GITS_CBASER_RaWt (2UL << 59) -#define GITS_CBASER_RaWb (3UL << 59) -#define GITS_CBASER_WaWt (4UL << 59) -#define GITS_CBASER_WaWb (5UL << 59) -#define GITS_CBASER_RaWaWt (6UL << 59) -#define GITS_CBASER_RaWaWb (7UL << 59) -#define GITS_CBASER_CACHEABILITY_MASK (7UL << 59) -#define GITS_CBASER_NonShareable (0UL << 10) -#define GITS_CBASER_InnerShareable (1UL << 10) -#define GITS_CBASER_OuterShareable (2UL << 10) -#define GITS_CBASER_SHAREABILITY_MASK (3UL << 10) +#define GITS_TYPER_HWCOLLCNT_SHIFT 24 + +#define GITS_CBASER_VALID (1UL << 63) +#define GITS_CBASER_SHAREABILITY_SHIFT (10) +#define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59) +#define GITS_CBASER_OUTER_CACHEABILITY_SHIFT (53) +#define GITS_CBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GITS_CBASER, SHAREABILITY_MASK) +#define GITS_CBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, MASK) +#define GITS_CBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GITS_CBASER, OUTER, MASK) +#define GITS_CBASER_CACHEABILITY_MASK GITS_CBASER_INNER_CACHEABILITY_MASK + +#define GITS_CBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable) +#define GITS_CBASER_nC GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC) +#define GITS_CBASER_WaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb) #define GITS_BASER_NR_REGS 8 -#define GITS_BASER_VALID (1UL << 63) -#define GITS_BASER_nCnB (0UL << 59) -#define GITS_BASER_nC (1UL << 59) -#define GITS_BASER_RaWt (2UL << 59) -#define GITS_BASER_RaWb (3UL << 59) -#define GITS_BASER_WaWt (4UL << 59) -#define GITS_BASER_WaWb (5UL << 59) -#define GITS_BASER_RaWaWt (6UL << 59) -#define GITS_BASER_RaWaWb (7UL << 59) -#define GITS_BASER_CACHEABILITY_MASK (7UL << 59) -#define GITS_BASER_TYPE_SHIFT (56) +#define GITS_BASER_VALID (1UL << 63) +#define GITS_BASER_INDIRECT (1ULL << 62) +#define GITS_BASER_INNER_CACHEABILITY_SHIFT (59) +#define GITS_BASER_OUTER_CACHEABILITY_SHIFT (53) +#define GITS_BASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK) +#define GITS_BASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK) +#define GITS_BASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK) + +#define GITS_BASER_nC GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC) +#define GITS_BASER_WaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb) +#define GITS_BASER_TYPE_SHIFT (56) #define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7) -#define GITS_BASER_ENTRY_SIZE_SHIFT (48) +#define GITS_BASER_ENTRY_SIZE_SHIFT (48) #define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0xff) + 1) -#define GITS_BASER_NonShareable (0UL << 10) -#define GITS_BASER_InnerShareable (1UL << 10) -#define GITS_BASER_OuterShareable (2UL << 10) #define GITS_BASER_SHAREABILITY_SHIFT (10) -#define GITS_BASER_SHAREABILITY_MASK (3UL << GITS_BASER_SHAREABILITY_SHIFT) +#define GITS_BASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) #define GITS_BASER_PAGE_SIZE_SHIFT (8) #define GITS_BASER_PAGE_SIZE_4K (0UL << GITS_BASER_PAGE_SIZE_SHIFT) #define GITS_BASER_PAGE_SIZE_16K (1UL << GITS_BASER_PAGE_SIZE_SHIFT) #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_NR_PAGES(r) (((r) & 0xff) + 1) #define GITS_BASER_TYPE_NONE 0 #define GITS_BASER_TYPE_DEVICE 1 @@ -243,7 +284,10 @@ */ #define GITS_CMD_MAPD 0x08 #define GITS_CMD_MAPC 0x09 -#define GITS_CMD_MAPVI 0x0a +#define GITS_CMD_MAPTI 0x0a +/* older GIC documentation used MAPVI for this command */ +#define GITS_CMD_MAPVI GITS_CMD_MAPTI +#define GITS_CMD_MAPI 0x0b #define GITS_CMD_MOVI 0x01 #define GITS_CMD_DISCARD 0x0f #define GITS_CMD_INV 0x0c @@ -253,6 +297,22 @@ #define GITS_CMD_CLEAR 0x04 #define GITS_CMD_SYNC 0x05 +/* + * ITS error numbers + */ +#define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 +#define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 +#define E_ITS_MAPD_DEVICE_OOR 0x010801 +#define E_ITS_MAPC_PROCNUM_OOR 0x010902 +#define E_ITS_MAPC_COLLECTION_OOR 0x010903 +#define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04 +#define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06 +#define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07 +#define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09 +#define E_ITS_MOVALL_PROCNUM_OOR 0x010e01 +#define E_ITS_DISCARD_UNMAPPED_INTERRUPT 0x010f07 + /* * CPU interface registers */ -- cgit v1.2.3 From 0aa1de57319c4e023187aca0d59dd593a96459a8 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:29 +0100 Subject: KVM: arm64: vgic: Handle ITS related GICv3 redistributor registers In the GICv3 redistributor there are the PENDBASER and PROPBASER registers which we did not emulate so far, as they only make sense when having an ITS. In preparation for that emulate those MMIO accesses by storing the 64-bit data written into it into a variable which we later read in the ITS emulation. We also sanitise the registers, making sure RES0 regions are respected and checking for valid memory attributes. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 450b4dab9a9f..df2dec5ef620 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -146,6 +146,14 @@ struct vgic_dist { struct vgic_irq *spis; struct vgic_io_device dist_iodev; + + /* + * Contains the attributes and gpa of the LPI configuration table. + * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share + * one address across all redistributors. + * GICv3 spec: 6.1.2 "LPI Configuration tables" + */ + u64 propbaser; }; struct vgic_v2_cpu_if { @@ -200,6 +208,11 @@ struct vgic_cpu { */ struct vgic_io_device rd_iodev; struct vgic_io_device sgi_iodev; + + /* Contains the attributes and gpa of the LPI pending tables. */ + u64 pendbaser; + + bool lpis_enabled; }; int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write); -- cgit v1.2.3 From 59c5ab40989afa5aba9c4a0918a5ed910a917422 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:30 +0100 Subject: KVM: arm64: vgic-its: Introduce ITS emulation file with MMIO framework The ARM GICv3 ITS emulation code goes into a separate file, but needs to be connected to the GICv3 emulation, of which it is an option. The ITS MMIO handlers require the respective ITS pointer to be passed in, so we amend the existing VGIC MMIO framework to let it cope with that. Also we introduce the basic ITS data structure and initialize it, but don't return any success yet, as we are not yet ready for the show. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index df2dec5ef620..685f33975ce4 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -108,15 +108,35 @@ struct vgic_irq { }; struct vgic_register_region; +struct vgic_its; + +enum iodev_type { + IODEV_CPUIF, + IODEV_DIST, + IODEV_REDIST, + IODEV_ITS +}; struct vgic_io_device { gpa_t base_addr; - struct kvm_vcpu *redist_vcpu; + union { + struct kvm_vcpu *redist_vcpu; + struct vgic_its *its; + }; const struct vgic_register_region *regions; + enum iodev_type iodev_type; int nr_regions; struct kvm_io_device dev; }; +struct vgic_its { + /* The base address of the ITS control register frame */ + gpa_t vgic_its_base; + + bool enabled; + struct vgic_io_device iodev; +}; + struct vgic_dist { bool in_kernel; bool ready; -- cgit v1.2.3 From 1085fdc68c6097244627a02a56bd2d8fe58a1a9c Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:31 +0100 Subject: KVM: arm64: vgic-its: Introduce new KVM ITS device Introduce a new KVM device that represents an ARM Interrupt Translation Service (ITS) controller. Since there can be multiple of this per guest, we can't piggy back on the existing GICv3 distributor device, but create a new type of KVM device. On the KVM_CREATE_DEVICE ioctl we allocate and initialize the ITS data structure and store the pointer in the kvm_device data. Upon an explicit init ioctl from userland (after having setup the MMIO address) we register the handlers with the kvm_io_bus framework. Any reference to an ITS thus has to go via this interface. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 3 +++ include/uapi/linux/kvm.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 685f33975ce4..8609faced83e 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -134,6 +134,7 @@ struct vgic_its { gpa_t vgic_its_base; bool enabled; + bool initialized; struct vgic_io_device iodev; }; @@ -167,6 +168,8 @@ struct vgic_dist { struct vgic_io_device dist_iodev; + bool has_its; + /* * Contains the attributes and gpa of the LPI configuration table. * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7de96f5bb92c..d8c4c324cfae 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1077,6 +1077,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_ARM_VGIC_V3, #define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 + KVM_DEV_TYPE_ARM_VGIC_ITS, +#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_MAX, }; -- cgit v1.2.3 From 424c33830f53f248a68da125e70d9a4d95a8e010 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:32 +0100 Subject: KVM: arm64: vgic-its: Implement basic ITS register handlers Add emulation for some basic MMIO registers used in the ITS emulation. This includes: - GITS_{CTLR,TYPER,IIDR} - ID registers - GITS_{CBASER,CREADR,CWRITER} (which implement the ITS command buffer handling) - GITS_BASER Most of the handlers are pretty straight forward, only the CWRITER handler is a bit more involved by taking the new its_cmd mutex and then iterating over the command buffer. The registers holding base addresses and attributes are sanitised before storing them. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 8609faced83e..61867492d361 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -22,6 +22,7 @@ #include #include #include +#include #define VGIC_V3_MAX_CPUS 255 #define VGIC_V2_MAX_CPUS 8 @@ -136,6 +137,21 @@ struct vgic_its { bool enabled; bool initialized; struct vgic_io_device iodev; + + /* These registers correspond to GITS_BASER{0,1} */ + u64 baser_device_table; + u64 baser_coll_table; + + /* Protects the command queue */ + struct mutex cmd_lock; + u64 cbaser; + u32 creadr; + u32 cwriter; + + /* Protects the device and collection lists */ + struct mutex its_lock; + struct list_head device_list; + struct list_head collection_list; }; struct vgic_dist { -- cgit v1.2.3 From 3802411d01880c4283426d22653e011159b1c947 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:33 +0100 Subject: KVM: arm64: vgic-its: Connect LPIs to the VGIC emulation LPIs are dynamically created (mapped) at guest runtime and their actual number can be quite high, but is mostly assigned using a very sparse allocation scheme. So arrays are not an ideal data structure to hold the information. We use a spin-lock protected linked list to hold all mapped LPIs, represented by their struct vgic_irq. This lock is grouped between the ap_list_lock and the vgic_irq lock in our locking order. Also we store a pointer to that struct vgic_irq in our struct its_itte, so we can easily access it. Eventually we call our new vgic_get_lpi() from vgic_get_irq(), so the VGIC code gets transparently access to LPIs. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 61867492d361..a6ca326055cf 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -77,6 +77,7 @@ enum vgic_irq_config { struct vgic_irq { spinlock_t irq_lock; /* Protects the content of the struct */ + struct list_head lpi_list; /* Used to link all LPIs together */ struct list_head ap_list; struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU @@ -193,6 +194,11 @@ struct vgic_dist { * GICv3 spec: 6.1.2 "LPI Configuration tables" */ u64 propbaser; + + /* Protects the lpi_list and the count value below. */ + spinlock_t lpi_list_lock; + struct list_head lpi_list_head; + int lpi_list_count; }; struct vgic_v2_cpu_if { -- cgit v1.2.3 From 0e4e82f154e387969ea7ecd2c8876689fb68f710 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Fri, 15 Jul 2016 12:43:38 +0100 Subject: KVM: arm64: vgic-its: Enable ITS emulation as a virtual MSI controller Now that all ITS emulation functionality is in place, we advertise MSI functionality to userland and also the ITS device to the guest - if userland has configured that. Signed-off-by: Andre Przywara Reviewed-by: Marc Zyngier Tested-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index a6ca326055cf..4e63a07b9001 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -163,6 +163,9 @@ struct vgic_dist { /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */ u32 vgic_model; + /* Do injected MSIs require an additional device ID? */ + bool msis_require_devid; + int nr_spis; /* TODO: Consider moving to global state */ @@ -308,4 +311,6 @@ static inline int kvm_vgic_get_max_vcpus(void) return kvm_vgic_global_state.max_gic_vcpus; } +int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); + #endif /* __KVM_ARM_VGIC_H */ -- cgit v1.2.3 From 8c828a535e29f50282f1a49a52c3b20ccaa039aa Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 18 Jul 2016 15:28:52 +0100 Subject: irqchip/gicv3-its: Restore all cacheability attributes Let's restore some of the #defines that have been savagely dropped by the introduction of the KVM ITS code, as pointlessly break other users (including series that are already in -next). Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 48 +++++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 9442be7f2461..700b4216c87a 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -146,8 +146,16 @@ #define GICR_PROPBASER_InnerShareable \ GIC_BASER_SHAREABILITY(GICR_PROPBASER, InnerShareable) -#define GICR_PROPBASER_nC GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC) -#define GICR_PROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb) + +#define GICR_PROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nCnB) +#define GICR_PROPBASER_nC GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, nC) +#define GICR_PROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt) +#define GICR_PROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWt) +#define GICR_PROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWt) +#define GICR_PROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, WaWb) +#define GICR_PROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWt) +#define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb) + #define GICR_PROPBASER_IDBITS_MASK (0x1f) #define GICR_PENDBASER_SHAREABILITY_SHIFT (10) @@ -163,8 +171,16 @@ #define GICR_PENDBASER_InnerShareable \ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable) -#define GICR_PENDBASER_nC GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC) -#define GICR_PENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb) + +#define GICR_PENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nCnB) +#define GICR_PENDBASER_nC GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, nC) +#define GICR_PENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt) +#define GICR_PENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWt) +#define GICR_PENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWt) +#define GICR_PENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, WaWb) +#define GICR_PENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWt) +#define GICR_PENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWaWb) + #define GICR_PENDBASER_PTZ BIT_ULL(62) /* @@ -237,24 +253,40 @@ #define GITS_CBASER_InnerShareable \ GIC_BASER_SHAREABILITY(GITS_CBASER, InnerShareable) -#define GITS_CBASER_nC GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC) -#define GITS_CBASER_WaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb) + +#define GITS_CBASER_nCnB GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nCnB) +#define GITS_CBASER_nC GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, nC) +#define GITS_CBASER_RaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt) +#define GITS_CBASER_RaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWt) +#define GITS_CBASER_WaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWt) +#define GITS_CBASER_WaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, WaWb) +#define GITS_CBASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWt) +#define GITS_CBASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_CBASER, INNER, RaWaWb) #define GITS_BASER_NR_REGS 8 #define GITS_BASER_VALID (1UL << 63) #define GITS_BASER_INDIRECT (1ULL << 62) + #define GITS_BASER_INNER_CACHEABILITY_SHIFT (59) #define GITS_BASER_OUTER_CACHEABILITY_SHIFT (53) #define GITS_BASER_INNER_CACHEABILITY_MASK \ GIC_BASER_CACHEABILITY(GITS_BASER, INNER, MASK) +#define GITS_BASER_CACHEABILITY_MASK GITS_BASER_INNER_CACHEABILITY_MASK #define GITS_BASER_OUTER_CACHEABILITY_MASK \ GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, MASK) #define GITS_BASER_SHAREABILITY_MASK \ GIC_BASER_SHAREABILITY(GITS_BASER, SHAREABILITY_MASK) -#define GITS_BASER_nC GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC) -#define GITS_BASER_WaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb) +#define GITS_BASER_nCnB GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nCnB) +#define GITS_BASER_nC GIC_BASER_CACHEABILITY(GITS_BASER, INNER, nC) +#define GITS_BASER_RaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt) +#define GITS_BASER_RaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWt) +#define GITS_BASER_WaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWt) +#define GITS_BASER_WaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, WaWb) +#define GITS_BASER_RaWaWt GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWt) +#define GITS_BASER_RaWaWb GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWaWb) + #define GITS_BASER_TYPE_SHIFT (56) #define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7) #define GITS_BASER_ENTRY_SIZE_SHIFT (48) -- cgit v1.2.3 From bb7176449f6da27534a0faf3a67997bf2c3172aa Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 17 Jul 2016 21:35:07 +0100 Subject: KVM: arm64: vgic-its: Add pointer to corresponding kvm_device Going from the ITS structure to the corresponding KVM structure would be quite handy at times. The kvm_device pointer that is passed at create time is quite convenient for this, so let's keep a copy of it in the vgic_its structure. This will be put to a good use in subsequent patches. Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4e63a07b9001..540da5149ba7 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -138,6 +138,7 @@ struct vgic_its { bool enabled; bool initialized; struct vgic_io_device iodev; + struct kvm_device *dev; /* These registers correspond to GITS_BASER{0,1} */ u64 baser_device_table; -- cgit v1.2.3 From f4dc77713f8016d2e8a3295e1c9c53a21f296def Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 14 Jul 2016 17:51:26 +0200 Subject: netfilter: x_tables: speed up jump target validation The dummy ruleset I used to test the original validation change was broken, most rules were unreachable and were not tested by mark_source_chains(). In some cases rulesets that used to load in a few seconds now require several minutes. sample ruleset that shows the behaviour: echo "*filter" for i in $(seq 0 100000);do printf ":chain_%06x - [0:0]\n" $i done for i in $(seq 0 100000);do printf -- "-A INPUT -j chain_%06x\n" $i printf -- "-A INPUT -j chain_%06x\n" $i printf -- "-A INPUT -j chain_%06x\n" $i done echo COMMIT [ pipe result into iptables-restore ] This ruleset will be about 74mbyte in size, with ~500k searches though all 500k[1] rule entries. iptables-restore will take forever (gave up after 10 minutes) Instead of always searching the entire blob for a match, fill an array with the start offsets of every single ipt_entry struct, then do a binary search to check if the jump target is present or not. After this change ruleset restore times get again close to what one gets when reverting 36472341017529e (~3 seconds on my workstation). [1] every user-defined rule gets an implicit RETURN, so we get 300k jumps + 100k userchains + 100k returns -> 500k rule entries Fixes: 36472341017529e ("netfilter: x_tables: validate targets of jumps") Reported-by: Jeff Wu Tested-by: Jeff Wu Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index e94e81ab2b58..2ad1a2b289b5 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -250,6 +250,10 @@ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); +unsigned int *xt_alloc_entry_offsets(unsigned int size); +bool xt_find_jump_offset(const unsigned int *offsets, + unsigned int target, unsigned int size); + int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto, -- cgit v1.2.3 From 35303d5c36415754680f953aa6128b8b907d0543 Mon Sep 17 00:00:00 2001 From: Tom Yan Date: Fri, 15 Jul 2016 05:09:02 +0800 Subject: ata: make lba_{28,48}_ok() use ATA_MAX_SECTORS{,_LBA48} Since we set ATA_MAX_SECTORS_LBA48 to 65535 to avoid the corner case in some drives that commands with "count" set to 0000h (which reprsents 65536) does not work as expected, lba_48_ok(), which is used for number-of-blocks checking when libata pack commands, should use the same limit as well. In fact, there is no reason for the two functions not to use the macros anyway. Signed-off-by: Tom Yan Signed-off-by: Tejun Heo --- include/linux/ata.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 35857d1f15c8..5b67ff407ec2 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -46,7 +46,7 @@ enum { ATA_MAX_SECTORS_128 = 128, ATA_MAX_SECTORS = 256, ATA_MAX_SECTORS_1024 = 1024, - ATA_MAX_SECTORS_LBA48 = 65535,/* TODO: 65536? */ + ATA_MAX_SECTORS_LBA48 = 65535,/* avoid count to be 0000h */ ATA_MAX_SECTORS_TAPE = 65535, ATA_MAX_TRIM_RNUM = 64, /* 512-byte payload / (6-byte LBA + 2-byte range per entry) */ @@ -1100,13 +1100,13 @@ static inline bool ata_ok(u8 status) static inline bool lba_28_ok(u64 block, u32 n_block) { /* check the ending block number: must be LESS THAN 0x0fffffff */ - return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= 256); + return ((block + n_block) < ((1 << 28) - 1)) && (n_block <= ATA_MAX_SECTORS); } static inline bool lba_48_ok(u64 block, u32 n_block) { /* check the ending block number */ - return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= 65536); + return ((block + n_block - 1) < ((u64)1 << 48)) && (n_block <= ATA_MAX_SECTORS_LBA48); } #define sata_pmp_gscr_vendor(gscr) ((gscr)[SATA_PMP_GSCR_PROD_ID] & 0xffff) -- cgit v1.2.3 From eb0effdf53b061bd57d8efc86032454e79487263 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Jul 2016 22:16:41 +0900 Subject: libata: remove ata_is_nodata The only caller can just check for !ata_is_data instead. Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/libata.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 1abd6690c776..283b6be6c319 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1070,11 +1070,6 @@ static inline bool ata_is_atapi(u8 prot) return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; } -static inline bool ata_is_nodata(u8 prot) -{ - return !(ata_prot_flags(prot) & ATA_PROT_FLAG_DATA); -} - static inline bool ata_is_pio(u8 prot) { return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; -- cgit v1.2.3 From d6e50e379eb1e7f2426eac61a1bbbf6e4cf68905 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Jul 2016 22:16:42 +0900 Subject: libata: remove ATA_PROT_FLAG_DATA Instead we can simply check for PIO or DMA in ata_is_data. Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/libata.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index 283b6be6c319..5838fbf6acf7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -149,7 +149,6 @@ enum { /* protocol flags */ ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ - ATA_PROT_FLAG_DATA = ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA, ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ @@ -1087,7 +1086,7 @@ static inline bool ata_is_ncq(u8 prot) static inline bool ata_is_data(u8 prot) { - return ata_prot_flags(prot) & ATA_PROT_FLAG_DATA; + return ata_prot_flags(prot) & (ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA); } static inline int is_multi_taskfile(struct ata_taskfile *tf) -- cgit v1.2.3 From 37f92d77dc45d1fb74eff8501f26e72a3dcaa3cf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Jul 2016 22:16:43 +0900 Subject: ata: define ATA_PROT_* in terms of ATA_PROT_FLAG_* This avoid the need to always translate between the two in ata_prot_flags and generally cleans up the taskfile protocol usage. Signed-off-by: Christoph Hellwig Signed-off-by: Tejun Heo --- include/linux/ata.h | 28 +++++++++++++++++----------- include/linux/libata.h | 42 +++++------------------------------------- 2 files changed, 22 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/linux/ata.h b/include/linux/ata.h index 5b67ff407ec2..adbc812c009b 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -523,17 +523,23 @@ enum { SERR_DEV_XCHG = (1 << 26), /* device exchanged */ }; -enum ata_tf_protocols { - /* ATA taskfile protocols */ - ATA_PROT_UNKNOWN, /* unknown/invalid */ - ATA_PROT_NODATA, /* no data */ - ATA_PROT_PIO, /* PIO data xfer */ - ATA_PROT_DMA, /* DMA */ - ATA_PROT_NCQ, /* NCQ */ - ATA_PROT_NCQ_NODATA, /* NCQ no data */ - ATAPI_PROT_NODATA, /* packet command, no data */ - ATAPI_PROT_PIO, /* packet command, PIO data xfer*/ - ATAPI_PROT_DMA, /* packet command with special DMA sauce */ +enum ata_prot_flags { + /* protocol flags */ + ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ + ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ + ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ + ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ + + /* taskfile protocols */ + ATA_PROT_UNKNOWN = (u8)-1, + ATA_PROT_NODATA = 0, + ATA_PROT_PIO = ATA_PROT_FLAG_PIO, + ATA_PROT_DMA = ATA_PROT_FLAG_DMA, + ATA_PROT_NCQ_NODATA = ATA_PROT_FLAG_NCQ, + ATA_PROT_NCQ = ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ, + ATAPI_PROT_NODATA = ATA_PROT_FLAG_ATAPI, + ATAPI_PROT_PIO = ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO, + ATAPI_PROT_DMA = ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA, }; enum ata_ioctls { diff --git a/include/linux/libata.h b/include/linux/libata.h index 5838fbf6acf7..e37d4f99f510 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -146,12 +146,6 @@ enum { ATA_TFLAG_FUA = (1 << 5), /* enable FUA */ ATA_TFLAG_POLLING = (1 << 6), /* set nIEN to 1 and use polling */ - /* protocol flags */ - ATA_PROT_FLAG_PIO = (1 << 0), /* is PIO */ - ATA_PROT_FLAG_DMA = (1 << 1), /* is DMA */ - ATA_PROT_FLAG_NCQ = (1 << 2), /* is NCQ */ - ATA_PROT_FLAG_ATAPI = (1 << 3), /* is ATAPI */ - /* struct ata_device stuff */ ATA_DFLAG_LBA = (1 << 0), /* device supports LBA */ ATA_DFLAG_LBA48 = (1 << 1), /* device supports LBA48 */ @@ -1038,55 +1032,29 @@ extern const unsigned long sata_deb_timing_long[]; extern struct ata_port_operations ata_dummy_port_ops; extern const struct ata_port_info ata_dummy_port_info; -/* - * protocol tests - */ -static inline unsigned int ata_prot_flags(u8 prot) -{ - switch (prot) { - case ATA_PROT_NODATA: - return 0; - case ATA_PROT_PIO: - return ATA_PROT_FLAG_PIO; - case ATA_PROT_DMA: - return ATA_PROT_FLAG_DMA; - case ATA_PROT_NCQ: - return ATA_PROT_FLAG_DMA | ATA_PROT_FLAG_NCQ; - case ATA_PROT_NCQ_NODATA: - return ATA_PROT_FLAG_NCQ; - case ATAPI_PROT_NODATA: - return ATA_PROT_FLAG_ATAPI; - case ATAPI_PROT_PIO: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_PIO; - case ATAPI_PROT_DMA: - return ATA_PROT_FLAG_ATAPI | ATA_PROT_FLAG_DMA; - } - return 0; -} - static inline bool ata_is_atapi(u8 prot) { - return ata_prot_flags(prot) & ATA_PROT_FLAG_ATAPI; + return prot & ATA_PROT_FLAG_ATAPI; } static inline bool ata_is_pio(u8 prot) { - return ata_prot_flags(prot) & ATA_PROT_FLAG_PIO; + return prot & ATA_PROT_FLAG_PIO; } static inline bool ata_is_dma(u8 prot) { - return ata_prot_flags(prot) & ATA_PROT_FLAG_DMA; + return prot & ATA_PROT_FLAG_DMA; } static inline bool ata_is_ncq(u8 prot) { - return ata_prot_flags(prot) & ATA_PROT_FLAG_NCQ; + return prot & ATA_PROT_FLAG_NCQ; } static inline bool ata_is_data(u8 prot) { - return ata_prot_flags(prot) & (ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA); + return prot & (ATA_PROT_FLAG_PIO | ATA_PROT_FLAG_DMA); } static inline int is_multi_taskfile(struct ata_taskfile *tf) -- cgit v1.2.3 From 38d0fc4662474c6219166505d0a68b45a583fcfb Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 19 Jul 2016 05:54:56 +0200 Subject: Revert "i2c: core: Add function for finding the bus speed from ACPI" This reverts commit 55d38d060e999ca1a3ea6eb132105a0301e4cd04. There were too heavy merge conflicts and the driver code making use of this was not ready yet anyhow. So, we wait one cycle. Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5cde08719fb6..fffdc270ca18 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -766,13 +766,4 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node } #endif /* CONFIG_OF */ -#if IS_ENABLED(CONFIG_ACPI) -u32 i2c_acpi_find_bus_speed(struct device *dev); -#else -static inline u32 i2c_acpi_find_bus_speed(struct device *dev) -{ - return 0; -} -#endif /* CONFIG_ACPI */ - #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 6a0fb306738994d6f091791aeb11a5dc87ad8f4c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 19 Jul 2016 03:04:34 -0400 Subject: new helper: wait_event_killable_exclusive() Signed-off-by: Al Viro --- include/linux/wait.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/wait.h b/include/linux/wait.h index 27d7a0ab5da3..c3ff74d764fa 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -600,6 +600,19 @@ do { \ __ret; \ }) +#define __wait_event_killable_exclusive(wq, condition) \ + ___wait_event(wq, condition, TASK_KILLABLE, 1, 0, \ + schedule()) + +#define wait_event_killable_exclusive(wq, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __wait_event_killable_exclusive(wq, condition); \ + __ret; \ +}) + #define __wait_event_freezable_exclusive(wq, condition) \ ___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0, \ -- cgit v1.2.3 From 5c562338dea29dc09415f39676e7107fa48ce763 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 19 Jul 2016 00:59:30 +0800 Subject: crypto: skcipher - Add comment for skcipher_alg->base This patch adds a missing comment for the base parameter in struct skcipher_alg. Reported-by: kbuild test robot Signed-off-by: Herbert Xu --- include/crypto/skcipher.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 59c8f6c593e6..cc4d98a7892e 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -115,6 +115,7 @@ struct crypto_skcipher { * IV of exactly that size to perform the encrypt or decrypt operation. * @chunksize: Equal to the block size except for stream ciphers such as * CTR where it is set to the underlying block size. + * @base: Definition of a generic crypto algorithm. * * All fields except @ivsize are mandatory and must be filled. */ -- cgit v1.2.3 From cae8b441fc20812d7260dc3b45e05ee98fcfff1b Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 12 Jul 2016 11:41:49 -0600 Subject: tpm: Factor out common startup code The TCG standard startup sequence (get timeouts, tpm startup, etc) for TPM and TPM2 chips is being open coded in many drivers, move it into the core code. tpm_tis and tpm_crb are used as the basis for the core code implementation and the easy drivers are converted. In the process several small drivers bugs relating to error handling this flow are fixed. For now the flag TPM_OPS_AUTO_STARTUP is optional to allow a staged driver roll out, but ultimately all drivers should use this flow and the flag removed. Some drivers still do not implement the startup sequence at all and will need to be tested with it enabled. Signed-off-by: Jason Gunthorpe Tested-by: Andrew Zamansky Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- include/linux/tpm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 706e63eea080..da158f06e0b2 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -33,7 +33,12 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +enum TPM_OPS_FLAGS { + TPM_OPS_AUTO_STARTUP = BIT(0), +}; + struct tpm_class_ops { + unsigned int flags; const u8 req_complete_mask; const u8 req_complete_val; bool (*req_canceled)(struct tpm_chip *chip, u8 status); -- cgit v1.2.3 From 11065f8531ed33d5e847a36ad64231ee599d4996 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sun, 17 Jul 2016 11:40:05 -0300 Subject: [media] cec: limit the size of the transmit queue The size of the transmit queue was unlimited, which meant that in non-blocking mode you could flood the CEC adapter with messages to be transmitted. Limit this to 18 messages. Also print the number of pending transmits and the timeout value in the status debugfs file. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cec.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/cec.h b/include/media/cec.h index 9a791c08a789..dc7854b855f3 100644 --- a/include/media/cec.h +++ b/include/media/cec.h @@ -126,12 +126,20 @@ struct cec_adap_ops { * With a transfer rate of at most 36 bytes per second this makes 18 messages * per second worst case. * - * We queue at most 3 seconds worth of messages. The CEC specification requires - * that messages are replied to within a second, so 3 seconds should give more - * than enough margin. Since most messages are actually more than 2 bytes, this - * is in practice a lot more than 3 seconds. + * We queue at most 3 seconds worth of received messages. The CEC specification + * requires that messages are replied to within a second, so 3 seconds should + * give more than enough margin. Since most messages are actually more than 2 + * bytes, this is in practice a lot more than 3 seconds. */ -#define CEC_MAX_MSG_QUEUE_SZ (18 * 3) +#define CEC_MAX_MSG_RX_QUEUE_SZ (18 * 3) + +/* + * The transmit queue is limited to 1 second worth of messages (worst case). + * Messages can be transmitted by userspace and kernel space. But for both it + * makes no sense to have a lot of messages queued up. One second seems + * reasonable. + */ +#define CEC_MAX_MSG_TX_QUEUE_SZ (18 * 1) struct cec_adapter { struct module *owner; @@ -141,6 +149,7 @@ struct cec_adapter { struct rc_dev *rc; struct list_head transmit_queue; + unsigned int transmit_queue_sz; struct list_head wait_queue; struct cec_data *transmitting; -- cgit v1.2.3 From a4a4f9439c73b921ef246368fc6f2d7c0281e99d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 19 Jul 2016 13:16:52 -0400 Subject: bdev: get rid of ->bd_inodes Since 2006 we have ->i_bdev pinning bdev in question, so there's no way to get to bdev ->evict_inode() while there's an aliasing inode anywhere. In other words, the only place walking the list of aliases is guaranteed to do it only when the list is empty... Remove the detritus; it should've been done in "[PATCH] Fix a race condition between ->i_mapping and iput()", but nobody had noticed it back then. Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index bacc0733663c..1878c8461622 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -459,7 +459,6 @@ struct block_device { struct inode * bd_inode; /* will die */ struct super_block * bd_super; struct mutex bd_mutex; /* open/close mutex */ - struct list_head bd_inodes; void * bd_claiming; void * bd_holder; int bd_holders; -- cgit v1.2.3 From cc2d1de06f0572a51437d1f31633d81afea5eb47 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Fri, 8 Jul 2016 17:14:18 +0200 Subject: bcma: define ChipCommon B MII registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We don't have access to datasheets to document all the bits but we can name these registers at least. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/bcma/bcma_driver_chipcommon.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index a5ac2cad5cb7..b20e3d56253f 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -504,6 +504,9 @@ #define BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_MASK 0x1ff00000 #define BCMA_CC_PMU1_PLL0_PC2_NDIV_INT_SHIFT 20 +#define BCMA_CCB_MII_MNG_CTL 0x0000 +#define BCMA_CCB_MII_MNG_CMD_DATA 0x0004 + /* BCM4331 ChipControl numbers. */ #define BCMA_CHIPCTL_4331_BT_COEXIST BIT(0) /* 0 disable */ #define BCMA_CHIPCTL_4331_SECI BIT(1) /* 0 SECI is disabled (JATG functional) */ -- cgit v1.2.3 From ce52914eb76efd62aa48d738cf845b37852bf920 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 7 Jun 2016 15:14:48 -0400 Subject: sunrpc: move NO_CRKEY_TIMEOUT to the auth->au_flags A generic_cred can be used to look up a unx_cred or a gss_cred, so it's not really safe to use the the generic_cred->acred->ac_flags to store the NO_CRKEY_TIMEOUT flag. A lookup for a unx_cred triggered while the KEY_EXPIRE_SOON flag is already set will cause both NO_CRKEY_TIMEOUT and KEY_EXPIRE_SOON to be set in the ac_flags, leaving the user associated with the auth_cred to be in a state where they're perpetually doing 4K NFS_FILE_SYNC writes. This can be reproduced as follows: 1. Mount two NFS filesystems, one with sec=krb5 and one with sec=sys. They do not need to be the same export, nor do they even need to be from the same NFS server. Also, v3 is fine. $ sudo mount -o v3,sec=krb5 server1:/export /mnt/krb5 $ sudo mount -o v3,sec=sys server2:/export /mnt/sys 2. As the normal user, before accessing the kerberized mount, kinit with a short lifetime (but not so short that renewing the ticket would leave you within the 4-minute window again by the time the original ticket expires), e.g. $ kinit -l 10m -r 60m 3. Do some I/O to the kerberized mount and verify that the writes are wsize, UNSTABLE: $ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1 4. Wait until you're within 4 minutes of key expiry, then do some more I/O to the kerberized mount to ensure that RPC_CRED_KEY_EXPIRE_SOON gets set. Verify that the writes are 4K, FILE_SYNC: $ dd if=/dev/zero of=/mnt/krb5/file bs=1M count=1 5. Now do some I/O to the sec=sys mount. This will cause RPC_CRED_NO_CRKEY_TIMEOUT to be set: $ dd if=/dev/zero of=/mnt/sys/file bs=1M count=1 6. Writes for that user will now be permanently 4K, FILE_SYNC for that user, regardless of which mount is being written to, until you reboot the client. Renewing the kerberos ticket (assuming it hasn't already expired) will have no effect. Grabbing a new kerberos ticket at this point will have no effect either. Move the flag to the auth->au_flags field (which is currently unused) and rename it slightly to reflect that it's no longer associated with the auth_cred->ac_flags. Add the rpc_auth to the arg list of rpcauth_cred_key_to_expire and check the au_flags there too. Finally, add the inode to the arg list of nfs_ctx_key_to_expire so we can determine the rpc_auth to pass to rpcauth_cred_key_to_expire. Signed-off-by: Scott Mayhew Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 899791573a40..f890a295a7ff 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -37,7 +37,6 @@ struct rpcsec_gss_info; /* auth_cred ac_flags bits */ enum { - RPC_CRED_NO_CRKEY_TIMEOUT = 0, /* underlying cred has no key timeout */ RPC_CRED_KEY_EXPIRE_SOON = 1, /* underlying cred key will expire soon */ RPC_CRED_NOTIFY_TIMEOUT = 2, /* nofity generic cred when underlying key will expire soon */ @@ -82,6 +81,9 @@ struct rpc_cred { #define RPCAUTH_CRED_MAGIC 0x0f4aa4f0 +/* rpc_auth au_flags */ +#define RPCAUTH_AUTH_NO_CRKEY_TIMEOUT 0x0001 /* underlying cred has no key timeout */ + /* * Client authentication handle */ @@ -196,7 +198,7 @@ void rpcauth_destroy_credcache(struct rpc_auth *); void rpcauth_clear_credcache(struct rpc_cred_cache *); int rpcauth_key_timeout_notify(struct rpc_auth *, struct rpc_cred *); -bool rpcauth_cred_key_to_expire(struct rpc_cred *); +bool rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *); char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline -- cgit v1.2.3 From 359ebda25aa06fe3a1d028f7e338a849165e661b Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 18 Jul 2016 14:49:33 +0300 Subject: net/ipv4: Introduce IPSKB_FRAG_SEGS bit to inet_skb_parm.flags This flag indicates whether fragmentation of segments is allowed. Formerly this policy was hardcoded according to IPSKB_FORWARDED (set by either ip_forward or ipmr_forward). Cc: Hannes Frederic Sowa Cc: Florian Westphal Signed-off-by: Shmulik Ladkani Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/ip.h b/include/net/ip.h index 08f36cd2b874..9742b92dc933 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -47,6 +47,7 @@ struct inet_skb_parm { #define IPSKB_REROUTED BIT(4) #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) +#define IPSKB_FRAG_SEGS BIT(7) u16 frag_max_size; }; -- cgit v1.2.3 From 34a79f63bbe49c888f95e75dd759685a238556b6 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Mon, 18 Jul 2016 20:45:38 -0400 Subject: net: dsa: support switchdev ageing time attr Add a new function for DSA drivers to handle the switchdev SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME attribute. The ageing time is passed as milliseconds. Also because we can have multiple logical bridges on top of a physical switch and ageing time are switch-wide, call the driver function with the fastest ageing time in use on the chip instead of the requested one. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 52ab18bc2b0d..2217a3f817f8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -141,6 +141,7 @@ struct dsa_switch_tree { struct dsa_port { struct net_device *netdev; struct device_node *dn; + unsigned int ageing_time; }; struct dsa_switch { @@ -329,6 +330,7 @@ struct dsa_switch_driver { /* * Bridge integration */ + int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port); -- cgit v1.2.3 From 2d283bdd079c0ad4da020bbc9e9c2a4280823098 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 19 Jul 2016 11:54:16 +1000 Subject: net/ncsi: Resource management NCSI spec (DSP0222) defines several objects: package, channel, mode, filter, version and statistics etc. This introduces the data structs to represent those objects and implement functions to manage them. Also, this introduces CONFIG_NET_NCSI for the newly implemented NCSI stack. * The user (e.g. netdev driver) dereference NCSI device by "struct ncsi_dev", which is embedded to "struct ncsi_dev_priv". The later one is used by NCSI stack internally. * Every NCSI device can have multiple packages simultaneously, up to 8 packages. It's represented by "struct ncsi_package" and identified by 3-bits ID. * Every NCSI package can have multiple channels, up to 32. It's represented by "struct ncsi_channel" and identified by 5-bits ID. * Every NCSI channel has version, statistics, various modes and filters. They are represented by "struct ncsi_channel_version", "struct ncsi_channel_stats", "struct ncsi_channel_mode" and "struct ncsi_channel_filter" separately. * Apart from AEN (Asynchronous Event Notification), the NCSI stack works in terms of command and response. This introduces "struct ncsi_req" to represent a complete NCSI transaction made of NCSI request and response. link: https://www.dmtf.org/sites/default/files/standards/documents/DSP0222_1.1.0.pdf Signed-off-by: Gavin Shan Acked-by: Joel Stanley Signed-off-by: David S. Miller --- include/net/ncsi.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 include/net/ncsi.h (limited to 'include') diff --git a/include/net/ncsi.h b/include/net/ncsi.h new file mode 100644 index 000000000000..70d14ee1ef84 --- /dev/null +++ b/include/net/ncsi.h @@ -0,0 +1,46 @@ +#ifndef __NET_NCSI_H +#define __NET_NCSI_H + +/* + * The NCSI device states seen from external. More NCSI device states are + * only visible internally (in net/ncsi/internal.h). When the NCSI device + * is registered, it's in ncsi_dev_state_registered state. The state + * ncsi_dev_state_start is used to drive to choose active package and + * channel. After that, its state is changed to ncsi_dev_state_functional. + * + * The state ncsi_dev_state_stop helps to shut down the currently active + * package and channel while ncsi_dev_state_config helps to reconfigure + * them. + */ +enum { + ncsi_dev_state_registered = 0x0000, + ncsi_dev_state_functional = 0x0100, + ncsi_dev_state_probe = 0x0200, + ncsi_dev_state_config = 0x0300, + ncsi_dev_state_suspend = 0x0400, +}; + +struct ncsi_dev { + int state; + int link_up; + struct net_device *dev; + void (*handler)(struct ncsi_dev *ndev); +}; + +#ifdef CONFIG_NET_NCSI +struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + void (*notifier)(struct ncsi_dev *nd)); +void ncsi_unregister_dev(struct ncsi_dev *nd); +#else /* !CONFIG_NET_NCSI */ +static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev, + void (*notifier)(struct ncsi_dev *nd)) +{ + return NULL; +} + +static inline void ncsi_unregister_dev(struct ncsi_dev *nd) +{ +} +#endif /* CONFIG_NET_NCSI */ + +#endif /* __NET_NCSI_H */ -- cgit v1.2.3 From 6389eaa7fa9c3ee6c7d39f6087b86660d17236ac Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 19 Jul 2016 11:54:17 +1000 Subject: net/ncsi: NCSI command packet handler The NCSI command packets are sent from MC (Management Controller) to remote end. They are used for multiple purposes: probe existing NCSI package/channel, retrieve NCSI channel's capability, configure NCSI channel etc. This defines struct to represent NCSI command packets and introduces function ncsi_xmit_cmd(), which will be used to transmit NCSI command packet according to the request. The request is represented by struct ncsi_cmd_arg. Signed-off-by: Gavin Shan Acked-by: Joel Stanley Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index cec849a239f6..117d02e0fc31 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -87,6 +87,7 @@ #define ETH_P_8021AH 0x88E7 /* 802.1ah Backbone Service Tag */ #define ETH_P_MVRP 0x88F5 /* 802.1Q MVRP */ #define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */ +#define ETH_P_NCSI 0x88F8 /* NCSI protocol */ #define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_TDLS 0x890D /* TDLS */ -- cgit v1.2.3 From e6f44ed6d04d3185dcd8e8e98af8742d87bdffcc Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 19 Jul 2016 11:54:19 +1000 Subject: net/ncsi: Package and channel management This manages NCSI packages and channels: * The available packages and channels are enumerated in the first time of calling ncsi_start_dev(). The channels' capabilities are probed in the meanwhile. The NCSI network topology won't change until the NCSI device is destroyed. * There in a queue in every NCSI device. The element in the queue, channel, is waiting for configuration (bringup) or suspending (teardown). The channel's state (inactive/active) indicates the futher action (configuration or suspending) will be applied on the channel. Another channel's state (invisible) means the requested action is being applied. * The hardware arbitration will be enabled if all available packages and channels support it. All available channels try to provide service when hardware arbitration is enabled. Otherwise, one channel is selected as the active one at once. * When channel is in active state, meaning it's providing service, a timer started to retrieve the channe's link status. If the channel's link status fails to be updated in the determined period, the channel is going to be reconfigured. It's the error handling implementation as defined in NCSI spec. Signed-off-by: Gavin Shan Acked-by: Joel Stanley Signed-off-by: David S. Miller --- include/net/ncsi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/ncsi.h b/include/net/ncsi.h index 70d14ee1ef84..1dbf42f79750 100644 --- a/include/net/ncsi.h +++ b/include/net/ncsi.h @@ -30,6 +30,7 @@ struct ncsi_dev { #ifdef CONFIG_NET_NCSI struct ncsi_dev *ncsi_register_dev(struct net_device *dev, void (*notifier)(struct ncsi_dev *nd)); +int ncsi_start_dev(struct ncsi_dev *nd); void ncsi_unregister_dev(struct ncsi_dev *nd); #else /* !CONFIG_NET_NCSI */ static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev, @@ -38,6 +39,11 @@ static inline struct ncsi_dev *ncsi_register_dev(struct net_device *dev, return NULL; } +static inline int ncsi_start_dev(struct ncsi_dev *nd) +{ + return -ENOTTY; +} + static inline void ncsi_unregister_dev(struct ncsi_dev *nd) { } -- cgit v1.2.3 From b9c13fe32faaa71c4e4f8a426d79f8c93495e9f9 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 8 Jul 2016 08:35:59 +1000 Subject: dt: Add of_device_compatible_match() This provides an equivalent of of_fdt_match() for non-flat trees. This is more practical than matching an array of of_device_id structs when converting a bunch of existing users of of_fdt_match(). Signed-off-by: Benjamin Herrenschmidt Acked-by: Rob Herring Signed-off-by: Michael Ellerman --- include/linux/of.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index 74eb28cadbef..33c184d3dcd8 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -324,6 +324,8 @@ extern int of_property_read_string_helper(const struct device_node *np, const char **out_strs, size_t sz, int index); extern int of_device_is_compatible(const struct device_node *device, const char *); +extern int of_device_compatible_match(struct device_node *device, + const char *const *compat); extern bool of_device_is_available(const struct device_node *device); extern bool of_device_is_big_endian(const struct device_node *device); extern const void *of_get_property(const struct device_node *node, -- cgit v1.2.3 From 59d3656d5bf504f771fc44fdbc7a9a8590795f22 Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:46 -0700 Subject: bpf: add bpf_prog_add api for bulk prog refcnt A subsystem may need to store many copies of a bpf program, each deserving its own reference. Rather than requiring the caller to loop one by one (with possible mid-loop failure), add a bulk bpf_prog_add api. Signed-off-by: Brenden Blanco Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c13e92b00bf5..75a5ae6bee07 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -224,6 +224,7 @@ void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); +struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i); struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -- cgit v1.2.3 From 6a773a15a1e8874e5eccd2f29190c31085912c95 Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:47 -0700 Subject: bpf: add XDP prog type for early driver filter Add a new bpf prog type that is intended to run in early stages of the packet rx path. Only minimal packet metadata will be available, hence a new context type, struct xdp_md, is exposed to userspace. So far only expose the packet start and end pointers, and only in read mode. An XDP program must return one of the well known enum values, all other return codes are reserved for future use. Unfortunately, this restriction is hard to enforce at verification time, so take the approach of warning at runtime when such programs are encountered. Out of bounds return codes should alias to XDP_ABORTED. Signed-off-by: Brenden Blanco Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 18 ++++++++++++++++++ include/uapi/linux/bpf.h | 20 ++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fc31ef1da2d..15d816a8b755 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -368,6 +368,11 @@ struct bpf_skb_data_end { void *data_end; }; +struct xdp_buff { + void *data; + void *data_end; +}; + /* compute the linear packet data range [data, data_end) which * will be accessed by cls_bpf and act_bpf programs */ @@ -429,6 +434,18 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, return BPF_PROG_RUN(prog, skb); } +static inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, + struct xdp_buff *xdp) +{ + u32 ret; + + rcu_read_lock(); + ret = BPF_PROG_RUN(prog, (void *)xdp); + rcu_read_unlock(); + + return ret; +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), @@ -509,6 +526,7 @@ bool bpf_helper_changes_skb_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c4d922439d20..a51786566c2f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -94,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -439,4 +440,23 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From a7862b45849fe2f8610a2bec89235580f55d337f Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:48 -0700 Subject: net: add ndo to setup/query xdp prog in adapter rx Add one new netdev op for drivers implementing the BPF_PROG_TYPE_XDP filter. The single op is used for both setup/query of the xdp program, modelled after ndo_setup_tc. Signed-off-by: Brenden Blanco Signed-off-by: David S. Miller --- include/linux/netdevice.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 49736a31acaa..fab9a1c2a2ac 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -63,6 +63,7 @@ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; +struct bpf_prog; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -799,6 +800,33 @@ struct tc_to_netdev { }; }; +/* These structures hold the attributes of xdp state that are being passed + * to the netdevice through the xdp op. + */ +enum xdp_netdev_command { + /* Set or clear a bpf program used in the earliest stages of packet + * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee + * is responsible for calling bpf_prog_put on any old progs that are + * stored. In case of error, the callee need not release the new prog + * reference, but on success it takes ownership and must bpf_prog_put + * when it is no longer used. + */ + XDP_SETUP_PROG, + /* Check if a bpf program is set on the device. The callee should + * return true if a program is currently attached and running. + */ + XDP_QUERY_PROG, +}; + +struct netdev_xdp { + enum xdp_netdev_command command; + union { + /* XDP_SETUP_PROG */ + struct bpf_prog *prog; + /* XDP_QUERY_PROG */ + bool prog_attached; + }; +}; /* * This structure defines the management hooks for network devices. @@ -1087,6 +1115,9 @@ struct tc_to_netdev { * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. + * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + * This function is used to set or query state related to XDP on the + * netdevice. See definition of enum xdp_netdev_command for details. * */ struct net_device_ops { @@ -1271,6 +1302,8 @@ struct net_device_ops { struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); + int (*ndo_xdp)(struct net_device *dev, + struct netdev_xdp *xdp); }; /** @@ -3257,6 +3290,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); +int dev_change_xdp_fd(struct net_device *dev, int fd); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From d1fdd9138682e0f272beee0cb08b6328c5478b26 Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:49 -0700 Subject: rtnl: add option for setting link xdp prog Sets the bpf program represented by fd as an early filter in the rx path of the netdev. The fd must have been created as BPF_PROG_TYPE_XDP. Providing a negative value as fd clears the program. Getting the fd back via rtnl is not possible, therefore reading of this value merely provides a bool whether the program is valid on the link or not. Signed-off-by: Brenden Blanco Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4285ac31e865..a1b5202c5f6b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -156,6 +156,7 @@ enum { IFLA_GSO_MAX_SEGS, IFLA_GSO_MAX_SIZE, IFLA_PAD, + IFLA_XDP, __IFLA_MAX }; @@ -843,4 +844,15 @@ enum { }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) +/* XDP section */ + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ -- cgit v1.2.3 From 6ce96ca348a9e949f8c43f4d3e98db367d93cffd Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:53 -0700 Subject: bpf: add XDP_TX xdp_action for direct forwarding XDP enabled drivers must transmit received packets back out on the same port they were received on when a program returns this action. Signed-off-by: Brenden Blanco Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a51786566c2f..2b7076f5b5ad 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -449,6 +449,7 @@ enum xdp_action { XDP_ABORTED = 0, XDP_DROP, XDP_PASS, + XDP_TX, }; /* user accessible metadata for XDP packet hook -- cgit v1.2.3 From 224e92e02a769b8028ca2450443586af8b4f1715 Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Tue, 19 Jul 2016 12:16:54 -0700 Subject: net/mlx4_en: break out tx_desc write into separate function In preparation for writing the tx descriptor from multiple functions, create a helper for both normal and blueflame access. Signed-off-by: Brenden Blanco Signed-off-by: David S. Miller --- include/linux/mlx4/qp.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 587cdf943b52..deaa2217214d 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -291,16 +291,18 @@ enum { MLX4_WQE_CTRL_FORCE_LOOPBACK = 1 << 0, }; +union mlx4_wqe_qpn_vlan { + struct { + __be16 vlan_tag; + u8 ins_vlan; + u8 fence_size; + }; + __be32 bf_qpn; +}; + struct mlx4_wqe_ctrl_seg { __be32 owner_opcode; - union { - struct { - __be16 vlan_tag; - u8 ins_vlan; - u8 fence_size; - }; - __be32 bf_qpn; - }; + union mlx4_wqe_qpn_vlan qpn_vlan; /* * High 24 bits are SRC remote buffer; low 8 bits are flags: * [7] SO (strong ordering) -- cgit v1.2.3 From 37b502f121adab26ccc2769c3063f0e1272be7de Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 20 Jul 2016 09:51:11 +0200 Subject: arm/perf: Fix hotplug state machine conversion Mark Rutland pointed out that this commit is incomplete: 7d88eb695a1f ("arm/perf: Convert to hotplug state machine") The problem is that: > We may have multiple PMUs (e.g. two in big.LITTLE systems), and > __oprofile_cpu_pmu only contains one of these. So this conversion is not > correct. > > We were relying on the notifier list implicitly containing a list of > those PMUs. It seems like we need an explicit list here. > > We keep __oprofile_cpu_pmu around for legacy 32-bit users of OProfile > (on non-hetereogeneous systems), and that's all that the variable should > be used for. Introduce arm_pmu_list to correctly handle multiple PMUs in the system. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Mark Rutland Cc: Anna-Maria Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-tip-commits@vger.kernel.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160719111733.GA22911@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/perf/arm_pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index e6ed34eb2b2b..e18843809eec 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -109,6 +109,7 @@ struct arm_pmu { DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); struct platform_device *plat_device; struct pmu_hw_events __percpu *hw_events; + struct list_head entry; struct notifier_block cpu_pm_nb; }; -- cgit v1.2.3 From ea263c7fada4af8ec7fe5fcfd6e7d7705a89351b Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 2 Jun 2016 20:12:37 -0500 Subject: target: Fix max_unmap_lba_count calc overflow max_discard_sectors only 32bits, and some non scsi backend devices will set this to the max 0xffffffff, so we can end up overflowing during the max_unmap_lba_count calculation. This fixes a regression caused by my patch: commit 8a9ebe717a133ba7bc90b06047f43cc6b8bcb8b3 Author: Mike Christie Date: Mon Jan 18 14:09:27 2016 -0600 target: Fix WRITE_SAME/DISCARD conversion to linux 512b sectors which can result in extra discards being sent to due the overflow causing max_unmap_lba_count to be smaller than what the backing device can actually support. Signed-off-by: Mike Christie Reviewed-by: Bart Van Assche Cc: stable@vger.kernel.org Signed-off-by: Nicholas Bellinger --- include/target/target_core_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index d8ab5101fad5..f6f3bc52c1ac 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -95,6 +95,6 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q, int block_size); + struct request_queue *q); #endif /* TARGET_CORE_BACKEND_H */ -- cgit v1.2.3 From dff0ca9ea7dc8be2181a62df4a722c32ce68ff4a Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Tue, 17 May 2016 22:19:10 -0700 Subject: target: Fix ordered task target_setup_cmd_from_cdb exception hang If a command with a Simple task attribute is failed due to a Unit Attention, then a subsequent command with an Ordered task attribute will hang forever. The reason for this is that the Unit Attention status is checked for in target_setup_cmd_from_cdb, before the call to target_execute_cmd, which calls target_handle_task_attr, which in turn increments dev->simple_cmds. However, transport_generic_request_failure still calls transport_complete_task_attr, which will decrement dev->simple_cmds. In this case, simple_cmds is now -1. So when a command with the Ordered task attribute is sent, target_handle_task_attr sees that dev->simple_cmds is not 0, so it decides it can't execute the command until all the (nonexistent) Simple commands have completed. Reported-by: Michael Cyr Tested-by: Michael Cyr Reported-by: Bryant G. Ly Tested-by: Bryant G. Ly Cc: stable@vger.kernel.org # 4.4+ Signed-off-by: Nicholas Bellinger --- include/target/target_core_fabric.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index de44462a7680..5cd6faa6e0d1 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -163,7 +163,6 @@ int core_tmr_alloc_req(struct se_cmd *, void *, u8, gfp_t); void core_tmr_release_req(struct se_tmr_req *); int transport_generic_handle_tmr(struct se_cmd *); void transport_generic_request_failure(struct se_cmd *, sense_reason_t); -void __target_execute_cmd(struct se_cmd *); int transport_lookup_tmr_lun(struct se_cmd *, u64); void core_allocate_nexus_loss_ua(struct se_node_acl *acl); -- cgit v1.2.3 From 410c29dfbfdf73d0d0b5d14a21868ab038eca703 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Mon, 13 Jun 2016 22:58:09 -0700 Subject: target: Fix ordered task CHECK_CONDITION early exception handling If a Simple command is sent with a failure, target_setup_cmd_from_cdb returns with TCM_UNSUPPORTED_SCSI_OPCODE or TCM_INVALID_CDB_FIELD. So in the cases where target_setup_cmd_from_cdb returns an error, we never get far enough to call target_execute_cmd to increment simple_cmds. Since simple_cmds isn't incremented, the result of the failure from target_setup_cmd_from_cdb causes transport_generic_request_failure to decrement simple_cmds, due to call to transport_complete_task_attr. With this dev->simple_cmds or dev->dev_ordered_sync is now -1, not 0. So when a subsequent command with an Ordered Task is sent, it causes a hang, since dev->simple_cmds is at -1. Tested-by: Bryant G. Ly Signed-off-by: Bryant G. Ly Tested-by: Michael Cyr Signed-off-by: Michael Cyr Cc: stable@vger.kernel.org # 4.4+ Signed-off-by: Nicholas Bellinger --- include/target/target_core_base.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index b316b44d03f3..fb8e3b6febdf 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -142,6 +142,7 @@ enum se_cmd_flags_table { SCF_PASSTHROUGH_PROT_SG_TO_MEM_NOALLOC = 0x00200000, SCF_ACK_KREF = 0x00400000, SCF_USE_CPUID = 0x00800000, + SCF_TASK_ATTR_SET = 0x01000000, }; /* -- cgit v1.2.3 From 88a678bbc34cecce36bf2c7a8af4cba38f9f77ce Mon Sep 17 00:00:00 2001 From: "Bryant G. Ly" Date: Tue, 28 Jun 2016 17:05:35 -0500 Subject: ibmvscsis: Initial commit of IBM VSCSI Tgt Driver This driver is a pick up of the old IBM VIO scsi Target Driver that was started by Nick and Fujita 2-4 years ago. http://comments.gmane.org/gmane.linux.scsi/90119 The driver provides a virtual SCSI device on IBM Power Servers. This patch contains the fifth version for an initial merge of the tcm ibmvscsis driver. More information on this driver and config can be found: https://github.com/powervm/ibmvscsis/wiki/Configuration http://www.linux-iscsi.org/wiki/IBM_vSCSI (Drop extra libsrp review breakage + Fix kconfig typo - nab) Signed-off-by: Steven Royer Signed-off-by: Tyrel Datwyler Signed-off-by: Michael Cyr Signed-off-by: Bryant G. Ly Cc: FUJITA Tomonori Signed-off-by: Nicholas Bellinger --- include/scsi/viosrp.h | 220 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 220 insertions(+) create mode 100644 include/scsi/viosrp.h (limited to 'include') diff --git a/include/scsi/viosrp.h b/include/scsi/viosrp.h new file mode 100644 index 000000000000..974e07bd8e59 --- /dev/null +++ b/include/scsi/viosrp.h @@ -0,0 +1,220 @@ +/*****************************************************************************/ +/* srp.h -- SCSI RDMA Protocol definitions */ +/* */ +/* Written By: Colin Devilbis, IBM Corporation */ +/* */ +/* Copyright (C) 2003 IBM Corporation */ +/* */ +/* This program is free software; you can redistribute it and/or modify */ +/* it under the terms of the GNU General Public License as published by */ +/* the Free Software Foundation; 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. */ +/* */ +/* This file contains structures and definitions for IBM RPA (RS/6000 */ +/* platform architecture) implementation of the SRP (SCSI RDMA Protocol) */ +/* standard. SRP is used on IBM iSeries and pSeries platforms to send SCSI */ +/* commands between logical partitions. */ +/* */ +/* SRP Information Units (IUs) are sent on a "Command/Response Queue" (CRQ) */ +/* between partitions. The definitions in this file are architected, */ +/* and cannot be changed without breaking compatibility with other versions */ +/* of Linux and other operating systems (AIX, OS/400) that talk this protocol*/ +/* between logical partitions */ +/*****************************************************************************/ +#ifndef VIOSRP_H +#define VIOSRP_H +#include + +#define SRP_VERSION "16.a" +#define SRP_MAX_IU_LEN 256 +#define SRP_MAX_LOC_LEN 32 + +union srp_iu { + struct srp_login_req login_req; + struct srp_login_rsp login_rsp; + struct srp_login_rej login_rej; + struct srp_i_logout i_logout; + struct srp_t_logout t_logout; + struct srp_tsk_mgmt tsk_mgmt; + struct srp_cmd cmd; + struct srp_rsp rsp; + u8 reserved[SRP_MAX_IU_LEN]; +}; + +enum viosrp_crq_headers { + VIOSRP_CRQ_FREE = 0x00, + VIOSRP_CRQ_CMD_RSP = 0x80, + VIOSRP_CRQ_INIT_RSP = 0xC0, + VIOSRP_CRQ_XPORT_EVENT = 0xFF +}; + +enum viosrp_crq_init_formats { + VIOSRP_CRQ_INIT = 0x01, + VIOSRP_CRQ_INIT_COMPLETE = 0x02 +}; + +enum viosrp_crq_formats { + VIOSRP_SRP_FORMAT = 0x01, + VIOSRP_MAD_FORMAT = 0x02, + VIOSRP_OS400_FORMAT = 0x03, + VIOSRP_AIX_FORMAT = 0x04, + VIOSRP_LINUX_FORMAT = 0x05, + VIOSRP_INLINE_FORMAT = 0x06 +}; + +enum viosrp_crq_status { + VIOSRP_OK = 0x0, + VIOSRP_NONRECOVERABLE_ERR = 0x1, + VIOSRP_VIOLATES_MAX_XFER = 0x2, + VIOSRP_PARTNER_PANIC = 0x3, + VIOSRP_DEVICE_BUSY = 0x8, + VIOSRP_ADAPTER_FAIL = 0x10, + VIOSRP_OK2 = 0x99, +}; + +struct viosrp_crq { + u8 valid; /* used by RPA */ + u8 format; /* SCSI vs out-of-band */ + u8 reserved; + u8 status; /* non-scsi failure? (e.g. DMA failure) */ + __be16 timeout; /* in seconds */ + __be16 IU_length; /* in bytes */ + __be64 IU_data_ptr; /* the TCE for transferring data */ +}; + +/* MADs are Management requests above and beyond the IUs defined in the SRP + * standard. + */ +enum viosrp_mad_types { + VIOSRP_EMPTY_IU_TYPE = 0x01, + VIOSRP_ERROR_LOG_TYPE = 0x02, + VIOSRP_ADAPTER_INFO_TYPE = 0x03, + VIOSRP_CAPABILITIES_TYPE = 0x05, + VIOSRP_ENABLE_FAST_FAIL = 0x08, +}; + +enum viosrp_mad_status { + VIOSRP_MAD_SUCCESS = 0x00, + VIOSRP_MAD_NOT_SUPPORTED = 0xF1, + VIOSRP_MAD_FAILED = 0xF7, +}; + +enum viosrp_capability_type { + MIGRATION_CAPABILITIES = 0x01, + RESERVATION_CAPABILITIES = 0x02, +}; + +enum viosrp_capability_support { + SERVER_DOES_NOT_SUPPORTS_CAP = 0x0, + SERVER_SUPPORTS_CAP = 0x01, + SERVER_CAP_DATA = 0x02, +}; + +enum viosrp_reserve_type { + CLIENT_RESERVE_SCSI_2 = 0x01, +}; + +enum viosrp_capability_flag { + CLIENT_MIGRATED = 0x01, + CLIENT_RECONNECT = 0x02, + CAP_LIST_SUPPORTED = 0x04, + CAP_LIST_DATA = 0x08, +}; + +/* + * Common MAD header + */ +struct mad_common { + __be32 type; + __be16 status; + __be16 length; + __be64 tag; +}; + +/* + * All SRP (and MAD) requests normally flow from the + * client to the server. There is no way for the server to send + * an asynchronous message back to the client. The Empty IU is used + * to hang out a meaningless request to the server so that it can respond + * asynchrouously with something like a SCSI AER + */ +struct viosrp_empty_iu { + struct mad_common common; + __be64 buffer; + __be32 port; +}; + +struct viosrp_error_log { + struct mad_common common; + __be64 buffer; +}; + +struct viosrp_adapter_info { + struct mad_common common; + __be64 buffer; +}; + +struct viosrp_fast_fail { + struct mad_common common; +}; + +struct viosrp_capabilities { + struct mad_common common; + __be64 buffer; +}; + +struct mad_capability_common { + __be32 cap_type; + __be16 length; + __be16 server_support; +}; + +struct mad_reserve_cap { + struct mad_capability_common common; + __be32 type; +}; + +struct mad_migration_cap { + struct mad_capability_common common; + __be32 ecl; +}; + +struct capabilities { + __be32 flags; + char name[SRP_MAX_LOC_LEN]; + char loc[SRP_MAX_LOC_LEN]; + struct mad_migration_cap migration; + struct mad_reserve_cap reserve; +}; + +union mad_iu { + struct viosrp_empty_iu empty_iu; + struct viosrp_error_log error_log; + struct viosrp_adapter_info adapter_info; + struct viosrp_fast_fail fast_fail; + struct viosrp_capabilities capabilities; +}; + +union viosrp_iu { + union srp_iu srp; + union mad_iu mad; +}; + +struct mad_adapter_info_data { + char srp_version[8]; + char partition_name[96]; + __be32 partition_number; +#define SRP_MAD_VERSION_1 1 + __be32 mad_version; +#define SRP_MAD_OS_LINUX 2 +#define SRP_MAD_OS_AIX 3 + __be32 os_type; + __be32 port_max_txu[8]; /* per-port maximum transfer */ +}; + +#endif -- cgit v1.2.3 From cc2e0b3fbcdd9667d7b7ecdf36d7b4d3647681d6 Mon Sep 17 00:00:00 2001 From: Brenden Blanco Date: Wed, 20 Jul 2016 07:55:52 -0700 Subject: bpf: fix implicit declaration of bpf_prog_add For the ifndef case of CONFIG_BPF_SYSCALL, an inline version of bpf_prog_add needs to exist otherwise the build breaks on some configs. drivers/net/ethernet/mellanox/mlx4/en_netdev.c:2544:10: error: implicit declaration of function 'bpf_prog_add' prog = bpf_prog_add(prog, priv->rx_ring_num - 1); The function is introduced in 59d3656d5bf50 ("bpf: add bpf_prog_add api for bulk prog refcnt") and first used in 47f1afdba2b87 ("net/mlx4_en: add support for fast rx drop bpf program"). Fixes: 47f1afdba2b87 ("net/mlx4_en: add support for fast rx drop bpf program") Reported-by: kbuild test robot Reported-by: Tariq Toukan Signed-off-by: Brenden Blanco Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75a5ae6bee07..36da0749205a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -289,6 +289,10 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i) +{ + return ERR_PTR(-EOPNOTSUPP); +} static inline void bpf_prog_put(struct bpf_prog *prog) { -- cgit v1.2.3 From b02b94b331be5097d248d49242bd1fc0649a8092 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 20 Jul 2016 20:17:47 +0200 Subject: bpf, elf: add official ELF machine define for eBPF Add the official BPF ELF e_machine value that was assigned recently [1,2] and will be propagated to glibc, et al. LLVM is switching to it in 3.9 release. [1] https://github.com/llvm-mirror/llvm/commit/36b9c09330bfb5e771914cfe307588f30d5510d2 [2] http://lists.iovisor.org/pipermail/iovisor-dev/2016-June/000266.html Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/elf-em.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index c3fdfe79e5cc..cb5d1a519202 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -40,6 +40,7 @@ #define EM_TILEPRO 188 /* Tilera TILEPro */ #define EM_MICROBLAZE 189 /* Xilinx MicroBlaze */ #define EM_TILEGX 191 /* Tilera TILE-Gx */ +#define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */ #define EM_FRV 0x5441 /* Fujitsu FR-V */ #define EM_AVR32 0x18ad /* Atmel AVR32 */ -- cgit v1.2.3 From e950fdf71c9b4a6b63b58fed78956a96cc907402 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:23:33 +0200 Subject: block: introduce BLKDEV_DISCARD_ZERO to fix zeroout Currently blkdev_issue_zeroout cascades down from discards (if the driver guarantees that discards zero data), to WRITE SAME and then to a loop writing zeroes. Unfortunately we ignore run-time EOPNOTSUPP errors in the block layer blkdev_issue_discard helper to work around DM volumes that may have mixed discard support underneath. This patch intoroduces a new BLKDEV_DISCARD_ZERO flag to blkdev_issue_discard that indicates we are called for zeroing operation. This allows both to ignore the EOPNOTSUPP hack and actually consolidating the discard_zeroes_data check into the function. Signed-off-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 53fee6123893..156455cb07ad 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1137,7 +1137,9 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return bqt->tag_index[tag]; } -#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */ + +#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ +#define BLKDEV_DISCARD_ZERO (1 << 1) /* must reliably zero data */ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, -- cgit v1.2.3 From 70246286e94c335b5bea0cbc68a17a96dd620281 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:28:41 +0200 Subject: block: get rid of bio_rw and READA These two are confusing leftover of the old world order, combining values of the REQ_OP_ and REQ_ namespaces. For callers that don't special case we mostly just replace bi_rw with bio_data_dir or op_is_write, except for the few cases where a switch over the REQ_OP_ values makes more sense. Any check for READA is replaced with an explicit check for REQ_RAHEAD. Also remove the READA alias for REQ_RAHEAD. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/fs.h | 18 +----------------- include/trace/events/f2fs.h | 4 ++-- 2 files changed, 3 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 183024525d40..dc488662ce0b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -178,9 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * READ_SYNC A synchronous read. Device is not plugged, caller can * immediately wait on this read without caring about * unplugging. - * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this - * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO @@ -195,11 +192,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * */ #define RW_MASK REQ_OP_WRITE -#define RWA_MASK REQ_RAHEAD #define READ REQ_OP_READ -#define WRITE RW_MASK -#define READA RWA_MASK +#define WRITE REQ_OP_WRITE #define READ_SYNC REQ_SYNC #define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) @@ -2470,17 +2465,6 @@ static inline bool op_is_write(unsigned int op) return op == REQ_OP_READ ? false : true; } -/* - * return READ, READA, or WRITE - */ -static inline int bio_rw(struct bio *bio) -{ - if (op_is_write(bio_op(bio))) - return WRITE; - - return bio->bi_rw & RWA_MASK; -} - /* * return data direction, READ or WRITE */ diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 878963a1f058..ff95fd02116f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -55,7 +55,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) -#define F2FS_BIO_FLAG_MASK(t) (t & (READA | WRITE_FLUSH_FUA)) +#define F2FS_BIO_FLAG_MASK(t) (t & (REQ_RAHEAD | WRITE_FLUSH_FUA)) #define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO)) #define show_bio_type(op, op_flags) show_bio_op(op), \ @@ -68,7 +68,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); #define show_bio_op_flags(flags) \ __print_symbolic(F2FS_BIO_FLAG_MASK(flags), \ - { READA, "READAHEAD" }, \ + { REQ_RAHEAD, "READAHEAD" }, \ { READ_SYNC, "READ_SYNC" }, \ { WRITE_SYNC, "WRITE_SYNC" }, \ { WRITE_FLUSH, "WRITE_FLUSH" }, \ -- cgit v1.2.3 From ed996a52c868b62c4e5bf529cb4ccb44bcfa2f8e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:28:42 +0200 Subject: block: simplify and cleanup bvec pool handling Instead of a flag and an index just make sure an index of 0 means no need to free the bvec array. Also move the constants related to the bvec pools together and use a consistent naming scheme for them. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- include/linux/blk_types.h | 22 ++++++++++++++-------- 2 files changed, 14 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0bbb2e332410..141cfa95a185 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -715,8 +715,6 @@ static inline void bio_inc_remaining(struct bio *bio) * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 -#define BIOVEC_NR_POOLS 6 -#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) struct bio_set { struct kmem_cache *bio_slab; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index efba1f2ace2e..b76463ea3587 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -134,19 +134,25 @@ struct bio { /* * Flags starting here get preserved by bio_reset() - this includes - * BIO_POOL_IDX() + * BVEC_POOL_IDX() */ #define BIO_RESET_BITS 13 -#define BIO_OWNS_VEC 13 /* bio_free() should free bvec */ /* - * top 4 bits of bio flags indicate the pool this bio came from + * We support 6 different bvec pools, the last one is magic in that it + * is backed by a mempool. */ -#define BIO_POOL_BITS (4) -#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) -#define BIO_POOL_OFFSET (32 - BIO_POOL_BITS) -#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) -#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) +#define BVEC_POOL_NR 6 +#define BVEC_POOL_MAX (BVEC_POOL_NR - 1) + +/* + * Top 4 bits of bio flags indicate the pool the bvecs came from. We add + * 1 to the actual index so that 0 indicates that there are no bvecs to be + * freed. + */ +#define BVEC_POOL_BITS (4) +#define BVEC_POOL_OFFSET (32 - BVEC_POOL_BITS) +#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From c0acf12a50c2b6cbaf72bdfe2b1b514c369a83c5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:28:43 +0200 Subject: block: shrink bio size again The recent ops split grew the bio by adding the new ioprio field. Shrink it again by using a 16-bit field for the bi_flags value and filling the holes near the beginning of the structure. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b76463ea3587..c3525c5564b2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -46,11 +46,11 @@ struct bvec_iter { struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_flags; /* status, command, etc */ int bi_error; unsigned int bi_rw; /* bottom bits req flags, * top bits REQ_OP */ + unsigned short bi_flags; /* status, command, etc */ unsigned short bi_ioprio; struct bvec_iter bi_iter; @@ -136,7 +136,7 @@ struct bio { * Flags starting here get preserved by bio_reset() - this includes * BVEC_POOL_IDX() */ -#define BIO_RESET_BITS 13 +#define BIO_RESET_BITS 10 /* * We support 6 different bvec pools, the last one is magic in that it @@ -151,7 +151,7 @@ struct bio { * freed. */ #define BVEC_POOL_BITS (4) -#define BVEC_POOL_OFFSET (32 - BVEC_POOL_BITS) +#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) #define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) #endif /* CONFIG_BLOCK */ -- cgit v1.2.3 From 98d61d5b1a65a9df7cb3d9605f5d37d3dbbb4b5e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:31:51 +0200 Subject: block: simplify and export blk_rq_append_bio The target SCSI passthrough backend is much better served with the low-level blk_rq_append_bio construct then the helpers built on top of it, so export it. Also use the opportunity to remove the pointless request_queue argument and make the code flow a little more readable. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 156455cb07ad..706c8bf61c84 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -802,6 +802,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); +extern int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_queue_split(struct request_queue *, struct bio **, struct bio_set *); -- cgit v1.2.3 From 4613c5f1df92f3cb5a8f89c7dfefc37402c16bd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Jul 2016 11:31:53 +0200 Subject: scsi/osd: open code blk_make_request I wish the OSD code could simply use blk_rq_map_* helpers like everyone else, but the complex nature of deciding if we have DATA IN and/or DATA OUT buffers might make this impossible (at least for a mere human like me). But using blk_rq_append_bio at least allows sharing the setup code between request with or without dat a buffers, and given that this is the last user of blk_make_request it allows getting rid of that somewhat awkward interface. Signed-off-by: Christoph Hellwig Acked-by: Boaz Harrosh Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 706c8bf61c84..0cdea75a6614 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -788,8 +788,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern struct request *blk_make_request(struct request_queue *, struct bio *, - gfp_t); extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, -- cgit v1.2.3 From 9a6cf881df0293cc1c06d31bcbeda6c23b95dcac Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 19 Jul 2016 13:49:40 +0200 Subject: fcoe: implement FIP VLAN responder When running in VN2VN mode there is no central instance which would send out any FIP VLAN discovery notifications. So this patch adds a new sysfs attribute 'fip_vlan_responder' which will activate a FIP VLAN discovery responder. Signed-off-by: Hannes Reinecke Acked-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/scsi/libfc.h | 1 + include/scsi/libfcoe.h | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 93d14daf0994..7428a53257ca 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -878,6 +878,7 @@ struct fc_lport { struct libfc_function_template tt; u8 link_up; u8 qfull; + u16 vlan; enum fc_lport_state state; unsigned long boot_time; struct fc_host_statistics host_stats; diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index bcc5c3e82977..722d3264d3bf 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -110,8 +110,10 @@ enum fip_mode { * @flogi_req_send: send of FLOGI requested * @flogi_count: number of FLOGI attempts in AUTO mode. * @map_dest: use the FC_MAP mode for destination MAC addresses. + * @fip_resp: start FIP VLAN discovery responder * @spma: supports SPMA server-provided MACs mode * @probe_tries: number of FC_IDs probed + * @priority: DCBx FCoE APP priority * @dest_addr: MAC address of the selected FC forwarder. * @ctl_src_addr: the native MAC address of our local port. * @send: LLD-supplied function to handle sending FIP Ethernet frames @@ -149,7 +151,8 @@ struct fcoe_ctlr { u16 flogi_oxid; u8 flogi_req_send; u8 flogi_count; - u8 map_dest; + bool map_dest; + bool fip_resp; u8 spma; u8 probe_tries; u8 priority; -- cgit v1.2.3 From 82de0be6862cdca2e6802267bda57cfc8844d3a7 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Mon, 18 Jul 2016 11:39:23 +0800 Subject: netfilter: Add helper array register/unregister functions Add nf_ct_helper_init(), nf_conntrack_helpers_register() and nf_conntrack_helpers_unregister() functions to avoid repetitive opencoded initialization in helpers. This patch keeps an id parameter for nf_ct_helper_init() not to break helper matching by name that has been inconsistently exposed to userspace through ports, eg. ftp-2121, and through an incremental id, eg. tftp-1. Signed-off-by: Gao Feng Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_helper.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 6cf614bc0029..1eaac1f4cd6a 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -58,10 +58,25 @@ struct nf_conntrack_helper *__nf_conntrack_helper_find(const char *name, struct nf_conntrack_helper *nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum); +void nf_ct_helper_init(struct nf_conntrack_helper *helper, + u16 l3num, u16 protonum, const char *name, + u16 default_port, u16 spec_port, u32 id, + const struct nf_conntrack_expect_policy *exp_pol, + u32 expect_class_max, u32 data_len, + int (*help)(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo), + int (*from_nlattr)(struct nlattr *attr, + struct nf_conn *ct), + struct module *module); int nf_conntrack_helper_register(struct nf_conntrack_helper *); void nf_conntrack_helper_unregister(struct nf_conntrack_helper *); +int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int); +void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *, + unsigned int); + struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp); -- cgit v1.2.3 From 163d4baaebe39c0e56d9c08597eab7b3ae0bf334 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 23 Jun 2016 17:05:50 -0400 Subject: block: add QUEUE_FLAG_DAX for devices to advertise their DAX support Currently, presence of direct_access() in block_device_operations indicates support of DAX on its block device. Because block_device_operations is instantiated with 'const', this DAX capablity may not be enabled conditinally. In preparation for supporting DAX to device-mapper devices, add QUEUE_FLAG_DAX to request_queue flags to advertise their DAX support. This will allow to set the DAX capability based on how mapped device is composed. Signed-off-by: Toshi Kani Acked-by: Dan Williams Signed-off-by: Mike Snitzer Cc: Jens Axboe Cc: Ross Zwisler Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d116d3b52c73..9d84c98b5c79 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -505,6 +505,7 @@ struct request_queue { #define QUEUE_FLAG_WC 23 /* Write back caching */ #define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ +#define QUEUE_FLAG_DAX 26 /* device supports DAX */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -594,6 +595,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_secdiscard(q) (blk_queue_discard(q) && \ test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) +#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ -- cgit v1.2.3 From 4f3ccd76572a83278166c12f3e351e74cc03578c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 16:06:15 -0400 Subject: qstr: constify dentry_init_security Signed-off-by: Al Viro --- include/linux/lsm_hooks.h | 2 +- include/linux/security.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7ae397669d8b..101bf19c0f41 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1356,7 +1356,7 @@ union security_list_options { struct super_block *newsb); int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); int (*dentry_init_security)(struct dentry *dentry, int mode, - struct qstr *name, void **ctx, + const struct qstr *name, void **ctx, u32 *ctxlen); diff --git a/include/linux/security.h b/include/linux/security.h index 14df373ff2ca..7831cd57bcf7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -240,7 +240,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb); int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_dentry_init_security(struct dentry *dentry, int mode, - struct qstr *name, void **ctx, + const struct qstr *name, void **ctx, u32 *ctxlen); int security_inode_alloc(struct inode *inode); @@ -591,7 +591,7 @@ static inline void security_inode_free(struct inode *inode) static inline int security_dentry_init_security(struct dentry *dentry, int mode, - struct qstr *name, + const struct qstr *name, void **ctx, u32 *ctxlen) { -- cgit v1.2.3 From beffb8feb6e26851165ee927e0eb963d6db334b0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 16:34:42 -0400 Subject: qstr: constify instances in nfs Signed-off-by: Al Viro --- include/linux/nfs_xdr.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c304a11b5b1a..890b4aba2711 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1543,7 +1543,7 @@ struct nfs_rpc_ops { struct nfs_fattr *, struct nfs4_label *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct qstr *, + int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); @@ -1551,18 +1551,18 @@ struct nfs_rpc_ops { unsigned int); int (*create) (struct inode *, struct dentry *, struct iattr *, int); - int (*remove) (struct inode *, struct qstr *); + int (*remove) (struct inode *, const struct qstr *); void (*unlink_setup) (struct rpc_message *, struct inode *dir); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); void (*rename_setup) (struct rpc_message *msg, struct inode *dir); void (*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *); int (*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir); - int (*link) (struct inode *, struct inode *, struct qstr *); + int (*link) (struct inode *, struct inode *, const struct qstr *); int (*symlink) (struct inode *, struct dentry *, struct page *, unsigned int, struct iattr *); int (*mkdir) (struct inode *, struct dentry *, struct iattr *); - int (*rmdir) (struct inode *, struct qstr *); + int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, u64, struct page **, unsigned int, int); int (*mknod) (struct inode *, struct dentry *, struct iattr *, -- cgit v1.2.3 From 9aba36dea59264d11cd36219937296b4903c89b6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 22:28:45 -0400 Subject: qstr constify instances in fs/dcache.c Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f53fa055021a..f912a1e5c7cb 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -264,7 +264,7 @@ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); -extern void dentry_update_name_case(struct dentry *, struct qstr *); +extern void dentry_update_name_case(struct dentry *, const struct qstr *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); -- cgit v1.2.3 From 72ef799b3f14f4cb4c56ba3af6e6bdcbae6df368 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Thu, 7 Jul 2016 11:48:22 -0700 Subject: block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan Signed-off-by: Jens Axboe --- include/linux/elevator.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 953d28647435..e7f358d2e5fc 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -16,7 +16,11 @@ typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int); -typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *); +typedef int (elevator_allow_bio_merge_fn) (struct request_queue *, + struct request *, struct bio *); + +typedef int (elevator_allow_rq_merge_fn) (struct request_queue *, + struct request *, struct request *); typedef void (elevator_bio_merged_fn) (struct request_queue *, struct request *, struct bio *); @@ -46,7 +50,8 @@ struct elevator_ops elevator_merge_fn *elevator_merge_fn; elevator_merged_fn *elevator_merged_fn; elevator_merge_req_fn *elevator_merge_req_fn; - elevator_allow_merge_fn *elevator_allow_merge_fn; + elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn; + elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn; elevator_bio_merged_fn *elevator_bio_merged_fn; elevator_dispatch_fn *elevator_dispatch_fn; @@ -157,7 +162,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); extern int elevator_change(struct request_queue *, const char *); -extern bool elv_rq_merge_ok(struct request *, struct bio *); +extern bool elv_bio_merge_ok(struct request *, struct bio *); extern struct elevator_queue *elevator_alloc(struct request_queue *, struct elevator_type *); -- cgit v1.2.3 From 17007f3994cdb4643355c73f54f0adad006cf59e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 20 Jul 2016 21:40:47 -0600 Subject: block: Fix front merge check For a front merge, the maximum number of sectors of the request must be checked against the front merge BIO sector, not the current sector of the request. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9d84c98b5c79..48f05d768a53 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -922,7 +922,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, (offset & (q->limits.chunk_sectors - 1)); } -static inline unsigned int blk_rq_get_max_sectors(struct request *rq) +static inline unsigned int blk_rq_get_max_sectors(struct request *rq, + sector_t offset) { struct request_queue *q = rq->q; @@ -932,7 +933,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) return blk_queue_get_max_sectors(q, req_op(rq)); - return min(blk_max_size_offset(q, blk_rq_pos(rq)), + return min(blk_max_size_offset(q, offset), blk_queue_get_max_sectors(q, req_op(rq))); } -- cgit v1.2.3 From 545ed20e6df68a4d2584a29a2a28ee8b2f7e9547 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 22 Jun 2016 17:54:53 -0600 Subject: dm: add infrastructure for DAX support Change mapped device to implement direct_access function, dm_blk_direct_access(), which calls a target direct_access function. 'struct target_type' is extended to have target direct_access interface. This function limits direct accessible size to the dm_target's limit with max_io_len(). Add dm_table_supports_dax() to iterate all targets and associated block devices to check for DAX support. To add DAX support to a DM target the target must only implement the direct_access function. Add a new dm type, DM_TYPE_DAX_BIO_BASED, which indicates that mapped device supports DAX and is bio based. This new type is used to assure that all target devices have DAX support and remain that way after QUEUE_FLAG_DAX is set in mapped device. At initial table load, QUEUE_FLAG_DAX is set to mapped device when setting DM_TYPE_DAX_BIO_BASED to the type. Any subsequent table load to the mapped device must have the same type, or else it fails per the check in table_load(). Signed-off-by: Toshi Kani Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 10 ++++++++++ include/uapi/linux/dm-ioctl.h | 4 ++-- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 2ce339212b6e..b0db857f334b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -26,6 +26,7 @@ struct bio_vec; #define DM_TYPE_BIO_BASED 1 #define DM_TYPE_REQUEST_BASED 2 #define DM_TYPE_MQ_REQUEST_BASED 3 +#define DM_TYPE_DAX_BIO_BASED 4 typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t; @@ -124,6 +125,14 @@ typedef void (*dm_io_hints_fn) (struct dm_target *ti, */ typedef int (*dm_busy_fn) (struct dm_target *ti); +/* + * Returns: + * < 0 : error + * >= 0 : the number of bytes accessible at the address + */ +typedef long (*dm_direct_access_fn) (struct dm_target *ti, sector_t sector, + void __pmem **kaddr, pfn_t *pfn, long size); + void dm_error(const char *message); struct dm_dev { @@ -170,6 +179,7 @@ struct target_type { dm_busy_fn busy; dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; + dm_direct_access_fn direct_access; /* For internal device-mapper use. */ struct list_head list; diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 30afd0a23c4b..4bf9f1eabffc 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 34 +#define DM_VERSION_MINOR 35 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2015-10-28)" +#define DM_VERSION_EXTRA "-ioctl (2016-06-23)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From e3c06236087051d5c62d60d0668588c370fda887 Mon Sep 17 00:00:00 2001 From: Steve Muckle Date: Wed, 13 Jul 2016 13:25:25 -0700 Subject: cpufreq: add cpufreq_driver_resolve_freq() Cpufreq governors may need to know what a particular target frequency maps to in the driver without necessarily wanting to set the frequency. Support this operation via a new cpufreq API, cpufreq_driver_resolve_freq(). This API returns the lowest driver frequency equal or greater than the target frequency (CPUFREQ_RELATION_L), subject to any policy (min/max) or driver limitations. The mapping is also cached in the policy so that a subsequent fast_switch operation can avoid repeating the same lookup. The API will call a new cpufreq driver callback, resolve_freq(), if it has been registered by the driver. Otherwise the frequency is resolved via cpufreq_frequency_table_target(). Rather than require ->target() style drivers to provide a resolve_freq() callback it is left to the caller to ensure that the driver implements this callback if necessary to use cpufreq_driver_resolve_freq(). Suggested-by: Rafael J. Wysocki Signed-off-by: Steve Muckle Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c6410b1b2490..631ba33bbe9f 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -120,6 +120,10 @@ struct cpufreq_policy { bool fast_switch_possible; bool fast_switch_enabled; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ + unsigned int cached_target_freq; + int cached_resolved_idx; + /* Synchronization for frequency transitions */ bool transition_ongoing; /* Tracks transition status */ spinlock_t transition_lock; @@ -270,6 +274,16 @@ struct cpufreq_driver { unsigned int index); unsigned int (*fast_switch)(struct cpufreq_policy *policy, unsigned int target_freq); + + /* + * Caches and returns the lowest driver-supported frequency greater than + * or equal to the target frequency, subject to any driver limitations. + * Does not set the frequency. Only to be implemented for drivers with + * target(). + */ + unsigned int (*resolve_freq)(struct cpufreq_policy *policy, + unsigned int target_freq); + /* * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION * unset. @@ -501,6 +515,8 @@ int cpufreq_driver_target(struct cpufreq_policy *policy, int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); +unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, + unsigned int target_freq); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); -- cgit v1.2.3 From aff171641d181ea573380efc3f559c9de4741fc5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Jul 2016 18:20:17 +0900 Subject: PCI: Provide sensible IRQ vector alloc/free routines Add a function to allocate and free a range of interrupt vectors, using MSI-X, MSI or legacy vectors (in that order) based on the capabilities of the underlying device and PCIe complex. Additionally a new helper is provided to get the Linux IRQ number for given device-relative vector so that the drivers don't need to allocate their own arrays to keep track of the vectors for the multi vector MSI-X case. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- include/linux/pci.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..52ecd49e8049 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1237,6 +1237,10 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); +#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ +#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ +#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ + /* kmem_cache style wrapper around pci_alloc_consistent() */ #include @@ -1284,6 +1288,11 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev, return rc; return 0; } +int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags); +void pci_free_irq_vectors(struct pci_dev *dev); +int pci_irq_vector(struct pci_dev *dev, unsigned int nr); + #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } static inline void pci_msi_shutdown(struct pci_dev *dev) { } @@ -1307,6 +1316,24 @@ static inline int pci_enable_msix_range(struct pci_dev *dev, static inline int pci_enable_msix_exact(struct pci_dev *dev, struct msix_entry *entries, int nvec) { return -ENOSYS; } +static inline int pci_alloc_irq_vectors(struct pci_dev *dev, + unsigned int min_vecs, unsigned int max_vecs, + unsigned int flags) +{ + if (min_vecs > 1) + return -EINVAL; + return 1; +} +static inline void pci_free_irq_vectors(struct pci_dev *dev) +{ +} + +static inline int pci_irq_vector(struct pci_dev *dev, unsigned int nr) +{ + if (WARN_ON_ONCE(nr > 0)) + return -EINVAL; + return dev->irq; +} #endif #ifdef CONFIG_PCIEPORTBUS -- cgit v1.2.3 From 4ef33685aa0957d771e068b60a5f3ca6b47ade1c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Jul 2016 18:20:18 +0900 Subject: PCI: Spread interrupt vectors in pci_alloc_irq_vectors() Set the affinity_mask in the PCI device before allocating vectors so that the affinity can be propagated through the MSI descriptor structures to the core IRQ code. To facilitate this, new __pci_enable_msi_range() and __pci_enable_msix_range() helpers are factored out of their not prefixed variants which assigning the new IRQ affinity mask in the PCI device so that the low-level interrupt code can perform the interrupt affinity assignment and do node-local allocations. A new PCI_IRQ_NOAFFINITY flag is added to pci_alloc_irq_vectors() so that this function can also be used by drivers that don't wish to use the automatic affinity assignment. [bhelgaas: omit "else" after "return" consistently] Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- include/linux/pci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 52ecd49e8049..f1406619f868 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -320,6 +320,7 @@ struct pci_dev { * directly, use the values stored here. They might be different! */ unsigned int irq; + struct cpumask *irq_affinity; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */ bool match_driver; /* Skip attaching driver */ @@ -1240,6 +1241,7 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ #define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ #define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ +#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ /* kmem_cache style wrapper around pci_alloc_consistent() */ -- cgit v1.2.3 From 35ae713355868aa493edbfbabf615473473215cc Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 19 Jul 2016 18:52:53 +0100 Subject: ACPI / processor_idle: introduce ACPI_PROCESSOR_CSTATE ACPI 6.0 adds a new method to specify the CPU idle states(C-states) called Low Power Idle(LPI) states. Since new architectures like ARM64 use only LPIs, introduce ACPI_PROCESSOR_CSTATE to encapsulate all the code supporting the old style C-states(_CST). This patch will help to extend the processor_idle module to support LPI. Signed-off-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/acpi/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 6f1805dd5d3c..48779d678122 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -242,7 +242,7 @@ extern int acpi_processor_get_performance_info(struct acpi_processor *pr); DECLARE_PER_CPU(struct acpi_processor *, processors); extern struct acpi_processor_errata errata; -#ifdef ARCH_HAS_POWER_INIT +#if defined(ARCH_HAS_POWER_INIT) && defined(CONFIG_ACPI_PROCESSOR_CSTATE) void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, unsigned int cpu); int acpi_processor_ffh_cstate_probe(unsigned int cpu, -- cgit v1.2.3 From a36a7fecfe6071732075ad5aa31196adce13181b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 21 Jul 2016 17:18:07 +0100 Subject: ACPI / processor_idle: Add support for Low Power Idle(LPI) states ACPI 6.0 introduced an optional object _LPI that provides an alternate method to describe Low Power Idle states. It defines the local power states for each node in a hierarchical processor topology. The OSPM can use _LPI object to select a local power state for each level of processor hierarchy in the system. They used to produce a composite power state request that is presented to the platform by the OSPM. Since multiple processors affect the idle state for any non-leaf hierarchy node, coordination of idle state requests between the processors is required. ACPI supports two different coordination schemes: Platform coordinated and OS initiated. This patch adds initial support for Platform coordination scheme of LPI. Signed-off-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/acpi/processor.h | 24 +++++++++++++++++++++--- include/linux/acpi.h | 4 ++++ 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 48779d678122..e2dcb0c51554 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -39,6 +39,7 @@ #define ACPI_CSTATE_SYSTEMIO 0 #define ACPI_CSTATE_FFH 1 #define ACPI_CSTATE_HALT 2 +#define ACPI_CSTATE_INTEGER 3 #define ACPI_CX_DESC_LEN 32 @@ -67,9 +68,25 @@ struct acpi_processor_cx { char desc[ACPI_CX_DESC_LEN]; }; +struct acpi_lpi_state { + u32 min_residency; + u32 wake_latency; /* worst case */ + u32 flags; + u32 arch_flags; + u32 res_cnt_freq; + u32 enable_parent_state; + u64 address; + u8 index; + u8 entry_method; + char desc[ACPI_CX_DESC_LEN]; +}; + struct acpi_processor_power { int count; - struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER]; + union { + struct acpi_processor_cx states[ACPI_PROCESSOR_MAX_POWER]; + struct acpi_lpi_state lpi_states[ACPI_PROCESSOR_MAX_POWER]; + }; int timer_broadcast_on_state; }; @@ -189,6 +206,7 @@ struct acpi_processor_flags { u8 bm_control:1; u8 bm_check:1; u8 has_cst:1; + u8 has_lpi:1; u8 power_setup_done:1; u8 bm_rld_set:1; u8 need_hotplug_init:1; @@ -371,7 +389,7 @@ extern struct cpuidle_driver acpi_idle_driver; #ifdef CONFIG_ACPI_PROCESSOR_IDLE int acpi_processor_power_init(struct acpi_processor *pr); int acpi_processor_power_exit(struct acpi_processor *pr); -int acpi_processor_cst_has_changed(struct acpi_processor *pr); +int acpi_processor_power_state_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); #else static inline int acpi_processor_power_init(struct acpi_processor *pr) @@ -384,7 +402,7 @@ static inline int acpi_processor_power_exit(struct acpi_processor *pr) return -ENODEV; } -static inline int acpi_processor_cst_has_changed(struct acpi_processor *pr) +static inline int acpi_processor_power_state_has_changed(struct acpi_processor *pr) { return -ENODEV; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 288fac5294f5..65754566ae17 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -444,8 +444,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 +#define OSC_SB_CPCV2_SUPPORT 0x00000040 +#define OSC_SB_PCLPI_SUPPORT 0x00000080 +#define OSC_SB_OSLPI_SUPPORT 0x00000100 extern bool osc_sb_apei_support_acked; +extern bool osc_pc_lpi_support_confirmed; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 -- cgit v1.2.3 From 220276e09bd1ccf7563b8092f7bd794336420eb1 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 19 Jul 2016 18:52:56 +0100 Subject: cpuidle: introduce CPU_PM_CPU_IDLE_ENTER macro for ARM{32, 64} The function arm_enter_idle_state is exactly the same in both generic ARM{32,64} CPUIdle driver and will be the same even on ARM64 backend for ACPI processor idle driver. So we can unify it and move it to a common place by introducing CPU_PM_CPU_IDLE_ENTER macro that can be used in all places avoiding duplication. This is in preparation of reuse of the generic cpuidle entry function for ACPI LPI support on ARM64. Suggested-by: Rafael J. Wysocki Signed-off-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 07b83d32f66c..bb31373c3478 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -252,4 +252,22 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov) #define CPUIDLE_DRIVER_STATE_START 0 #endif +#define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx) \ +({ \ + int __ret; \ + \ + if (!idx) { \ + cpu_do_idle(); \ + return idx; \ + } \ + \ + __ret = cpu_pm_enter(); \ + if (!__ret) { \ + __ret = low_level_idle_enter(idx); \ + cpu_pm_exit(); \ + } \ + \ + __ret ? -1 : idx; \ +}) + #endif /* _LINUX_CPUIDLE_H */ -- cgit v1.2.3 From bc9775d8697f57b333b6b316fb5145d6ca9dc36d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 21 Jul 2016 20:03:19 -0700 Subject: libnvdimm: move ->module to struct nvdimm_bus_descriptor Let the provider module be explicitly passed in rather than implicitly assumed by the module that calls nvdimm_bus_register(). This is in preparation for unifying the nfit and nfit_test driver teardown paths. Reviewed-by: Lee, Chun-Yi Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index d37fda6dd64c..2ab869dece4a 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -70,6 +70,7 @@ struct nd_mapping { struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; unsigned long cmd_mask; + struct module *module; char *provider_name; ndctl_fn ndctl; int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); @@ -128,10 +129,8 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length); -struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, - struct nvdimm_bus_descriptor *nfit_desc, struct module *module); -#define nvdimm_bus_register(parent, desc) \ - __nvdimm_bus_register(parent, desc, THIS_MODULE) +struct nvdimm_bus *nvdimm_bus_register(struct device *parent, + struct nvdimm_bus_descriptor *nfit_desc); void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus); struct nvdimm_bus *to_nvdimm_bus(struct device *dev); struct nvdimm *to_nvdimm(struct device *dev); -- cgit v1.2.3 From 5f652bb2eb3eb38f97194ce5c41da1fa12e914b8 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 20 Jul 2016 18:11:31 +0200 Subject: gro_cells: gro_cells_receive now return error code so that the caller can update stats accordingly, if needed Signed-off-by: Paolo Abeni Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/gro_cells.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h index cf6c74550baa..d15214d673b2 100644 --- a/include/net/gro_cells.h +++ b/include/net/gro_cells.h @@ -14,27 +14,26 @@ struct gro_cells { struct gro_cell __percpu *cells; }; -static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) +static inline int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct gro_cell *cell; struct net_device *dev = skb->dev; - if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) { - netif_rx(skb); - return; - } + if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) + return netif_rx(skb); cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return; + return NET_RX_DROP; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); + return NET_RX_SUCCESS; } /* called under BH context */ -- cgit v1.2.3 From 1ab0a1192dc8b02162c7ce03d332ef8e599e5f4e Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 19 Jul 2016 13:15:49 +0200 Subject: i2c: i2c-smbus: drop useless stubs Drivers which use the SMBus extensions select I2C_SMBUS, so the stubs are not needed. Signed-off-by: Jean Delvare Reviewed-by: Benjamin Tissoires Signed-off-by: Wolfram Sang --- include/linux/i2c-smbus.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 4ac95bbe53ef..c2e3324f9468 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -73,23 +73,8 @@ struct smbus_host_notify { u8 addr; }; -#if IS_ENABLED(CONFIG_I2C_SMBUS) struct smbus_host_notify *i2c_setup_smbus_host_notify(struct i2c_adapter *adap); int i2c_handle_smbus_host_notify(struct smbus_host_notify *host_notify, unsigned short addr, unsigned int data); -#else -static inline struct smbus_host_notify * -i2c_setup_smbus_host_notify(struct i2c_adapter *adap) -{ - return NULL; -} - -static inline int -i2c_handle_smbus_host_notify(struct smbus_host_notify *host_notify, - unsigned short addr, unsigned int data) -{ - return 0; -} -#endif /* I2C_SMBUS */ #endif /* _LINUX_I2C_SMBUS_H */ -- cgit v1.2.3 From 23014011ba4209a086931ff402eac1c41abbe456 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 21 Jul 2016 12:51:16 +0200 Subject: netfilter: conntrack: support a fixed size of 128 distinct labels The conntrack label extension is currently variable-sized, e.g. if only 2 labels are used by iptables rules then the labels->bits[] array will only contain one element. We track size of each label storage area in the 'words' member. But in nftables and openvswitch we always have to ask for worst-case since we don't know what bit will be used at configuration time. As most arches are 64bit we need to allocate 24 bytes in this case: struct nf_conn_labels { u8 words; /* 0 1 */ /* XXX 7 bytes hole, try to pack */ long unsigned bits[2]; /* 8 24 */ Make bits a fixed size and drop the words member, it simplifies the code and only increases memory requirements on x86 when less than 64bit labels are required. We still only allocate the extension if its needed. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_labels.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index c5f8fc736b3d..0fd4989de836 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -10,8 +10,7 @@ #define NF_CT_LABELS_MAX_SIZE ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) struct nf_conn_labels { - u8 words; - unsigned long bits[]; + unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) @@ -26,20 +25,13 @@ static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS - struct nf_conn_labels *cl_ext; struct net *net = nf_ct_net(ct); - u8 words; - words = ACCESS_ONCE(net->ct.label_words); - if (words == 0) + if (net->ct.labels_used == 0) return NULL; - cl_ext = nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, - words * sizeof(long), GFP_ATOMIC); - if (cl_ext != NULL) - cl_ext->words = words; - - return cl_ext; + return nf_ct_ext_add_length(ct, NF_CT_EXT_LABELS, + sizeof(struct nf_conn_labels), GFP_ATOMIC); #else return NULL; #endif -- cgit v1.2.3 From 857ed310c013fe0d0059f955048dab589fa7a57a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 21 Jul 2016 12:51:17 +0200 Subject: netfilter: connlabels: move set helper to xt_connlabel xt_connlabel is the only user so move it. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_labels.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 0fd4989de836..498814626e28 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -37,8 +37,6 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) #endif } -int nf_connlabel_set(struct nf_conn *ct, u16 bit); - int nf_connlabels_replace(struct nf_conn *ct, const u32 *data, const u32 *mask, unsigned int words); -- cgit v1.2.3 From 76a10b86785c5e3fc49bcee355502d035b07e47a Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:37 +0000 Subject: KVM: api: Pass the devid in the msi routing entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On ARM, the MSI msg (address and data) comes along with out-of-band device ID information. The device ID encodes the device that writes the MSI msg. Let's convey the device id in kvm_irq_routing_msi and use KVM_MSI_VALID_DEVID flag value in kvm_irq_routing_entry to indicate the msi devid is populated. Signed-off-by: Eric Auger Reviewed-by: Andre Przywara Acked-by: Radim Krčmář Signed-off-by: Marc Zyngier --- include/uapi/linux/kvm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d8c4c324cfae..eb2220895c6e 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -879,7 +879,10 @@ struct kvm_irq_routing_msi { __u32 address_lo; __u32 address_hi; __u32 data; - __u32 pad; + union { + __u32 pad; + __u32 devid; + }; }; struct kvm_irq_routing_s390_adapter { -- cgit v1.2.3 From 0455e72c9ae9b7e9589f2cc5ba5bc7804be83342 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:38 +0000 Subject: KVM: Add devid in kvm_kernel_irq_routing_entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enhance kvm_kernel_irq_routing_entry to transport the device id field, devid. A new flags field makes possible to indicate the devid is valid. Those additions are used for ARM GICv3 ITS MSI injection. The original struct msi_msg msi field is replaced by a new custom structure that embeds the new fields. Signed-off-by: Eric Auger Suggested-by: Radim Krčmář Acked-by: Radim Krčmář Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 614a98137c5f..a15828fe845c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -317,7 +317,13 @@ struct kvm_kernel_irq_routing_entry { unsigned irqchip; unsigned pin; } irqchip; - struct msi_msg msi; + struct { + u32 address_lo; + u32 address_hi; + u32 data; + u32 flags; + u32 devid; + } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; }; -- cgit v1.2.3 From d9565a7399d665fa7313122504778cb3d5ef3e19 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:40 +0000 Subject: KVM: Move kvm_setup_default/empty_irq_routing declaration in arch specific header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm_setup_default_irq_routing and kvm_setup_empty_irq_routing are not used by generic code. So let's move the declarations in x86 irq.h header instead of kvm_host.h. Signed-off-by: Eric Auger Suggested-by: Andre Przywara Acked-by: Radim Krčmář Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a15828fe845c..a7eb5c48251e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1052,8 +1052,6 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #define KVM_MAX_IRQ_ROUTES 1024 #endif -int kvm_setup_default_irq_routing(struct kvm *kvm); -int kvm_setup_empty_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, -- cgit v1.2.3 From 180ae7b1182344ca617d8b5200306b02a6b5075d Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:41 +0000 Subject: KVM: arm/arm64: Enable irqchip routing This patch adds compilation and link against irqchip. Main motivation behind using irqchip code is to enable MSI routing code. In the future irqchip routing may also be useful when targeting multiple irqchips. Routing standard callbacks now are implemented in vgic-irqfd: - kvm_set_routing_entry - kvm_set_irq - kvm_set_msi They only are supported with new_vgic code. Both HAVE_KVM_IRQCHIP and HAVE_KVM_IRQ_ROUTING are defined. KVM_CAP_IRQ_ROUTING is advertised and KVM_SET_GSI_ROUTING is allowed. So from now on IRQCHIP routing is enabled and a routing table entry must exist for irqfd injection to succeed for a given SPI. This patch builds a default flat irqchip routing table (gsi=irqchip.pin) covering all the VGIC SPI indexes. This routing table is overwritten by the first first user-space call to KVM_SET_GSI_ROUTING ioctl. MSI routing setup is not yet allowed. Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier --- include/kvm/arm_vgic.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 540da5149ba7..19b698ef3336 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -34,6 +34,7 @@ #define VGIC_MAX_SPI 1019 #define VGIC_MAX_RESERVED 1023 #define VGIC_MIN_LPI 8192 +#define KVM_IRQCHIP_NUM_PINS (1020 - 32) enum vgic_type { VGIC_V2, /* Good ol' GICv2 */ @@ -314,4 +315,10 @@ static inline int kvm_vgic_get_max_vcpus(void) int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); +/** + * kvm_vgic_setup_default_irq_routing: + * Setup a default flat gsi routing table mapping all SPIs + */ +int kvm_vgic_setup_default_irq_routing(struct kvm *kvm); + #endif /* __KVM_ARM_VGIC_H */ -- cgit v1.2.3 From 995a0ee9809b6948bb7bfea77f129fe1d5157cc1 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:42 +0000 Subject: KVM: arm/arm64: Enable MSI routing Up to now, only irqchip routing entries could be set. This patch adds the capability to insert MSI routing entries. For ARM64, let's also increase KVM_MAX_IRQ_ROUTES to 4096: this include SPI irqchip routes plus MSI routes. In the future this might be extended. Signed-off-by: Eric Auger Reviewed-by: Andre Przywara Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a7eb5c48251e..a318c3b21608 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1048,6 +1048,8 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #ifdef CONFIG_S390 #define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that... +#elif defined(CONFIG_ARM64) +#define KVM_MAX_IRQ_ROUTES 4096 #else #define KVM_MAX_IRQ_ROUTES 1024 #endif -- cgit v1.2.3 From bdab88e006504cd83fac98705814485cbe3ef5b4 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 18 Jul 2016 16:07:28 +0200 Subject: powerpc/numa: Convert to hotplug state machine Install the callbacks via the state machine. On the boot cpu the callback is invoked manually because cpuhp is not up yet and everything must be preinitialized before additional CPUs are up. Signed-off-by: Sebastian Andrzej Siewior Cc: Nikunj A Dadhania Cc: Peter Zijlstra Cc: Benjamin Herrenschmidt Cc: Bharata B Rao Cc: Raghavendra K T Cc: Linus Torvalds Cc: Christophe Jaillet Cc: Anton Blanchard Cc: Michael Ellerman Cc: Paul Mackerras Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Cc: rt@linutronix.de Link: http://lkml.kernel.org/r/20160718140727.GA13132@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 09ef54bcba39..5015f463d314 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -15,6 +15,7 @@ enum cpuhp_state { CPUHP_X86_HPET_DEAD, CPUHP_X86_APB_DEAD, CPUHP_WORKQUEUE_PREP, + CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, -- cgit v1.2.3 From cd894f149732a06ba4b2ccdc4cb86edf7ff68620 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 20 Jul 2016 17:24:55 +0200 Subject: leds/trigger/cpu: Move from CPU_STARTING to ONLINE level There is no need the ledtriger to be called *that* early in the hotplug process (+ with disabled interrupts). As explained by Jacek Anaszewski [0] there is no need for it. Therefore this patch moves it to the ONLINE/PREPARE_DOWN level using the dynamic registration for the id. [0] https://lkml.kernel.org/r/578C92BC.2070603@samsung.com Signed-off-by: Sebastian Andrzej Siewior Acked-by: Jacek Anaszewski Acked-by: Linus Walleij Cc: Peter Zijlstra Cc: Paul Gortmaker Cc: Richard Purdie Cc: rt@linutronix.de Cc: Linus Torvalds Cc: linux-leds@vger.kernel.org Link: http://lkml.kernel.org/r/1469028295-14702-1-git-send-email-bigeasy@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/cpuhotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 5015f463d314..6d405db6fb12 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -66,7 +66,6 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM_CORESIGHT4_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, - CPUHP_AP_LEDTRIG_STARTING, CPUHP_AP_SMPCFD_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_NOTIFY_STARTING, -- cgit v1.2.3 From 5b8700e9f909d8fb2802d7ea2626460d3a233256 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 20 Jul 2016 09:22:38 -0300 Subject: [media] doc-rst: Fix some Sphinx warnings Fix all remaining media warnings with ReST that are fixable without changing at the Sphinx code. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 83877719bef4..3d885d97d149 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -180,8 +180,10 @@ struct media_pad { * view. The media_entity_pipeline_start() function * validates all links by calling this operation. Optional. * - * .. note:: Those these callbacks are called with struct media_device.@graph_mutex - * mutex held. + * .. note:: + * + * Those these callbacks are called with struct media_device.@graph_mutex + * mutex held. */ struct media_entity_operations { int (*link_setup)(struct media_entity *entity, -- cgit v1.2.3 From f58cad224796600f91a1faebec9f868985869851 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 20 Jul 2016 11:15:31 -0300 Subject: [media] media-entry.h: Fix a note markup The Sphinx note markup for media_remove_intf_links() is wrong: there's a missing space. While here, let's auto-numerate the two notes. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 3d885d97d149..17390cc7b538 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -968,12 +968,12 @@ void __media_remove_intf_links(struct media_interface *intf); * * @intf: pointer to &media_interface * - * ..note:: + * .. note:: * - * - This is called automatically when an entity is unregistered via - * media_device_register_entity() and by media_devnode_remove(). + * #) This is called automatically when an entity is unregistered via + * media_device_register_entity() and by media_devnode_remove(). * - * - Prefer to use this one, instead of __media_remove_intf_links(). + * #) Prefer to use this one, instead of __media_remove_intf_links(). */ void media_remove_intf_links(struct media_interface *intf); -- cgit v1.2.3 From 575f93084db35ced739a3df9ad398e46704c32c9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 20 Jul 2016 13:05:05 -0300 Subject: [media] v4l2-device.h: document functions The functions at v4l2-device.h are not using the proper markups. Add it, and include at the v4l2-core.rst. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-device.h | 198 ++++++++++++++++++++++++++++++++------------ 1 file changed, 143 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h index d5d45a8d3998..a9d6aa41790e 100644 --- a/include/media/v4l2-device.h +++ b/include/media/v4l2-device.h @@ -25,100 +25,188 @@ #include #include -/* Each instance of a V4L2 device should create the v4l2_device struct, - either stand-alone or embedded in a larger struct. - - It allows easy access to sub-devices (see v4l2-subdev.h) and provides - basic V4L2 device-level support. - */ - #define V4L2_DEVICE_NAME_SIZE (20 + 16) struct v4l2_ctrl_handler; +/** + * struct v4l2_device - main struct to for V4L2 device drivers + * + * @dev: pointer to struct device. + * @mdev: pointer to struct media_device + * @subdevs: used to keep track of the registered subdevs + * @lock: lock this struct; can be used by the driver as well + * if this struct is embedded into a larger struct. + * @name: unique device name, by default the driver name + bus ID + * @notify: notify callback called by some sub-devices. + * @ctrl_handler: The control handler. May be NULL. + * @prio: Device's priority state + * @ref: Keep track of the references to this struct. + * @release: Release function that is called when the ref count + * goes to 0. + * + * Each instance of a V4L2 device should create the v4l2_device struct, + * either stand-alone or embedded in a larger struct. + * + * It allows easy access to sub-devices (see v4l2-subdev.h) and provides + * basic V4L2 device-level support. + * + * .. note:: + * + * #) dev->driver_data points to this struct. + * #) dev might be NULL if there is no parent device + */ + struct v4l2_device { - /* dev->driver_data points to this struct. - Note: dev might be NULL if there is no parent device - as is the case with e.g. ISA devices. */ struct device *dev; #if defined(CONFIG_MEDIA_CONTROLLER) struct media_device *mdev; #endif - /* used to keep track of the registered subdevs */ struct list_head subdevs; - /* lock this struct; can be used by the driver as well if this - struct is embedded into a larger struct. */ spinlock_t lock; - /* unique device name, by default the driver name + bus ID */ char name[V4L2_DEVICE_NAME_SIZE]; - /* notify callback called by some sub-devices. */ void (*notify)(struct v4l2_subdev *sd, unsigned int notification, void *arg); - /* The control handler. May be NULL. */ struct v4l2_ctrl_handler *ctrl_handler; - /* Device's priority state */ struct v4l2_prio_state prio; - /* Keep track of the references to this struct. */ struct kref ref; - /* Release function that is called when the ref count goes to 0. */ void (*release)(struct v4l2_device *v4l2_dev); }; +/** + * v4l2_device_get - gets a V4L2 device reference + * + * @v4l2_dev: pointer to struct v4l2_device + * + * This is an ancillary routine meant to increment the usage for the + * struct v4l2_device pointed by @v4l2_dev. + */ static inline void v4l2_device_get(struct v4l2_device *v4l2_dev) { kref_get(&v4l2_dev->ref); } +/** + * v4l2_device_put - putss a V4L2 device reference + * + * @v4l2_dev: pointer to struct v4l2_device + * + * This is an ancillary routine meant to decrement the usage for the + * struct v4l2_device pointed by @v4l2_dev. + */ int v4l2_device_put(struct v4l2_device *v4l2_dev); -/* Initialize v4l2_dev and make dev->driver_data point to v4l2_dev. - dev may be NULL in rare cases (ISA devices). In that case you - must fill in the v4l2_dev->name field before calling this function. */ -int __must_check v4l2_device_register(struct device *dev, struct v4l2_device *v4l2_dev); - -/* Optional function to initialize the name field of struct v4l2_device using - the driver name and a driver-global atomic_t instance. - This function will increment the instance counter and returns the instance - value used in the name. - - Example: - - static atomic_t drv_instance = ATOMIC_INIT(0); - - ... - - instance = v4l2_device_set_name(&v4l2_dev, "foo", &drv_instance); - - The first time this is called the name field will be set to foo0 and - this function returns 0. If the name ends with a digit (e.g. cx18), - then the name will be set to cx18-0 since cx180 looks really odd. */ +/** + * v4l2_device_register -Initialize v4l2_dev and make dev->driver_data + * point to v4l2_dev. + * + * @dev: pointer to struct device + * @v4l2_dev: pointer to struct v4l2_device + * + * .. note:: + * dev may be NULL in rare cases (ISA devices). + * In such case the caller must fill in the v4l2_dev->name field + * before calling this function. + */ +int __must_check v4l2_device_register(struct device *dev, + struct v4l2_device *v4l2_dev); + +/** + * v4l2_device_set_name - Optional function to initialize the + * name field of struct v4l2_device + * + * @v4l2_dev: pointer to struct v4l2_device + * @basename: base name for the device name + * @instance: pointer to a static atomic_t var with the instance usage for + * the device driver. + * + * v4l2_device_set_name() initializes the name field of struct v4l2_device + * using the driver name and a driver-global atomic_t instance. + * + * This function will increment the instance counter and returns the + * instance value used in the name. + * + * Example: + * + * static atomic_t drv_instance = ATOMIC_INIT(0); + * + * ... + * + * instance = v4l2_device_set_name(&v4l2_dev, "foo", &drv_instance); + * + * The first time this is called the name field will be set to foo0 and + * this function returns 0. If the name ends with a digit (e.g. cx18), + * then the name will be set to cx18-0 since cx180 would look really odd. + */ int v4l2_device_set_name(struct v4l2_device *v4l2_dev, const char *basename, - atomic_t *instance); - -/* Set v4l2_dev->dev to NULL. Call when the USB parent disconnects. - Since the parent disappears this ensures that v4l2_dev doesn't have an - invalid parent pointer. */ + atomic_t *instance); + +/** + * v4l2_device_disconnect - Change V4L2 device state to disconnected. + * + * @v4l2_dev: pointer to struct v4l2_device + * + * Should be called when the USB parent disconnects. + * Since the parent disappears, this ensures that v4l2_dev doesn't have + * an invalid parent pointer. + * + * .. note:: This function sets v4l2_dev->dev to NULL. + */ void v4l2_device_disconnect(struct v4l2_device *v4l2_dev); -/* Unregister all sub-devices and any other resources related to v4l2_dev. */ +/** + * v4l2_device_unregister - Unregister all sub-devices and any other + * resources related to v4l2_dev. + * + * @v4l2_dev: pointer to struct v4l2_device + */ void v4l2_device_unregister(struct v4l2_device *v4l2_dev); -/* Register a subdev with a v4l2 device. While registered the subdev module - is marked as in-use. An error is returned if the module is no longer - loaded when you attempt to register it. */ +/** + * v4l2_device_register_subdev - Registers a subdev with a v4l2 device. + * + * @v4l2_dev: pointer to struct v4l2_device + * @sd: pointer to struct v4l2_subdev + * + * While registered, the subdev module is marked as in-use. + * + * An error is returned if the module is no longer loaded on any attempts + * to register it. + */ int __must_check v4l2_device_register_subdev(struct v4l2_device *v4l2_dev, - struct v4l2_subdev *sd); -/* Unregister a subdev with a v4l2 device. Can also be called if the subdev - wasn't registered. In that case it will do nothing. */ + struct v4l2_subdev *sd); + +/** + * v4l2_device_unregister_subdev - Unregisters a subdev with a v4l2 device. + * + * @sd: pointer to struct v4l2_subdev + * + * .. note :: + * + * Can also be called if the subdev wasn't registered. In such + * case, it will do nothing. + */ void v4l2_device_unregister_subdev(struct v4l2_subdev *sd); -/* Register device nodes for all subdev of the v4l2 device that are marked with - * the V4L2_SUBDEV_FL_HAS_DEVNODE flag. +/** + * v4l2_device_register_subdev_nodes - Registers device nodes for all subdevs + * of the v4l2 device that are marked with + * the V4L2_SUBDEV_FL_HAS_DEVNODE flag. + * + * @v4l2_dev: pointer to struct v4l2_device */ int __must_check v4l2_device_register_subdev_nodes(struct v4l2_device *v4l2_dev); -/* Send a notification to v4l2_device. */ +/** + * v4l2_subdev_notify - Sends a notification to v4l2_device. + * + * @sd: pointer to struct v4l2_subdev + * @notification: type of notification. Please notice that the notification + * type is driver-specific. + * @arg: arguments for the notification. Those are specific to each + * notification type. + */ static inline void v4l2_subdev_notify(struct v4l2_subdev *sd, unsigned int notification, void *arg) { -- cgit v1.2.3 From 21c29de1d090488f595c56be77c088c2ceed394b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 20 Jul 2016 14:20:26 -0300 Subject: [media] v4l2-subdev.h: Improve documentation This header were poorly documented, and weren't using the kernel-doc format. Document everything but the macros using the right format. While here, also fix the other comments to match the Linux CodingStyle. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-subdev.h | 572 +++++++++++++++++++++++++++++--------------- 1 file changed, 383 insertions(+), 189 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 1f672c0ac7d1..2a2240c99b30 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1,21 +1,17 @@ /* - V4L2 sub-device support header. - - Copyright (C) 2008 Hans Verkuil - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * V4L2 sub-device support header. + * + * Copyright (C) 2008 Hans Verkuil + * + * 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 _V4L2_SUBDEV_H @@ -52,55 +48,64 @@ struct v4l2_subdev_fh; struct tuner_setup; struct v4l2_mbus_frame_desc; -/* decode_vbi_line */ +/** + * struct v4l2_decode_vbi_line - used to decode_vbi_line + * + * @is_second_field: Set to 0 for the first (odd) field; + * set to 1 for the second (even) field. + * @p: Pointer to the sliced VBI data from the decoder. On exit, points to + * the start of the payload. + * @line: Line number of the sliced VBI data (1-23) + * @type: VBI service type (V4L2_SLICED_*). 0 if no service found + */ struct v4l2_decode_vbi_line { - u32 is_second_field; /* Set to 0 for the first (odd) field, - set to 1 for the second (even) field. */ - u8 *p; /* Pointer to the sliced VBI data from the decoder. - On exit points to the start of the payload. */ - u32 line; /* Line number of the sliced VBI data (1-23) */ - u32 type; /* VBI service type (V4L2_SLICED_*). 0 if no service found */ + u32 is_second_field; + u8 *p; + u32 line; + u32 type; }; -/* Sub-devices are devices that are connected somehow to the main bridge - device. These devices are usually audio/video muxers/encoders/decoders or - sensors and webcam controllers. - - Usually these devices are controlled through an i2c bus, but other busses - may also be used. - - The v4l2_subdev struct provides a way of accessing these devices in a - generic manner. Most operations that these sub-devices support fall in - a few categories: core ops, audio ops, video ops and tuner ops. - - More categories can be added if needed, although this should remain a - limited set (no more than approx. 8 categories). - - Each category has its own set of ops that subdev drivers can implement. - - A subdev driver can leave the pointer to the category ops NULL if - it does not implement them (e.g. an audio subdev will generally not - implement the video category ops). The exception is the core category: - this must always be present. - - These ops are all used internally so it is no problem to change, remove - or add ops or move ops from one to another category. Currently these - ops are based on the original ioctls, but since ops are not limited to - one argument there is room for improvement here once all i2c subdev - drivers are converted to use these ops. +/* + * Sub-devices are devices that are connected somehow to the main bridge + * device. These devices are usually audio/video muxers/encoders/decoders or + * sensors and webcam controllers. + * + * Usually these devices are controlled through an i2c bus, but other busses + * may also be used. + * + * The v4l2_subdev struct provides a way of accessing these devices in a + * generic manner. Most operations that these sub-devices support fall in + * a few categories: core ops, audio ops, video ops and tuner ops. + * + * More categories can be added if needed, although this should remain a + * limited set (no more than approx. 8 categories). + * + * Each category has its own set of ops that subdev drivers can implement. + * + * A subdev driver can leave the pointer to the category ops NULL if + * it does not implement them (e.g. an audio subdev will generally not + * implement the video category ops). The exception is the core category: + * this must always be present. + * + * These ops are all used internally so it is no problem to change, remove + * or add ops or move ops from one to another category. Currently these + * ops are based on the original ioctls, but since ops are not limited to + * one argument there is room for improvement here once all i2c subdev + * drivers are converted to use these ops. */ -/* Core ops: it is highly recommended to implement at least these ops: - - log_status - g_register - s_register - - This provides basic debugging support. - - The ioctl ops is meant for generic ioctl-like commands. Depending on - the use-case it might be better to use subdev-specific ops (currently - not yet implemented) since ops provide proper type-checking. +/* + * Core ops: it is highly recommended to implement at least these ops: + * + * log_status + * g_register + * s_register + * + * This provides basic debugging support. + * + * The ioctl ops is meant for generic ioctl-like commands. Depending on + * the use-case it might be better to use subdev-specific ops (currently + * not yet implemented) since ops provide proper type-checking. */ /* Subdevice external IO pin configuration */ @@ -110,18 +115,32 @@ struct v4l2_decode_vbi_line { #define V4L2_SUBDEV_IO_PIN_SET_VALUE (1 << 3) /* Set output value */ #define V4L2_SUBDEV_IO_PIN_ACTIVE_LOW (1 << 4) /* ACTIVE HIGH assumed */ +/** + * struct v4l2_subdev_io_pin_config - Subdevice external IO pin configuration + * + * @flags: bitmask with flags for this pin's config: + * %V4L2_SUBDEV_IO_PIN_DISABLE - disables a pin config, + * %V4L2_SUBDEV_IO_PIN_OUTPUT - if pin is an output, + * %V4L2_SUBDEV_IO_PIN_INPUT - if pin is an input, + * %V4L2_SUBDEV_IO_PIN_SET_VALUE - to set the output value via @value + * and %V4L2_SUBDEV_IO_PIN_ACTIVE_LOW - if active is 0. + * @pin: Chip external IO pin to configure + * @function: Internal signal pad/function to route to IO pin + * @value: Initial value for pin - e.g. GPIO output value + * @strength: Pin drive strength + */ struct v4l2_subdev_io_pin_config { - u32 flags; /* V4L2_SUBDEV_IO_PIN_* flags for this pin's config */ - u8 pin; /* Chip external IO pin to configure */ - u8 function; /* Internal signal pad/function to route to IO pin */ - u8 value; /* Initial value for pin - e.g. GPIO output value */ - u8 strength; /* Pin drive strength */ + u32 flags; + u8 pin; + u8 function; + u8 value; + u8 strength; }; /** * struct v4l2_subdev_core_ops - Define core ops callbacks for subdevs * - * @log_status: callback for VIDIOC_LOG_STATUS ioctl handler code. + * @log_status: callback for %VIDIOC_LOG_STATUS ioctl handler code. * * @s_io_pin_config: configure one or more chip I/O pins for chips that * multiplex different internal signal pads out to IO pins. This function @@ -149,9 +168,9 @@ struct v4l2_subdev_io_pin_config { * @compat_ioctl32: called when a 32 bits application uses a 64 bits Kernel, * in order to fix data passed from/to userspace. * - * @g_register: callback for VIDIOC_G_REGISTER ioctl handler code. + * @g_register: callback for %VIDIOC_G_REGISTER ioctl handler code. * - * @s_register: callback for VIDIOC_G_REGISTER ioctl handler code. + * @s_register: callback for %VIDIOC_G_REGISTER ioctl handler code. * * @s_power: puts subdevice in power saving mode (on == 0) or normal operation * mode (on == 1). @@ -159,7 +178,7 @@ struct v4l2_subdev_io_pin_config { * @interrupt_service_routine: Called by the bridge chip's interrupt service * handler, when an interrupt status has be raised due to this subdev, * so that this subdev can handle the details. It may schedule work to be - * performed later. It must not sleep. *Called from an IRQ context*. + * performed later. It must not sleep. **Called from an IRQ context**. * * @subscribe_event: used by the drivers to request the control framework that * for it to be warned when the value of a control changes. @@ -198,25 +217,25 @@ struct v4l2_subdev_core_ops { /** * struct s_radio - Callbacks used when v4l device was opened in radio mode. * - * @s_radio: callback for VIDIOC_S_RADIO ioctl handler code. + * @s_radio: callback for %VIDIOC_S_RADIO ioctl handler code. * - * @s_frequency: callback for VIDIOC_S_FREQUENCY ioctl handler code. + * @s_frequency: callback for %VIDIOC_S_FREQUENCY ioctl handler code. * - * @g_frequency: callback for VIDIOC_G_FREQUENCY ioctl handler code. - * freq->type must be filled in. Normally done by video_ioctl2 + * @g_frequency: callback for %VIDIOC_G_FREQUENCY ioctl handler code. + * freq->type must be filled in. Normally done by video_ioctl2() * or the bridge driver. * - * @enum_freq_bands: callback for VIDIOC_ENUM_FREQ_BANDS ioctl handler code. + * @enum_freq_bands: callback for %VIDIOC_ENUM_FREQ_BANDS ioctl handler code. * - * @g_tuner: callback for VIDIOC_G_TUNER ioctl handler code. + * @g_tuner: callback for %VIDIOC_G_TUNER ioctl handler code. * - * @s_tuner: callback for VIDIOC_S_TUNER ioctl handler code. vt->type must be + * @s_tuner: callback for %VIDIOC_S_TUNER ioctl handler code. &vt->type must be * filled in. Normally done by video_ioctl2 or the * bridge driver. * - * @g_modulator: callback for VIDIOC_G_MODULATOR ioctl handler code. + * @g_modulator: callback for %VIDIOC_G_MODULATOR ioctl handler code. * - * @s_modulator: callback for VIDIOC_S_MODULATOR ioctl handler code. + * @s_modulator: callback for %VIDIOC_S_MODULATOR ioctl handler code. * * @s_type_addr: sets tuner type and its I2C addr. * @@ -247,7 +266,7 @@ struct v4l2_subdev_tuner_ops { * @s_i2s_clock_freq: sets I2S speed in bps. This is used to provide a standard * way to select I2S clock used by driving digital audio streams at some * board designs. Usual values for the frequency are 1024000 and 2048000. - * If the frequency is not supported, then -EINVAL is returned. + * If the frequency is not supported, then %-EINVAL is returned. * * @s_routing: used to define the input and/or output pins of an audio chip, * and any additional configuration data. @@ -279,7 +298,8 @@ struct v4l2_subdev_audio_ops { /** * struct v4l2_mbus_frame_desc_entry - media bus frame description structure * - * @flags: V4L2_MBUS_FRAME_DESC_FL_* flags + * @flags: bitmask flags: %V4L2_MBUS_FRAME_DESC_FL_LEN_MAX and + * %V4L2_MBUS_FRAME_DESC_FL_BLOB. * @pixelcode: media bus pixel code, valid if FRAME_DESC_FL_BLOB is not set * @length: number of octets per frame, valid if V4L2_MBUS_FRAME_DESC_FL_BLOB * is set @@ -304,7 +324,7 @@ struct v4l2_mbus_frame_desc { /** * struct v4l2_subdev_video_ops - Callbacks used when v4l device was opened - * in video mode. + * in video mode. * * @s_routing: see s_routing in audio_ops, except this version is for video * devices. @@ -314,9 +334,9 @@ struct v4l2_mbus_frame_desc { * regarding clock frequency dividers, etc. If not used, then set flags * to 0. If the frequency is not supported, then -EINVAL is returned. * - * @g_std: callback for VIDIOC_G_STD ioctl handler code. + * @g_std: callback for %VIDIOC_G_STD ioctl handler code. * - * @s_std: callback for VIDIOC_S_STD ioctl handler code. + * @s_std: callback for %VIDIOC_S_STD ioctl handler code. * * @s_std_output: set v4l2_std_id for video OUTPUT devices. This is ignored by * video input devices. @@ -324,33 +344,33 @@ struct v4l2_mbus_frame_desc { * @g_std_output: get current standard for video OUTPUT devices. This is ignored * by video input devices. * - * @querystd: callback for VIDIOC_QUERYSTD ioctl handler code. + * @querystd: callback for %VIDIOC_QUERYSTD ioctl handler code. * - * @g_tvnorms: get v4l2_std_id with all standards supported by the video + * @g_tvnorms: get &v4l2_std_id with all standards supported by the video * CAPTURE device. This is ignored by video output devices. * * @g_tvnorms_output: get v4l2_std_id with all standards supported by the video * OUTPUT device. This is ignored by video capture devices. * - * @g_input_status: get input status. Same as the status field in the v4l2_input - * struct. + * @g_input_status: get input status. Same as the status field in the + * &struct &v4l2_input * * @s_stream: used to notify the driver that a video stream will start or has * stopped. * - * @cropcap: callback for VIDIOC_CROPCAP ioctl handler code. + * @cropcap: callback for %VIDIOC_CROPCAP ioctl handler code. * - * @g_crop: callback for VIDIOC_G_CROP ioctl handler code. + * @g_crop: callback for %VIDIOC_G_CROP ioctl handler code. * - * @s_crop: callback for VIDIOC_S_CROP ioctl handler code. + * @s_crop: callback for %VIDIOC_S_CROP ioctl handler code. * - * @g_parm: callback for VIDIOC_G_PARM ioctl handler code. + * @g_parm: callback for %VIDIOC_G_PARM ioctl handler code. * - * @s_parm: callback for VIDIOC_S_PARM ioctl handler code. + * @s_parm: callback for %VIDIOC_S_PARM ioctl handler code. * - * @g_frame_interval: callback for VIDIOC_G_FRAMEINTERVAL ioctl handler code. + * @g_frame_interval: callback for %VIDIOC_G_FRAMEINTERVAL ioctl handler code. * - * @s_frame_interval: callback for VIDIOC_S_FRAMEINTERVAL ioctl handler code. + * @s_frame_interval: callback for %VIDIOC_S_FRAMEINTERVAL ioctl handler code. * * @s_dv_timings: Set custom dv timings in the sub device. This is used * when sub device is capable of setting detailed timing information @@ -358,7 +378,7 @@ struct v4l2_mbus_frame_desc { * * @g_dv_timings: Get custom dv timings in the sub device. * - * @query_dv_timings: callback for VIDIOC_QUERY_DV_TIMINGS ioctl handler code. + * @query_dv_timings: callback for %VIDIOC_QUERY_DV_TIMINGS ioctl handler code. * * @g_mbus_config: get supported mediabus configurations * @@ -407,31 +427,31 @@ struct v4l2_subdev_video_ops { /** * struct v4l2_subdev_vbi_ops - Callbacks used when v4l device was opened - * in video mode via the vbi device node. + * in video mode via the vbi device node. * * @decode_vbi_line: video decoders that support sliced VBI need to implement - * this ioctl. Field p of the v4l2_sliced_vbi_line struct is set to the + * this ioctl. Field p of the &struct v4l2_sliced_vbi_line is set to the * start of the VBI data that was generated by the decoder. The driver * then parses the sliced VBI data and sets the other fields in the * struct accordingly. The pointer p is updated to point to the start of * the payload which can be copied verbatim into the data field of the - * v4l2_sliced_vbi_data struct. If no valid VBI data was found, then the + * &struct v4l2_sliced_vbi_data. If no valid VBI data was found, then the * type field is set to 0 on return. * * @s_vbi_data: used to generate VBI signals on a video signal. - * v4l2_sliced_vbi_data is filled with the data packets that should be - * output. Note that if you set the line field to 0, then that VBI signal - * is disabled. If no valid VBI data was found, then the type field is - * set to 0 on return. + * &struct v4l2_sliced_vbi_data is filled with the data packets that + * should be output. Note that if you set the line field to 0, then that + * VBI signal is disabled. If no valid VBI data was found, then the type + * field is set to 0 on return. * * @g_vbi_data: used to obtain the sliced VBI packet from a readback register. * Not all video decoders support this. If no data is available because - * the readback register contains invalid or erroneous data -EIO is + * the readback register contains invalid or erroneous data %-EIO is * returned. Note that you must fill in the 'id' member and the 'field' * member (to determine whether CC data from the first or second field * should be obtained). * - * @g_sliced_vbi_cap: callback for VIDIOC_SLICED_VBI_CAP ioctl handler code. + * @g_sliced_vbi_cap: callback for %VIDIOC_SLICED_VBI_CAP ioctl handler code. * * @s_raw_fmt: setup the video encoder/decoder for raw VBI. * @@ -464,58 +484,99 @@ struct v4l2_subdev_sensor_ops { int (*g_skip_frames)(struct v4l2_subdev *sd, u32 *frames); }; -/* - [rt]x_g_parameters: Get the current operating parameters and state of the - the IR receiver or transmitter. - - [rt]x_s_parameters: Set the current operating parameters and state of the - the IR receiver or transmitter. It is recommended to call - [rt]x_g_parameters first to fill out the current state, and only change - the fields that need to be changed. Upon return, the actual device - operating parameters and state will be returned. Note that hardware - limitations may prevent the actual settings from matching the requested - settings - e.g. an actual carrier setting of 35,904 Hz when 36,000 Hz - was requested. An exception is when the shutdown parameter is true. - The last used operational parameters will be returned, but the actual - state of the hardware be different to minimize power consumption and - processing when shutdown is true. - - rx_read: Reads received codes or pulse width data. - The semantics are similar to a non-blocking read() call. - - tx_write: Writes codes or pulse width data for transmission. - The semantics are similar to a non-blocking write() call. +/** + * enum v4l2_subdev_ir_mode- describes the type of IR supported + * + * @V4L2_SUBDEV_IR_MODE_PULSE_WIDTH: IR uses struct ir_raw_event records */ - enum v4l2_subdev_ir_mode { - V4L2_SUBDEV_IR_MODE_PULSE_WIDTH, /* uses struct ir_raw_event records */ + V4L2_SUBDEV_IR_MODE_PULSE_WIDTH, }; +/** + * struct v4l2_subdev_ir_parameters - Parameters for IR TX or TX + * + * @bytes_per_data_element: bytes per data element of data in read or + * write call. + * @mode: IR mode as defined by &enum v4l2_subdev_ir_mode. + * @enable: device is active if true + * @interrupt_enable: IR interrupts are enabled if true + * @shutdown: if true: set hardware to low/no power, false: normal mode + * + * @modulation: if true, it uses carrier, if false: baseband + * @max_pulse_width: maximum pulse width in ns, valid only for baseband signal + * @carrier_freq: carrier frequency in Hz, valid only for modulated signal + * @duty_cycle: duty cycle percentage, valid only for modulated signal + * @invert_level: invert signal level + * + * @invert_carrier_sense: Send 0/space as a carrier burst. used only in TX. + * + * @noise_filter_min_width: min time of a valid pulse, in ns. Used only for RX. + * @carrier_range_lower: Lower carrier range, in Hz, valid only for modulated + * signal. Used only for RX. + * @carrier_range_upper: Upper carrier range, in Hz, valid only for modulated + * signal. Used only for RX. + * @resolution: The receive resolution, in ns . Used only for RX. + */ struct v4l2_subdev_ir_parameters { - /* Either Rx or Tx */ - unsigned int bytes_per_data_element; /* of data in read or write call */ + unsigned int bytes_per_data_element; enum v4l2_subdev_ir_mode mode; bool enable; bool interrupt_enable; - bool shutdown; /* true: set hardware to low/no power, false: normal */ + bool shutdown; - bool modulation; /* true: uses carrier, false: baseband */ - u32 max_pulse_width; /* ns, valid only for baseband signal */ - unsigned int carrier_freq; /* Hz, valid only for modulated signal*/ - unsigned int duty_cycle; /* percent, valid only for modulated signal*/ - bool invert_level; /* invert signal level */ + bool modulation; + u32 max_pulse_width; + unsigned int carrier_freq; + unsigned int duty_cycle; + bool invert_level; /* Tx only */ - bool invert_carrier_sense; /* Send 0/space as a carrier burst */ + bool invert_carrier_sense; /* Rx only */ - u32 noise_filter_min_width; /* ns, min time of a valid pulse */ - unsigned int carrier_range_lower; /* Hz, valid only for modulated sig */ - unsigned int carrier_range_upper; /* Hz, valid only for modulated sig */ - u32 resolution; /* ns */ + u32 noise_filter_min_width; + unsigned int carrier_range_lower; + unsigned int carrier_range_upper; + u32 resolution; }; +/** + * struct v4l2_subdev_ir_ops - operations for IR subdevices + * + * @rx_read: Reads received codes or pulse width data. + * The semantics are similar to a non-blocking read() call. + * @rx_g_parameters: Get the current operating parameters and state of the + * the IR receiver. + * @rx_s_parameters: Set the current operating parameters and state of the + * the IR receiver. It is recommended to call + * [rt]x_g_parameters first to fill out the current state, and only change + * the fields that need to be changed. Upon return, the actual device + * operating parameters and state will be returned. Note that hardware + * limitations may prevent the actual settings from matching the requested + * settings - e.g. an actual carrier setting of 35,904 Hz when 36,000 Hz + * was requested. An exception is when the shutdown parameter is true. + * The last used operational parameters will be returned, but the actual + * state of the hardware be different to minimize power consumption and + * processing when shutdown is true. + * + * @tx_write: Writes codes or pulse width data for transmission. + * The semantics are similar to a non-blocking write() call. + * @tx_g_parameters: Get the current operating parameters and state of the + * the IR transmitter. + * @tx_s_parameters: Set the current operating parameters and state of the + * the IR transmitter. It is recommended to call + * [rt]x_g_parameters first to fill out the current state, and only change + * the fields that need to be changed. Upon return, the actual device + * operating parameters and state will be returned. Note that hardware + * limitations may prevent the actual settings from matching the requested + * settings - e.g. an actual carrier setting of 35,904 Hz when 36,000 Hz + * was requested. An exception is when the shutdown parameter is true. + * The last used operational parameters will be returned, but the actual + * state of the hardware be different to minimize power consumption and + * processing when shutdown is true. + */ struct v4l2_subdev_ir_ops { /* Receiver */ int (*rx_read)(struct v4l2_subdev *sd, u8 *buf, size_t count, @@ -536,11 +597,16 @@ struct v4l2_subdev_ir_ops { struct v4l2_subdev_ir_parameters *params); }; -/* - * Used for storing subdev pad information. This structure only needs - * to be passed to the pad op if the 'which' field of the main argument - * is set to V4L2_SUBDEV_FORMAT_TRY. For V4L2_SUBDEV_FORMAT_ACTIVE it is - * safe to pass NULL. +/** + * struct v4l2_subdev_pad_config - Used for storing subdev pad information. + * + * @try_fmt: pointer to &struct v4l2_mbus_framefmt + * @try_crop: pointer to &struct v4l2_rect to be used for crop + * @try_compose: pointer to &struct v4l2_rect to be used for compose + * + * This structure only needs to be passed to the pad op if the 'which' field + * of the main argument is set to %V4L2_SUBDEV_FORMAT_TRY. For + * %V4L2_SUBDEV_FORMAT_ACTIVE it is safe to pass %NULL. */ struct v4l2_subdev_pad_config { struct v4l2_mbus_framefmt try_fmt; @@ -552,30 +618,30 @@ struct v4l2_subdev_pad_config { * struct v4l2_subdev_pad_ops - v4l2-subdev pad level operations * * @init_cfg: initialize the pad config to default values - * @enum_mbus_code: callback for VIDIOC_SUBDEV_ENUM_MBUS_CODE ioctl handler + * @enum_mbus_code: callback for %VIDIOC_SUBDEV_ENUM_MBUS_CODE ioctl handler * code. - * @enum_frame_size: callback for VIDIOC_SUBDEV_ENUM_FRAME_SIZE ioctl handler + * @enum_frame_size: callback for %VIDIOC_SUBDEV_ENUM_FRAME_SIZE ioctl handler * code. * - * @enum_frame_interval: callback for VIDIOC_SUBDEV_ENUM_FRAME_INTERVAL ioctl + * @enum_frame_interval: callback for %VIDIOC_SUBDEV_ENUM_FRAME_INTERVAL ioctl * handler code. * - * @get_fmt: callback for VIDIOC_SUBDEV_G_FMT ioctl handler code. + * @get_fmt: callback for %VIDIOC_SUBDEV_G_FMT ioctl handler code. * - * @set_fmt: callback for VIDIOC_SUBDEV_S_FMT ioctl handler code. + * @set_fmt: callback for %VIDIOC_SUBDEV_S_FMT ioctl handler code. * - * @get_selection: callback for VIDIOC_SUBDEV_G_SELECTION ioctl handler code. + * @get_selection: callback for %VIDIOC_SUBDEV_G_SELECTION ioctl handler code. * - * @set_selection: callback for VIDIOC_SUBDEV_S_SELECTION ioctl handler code. + * @set_selection: callback for %VIDIOC_SUBDEV_S_SELECTION ioctl handler code. * - * @get_edid: callback for VIDIOC_SUBDEV_G_EDID ioctl handler code. + * @get_edid: callback for %VIDIOC_SUBDEV_G_EDID ioctl handler code. * - * @set_edid: callback for VIDIOC_SUBDEV_S_EDID ioctl handler code. + * @set_edid: callback for %VIDIOC_SUBDEV_S_EDID ioctl handler code. * - * @dv_timings_cap: callback for VIDIOC_SUBDEV_DV_TIMINGS_CAP ioctl handler + * @dv_timings_cap: callback for %VIDIOC_SUBDEV_DV_TIMINGS_CAP ioctl handler * code. * - * @enum_dv_timings: callback for VIDIOC_SUBDEV_ENUM_DV_TIMINGS ioctl handler + * @enum_dv_timings: callback for %VIDIOC_SUBDEV_ENUM_DV_TIMINGS ioctl handler * code. * * @link_validate: used by the media controller code to check if the links @@ -627,6 +693,18 @@ struct v4l2_subdev_pad_ops { struct v4l2_mbus_frame_desc *fd); }; +/** + * struct v4l2_subdev_ops - Subdev operations + * + * @core: pointer to &struct v4l2_subdev_core_ops. Can be %NULL + * @tuner: pointer to &struct v4l2_subdev_tuner_ops. Can be %NULL + * @audio: pointer to &struct v4l2_subdev_audio_ops. Can be %NULL + * @video: pointer to &struct v4l2_subdev_video_ops. Can be %NULL + * @vbi: pointer to &struct v4l2_subdev_vbi_ops. Can be %NULL + * @ir: pointer to &struct v4l2_subdev_ir_ops. Can be %NULL + * @sensor: pointer to &struct v4l2_subdev_sensor_ops. Can be %NULL + * @pad: pointer to &struct v4l2_subdev_pad_ops. Can be %NULL + */ struct v4l2_subdev_ops { const struct v4l2_subdev_core_ops *core; const struct v4l2_subdev_tuner_ops *tuner; @@ -638,19 +716,22 @@ struct v4l2_subdev_ops { const struct v4l2_subdev_pad_ops *pad; }; -/* - * Internal ops. Never call this from drivers, only the v4l2 framework can call - * these ops. +/** + * struct v4l2_subdev_internal_ops - V4L2 subdev internal ops * - * registered: called when this subdev is registered. When called the v4l2_dev + * @registered: called when this subdev is registered. When called the v4l2_dev * field is set to the correct v4l2_device. * - * unregistered: called when this subdev is unregistered. When called the + * @unregistered: called when this subdev is unregistered. When called the * v4l2_dev field is still set to the correct v4l2_device. * - * open: called when the subdev device node is opened by an application. + * @open: called when the subdev device node is opened by an application. * - * close: called when the subdev device node is closed. + * @close: called when the subdev device node is closed. + * + * .. note:: + * Never call this from drivers, only the v4l2 framework can call + * these ops. */ struct v4l2_subdev_internal_ops { int (*registered)(struct v4l2_subdev *sd); @@ -672,17 +753,60 @@ struct v4l2_subdev_internal_ops { struct regulator_bulk_data; +/** + * struct v4l2_subdev_platform_data - regulators config struct + * + * @regulators: Optional regulators used to power on/off the subdevice + * @num_regulators: Number of regululators + * @host_priv: Per-subdevice data, specific for a certain video host device + */ struct v4l2_subdev_platform_data { - /* Optional regulators uset to power on/off the subdevice */ struct regulator_bulk_data *regulators; int num_regulators; - /* Per-subdevice data, specific for a certain video host device */ void *host_priv; }; -/* Each instance of a subdev driver should create this struct, either - stand-alone or embedded in a larger struct. +/** + * struct v4l2_subdev - describes a V4L2 sub-device + * + * @entity: pointer to &struct media_entity + * @list: List of sub-devices + * @owner: The owner is the same as the driver's &struct device owner. + * @owner_v4l2_dev: true if the &sd->owner matches the owner of &v4l2_dev->dev + * ownner. Initialized by v4l2_device_register_subdev(). + * @flags: subdev flags. Can be: + * %V4L2_SUBDEV_FL_IS_I2C - Set this flag if this subdev is a i2c device; + * %V4L2_SUBDEV_FL_IS_SPI - Set this flag if this subdev is a spi device; + * %V4L2_SUBDEV_FL_HAS_DEVNODE - Set this flag if this subdev needs a + * device node; + * %V4L2_SUBDEV_FL_HAS_EVENTS - Set this flag if this subdev generates + * events. + * + * @v4l2_dev: pointer to &struct v4l2_device + * @ops: pointer to &struct v4l2_subdev_ops + * @internal_ops: pointer to &struct v4l2_subdev_internal_ops. + * Never call these internal ops from within a driver! + * @ctrl_handler: The control handler of this subdev. May be NULL. + * @name: Name of the sub-device. Please notice that the name must be unique. + * @grp_id: can be used to group similar subdevs. Value is driver-specific + * @dev_priv: pointer to private data + * @host_priv: pointer to private data used by the device where the subdev + * is attached. + * @devnode: subdev device node + * @dev: pointer to the physical device, if any + * @of_node: The device_node of the subdev, usually the same as dev->of_node. + * @async_list: Links this subdev to a global subdev_list or @notifier->done + * list. + * @asd: Pointer to respective &struct v4l2_async_subdev. + * @notifier: Pointer to the managing notifier. + * @pdata: common part of subdevice platform data + * + * Each instance of a subdev driver should create this struct, either + * stand-alone or embedded in a larger struct. + * + * This structure should be initialized by v4l2_subdev_init() or one of + * its variants: v4l2_spi_subdev_init(), v4l2_i2c_subdev_init(). */ struct v4l2_subdev { #if defined(CONFIG_MEDIA_CONTROLLER) @@ -694,30 +818,18 @@ struct v4l2_subdev { u32 flags; struct v4l2_device *v4l2_dev; const struct v4l2_subdev_ops *ops; - /* Never call these internal ops from within a driver! */ const struct v4l2_subdev_internal_ops *internal_ops; - /* The control handler of this subdev. May be NULL. */ struct v4l2_ctrl_handler *ctrl_handler; - /* name must be unique */ char name[V4L2_SUBDEV_NAME_SIZE]; - /* can be used to group similar subdevs, value is driver-specific */ u32 grp_id; - /* pointer to private data */ void *dev_priv; void *host_priv; - /* subdev device node */ struct video_device *devnode; - /* pointer to the physical device, if any */ struct device *dev; - /* The device_node of the subdev, usually the same as dev->of_node. */ struct device_node *of_node; - /* Links this subdev to a global subdev_list or @notifier->done list. */ struct list_head async_list; - /* Pointer to respective struct v4l2_async_subdev. */ struct v4l2_async_subdev *asd; - /* Pointer to the managing notifier. */ struct v4l2_async_notifier *notifier; - /* common part of subdevice platform data */ struct v4l2_subdev_platform_data *pdata; }; @@ -726,8 +838,11 @@ struct v4l2_subdev { #define vdev_to_v4l2_subdev(vdev) \ ((struct v4l2_subdev *)video_get_drvdata(vdev)) -/* - * Used for storing subdev information per file handle +/** + * struct v4l2_subdev_fh - Used for storing subdev information per file handle + * + * @vfh: pointer to struct v4l2_fh + * @pad: pointer to v4l2_subdev_pad_config */ struct v4l2_subdev_fh { struct v4l2_fh vfh; @@ -757,53 +872,132 @@ __V4L2_SUBDEV_MK_GET_TRY(v4l2_rect, v4l2_subdev_get_try_compose, try_compose) extern const struct v4l2_file_operations v4l2_subdev_fops; +/** + * v4l2_set_subdevdata - Sets V4L2 dev private device data + * + * @sd: pointer to &struct v4l2_subdev + * @p: pointer to the private device data to be stored. + */ static inline void v4l2_set_subdevdata(struct v4l2_subdev *sd, void *p) { sd->dev_priv = p; } +/** + * v4l2_get_subdevdata - Gets V4L2 dev private device data + * + * @sd: pointer to &struct v4l2_subdev + * + * Returns the pointer to the private device data to be stored. + */ static inline void *v4l2_get_subdevdata(const struct v4l2_subdev *sd) { return sd->dev_priv; } +/** + * v4l2_set_subdevdata - Sets V4L2 dev private host data + * + * @sd: pointer to &struct v4l2_subdev + * @p: pointer to the private data to be stored. + */ static inline void v4l2_set_subdev_hostdata(struct v4l2_subdev *sd, void *p) { sd->host_priv = p; } +/** + * v4l2_get_subdevdata - Gets V4L2 dev private data + * + * @sd: pointer to &struct v4l2_subdev + * + * Returns the pointer to the private host data to be stored. + */ static inline void *v4l2_get_subdev_hostdata(const struct v4l2_subdev *sd) { return sd->host_priv; } #ifdef CONFIG_MEDIA_CONTROLLER + +/** + * v4l2_subdev_link_validate_default - validates a media link + * + * @sd: pointer to &struct v4l2_subdev + * @link: pointer to &struct media_link + * @source_fmt: pointer to &struct v4l2_subdev_format + * @sink_fmt: pointer to &struct v4l2_subdev_format + * + * This function ensures that width, height and the media bus pixel + * code are equal on both source and sink of the link. + */ int v4l2_subdev_link_validate_default(struct v4l2_subdev *sd, struct media_link *link, struct v4l2_subdev_format *source_fmt, struct v4l2_subdev_format *sink_fmt); + +/** + * v4l2_subdev_link_validate - validates a media link + * + * @link: pointer to &struct media_link + * + * This function calls the subdev's link_validate ops to validate + * if a media link is valid for streaming. It also internally + * calls v4l2_subdev_link_validate_default() to ensure that + * width, height and the media bus pixel code are equal on both + * source and sink of the link. + */ int v4l2_subdev_link_validate(struct media_link *link); -struct v4l2_subdev_pad_config * -v4l2_subdev_alloc_pad_config(struct v4l2_subdev *sd); +/** + * v4l2_subdev_alloc_pad_config - Allocates memory for pad config + * + * @sd: pointer to struct v4l2_subdev + */ +struct +v4l2_subdev_pad_config *v4l2_subdev_alloc_pad_config(struct v4l2_subdev *sd); + +/** + * v4l2_subdev_free_pad_config - Frees memory allocated by + * v4l2_subdev_alloc_pad_config(). + * + * @cfg: pointer to &struct v4l2_subdev_pad_config + */ void v4l2_subdev_free_pad_config(struct v4l2_subdev_pad_config *cfg); #endif /* CONFIG_MEDIA_CONTROLLER */ +/** + * v4l2_subdev_init - initializes the sub-device struct + * + * @sd: pointer to the &struct v4l2_subdev to be initialized + * @ops: pointer to &struct v4l2_subdev_ops. + */ void v4l2_subdev_init(struct v4l2_subdev *sd, const struct v4l2_subdev_ops *ops); -/* Call an ops of a v4l2_subdev, doing the right checks against - NULL pointers. - - Example: err = v4l2_subdev_call(sd, video, s_std, norm); +/* + * Call an ops of a v4l2_subdev, doing the right checks against + * NULL pointers. + * + * Example: err = v4l2_subdev_call(sd, video, s_std, norm); */ #define v4l2_subdev_call(sd, o, f, args...) \ (!(sd) ? -ENODEV : (((sd)->ops->o && (sd)->ops->o->f) ? \ - (sd)->ops->o->f((sd) , ##args) : -ENOIOCTLCMD)) + (sd)->ops->o->f((sd), ##args) : -ENOIOCTLCMD)) #define v4l2_subdev_has_op(sd, o, f) \ ((sd)->ops->o && (sd)->ops->o->f) +/** + * v4l2_subdev_notify_event() - Delivers event notification for subdevice + * @sd: The subdev for which to deliver the event + * @ev: The event to deliver + * + * Will deliver the specified event to all userspace event listeners which are + * subscribed to the v42l subdev event queue as well as to the bridge driver + * using the notify callback. The notification type for the notify callback + * will be %V4L2_DEVICE_NOTIFY_EVENT. + */ void v4l2_subdev_notify_event(struct v4l2_subdev *sd, const struct v4l2_event *ev); -- cgit v1.2.3 From ab4f5a4afc2d7a32285baba8ffab865beba60e13 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Jul 2016 09:24:55 -0300 Subject: [media] v4l2-async: document the remaining stuff There are one enum and 4 functions undocumented there. Document them. That will fix the broken links at the v4l2-subdev.rst file. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-async.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-async.h b/include/media/v4l2-async.h index 1d6d7da4c45d..8e2a236a4d03 100644 --- a/include/media/v4l2-async.h +++ b/include/media/v4l2-async.h @@ -23,6 +23,19 @@ struct v4l2_async_notifier; /* A random max subdevice number, used to allocate an array on stack */ #define V4L2_MAX_SUBDEVS 128U +/** + * enum v4l2_async_match_type - type of asynchronous subdevice logic to be used + * in order to identify a match + * + * @V4L2_ASYNC_MATCH_CUSTOM: Match will use the logic provided by &struct + * v4l2_async_subdev.match ops + * @V4L2_ASYNC_MATCH_DEVNAME: Match will use the device name + * @V4L2_ASYNC_MATCH_I2C: Match will check for I2C adapter ID and address + * @V4L2_ASYNC_MATCH_OF: Match will use OF node + * + * This enum is used by the asyncrhronous sub-device logic to define the + * algorithm that will be used to match an asynchronous device. + */ enum v4l2_async_match_type { V4L2_ASYNC_MATCH_CUSTOM, V4L2_ASYNC_MATCH_DEVNAME, @@ -91,9 +104,35 @@ struct v4l2_async_notifier { struct v4l2_async_subdev *asd); }; +/** + * v4l2_async_notifier_register - registers a subdevice asynchronous notifier + * + * @v4l2_dev: pointer to &struct v4l2_device + * @notifier: pointer to &struct v4l2_async_notifier + */ int v4l2_async_notifier_register(struct v4l2_device *v4l2_dev, struct v4l2_async_notifier *notifier); + +/** + * v4l2_async_notifier_unregister - unregisters a subdevice asynchronous notifier + * + * @notifier: pointer to &struct v4l2_async_notifier + */ void v4l2_async_notifier_unregister(struct v4l2_async_notifier *notifier); + +/** + * v4l2_async_register_subdev - registers a sub-device to the asynchronous + * subdevice framework + * + * @sd: pointer to &struct v4l2_subdev + */ int v4l2_async_register_subdev(struct v4l2_subdev *sd); + +/** + * v4l2_async_unregister_subdev - unregisters a sub-device to the asynchronous + * subdevice framework + * + * @sd: pointer to &struct v4l2_subdev + */ void v4l2_async_unregister_subdev(struct v4l2_subdev *sd); #endif -- cgit v1.2.3 From a39c57f8cd0526d8227468f8e0f88c4be4f97139 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Jul 2016 10:08:31 -0300 Subject: [media] v4l2-common.h: document the subdev functions There are some subdev-specific functions at v4l2-common.h that are mentioned at v4l2-subdev.rst. Document them. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 49 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 1cc0c5ba16b3..9b1dfcd9e229 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -80,8 +80,6 @@ /* ------------------------------------------------------------------------- */ -/* Control helper function */ - int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def); /* ------------------------------------------------------------------------- */ @@ -96,23 +94,60 @@ struct v4l2_device; struct v4l2_subdev; struct v4l2_subdev_ops; - -/* Load an i2c module and return an initialized v4l2_subdev struct. - The client_type argument is the name of the chip that's on the adapter. */ +/** + * v4l2_i2c_new_subdev - Load an i2c module and return an initialized + * &struct v4l2_subdev. + * + * @v4l2_dev: pointer to &struct v4l2_device + * @adapter: pointer to struct i2c_adapter + * @client_type: name of the chip that's on the adapter. + * @addr: I2C address. If zero, it will use @probe_addrs + * @probe_addrs: array with a list of address. The last entry at such + * array should be %I2C_CLIENT_END. + * + * returns a &struct v4l2_subdev pointer. + */ struct v4l2_subdev *v4l2_i2c_new_subdev(struct v4l2_device *v4l2_dev, struct i2c_adapter *adapter, const char *client_type, u8 addr, const unsigned short *probe_addrs); struct i2c_board_info; +/** + * v4l2_i2c_new_subdev_board - Load an i2c module and return an initialized + * &struct v4l2_subdev. + * + * @v4l2_dev: pointer to &struct v4l2_device + * @adapter: pointer to struct i2c_adapter + * @info: pointer to struct i2c_board_info used to replace the irq, + * platform_data and addr arguments. + * @probe_addrs: array with a list of address. The last entry at such + * array should be %I2C_CLIENT_END. + * + * returns a &struct v4l2_subdev pointer. + */ struct v4l2_subdev *v4l2_i2c_new_subdev_board(struct v4l2_device *v4l2_dev, struct i2c_adapter *adapter, struct i2c_board_info *info, const unsigned short *probe_addrs); -/* Initialize a v4l2_subdev with data from an i2c_client struct */ +/** + * v4l2_i2c_subdev_init - Initializes a &struct v4l2_subdev with data from + * an i2c_client struct. + * + * @sd: pointer to &struct v4l2_subdev + * @client: pointer to struct i2c_client + * @ops: pointer to &struct v4l2_subdev_ops + */ void v4l2_i2c_subdev_init(struct v4l2_subdev *sd, struct i2c_client *client, const struct v4l2_subdev_ops *ops); -/* Return i2c client address of v4l2_subdev. */ + +/** + * v4l2_i2c_subdev_addr - returns i2c client address of &struct v4l2_subdev. + * + * @sd: pointer to &struct v4l2_subdev + * + * Returns the address of an I2C sub-device + */ unsigned short v4l2_i2c_subdev_addr(struct v4l2_subdev *sd); enum v4l2_i2c_tuner_type { -- cgit v1.2.3 From b871915893c32473ef5ce0d075c1952ed8232ce1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Jul 2016 12:26:04 -0300 Subject: [media] v4l2-common.h: Add documentation for other functions Not all functions at v4l2-common.h are documented. Add documentation for some other ones. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-common.h | 43 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 9b1dfcd9e229..350cbf9fb10e 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -78,9 +78,26 @@ v4l2_printk(KERN_DEBUG, dev, fmt , ## arg); \ } while (0) -/* ------------------------------------------------------------------------- */ +/** + * v4l2_ctrl_query_fill- Fill in a struct v4l2_queryctrl + * + * @qctrl: pointer to the &struct v4l2_queryctrl to be filled + * @min: minimum value for the control + * @max: maximum value for the control + * @step: control step + * @def: default value for the control + * + * Fills the &struct v4l2_queryctrl fields for the query control. + * + * .. note:: + * + * This function assumes that the @qctrl->id field is filled. + * + * Returns -EINVAL if the control is not known by the V4L2 core, 0 on success. + */ -int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def); +int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, + s32 min, s32 max, s32 step, s32 def); /* ------------------------------------------------------------------------- */ @@ -172,12 +189,28 @@ const unsigned short *v4l2_i2c_tuner_addrs(enum v4l2_i2c_tuner_type type); struct spi_device; -/* Load an spi module and return an initialized v4l2_subdev struct. - The client_type argument is the name of the chip that's on the adapter. */ +/** + * v4l2_spi_new_subdev - Load an spi module and return an initialized + * &struct v4l2_subdev. + * + * + * @v4l2_dev: pointer to &struct v4l2_device. + * @master: pointer to struct spi_master. + * @info: pointer to struct spi_board_info. + * + * returns a &struct v4l2_subdev pointer. + */ struct v4l2_subdev *v4l2_spi_new_subdev(struct v4l2_device *v4l2_dev, struct spi_master *master, struct spi_board_info *info); -/* Initialize a v4l2_subdev with data from an spi_device struct */ +/** + * v4l2_spi_subdev_init - Initialize a v4l2_subdev with data from an + * spi_device struct. + * + * @sd: pointer to &struct v4l2_subdev + * @spi: pointer to struct spi_device. + * @ops: pointer to &struct v4l2_subdev_ops + */ void v4l2_spi_subdev_init(struct v4l2_subdev *sd, struct spi_device *spi, const struct v4l2_subdev_ops *ops); #endif -- cgit v1.2.3 From d9d3d1761abecf72a8044762724fb04b5974a513 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 21 Jul 2016 15:30:20 -0300 Subject: [media] doc-rst: document v4l2-dev.h Add documentation for v4l2-dev.h, and put it at v4l2-framework.rst, where struct video_device is currently documented. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-dev.h | 364 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 315 insertions(+), 49 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 25a3190308fb..5921c24565cf 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -47,19 +47,105 @@ struct v4l2_ctrl_handler; /* Priority helper functions */ +/** + * struct v4l2_prio_state - stores the priority states + * + * @prios: array with elements to store the array priorities + * + * + * .. note:: + * The size of @prios array matches the number of priority types defined + * by :ref:`enum v4l2_priority `. + */ struct v4l2_prio_state { atomic_t prios[4]; }; +/** + * v4l2_prio_init - initializes a struct v4l2_prio_state + * + * @global: pointer to &struct v4l2_prio_state + */ void v4l2_prio_init(struct v4l2_prio_state *global); + +/** + * v4l2_prio_change - changes the v4l2 file handler priority + * + * @global: pointer to the &struct v4l2_prio_state of the device node. + * @local: pointer to the desired priority, as defined by :ref:`enum v4l2_priority ` + * @new: Priority type requested, as defined by :ref:`enum v4l2_priority `. + * + * .. note:: + * This function should be used only by the V4L2 core. + */ int v4l2_prio_change(struct v4l2_prio_state *global, enum v4l2_priority *local, enum v4l2_priority new); + +/** + * v4l2_prio_open - Implements the priority logic for a file handler open + * + * @global: pointer to the &struct v4l2_prio_state of the device node. + * @local: pointer to the desired priority, as defined by :ref:`enum v4l2_priority ` + * + * .. note:: + * This function should be used only by the V4L2 core. + */ void v4l2_prio_open(struct v4l2_prio_state *global, enum v4l2_priority *local); + +/** + * v4l2_prio_close - Implements the priority logic for a file handler close + * + * @global: pointer to the &struct v4l2_prio_state of the device node. + * @local: priority to be released, as defined by :ref:`enum v4l2_priority ` + * + * .. note:: + * This function should be used only by the V4L2 core. + */ void v4l2_prio_close(struct v4l2_prio_state *global, enum v4l2_priority local); + +/** + * v4l2_prio_max - Return the maximum priority, as stored at the @global array. + * + * @global: pointer to the &struct v4l2_prio_state of the device node. + * + * .. note:: + * This function should be used only by the V4L2 core. + */ enum v4l2_priority v4l2_prio_max(struct v4l2_prio_state *global); -int v4l2_prio_check(struct v4l2_prio_state *global, enum v4l2_priority local); +/** + * v4l2_prio_close - Implements the priority logic for a file handler close + * + * @global: pointer to the &struct v4l2_prio_state of the device node. + * @local: desired priority, as defined by :ref:`enum v4l2_priority ` local + * + * .. note:: + * This function should be used only by the V4L2 core. + */ +int v4l2_prio_check(struct v4l2_prio_state *global, enum v4l2_priority local); +/** + * struct v4l2_file_operations - fs operations used by a V4L2 device + * + * @owner: pointer to struct module + * @read: operations needed to implement the read() syscall + * @write: operations needed to implement the write() syscall + * @poll: operations needed to implement the poll() syscall + * @unlocked_ioctl: operations needed to implement the ioctl() syscall + * @compat_ioctl32: operations needed to implement the ioctl() syscall for + * the special case where the Kernel uses 64 bits instructions, but + * the userspace uses 32 bits. + * @get_unmapped_area: called by the mmap() syscall, used when %!CONFIG_MMU + * @mmap: operations needed to implement the mmap() syscall + * @open: operations needed to implement the open() syscall + * @release: operations needed to implement the release() syscall + * + * .. note:: + * + * Those operations are used to implemente the fs struct file_operations + * at the V4L2 drivers. The V4L2 core overrides the fs ops with some + * extra logic needed by the subsystem. + */ struct v4l2_file_operations { struct module *owner; ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); @@ -82,6 +168,47 @@ struct v4l2_file_operations { * the common handler */ +/** + * struct video_device - Structure used to create and manage the V4L2 device + * nodes. + * + * @entity: &struct media_entity + * @intf_devnode: pointer to &struct media_intf_devnode + * @pipe: &struct media_pipeline + * @fops: pointer to &struct v4l2_file_operations for the video device + * @device_caps: device capabilities as used in v4l2_capabilities + * @dev: &struct device for the video device + * @cdev: character device + * @v4l2_dev: pointer to &struct v4l2_device parent + * @dev_parent: pointer to &struct device parent + * @ctrl_handler: Control handler associated with this device node. + * May be NULL. + * @queue: &struct vb2_queue associated with this device node. May be NULL. + * @prio: pointer to &struct v4l2_prio_state with device's Priority state. + * If NULL, then v4l2_dev->prio will be used. + * @name: video device name + * @vfl_type: V4L device type + * @vfl_dir: V4L receiver, transmitter or m2m + * @minor: device node 'minor'. It is set to -1 if the registration failed + * @num: number of the video device node + * @flags: video device flags. Use bitops to set/clear/test flags + * @index: attribute to differentiate multiple indices on one physical device + * @fh_lock: Lock for all v4l2_fhs + * @fh_list: List of &struct v4l2_fh + * @dev_debug: Internal device debug flags, not for use by drivers + * @tvnorms: Supported tv norms + * + * @release: video device release() callback + * @ioctl_ops: pointer to &struct v4l2_ioctl_ops with ioctl callbacks + * + * @valid_ioctls: bitmap with the valid ioctls for this device + * @disable_locking: bitmap with the ioctls that don't require locking + * @lock: pointer to &struct mutex serialization lock + * + * .. note:: + * Only set @dev_parent if that can't be deduced from @v4l2_dev. + */ + struct video_device { #if defined(CONFIG_MEDIA_CONTROLLER) @@ -89,59 +216,45 @@ struct video_device struct media_intf_devnode *intf_devnode; struct media_pipeline pipe; #endif - /* device ops */ const struct v4l2_file_operations *fops; - /* device capabilities as used in v4l2_capabilities */ u32 device_caps; /* sysfs */ - struct device dev; /* v4l device */ - struct cdev *cdev; /* character device */ + struct device dev; + struct cdev *cdev; - struct v4l2_device *v4l2_dev; /* v4l2_device parent */ - /* Only set parent if that can't be deduced from v4l2_dev */ - struct device *dev_parent; /* device parent */ + struct v4l2_device *v4l2_dev; + struct device *dev_parent; - /* Control handler associated with this device node. May be NULL. */ struct v4l2_ctrl_handler *ctrl_handler; - /* vb2_queue associated with this device node. May be NULL. */ struct vb2_queue *queue; - /* Priority state. If NULL, then v4l2_dev->prio will be used. */ struct v4l2_prio_state *prio; /* device info */ char name[32]; - int vfl_type; /* device type */ - int vfl_dir; /* receiver, transmitter or m2m */ - /* 'minor' is set to -1 if the registration failed */ + int vfl_type; + int vfl_dir; int minor; u16 num; - /* use bitops to set/clear/test flags */ unsigned long flags; - /* attribute to differentiate multiple indices on one physical device */ int index; /* V4L2 file handles */ - spinlock_t fh_lock; /* Lock for all v4l2_fhs */ - struct list_head fh_list; /* List of struct v4l2_fh */ + spinlock_t fh_lock; + struct list_head fh_list; - /* Internal device debug flags, not for use by drivers */ int dev_debug; - /* Video standard vars */ - v4l2_std_id tvnorms; /* Supported tv norms */ + v4l2_std_id tvnorms; /* callbacks */ void (*release)(struct video_device *vdev); - - /* ioctl callbacks */ const struct v4l2_ioctl_ops *ioctl_ops; DECLARE_BITMAP(valid_ioctls, BASE_VIDIOC_PRIVATE); - /* serialization lock */ DECLARE_BITMAP(disable_locking, BASE_VIDIOC_PRIVATE); struct mutex *lock; }; @@ -151,88 +264,241 @@ struct video_device /* dev to video-device */ #define to_video_device(cd) container_of(cd, struct video_device, dev) +/** + * __video_register_device - register video4linux devices + * + * @vdev: struct video_device to register + * @type: type of device to register + * @nr: which device node number is desired: + * (0 == /dev/video0, 1 == /dev/video1, ..., -1 == first free) + * @warn_if_nr_in_use: warn if the desired device node number + * was already in use and another number was chosen instead. + * @owner: module that owns the video device node + * + * The registration code assigns minor numbers and device node numbers + * based on the requested type and registers the new device node with + * the kernel. + * + * This function assumes that struct video_device was zeroed when it + * was allocated and does not contain any stale date. + * + * An error is returned if no free minor or device node number could be + * found, or if the registration of the device node failed. + * + * Returns 0 on success. + * + * Valid values for @type are: + * + * - %VFL_TYPE_GRABBER - A frame grabber + * - %VFL_TYPE_VBI - Vertical blank data (undecoded) + * - %VFL_TYPE_RADIO - A radio card + * - %VFL_TYPE_SUBDEV - A subdevice + * - %VFL_TYPE_SDR - Software Defined Radio + * + * .. note:: + * + * This function is meant to be used only inside the V4L2 core. + * Drivers should use video_register_device() or + * video_register_device_no_warn(). + */ int __must_check __video_register_device(struct video_device *vdev, int type, int nr, int warn_if_nr_in_use, struct module *owner); -/* Register video devices. Note that if video_register_device fails, - the release() callback of the video_device structure is *not* called, so - the caller is responsible for freeing any data. Usually that means that - you call video_device_release() on failure. */ +/** + * video_register_device - register video4linux devices + * + * @vdev: struct video_device to register + * @type: type of device to register + * @nr: which device node number is desired: + * (0 == /dev/video0, 1 == /dev/video1, ..., -1 == first free) + * + * Internally, it calls __video_register_device(). Please see its + * documentation for more details. + * + * .. note:: + * if video_register_device fails, the release() callback of + * &struct video_device structure is *not* called, so the caller + * is responsible for freeing any data. Usually that means that + * you video_device_release() should be called on failure. + */ static inline int __must_check video_register_device(struct video_device *vdev, int type, int nr) { return __video_register_device(vdev, type, nr, 1, vdev->fops->owner); } -/* Same as video_register_device, but no warning is issued if the desired - device node number was already in use. */ +/** + * video_register_device_no_warn - register video4linux devices + * + * @vdev: struct video_device to register + * @type: type of device to register + * @nr: which device node number is desired: + * (0 == /dev/video0, 1 == /dev/video1, ..., -1 == first free) + * + * This function is identical to video_register_device() except that no + * warning is issued if the desired device node number was already in use. + * + * Internally, it calls __video_register_device(). Please see its + * documentation for more details. + * + * .. note:: + * if video_register_device fails, the release() callback of + * &struct video_device structure is *not* called, so the caller + * is responsible for freeing any data. Usually that means that + * you video_device_release() should be called on failure. + */ static inline int __must_check video_register_device_no_warn( struct video_device *vdev, int type, int nr) { return __video_register_device(vdev, type, nr, 0, vdev->fops->owner); } -/* Unregister video devices. Will do nothing if vdev == NULL or - video_is_registered() returns false. */ +/** + * video_unregister_device - Unregister video devices. + * + * @vdev: &struct video_device to register + * + * Does nothing if vdev == NULL or if video_is_registered() returns false. + */ void video_unregister_device(struct video_device *vdev); -/* helper functions to alloc/release struct video_device, the - latter can also be used for video_device->release(). */ +/** + * video_device_alloc - helper function to alloc &struct video_device + * + * Returns NULL if %-ENOMEM or a &struct video_device on success. + */ struct video_device * __must_check video_device_alloc(void); -/* this release function frees the vdev pointer */ +/** + * video_device_release - helper function to release &struct video_device + * + * @vdev: pointer to &struct video_device + * + * Can also be used for video_device->release(). + */ void video_device_release(struct video_device *vdev); -/* this release function does nothing, use when the video_device is a - static global struct. Note that having a static video_device is - a dubious construction at best. */ +/** + * video_device_release_empty - helper function to implement the + * video_device->release() callback. + * + * @vdev: pointer to &struct video_device + * + * This release function does nothing. + * + * It should be used when the video_device is a static global struct. + * + * .. note:: + * Having a static video_device is a dubious construction at best. + */ void video_device_release_empty(struct video_device *vdev); -/* returns true if cmd is a known V4L2 ioctl */ +/** + * v4l2_is_known_ioctl - Checks if a given cmd is a known V4L ioctl + * + * @cmd: ioctl command + * + * returns true if cmd is a known V4L2 ioctl + */ bool v4l2_is_known_ioctl(unsigned int cmd); -/* mark that this command shouldn't use core locking */ -static inline void v4l2_disable_ioctl_locking(struct video_device *vdev, unsigned int cmd) +/** v4l2_disable_ioctl_locking - mark that a given command + * shouldn't use core locking + * + * @vdev: pointer to &struct video_device + * @cmd: ioctl command + */ +static inline void v4l2_disable_ioctl_locking(struct video_device *vdev, + unsigned int cmd) { if (_IOC_NR(cmd) < BASE_VIDIOC_PRIVATE) set_bit(_IOC_NR(cmd), vdev->disable_locking); } -/* Mark that this command isn't implemented. This must be called before - video_device_register. See also the comments in determine_valid_ioctls(). - This function allows drivers to provide just one v4l2_ioctl_ops struct, but - disable ioctls based on the specific card that is actually found. */ -static inline void v4l2_disable_ioctl(struct video_device *vdev, unsigned int cmd) +/** + * v4l2_disable_ioctl- mark that a given command isn't implemented. + * shouldn't use core locking + * + * @vdev: pointer to &struct video_device + * @cmd: ioctl command + * + * This function allows drivers to provide just one v4l2_ioctl_ops struct, but + * disable ioctls based on the specific card that is actually found. + * + * .. note:: + * + * This must be called before video_register_device. + * See also the comments for determine_valid_ioctls(). + */ +static inline void v4l2_disable_ioctl(struct video_device *vdev, + unsigned int cmd) { if (_IOC_NR(cmd) < BASE_VIDIOC_PRIVATE) set_bit(_IOC_NR(cmd), vdev->valid_ioctls); } -/* helper functions to access driver private data. */ +/** + * video_get_drvdata - gets private data from &struct video_device. + * + * @vdev: pointer to &struct video_device + * + * returns a pointer to the private data + */ static inline void *video_get_drvdata(struct video_device *vdev) { return dev_get_drvdata(&vdev->dev); } +/** + * video_set_drvdata - sets private data from &struct video_device. + * + * @vdev: pointer to &struct video_device + * @data: private data pointer + */ static inline void video_set_drvdata(struct video_device *vdev, void *data) { dev_set_drvdata(&vdev->dev, data); } +/** + * video_devdata - gets &struct video_device from struct file. + * + * @file: pointer to struct file + */ struct video_device *video_devdata(struct file *file); -/* Combine video_get_drvdata and video_devdata as this is - used very often. */ +/** + * video_drvdata - gets private data from &struct video_device using the + * struct file. + * + * @file: pointer to struct file + * + * This is function combines both video_get_drvdata() and video_devdata() + * as this is used very often. + */ static inline void *video_drvdata(struct file *file) { return video_get_drvdata(video_devdata(file)); } +/** + * video_device_node_name - returns the video device name + * + * @vdev: pointer to &struct video_device + * + * Returns the device name string + */ static inline const char *video_device_node_name(struct video_device *vdev) { return dev_name(&vdev->dev); } +/** + * video_is_registered - returns true if the &struct video_device is registered. + * + * + * @vdev: pointer to &struct video_device + */ static inline int video_is_registered(struct video_device *vdev) { return test_bit(V4L2_FL_REGISTERED, &vdev->flags); -- cgit v1.2.3 From 9d4ee1ad925ffc77fe3b8d6f6a188c54d65af5dc Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 22 Jul 2016 07:27:06 -0300 Subject: [media] v4l2-event.h: document all functions Several functions weren't documented. Document them all. While here, makes checkpatch.pl happy. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-event.h | 125 ++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 113 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-event.h b/include/media/v4l2-event.h index 9792f906423b..ca854203b8b9 100644 --- a/include/media/v4l2-event.h +++ b/include/media/v4l2-event.h @@ -73,14 +73,15 @@ struct video_device; * @list: List node for the v4l2_fh->available list. * @sev: Pointer to parent v4l2_subscribed_event. * @event: The event itself. - */ + */ struct v4l2_kevent { struct list_head list; struct v4l2_subscribed_event *sev; struct v4l2_event event; }; -/** struct v4l2_subscribed_event_ops - Subscribed event operations. +/** + * struct v4l2_subscribed_event_ops - Subscribed event operations. * * @add: Optional callback, called when a new listener is added * @del: Optional callback, called when a listener stops listening @@ -88,20 +89,23 @@ struct v4l2_kevent { * @merge: Optional callback that can merge event 'old' into event 'new'. */ struct v4l2_subscribed_event_ops { - int (*add)(struct v4l2_subscribed_event *sev, unsigned elems); + int (*add)(struct v4l2_subscribed_event *sev, unsigned int elems); void (*del)(struct v4l2_subscribed_event *sev); void (*replace)(struct v4l2_event *old, const struct v4l2_event *new); void (*merge)(const struct v4l2_event *old, struct v4l2_event *new); }; /** - * struct v4l2_subscribed_event - Internal struct representing a subscribed event. + * struct v4l2_subscribed_event - Internal struct representing a subscribed + * event. + * * @list: List node for the v4l2_fh->subscribed list. * @type: Event type. * @id: Associated object ID (e.g. control ID). 0 if there isn't any. * @flags: Copy of v4l2_event_subscription->flags. * @fh: Filehandle that subscribed to this event. - * @node: List node that hooks into the object's event list (if there is one). + * @node: List node that hooks into the object's event list + * (if there is one). * @ops: v4l2_subscribed_event_ops * @elems: The number of elements in the events array. * @first: The index of the events containing the oldest available event. @@ -116,27 +120,124 @@ struct v4l2_subscribed_event { struct v4l2_fh *fh; struct list_head node; const struct v4l2_subscribed_event_ops *ops; - unsigned elems; - unsigned first; - unsigned in_use; + unsigned int elems; + unsigned int first; + unsigned int in_use; struct v4l2_kevent events[]; }; +/** + * v4l2_event_dequeue - Dequeue events from video device. + * + * @fh: pointer to struct v4l2_fh + * @event: pointer to struct v4l2_event + * @nonblocking: if not zero, waits for an event to arrive + */ int v4l2_event_dequeue(struct v4l2_fh *fh, struct v4l2_event *event, int nonblocking); + +/** + * v4l2_event_queue - Queue events to video device. + * + * @vdev: pointer to &struct video_device + * @ev: pointer to &struct v4l2_event + * + * The event will be queued for all &struct v4l2_fh file handlers. + * + * .. note:: + * The driver's only responsibility is to fill in the type and the data + * fields.The other fields will be filled in by V4L2. + */ void v4l2_event_queue(struct video_device *vdev, const struct v4l2_event *ev); + +/** + * v4l2_event_queue_fh - Queue events to video device. + * + * @fh: pointer to &struct v4l2_fh + * @ev: pointer to &struct v4l2_event + * + * + * The event will be queued only for the specified &struct v4l2_fh file handler. + * + * .. note:: + * The driver's only responsibility is to fill in the type and the data + * fields.The other fields will be filled in by V4L2. + */ void v4l2_event_queue_fh(struct v4l2_fh *fh, const struct v4l2_event *ev); + +/** + * v4l2_event_pending - Check if an event is available + * + * @fh: pointer to &struct v4l2_fh + * + * Returns the number of pending events. + */ int v4l2_event_pending(struct v4l2_fh *fh); + +/** + * v4l2_event_subscribe - Subscribes to an event + * + * @fh: pointer to &struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + * @elems: size of the events queue + * @ops: pointer to &v4l2_subscribed_event_ops + * + * .. note:: + * + * if @elems is zero, the framework will fill in a default value, + * with is currently 1 element. + */ int v4l2_event_subscribe(struct v4l2_fh *fh, - const struct v4l2_event_subscription *sub, unsigned elems, + const struct v4l2_event_subscription *sub, + unsigned int elems, const struct v4l2_subscribed_event_ops *ops); +/** + * v4l2_event_unsubscribe - Unsubscribes to an event + * + * @fh: pointer to &struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + */ int v4l2_event_unsubscribe(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub); +/** + * v4l2_event_unsubscribe_all - Unsubscribes to all events + * + * @fh: pointer to &struct v4l2_fh + */ void v4l2_event_unsubscribe_all(struct v4l2_fh *fh); -int v4l2_event_subdev_unsubscribe(struct v4l2_subdev *sd, struct v4l2_fh *fh, + +/** + * v4l2_event_subdev_unsubscribe - Subdev variant of v4l2_event_unsubscribe() + * + * @sd: pointer to &struct v4l2_subdev + * @fh: pointer to &struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + * + * .. note:: + * + * This function should be used for the &struct v4l2_subdev_core_ops + * %unsubscribe_event field. + */ +int v4l2_event_subdev_unsubscribe(struct v4l2_subdev *sd, + struct v4l2_fh *fh, struct v4l2_event_subscription *sub); +/** + * v4l2_src_change_event_subscribe - + * + * @fh: pointer to struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + */ int v4l2_src_change_event_subscribe(struct v4l2_fh *fh, - const struct v4l2_event_subscription *sub); + const struct v4l2_event_subscription *sub); +/** + * v4l2_src_change_event_subdev_subscribe - Variant of v4l2_event_subscribe(), + * meant to subscribe only events of the type %V4L2_EVENT_SOURCE_CHANGE. + * + * @sd: pointer to &struct v4l2_subdev + * @fh: pointer to &struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + */ int v4l2_src_change_event_subdev_subscribe(struct v4l2_subdev *sd, - struct v4l2_fh *fh, struct v4l2_event_subscription *sub); + struct v4l2_fh *fh, + struct v4l2_event_subscription *sub); #endif /* V4L2_EVENT_H */ -- cgit v1.2.3 From 4ada120eaa2d57378b9c270273e8c0b7e542f019 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 22 Jul 2016 09:06:45 -0300 Subject: [media] v4l2-fh.h: add documentation for it This header file was undocumented. Add documentation for it. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-fh.h | 128 ++++++++++++++++++++++++++++++++++++------------ 1 file changed, 96 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h index 803516775162..e19e6246e21c 100644 --- a/include/media/v4l2-fh.h +++ b/include/media/v4l2-fh.h @@ -33,6 +33,21 @@ struct video_device; struct v4l2_ctrl_handler; +/** + * struct v4l2_fh - Describes a V4L2 file handler + * + * @list: list of file handlers + * @vdev: pointer to &struct video_device + * @ctrl_handler: pointer to &struct v4l2_ctrl_handler + * @prio: priority of the file handler, as defined by &enum v4l2_priority + * + * @wait: event' s wait queue + * @subscribed: list of subscribed events + * @available: list of events waiting to be dequeued + * @navailable: number of available events at @available list + * @sequence: event sequence number + * @m2m_ctx: pointer to &struct v4l2_m2m_ctx + */ struct v4l2_fh { struct list_head list; struct video_device *vdev; @@ -41,8 +56,8 @@ struct v4l2_fh { /* Events */ wait_queue_head_t wait; - struct list_head subscribed; /* Subscribed events */ - struct list_head available; /* Dequeueable event */ + struct list_head subscribed; + struct list_head available; unsigned int navailable; u32 sequence; @@ -51,53 +66,102 @@ struct v4l2_fh { #endif }; -/* - * Initialise the file handle. Parts of the V4L2 framework using the +/** + * v4l2_fh_init - Initialise the file handle. + * + * @fh: pointer to &struct v4l2_fh + * @vdev: pointer to &struct video_device + * + * Parts of the V4L2 framework using the * file handles should be initialised in this function. Must be called - * from driver's v4l2_file_operations->open() handler if the driver - * uses v4l2_fh. + * from driver's v4l2_file_operations->open\(\) handler if the driver + * uses &struct v4l2_fh. */ void v4l2_fh_init(struct v4l2_fh *fh, struct video_device *vdev); -/* - * Add the fh to the list of file handles on a video_device. The file - * handle must be initialised first. + +/** + * v4l2_fh_add - Add the fh to the list of file handles on a video_device. + * + * @fh: pointer to &struct v4l2_fh + * + * .. note:: + * The @fh file handle must be initialised first. */ void v4l2_fh_add(struct v4l2_fh *fh); -/* - * Can be used as the open() op of v4l2_file_operations. - * It allocates a v4l2_fh and inits and adds it to the video_device associated - * with the file pointer. + +/** + * v4l2_fh_open - Ancillary routine that can be used as the open\(\) op + * of v4l2_file_operations. + * + * @filp: pointer to struct file + * + * It allocates a v4l2_fh and inits and adds it to the &struct video_device + * associated with the file pointer. */ int v4l2_fh_open(struct file *filp); -/* - * Remove file handle from the list of file handles. Must be called in - * v4l2_file_operations->release() handler if the driver uses v4l2_fh. - * On error filp->private_data will be NULL, otherwise it will point to - * the v4l2_fh struct. + +/** + * v4l2_fh_del - Remove file handle from the list of file handles. + * + * @fh: pointer to &struct v4l2_fh + * + * On error filp->private_data will be %NULL, otherwise it will point to + * the &struct v4l2_fh. + * + * .. note:: + * Must be called in v4l2_file_operations->release\(\) handler if the driver + * uses &struct v4l2_fh. */ void v4l2_fh_del(struct v4l2_fh *fh); -/* - * Release resources related to a file handle. Parts of the V4L2 - * framework using the v4l2_fh must release their resources here, too. - * Must be called in v4l2_file_operations->release() handler if the - * driver uses v4l2_fh. + +/** + * v4l2_fh_exit - Release resources related to a file handle. + * + * @fh: pointer to &struct v4l2_fh + * + * Parts of the V4L2 framework using the v4l2_fh must release their + * resources here, too. + * + * .. note:: + * Must be called in v4l2_file_operations->release\(\) handler if the + * driver uses &struct v4l2_fh. */ void v4l2_fh_exit(struct v4l2_fh *fh); -/* - * Can be used as the release() op of v4l2_file_operations. + +/** + * v4l2_fh_release - Ancillary routine that can be used as the release\(\) op + * of v4l2_file_operations. + * + * @filp: pointer to struct file + * * It deletes and exits the v4l2_fh associated with the file pointer and * frees it. It will do nothing if filp->private_data (the pointer to the - * v4l2_fh struct) is NULL. This function always returns 0. + * v4l2_fh struct) is %NULL. + * + * This function always returns 0. */ int v4l2_fh_release(struct file *filp); -/* - * Returns 1 if this filehandle is the only filehandle opened for the - * associated video_device. If fh is NULL, then it returns 0. + +/** + * v4l2_fh_is_singular - Returns 1 if this filehandle is the only filehandle + * opened for the associated video_device. + * + * @fh: pointer to &struct v4l2_fh + * + * If @fh is NULL, then it returns 0. */ int v4l2_fh_is_singular(struct v4l2_fh *fh); -/* - * Helper function with struct file as argument. If filp->private_data is - * NULL, then it will return 0. + +/** + * v4l2_fh_is_singular_file - Returns 1 if this filehandle is the only + * filehandle opened for the associated video_device. + * + * @filp: pointer to struct file + * + * This is a helper function variant of v4l2_fh_is_singular() with uses + * struct file as argument. + * + * If filp->private_data is %NULL, then it will return 0. */ static inline int v4l2_fh_is_singular_file(struct file *filp) { -- cgit v1.2.3 From 6d85d7d7eb86f0f16f9da94d5999ed4d55396d2e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 22 Jul 2016 10:58:03 -0300 Subject: [media] doc-rst: Fix some typedef ugly warnings Sphinx can't handle well typedefs. Change two typedef occurrences, in order to cleanup some of such warnings. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ctrls.h | 4 +++- include/media/v4l2-dv-timings.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 8b59336b2217..d6f63406b885 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -534,6 +534,8 @@ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl, const struct v4l2_ctrl_ops *ops, u32 id, u8 max, u8 def, const s64 *qmenu_int); +typedef bool (*v4l2_ctrl_filter)(const struct v4l2_ctrl *ctrl); + /** * v4l2_ctrl_add_handler() - Add all controls from handler @add to * handler @hdl. @@ -550,7 +552,7 @@ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl, */ int v4l2_ctrl_add_handler(struct v4l2_ctrl_handler *hdl, struct v4l2_ctrl_handler *add, - bool (*filter)(const struct v4l2_ctrl *ctrl)); + v4l2_ctrl_filter filter); /** * v4l2_ctrl_radio_filter() - Standard filter for radio controls. diff --git a/include/media/v4l2-dv-timings.h b/include/media/v4l2-dv-timings.h index 1113c8874c26..65caadf13eec 100644 --- a/include/media/v4l2-dv-timings.h +++ b/include/media/v4l2-dv-timings.h @@ -28,7 +28,7 @@ */ extern const struct v4l2_dv_timings v4l2_dv_timings_presets[]; -/** +/* * v4l2_check_dv_timings_fnc - timings check callback * * @t: the v4l2_dv_timings struct. -- cgit v1.2.3 From 8ec4bee7c10e55ca9df398a28cbd53beb26b343c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 22 Jul 2016 13:57:29 -0300 Subject: [media] v4l2-ctrls.h: fully document the header file There are lots of undocumented stuff on this header. Document them. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ctrls.h | 365 ++++++++++++++++++++++++++++++++++----------- 1 file changed, 279 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index d6f63406b885..178a88d45aea 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -1,21 +1,17 @@ /* - V4L2 controls support header. - - Copyright (C) 2010 Hans Verkuil - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * V4L2 controls support header. + * + * Copyright (C) 2010 Hans Verkuil + * + * 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 _V4L2_CTRLS_H @@ -58,6 +54,7 @@ union v4l2_ctrl_ptr { /** * struct v4l2_ctrl_ops - The control operations that the driver has to provide. + * * @g_volatile_ctrl: Get a new value for this control. Generally only relevant * for volatile (and usually read-only) controls such as a control * that returns the current signal strength which changes @@ -77,12 +74,13 @@ struct v4l2_ctrl_ops { /** * struct v4l2_ctrl_type_ops - The control type operations that the driver - * has to provide. + * has to provide. * * @equal: return true if both values are equal. * @init: initialize the value. * @log: log the value. - * @validate: validate the value. Return 0 on success and a negative value otherwise. + * @validate: validate the value. Return 0 on success and a negative value + * otherwise. */ struct v4l2_ctrl_type_ops { bool (*equal)(const struct v4l2_ctrl *ctrl, u32 idx, @@ -99,6 +97,7 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv); /** * struct v4l2_ctrl - The control structure. + * * @node: The list node. * @ev_subs: The list of control event subscriptions. * @handler: The handler that owns the control. @@ -106,7 +105,7 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv); * @ncontrols: Number of controls in cluster array. * @done: Internal flag: set for each processed control. * @is_new: Set when the user specified a new value for this control. It - * is also set when called from v4l2_ctrl_handler_setup. Drivers + * is also set when called from v4l2_ctrl_handler_setup(). Drivers * should never set this flag. * @has_changed: Set when the current value differs from the new value. Drivers * should never use this flag. @@ -119,9 +118,10 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv); * set this flag directly. * @is_int: If set, then this control has a simple integer value (i.e. it * uses ctrl->val). - * @is_string: If set, then this control has type V4L2_CTRL_TYPE_STRING. - * @is_ptr: If set, then this control is an array and/or has type >= V4L2_CTRL_COMPOUND_TYPES - * and/or has type V4L2_CTRL_TYPE_STRING. In other words, struct + * @is_string: If set, then this control has type %V4L2_CTRL_TYPE_STRING. + * @is_ptr: If set, then this control is an array and/or has type >= + * %V4L2_CTRL_COMPOUND_TYPES + * and/or has type %V4L2_CTRL_TYPE_STRING. In other words, &struct * v4l2_ext_control uses field p to point to the data. * @is_array: If set, then this control contains an N-dimensional array. * @has_volatiles: If set, then one or more members of the cluster are volatile. @@ -177,7 +177,8 @@ struct v4l2_ctrl { struct list_head ev_subs; struct v4l2_ctrl_handler *handler; struct v4l2_ctrl **cluster; - unsigned ncontrols; + unsigned int ncontrols; + unsigned int done:1; unsigned int is_new:1; @@ -223,10 +224,12 @@ struct v4l2_ctrl { /** * struct v4l2_ctrl_ref - The control reference. + * * @node: List node for the sorted list. * @next: Single-link list node for the hash. * @ctrl: The actual control information. - * @helper: Pointer to helper struct. Used internally in prepare_ext_ctrls(). + * @helper: Pointer to helper struct. Used internally in + * prepare_ext_ctrls(). * * Each control handler has a list of these refs. The list_head is used to * keep a sorted-by-control-ID list of all controls, while the next pointer @@ -241,8 +244,9 @@ struct v4l2_ctrl_ref { /** * struct v4l2_ctrl_handler - The control handler keeps track of all the - * controls: both the controls owned by the handler and those inherited - * from other handlers. + * controls: both the controls owned by the handler and those inherited + * from other handlers. + * * @_lock: Default for "lock". * @lock: Lock to control access to this handler and its controls. * May be replaced by the user right after init. @@ -252,7 +256,8 @@ struct v4l2_ctrl_ref { * control is needed multiple times, so this is a simple * optimization. * @buckets: Buckets for the hashing. Allows for quick control lookup. - * @notify: A notify callback that is called whenever the control changes value. + * @notify: A notify callback that is called whenever the control changes + * value. * Note that the handler's lock is held when the notify function * is called! * @notify_priv: Passed as argument to the v4l2_ctrl notify callback. @@ -274,6 +279,7 @@ struct v4l2_ctrl_handler { /** * struct v4l2_ctrl_config - Control configuration structure. + * * @ops: The control ops. * @type_ops: The control type ops. Only needed for compound controls. * @id: The control ID. @@ -282,7 +288,7 @@ struct v4l2_ctrl_handler { * @min: The control's minimum value. * @max: The control's maximum value. * @step: The control's step value for non-menu controls. - * @def: The control's default value. + * @def: The control's default value. * @dims: The size of each dimension. * @elem_size: The size in bytes of the control. * @flags: The control's flags. @@ -297,7 +303,7 @@ struct v4l2_ctrl_handler { * is in addition to the menu_skip_mask above). The last entry * must be NULL. * @qmenu_int: A const s64 integer array for all menu items of the type - * V4L2_CTRL_TYPE_INTEGER_MENU. + * V4L2_CTRL_TYPE_INTEGER_MENU. * @is_private: If set, then this control is private to its handler and it * will not be added to any other handlers. */ @@ -320,20 +326,31 @@ struct v4l2_ctrl_config { unsigned int is_private:1; }; -/* - * v4l2_ctrl_fill() - Fill in the control fields based on the control ID. +/** + * v4l2_ctrl_fill - Fill in the control fields based on the control ID. + * + * @id: ID of the control + * @name: name of the control + * @type: type of the control + * @min: minimum value for the control + * @max: maximum value for the control + * @step: control step + * @def: default value for the control + * @flags: flags to be used on the control * * This works for all standard V4L2 controls. * For non-standard controls it will only fill in the given arguments - * and @name will be NULL. + * and @name will be %NULL. * * This function will overwrite the contents of @name, @type and @flags. * The contents of @min, @max, @step and @def may be modified depending on * the type. * - * Do not use in drivers! It is used internally for backwards compatibility - * control handling only. Once all drivers are converted to use the new - * control framework this function will no longer be exported. + * .. note:: + * + * Do not use in drivers! It is used internally for backwards compatibility + * control handling only. Once all drivers are converted to use the new + * control framework this function will no longer be exported. */ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, s64 *min, s64 *max, u64 *step, s64 *def, u32 *flags); @@ -359,7 +376,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, * macro that hides the @key and @name arguments. */ int v4l2_ctrl_handler_init_class(struct v4l2_ctrl_handler *hdl, - unsigned nr_of_controls_hint, + unsigned int nr_of_controls_hint, struct lock_class_key *key, const char *name); #ifdef CONFIG_LOCKDEP @@ -436,7 +453,8 @@ void v4l2_ctrl_handler_log_status(struct v4l2_ctrl_handler *hdl, /** * v4l2_ctrl_new_custom() - Allocate and initialize a new custom V4L2 - * control. + * control. + * * @hdl: The control handler. * @cfg: The control's configuration data. * @priv: The control's driver-specific private data. @@ -445,17 +463,20 @@ void v4l2_ctrl_handler_log_status(struct v4l2_ctrl_handler *hdl, * and @hdl->error is set to the error code (if it wasn't set already). */ struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl, - const struct v4l2_ctrl_config *cfg, void *priv); + const struct v4l2_ctrl_config *cfg, + void *priv); /** - * v4l2_ctrl_new_std() - Allocate and initialize a new standard V4L2 non-menu control. + * v4l2_ctrl_new_std() - Allocate and initialize a new standard V4L2 non-menu + * control. + * * @hdl: The control handler. * @ops: The control ops. - * @id: The control ID. + * @id: The control ID. * @min: The control's minimum value. * @max: The control's maximum value. * @step: The control's step value - * @def: The control's default value. + * @def: The control's default value. * * If the &v4l2_ctrl struct could not be allocated, or the control * ID is not known, then NULL is returned and @hdl->error is set to the @@ -466,22 +487,25 @@ struct v4l2_ctrl *v4l2_ctrl_new_custom(struct v4l2_ctrl_handler *hdl, * Use v4l2_ctrl_new_std_menu() when adding menu controls. */ struct v4l2_ctrl *v4l2_ctrl_new_std(struct v4l2_ctrl_handler *hdl, - const struct v4l2_ctrl_ops *ops, - u32 id, s64 min, s64 max, u64 step, s64 def); + const struct v4l2_ctrl_ops *ops, + u32 id, s64 min, s64 max, u64 step, + s64 def); /** - * v4l2_ctrl_new_std_menu() - Allocate and initialize a new standard V4L2 menu control. + * v4l2_ctrl_new_std_menu() - Allocate and initialize a new standard V4L2 + * menu control. + * * @hdl: The control handler. * @ops: The control ops. - * @id: The control ID. + * @id: The control ID. * @max: The control's maximum value. - * @mask: The control's skip mask for menu controls. This makes it + * @mask: The control's skip mask for menu controls. This makes it * easy to skip menu items that are not valid. If bit X is set, * then menu item X is skipped. Of course, this only works for * menus with <= 64 menu items. There are no menus that come * close to that number, so this is OK. Should we ever need more, * then this will have to be extended to a bit array. - * @def: The control's default value. + * @def: The control's default value. * * Same as v4l2_ctrl_new_std(), but @min is set to 0 and the @mask value * determines which menu items are to be skipped. @@ -489,12 +513,13 @@ struct v4l2_ctrl *v4l2_ctrl_new_std(struct v4l2_ctrl_handler *hdl, * If @id refers to a non-menu control, then this function will return NULL. */ struct v4l2_ctrl *v4l2_ctrl_new_std_menu(struct v4l2_ctrl_handler *hdl, - const struct v4l2_ctrl_ops *ops, - u32 id, u8 max, u64 mask, u8 def); + const struct v4l2_ctrl_ops *ops, + u32 id, u8 max, u64 mask, u8 def); /** * v4l2_ctrl_new_std_menu_items() - Create a new standard V4L2 menu control - * with driver specific menu. + * with driver specific menu. + * * @hdl: The control handler. * @ops: The control ops. * @id: The control ID. @@ -513,11 +538,14 @@ struct v4l2_ctrl *v4l2_ctrl_new_std_menu(struct v4l2_ctrl_handler *hdl, * */ struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(struct v4l2_ctrl_handler *hdl, - const struct v4l2_ctrl_ops *ops, u32 id, u8 max, - u64 mask, u8 def, const char * const *qmenu); + const struct v4l2_ctrl_ops *ops, + u32 id, u8 max, + u64 mask, u8 def, + const char * const *qmenu); /** * v4l2_ctrl_new_int_menu() - Create a new standard V4L2 integer menu control. + * * @hdl: The control handler. * @ops: The control ops. * @id: The control ID. @@ -528,17 +556,20 @@ struct v4l2_ctrl *v4l2_ctrl_new_std_menu_items(struct v4l2_ctrl_handler *hdl, * Same as v4l2_ctrl_new_std_menu(), but @mask is set to 0 and it additionaly * takes as an argument an array of integers determining the menu items. * - * If @id refers to a non-integer-menu control, then this function will return NULL. + * If @id refers to a non-integer-menu control, then this function will + * return %NULL. */ struct v4l2_ctrl *v4l2_ctrl_new_int_menu(struct v4l2_ctrl_handler *hdl, - const struct v4l2_ctrl_ops *ops, - u32 id, u8 max, u8 def, const s64 *qmenu_int); + const struct v4l2_ctrl_ops *ops, + u32 id, u8 max, u8 def, + const s64 *qmenu_int); typedef bool (*v4l2_ctrl_filter)(const struct v4l2_ctrl *ctrl); /** * v4l2_ctrl_add_handler() - Add all controls from handler @add to - * handler @hdl. + * handler @hdl. + * * @hdl: The control handler. * @add: The control handler whose controls you want to add to * the @hdl control handler. @@ -556,6 +587,7 @@ int v4l2_ctrl_add_handler(struct v4l2_ctrl_handler *hdl, /** * v4l2_ctrl_radio_filter() - Standard filter for radio controls. + * * @ctrl: The control that is filtered. * * This will return true for any controls that are valid for radio device @@ -567,16 +599,19 @@ int v4l2_ctrl_add_handler(struct v4l2_ctrl_handler *hdl, bool v4l2_ctrl_radio_filter(const struct v4l2_ctrl *ctrl); /** - * v4l2_ctrl_cluster() - Mark all controls in the cluster as belonging to that cluster. + * v4l2_ctrl_cluster() - Mark all controls in the cluster as belonging + * to that cluster. + * * @ncontrols: The number of controls in this cluster. - * @controls: The cluster control array of size @ncontrols. + * @controls: The cluster control array of size @ncontrols. */ -void v4l2_ctrl_cluster(unsigned ncontrols, struct v4l2_ctrl **controls); +void v4l2_ctrl_cluster(unsigned int ncontrols, struct v4l2_ctrl **controls); /** - * v4l2_ctrl_auto_cluster() - Mark all controls in the cluster as belonging to - * that cluster and set it up for autofoo/foo-type handling. + * v4l2_ctrl_auto_cluster() - Mark all controls in the cluster as belonging + * to that cluster and set it up for autofoo/foo-type handling. + * * @ncontrols: The number of controls in this cluster. * @controls: The cluster control array of size @ncontrols. The first control * must be the 'auto' control (e.g. autogain, autoexposure, etc.) @@ -604,12 +639,14 @@ void v4l2_ctrl_cluster(unsigned ncontrols, struct v4l2_ctrl **controls); * on the autofoo control and V4L2_CTRL_FLAG_INACTIVE on the foo control(s) * if autofoo is in auto mode. */ -void v4l2_ctrl_auto_cluster(unsigned ncontrols, struct v4l2_ctrl **controls, - u8 manual_val, bool set_volatile); +void v4l2_ctrl_auto_cluster(unsigned int ncontrols, + struct v4l2_ctrl **controls, + u8 manual_val, bool set_volatile); /** * v4l2_ctrl_find() - Find a control with the given ID. + * * @hdl: The control handler. * @id: The control ID to find. * @@ -634,6 +671,7 @@ void v4l2_ctrl_activate(struct v4l2_ctrl *ctrl, bool active); /** * v4l2_ctrl_grab() - Mark the control as grabbed or not grabbed. + * * @ctrl: The control to (de)activate. * @grabbed: True if the control should become grabbed. * @@ -673,6 +711,7 @@ int __v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl, /** * v4l2_ctrl_modify_range() - Update the range of a control. + * * @ctrl: The control to update. * @min: The control's minimum value. * @max: The control's maximum value. @@ -703,6 +742,7 @@ static inline int v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl, /** * v4l2_ctrl_notify() - Function to set a notify callback for a control. + * * @ctrl: The control. * @notify: The callback function. * @priv: The callback private handle, passed as argument to the callback. @@ -714,10 +754,12 @@ static inline int v4l2_ctrl_modify_range(struct v4l2_ctrl *ctrl, * There can be only one notify. If another already exists, then a WARN_ON * will be issued and the function will do nothing. */ -void v4l2_ctrl_notify(struct v4l2_ctrl *ctrl, v4l2_ctrl_notify_fnc notify, void *priv); +void v4l2_ctrl_notify(struct v4l2_ctrl *ctrl, v4l2_ctrl_notify_fnc notify, + void *priv); /** * v4l2_ctrl_get_name() - Get the name of the control + * * @id: The control ID. * * This function returns the name of the given control ID or NULL if it isn't @@ -727,6 +769,7 @@ const char *v4l2_ctrl_get_name(u32 id); /** * v4l2_ctrl_get_menu() - Get the menu string array of the control + * * @id: The control ID. * * This function returns the NULL-terminated menu string array name of the @@ -736,6 +779,7 @@ const char * const *v4l2_ctrl_get_menu(u32 id); /** * v4l2_ctrl_get_int_menu() - Get the integer menu array of the control + * * @id: The control ID. * @len: The size of the integer array. * @@ -745,7 +789,9 @@ const char * const *v4l2_ctrl_get_menu(u32 id); const s64 *v4l2_ctrl_get_int_menu(u32 id, u32 *len); /** - * v4l2_ctrl_g_ctrl() - Helper function to get the control's value from within a driver. + * v4l2_ctrl_g_ctrl() - Helper function to get the control's value from + * within a driver. + * * @ctrl: The control. * * This returns the control's value safely by going through the control @@ -758,8 +804,9 @@ s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl); /** * __v4l2_ctrl_s_ctrl() - Unlocked variant of v4l2_ctrl_s_ctrl(). + * * @ctrl: The control. - * @val: The new value. + * @val: TheControls name new value. * * This sets the control's new value safely by going through the control * framework. This function assumes the control's handler is already locked, @@ -769,7 +816,9 @@ s32 v4l2_ctrl_g_ctrl(struct v4l2_ctrl *ctrl); */ int __v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val); -/** v4l2_ctrl_s_ctrl() - Helper function to set the control's value from within a driver. +/** + * v4l2_ctrl_s_ctrl() - Helper function to set the control's value from + * within a driver. * @ctrl: The control. * @val: The new value. * @@ -793,6 +842,7 @@ static inline int v4l2_ctrl_s_ctrl(struct v4l2_ctrl *ctrl, s32 val) /** * v4l2_ctrl_g_ctrl_int64() - Helper function to get a 64-bit control's value * from within a driver. + * * @ctrl: The control. * * This returns the control's value safely by going through the control @@ -817,7 +867,8 @@ s64 v4l2_ctrl_g_ctrl_int64(struct v4l2_ctrl *ctrl); */ int __v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val); -/** v4l2_ctrl_s_ctrl_int64() - Helper function to set a 64-bit control's value +/** + * v4l2_ctrl_s_ctrl_int64() - Helper function to set a 64-bit control's value * from within a driver. * * @ctrl: The control. @@ -840,7 +891,8 @@ static inline int v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val) return rval; } -/** __v4l2_ctrl_s_ctrl_string() - Unlocked variant of v4l2_ctrl_s_ctrl_string(). +/** + * __v4l2_ctrl_s_ctrl_string() - Unlocked variant of v4l2_ctrl_s_ctrl_string(). * * @ctrl: The control. * @s: The new string. @@ -853,12 +905,13 @@ static inline int v4l2_ctrl_s_ctrl_int64(struct v4l2_ctrl *ctrl, s64 val) */ int __v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s); -/** v4l2_ctrl_s_ctrl_string() - Helper function to set a control's string value +/** + * v4l2_ctrl_s_ctrl_string() - Helper function to set a control's string value * from within a driver. * * @ctrl: The control. * @s: The new string. - * + *Controls name * This sets the control's new string safely by going through the control * framework. This function will lock the control's handler, so it cannot be * used from within the &v4l2_ctrl_ops functions. @@ -878,39 +931,179 @@ static inline int v4l2_ctrl_s_ctrl_string(struct v4l2_ctrl *ctrl, const char *s) /* Internal helper functions that deal with control events. */ extern const struct v4l2_subscribed_event_ops v4l2_ctrl_sub_ev_ops; + +/** + * v4l2_ctrl_replace - Function to be used as a callback to + * &struct v4l2_subscribed_event_ops replace\(\) + * + * @old: pointer to :ref:`struct v4l2_event ` with the reported + * event; + * @new: pointer to :ref:`struct v4l2_event ` with the modified + * event; + */ void v4l2_ctrl_replace(struct v4l2_event *old, const struct v4l2_event *new); + +/** + * v4l2_ctrl_merge - Function to be used as a callback to + * &struct v4l2_subscribed_event_ops merge(\) + * + * @old: pointer to :ref:`struct v4l2_event ` with the reported + * event; + * @new: pointer to :ref:`struct v4l2_event ` with the merged + * event; + */ void v4l2_ctrl_merge(const struct v4l2_event *old, struct v4l2_event *new); -/* Can be used as a vidioc_log_status function that just dumps all controls - associated with the filehandle. */ +/** + * v4l2_ctrl_log_status - helper function to implement %VIDIOC_LOG_STATUS ioctl + * + * @file: pointer to struct file + * @fh: unused. Kept just to be compatible to the arguments expected by + * &struct v4l2_ioctl_ops.vidioc_log_status. + * + * Can be used as a vidioc_log_status function that just dumps all controls + * associated with the filehandle. + */ int v4l2_ctrl_log_status(struct file *file, void *fh); -/* Can be used as a vidioc_subscribe_event function that just subscribes - control events. */ +/** + * v4l2_ctrl_subscribe_event - Subscribes to an event + * + * + * @fh: pointer to struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + * + * Can be used as a vidioc_subscribe_event function that just subscribes + * control events. + */ int v4l2_ctrl_subscribe_event(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub); -/* Can be used as a poll function that just polls for control events. */ +/** + * v4l2_ctrl_poll - function to be used as a callback to the poll() + * That just polls for control events. + * + * @file: pointer to struct file + * @wait: pointer to struct poll_table_struct + */ unsigned int v4l2_ctrl_poll(struct file *file, struct poll_table_struct *wait); -/* Helpers for ioctl_ops. If hdl == NULL then they will all return -EINVAL. */ +/* Helpers for ioctl_ops */ + +/** + * v4l2_queryctrl - Helper function to implement + * :ref:`VIDIOC_QUERYCTRL ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @qc: pointer to &struct v4l2_queryctrl + * + * If hdl == NULL then they will all return -EINVAL. + */ int v4l2_queryctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_queryctrl *qc); -int v4l2_query_ext_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_query_ext_ctrl *qc); + +/** + * v4l2_query_ext_ctrl - Helper function to implement + * :ref:`VIDIOC_QUERY_EXT_CTRL ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @qc: pointer to &struct v4l2_query_ext_ctrl + * + * If hdl == NULL then they will all return -EINVAL. + */ +int v4l2_query_ext_ctrl(struct v4l2_ctrl_handler *hdl, + struct v4l2_query_ext_ctrl *qc); + +/** + * v4l2_querymenu - Helper function to implement + * :ref:`VIDIOC_QUERYMENU ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @qm: pointer to &struct v4l2_querymenu + * + * If hdl == NULL then they will all return -EINVAL. + */ int v4l2_querymenu(struct v4l2_ctrl_handler *hdl, struct v4l2_querymenu *qm); + +/** + * v4l2_g_ctrl - Helper function to implement + * :ref:`VIDIOC_G_CTRL ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @ctrl: pointer to &struct v4l2_control + * + * If hdl == NULL then they will all return -EINVAL. + */ int v4l2_g_ctrl(struct v4l2_ctrl_handler *hdl, struct v4l2_control *ctrl); + +/** + * v4l2_s_ctrl - Helper function to implement + * :ref:`VIDIOC_S_CTRL ` ioctl + * + * @fh: pointer to &struct v4l2_fh + * @hdl: pointer to &struct v4l2_ctrl_handler + * + * @ctrl: pointer to &struct v4l2_control + * + * If hdl == NULL then they will all return -EINVAL. + */ int v4l2_s_ctrl(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, - struct v4l2_control *ctrl); -int v4l2_g_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *c); -int v4l2_try_ext_ctrls(struct v4l2_ctrl_handler *hdl, struct v4l2_ext_controls *c); + struct v4l2_control *ctrl); + +/** + * v4l2_g_ext_ctrls - Helper function to implement + * :ref:`VIDIOC_G_EXT_CTRLS ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @c: pointer to &struct v4l2_ext_controls + * + * If hdl == NULL then they will all return -EINVAL. + */ +int v4l2_g_ext_ctrls(struct v4l2_ctrl_handler *hdl, + struct v4l2_ext_controls *c); + +/** + * v4l2_try_ext_ctrls - Helper function to implement + * :ref:`VIDIOC_TRY_EXT_CTRLS ` ioctl + * + * @hdl: pointer to &struct v4l2_ctrl_handler + * @c: pointer to &struct v4l2_ext_controls + * + * If hdl == NULL then they will all return -EINVAL. + */ +int v4l2_try_ext_ctrls(struct v4l2_ctrl_handler *hdl, + struct v4l2_ext_controls *c); + +/** + * v4l2_s_ext_ctrls - Helper function to implement + * :ref:`VIDIOC_S_EXT_CTRLS ` ioctl + * + * @fh: pointer to &struct v4l2_fh + * @hdl: pointer to &struct v4l2_ctrl_handler + * @c: pointer to &struct v4l2_ext_controls + * + * If hdl == NULL then they will all return -EINVAL. + */ int v4l2_s_ext_ctrls(struct v4l2_fh *fh, struct v4l2_ctrl_handler *hdl, - struct v4l2_ext_controls *c); + struct v4l2_ext_controls *c); -/* Can be used as a subscribe_event function that just subscribes control - events. */ +/** + * v4l2_ctrl_subdev_subscribe_event - Helper function to implement + * as a &struct v4l2_subdev_core_ops subscribe_event function + * that just subscribes control events. + * + * @sd: pointer to &struct v4l2_subdev + * @fh: pointer to &struct v4l2_fh + * @sub: pointer to &struct v4l2_event_subscription + */ int v4l2_ctrl_subdev_subscribe_event(struct v4l2_subdev *sd, struct v4l2_fh *fh, struct v4l2_event_subscription *sub); -/* Log all controls owned by subdev's control handler. */ +/** + * v4l2_ctrl_subdev_log_status - Log all controls owned by subdev's control + * handler. + * + * @sd: pointer to &struct v4l2_subdev + */ int v4l2_ctrl_subdev_log_status(struct v4l2_subdev *sd); #endif -- cgit v1.2.3 From c91661f1e69bec066c970f3a911de5713ec4a91e Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 22 Jul 2016 16:22:41 -0300 Subject: [media] v4l2-ioctl.h add debug info for struct v4l2_ioctl_ops This struct is mentioned at the kAPI docbook. So, let's document it. Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-ioctl.h | 266 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 266 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h index 017ffb2220c7..8b1d19bc9b0e 100644 --- a/include/media/v4l2-ioctl.h +++ b/include/media/v4l2-ioctl.h @@ -17,6 +17,272 @@ struct v4l2_fh; +/** + * struct v4l2_ioctl_ops - describe operations for each V4L2 ioctl + * + * @vidioc_querycap: pointer to the function that implements + * :ref:`VIDIOC_QUERYCAP ` ioctl + * @vidioc_enum_fmt_vid_cap: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for video capture in single plane mode + * @vidioc_enum_fmt_vid_overlay: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for video overlay + * @vidioc_enum_fmt_vid_out: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for video output in single plane mode + * @vidioc_enum_fmt_vid_cap_mplane: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for video capture in multiplane mode + * @vidioc_enum_fmt_vid_out_mplane: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for video output in multiplane mode + * @vidioc_enum_fmt_sdr_cap: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for Software Defined Radio capture + * @vidioc_enum_fmt_sdr_out: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FMT ` ioctl logic + * for Software Defined Radio output + * @vidioc_g_fmt_vid_cap: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video capture + * in single plane mode + * @vidioc_g_fmt_vid_overlay: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video overlay + * @vidioc_g_fmt_vid_out: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video out + * in single plane mode + * @vidioc_g_fmt_vid_out_overlay: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video overlay output + * @vidioc_g_fmt_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for raw VBI capture + * @vidioc_g_fmt_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for raw VBI output + * @vidioc_g_fmt_sliced_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for sliced VBI capture + * @vidioc_g_fmt_sliced_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for sliced VBI output + * @vidioc_g_fmt_vid_cap_mplane: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video capture + * in multiple plane mode + * @vidioc_g_fmt_vid_out_mplane: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for video out + * in multiplane plane mode + * @vidioc_g_fmt_sdr_cap: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for Software Defined + * Radio capture + * @vidioc_g_fmt_sdr_out: pointer to the function that implements + * :ref:`VIDIOC_G_FMT ` ioctl logic for Software Defined + * Radio output + * @vidioc_s_fmt_vid_cap: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video capture + * in single plane mode + * @vidioc_s_fmt_vid_overlay: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video overlay + * @vidioc_s_fmt_vid_out: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video out + * in single plane mode + * @vidioc_s_fmt_vid_out_overlay: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video overlay output + * @vidioc_s_fmt_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for raw VBI capture + * @vidioc_s_fmt_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for raw VBI output + * @vidioc_s_fmt_sliced_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for sliced VBI capture + * @vidioc_s_fmt_sliced_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for sliced VBI output + * @vidioc_s_fmt_vid_cap_mplane: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video capture + * in multiple plane mode + * @vidioc_s_fmt_vid_out_mplane: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for video out + * in multiplane plane mode + * @vidioc_s_fmt_sdr_cap: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for Software Defined + * Radio capture + * @vidioc_s_fmt_sdr_out: pointer to the function that implements + * :ref:`VIDIOC_S_FMT ` ioctl logic for Software Defined + * Radio output + * @vidioc_try_fmt_vid_cap: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video capture + * in single plane mode + * @vidioc_try_fmt_vid_overlay: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video overlay + * @vidioc_try_fmt_vid_out: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video out + * in single plane mode + * @vidioc_try_fmt_vid_out_overlay: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video overlay + * output + * @vidioc_try_fmt_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for raw VBI capture + * @vidioc_try_fmt_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for raw VBI output + * @vidioc_try_fmt_sliced_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for sliced VBI + * capture + * @vidioc_try_fmt_sliced_vbi_out: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for sliced VBI output + * @vidioc_try_fmt_vid_cap_mplane: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video capture + * in multiple plane mode + * @vidioc_try_fmt_vid_out_mplane: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for video out + * in multiplane plane mode + * @vidioc_try_fmt_sdr_cap: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for Software Defined + * Radio capture + * @vidioc_try_fmt_sdr_out: pointer to the function that implements + * :ref:`VIDIOC_TRY_FMT ` ioctl logic for Software Defined + * Radio output + * @vidioc_reqbufs: pointer to the function that implements + * :ref:`VIDIOC_REQBUFS ` ioctl + * @vidioc_querybuf: pointer to the function that implements + * :ref:`VIDIOC_QUERYBUF ` ioctl + * @vidioc_qbuf: pointer to the function that implements + * :ref:`VIDIOC_QBUF ` ioctl + * @vidioc_expbuf: pointer to the function that implements + * :ref:`VIDIOC_EXPBUF ` ioctl + * @vidioc_dqbuf: pointer to the function that implements + * :ref:`VIDIOC_DQBUF ` ioctl + * @vidioc_create_bufs: pointer to the function that implements + * :ref:`VIDIOC_CREATE_BUFS ` ioctl + * @vidioc_prepare_buf: pointer to the function that implements + * :ref:`VIDIOC_PREPARE_BUF ` ioctl + * @vidioc_overlay: pointer to the function that implements + * :ref:`VIDIOC_OVERLAY ` ioctl + * @vidioc_g_fbuf: pointer to the function that implements + * :ref:`VIDIOC_G_FBUF ` ioctl + * @vidioc_s_fbuf: pointer to the function that implements + * :ref:`VIDIOC_S_FBUF ` ioctl + * @vidioc_streamon: pointer to the function that implements + * :ref:`VIDIOC_STREAMON ` ioctl + * @vidioc_streamoff: pointer to the function that implements + * :ref:`VIDIOC_STREAMOFF ` ioctl + * @vidioc_g_std: pointer to the function that implements + * :ref:`VIDIOC_G_STD ` ioctl + * @vidioc_s_std: pointer to the function that implements + * :ref:`VIDIOC_S_STD ` ioctl + * @vidioc_querystd: pointer to the function that implements + * :ref:`VIDIOC_QUERYSTD ` ioctl + * @vidioc_enum_input: pointer to the function that implements + * :ref:`VIDIOC_ENUM_INPUT ` ioctl + * @vidioc_g_input: pointer to the function that implements + * :ref:`VIDIOC_G_INPUT ` ioctl + * @vidioc_s_input: pointer to the function that implements + * :ref:`VIDIOC_S_INPUT ` ioctl + * @vidioc_enum_output: pointer to the function that implements + * :ref:`VIDIOC_ENUM_OUTPUT ` ioctl + * @vidioc_g_output: pointer to the function that implements + * :ref:`VIDIOC_G_OUTPUT ` ioctl + * @vidioc_s_output: pointer to the function that implements + * :ref:`VIDIOC_S_OUTPUT ` ioctl + * @vidioc_queryctrl: pointer to the function that implements + * :ref:`VIDIOC_QUERYCTRL ` ioctl + * @vidioc_query_ext_ctrl: pointer to the function that implements + * :ref:`VIDIOC_QUERY_EXT_CTRL ` ioctl + * @vidioc_g_ctrl: pointer to the function that implements + * :ref:`VIDIOC_G_CTRL ` ioctl + * @vidioc_s_ctrl: pointer to the function that implements + * :ref:`VIDIOC_S_CTRL ` ioctl + * @vidioc_g_ext_ctrls: pointer to the function that implements + * :ref:`VIDIOC_G_EXT_CTRLS ` ioctl + * @vidioc_s_ext_ctrls: pointer to the function that implements + * :ref:`VIDIOC_S_EXT_CTRLS ` ioctl + * @vidioc_try_ext_ctrls: pointer to the function that implements + * :ref:`VIDIOC_TRY_EXT_CTRLS ` ioctl + * @vidioc_querymenu: pointer to the function that implements + * :ref:`VIDIOC_QUERYMENU ` ioctl + * @vidioc_enumaudio: pointer to the function that implements + * :ref:`VIDIOC_ENUMAUDIO ` ioctl + * @vidioc_g_audio: pointer to the function that implements + * :ref:`VIDIOC_G_AUDIO ` ioctl + * @vidioc_s_audio: pointer to the function that implements + * :ref:`VIDIOC_S_AUDIO ` ioctl + * @vidioc_enumaudout: pointer to the function that implements + * :ref:`VIDIOC_ENUMAUDOUT ` ioctl + * @vidioc_g_audout: pointer to the function that implements + * :ref:`VIDIOC_G_AUDOUT ` ioctl + * @vidioc_s_audout: pointer to the function that implements + * :ref:`VIDIOC_S_AUDOUT ` ioctl + * @vidioc_g_modulator: pointer to the function that implements + * :ref:`VIDIOC_G_MODULATOR ` ioctl + * @vidioc_s_modulator: pointer to the function that implements + * :ref:`VIDIOC_S_MODULATOR ` ioctl + * @vidioc_cropcap: pointer to the function that implements + * :ref:`VIDIOC_CROPCAP ` ioctl + * @vidioc_g_crop: pointer to the function that implements + * :ref:`VIDIOC_G_CROP ` ioctl + * @vidioc_s_crop: pointer to the function that implements + * :ref:`VIDIOC_S_CROP ` ioctl + * @vidioc_g_selection: pointer to the function that implements + * :ref:`VIDIOC_G_SELECTION ` ioctl + * @vidioc_s_selection: pointer to the function that implements + * :ref:`VIDIOC_S_SELECTION ` ioctl + * @vidioc_g_jpegcomp: pointer to the function that implements + * :ref:`VIDIOC_G_JPEGCOMP ` ioctl + * @vidioc_s_jpegcomp: pointer to the function that implements + * :ref:`VIDIOC_S_JPEGCOMP ` ioctl + * @vidioc_g_enc_index: pointer to the function that implements + * :ref:`VIDIOC_G_ENC_INDEX ` ioctl + * @vidioc_encoder_cmd: pointer to the function that implements + * :ref:`VIDIOC_ENCODER_CMD ` ioctl + * @vidioc_try_encoder_cmd: pointer to the function that implements + * :ref:`VIDIOC_TRY_ENCODER_CMD ` ioctl + * @vidioc_decoder_cmd: pointer to the function that implements + * :ref:`VIDIOC_DECODER_CMD ` ioctl + * @vidioc_try_decoder_cmd: pointer to the function that implements + * :ref:`VIDIOC_TRY_DECODER_CMD ` ioctl + * @vidioc_g_parm: pointer to the function that implements + * :ref:`VIDIOC_G_PARM ` ioctl + * @vidioc_s_parm: pointer to the function that implements + * :ref:`VIDIOC_S_PARM ` ioctl + * @vidioc_g_tuner: pointer to the function that implements + * :ref:`VIDIOC_G_TUNER ` ioctl + * @vidioc_s_tuner: pointer to the function that implements + * :ref:`VIDIOC_S_TUNER ` ioctl + * @vidioc_g_frequency: pointer to the function that implements + * :ref:`VIDIOC_G_FREQUENCY ` ioctl + * @vidioc_s_frequency: pointer to the function that implements + * :ref:`VIDIOC_S_FREQUENCY ` ioctl + * @vidioc_enum_freq_bands: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FREQ_BANDS ` ioctl + * @vidioc_g_sliced_vbi_cap: pointer to the function that implements + * :ref:`VIDIOC_G_SLICED_VBI_CAP ` ioctl + * @vidioc_log_status: pointer to the function that implements + * :ref:`VIDIOC_LOG_STATUS ` ioctl + * @vidioc_s_hw_freq_seek: pointer to the function that implements + * :ref:`VIDIOC_S_HW_FREQ_SEEK ` ioctl + * @vidioc_g_register: pointer to the function that implements + * :ref:`VIDIOC_DBG_G_REGISTER ` ioctl + * @vidioc_s_register: pointer to the function that implements + * :ref:`VIDIOC_DBG_S_REGISTER ` ioctl + * @vidioc_g_chip_info: pointer to the function that implements + * :ref:`VIDIOC_DBG_G_CHIP_INFO ` ioctl + * @vidioc_enum_framesizes: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FRAMESIZES ` ioctl + * @vidioc_enum_frameintervals: pointer to the function that implements + * :ref:`VIDIOC_ENUM_FRAMEINTERVALS ` ioctl + * @vidioc_s_dv_timings: pointer to the function that implements + * :ref:`VIDIOC_S_DV_TIMINGS ` ioctl + * @vidioc_g_dv_timings: pointer to the function that implements + * :ref:`VIDIOC_G_DV_TIMINGS ` ioctl + * @vidioc_query_dv_timings: pointer to the function that implements + * :ref:`VIDIOC_QUERY_DV_TIMINGS ` ioctl + * @vidioc_enum_dv_timings: pointer to the function that implements + * :ref:`VIDIOC_ENUM_DV_TIMINGS ` ioctl + * @vidioc_dv_timings_cap: pointer to the function that implements + * :ref:`VIDIOC_DV_TIMINGS_CAP ` ioctl + * @vidioc_g_edid: pointer to the function that implements + * :ref:`VIDIOC_G_EDID ` ioctl + * @vidioc_s_edid: pointer to the function that implements + * :ref:`VIDIOC_S_EDID ` ioctl + * @vidioc_subscribe_event: pointer to the function that implements + * :ref:`VIDIOC_SUBSCRIBE_EVENT ` ioctl + * @vidioc_unsubscribe_event: pointer to the function that implements + * :ref:`VIDIOC_UNSUBSCRIBE_EVENT ` ioctl + * @vidioc_default: pointed used to allow other ioctls + */ struct v4l2_ioctl_ops { /* ioctl callbacks */ -- cgit v1.2.3 From 564aaf69208d6f9e37cd82c06b889e5d9c59bfb6 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Sat, 23 Jul 2016 07:12:03 -0300 Subject: [media] doc-rst: add some needed escape codes Some extra escape codes are needed to avoid Sphinx to not identify the tags. Signed-off-by: Mauro Carvalho Chehab --- include/media/media-entity.h | 2 +- include/media/v4l2-dev.h | 4 ++-- include/media/videobuf2-core.h | 50 +++++++++++++++++++++--------------------- 3 files changed, 28 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/media/media-entity.h b/include/media/media-entity.h index 17390cc7b538..09b03c17784d 100644 --- a/include/media/media-entity.h +++ b/include/media/media-entity.h @@ -540,7 +540,7 @@ static inline bool media_entity_enum_intersects( * @gobj: Pointer to the graph object * * This routine initializes the embedded struct media_gobj inside a - * media graph object. It is called automatically if media_*_create() + * media graph object. It is called automatically if media_*_create\(\) * calls are used. However, if the object (entity, link, pad, interface) * is embedded on some other object, this function should be called before * registering the object at the media controller. diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h index 5921c24565cf..a122b1bd40f9 100644 --- a/include/media/v4l2-dev.h +++ b/include/media/v4l2-dev.h @@ -374,13 +374,13 @@ struct video_device * __must_check video_device_alloc(void); * * @vdev: pointer to &struct video_device * - * Can also be used for video_device->release(). + * Can also be used for video_device->release\(\). */ void video_device_release(struct video_device *vdev); /** * video_device_release_empty - helper function to implement the - * video_device->release() callback. + * video_device->release\(\) callback. * * @vdev: pointer to &struct video_device * diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index c346beaaeae6..946340ce7701 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -277,7 +277,7 @@ struct vb2_buffer { /** * struct vb2_ops - driver-specific callbacks * - * @queue_setup: called from VIDIOC_REQBUFS and VIDIOC_CREATE_BUFS + * @queue_setup: called from %VIDIOC_REQBUFS and %VIDIOC_CREATE_BUFS * handlers before memory allocation. It can be called * twice: if the original number of requested buffers * could not be allocated, then it will be called a @@ -286,17 +286,17 @@ struct vb2_buffer { * The driver should return the required number of buffers * in \*num_buffers, the required number of planes per * buffer in \*num_planes, the size of each plane should be - * set in the sizes[] array and optional per-plane - * allocator specific device in the alloc_devs[] array. - * When called from VIDIOC_REQBUFS, *num_planes == 0, the + * set in the sizes\[\] array and optional per-plane + * allocator specific device in the alloc_devs\[\] array. + * When called from %VIDIOC_REQBUFS, \*num_planes == 0, the * driver has to use the currently configured format to * determine the plane sizes and \*num_buffers is the total * number of buffers that are being allocated. When called - * from VIDIOC_CREATE_BUFS, \*num_planes != 0 and it - * describes the requested number of planes and sizes[] + * from %VIDIOC_CREATE_BUFS, \*num_planes != 0 and it + * describes the requested number of planes and sizes\[\] * contains the requested plane sizes. If either * \*num_planes or the requested sizes are invalid callback - * must return -EINVAL. In this case \*num_buffers are + * must return %-EINVAL. In this case \*num_buffers are * being allocated additionally to q->num_buffers. * @wait_prepare: release any locks taken while calling vb2 functions; * it is called before an ioctl needs to wait for a new @@ -311,11 +311,11 @@ struct vb2_buffer { * initialization failure (return != 0) will prevent * queue setup from completing successfully; optional. * @buf_prepare: called every time the buffer is queued from userspace - * and from the VIDIOC_PREPARE_BUF ioctl; drivers may + * and from the %VIDIOC_PREPARE_BUF ioctl; drivers may * perform any initialization required before each * hardware operation in this callback; drivers can * access/modify the buffer here as it is still synced for - * the CPU; drivers that support VIDIOC_CREATE_BUFS must + * the CPU; drivers that support %VIDIOC_CREATE_BUFS must * also validate the buffer size; if an error is returned, * the buffer will not be queued in driver; optional. * @buf_finish: called before every dequeue of the buffer back to @@ -323,23 +323,23 @@ struct vb2_buffer { * can access/modify the buffer contents; drivers may * perform any operations required before userspace * accesses the buffer; optional. The buffer state can be - * one of the following: DONE and ERROR occur while - * streaming is in progress, and the PREPARED state occurs + * one of the following: %DONE and %ERROR occur while + * streaming is in progress, and the %PREPARED state occurs * when the queue has been canceled and all pending - * buffers are being returned to their default DEQUEUED + * buffers are being returned to their default %DEQUEUED * state. Typically you only have to do something if the - * state is VB2_BUF_STATE_DONE, since in all other cases + * state is %VB2_BUF_STATE_DONE, since in all other cases * the buffer contents will be ignored anyway. * @buf_cleanup: called once before the buffer is freed; drivers may * perform any additional cleanup; optional. * @start_streaming: called once to enter 'streaming' state; the driver may - * receive buffers with @buf_queue callback before - * @start_streaming is called; the driver gets the number - * of already queued buffers in count parameter; driver - * can return an error if hardware fails, in that case all - * buffers that have been already given by the @buf_queue - * callback are to be returned by the driver by calling - * @vb2_buffer_done(VB2_BUF_STATE_QUEUED). + * receive buffers with @buf_queue callback + * before @start_streaming is called; the driver gets the + * number of already queued buffers in count parameter; + * driver can return an error if hardware fails, in that + * case all buffers that have been already given by + * the @buf_queue callback are to be returned by the driver + * by calling @vb2_buffer_done\(%VB2_BUF_STATE_QUEUED\). * If you need a minimum number of buffers before you can * start streaming, then set @min_buffers_needed in the * vb2_queue structure. If that is non-zero then @@ -347,16 +347,16 @@ struct vb2_buffer { * many buffers have been queued up by userspace. * @stop_streaming: called when 'streaming' state must be disabled; driver * should stop any DMA transactions or wait until they - * finish and give back all buffers it got from buf_queue() - * callback by calling @vb2_buffer_done() with either - * VB2_BUF_STATE_DONE or VB2_BUF_STATE_ERROR; may use + * finish and give back all buffers it got from &buf_queue + * callback by calling @vb2_buffer_done\(\) with either + * %VB2_BUF_STATE_DONE or %VB2_BUF_STATE_ERROR; may use * vb2_wait_for_all_buffers() function * @buf_queue: passes buffer vb to the driver; driver may start * hardware operation on this buffer; driver should give * the buffer back by calling vb2_buffer_done() function; - * it is allways called after calling STREAMON ioctl; + * it is allways called after calling %VIDIOC_STREAMON ioctl; * might be called before start_streaming callback if user - * pre-queued buffers before calling STREAMON. + * pre-queued buffers before calling %VIDIOC_STREAMON. */ struct vb2_ops { int (*queue_setup)(struct vb2_queue *q, -- cgit v1.2.3 From 37b137ff8c833385b75ff2baf4bace25e52247d2 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Sat, 23 Jul 2016 21:51:42 -0700 Subject: nfit, libnvdimm: allow an ARS scrub to be triggered on demand Normally, an ARS (Address Range Scrub) only happens at boot/initialization time. There can however arise situations where a bus-wide rescan is needed - notably, in the case of discovering a latent media error, we should do a full rescan to figure out what other sectors are bad, and thus potentially avoid triggering an mce on them in the future. Also provide a sysfs trigger to start a bus-wide scrub. Cc: Rafael J. Wysocki Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 2ab869dece4a..b519e137b9b7 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -137,6 +137,7 @@ struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); +struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); const char *nvdimm_name(struct nvdimm *nvdimm); unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm); void *nvdimm_provider_data(struct nvdimm *nvdimm); -- cgit v1.2.3 From 285b102d3b745f3c2c110c9c327741d87e64aacc Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 28 Jun 2016 11:47:32 +0200 Subject: vfs: new d_init method Allow filesystem to initialize dentry at allocation time. Signed-off-by: Miklos Szeredi Signed-off-by: Al Viro --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 14df83609c7f..98044a8d1487 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -133,6 +133,7 @@ struct dentry_operations { int (*d_compare)(const struct dentry *, const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); + int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); -- cgit v1.2.3 From bf3994d2ed310813da28362d87bfe9f0e1c3e37f Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 21 Jul 2016 12:03:11 +0200 Subject: net/sched: introduce Match-all classifier The matchall classifier matches every packet and allows the user to apply actions on it. This filter is very useful in usecases where every packet should be matched, for example, packet mirroring (SPAN) can be setup very easily using that filter. Signed-off-by: Jiri Pirko Signed-off-by: Yotam Gigi Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 5702e933dc07..a32494887e01 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -433,6 +433,17 @@ enum { #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + /* Extended Matches */ struct tcf_ematch_tree_hdr { -- cgit v1.2.3 From b87f7936a93246804cf70e7e2e0568799c948bb1 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Thu, 21 Jul 2016 12:03:12 +0200 Subject: net/sched: Add match-all classifier hw offloading. Following the work that have been done on offloading classifiers like u32 and flower, now the match-all classifier hw offloading is possible. if the interface supports tc offloading. To control the offloading, two tc flags have been introduced: skip_sw and skip_hw. Typical usage: tc filter add dev eth25 parent ffff: \ matchall skip_sw \ action mirred egress mirror \ dev eth27 Signed-off-by: Yotam Gigi Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ include/net/pkt_cls.h | 11 +++++++++++ include/uapi/linux/pkt_cls.h | 1 + 3 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 43c749b1b619..076df5360ba5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -787,6 +787,7 @@ enum { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, + TC_SETUP_MATCHALL, }; struct tc_cls_u32_offload; @@ -797,6 +798,7 @@ struct tc_to_netdev { u8 tc; struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; + struct tc_cls_matchall_offload *cls_mall; }; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 3722dda0199d..6f8d65342d3a 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -442,4 +442,15 @@ struct tc_cls_flower_offload { struct tcf_exts *exts; }; +enum tc_matchall_command { + TC_CLSMATCHALL_REPLACE, + TC_CLSMATCHALL_DESTROY, +}; + +struct tc_cls_matchall_offload { + enum tc_matchall_command command; + struct tcf_exts *exts; + unsigned long cookie; +}; + #endif diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index a32494887e01..d1c1ccaba787 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -439,6 +439,7 @@ enum { TCA_MATCHALL_UNSPEC, TCA_MATCHALL_CLASSID, TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, __TCA_MATCHALL_MAX, }; -- cgit v1.2.3 From 56a20680f70393d199fc5e8ecc7859549ca5a0c0 Mon Sep 17 00:00:00 2001 From: Yotam Gigi Date: Thu, 21 Jul 2016 12:03:16 +0200 Subject: net/sched: act_mirred: Add helper inlines to access tcf_mirred info. The helper function is_tcf_mirred_mirror helps finding whether an action struct is of type mirred and is configured to be of type mirror. Signed-off-by: Yotam Gigi Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/tc_act/tc_mirred.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index e891835eb74e..6a13a7c74e0c 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -24,6 +24,15 @@ static inline bool is_tcf_mirred_redirect(const struct tc_action *a) return false; } +static inline bool is_tcf_mirred_mirror(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_MIRRED) + return to_mirred(a)->tcfm_eaction == TCA_EGRESS_MIRROR; +#endif + return false; +} + static inline int tcf_mirred_ifindex(const struct tc_action *a) { return to_mirred(a)->tcfm_ifindex; -- cgit v1.2.3 From 7e7ec6a934349ef6983f06f7ac0da09cc8a42983 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sun, 24 Jul 2016 11:30:18 -0400 Subject: elf_fdpic_transfer_args_to_stack(): make it generic This copying of arguments and environment is common to both NOMMU binary formats we support. Let's make the elf_fdpic version available to the flat format as well. While at it, improve the code a bit not to copy below the actual data area. Signed-off-by: Nicolas Pitre Reviewed-by: Greg Ungerer Signed-off-by: Greg Ungerer --- include/linux/binfmts.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 314b3caa701c..1303b570b18c 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -113,6 +113,8 @@ extern int suid_dumpable; extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); +extern int transfer_args_to_stack(struct linux_binprm *bprm, + unsigned long *sp_location); extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -- cgit v1.2.3 From 9798ac6d32c1a32d6d92d853ff507d2d39c4300c Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 15 Jul 2016 16:28:41 -0700 Subject: mfd: cros_ec: Add cros_ec_cmd_xfer_status() helper So that callers of cros_ec_cmd_xfer() don't have to repeat boilerplate code when checking for errors from the EC side. Signed-off-by: Tomeu Vizoso Reviewed-by: Benson Leung Signed-off-by: Brian Norris Acked-by: Lee Jones Tested-by: Enric Balletbo i Serra Signed-off-by: Thierry Reding --- include/linux/mfd/cros_ec.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 64184d27e3cd..d641a18abacb 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -225,6 +225,21 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +/** + * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC + * + * This function is identical to cros_ec_cmd_xfer, except it returns success + * status only if both the command was transmitted successfully and the EC + * replied with success status. It's not necessary to check msg->result when + * using this function. + * + * @ec_dev: EC device + * @msg: Message to write + * @return: Num. of bytes transferred on success, <0 on failure + */ +int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg); + /** * cros_ec_remove - Remove a ChromeOS EC * -- cgit v1.2.3 From 2b66bd692c40034d42d905f37f7f20c3540f185e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 15 Jul 2016 16:28:42 -0700 Subject: mfd: cros_ec: Add EC_PWM function definitions The EC_CMD_PWM_{GET,SET}_DUTY commands allow us to control a PWM that is attached to the EC, rather than the main host SoC. The API provides functionality-based (e.g., keyboard light, backlight) or index-based addressing of the PWM(s). Duty cycles are represented by a 16-bit value, where 0 maps to 0% duty cycle and U16_MAX maps to 100%. The period cannot be controlled. This command set is more generic than, e.g., EC_CMD_PWM_{GET,SET}_KEYBOARD_BACKLIGHT and could possibly used to replace it on future products. Let's update the command header to include the definitions. Signed-off-by: Brian Norris Acked-by: Lee Jones Signed-off-by: Thierry Reding --- include/linux/mfd/cros_ec_commands.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 13b630c10d4c..7e7a8d4b4551 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -949,6 +949,37 @@ struct ec_params_pwm_set_fan_duty { uint32_t percent; } __packed; +#define EC_CMD_PWM_SET_DUTY 0x25 +/* 16 bit duty cycle, 0xffff = 100% */ +#define EC_PWM_MAX_DUTY 0xffff + +enum ec_pwm_type { + /* All types, indexed by board-specific enum pwm_channel */ + EC_PWM_TYPE_GENERIC = 0, + /* Keyboard backlight */ + EC_PWM_TYPE_KB_LIGHT, + /* Display backlight */ + EC_PWM_TYPE_DISPLAY_LIGHT, + EC_PWM_TYPE_COUNT, +}; + +struct ec_params_pwm_set_duty { + uint16_t duty; /* Duty cycle, EC_PWM_MAX_DUTY = 100% */ + uint8_t pwm_type; /* ec_pwm_type */ + uint8_t index; /* Type-specific index, or 0 if unique */ +} __packed; + +#define EC_CMD_PWM_GET_DUTY 0x26 + +struct ec_params_pwm_get_duty { + uint8_t pwm_type; /* ec_pwm_type */ + uint8_t index; /* Type-specific index, or 0 if unique */ +} __packed; + +struct ec_response_pwm_get_duty { + uint16_t duty; /* Duty cycle, EC_PWM_MAX_DUTY = 100% */ +} __packed; + /*****************************************************************************/ /* * Lightbar commands. This looks worse than it is. Since we only use one HOST -- cgit v1.2.3 From ef29c0e273b874018f1802d12957d22008138240 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Thu, 26 May 2016 09:56:12 +0800 Subject: mmc: core: add mmc-hs400-enhanced-strobe support This patch introduce mmc-hs400-enhanced-strobe for platforms which want to enable enhanced strobe function from DT if the mmc host controller claims to support enhanced strobe. Signed-off-by: Shawn Lin Reviewed-by: Douglas Anderson Tested-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 45cde8cd39f2..b836a271e2df 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -302,6 +302,7 @@ struct mmc_host { #define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17) #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18) /* No physical write protect pin, assume that card is always read-write */ #define MMC_CAP2_NO_SDIO (1 << 19) /* Do not send SDIO commands during initialization */ +#define MMC_CAP2_HS400_ES (1 << 20) /* Host supports enhanced strobe */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From 81ac2af65793ecfbd79875d45043ff4adc0982b8 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Thu, 26 May 2016 09:56:22 +0800 Subject: mmc: core: implement enhanced strobe support Controllers use data strobe line to latch data from devices under hs400 mode, but not for cmd line. So since emmc 5.1, JEDEC introduces enhanced strobe mode for latching cmd response from emmc devices to host controllers. This new feature is optional, so it depends both on device's cap and host's cap to decide whether to use it or not. Signed-off-by: Shawn Lin Reviewed-by: Jaehoon Chung Tested-by: Douglas Anderson Tested-by: Jaehoon Chung Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 1 + include/linux/mmc/host.h | 11 +++++++++++ include/linux/mmc/mmc.h | 3 +++ 3 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index eb0151bac50c..22defc2a83b7 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -95,6 +95,7 @@ struct mmc_ext_csd { u8 raw_partition_support; /* 160 */ u8 raw_rpmb_size_mult; /* 168 */ u8 raw_erased_mem_count; /* 181 */ + u8 strobe_support; /* 184 */ u8 raw_ext_csd_structure; /* 194 */ u8 raw_card_type; /* 196 */ u8 raw_driver_strength; /* 197 */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index b836a271e2df..d72c0c34c21d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -19,6 +19,7 @@ #include #include +#include #include struct mmc_ios { @@ -77,6 +78,8 @@ struct mmc_ios { #define MMC_SET_DRIVER_TYPE_A 1 #define MMC_SET_DRIVER_TYPE_C 2 #define MMC_SET_DRIVER_TYPE_D 3 + + bool enhanced_strobe; /* hs400es selection */ }; struct mmc_host_ops { @@ -143,6 +146,9 @@ struct mmc_host_ops { /* Prepare HS400 target operating frequency depending host driver */ int (*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios); + /* Prepare enhanced strobe depending host driver */ + void (*hs400_enhanced_strobe)(struct mmc_host *host, + struct mmc_ios *ios); int (*select_drive_strength)(struct mmc_card *card, unsigned int max_dtr, int host_drv, int card_drv, int *drv_type); @@ -514,6 +520,11 @@ static inline bool mmc_card_hs400(struct mmc_card *card) return card->host->ios.timing == MMC_TIMING_MMC_HS400; } +static inline bool mmc_card_hs400es(struct mmc_card *card) +{ + return card->host->ios.enhanced_strobe; +} + void mmc_retune_timer_stop(struct mmc_host *host); static inline void mmc_retune_needed(struct mmc_host *host) diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 15f2c4a0a62c..c376209c70ef 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -297,6 +297,7 @@ struct _mmc_csd { #define EXT_CSD_PART_CONFIG 179 /* R/W */ #define EXT_CSD_ERASED_MEM_CONT 181 /* RO */ #define EXT_CSD_BUS_WIDTH 183 /* R/W */ +#define EXT_CSD_STROBE_SUPPORT 184 /* RO */ #define EXT_CSD_HS_TIMING 185 /* R/W */ #define EXT_CSD_POWER_CLASS 187 /* R/W */ #define EXT_CSD_REV 192 /* RO */ @@ -380,12 +381,14 @@ struct _mmc_csd { #define EXT_CSD_CARD_TYPE_HS400_1_2V (1<<7) /* Card can run at 200MHz DDR, 1.2V */ #define EXT_CSD_CARD_TYPE_HS400 (EXT_CSD_CARD_TYPE_HS400_1_8V | \ EXT_CSD_CARD_TYPE_HS400_1_2V) +#define EXT_CSD_CARD_TYPE_HS400ES (1<<8) /* Card can run at HS400ES */ #define EXT_CSD_BUS_WIDTH_1 0 /* Card is in 1 bit mode */ #define EXT_CSD_BUS_WIDTH_4 1 /* Card is in 4 bit mode */ #define EXT_CSD_BUS_WIDTH_8 2 /* Card is in 8 bit mode */ #define EXT_CSD_DDR_BUS_WIDTH_4 5 /* Card is in 4 bit DDR mode */ #define EXT_CSD_DDR_BUS_WIDTH_8 6 /* Card is in 8 bit DDR mode */ +#define EXT_CSD_BUS_WIDTH_STROBE BIT(7) /* Enhanced strobe mode */ #define EXT_CSD_TIMING_BC 0 /* Backwards compatility */ #define EXT_CSD_TIMING_HS 1 /* High speed */ -- cgit v1.2.3 From 5320226a051248b50cc2d80f2cb9599dfb56d422 Mon Sep 17 00:00:00 2001 From: Pratibhasagar V Date: Thu, 9 Jun 2016 18:09:31 -0400 Subject: mmc: core: Disable HPI for certain Hynix eMMC cards Certain Hynix eMMC 4.41 cards might get broken when HPI feature is used and hence this patch disables the HPI feature for such buggy cards. As some of the other features like BKOPs/Cache/Sanitize are dependent on HPI feature, those features would also get disabled if HPI is disabled. Signed-off-by: Pratibhasagar V Signed-off-by: Subhash Jadavani [gdavis: Forward port and cleanup] Signed-off-by: George G. Davis Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 22defc2a83b7..d8673ca968ba 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -280,6 +280,7 @@ struct mmc_card { #define MMC_QUIRK_SEC_ERASE_TRIM_BROKEN (1<<10) /* Skip secure for erase/trim */ #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ +#define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ unsigned int erase_size; /* erase size in sectors */ @@ -354,6 +355,9 @@ struct mmc_fixup { /* SDIO-specfic fields. You can use SDIO_ANY_ID here of course */ u16 cis_vendor, cis_device; + /* for MMC cards */ + unsigned int ext_csd_rev; + void (*vendor_fixup)(struct mmc_card *card, int data); int data; }; @@ -362,11 +366,20 @@ struct mmc_fixup { #define CID_OEMID_ANY ((unsigned short) -1) #define CID_NAME_ANY (NULL) +#define EXT_CSD_REV_ANY (-1u) + +#define CID_MANFID_SANDISK 0x2 +#define CID_MANFID_TOSHIBA 0x11 +#define CID_MANFID_MICRON 0x13 +#define CID_MANFID_SAMSUNG 0x15 +#define CID_MANFID_KINGSTON 0x70 +#define CID_MANFID_HYNIX 0x90 + #define END_FIXUP { NULL } #define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end, \ _cis_vendor, _cis_device, \ - _fixup, _data) \ + _fixup, _data, _ext_csd_rev) \ { \ .name = (_name), \ .manfid = (_manfid), \ @@ -377,23 +390,30 @@ struct mmc_fixup { .cis_device = (_cis_device), \ .vendor_fixup = (_fixup), \ .data = (_data), \ + .ext_csd_rev = (_ext_csd_rev), \ } #define MMC_FIXUP_REV(_name, _manfid, _oemid, _rev_start, _rev_end, \ - _fixup, _data) \ + _fixup, _data, _ext_csd_rev) \ _FIXUP_EXT(_name, _manfid, \ _oemid, _rev_start, _rev_end, \ SDIO_ANY_ID, SDIO_ANY_ID, \ - _fixup, _data) \ + _fixup, _data, _ext_csd_rev) \ #define MMC_FIXUP(_name, _manfid, _oemid, _fixup, _data) \ - MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data) + MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data, \ + EXT_CSD_REV_ANY) + +#define MMC_FIXUP_EXT_CSD_REV(_name, _manfid, _oemid, _fixup, _data, \ + _ext_csd_rev) \ + MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data, \ + _ext_csd_rev) #define SDIO_FIXUP(_vendor, _device, _fixup, _data) \ _FIXUP_EXT(CID_NAME_ANY, CID_MANFID_ANY, \ CID_OEMID_ANY, 0, -1ull, \ _vendor, _device, \ - _fixup, _data) \ + _fixup, _data, EXT_CSD_REV_ANY) \ #define cid_rev(hwrev, fwrev, year, month) \ (((u64) hwrev) << 40 | \ @@ -512,6 +532,11 @@ static inline int mmc_card_broken_irq_polling(const struct mmc_card *c) return c->quirks & MMC_QUIRK_BROKEN_IRQ_POLLING; } +static inline int mmc_card_broken_hpi(const struct mmc_card *c) +{ + return c->quirks & MMC_QUIRK_BROKEN_HPI; +} + #define mmc_card_name(c) ((c)->cid.prod_name) #define mmc_card_id(c) (dev_name(&(c)->dev)) -- cgit v1.2.3 From 1b8d79c5494484d140f2a19101412b51e2d5f6b5 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 21 Jun 2016 15:12:46 +0200 Subject: mmc: core: Allow hosts to specify non-support for SD commands There are host drivers which needs to valdiate for non-supported SD commands and returnn error code for such requests. To improve and simplify the behaviour, let's invent MMC_CAP2_NO_SD which these host drivers can set to tell the mmc core to skip sending SD commands during card initialization. Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index d72c0c34c21d..c22476d23b84 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -309,6 +309,7 @@ struct mmc_host { #define MMC_CAP2_NO_WRITE_PROTECT (1 << 18) /* No physical write protect pin, assume that card is always read-write */ #define MMC_CAP2_NO_SDIO (1 << 19) /* Do not send SDIO commands during initialization */ #define MMC_CAP2_HS400_ES (1 << 20) /* Host supports enhanced strobe */ +#define MMC_CAP2_NO_SD (1 << 21) /* Do not send SD commands during initialization */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From 16a34574c6ca12bb8fd73ae034acd5b536d3cdaa Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Tue, 21 Jun 2016 14:35:37 +0900 Subject: mmc: dw_mmc: remove the quirks flags Remove the quirks flag. (DW_MCI_QUIRK_BROKEN_DTO) For removing this, enabled the dto_timer by defaults. It doesn't see any I/O performance degression. In future, dwmmc controller should not use the quirks flag. Signed-off-by: Jaehoon Chung Reviewed-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index f7ed271a1d54..83b0edfce471 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -112,7 +112,6 @@ struct dw_mci_dma_slave { * @part_buf: Simple buffer for partial fifo reads/writes. * @push_data: Pointer to FIFO push function. * @pull_data: Pointer to FIFO pull function. - * @quirks: Set of quirks that apply to specific versions of the IP. * @vqmmc_enabled: Status of vqmmc, should be true or false. * @irq_flags: The flags to be passed to request_irq. * @irq: The irq value to be passed to request_irq. @@ -218,9 +217,6 @@ struct dw_mci { void (*push_data)(struct dw_mci *host, void *buf, int cnt); void (*pull_data)(struct dw_mci *host, void *buf, int cnt); - /* Workaround flags */ - u32 quirks; - bool vqmmc_enabled; unsigned long irq_flags; /* IRQ flags */ int irq; @@ -242,17 +238,12 @@ struct dw_mci_dma_ops { void (*exit)(struct dw_mci *host); }; -/* IP Quirks/flags. */ -/* Timer for broken data transfer over scheme */ -#define DW_MCI_QUIRK_BROKEN_DTO BIT(0) - struct dma_pdata; /* Board platform data */ struct dw_mci_board { u32 num_slots; - u32 quirks; /* Workaround / Quirk flags */ unsigned int bus_hz; /* Clock speed at the cclk_in pad */ u32 caps; /* Capabilities */ -- cgit v1.2.3 From a0c3b68c72a355f5dab33c3ddcd257e5a718de0c Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Fri, 1 Jul 2016 15:45:28 +0800 Subject: mmc: core: Allow hosts to specify non-support for MMC commands Host drivers which needs to valdiate for non-supported MMC commands and returnn error code for such requests. To improve and simplify the behaviour, let's invent MMC_CAP2_NO_MMC which these host drivers can set to tell the mmc core to skip sending MMC commands during card initialization. Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index c22476d23b84..aa4bfbf129e4 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -310,6 +310,7 @@ struct mmc_host { #define MMC_CAP2_NO_SDIO (1 << 19) /* Do not send SDIO commands during initialization */ #define MMC_CAP2_HS400_ES (1 << 20) /* Host supports enhanced strobe */ #define MMC_CAP2_NO_SD (1 << 21) /* Do not send SD commands during initialization */ +#define MMC_CAP2_NO_MMC (1 << 22) /* Do not send (e)MMC commands during initialization */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From d87fc96636884430278bc3b425a5a6e2c071a377 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Tue, 12 Jul 2016 15:46:15 +0800 Subject: mmc: sdhci-esdhc-imx: support setting tuning start point The delay cells of some SoCs may have less delay per one cell, for such SoCs, user could set the start delay cell point to bypass the first a few meaningless tuning commands. Acked-by: Adrian Hunter Signed-off-by: Dong Aisheng Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-esdhc-imx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index 95ccab3f454a..7daa78a2f342 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -46,5 +46,6 @@ struct esdhc_platform_data { bool support_vsel; unsigned int delay_line; unsigned int tuning_step; /* The delay cell steps in tuning procedure */ + unsigned int tuning_start_tap; /* The start delay cell point in tuning procedure */ }; #endif /* __ASM_ARCH_IMX_ESDHC_H */ -- cgit v1.2.3 From fbc872c38c8fed31948c85683b5326ee5ab9fccc Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Mon, 11 Jul 2016 15:45:51 +0100 Subject: xen/evtchn: add IOCTL_EVTCHN_RESTRICT IOCTL_EVTCHN_RESTRICT limits the file descriptor to being able to bind to interdomain event channels from a specific domain. Event channels that are already bound continue to work for sending and receiving notifications. This is useful as part of deprivileging a user space PV backend or device model (QEMU). e.g., Once the device model as bound to the ioreq server event channels it can restrict the file handle so an exploited DM cannot use it to create or bind to arbitrary event channels. Signed-off-by: David Vrabel Reviewed-by: Boris Ostrovsky --- include/uapi/xen/evtchn.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/xen/evtchn.h b/include/uapi/xen/evtchn.h index 14e833ee4e0b..cb4aa4bb905e 100644 --- a/include/uapi/xen/evtchn.h +++ b/include/uapi/xen/evtchn.h @@ -85,4 +85,19 @@ struct ioctl_evtchn_notify { #define IOCTL_EVTCHN_RESET \ _IOC(_IOC_NONE, 'E', 5, 0) +/* + * Restrict this file descriptor so that it can only be used to bind + * new interdomain events from one domain. + * + * Once a file descriptor has been restricted it cannot be + * de-restricted, and must be closed and re-opened. Event channels + * which were bound before restricting remain bound afterwards, and + * can be notified as usual. + */ +#define IOCTL_EVTCHN_RESTRICT_DOMID \ + _IOC(_IOC_NONE, 'E', 6, sizeof(struct ioctl_evtchn_restrict_domid)) +struct ioctl_evtchn_restrict_domid { + domid_t domid; +}; + #endif /* __LINUX_PUBLIC_EVTCHN_H__ */ -- cgit v1.2.3 From ef4d96ec4ad947360f48677b6007a4c77953b090 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 21 Jul 2016 23:53:31 +0100 Subject: spi: Split bus and I/O locking The current SPI code attempts to use bus_lock_mutex for two purposes. One is to implement spi_bus_lock() which grants exclusive access to the bus. The other is to serialize access to the physical hardware. This duplicate purpose causes confusion which leads to cases where access is not locked when a caller holds the bus lock mutex. Fix this by splitting out the I/O functionality into a new io_mutex. This means taking both mutexes in the DMA path, replacing the existing mutex with the new I/O one in the message pump (the mutex now always being taken in the message pump) and taking the bus lock mutex in spi_sync(), allowing __spi_sync() to have no mutex handling. While we're at it hoist the mutex further up the message pump before we power up the device so that all power up/down of the block is covered by it and there are no races with in-line pumping of messages. Reported-by: Rich Felker Tested-by: Rich Felker Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7b53af4ba5f8..072cb2aa2413 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -312,8 +312,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @flags: other constraints relevant to this driver * @max_transfer_size: function that returns the max transfer size for * a &spi_device; may be %NULL, so the default %SIZE_MAX will be used. + * @io_mutex: mutex for physical bus access * @bus_lock_spinlock: spinlock for SPI bus locking - * @bus_lock_mutex: mutex for SPI bus locking + * @bus_lock_mutex: mutex for exclusion of multiple callers * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use * @setup: updates the device mode and clocking records used by a * device's SPI controller; protocol code may call this. This @@ -446,6 +447,9 @@ struct spi_master { */ size_t (*max_transfer_size)(struct spi_device *spi); + /* I/O mutex */ + struct mutex io_mutex; + /* lock and mutex for SPI bus locking */ spinlock_t bus_lock_spinlock; struct mutex bus_lock_mutex; -- cgit v1.2.3 From 88e957d6e47f1232ad15b21e54a44f1147ea8c1b Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 30 Jun 2016 17:56:37 +0200 Subject: xen: introduce xen_vcpu_id mapping It may happen that Xen's and Linux's ideas of vCPU id diverge. In particular, when we crash on a secondary vCPU we may want to do kdump and unlike plain kexec where we do migrate_to_reboot_cpu() we try booting on the vCPU which crashed. This doesn't work very well for PVHVM guests as we have a number of hypercalls where we pass vCPU id as a parameter. These hypercalls either fail or do something unexpected. To solve the issue introduce percpu xen_vcpu_id mapping. ARM and PV guests get direct mapping for now. Boot CPU for PVHVM guest gets its id from CPUID. With secondary CPUs it is a bit more trickier. Currently, we initialize IPI vectors before these CPUs boot so we can't use CPUID. Use ACPI ids from MADT instead. Signed-off-by: Vitaly Kuznetsov Signed-off-by: David Vrabel --- include/xen/xen-ops.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 355275bad2cf..c9c532d56623 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -9,6 +9,12 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); +DECLARE_PER_CPU(int, xen_vcpu_id); +static inline int xen_vcpu_nr(int cpu) +{ + return per_cpu(xen_vcpu_id, cpu); +} + void xen_arch_pre_suspend(void); void xen_arch_post_suspend(int suspend_cancelled); -- cgit v1.2.3 From aa7145c16d6bf086538ad7eb20c807513bfa5efc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 22 Jul 2016 01:19:42 +0200 Subject: bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- include/linux/perf_event.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 36da0749205a..11134238417d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -211,7 +211,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f const struct bpf_func_proto *bpf_get_trace_printk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, - unsigned long len); + unsigned long off, unsigned long len); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e79e6c6fed89..15e55b7ee096 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -70,7 +70,7 @@ struct perf_callchain_entry_ctx { }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, - unsigned long len); + unsigned long off, unsigned long len); struct perf_raw_frag { union { -- cgit v1.2.3 From e16b46605960bd071a3e26f316e0bb600ae91e37 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 21 Jul 2016 21:40:28 -0600 Subject: PCI: Allow additional bus numbers for hotplug bridges A user may hot add a switch requiring more than one bus to enumerate. This previously required a system reboot if BIOS did not sufficiently pad the bus resource, which they frequently don't do. Add a kernel parameter so a user can specify the minimum number of bus numbers to reserve for a hotplug bridge's subordinate buses so rebooting won't be necessary. The default is 1, which is equivalent to previous behavior. Signed-off-by: Keith Busch Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index b67e4df20801..0c283254111d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1706,6 +1706,7 @@ extern u8 pci_cache_line_size; extern unsigned long pci_hotplug_io_size; extern unsigned long pci_hotplug_mem_size; +extern unsigned long pci_hotplug_bus_size; /* Architecture-specific versions may override these (weak) */ void pcibios_disable_device(struct pci_dev *dev); -- cgit v1.2.3 From 2ccbe2cb79f2f74ab739252299b6f9ff27586f2c Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Fri, 22 Jul 2016 15:07:56 +0200 Subject: macsec: limit ICV length to 16 octets IEEE 802.1AE-2006 standard recommends that the ICV element in a MACsec frame should not exceed 16 octets: add MACSEC_STD_ICV_LEN in uapi definitions accordingly, and avoid accepting configurations where the ICV length exceeds the standard value. Leave definition of MACSEC_MAX_ICV_LEN unchanged for backwards compatibility with userspace programs. Fixes: dece8d2b78d1 ("uapi: add MACsec bits") Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- include/uapi/linux/if_macsec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index f7d4831a2cc7..02fc49cb72d8 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -26,6 +26,8 @@ #define MACSEC_MIN_ICV_LEN 8 #define MACSEC_MAX_ICV_LEN 32 +/* upper limit for ICV length as recommended by IEEE802.1AE-2006 */ +#define MACSEC_STD_ICV_LEN 16 enum macsec_attrs { MACSEC_ATTR_UNSPEC, -- cgit v1.2.3 From ae76715d153e33c249b6850361e4d8d775388b5a Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Sun, 24 Jul 2016 16:12:39 +0300 Subject: net/mlx5e: Check the minimum inline header mode before xmit Each send queue (SQ) has inline mode that defines the minimal required inline headers in the SQ WQE. Before sending each packet check that the minimum required headers on the WQE are copied. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index e0a3ed758287..0b6d15cddb2f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -129,6 +129,13 @@ __mlx5_mask(typ, fld)) tmp; \ }) +enum mlx5_inline_modes { + MLX5_INLINE_MODE_NONE, + MLX5_INLINE_MODE_L2, + MLX5_INLINE_MODE_IP, + MLX5_INLINE_MODE_TCP_UDP, +}; + enum { MLX5_MAX_COMMANDS = 32, MLX5_CMD_DATA_BLOCK_SIZE = 512, -- cgit v1.2.3 From cff92d7c7ebd7ceddd4def6b39e0302585b1eb14 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Sun, 24 Jul 2016 16:12:40 +0300 Subject: net/mlx5e: Query minimum required header copy during xmit Add support for query the minimum inline mode from the Firmware. It is required for correct TX steering according to L3/L4 packet headers. Each send queue (SQ) has inline mode that defines the minimal required headers that needs to be copied into the SQ WQE. The driver asks the Firmware for the wqe_inline_mode device capability value. In case the device capability defined as "vport context" the driver must check the reported min inline mode from the vport context before creating its SQs. Signed-off-by: Hadar Hen Zion Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- include/linux/mlx5/vport.h | 2 ++ 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index d671e4e8e7db..21bc4557b67a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -536,7 +536,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 self_lb_en_modifiable[0x1]; u8 reserved_at_9[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_at_10[0x4]; + u8 reserved_at_10[0x2]; + u8 wqe_inline_mode[0x2]; u8 rss_ind_tbl_cap[0x4]; u8 reg_umr_sq[0x1]; u8 scatter_fcs[0x1]; @@ -2270,7 +2271,8 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_at_4[0x4]; + u8 reserved_at_4[0x1]; + u8 min_wqe_inline_mode[0x3]; u8 state[0x4]; u8 reg_umr[0x1]; u8 reserved_at_d[0x13]; @@ -2367,7 +2369,9 @@ struct mlx5_ifc_rmpc_bits { }; struct mlx5_ifc_nic_vport_context_bits { - u8 reserved_at_0[0x1f]; + u8 reserved_at_0[0x5]; + u8 min_wqe_inline_mode[0x3]; + u8 reserved_at_8[0x17]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 6c16c198f680..e087b7d047ac 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -43,6 +43,8 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); +void mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, + u8 *min_inline); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, u16 vport, u8 *addr); int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); -- cgit v1.2.3 From 9b8ac4f9dd60ac7375fb0e221dbf596db4c4e622 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Sun, 24 Jul 2016 19:24:09 +0100 Subject: gtp: #define #define _GTP_H_ and not #define _GTP_H Fix clang build warning: ./include/net/gtp.h:1:9: warning: '_GTP_H_' is used as a header guard here, followed by #define of a different macro [-Wheader-guard] fix by defining _GTP_H_ and not _GTP_H Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- include/net/gtp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/gtp.h b/include/net/gtp.h index 894a37b87d63..6398891b99ba 100644 --- a/include/net/gtp.h +++ b/include/net/gtp.h @@ -1,5 +1,5 @@ #ifndef _GTP_H_ -#define _GTP_H +#define _GTP_H_ /* General GTP protocol related definitions. */ -- cgit v1.2.3 From 86cb13e4ec5060d94069a8418fd4f3ccb38edee2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 25 Jul 2016 13:12:33 +0300 Subject: mlxsw: spectrum: Fix compilation error when CLS_ACT isn't set When CONFIG_NET_CLS_ACT isn't set 'struct tcf_exts' has no member named 'actions' and we therefore must not access it. Otherwise compilation fails. Fix this by introducing a new macro similar to tc_no_actions(), which always returns 'false' if CONFIG_NET_CLS_ACT isn't set. Fixes: 763b4b70afcd ("mlxsw: spectrum: Add support in matchall mirror TC offloading") Reported-by: kbuild test robot Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/net/act_api.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index fb82b5b5d9e7..0bb210635e5f 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -192,6 +192,9 @@ int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); #define tc_for_each_action(_a, _exts) \ list_for_each_entry(a, &(_exts)->actions, list) +#define tc_single_action(_exts) \ + (list_is_singular(&(_exts)->actions)) + static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 lastuse) { @@ -205,6 +208,7 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #define tc_no_actions(_exts) true #define tc_for_each_action(_a, _exts) while ((void)(_a), 0) +#define tc_single_action(_exts) false #define tcf_action_stats_update(a, bytes, packets, lastuse) #endif /* CONFIG_NET_CLS_ACT */ -- cgit v1.2.3 From 96ae52279594470622ff0585621a13e96b700600 Mon Sep 17 00:00:00 2001 From: Sargun Dhillon Date: Mon, 25 Jul 2016 05:54:46 -0700 Subject: bpf: Add bpf_probe_write_user BPF helper to be called in tracers This allows user memory to be written to during the course of a kprobe. It shouldn't be used to implement any kind of security mechanism because of TOC-TOU attacks, but rather to debug, divert, and manipulate execution of semi-cooperative processes. Although it uses probe_kernel_write, we limit the address space the probe can write into by checking the space with access_ok. We do this as opposed to calling copy_to_user directly, in order to avoid sleeping. In addition we ensure the threads's current fs / segment is USER_DS and the thread isn't exiting nor a kernel thread. Given this feature is meant for experiments, and it has a risk of crashing the system, and running programs, we print a warning on when a proglet that attempts to use this helper is installed, along with the pid and process name. Signed-off-by: Sargun Dhillon Cc: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2b7076f5b5ad..da218fec6056 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -365,6 +365,16 @@ enum bpf_func_id { */ BPF_FUNC_get_current_task, + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From a85a970af265f156740977168b542234511b28a8 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 25 Jul 2016 16:09:41 -0700 Subject: net_sched: move tc_action into tcf_common struct tc_action is confusing, currently we use it for two purposes: 1) Pass in arguments and carry out results from helper functions 2) A generic representation for tc actions The first one is error-prone, since we need to make sure we don't miss anything. This patch aims to get rid of this use, by moving tc_action into tcf_common, so that they are allocated together in hashtable and can be cast'ed easily. And together with the following patch, we could really make tc_action a generic representation for all tc actions and each type of action can inherit from it. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/act_api.h | 52 ++++++++++++++++++++++------------------ include/net/tc_act/tc_bpf.h | 3 +-- include/net/tc_act/tc_connmark.h | 3 +-- include/net/tc_act/tc_csum.h | 3 +-- include/net/tc_act/tc_defact.h | 3 +-- include/net/tc_act/tc_gact.h | 5 ++-- include/net/tc_act/tc_ife.h | 3 +-- include/net/tc_act/tc_ipt.h | 3 +-- include/net/tc_act/tc_mirred.h | 3 +-- include/net/tc_act/tc_nat.h | 5 +--- include/net/tc_act/tc_pedit.h | 3 +-- include/net/tc_act/tc_skbedit.h | 3 +-- include/net/tc_act/tc_vlan.h | 3 +-- 13 files changed, 42 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 0bb210635e5f..8b199095ea51 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -10,7 +10,26 @@ #include #include + +struct tcf_hashinfo { + struct hlist_head *htab; + unsigned int hmask; + spinlock_t lock; + u32 index; +}; + +struct tc_action_ops; + +struct tc_action { + const struct tc_action_ops *ops; + __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ + __u32 order; + struct list_head list; + struct tcf_hashinfo *hinfo; +}; + struct tcf_common { + struct tc_action tcfc_act; struct hlist_node tcfc_head; u32 tcfc_index; int tcfc_refcnt; @@ -26,6 +45,7 @@ struct tcf_common { struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; }; +#define tcf_act common.tcfc_act #define tcf_head common.tcfc_head #define tcf_index common.tcfc_index #define tcf_refcnt common.tcfc_refcnt @@ -39,13 +59,6 @@ struct tcf_common { #define tcf_lock common.tcfc_lock #define tcf_rcu common.tcfc_rcu -struct tcf_hashinfo { - struct hlist_head *htab; - unsigned int hmask; - spinlock_t lock; - u32 index; -}; - static inline unsigned int tcf_hash(u32 index, unsigned int hmask) { return index & hmask; @@ -88,15 +101,6 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) dtm->expires = jiffies_to_clock_t(stm->expires); } -struct tc_action { - void *priv; - const struct tc_action_ops *ops; - __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ - __u32 order; - struct list_head list; - struct tcf_hashinfo *hinfo; -}; - #ifdef CONFIG_NET_CLS_ACT #define ACT_P_CREATED 1 @@ -106,17 +110,18 @@ struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; __u32 type; /* TBD to match kind */ + size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *, int bind); - int (*lookup)(struct net *, struct tc_action *, u32); + int (*lookup)(struct net *, struct tc_action **, u32); int (*init)(struct net *net, struct nlattr *nla, - struct nlattr *est, struct tc_action *act, int ovr, + struct nlattr *est, struct tc_action **act, int ovr, int bind); int (*walk)(struct net *, struct sk_buff *, - struct netlink_callback *, int, struct tc_action *); + struct netlink_callback *, int, const struct tc_action_ops *); void (*stats_update)(struct tc_action *, u64, u32, u64); }; @@ -152,13 +157,14 @@ static inline void tc_action_net_exit(struct tc_action_net *tn) int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct netlink_callback *cb, int type, - struct tc_action *a); -int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index); + const struct tc_action_ops *ops); +int tcf_hash_search(struct tc_action_net *tn, struct tc_action **a, u32 index); u32 tcf_hash_new_index(struct tc_action_net *tn); -bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, +bool tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action **a, int bind); int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, - struct tc_action *a, int size, int bind, bool cpustats); + struct tc_action **a, const struct tc_action_ops *ops, int bind, + bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a); diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h index 958d69cfb19c..80a4d6f49773 100644 --- a/include/net/tc_act/tc_bpf.h +++ b/include/net/tc_act/tc_bpf.h @@ -23,7 +23,6 @@ struct tcf_bpf { struct sock_filter *bpf_ops; const char *bpf_name; }; -#define to_bpf(a) \ - container_of(a->priv, struct tcf_bpf, common) +#define to_bpf(a) ((struct tcf_bpf *)a) #endif /* __NET_TC_BPF_H */ diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h index 02caa406611b..8a661135f4ac 100644 --- a/include/net/tc_act/tc_connmark.h +++ b/include/net/tc_act/tc_connmark.h @@ -9,7 +9,6 @@ struct tcf_connmark_info { u16 zone; }; -#define to_connmark(a) \ - container_of(a->priv, struct tcf_connmark_info, common) +#define to_connmark(a) ((struct tcf_connmark_info *)a) #endif /* __NET_TC_CONNMARK_H */ diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index fa8f5fac65e9..1a9ef15d573b 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -9,7 +9,6 @@ struct tcf_csum { u32 update_flags; }; -#define to_tcf_csum(a) \ - container_of(a->priv,struct tcf_csum,common) +#define to_tcf_csum(a) ((struct tcf_csum *)a) #endif /* __NET_TC_CSUM_H */ diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h index ab9b5d6be67b..e25b4eb4fc66 100644 --- a/include/net/tc_act/tc_defact.h +++ b/include/net/tc_act/tc_defact.h @@ -8,7 +8,6 @@ struct tcf_defact { u32 tcfd_datalen; void *tcfd_defdata; }; -#define to_defact(a) \ - container_of(a->priv, struct tcf_defact, common) +#define to_defact(a) ((struct tcf_defact *)a) #endif /* __NET_TC_DEF_H */ diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 93c520b83d10..119cdb418c23 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -13,8 +13,7 @@ struct tcf_gact { atomic_t packets; #endif }; -#define to_gact(a) \ - container_of(a->priv, struct tcf_gact, common) +#define to_gact(a) ((struct tcf_gact *)a) static inline bool is_tcf_gact_shot(const struct tc_action *a) { @@ -24,7 +23,7 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a) if (a->ops && a->ops->type != TCA_ACT_GACT) return false; - gact = a->priv; + gact = to_gact(a); if (gact->tcf_action == TC_ACT_SHOT) return true; diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index c55facd17b7e..7921abe42adc 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -16,8 +16,7 @@ struct tcf_ife_info { /* list of metaids allowed */ struct list_head metalist; }; -#define to_ife(a) \ - container_of(a->priv, struct tcf_ife_info, common) +#define to_ife(a) ((struct tcf_ife_info *)a) struct tcf_meta_info { const struct tcf_meta_ops *ops; diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h index c0f4193f432c..c22ae7ab66ed 100644 --- a/include/net/tc_act/tc_ipt.h +++ b/include/net/tc_act/tc_ipt.h @@ -11,7 +11,6 @@ struct tcf_ipt { char *tcfi_tname; struct xt_entry_target *tcfi_t; }; -#define to_ipt(a) \ - container_of(a->priv, struct tcf_ipt, common) +#define to_ipt(a) ((struct tcf_ipt *)a) #endif /* __NET_TC_IPT_H */ diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 6a13a7c74e0c..89aebd22cd79 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -12,8 +12,7 @@ struct tcf_mirred { struct net_device __rcu *tcfm_dev; struct list_head tcfm_list; }; -#define to_mirred(a) \ - container_of(a->priv, struct tcf_mirred, common) +#define to_mirred(a) ((struct tcf_mirred *)a) static inline bool is_tcf_mirred_redirect(const struct tc_action *a) { diff --git a/include/net/tc_act/tc_nat.h b/include/net/tc_act/tc_nat.h index 63d8e9ca9d99..a91ad3ad565e 100644 --- a/include/net/tc_act/tc_nat.h +++ b/include/net/tc_act/tc_nat.h @@ -13,9 +13,6 @@ struct tcf_nat { u32 flags; }; -static inline struct tcf_nat *to_tcf_nat(struct tc_action *a) -{ - return container_of(a->priv, struct tcf_nat, common); -} +#define to_tcf_nat(a) ((struct tcf_nat *)a) #endif /* __NET_TC_NAT_H */ diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 5b80998879c7..2cccfbaae800 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -9,7 +9,6 @@ struct tcf_pedit { unsigned char tcfp_flags; struct tc_pedit_key *tcfp_keys; }; -#define to_pedit(a) \ - container_of(a->priv, struct tcf_pedit, common) +#define to_pedit(a) ((struct tcf_pedit *)a) #endif /* __NET_TC_PED_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index d01a5d40cfb5..9e0548998327 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -30,8 +30,7 @@ struct tcf_skbedit { u16 queue_mapping; u16 ptype; }; -#define to_skbedit(a) \ - container_of(a->priv, struct tcf_skbedit, common) +#define to_skbedit(a) ((struct tcf_skbedit *)a) /* Return true iff action is mark */ static inline bool is_tcf_skbedit_mark(const struct tc_action *a) diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 93b70ade1ff3..584b80788d52 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -21,7 +21,6 @@ struct tcf_vlan { u16 tcfv_push_vid; __be16 tcfv_push_proto; }; -#define to_vlan(a) \ - container_of(a->priv, struct tcf_vlan, common) +#define to_vlan(a) ((struct tcf_vlan *)a) #endif /* __NET_TC_VLAN_H */ -- cgit v1.2.3 From ec0595cc4495be579309b4bfd5e997af0f2ae6f9 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Mon, 25 Jul 2016 16:09:42 -0700 Subject: net_sched: get rid of struct tcf_common After the previous patch, struct tc_action should be enough to represent the generic tc action, tcf_common is not necessary any more. This patch gets rid of it to make tc action code more readable. Cc: Jamal Hadi Salim Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/act_api.h | 63 +++++++++++++++++++--------------------- include/net/tc_act/tc_bpf.h | 2 +- include/net/tc_act/tc_connmark.h | 2 +- include/net/tc_act/tc_csum.h | 2 +- include/net/tc_act/tc_defact.h | 2 +- include/net/tc_act/tc_gact.h | 2 +- include/net/tc_act/tc_ife.h | 2 +- include/net/tc_act/tc_ipt.h | 2 +- include/net/tc_act/tc_mirred.h | 2 +- include/net/tc_act/tc_nat.h | 2 +- include/net/tc_act/tc_pedit.h | 2 +- include/net/tc_act/tc_skbedit.h | 2 +- include/net/tc_act/tc_vlan.h | 2 +- 13 files changed, 42 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 8b199095ea51..41e6a24a44b9 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -22,42 +22,39 @@ struct tc_action_ops; struct tc_action { const struct tc_action_ops *ops; - __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ - __u32 order; - struct list_head list; - struct tcf_hashinfo *hinfo; -}; - -struct tcf_common { - struct tc_action tcfc_act; - struct hlist_node tcfc_head; - u32 tcfc_index; - int tcfc_refcnt; - int tcfc_bindcnt; - u32 tcfc_capab; - int tcfc_action; - struct tcf_t tcfc_tm; - struct gnet_stats_basic_packed tcfc_bstats; - struct gnet_stats_queue tcfc_qstats; - struct gnet_stats_rate_est64 tcfc_rate_est; - spinlock_t tcfc_lock; - struct rcu_head tcfc_rcu; + __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ + __u32 order; + struct list_head list; + struct tcf_hashinfo *hinfo; + + struct hlist_node tcfa_head; + u32 tcfa_index; + int tcfa_refcnt; + int tcfa_bindcnt; + u32 tcfa_capab; + int tcfa_action; + struct tcf_t tcfa_tm; + struct gnet_stats_basic_packed tcfa_bstats; + struct gnet_stats_queue tcfa_qstats; + struct gnet_stats_rate_est64 tcfa_rate_est; + spinlock_t tcfa_lock; + struct rcu_head tcfa_rcu; struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; }; -#define tcf_act common.tcfc_act -#define tcf_head common.tcfc_head -#define tcf_index common.tcfc_index -#define tcf_refcnt common.tcfc_refcnt -#define tcf_bindcnt common.tcfc_bindcnt -#define tcf_capab common.tcfc_capab -#define tcf_action common.tcfc_action -#define tcf_tm common.tcfc_tm -#define tcf_bstats common.tcfc_bstats -#define tcf_qstats common.tcfc_qstats -#define tcf_rate_est common.tcfc_rate_est -#define tcf_lock common.tcfc_lock -#define tcf_rcu common.tcfc_rcu +#define tcf_act common.tcfa_act +#define tcf_head common.tcfa_head +#define tcf_index common.tcfa_index +#define tcf_refcnt common.tcfa_refcnt +#define tcf_bindcnt common.tcfa_bindcnt +#define tcf_capab common.tcfa_capab +#define tcf_action common.tcfa_action +#define tcf_tm common.tcfa_tm +#define tcf_bstats common.tcfa_bstats +#define tcf_qstats common.tcfa_qstats +#define tcf_rate_est common.tcfa_rate_est +#define tcf_lock common.tcfa_lock +#define tcf_rcu common.tcfa_rcu static inline unsigned int tcf_hash(u32 index, unsigned int hmask) { diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h index 80a4d6f49773..2b94673a3dbc 100644 --- a/include/net/tc_act/tc_bpf.h +++ b/include/net/tc_act/tc_bpf.h @@ -14,7 +14,7 @@ #include struct tcf_bpf { - struct tcf_common common; + struct tc_action common; struct bpf_prog __rcu *filter; union { u32 bpf_fd; diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h index 8a661135f4ac..59b515d32bb4 100644 --- a/include/net/tc_act/tc_connmark.h +++ b/include/net/tc_act/tc_connmark.h @@ -4,7 +4,7 @@ #include struct tcf_connmark_info { - struct tcf_common common; + struct tc_action common; struct net *net; u16 zone; }; diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 1a9ef15d573b..f31fb6331a53 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -5,7 +5,7 @@ #include struct tcf_csum { - struct tcf_common common; + struct tc_action common; u32 update_flags; }; diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h index e25b4eb4fc66..d47f040a3bdf 100644 --- a/include/net/tc_act/tc_defact.h +++ b/include/net/tc_act/tc_defact.h @@ -4,7 +4,7 @@ #include struct tcf_defact { - struct tcf_common common; + struct tc_action common; u32 tcfd_datalen; void *tcfd_defdata; }; diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 119cdb418c23..b6f173910226 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -5,7 +5,7 @@ #include struct tcf_gact { - struct tcf_common common; + struct tc_action common; #ifdef CONFIG_GACT_PROB u16 tcfg_ptype; u16 tcfg_pval; diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index 7921abe42adc..5164bd7a38fb 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -8,7 +8,7 @@ #define IFE_METAHDRLEN 2 struct tcf_ife_info { - struct tcf_common common; + struct tc_action common; u8 eth_dst[ETH_ALEN]; u8 eth_src[ETH_ALEN]; u16 eth_type; diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h index c22ae7ab66ed..31309766e379 100644 --- a/include/net/tc_act/tc_ipt.h +++ b/include/net/tc_act/tc_ipt.h @@ -6,7 +6,7 @@ struct xt_entry_target; struct tcf_ipt { - struct tcf_common common; + struct tc_action common; u32 tcfi_hook; char *tcfi_tname; struct xt_entry_target *tcfi_t; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 89aebd22cd79..62770add15bd 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -5,7 +5,7 @@ #include struct tcf_mirred { - struct tcf_common common; + struct tc_action common; int tcfm_eaction; int tcfm_ifindex; int tcfm_ok_push; diff --git a/include/net/tc_act/tc_nat.h b/include/net/tc_act/tc_nat.h index a91ad3ad565e..56681a320612 100644 --- a/include/net/tc_act/tc_nat.h +++ b/include/net/tc_act/tc_nat.h @@ -5,7 +5,7 @@ #include struct tcf_nat { - struct tcf_common common; + struct tc_action common; __be32 old_addr; __be32 new_addr; diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 2cccfbaae800..29e38d6823df 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -4,7 +4,7 @@ #include struct tcf_pedit { - struct tcf_common common; + struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; struct tc_pedit_key *tcfp_keys; diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 9e0548998327..5767e9dbcf92 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -23,7 +23,7 @@ #include struct tcf_skbedit { - struct tcf_common common; + struct tc_action common; u32 flags; u32 priority; u32 mark; diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 584b80788d52..e29f52e8bdf1 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -16,7 +16,7 @@ #define VLAN_F_PUSH 0x2 struct tcf_vlan { - struct tcf_common common; + struct tc_action common; int tcfv_action; u16 tcfv_push_vid; __be16 tcfv_push_proto; -- cgit v1.2.3 From 7af7c616fa2f1ce6c0d806b89898d2df098b4bd8 Mon Sep 17 00:00:00 2001 From: Hans van Kranenburg Date: Sun, 3 Jul 2016 23:23:06 +0200 Subject: Btrfs: use the correct struct for BTRFS_IOC_LOGICAL_INO BTRFS_IOC_LOGICAL_INO takes a btrfs_ioctl_logical_ino_args as argument, not a btrfs_ioctl_ino_path_args. The lines were probably copy/pasted when the code was written. Since btrfs_ioctl_logical_ino_args and btrfs_ioctl_ino_path_args have the same size, the actual IOCTL definition here does not change. But, it makes the code less confusing for the reader. Signed-off-by: Hans van Kranenburg Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 2bdd1e3e7007..ac5eacd3055b 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -798,7 +798,7 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ - struct btrfs_ioctl_ino_path_args) + struct btrfs_ioctl_logical_ino_args) #define BTRFS_IOC_SET_RECEIVED_SUBVOL _IOWR(BTRFS_IOCTL_MAGIC, 37, \ struct btrfs_ioctl_received_subvol_args) #define BTRFS_IOC_SEND _IOW(BTRFS_IOCTL_MAGIC, 38, struct btrfs_ioctl_send_args) -- cgit v1.2.3 From bc074524e123ded281cde25ebc5661910f9679e3 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 9 Jun 2016 17:27:55 -0400 Subject: btrfs: prefix fsid to all trace events When using trace events to debug a problem, it's impossible to determine which file system generated a particular event. This patch adds a macro to prefix standard information to the head of a trace event. The extent_state alloc/free events are all that's left without an fs_info available. Signed-off-by: Jeff Mahoney Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 295 +++++++++++++++++++++++-------------------- 1 file changed, 159 insertions(+), 136 deletions(-) (limited to 'include') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 5b81ef304388..e030d6f6c19a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -66,6 +66,21 @@ struct btrfs_qgroup_extent_record; { BTRFS_BLOCK_GROUP_RAID6, "RAID6"} #define BTRFS_UUID_SIZE 16 +#define TP_STRUCT__entry_fsid __array(u8, fsid, BTRFS_UUID_SIZE) + +#define TP_fast_assign_fsid(fs_info) \ + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE) + +#define TP_STRUCT__entry_btrfs(args...) \ + TP_STRUCT__entry( \ + TP_STRUCT__entry_fsid \ + args) +#define TP_fast_assign_btrfs(fs_info, args...) \ + TP_fast_assign( \ + TP_fast_assign_fsid(fs_info); \ + args) +#define TP_printk_btrfs(fmt, args...) \ + TP_printk("%pU: " fmt, __entry->fsid, args) TRACE_EVENT(btrfs_transaction_commit, @@ -73,17 +88,17 @@ TRACE_EVENT(btrfs_transaction_commit, TP_ARGS(root), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, generation ) __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->generation = root->fs_info->generation; __entry->root_objectid = root->root_key.objectid; ), - TP_printk("root = %llu(%s), gen = %llu", + TP_printk_btrfs("root = %llu(%s), gen = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->generation) ); @@ -94,7 +109,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, TP_ARGS(inode), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( blkcnt_t, blocks ) __field( u64, disk_i_size ) @@ -104,7 +119,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->blocks = inode->i_blocks; __entry->disk_i_size = BTRFS_I(inode)->disk_i_size; @@ -115,7 +130,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, " + TP_printk_btrfs("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, " "disk_i_size = %llu, last_trans = %llu, logged_trans = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->generation, @@ -175,7 +190,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, TP_CONDITION(map), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, start ) __field( u64, len ) @@ -187,7 +202,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, __field( unsigned int, compress_type ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->start = map->start; __entry->len = map->len; @@ -199,7 +214,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, __entry->compress_type = map->compress_type; ), - TP_printk("root = %llu(%s), start = %llu, len = %llu, " + TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu, " "orig_start = %llu, block_start = %llu(%s), " "block_len = %llu, flags = %s, refs = %u, " "compress_type = %u", @@ -233,7 +248,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, TP_ARGS(inode, ordered), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( u64, file_offset ) __field( u64, start ) @@ -246,7 +261,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->file_offset = ordered->file_offset; __entry->start = ordered->start; @@ -260,7 +275,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %llu, file_offset = %llu, " + TP_printk_btrfs("root = %llu(%s), ino = %llu, file_offset = %llu, " "start = %llu, len = %llu, disk_len = %llu, " "bytes_left = %llu, flags = %s, compress_type = %d, " "refs = %d", @@ -310,7 +325,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, TP_ARGS(page, inode, wbc), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( pgoff_t, index ) __field( long, nr_to_write ) @@ -324,7 +339,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->index = page->index; __entry->nr_to_write = wbc->nr_to_write; @@ -339,7 +354,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, " + TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, " "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, " "range_end = %llu, for_kupdate = %d, " "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu", @@ -366,7 +381,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, TP_ARGS(page, start, end, uptodate), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( pgoff_t, index ) __field( u64, start ) @@ -375,7 +390,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(page->mapping->host->i_sb), __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; __entry->start = start; @@ -385,7 +400,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, BTRFS_I(page->mapping->host)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, " + TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, " "end = %llu, uptodate = %d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->index, @@ -399,7 +414,7 @@ TRACE_EVENT(btrfs_sync_file, TP_ARGS(file, datasync), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) @@ -410,6 +425,7 @@ TRACE_EVENT(btrfs_sync_file, struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); + TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); __entry->ino = inode->i_ino; __entry->parent = d_inode(dentry->d_parent)->i_ino; __entry->datasync = datasync; @@ -417,7 +433,7 @@ TRACE_EVENT(btrfs_sync_file, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d", + TP_printk_btrfs("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->parent, __entry->datasync) @@ -425,19 +441,19 @@ TRACE_EVENT(btrfs_sync_file, TRACE_EVENT(btrfs_sync_fs, - TP_PROTO(int wait), + TP_PROTO(struct btrfs_fs_info *fs_info, int wait), - TP_ARGS(wait), + TP_ARGS(fs_info, wait), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( int, wait ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->wait = wait; ), - TP_printk("wait = %d", __entry->wait) + TP_printk_btrfs("wait = %d", __entry->wait) ); TRACE_EVENT(btrfs_add_block_group, @@ -490,13 +506,14 @@ TRACE_EVENT(btrfs_add_block_group, DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action), + TP_ARGS(fs_info, ref, full_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) @@ -507,7 +524,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, __field( u64, seq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; @@ -518,7 +535,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, __entry->seq = ref->seq; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " "parent = %llu(%s), ref_root = %llu(%s), level = %d, " "type = %s, seq = %llu", (unsigned long long)__entry->bytenr, @@ -532,31 +549,34 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, DEFINE_EVENT(btrfs_delayed_tree_ref, add_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DEFINE_EVENT(btrfs_delayed_tree_ref, run_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action), + TP_ARGS(fs_info, ref, full_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) @@ -568,7 +588,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, __field( u64, seq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; @@ -580,7 +600,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, __entry->seq = ref->seq; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " "parent = %llu(%s), ref_root = %llu(%s), owner = %llu, " "offset = %llu, type = %s, seq = %llu", (unsigned long long)__entry->bytenr, @@ -596,45 +616,48 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, DEFINE_EVENT(btrfs_delayed_data_ref, add_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DEFINE_EVENT(btrfs_delayed_data_ref, run_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action), + TP_ARGS(fs_info, ref, head_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) __field( int, is_data ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; __entry->is_data = head_ref->is_data; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d", + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes, show_ref_action(__entry->action), @@ -643,20 +666,22 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, DEFINE_EVENT(btrfs_delayed_ref_head, add_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action) + TP_ARGS(fs_info, ref, head_ref, action) ); DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action) + TP_ARGS(fs_info, ref, head_ref, action) ); #define show_chunk_type(type) \ @@ -678,7 +703,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, TP_ARGS(root, map, offset, size), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( int, num_stripes ) __field( u64, type ) __field( int, sub_stripes ) @@ -687,7 +712,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->num_stripes = map->num_stripes; __entry->type = map->type; __entry->sub_stripes = map->sub_stripes; @@ -696,7 +721,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, __entry->root_objectid = root->root_key.objectid; ), - TP_printk("root = %llu(%s), offset = %llu, size = %llu, " + TP_printk_btrfs("root = %llu(%s), offset = %llu, size = %llu, " "num_stripes = %d, sub_stripes = %d, type = %s", show_root_type(__entry->root_objectid), (unsigned long long)__entry->offset, @@ -728,7 +753,7 @@ TRACE_EVENT(btrfs_cow_block, TP_ARGS(root, buf, cow), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, buf_start ) __field( int, refs ) @@ -737,7 +762,7 @@ TRACE_EVENT(btrfs_cow_block, __field( int, cow_level ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->buf_start = buf->start; __entry->refs = atomic_read(&buf->refs); @@ -746,7 +771,7 @@ TRACE_EVENT(btrfs_cow_block, __entry->cow_level = btrfs_header_level(cow); ), - TP_printk("root = %llu(%s), refs = %d, orig_buf = %llu " + TP_printk_btrfs("root = %llu(%s), refs = %d, orig_buf = %llu " "(orig_level = %d), cow_buf = %llu (cow_level = %d)", show_root_type(__entry->root_objectid), __entry->refs, @@ -763,25 +788,23 @@ TRACE_EVENT(btrfs_space_reservation, TP_ARGS(fs_info, type, val, bytes, reserve), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) + TP_STRUCT__entry_btrfs( __string( type, type ) __field( u64, val ) __field( u64, bytes ) __field( int, reserve ) ), - TP_fast_assign( - memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(fs_info, __assign_str(type, type); __entry->val = val; __entry->bytes = bytes; __entry->reserve = reserve; ), - TP_printk("%pU: %s: %Lu %s %Lu", __entry->fsid, __get_str(type), - __entry->val, __entry->reserve ? "reserve" : "release", - __entry->bytes) + TP_printk_btrfs("%s: %Lu %s %Lu", __get_str(type), __entry->val, + __entry->reserve ? "reserve" : "release", + __entry->bytes) ); #define show_flush_action(action) \ @@ -872,22 +895,19 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_ARGS(root, start, len), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) - __field( u64, root_objectid ) - __field( u64, start ) - __field( u64, len ) + TP_STRUCT__entry_btrfs( + __field( u64, root_objectid ) + __field( u64, start ) + __field( u64, len ) ), - TP_fast_assign( - memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->start = start; __entry->len = len; ), - TP_printk("%pU: root = %llu(%s), start = %llu, len = %llu", - __entry->fsid, + TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->start, (unsigned long long)__entry->len) @@ -914,21 +934,21 @@ TRACE_EVENT(find_free_extent, TP_ARGS(root, num_bytes, empty_size, data), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, data ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = num_bytes; __entry->empty_size = empty_size; __entry->data = data; ), - TP_printk("root = %Lu(%s), len = %Lu, empty_size = %Lu, " + TP_printk_btrfs("root = %Lu(%s), len = %Lu, empty_size = %Lu, " "flags = %Lu(%s)", show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->data, __print_flags((unsigned long)__entry->data, "|", @@ -943,8 +963,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, TP_ARGS(root, block_group, start, len), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, bg_objectid ) __field( u64, flags ) @@ -952,8 +971,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __field( u64, len ) ), - TP_fast_assign( - memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; @@ -961,8 +979,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __entry->len = len; ), - TP_printk("%pU: root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " - "start = %Lu, len = %Lu", __entry->fsid, + TP_printk_btrfs("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " + "start = %Lu, len = %Lu", show_root_type(__entry->root_objectid), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), @@ -994,7 +1012,7 @@ TRACE_EVENT(btrfs_find_cluster, TP_ARGS(block_group, start, bytes, empty_size, min_bytes), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) @@ -1003,7 +1021,7 @@ TRACE_EVENT(btrfs_find_cluster, __field( u64, min_bytes ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; __entry->start = start; @@ -1012,7 +1030,7 @@ TRACE_EVENT(btrfs_find_cluster, __entry->min_bytes = min_bytes; ), - TP_printk("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu," + TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu," " empty_size = %Lu, min_bytes = %Lu", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", @@ -1026,15 +1044,15 @@ TRACE_EVENT(btrfs_failed_cluster_setup, TP_ARGS(block_group), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; ), - TP_printk("block_group = %Lu", __entry->bg_objectid) + TP_printk_btrfs("block_group = %Lu", __entry->bg_objectid) ); TRACE_EVENT(btrfs_setup_cluster, @@ -1044,7 +1062,7 @@ TRACE_EVENT(btrfs_setup_cluster, TP_ARGS(block_group, cluster, size, bitmap), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) @@ -1053,7 +1071,7 @@ TRACE_EVENT(btrfs_setup_cluster, __field( int, bitmap ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; __entry->start = cluster->window_start; @@ -1062,7 +1080,7 @@ TRACE_EVENT(btrfs_setup_cluster, __entry->bitmap = bitmap; ), - TP_printk("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, " + TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, " "size = %Lu, max_size = %Lu, bitmap = %d", __entry->bg_objectid, __entry->flags, @@ -1120,7 +1138,7 @@ DECLARE_EVENT_CLASS(btrfs__work, TP_ARGS(work), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, work ) __field( void *, wq ) __field( void *, func ) @@ -1129,7 +1147,7 @@ DECLARE_EVENT_CLASS(btrfs__work, __field( void *, normal_work ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_work_owner(work), __entry->work = work; __entry->wq = work->wq; __entry->func = work->func; @@ -1138,7 +1156,7 @@ DECLARE_EVENT_CLASS(btrfs__work, __entry->normal_work = &work->normal_work; ), - TP_printk("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p," + TP_printk_btrfs("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p," " ordered_free=%p", __entry->work, __entry->normal_work, __entry->wq, __entry->func, __entry->ordered_func, __entry->ordered_free) @@ -1151,15 +1169,15 @@ DECLARE_EVENT_CLASS(btrfs__work__done, TP_ARGS(work), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, work ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_work_owner(work), __entry->work = work; ), - TP_printk("work->%p", __entry->work) + TP_printk_btrfs("work->%p", __entry->work) ); DEFINE_EVENT(btrfs__work, btrfs_work_queued, @@ -1196,19 +1214,19 @@ DECLARE_EVENT_CLASS(btrfs__workqueue, TP_ARGS(wq, name, high), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, wq ) __string( name, name ) __field( int , high ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); __entry->high = high; ), - TP_printk("name=%s%s, wq=%p", __get_str(name), + TP_printk_btrfs("name=%s%s, wq=%p", __get_str(name), __print_flags(__entry->high, "", {(WQ_HIGHPRI), "-high"}), __entry->wq) @@ -1227,15 +1245,15 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_ARGS(wq), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, wq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; ), - TP_printk("wq=%p", __entry->wq) + TP_printk_btrfs("wq=%p", __entry->wq) ); DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, @@ -1251,19 +1269,19 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_data_map, TP_ARGS(inode, free_reserved), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, rootid ) __field( unsigned long, ino ) __field( u64, free_reserved ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->rootid = BTRFS_I(inode)->root->objectid; __entry->ino = inode->i_ino; __entry->free_reserved = free_reserved; ), - TP_printk("rootid=%llu, ino=%lu, free_reserved=%llu", + TP_printk_btrfs("rootid=%llu, ino=%lu, free_reserved=%llu", __entry->rootid, __entry->ino, __entry->free_reserved) ); @@ -1292,7 +1310,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, TP_ARGS(inode, start, len, reserved, op), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, rootid ) __field( unsigned long, ino ) __field( u64, start ) @@ -1301,7 +1319,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, __field( int, op ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->rootid = BTRFS_I(inode)->root->objectid; __entry->ino = inode->i_ino; __entry->start = start; @@ -1310,7 +1328,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, __entry->op = op; ), - TP_printk("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s", + TP_printk_btrfs("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s", __entry->rootid, __entry->ino, __entry->start, __entry->len, __entry->reserved, __print_flags((unsigned long)__entry->op, "", @@ -1334,86 +1352,90 @@ DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data, DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref, - TP_PROTO(u64 ref_root, u64 reserved), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 ref_root, u64 reserved), - TP_ARGS(ref_root, reserved), + TP_ARGS(fs_info, ref_root, reserved), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, ref_root ) __field( u64, reserved ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->ref_root = ref_root; __entry->reserved = reserved; ), - TP_printk("root=%llu, reserved=%llu, op=free", + TP_printk_btrfs("root=%llu, reserved=%llu, op=free", __entry->ref_root, __entry->reserved) ); DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref, - TP_PROTO(u64 ref_root, u64 reserved), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 ref_root, u64 reserved), - TP_ARGS(ref_root, reserved) + TP_ARGS(fs_info, ref_root, reserved) ); DECLARE_EVENT_CLASS(btrfs_qgroup_extent, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec), + TP_ARGS(fs_info, rec), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = rec->bytenr, __entry->num_bytes = rec->num_bytes; ), - TP_printk("bytenr = %llu, num_bytes = %llu", + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec) + TP_ARGS(fs_info, rec) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_insert_dirty_extent, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec) + TP_ARGS(fs_info, rec) ); TRACE_EVENT(btrfs_qgroup_account_extent, - TP_PROTO(u64 bytenr, u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots), - TP_ARGS(bytenr, num_bytes, nr_old_roots, nr_new_roots), + TP_ARGS(fs_info, bytenr, num_bytes, nr_old_roots, nr_new_roots), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( u64, nr_old_roots ) __field( u64, nr_new_roots ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = bytenr; __entry->num_bytes = num_bytes; __entry->nr_old_roots = nr_old_roots; __entry->nr_new_roots = nr_new_roots; ), - TP_printk("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, " "nr_new_roots = %llu", __entry->bytenr, __entry->num_bytes, @@ -1423,23 +1445,24 @@ TRACE_EVENT(btrfs_qgroup_account_extent, TRACE_EVENT(qgroup_update_counters, - TP_PROTO(u64 qgid, u64 cur_old_count, u64 cur_new_count), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 qgid, + u64 cur_old_count, u64 cur_new_count), - TP_ARGS(qgid, cur_old_count, cur_new_count), + TP_ARGS(fs_info, qgid, cur_old_count, cur_new_count), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, qgid ) __field( u64, cur_old_count ) __field( u64, cur_new_count ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->qgid = qgid; __entry->cur_old_count = cur_old_count; __entry->cur_new_count = cur_new_count; ), - TP_printk("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu", + TP_printk_btrfs("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu", __entry->qgid, __entry->cur_old_count, __entry->cur_new_count) -- cgit v1.2.3 From d34c30cc1fa80f509500ff192ea6bc7d30671061 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 26 Jul 2016 14:15:11 +0200 Subject: xen: add static initialization of steal_clock op to xen_time_ops pv_time_ops might be overwritten with xen_time_ops after the steal_clock operation has been initialized already. To prevent calling a now uninitialized function pointer add the steal_clock static initialization to xen_time_ops. Signed-off-by: Juergen Gross Signed-off-by: David Vrabel --- include/xen/xen-ops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index c9c532d56623..9a37c541822f 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -29,6 +29,7 @@ bool xen_vcpu_stolen(int vcpu); void xen_setup_runstate_info(int cpu); void xen_time_setup_guest(void); void xen_get_runstate_snapshot(struct vcpu_runstate_info *res); +u64 xen_steal_clock(int cpu); int xen_setup_shutdown_event(void); -- cgit v1.2.3 From 9ff26e9fabaf52f28fb5e875c0b9ffc2d1512039 Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Tue, 26 Jul 2016 08:47:18 +0200 Subject: tipc: introduce constants for tipc address validation In this commit, we introduce defines for tipc address size, offset and mask specification for Zone.Cluster.Node. There is no functional change in this commit. Reviewed-by: Jon Maloy Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- include/uapi/linux/tipc.h | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index 6f71b9b41595..bf049e8fe31b 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -60,26 +60,48 @@ struct tipc_name_seq { __u32 upper; }; +/* TIPC Address Size, Offset, Mask specification for Z.C.N + */ +#define TIPC_NODE_BITS 12 +#define TIPC_CLUSTER_BITS 12 +#define TIPC_ZONE_BITS 8 + +#define TIPC_NODE_OFFSET 0 +#define TIPC_CLUSTER_OFFSET TIPC_NODE_BITS +#define TIPC_ZONE_OFFSET (TIPC_CLUSTER_OFFSET + TIPC_CLUSTER_BITS) + +#define TIPC_NODE_SIZE ((1UL << TIPC_NODE_BITS) - 1) +#define TIPC_CLUSTER_SIZE ((1UL << TIPC_CLUSTER_BITS) - 1) +#define TIPC_ZONE_SIZE ((1UL << TIPC_ZONE_BITS) - 1) + +#define TIPC_NODE_MASK (TIPC_NODE_SIZE << TIPC_NODE_OFFSET) +#define TIPC_CLUSTER_MASK (TIPC_CLUSTER_SIZE << TIPC_CLUSTER_OFFSET) +#define TIPC_ZONE_MASK (TIPC_ZONE_SIZE << TIPC_ZONE_OFFSET) + +#define TIPC_ZONE_CLUSTER_MASK (TIPC_ZONE_MASK | TIPC_CLUSTER_MASK) + static inline __u32 tipc_addr(unsigned int zone, unsigned int cluster, unsigned int node) { - return (zone << 24) | (cluster << 12) | node; + return (zone << TIPC_ZONE_OFFSET) | + (cluster << TIPC_CLUSTER_OFFSET) | + node; } static inline unsigned int tipc_zone(__u32 addr) { - return addr >> 24; + return addr >> TIPC_ZONE_OFFSET; } static inline unsigned int tipc_cluster(__u32 addr) { - return (addr >> 12) & 0xfff; + return (addr & TIPC_CLUSTER_MASK) >> TIPC_CLUSTER_OFFSET; } static inline unsigned int tipc_node(__u32 addr) { - return addr & 0xfff; + return addr & TIPC_NODE_MASK; } /* -- cgit v1.2.3 From 7b3f52296493656015f0c0deddb6e90e36b9cda2 Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Tue, 26 Jul 2016 08:47:19 +0200 Subject: tipc: make cluster size threshold for monitoring configurable In this commit, we introduce support to configure the minimum threshold to activate the new link monitoring algorithm. Reviewed-by: Jon Maloy Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index d4c8f142ba63..d387b65a0d97 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -56,6 +56,7 @@ enum { TIPC_NL_NET_GET, TIPC_NL_NET_SET, TIPC_NL_NAME_TABLE_GET, + TIPC_NL_MON_SET, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 @@ -72,6 +73,7 @@ enum { TIPC_NLA_NODE, /* nest */ TIPC_NLA_NET, /* nest */ TIPC_NLA_NAME_TABLE, /* nest */ + TIPC_NLA_MON, /* nest */ __TIPC_NLA_MAX, TIPC_NLA_MAX = __TIPC_NLA_MAX - 1 @@ -166,6 +168,15 @@ enum { TIPC_NLA_NAME_TABLE_MAX = __TIPC_NLA_NAME_TABLE_MAX - 1 }; +/* Monitor info */ +enum { + TIPC_NLA_MON_UNSPEC, + TIPC_NLA_MON_ACTIVATION_THRESHOLD, /* u32 */ + + __TIPC_NLA_MON_MAX, + TIPC_NLA_MON_MAX = __TIPC_NLA_MON_MAX - 1 +}; + /* Publication info */ enum { TIPC_NLA_PUBL_UNSPEC, -- cgit v1.2.3 From bf1035b2ff5296c7c49e262152253ce29d87e82d Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Tue, 26 Jul 2016 08:47:20 +0200 Subject: tipc: get monitor threshold for the cluster In this commit, we add support to fetch the configured cluster monitoring threshold. Reviewed-by: Jon Maloy Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index d387b65a0d97..d07c6ec76062 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -57,6 +57,7 @@ enum { TIPC_NL_NET_SET, TIPC_NL_NAME_TABLE_GET, TIPC_NL_MON_SET, + TIPC_NL_MON_GET, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 -- cgit v1.2.3 From cf6f7e1d51090772d5ff7355aaf0fcff17f20d1a Mon Sep 17 00:00:00 2001 From: Parthasarathy Bhuvaragan Date: Tue, 26 Jul 2016 08:47:22 +0200 Subject: tipc: dump monitor attributes In this commit, we dump the monitor attributes when queried. The link monitor attributes are separated into two kinds: 1. general attributes per bearer 2. specific attributes per node/peer This style resembles the socket attributes and the nametable publications per socket. Reviewed-by: Jon Maloy Signed-off-by: Parthasarathy Bhuvaragan Signed-off-by: David S. Miller --- include/uapi/linux/tipc_netlink.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index d07c6ec76062..5f3f6d09fb79 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -58,6 +58,7 @@ enum { TIPC_NL_NAME_TABLE_GET, TIPC_NL_MON_SET, TIPC_NL_MON_GET, + TIPC_NL_MON_PEER_GET, __TIPC_NL_CMD_MAX, TIPC_NL_CMD_MAX = __TIPC_NL_CMD_MAX - 1 @@ -75,6 +76,7 @@ enum { TIPC_NLA_NET, /* nest */ TIPC_NLA_NAME_TABLE, /* nest */ TIPC_NLA_MON, /* nest */ + TIPC_NLA_MON_PEER, /* nest */ __TIPC_NLA_MAX, TIPC_NLA_MAX = __TIPC_NLA_MAX - 1 @@ -173,6 +175,11 @@ enum { enum { TIPC_NLA_MON_UNSPEC, TIPC_NLA_MON_ACTIVATION_THRESHOLD, /* u32 */ + TIPC_NLA_MON_REF, /* u32 */ + TIPC_NLA_MON_ACTIVE, /* flag */ + TIPC_NLA_MON_BEARER_NAME, /* string */ + TIPC_NLA_MON_PEERCNT, /* u32 */ + TIPC_NLA_MON_LISTGEN, /* u32 */ __TIPC_NLA_MON_MAX, TIPC_NLA_MON_MAX = __TIPC_NLA_MON_MAX - 1 @@ -194,6 +201,24 @@ enum { TIPC_NLA_PUBL_MAX = __TIPC_NLA_PUBL_MAX - 1 }; +/* Monitor peer info */ +enum { + TIPC_NLA_MON_PEER_UNSPEC, + + TIPC_NLA_MON_PEER_ADDR, /* u32 */ + TIPC_NLA_MON_PEER_DOMGEN, /* u32 */ + TIPC_NLA_MON_PEER_APPLIED, /* u32 */ + TIPC_NLA_MON_PEER_UPMAP, /* u64 */ + TIPC_NLA_MON_PEER_MEMBERS, /* tlv */ + TIPC_NLA_MON_PEER_UP, /* flag */ + TIPC_NLA_MON_PEER_HEAD, /* flag */ + TIPC_NLA_MON_PEER_LOCAL, /* flag */ + TIPC_NLA_MON_PEER_PAD, /* flag */ + + __TIPC_NLA_MON_PEER_MAX, + TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1 +}; + /* Nest, connection info */ enum { TIPC_NLA_CON_UNSPEC, -- cgit v1.2.3 From 7c15d9bb8231f998ae7dc0b72415f5215459f7fb Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 19 Jul 2016 15:00:04 -0700 Subject: mm: Add is_migrate_cma_page Code such as hardened user copy[1] needs a way to tell if a page is CMA or not. Add is_migrate_cma_page in a similar way to is_migrate_isolate_page. [1]http://article.gmane.org/gmane.linux.kernel.mm/155238 Signed-off-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 02069c23486d..c8478b29f070 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -68,8 +68,10 @@ extern char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false +# define is_migrate_cma_page(_page) false #endif #define for_each_migratetype_order(order, type) \ -- cgit v1.2.3 From 0f60a8efe4005ab5e65ce000724b04d4ca04a199 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 12 Jul 2016 16:19:48 -0700 Subject: mm: Implement stack frame object validation This creates per-architecture function arch_within_stack_frames() that should validate if a given object is contained by a kernel stack frame. Initial implementation is on x86. This is based on code from PaX. Signed-off-by: Kees Cook --- include/linux/thread_info.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index b4c2a485b28a..3d5c80b4391d 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -146,6 +146,15 @@ static inline bool test_and_clear_restore_sigmask(void) #error "no set_restore_sigmask() provided and default one won't work" #endif +#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From f5509cc18daa7f82bcc553be70df2117c8eedc16 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Jun 2016 11:05:33 -0700 Subject: mm: Hardened usercopy This is the start of porting PAX_USERCOPY into the mainline kernel. This is the first set of features, controlled by CONFIG_HARDENED_USERCOPY. The work is based on code by PaX Team and Brad Spengler, and an earlier port from Casey Schaufler. Additional non-slab page tests are from Rik van Riel. This patch contains the logic for validating several conditions when performing copy_to_user() and copy_from_user() on the kernel object being copied to/from: - address range doesn't wrap around - address range isn't NULL or zero-allocated (with a non-zero copy size) - if on the slab allocator: - object size must be less than or equal to copy size (when check is implemented in the allocator, which appear in subsequent patches) - otherwise, object must not span page allocations (excepting Reserved and CMA ranges) - if on the stack - object must not extend before/after the current process stack - object must be contained by a valid stack frame (when there is arch/build support for identifying stack frames) - object must not overlap with kernel text Signed-off-by: Kees Cook Tested-by: Valdis Kletnieks Tested-by: Michael Ellerman --- include/linux/slab.h | 12 ++++++++++++ include/linux/thread_info.h | 15 +++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index aeb3e6d00a66..96a16a3fb7cb 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -155,6 +155,18 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page); +#else +static inline const char *__check_heap_object(const void *ptr, + unsigned long n, + struct page *page) +{ + return NULL; +} +#endif + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 3d5c80b4391d..f24b99eac969 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -155,6 +155,21 @@ static inline int arch_within_stack_frames(const void * const stack, } #endif +#ifdef CONFIG_HARDENED_USERCOPY +extern void __check_object_size(const void *ptr, unsigned long n, + bool to_user); + +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ + __check_object_size(ptr, n, to_user); +} +#else +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ } +#endif /* CONFIG_HARDENED_USERCOPY */ + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From 6b524995a71d49ae032dba308d117dbf2a18d175 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 26 Jul 2016 15:21:05 -0700 Subject: dax: remote unused fault wrappers Remove the unused wrappers dax_fault() and dax_pmd_fault(). After this removal, rename __dax_fault() and __dax_pmd_fault() to dax_fault() and dax_pmd_fault() respectively, and update all callers. The dax_fault() and dax_pmd_fault() wrappers were initially intended to capture some filesystem independent functionality around page faults (calling sb_start_pagefault() & sb_end_pagefault(), updating file mtime and ctime). However, the following commits: 5726b27b09cc ("ext2: Add locking for DAX faults") ea3d7209ca01 ("ext4: fix races between page faults and hole punching") added locking to the ext2 and ext4 filesystems after these common operations but before __dax_fault() and __dax_pmd_fault() were called. This means that these wrappers are no longer used, and are unlikely to be used in the future. XFS has had locking analogous to what was recently added to ext2 and ext4 since DAX support was initially introduced by: 6b698edeeef0 ("xfs: add DAX file operations support") Link: http://lkml.kernel.org/r/20160714214049.20075-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Dan Williams Cc: Dave Chinner Reviewed-by: Jan Kara Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/dax.h b/include/linux/dax.h index 43d5f0b799c7..9c6dc7704043 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,7 +14,6 @@ ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); -int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_wake_mapping_entry_waiter(struct address_space *mapping, pgoff_t index, bool wake_all); @@ -46,19 +45,15 @@ static inline int __dax_zero_page_range(struct block_device *bdev, #if defined(CONFIG_TRANSPARENT_HUGEPAGE) int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, unsigned int flags, get_block_t); -int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned int flags, get_block_t); #else static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, get_block_t gb) { return VM_FAULT_FALLBACK; } -#define __dax_pmd_fault dax_pmd_fault #endif int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -#define __dax_mkwrite(vma, vmf, gb) __dax_fault(vma, vmf, gb) static inline bool vma_is_dax(struct vm_area_struct *vma) { -- cgit v1.2.3 From 17359a80b9315670f56cd016a92c083665e80ae1 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 26 Jul 2016 15:21:26 -0700 Subject: debugobjects.h: fix trivial kernel doc warning Add ':' to fix trivial kernel-doc warning in : ..//include/linux/debugobjects.h:63: warning: No description found for parameter 'is_static_object' Link: http://lkml.kernel.org/r/575B01B8.5060600@infradead.org Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/debugobjects.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 46056cb161fc..d82bf1994485 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -38,7 +38,7 @@ struct debug_obj { * @name: name of the object typee * @debug_hint: function returning address, which have associated * kernel symbol, to allow identify the object - * @is_static_object return true if the obj is static, otherwise return false + * @is_static_object: return true if the obj is static, otherwise return false * @fixup_init: fixup function, which is called when the init check * fails. All fixup functions must return true if fixup * was successful, otherwise return false -- cgit v1.2.3 From 6c60d2b5746cf23025ffe71bd7ff9075048fc90c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 26 Jul 2016 15:21:50 -0700 Subject: fs/fs-writeback.c: add a new writeback list for sync MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit wait_sb_inodes() currently does a walk of all inodes in the filesystem to find dirty one to wait on during sync. This is highly inefficient and wastes a lot of CPU when there are lots of clean cached inodes that we don't need to wait on. To avoid this "all inode" walk, we need to track inodes that are currently under writeback that we need to wait for. We do this by adding inodes to a writeback list on the sb when the mapping is first tagged as having pages under writeback. wait_sb_inodes() can then walk this list of "inodes under IO" and wait specifically just for the inodes that the current sync(2) needs to wait for. Define a couple helpers to add/remove an inode from the writeback list and call them when the overall mapping is tagged for or cleared from writeback. Update wait_sb_inodes() to walk only the inodes under writeback due to the sync. With this change, filesystem sync times are significantly reduced for fs' with largely populated inode caches and otherwise no other work to do. For example, on a 16xcpu 2GHz x86-64 server, 10TB XFS filesystem with a ~10m entry inode cache, sync times are reduced from ~7.3s to less than 0.1s when the filesystem is fully clean. Link: http://lkml.kernel.org/r/1466594593-6757-2-git-send-email-bfoster@redhat.com Signed-off-by: Dave Chinner Signed-off-by: Josef Bacik Signed-off-by: Brian Foster Reviewed-by: Jan Kara Tested-by: Holger Hoffstätte Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++++ include/linux/writeback.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..0c9ebf530d9e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -665,6 +665,7 @@ struct inode { #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; + struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; @@ -1448,6 +1449,9 @@ struct super_block { /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ + + spinlock_t s_inode_wblist_lock; + struct list_head s_inodes_wb; /* writeback inodes */ }; extern struct timespec current_fs_time(struct super_block *sb); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d0b5ca5d4e08..717e6149e753 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -384,4 +384,7 @@ void tag_pages_for_writeback(struct address_space *mapping, void account_page_redirty(struct page *page); +void sb_mark_inode_writeback(struct inode *inode); +void sb_clear_inode_writeback(struct inode *inode); + #endif /* WRITEBACK_H */ -- cgit v1.2.3 From 9a46b04f16a032c26bbf0ece61d6cd1e7ba9f627 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Tue, 26 Jul 2016 15:21:53 -0700 Subject: fs/fs-writeback.c: inode writeback list tracking tracepoints MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The per-sb inode writeback list tracks inodes currently under writeback to facilitate efficient sync processing. In particular, it ensures that sync only needs to walk through a list of inodes that were cleaned by the sync. Add a couple tracepoints to help identify when inodes are added/removed to and from the writeback lists. Piggyback off of the writeback lazytime tracepoint template as it already tracks the relevant inode information. Link: http://lkml.kernel.org/r/1466594593-6757-3-git-send-email-bfoster@redhat.com Signed-off-by: Brian Foster Reviewed-by: Jan Kara Cc: Dave Chinner cc: Josef Bacik Cc: Holger Hoffstätte Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/writeback.h | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 73614ce1d204..531f5811ff6b 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -696,7 +696,7 @@ DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_ARGS(inode, wbc, nr_to_write) ); -DECLARE_EVENT_CLASS(writeback_lazytime_template, +DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), @@ -723,25 +723,39 @@ DECLARE_EVENT_CLASS(writeback_lazytime_template, show_inode_state(__entry->state), __entry->mode) ); -DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime, +DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); -DEFINE_EVENT(writeback_lazytime_template, writeback_lazytime_iput, +DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); -DEFINE_EVENT(writeback_lazytime_template, writeback_dirty_inode_enqueue, +DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); +/* + * Inode writeback list tracking. + */ + +DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, + TP_PROTO(struct inode *inode), + TP_ARGS(inode) +); + +DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, + TP_PROTO(struct inode *inode), + TP_ARGS(inode) +); + #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7c00fce98c3e15334a603925b41aa49f76e83227 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Tue, 26 Jul 2016 15:21:56 -0700 Subject: mm: reorganize SLAB freelist randomization The kernel heap allocators are using a sequential freelist making their allocation predictable. This predictability makes kernel heap overflow easier to exploit. An attacker can careful prepare the kernel heap to control the following chunk overflowed. For example these attacks exploit the predictability of the heap: - Linux Kernel CAN SLUB overflow (https://goo.gl/oMNWkU) - Exploiting Linux Kernel Heap corruptions (http://goo.gl/EXLn95) ***Problems that needed solving: - Randomize the Freelist (singled linked) used in the SLUB allocator. - Ensure good performance to encourage usage. - Get best entropy in early boot stage. ***Parts: - 01/02 Reorganize the SLAB Freelist randomization to share elements with the SLUB implementation. - 02/02 The SLUB Freelist randomization implementation. Similar approach than the SLAB but tailored to the singled freelist used in SLUB. ***Performance data: slab_test impact is between 3% to 4% on average for 100000 attempts without smp. It is a very focused testing, kernbench show the overall impact on the system is way lower. Before: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 100000 times kmalloc(8) -> 49 cycles kfree -> 77 cycles 100000 times kmalloc(16) -> 51 cycles kfree -> 79 cycles 100000 times kmalloc(32) -> 53 cycles kfree -> 83 cycles 100000 times kmalloc(64) -> 62 cycles kfree -> 90 cycles 100000 times kmalloc(128) -> 81 cycles kfree -> 97 cycles 100000 times kmalloc(256) -> 98 cycles kfree -> 121 cycles 100000 times kmalloc(512) -> 95 cycles kfree -> 122 cycles 100000 times kmalloc(1024) -> 96 cycles kfree -> 126 cycles 100000 times kmalloc(2048) -> 115 cycles kfree -> 140 cycles 100000 times kmalloc(4096) -> 149 cycles kfree -> 171 cycles 2. Kmalloc: alloc/free test 100000 times kmalloc(8)/kfree -> 70 cycles 100000 times kmalloc(16)/kfree -> 70 cycles 100000 times kmalloc(32)/kfree -> 70 cycles 100000 times kmalloc(64)/kfree -> 70 cycles 100000 times kmalloc(128)/kfree -> 70 cycles 100000 times kmalloc(256)/kfree -> 69 cycles 100000 times kmalloc(512)/kfree -> 70 cycles 100000 times kmalloc(1024)/kfree -> 73 cycles 100000 times kmalloc(2048)/kfree -> 72 cycles 100000 times kmalloc(4096)/kfree -> 71 cycles After: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 100000 times kmalloc(8) -> 57 cycles kfree -> 78 cycles 100000 times kmalloc(16) -> 61 cycles kfree -> 81 cycles 100000 times kmalloc(32) -> 76 cycles kfree -> 93 cycles 100000 times kmalloc(64) -> 83 cycles kfree -> 94 cycles 100000 times kmalloc(128) -> 106 cycles kfree -> 107 cycles 100000 times kmalloc(256) -> 118 cycles kfree -> 117 cycles 100000 times kmalloc(512) -> 114 cycles kfree -> 116 cycles 100000 times kmalloc(1024) -> 115 cycles kfree -> 118 cycles 100000 times kmalloc(2048) -> 147 cycles kfree -> 131 cycles 100000 times kmalloc(4096) -> 214 cycles kfree -> 161 cycles 2. Kmalloc: alloc/free test 100000 times kmalloc(8)/kfree -> 66 cycles 100000 times kmalloc(16)/kfree -> 66 cycles 100000 times kmalloc(32)/kfree -> 66 cycles 100000 times kmalloc(64)/kfree -> 66 cycles 100000 times kmalloc(128)/kfree -> 65 cycles 100000 times kmalloc(256)/kfree -> 67 cycles 100000 times kmalloc(512)/kfree -> 67 cycles 100000 times kmalloc(1024)/kfree -> 64 cycles 100000 times kmalloc(2048)/kfree -> 67 cycles 100000 times kmalloc(4096)/kfree -> 67 cycles Kernbench, before: Average Optimal load -j 12 Run (std deviation): Elapsed Time 101.873 (1.16069) User Time 1045.22 (1.60447) System Time 88.969 (0.559195) Percent CPU 1112.9 (13.8279) Context Switches 189140 (2282.15) Sleeps 99008.6 (768.091) After: Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.47 (0.562732) User Time 1045.3 (1.34263) System Time 88.311 (0.342554) Percent CPU 1105.8 (6.49444) Context Switches 189081 (2355.78) Sleeps 99231.5 (800.358) This patch (of 2): This commit reorganizes the previous SLAB freelist randomization to prepare for the SLUB implementation. It moves functions that will be shared to slab_common. The entropy functions are changed to align with the SLUB implementation, now using get_random_(int|long) functions. These functions were chosen because they provide a bit more entropy early on boot and better performance when specific arch instructions are not available. [akpm@linux-foundation.org: fix build] Link: http://lkml.kernel.org/r/1464295031-26375-2-git-send-email-thgarnie@google.com Signed-off-by: Thomas Garnier Reviewed-by: Kees Cook Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 8694f7a5d92b..339ba027ade9 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -81,7 +81,7 @@ struct kmem_cache { #endif #ifdef CONFIG_SLAB_FREELIST_RANDOM - void *random_seq; + unsigned int *random_seq; #endif struct kmem_cache_node *node[MAX_NUMNODES]; -- cgit v1.2.3 From 210e7a43fa905bccafa9bb5966fba1d71f33eb8b Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Tue, 26 Jul 2016 15:21:59 -0700 Subject: mm: SLUB freelist randomization Implements freelist randomization for the SLUB allocator. It was previous implemented for the SLAB allocator. Both use the same configuration option (CONFIG_SLAB_FREELIST_RANDOM). The list is randomized during initialization of a new set of pages. The order on different freelist sizes is pre-computed at boot for performance. Each kmem_cache has its own randomized freelist. This security feature reduces the predictability of the kernel SLUB allocator against heap overflows rendering attacks much less stable. For example these attacks exploit the predictability of the heap: - Linux Kernel CAN SLUB overflow (https://goo.gl/oMNWkU) - Exploiting Linux Kernel Heap corruptions (http://goo.gl/EXLn95) Performance results: slab_test impact is between 3% to 4% on average for 100000 attempts without smp. It is a very focused testing, kernbench show the overall impact on the system is way lower. Before: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 100000 times kmalloc(8) -> 49 cycles kfree -> 77 cycles 100000 times kmalloc(16) -> 51 cycles kfree -> 79 cycles 100000 times kmalloc(32) -> 53 cycles kfree -> 83 cycles 100000 times kmalloc(64) -> 62 cycles kfree -> 90 cycles 100000 times kmalloc(128) -> 81 cycles kfree -> 97 cycles 100000 times kmalloc(256) -> 98 cycles kfree -> 121 cycles 100000 times kmalloc(512) -> 95 cycles kfree -> 122 cycles 100000 times kmalloc(1024) -> 96 cycles kfree -> 126 cycles 100000 times kmalloc(2048) -> 115 cycles kfree -> 140 cycles 100000 times kmalloc(4096) -> 149 cycles kfree -> 171 cycles 2. Kmalloc: alloc/free test 100000 times kmalloc(8)/kfree -> 70 cycles 100000 times kmalloc(16)/kfree -> 70 cycles 100000 times kmalloc(32)/kfree -> 70 cycles 100000 times kmalloc(64)/kfree -> 70 cycles 100000 times kmalloc(128)/kfree -> 70 cycles 100000 times kmalloc(256)/kfree -> 69 cycles 100000 times kmalloc(512)/kfree -> 70 cycles 100000 times kmalloc(1024)/kfree -> 73 cycles 100000 times kmalloc(2048)/kfree -> 72 cycles 100000 times kmalloc(4096)/kfree -> 71 cycles After: Single thread testing ===================== 1. Kmalloc: Repeatedly allocate then free test 100000 times kmalloc(8) -> 57 cycles kfree -> 78 cycles 100000 times kmalloc(16) -> 61 cycles kfree -> 81 cycles 100000 times kmalloc(32) -> 76 cycles kfree -> 93 cycles 100000 times kmalloc(64) -> 83 cycles kfree -> 94 cycles 100000 times kmalloc(128) -> 106 cycles kfree -> 107 cycles 100000 times kmalloc(256) -> 118 cycles kfree -> 117 cycles 100000 times kmalloc(512) -> 114 cycles kfree -> 116 cycles 100000 times kmalloc(1024) -> 115 cycles kfree -> 118 cycles 100000 times kmalloc(2048) -> 147 cycles kfree -> 131 cycles 100000 times kmalloc(4096) -> 214 cycles kfree -> 161 cycles 2. Kmalloc: alloc/free test 100000 times kmalloc(8)/kfree -> 66 cycles 100000 times kmalloc(16)/kfree -> 66 cycles 100000 times kmalloc(32)/kfree -> 66 cycles 100000 times kmalloc(64)/kfree -> 66 cycles 100000 times kmalloc(128)/kfree -> 65 cycles 100000 times kmalloc(256)/kfree -> 67 cycles 100000 times kmalloc(512)/kfree -> 67 cycles 100000 times kmalloc(1024)/kfree -> 64 cycles 100000 times kmalloc(2048)/kfree -> 67 cycles 100000 times kmalloc(4096)/kfree -> 67 cycles Kernbench, before: Average Optimal load -j 12 Run (std deviation): Elapsed Time 101.873 (1.16069) User Time 1045.22 (1.60447) System Time 88.969 (0.559195) Percent CPU 1112.9 (13.8279) Context Switches 189140 (2282.15) Sleeps 99008.6 (768.091) After: Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.47 (0.562732) User Time 1045.3 (1.34263) System Time 88.311 (0.342554) Percent CPU 1105.8 (6.49444) Context Switches 189081 (2355.78) Sleeps 99231.5 (800.358) Link: http://lkml.kernel.org/r/1464295031-26375-3-git-send-email-thgarnie@google.com Signed-off-by: Thomas Garnier Reviewed-by: Kees Cook Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index d1faa019c02a..5624c1f3eb0a 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -99,6 +99,11 @@ struct kmem_cache { */ int remote_node_defrag_ratio; #endif + +#ifdef CONFIG_SLAB_FREELIST_RANDOM + unsigned int *random_seq; +#endif + struct kmem_cache_node *node[MAX_NUMNODES]; }; -- cgit v1.2.3 From 91c6a05f72a996bee5133e76374ab3ad7d3b9b72 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 26 Jul 2016 15:22:08 -0700 Subject: mm: faster kmalloc_array(), kcalloc() When both arguments to kmalloc_array() or kcalloc() are known at compile time then their product is known at compile time but search for kmalloc cache happens at runtime not at compile time. Link: http://lkml.kernel.org/r/20160627213454.GA2440@p183.telecom.by Signed-off-by: Alexey Dobriyan Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index aeb3e6d00a66..1a4ea551aae5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -565,6 +565,8 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { if (size != 0 && n > SIZE_MAX / size) return NULL; + if (__builtin_constant_p(n) && __builtin_constant_p(size)) + return kmalloc(n * size, flags); return __kmalloc(n * size, flags); } -- cgit v1.2.3 From df429ac039360005299d56247647ca77098d660e Mon Sep 17 00:00:00 2001 From: Reza Arbab Date: Tue, 26 Jul 2016 15:22:23 -0700 Subject: memory-hotplug: more general validation of zone during online When memory is onlined, we are only able to rezone from ZONE_MOVABLE to ZONE_KERNEL, or from (ZONE_MOVABLE - 1) to ZONE_MOVABLE. To be more flexible, use the following criteria instead; to online memory from zone X into zone Y, * Any zones between X and Y must be unused. * If X is lower than Y, the onlined memory must lie at the end of X. * If X is higher than Y, the onlined memory must lie at the start of X. Add zone_can_shift() to make this determination. Link: http://lkml.kernel.org/r/1462816419-4479-3-git-send-email-arbab@linux.vnet.ibm.com Signed-off-by: Reza Arbab Reviewd-by: Yasuaki Ishimatsu Cc: Greg Kroah-Hartman Cc: Daniel Kiper Cc: Dan Williams Cc: Vlastimil Babka Cc: Tang Chen Cc: Joonsoo Kim Cc: David Vrabel Cc: Vitaly Kuznetsov Cc: David Rientjes Cc: Andrew Banman Cc: Chen Yucong Cc: Yasunori Goto Cc: Zhang Zhen Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 5145620ba48a..01033fadea47 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -284,5 +284,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); +extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages, + enum zone_type target); #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From 798fd756952c4b6cb7dfe6f6437e9f02da79a5bc Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:22:30 -0700 Subject: mm: zap ZONE_OOM_LOCKED Not used since oom_lock was instroduced. Link: http://lkml.kernel.org/r/1464358093-22663-1-git-send-email-vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 02069c23486d..3388ccbab7d6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -524,7 +524,6 @@ struct zone { enum zone_flags { ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ - ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */ ZONE_CONGESTED, /* zone has many dirty pages backed by * a congested BDI */ -- cgit v1.2.3 From 2a966b77ae3ede207e787e7538b87d1011c4364e Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:22:33 -0700 Subject: mm: oom: add memcg to oom_control It's a part of oom context just like allocation order and nodemask, so let's move it to oom_control instead of passing it in the argument list. Link: http://lkml.kernel.org/r/40e03fd7aaf1f55c75d787128d6d17c5a71226c2.1464358556.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tetsuo Handa Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 83469522690a..cbc24a5fe28d 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -23,6 +23,9 @@ struct oom_control { /* Used to determine mempolicy */ nodemask_t *nodemask; + /* Memory cgroup in which oom is invoked, or NULL for global oom */ + struct mem_cgroup *memcg; + /* Used to determine cpuset and node locality requirement */ const gfp_t gfp_mask; @@ -83,11 +86,10 @@ extern unsigned long oom_badness(struct task_struct *p, extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, const char *message); + const char *message); extern void check_panic_on_oom(struct oom_control *oc, - enum oom_constraint constraint, - struct mem_cgroup *memcg); + enum oom_constraint constraint); extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, struct task_struct *task, unsigned long totalpages); -- cgit v1.2.3 From a54f9aebaa9f0ea2ce6b01f12b65062fb2e74e6c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:22:36 -0700 Subject: include/linux/mmdebug.h: add VM_WARN which maps to WARN() This enables us to do VM_WARN(condition, "warn message"); Link: http://lkml.kernel.org/r/1464692688-6612-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmdebug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index de7be78c6f0e..451a811f48f2 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -39,6 +39,7 @@ void dump_mm(const struct mm_struct *mm); #define VM_WARN_ON(cond) WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond) #define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format) +#define VM_WARN(cond, format...) WARN(cond, format) #else #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond) @@ -47,6 +48,7 @@ void dump_mm(const struct mm_struct *mm); #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif #ifdef CONFIG_DEBUG_VIRTUAL -- cgit v1.2.3 From bda807d4445414e8e77da704f116bb0880fe0c76 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 26 Jul 2016 15:23:05 -0700 Subject: mm: migrate: support non-lru movable page migration We have allowed migration for only LRU pages until now and it was enough to make high-order pages. But recently, embedded system(e.g., webOS, android) uses lots of non-movable pages(e.g., zram, GPU memory) so we have seen several reports about troubles of small high-order allocation. For fixing the problem, there were several efforts (e,g,. enhance compaction algorithm, SLUB fallback to 0-order page, reserved memory, vmalloc and so on) but if there are lots of non-movable pages in system, their solutions are void in the long run. So, this patch is to support facility to change non-movable pages with movable. For the feature, this patch introduces functions related to migration to address_space_operations as well as some page flags. If a driver want to make own pages movable, it should define three functions which are function pointers of struct address_space_operations. 1. bool (*isolate_page) (struct page *page, isolate_mode_t mode); What VM expects on isolate_page function of driver is to return *true* if driver isolates page successfully. On returing true, VM marks the page as PG_isolated so concurrent isolation in several CPUs skip the page for isolation. If a driver cannot isolate the page, it should return *false*. Once page is successfully isolated, VM uses page.lru fields so driver shouldn't expect to preserve values in that fields. 2. int (*migratepage) (struct address_space *mapping, struct page *newpage, struct page *oldpage, enum migrate_mode); After isolation, VM calls migratepage of driver with isolated page. The function of migratepage is to move content of the old page to new page and set up fields of struct page newpage. Keep in mind that you should indicate to the VM the oldpage is no longer movable via __ClearPageMovable() under page_lock if you migrated the oldpage successfully and returns 0. If driver cannot migrate the page at the moment, driver can return -EAGAIN. On -EAGAIN, VM will retry page migration in a short time because VM interprets -EAGAIN as "temporal migration failure". On returning any error except -EAGAIN, VM will give up the page migration without retrying in this time. Driver shouldn't touch page.lru field VM using in the functions. 3. void (*putback_page)(struct page *); If migration fails on isolated page, VM should return the isolated page to the driver so VM calls driver's putback_page with migration failed page. In this function, driver should put the isolated page back to the own data structure. 4. non-lru movable page flags There are two page flags for supporting non-lru movable page. * PG_movable Driver should use the below function to make page movable under page_lock. void __SetPageMovable(struct page *page, struct address_space *mapping) It needs argument of address_space for registering migration family functions which will be called by VM. Exactly speaking, PG_movable is not a real flag of struct page. Rather than, VM reuses page->mapping's lower bits to represent it. #define PAGE_MAPPING_MOVABLE 0x2 page->mapping = page->mapping | PAGE_MAPPING_MOVABLE; so driver shouldn't access page->mapping directly. Instead, driver should use page_mapping which mask off the low two bits of page->mapping so it can get right struct address_space. For testing of non-lru movable page, VM supports __PageMovable function. However, it doesn't guarantee to identify non-lru movable page because page->mapping field is unified with other variables in struct page. As well, if driver releases the page after isolation by VM, page->mapping doesn't have stable value although it has PAGE_MAPPING_MOVABLE (Look at __ClearPageMovable). But __PageMovable is cheap to catch whether page is LRU or non-lru movable once the page has been isolated. Because LRU pages never can have PAGE_MAPPING_MOVABLE in page->mapping. It is also good for just peeking to test non-lru movable pages before more expensive checking with lock_page in pfn scanning to select victim. For guaranteeing non-lru movable page, VM provides PageMovable function. Unlike __PageMovable, PageMovable functions validates page->mapping and mapping->a_ops->isolate_page under lock_page. The lock_page prevents sudden destroying of page->mapping. Driver using __SetPageMovable should clear the flag via __ClearMovablePage under page_lock before the releasing the page. * PG_isolated To prevent concurrent isolation among several CPUs, VM marks isolated page as PG_isolated under lock_page. So if a CPU encounters PG_isolated non-lru movable page, it can skip it. Driver doesn't need to manipulate the flag because VM will set/clear it automatically. Keep in mind that if driver sees PG_isolated page, it means the page have been isolated by VM so it shouldn't touch page.lru field. PG_isolated is alias with PG_reclaim flag so driver shouldn't use the flag for own purpose. [opensource.ganesh@gmail.com: mm/compaction: remove local variable is_lru] Link: http://lkml.kernel.org/r/20160618014841.GA7422@leo-test Link: http://lkml.kernel.org/r/1464736881-24886-3-git-send-email-minchan@kernel.org Signed-off-by: Gioh Kim Signed-off-by: Minchan Kim Signed-off-by: Ganesh Mahendran Acked-by: Vlastimil Babka Cc: Sergey Senozhatsky Cc: Rik van Riel Cc: Joonsoo Kim Cc: Mel Gorman Cc: Hugh Dickins Cc: Rafael Aquini Cc: Jonathan Corbet Cc: John Einar Reitan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 17 +++++++++++++++++ include/linux/fs.h | 2 ++ include/linux/ksm.h | 3 +-- include/linux/migrate.h | 2 ++ include/linux/mm.h | 1 + include/linux/page-flags.h | 33 +++++++++++++++++++++++---------- 6 files changed, 46 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index a58c852a268f..c6b47c861cea 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -54,6 +54,9 @@ enum compact_result { struct alloc_context; /* in mm/internal.h */ #ifdef CONFIG_COMPACTION +extern int PageMovable(struct page *page); +extern void __SetPageMovable(struct page *page, struct address_space *mapping); +extern void __ClearPageMovable(struct page *page); extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); @@ -151,6 +154,19 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else +static inline int PageMovable(struct page *page) +{ + return 0; +} +static inline void __SetPageMovable(struct page *page, + struct address_space *mapping) +{ +} + +static inline void __ClearPageMovable(struct page *page) +{ +} + static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, int alloc_flags, const struct alloc_context *ac, @@ -212,6 +228,7 @@ static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_i #endif /* CONFIG_COMPACTION */ #if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) +struct node; extern int compaction_register_node(struct node *node); extern void compaction_unregister_node(struct node *node); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0c9ebf530d9e..97fe08d17d89 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -402,6 +402,8 @@ struct address_space_operations { */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); + bool (*isolate_page)(struct page *, isolate_mode_t); + void (*putback_page)(struct page *); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, unsigned long, unsigned long); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7ae216a39c9e..481c8c4627ca 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -43,8 +43,7 @@ static inline struct stable_node *page_stable_node(struct page *page) static inline void set_page_stable_node(struct page *page, struct stable_node *stable_node) { - page->mapping = (void *)stable_node + - (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); + page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } /* diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 9b50325e4ddf..404fbfefeb33 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -37,6 +37,8 @@ extern int migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, unsigned long private, enum migrate_mode mode, int reason); +extern bool isolate_movable_page(struct page *page, isolate_mode_t mode); +extern void putback_movable_page(struct page *page); extern int migrate_prep(void); extern int migrate_prep_local(void); diff --git a/include/linux/mm.h b/include/linux/mm.h index ece042dfe23c..3e22335a435c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1035,6 +1035,7 @@ static inline pgoff_t page_file_index(struct page *page) } bool page_mapped(struct page *page); +struct address_space *page_mapping(struct page *page); /* * Return true only if the page has been allocated with diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e5a32445f930..f36dbb3a3060 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -129,6 +129,9 @@ enum pageflags { /* Compound pages. Stored in first tail page's flags */ PG_double_map = PG_private_2, + + /* non-lru isolated movable page */ + PG_isolated = PG_reclaim, }; #ifndef __GENERATING_BOUNDS_H @@ -357,29 +360,37 @@ PAGEFLAG(Idle, idle, PF_ANY) * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, - * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit; - * and then page->mapping points, not to an anon_vma, but to a private + * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON + * bit; and then page->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * - * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used. + * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable + * page and then page->mapping points a struct address_space. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ -#define PAGE_MAPPING_ANON 1 -#define PAGE_MAPPING_KSM 2 -#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) +#define PAGE_MAPPING_ANON 0x1 +#define PAGE_MAPPING_MOVABLE 0x2 +#define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) -static __always_inline int PageAnonHead(struct page *page) +static __always_inline int PageMappingFlags(struct page *page) { - return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; + return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline int PageAnon(struct page *page) { page = compound_head(page); - return PageAnonHead(page); + return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; +} + +static __always_inline int __PageMovable(struct page *page) +{ + return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == + PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM @@ -393,7 +404,7 @@ static __always_inline int PageKsm(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == - (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); + PAGE_MAPPING_KSM; } #else TESTPAGEFLAG_FALSE(Ksm) @@ -641,6 +652,8 @@ static inline void __ClearPageBalloon(struct page *page) atomic_set(&page->_mapcount, -1); } +__PAGEFLAG(Isolated, isolated, PF_ANY); + /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. -- cgit v1.2.3 From b1123ea6d3b3da25af5c8a9d843bd07ab63213f4 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 26 Jul 2016 15:23:09 -0700 Subject: mm: balloon: use general non-lru movable page feature Now, VM has a feature to migrate non-lru movable pages so balloon doesn't need custom migration hooks in migrate.c and compaction.c. Instead, this patch implements the page->mapping->a_ops-> {isolate|migrate|putback} functions. With that, we could remove hooks for ballooning in general migration functions and make balloon compaction simple. [akpm@linux-foundation.org: compaction.h requires that the includer first include node.h] Link: http://lkml.kernel.org/r/1464736881-24886-4-git-send-email-minchan@kernel.org Signed-off-by: Gioh Kim Signed-off-by: Minchan Kim Acked-by: Vlastimil Babka Cc: Rafael Aquini Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/balloon_compaction.h | 54 ++++++++++++-------------------------- include/uapi/linux/magic.h | 1 + 2 files changed, 18 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 9b0a15d06a4f..504bd724e6ab 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -45,9 +45,11 @@ #define _LINUX_BALLOON_COMPACTION_H #include #include -#include +#include +#include #include #include +#include /* * Balloon device information descriptor. @@ -62,6 +64,7 @@ struct balloon_dev_info { struct list_head pages; /* Pages enqueued & handled to Host */ int (*migratepage)(struct balloon_dev_info *, struct page *newpage, struct page *page, enum migrate_mode mode); + struct inode *inode; }; extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info); @@ -73,44 +76,18 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) spin_lock_init(&balloon->pages_lock); INIT_LIST_HEAD(&balloon->pages); balloon->migratepage = NULL; + balloon->inode = NULL; } #ifdef CONFIG_BALLOON_COMPACTION -extern bool balloon_page_isolate(struct page *page); +extern const struct address_space_operations balloon_aops; +extern bool balloon_page_isolate(struct page *page, + isolate_mode_t mode); extern void balloon_page_putback(struct page *page); -extern int balloon_page_migrate(struct page *newpage, +extern int balloon_page_migrate(struct address_space *mapping, + struct page *newpage, struct page *page, enum migrate_mode mode); -/* - * __is_movable_balloon_page - helper to perform @page PageBalloon tests - */ -static inline bool __is_movable_balloon_page(struct page *page) -{ - return PageBalloon(page); -} - -/* - * balloon_page_movable - test PageBalloon to identify balloon pages - * and PagePrivate to check that the page is not - * isolated and can be moved by compaction/migration. - * - * As we might return false positives in the case of a balloon page being just - * released under us, this need to be re-tested later, under the page lock. - */ -static inline bool balloon_page_movable(struct page *page) -{ - return PageBalloon(page) && PagePrivate(page); -} - -/* - * isolated_balloon_page - identify an isolated balloon page on private - * compaction/migration page lists. - */ -static inline bool isolated_balloon_page(struct page *page) -{ - return PageBalloon(page); -} - /* * balloon_page_insert - insert a page into the balloon's page list and make * the page->private assignment accordingly. @@ -124,7 +101,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { __SetPageBalloon(page); - SetPagePrivate(page); + __SetPageMovable(page, balloon->inode->i_mapping); set_page_private(page, (unsigned long)balloon); list_add(&page->lru, &balloon->pages); } @@ -140,11 +117,14 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, static inline void balloon_page_delete(struct page *page) { __ClearPageBalloon(page); + __ClearPageMovable(page); set_page_private(page, 0); - if (PagePrivate(page)) { - ClearPagePrivate(page); + /* + * No touch page.lru field once @page has been isolated + * because VM is using the field. + */ + if (!PageIsolated(page)) list_del(&page->lru); - } } /* diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 546b38886e11..d829ce63529d 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -80,5 +80,6 @@ #define BPF_FS_MAGIC 0xcafe4a11 /* Since UDF 2.01 is ISO 13346 based... */ #define UDF_SUPER_MAGIC 0x15013346 +#define BALLOON_KVM_MAGIC 0x13661366 #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From 48b4800a1c6af2cdda344ea4e2c843dcc1f6afc9 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 26 Jul 2016 15:23:31 -0700 Subject: zsmalloc: page migration support This patch introduces run-time migration feature for zspage. For migration, VM uses page.lru field so it would be better to not use page.next field which is unified with page.lru for own purpose. For that, firstly, we can get first object offset of the page via runtime calculation instead of using page.index so we can use page.index as link for page chaining instead of page.next. In case of huge object, it stores handle to page.index instead of next link of page chaining because huge object doesn't need to next link for page chaining. So get_next_page need to identify huge object to return NULL. For it, this patch uses PG_owner_priv_1 flag of the page flag. For migration, it supports three functions * zs_page_isolate It isolates a zspage which includes a subpage VM want to migrate from class so anyone cannot allocate new object from the zspage. We could try to isolate a zspage by the number of subpage so subsequent isolation trial of other subpage of the zpsage shouldn't fail. For that, we introduce zspage.isolated count. With that, zs_page_isolate can know whether zspage is already isolated or not for migration so if it is isolated for migration, subsequent isolation trial can be successful without trying further isolation. * zs_page_migrate First of all, it holds write-side zspage->lock to prevent migrate other subpage in zspage. Then, lock all objects in the page VM want to migrate. The reason we should lock all objects in the page is due to race between zs_map_object and zs_page_migrate. zs_map_object zs_page_migrate pin_tag(handle) obj = handle_to_obj(handle) obj_to_location(obj, &page, &obj_idx); write_lock(&zspage->lock) if (!trypin_tag(handle)) goto unpin_object zspage = get_zspage(page); read_lock(&zspage->lock); If zs_page_migrate doesn't do trypin_tag, zs_map_object's page can be stale by migration so it goes crash. If it locks all of objects successfully, it copies content from old page to new one, finally, create new zspage chain with new page. And if it's last isolated subpage in the zspage, put the zspage back to class. * zs_page_putback It returns isolated zspage to right fullness_group list if it fails to migrate a page. If it find a zspage is ZS_EMPTY, it queues zspage freeing to workqueue. See below about async zspage freeing. This patch introduces asynchronous zspage free. The reason to need it is we need page_lock to clear PG_movable but unfortunately, zs_free path should be atomic so the apporach is try to grab page_lock. If it got page_lock of all of pages successfully, it can free zspage immediately. Otherwise, it queues free request and free zspage via workqueue in process context. If zs_free finds the zspage is isolated when it try to free zspage, it delays the freeing until zs_page_putback finds it so it will free free the zspage finally. In this patch, we expand fullness_list from ZS_EMPTY to ZS_FULL. First of all, it will use ZS_EMPTY list for delay freeing. And with adding ZS_FULL list, it makes to identify whether zspage is isolated or not via list_empty(&zspage->list) test. [minchan@kernel.org: zsmalloc: keep first object offset in struct page] Link: http://lkml.kernel.org/r/1465788015-23195-1-git-send-email-minchan@kernel.org [minchan@kernel.org: zsmalloc: zspage sanity check] Link: http://lkml.kernel.org/r/20160603010129.GC3304@bbox Link: http://lkml.kernel.org/r/1464736881-24886-12-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim Cc: Sergey Senozhatsky Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index d829ce63529d..e398beac67b8 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -81,5 +81,6 @@ /* Since UDF 2.01 is ISO 13346 based... */ #define UDF_SUPER_MAGIC 0x15013346 #define BALLOON_KVM_MAGIC 0x13661366 +#define ZSMALLOC_MAGIC 0x58295829 #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From 66c64223ad4e7a4a9161fcd9606426d9f57227ca Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 26 Jul 2016 15:23:40 -0700 Subject: mm/compaction: split freepages without holding the zone lock We don't need to split freepages with holding the zone lock. It will cause more contention on zone lock so not desirable. [rientjes@google.com: if __isolate_free_page() fails, avoid adding to freelist so we don't call map_pages() with it] Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1606211447001.43430@chino.kir.corp.google.com Link: http://lkml.kernel.org/r/1464230275-25791-1-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Minchan Kim Cc: Alexander Potapenko Cc: Hugh Dickins Cc: Michal Hocko Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3e22335a435c..6c9a394b2979 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -537,7 +537,6 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); -int split_free_page(struct page *page); /* * Compound pages have a destructor function. Provide a -- cgit v1.2.3 From a9627bc5e34e79ae80a33241b8a1501cc498e191 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 26 Jul 2016 15:23:49 -0700 Subject: mm/page_owner: introduce split_page_owner and replace manual handling split_page() calls set_page_owner() to set up page_owner to each pages. But, it has a drawback that head page and the others have different stacktrace because callsite of set_page_owner() is slightly differnt. To avoid this problem, this patch copies head page's page_owner to the others. It needs to introduce new function, split_page_owner() but it also remove the other function, get_page_owner_gfp() so looks good to do. Link: http://lkml.kernel.org/r/1464230275-25791-4-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Minchan Kim Cc: Alexander Potapenko Cc: Hugh Dickins Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 46f1b939948c..30583ab0ffb1 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -10,7 +10,7 @@ extern struct page_ext_operations page_owner_ops; extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); -extern gfp_t __get_page_owner_gfp(struct page *page); +extern void __split_page_owner(struct page *page, unsigned int order); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(struct page *page); @@ -28,12 +28,10 @@ static inline void set_page_owner(struct page *page, __set_page_owner(page, order, gfp_mask); } -static inline gfp_t get_page_owner_gfp(struct page *page) +static inline void split_page_owner(struct page *page, unsigned int order) { if (static_branch_unlikely(&page_owner_inited)) - return __get_page_owner_gfp(page); - else - return 0; + __split_page_owner(page, order); } static inline void copy_page_owner(struct page *oldpage, struct page *newpage) { @@ -58,9 +56,9 @@ static inline void set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { } -static inline gfp_t get_page_owner_gfp(struct page *page) +static inline void split_page_owner(struct page *page, + unsigned int order) { - return 0; } static inline void copy_page_owner(struct page *oldpage, struct page *newpage) { -- cgit v1.2.3 From f2ca0b55710752588ccff5224a11e6aea43a996a Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Tue, 26 Jul 2016 15:23:55 -0700 Subject: mm/page_owner: use stackdepot to store stacktrace Currently, we store each page's allocation stacktrace on corresponding page_ext structure and it requires a lot of memory. This causes the problem that memory tight system doesn't work well if page_owner is enabled. Moreover, even with this large memory consumption, we cannot get full stacktrace because we allocate memory at boot time and just maintain 8 stacktrace slots to balance memory consumption. We could increase it to more but it would make system unusable or change system behaviour. To solve the problem, this patch uses stackdepot to store stacktrace. It obviously provides memory saving but there is a drawback that stackdepot could fail. stackdepot allocates memory at runtime so it could fail if system has not enough memory. But, most of allocation stack are generated at very early time and there are much memory at this time. So, failure would not happen easily. And, one failure means that we miss just one page's allocation stacktrace so it would not be a big problem. In this patch, when memory allocation failure happens, we store special stracktrace handle to the page that is failed to save stacktrace. With it, user can guess memory usage properly even if failure happens. Memory saving looks as following. (4GB memory system with page_owner) (before the patch -> after the patch) static allocation: 92274688 bytes -> 25165824 bytes dynamic allocation after boot + kernel build: 0 bytes -> 327680 bytes total: 92274688 bytes -> 25493504 bytes 72% reduction in total. Note that implementation looks complex than someone would imagine because there is recursion issue. stackdepot uses page allocator and page_owner is called at page allocation. Using stackdepot in page_owner could re-call page allcator and then page_owner. That is a recursion. To detect and avoid it, whenever we obtain stacktrace, recursion is checked and page_owner is set to dummy information if found. Dummy information means that this page is allocated for page_owner feature itself (such as stackdepot) and it's understandable behavior for user. [iamjoonsoo.kim@lge.com: mm-page_owner-use-stackdepot-to-store-stacktrace-v3] Link: http://lkml.kernel.org/r/1464230275-25791-6-git-send-email-iamjoonsoo.kim@lge.com Link: http://lkml.kernel.org/r/1466150259-27727-7-git-send-email-iamjoonsoo.kim@lge.com Link: http://lkml.kernel.org/r/1464230275-25791-6-git-send-email-iamjoonsoo.kim@lge.com Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Mel Gorman Cc: Minchan Kim Cc: Alexander Potapenko Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index e1fe7cf5bddf..03f2a3e7d76d 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -3,6 +3,7 @@ #include #include +#include struct pglist_data; struct page_ext_operations { @@ -44,9 +45,8 @@ struct page_ext { #ifdef CONFIG_PAGE_OWNER unsigned int order; gfp_t gfp_mask; - unsigned int nr_entries; int last_migrate_reason; - unsigned long trace_entries[8]; + depot_stack_handle_t handle; #endif }; -- cgit v1.2.3 From e9d55e157034a9efd99405c99c1565d64619d82b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:24:09 -0700 Subject: mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 9dbb739cafa0..7b899a46a4cb 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -107,6 +107,11 @@ struct mmu_gather { struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; unsigned int batch_count; + /* + * __tlb_adjust_range will track the new addr here, + * that that we can adjust the range after the flush + */ + unsigned long addr; }; #define HAVE_GENERIC_MMU_GATHER @@ -115,23 +120,19 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long void tlb_flush_mmu(struct mmu_gather *tlb); void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); -int __tlb_remove_page(struct mmu_gather *tlb, struct page *page); - -/* tlb_remove_page - * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when - * required. - */ -static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) -{ - if (!__tlb_remove_page(tlb, page)) - tlb_flush_mmu(tlb); -} +bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + PAGE_SIZE); + /* + * Track the last address with which we adjusted the range. This + * will be used later to adjust again after a mmu_flush due to + * failed __tlb_remove_page + */ + tlb->addr = address; } static inline void __tlb_reset_range(struct mmu_gather *tlb) @@ -144,6 +145,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) } } +/* tlb_remove_page + * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when + * required. + */ +static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + if (__tlb_remove_page(tlb, page)) { + tlb_flush_mmu(tlb); + __tlb_adjust_range(tlb, tlb->addr); + __tlb_remove_page(tlb, page); + } +} + +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) +{ + /* active->nr should be zero when we call this */ + VM_BUG_ON_PAGE(tlb->active->nr, page); + __tlb_adjust_range(tlb, tlb->addr); + return __tlb_remove_page(tlb, page); +} + /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, -- cgit v1.2.3 From e77b0852b551ffd8b29fa0225e1ef62c195e3160 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:24:12 -0700 Subject: mm/mmu_gather: track page size with mmu gather and force flush if page size change This allows an arch which needs to do special handing with respect to different page size when flushing tlb to implement the same in mmu gather. Link: http://lkml.kernel.org/r/1465049193-22197-3-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 7b899a46a4cb..c6d667187608 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -112,6 +112,7 @@ struct mmu_gather { * that that we can adjust the range after the flush */ unsigned long addr; + int page_size; }; #define HAVE_GENERIC_MMU_GATHER @@ -120,7 +121,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long void tlb_flush_mmu(struct mmu_gather *tlb); void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); -bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page); +extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, + int page_size); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address) @@ -145,23 +147,36 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) } } +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + if (__tlb_remove_page_size(tlb, page, page_size)) { + tlb_flush_mmu(tlb); + tlb->page_size = page_size; + __tlb_adjust_range(tlb, tlb->addr); + __tlb_remove_page_size(tlb, page, page_size); + } +} + +static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +{ + return __tlb_remove_page_size(tlb, page, PAGE_SIZE); +} + /* tlb_remove_page * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when * required. */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - if (__tlb_remove_page(tlb, page)) { - tlb_flush_mmu(tlb); - __tlb_adjust_range(tlb, tlb->addr); - __tlb_remove_page(tlb, page); - } + return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { /* active->nr should be zero when we call this */ VM_BUG_ON_PAGE(tlb->active->nr, page); + tlb->page_size = PAGE_SIZE; __tlb_adjust_range(tlb, tlb->addr); return __tlb_remove_page(tlb, page); } -- cgit v1.2.3 From 99691addb42919251dcc082a70b7a11733dfcbcc Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:16 -0700 Subject: mm: remove pointless struct in struct page definition This patchset implements per kmemcg accounting of page tables (x86-only), pipe buffers, and unix socket buffers. Patches 1-3 are just cleanups that are not supposed to introduce any functional changes. Patches 4 and 5 move charge/uncharge to generic page allocator paths for the sake of accounting pipe and unix socket buffers. Patches 5-7 make x86 page tables, pipe buffers, and unix socket buffers accountable. This patch (of 8): ... to reduce indentation level thus leaving more space for comments. Link: http://lkml.kernel.org/r/f34ffe70fce2b0b9220856437f77972d67c14275.1464079537.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 68 +++++++++++++++++++++++------------------------- 1 file changed, 32 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 917f2b6a0cde..a50ad735d518 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -60,51 +60,47 @@ struct page { }; /* Second double word */ - struct { - union { - pgoff_t index; /* Our offset within mapping. */ - void *freelist; /* sl[aou]b first free object */ - /* page_deferred_list().prev -- second tail page */ - }; + union { + pgoff_t index; /* Our offset within mapping. */ + void *freelist; /* sl[aou]b first free object */ + /* page_deferred_list().prev -- second tail page */ + }; - union { + union { #if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) - /* Used for cmpxchg_double in slub */ - unsigned long counters; + /* Used for cmpxchg_double in slub */ + unsigned long counters; #else - /* - * Keep _refcount separate from slub cmpxchg_double - * data. As the rest of the double word is protected by - * slab_lock but _refcount is not. - */ - unsigned counters; + /* + * Keep _refcount separate from slub cmpxchg_double data. + * As the rest of the double word is protected by slab_lock + * but _refcount is not. + */ + unsigned counters; #endif + struct { - struct { - - union { - /* - * Count of ptes mapped in mms, to show - * when page is mapped & limit reverse - * map searches. - */ - atomic_t _mapcount; - - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - int units; /* SLOB */ - }; + union { /* - * Usage count, *USE WRAPPER FUNCTION* - * when manual accounting. See page_ref.h + * Count of ptes mapped in mms, to show when + * page is mapped & limit reverse map searches. */ - atomic_t _refcount; + atomic_t _mapcount; + + unsigned int active; /* SLAB */ + struct { /* SLUB */ + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; + int units; /* SLOB */ }; - unsigned int active; /* SLAB */ + /* + * Usage count, *USE WRAPPER FUNCTION* when manual + * accounting. See page_ref.h + */ + atomic_t _refcount; }; }; -- cgit v1.2.3 From 632c0a1affd861f81abdd136c886418571e19a51 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:18 -0700 Subject: mm: clean up non-standard page->_mapcount users - Add a proper comment to page->_mapcount. - Introduce a macro for generating helper functions. - Place all special page->_mapcount values next to each other so that readers can see all possible values and so we don't get duplicates. Link: http://lkml.kernel.org/r/502f49000e0b63e6c62e338fac6b420bf34fb526.1464079537.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 5 ++++ include/linux/page-flags.h | 73 ++++++++++++++++++++-------------------------- 2 files changed, 37 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a50ad735d518..79472b22d23f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -85,6 +85,11 @@ struct page { /* * Count of ptes mapped in mms, to show when * page is mapped & limit reverse map searches. + * + * Extra information about page type may be + * stored here for pages that are never mapped, + * in which case the value MUST BE <= -2. + * See page-flags.h for more details. */ atomic_t _mapcount; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f36dbb3a3060..96084ee74ee8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -604,54 +604,45 @@ TESTPAGEFLAG_FALSE(DoubleMap) #endif /* - * PageBuddy() indicate that the page is free and in the buddy system - * (see mm/page_alloc.c). - * - * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to - * -2 so that an underflow of the page_mapcount() won't be mistaken - * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very - * efficiently by most CPU architectures. + * For pages that are never mapped to userspace, page->mapcount may be + * used for storing extra information about page type. Any value used + * for this purpose must be <= -2, but it's better start not too close + * to -2 so that an underflow of the page_mapcount() won't be mistaken + * for a special page. */ -#define PAGE_BUDDY_MAPCOUNT_VALUE (-128) - -static inline int PageBuddy(struct page *page) -{ - return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE; +#define PAGE_MAPCOUNT_OPS(uname, lname) \ +static __always_inline int Page##uname(struct page *page) \ +{ \ + return atomic_read(&page->_mapcount) == \ + PAGE_##lname##_MAPCOUNT_VALUE; \ +} \ +static __always_inline void __SetPage##uname(struct page *page) \ +{ \ + VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page); \ + atomic_set(&page->_mapcount, PAGE_##lname##_MAPCOUNT_VALUE); \ +} \ +static __always_inline void __ClearPage##uname(struct page *page) \ +{ \ + VM_BUG_ON_PAGE(!Page##uname(page), page); \ + atomic_set(&page->_mapcount, -1); \ } -static inline void __SetPageBuddy(struct page *page) -{ - VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page); - atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE); -} +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +#define PAGE_BUDDY_MAPCOUNT_VALUE (-128) +PAGE_MAPCOUNT_OPS(Buddy, BUDDY) -static inline void __ClearPageBuddy(struct page *page) -{ - VM_BUG_ON_PAGE(!PageBuddy(page), page); - atomic_set(&page->_mapcount, -1); -} +/* + * PageBalloon() is set on pages that are on the balloon page list + * (see mm/balloon_compaction.c). + */ +#define PAGE_BALLOON_MAPCOUNT_VALUE (-256) +PAGE_MAPCOUNT_OPS(Balloon, BALLOON) extern bool is_free_buddy_page(struct page *page); -#define PAGE_BALLOON_MAPCOUNT_VALUE (-256) - -static inline int PageBalloon(struct page *page) -{ - return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE; -} - -static inline void __SetPageBalloon(struct page *page) -{ - VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page); - atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE); -} - -static inline void __ClearPageBalloon(struct page *page) -{ - VM_BUG_ON_PAGE(!PageBalloon(page), page); - atomic_set(&page->_mapcount, -1); -} - __PAGEFLAG(Isolated, isolated, PF_ANY); /* -- cgit v1.2.3 From 452647784b2fccfdeeb976f6f842c6719fb2daac Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:21 -0700 Subject: mm: memcontrol: cleanup kmem charge functions - Handle memcg_kmem_enabled check out to the caller. This reduces the number of function definitions making the code easier to follow. At the same time it doesn't result in code bloat, because all of these functions are used only in one or two places. - Move __GFP_ACCOUNT check to the caller as well so that one wouldn't have to dive deep into memcg implementation to see which allocations are charged and which are not. - Refresh comments. Link: http://lkml.kernel.org/r/52882a28b542c1979fd9a033b4dc8637fc347399.1464079537.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 103 +++------------------------------------------ 1 file changed, 7 insertions(+), 96 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 56e6069d2452..71aff733a497 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -749,6 +749,13 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) } #endif +struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); +void memcg_kmem_put_cache(struct kmem_cache *cachep); +int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, + struct mem_cgroup *memcg); +int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); +void memcg_kmem_uncharge(struct page *page, int order); + #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) extern struct static_key_false memcg_kmem_enabled_key; @@ -769,22 +776,6 @@ static inline bool memcg_kmem_enabled(void) return static_branch_unlikely(&memcg_kmem_enabled_key); } -/* - * In general, we'll do everything in our power to not incur in any overhead - * for non-memcg users for the kmem functions. Not even a function call, if we - * can avoid it. - * - * Therefore, we'll inline all those functions so that in the best case, we'll - * see that kmemcg is off for everybody and proceed quickly. If it is on, - * we'll still do most of the flag checking inline. We check a lot of - * conditions, but because they are pretty simple, they are expected to be - * fast. - */ -int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg); -int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); -void __memcg_kmem_uncharge(struct page *page, int order); - /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function @@ -795,67 +786,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } -struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp); -void __memcg_kmem_put_cache(struct kmem_cache *cachep); - -static inline bool __memcg_kmem_bypass(void) -{ - if (!memcg_kmem_enabled()) - return true; - if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) - return true; - return false; -} - -/** - * memcg_kmem_charge: charge a kmem page - * @page: page to charge - * @gfp: reclaim mode - * @order: allocation order - * - * Returns 0 on success, an error code on failure. - */ -static __always_inline int memcg_kmem_charge(struct page *page, - gfp_t gfp, int order) -{ - if (__memcg_kmem_bypass()) - return 0; - if (!(gfp & __GFP_ACCOUNT)) - return 0; - return __memcg_kmem_charge(page, gfp, order); -} - -/** - * memcg_kmem_uncharge: uncharge a kmem page - * @page: page to uncharge - * @order: allocation order - */ -static __always_inline void memcg_kmem_uncharge(struct page *page, int order) -{ - if (memcg_kmem_enabled()) - __memcg_kmem_uncharge(page, order); -} - -/** - * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation - * @cachep: the original global kmem cache - * - * All memory allocated from a per-memcg cache is charged to the owner memcg. - */ -static __always_inline struct kmem_cache * -memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) -{ - if (__memcg_kmem_bypass()) - return cachep; - return __memcg_kmem_get_cache(cachep, gfp); -} - -static __always_inline void memcg_kmem_put_cache(struct kmem_cache *cachep) -{ - if (memcg_kmem_enabled()) - __memcg_kmem_put_cache(cachep); -} - /** * memcg_kmem_update_page_stat - update kmem page state statistics * @page: the page @@ -878,15 +808,6 @@ static inline bool memcg_kmem_enabled(void) return false; } -static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) -{ - return 0; -} - -static inline void memcg_kmem_uncharge(struct page *page, int order) -{ -} - static inline int memcg_cache_id(struct mem_cgroup *memcg) { return -1; @@ -900,16 +821,6 @@ static inline void memcg_put_cache_ids(void) { } -static inline struct kmem_cache * -memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) -{ - return cachep; -} - -static inline void memcg_kmem_put_cache(struct kmem_cache *cachep) -{ -} - static inline void memcg_kmem_update_page_stat(struct page *page, enum mem_cgroup_stat_index idx, int val) { -- cgit v1.2.3 From 4949148ad433f6f11cf837978b2907092ec99f3a Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:24 -0700 Subject: mm: charge/uncharge kmemcg from generic page allocator paths Currently, to charge a non-slab allocation to kmemcg one has to use alloc_kmem_pages helper with __GFP_ACCOUNT flag. A page allocated with this helper should finally be freed using free_kmem_pages, otherwise it won't be uncharged. This API suits its current users fine, but it turns out to be impossible to use along with page reference counting, i.e. when an allocation is supposed to be freed with put_page, as it is the case with pipe or unix socket buffers. To overcome this limitation, this patch moves charging/uncharging to generic page allocator paths, i.e. to __alloc_pages_nodemask and free_pages_prepare, and zaps alloc/free_kmem_pages helpers. This way, one can use any of the available page allocation functions to get the allocated page charged to kmemcg - it's enough to pass __GFP_ACCOUNT, just like in case of kmalloc and friends. A charged page will be automatically uncharged on free. To make it possible, we need to mark pages charged to kmemcg somehow. To avoid introducing a new page flag, we make use of page->_mapcount for marking such pages. Since pages charged to kmemcg are not supposed to be mapped to userspace, it should work just fine. There are other (ab)users of page->_mapcount - buddy and balloon pages - but we don't conflict with them. In case kmemcg is compiled out or not used at runtime, this patch introduces no overhead to generic page allocator paths. If kmemcg is used, it will be plus one gfp flags check on alloc and plus one page->_mapcount check on free, which shouldn't hurt performance, because the data accessed are hot. Link: http://lkml.kernel.org/r/a9736d856f895bcb465d9f257b54efe32eda6f99.1464079538.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 10 +--------- include/linux/page-flags.h | 7 +++++++ 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 570383a41853..c29e9d347bc6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -78,8 +78,7 @@ struct vm_area_struct; * __GFP_THISNODE forces the allocation to be satisified from the requested * node with no fallbacks or placement policy enforcements. * - * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg (only relevant - * to kmem allocations). + * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) @@ -486,10 +485,6 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) -extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order); -extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, - unsigned int order); - extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); @@ -513,9 +508,6 @@ extern void *__alloc_page_frag(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void __free_page_frag(void *addr); -extern void __free_kmem_pages(struct page *page, unsigned int order); -extern void free_kmem_pages(unsigned long addr, unsigned int order); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 96084ee74ee8..7c8e82ac2eb7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -641,6 +641,13 @@ PAGE_MAPCOUNT_OPS(Buddy, BUDDY) #define PAGE_BALLOON_MAPCOUNT_VALUE (-256) PAGE_MAPCOUNT_OPS(Balloon, BALLOON) +/* + * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on + * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. + */ +#define PAGE_KMEMCG_MAPCOUNT_VALUE (-512) +PAGE_MAPCOUNT_OPS(Kmemcg, KMEMCG) + extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); -- cgit v1.2.3 From fbe84a09da746f781553051bb3dbc63f7b0a5162 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 26 Jul 2016 15:24:39 -0700 Subject: mm,oom: remove unused argument from oom_scan_process_thread(). oom_scan_process_thread() does not use totalpages argument. oom_badness() uses it. Link: http://lkml.kernel.org/r/1463796041-7889-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index cbc24a5fe28d..606137b3b778 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -92,7 +92,7 @@ extern void check_panic_on_oom(struct oom_control *oc, enum oom_constraint constraint); extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, - struct task_struct *task, unsigned long totalpages); + struct task_struct *task); extern bool out_of_memory(struct oom_control *oc); -- cgit v1.2.3 From 8ea1d2a1985a7ae096edf5850a31d844ad1b8e97 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 26 Jul 2016 15:24:42 -0700 Subject: mm, frontswap: convert frontswap_enabled to static key I have noticed that frontswap.h first declares "frontswap_enabled" as extern bool variable, and then overrides it with "#define frontswap_enabled (1)" for CONFIG_FRONTSWAP=Y or (0) when disabled. The bool variable isn't actually instantiated anywhere. This all looks like an unfinished attempt to make frontswap_enabled reflect whether a backend is instantiated. But in the current state, all frontswap hooks call unconditionally into frontswap.c just to check if frontswap_ops is non-NULL. This should at least be checked inline, but we can further eliminate the overhead when CONFIG_FRONTSWAP is enabled and no backend registered, using a static key that is initially disabled, and gets enabled only upon first backend registration. Thus, checks for "frontswap_enabled" are replaced with "frontswap_enabled()" wrapping the static key check. There are two exceptions: - xen's selfballoon_process() was testing frontswap_enabled in code guarded by #ifdef CONFIG_FRONTSWAP, which was effectively always true when reachable. The patch just removes this check. Using frontswap_enabled() does not sound correct here, as this can be true even without xen's own backend being registered. - in SYSCALL_DEFINE2(swapon), change the check to IS_ENABLED(CONFIG_FRONTSWAP) as it seems the bitmap allocation cannot currently be postponed until a backend is registered. This means that frontswap will still have some memory overhead by being configured, but without a backend. After the patch, we can expect that some functions in frontswap.c are called only when frontswap_ops is non-NULL. Change the checks there to VM_BUG_ONs. While at it, convert other BUG_ONs to VM_BUG_ONs as frontswap has been stable for some time. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1463152235-9717-1-git-send-email-vbabka@suse.cz Signed-off-by: Vlastimil Babka Cc: Konrad Rzeszutek Wilk Cc: Boris Ostrovsky Cc: David Vrabel Cc: Juergen Gross Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index e65ef959546c..c46d2aa16d81 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -4,6 +4,7 @@ #include #include #include +#include struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ @@ -14,7 +15,6 @@ struct frontswap_ops { struct frontswap_ops *next; /* private pointer to next ops */ }; -extern bool frontswap_enabled; extern void frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); @@ -30,7 +30,12 @@ extern void __frontswap_invalidate_page(unsigned, pgoff_t); extern void __frontswap_invalidate_area(unsigned); #ifdef CONFIG_FRONTSWAP -#define frontswap_enabled (1) +extern struct static_key_false frontswap_enabled_key; + +static inline bool frontswap_enabled(void) +{ + return static_branch_unlikely(&frontswap_enabled_key); +} static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { @@ -50,7 +55,10 @@ static inline unsigned long *frontswap_map_get(struct swap_info_struct *p) #else /* all inline routines become no-ops and all externs are ignored */ -#define frontswap_enabled (0) +static inline bool frontswap_enabled(void) +{ + return false; +} static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { @@ -70,37 +78,35 @@ static inline unsigned long *frontswap_map_get(struct swap_info_struct *p) static inline int frontswap_store(struct page *page) { - int ret = -1; + if (frontswap_enabled()) + return __frontswap_store(page); - if (frontswap_enabled) - ret = __frontswap_store(page); - return ret; + return -1; } static inline int frontswap_load(struct page *page) { - int ret = -1; + if (frontswap_enabled()) + return __frontswap_load(page); - if (frontswap_enabled) - ret = __frontswap_load(page); - return ret; + return -1; } static inline void frontswap_invalidate_page(unsigned type, pgoff_t offset) { - if (frontswap_enabled) + if (frontswap_enabled()) __frontswap_invalidate_page(type, offset); } static inline void frontswap_invalidate_area(unsigned type) { - if (frontswap_enabled) + if (frontswap_enabled()) __frontswap_invalidate_area(type); } static inline void frontswap_init(unsigned type, unsigned long *map) { - if (frontswap_enabled) + if (frontswap_enabled()) __frontswap_init(type, map); } -- cgit v1.2.3 From 91537fee001361b1a4d485f1af65d8efa03d49b5 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 26 Jul 2016 15:24:45 -0700 Subject: mm: add NR_ZSMALLOC to vmstat zram is very popular for some of the embedded world (e.g., TV, mobile phones). On those system, zsmalloc's consumed memory size is never trivial (one of example from real product system, total memory: 800M, zsmalloc consumed: 150M), so we have used this out of tree patch to monitor system memory behavior via /proc/vmstat. With zsmalloc in vmstat, it helps in tracking down system behavior due to memory usage. [minchan@kernel.org: zsmalloc: follow up zsmalloc vmstat] Link: http://lkml.kernel.org/r/20160607091737.GC23435@bbox [akpm@linux-foundation.org: fix build with CONFIG_ZSMALLOC=m] Link: http://lkml.kernel.org/r/1464919731-13255-1-git-send-email-minchan@kernel.org Signed-off-by: Minchan Kim Cc: Sangseok Lee Cc: Chanho Min Cc: Chan Gyun Jeong Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3388ccbab7d6..3d7ab30d4940 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -140,6 +140,9 @@ enum zone_stat_item { NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_PAGES_SCANNED, /* pages scanned since last reclaim */ +#if IS_ENABLED(CONFIG_ZSMALLOC) + NR_ZSPAGES, /* allocated in zsmalloc */ +#endif #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ -- cgit v1.2.3 From ba6c19fd113a3965f8cf4c183a813d528008d03e Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Tue, 26 Jul 2016 15:24:47 -0700 Subject: include/linux/memblock.h: Clean up code for several trivial details Correct the function parameters alignment, since original code already use both tabs and white spaces together for the incorrect parameters alignment functions. If one line can hold one statement within 80 columns, let it in one line (original code did not consider about the tabs/spaces for 2nd line when a statement is separated into 2 lines). Try to let '' aligned within one macro, since all related lines are short enough. Remove useless statement "idx = 0;", and always assign rgn within the 'for' statement. Link: http://lkml.kernel.org/r/1464904899-1714-1-git-send-email-chengang@emindsoft.com.cn Signed-off-by: Chen Gang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 3106ac1c895e..6c14b6179727 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -73,8 +73,8 @@ extern bool movable_node_enabled; if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, - phys_addr_t start, phys_addr_t end, - int nid, ulong flags); + phys_addr_t start, phys_addr_t end, + int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); @@ -110,7 +110,7 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, phys_addr_t *out_end, int *out_nid); void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, - phys_addr_t *out_end); + phys_addr_t *out_end); /** * for_each_mem_range - iterate through memblock areas from type_a and not @@ -148,7 +148,7 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, p_start, p_end, p_nid) \ for (i = (u64)ULLONG_MAX, \ __next_mem_range_rev(&i, nid, flags, type_a, type_b,\ - p_start, p_end, p_nid); \ + p_start, p_end, p_nid); \ i != (u64)ULLONG_MAX; \ __next_mem_range_rev(&i, nid, flags, type_a, type_b, \ p_start, p_end, p_nid)) @@ -163,8 +163,7 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, * is initialized. */ #define for_each_reserved_mem_region(i, p_start, p_end) \ - for (i = 0UL, \ - __next_reserved_mem_region(&i, p_start, p_end); \ + for (i = 0UL, __next_reserved_mem_region(&i, p_start, p_end); \ i != (u64)ULLONG_MAX; \ __next_reserved_mem_region(&i, p_start, p_end)) @@ -403,15 +402,14 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo } #define for_each_memblock(memblock_type, region) \ - for (region = memblock.memblock_type.regions; \ + for (region = memblock.memblock_type.regions; \ region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \ region++) #define for_each_memblock_type(memblock_type, rgn) \ - idx = 0; \ - rgn = &memblock_type->regions[idx]; \ - for (idx = 0; idx < memblock_type->cnt; \ - idx++,rgn = &memblock_type->regions[idx]) + for (idx = 0, rgn = &memblock_type->regions[0]; \ + idx < memblock_type->cnt; \ + idx++, rgn = &memblock_type->regions[idx]) #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); -- cgit v1.2.3 From 8a5c743e308dd2b90ad10d1faaa7a1b09173a132 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2016 15:24:53 -0700 Subject: mm, memcg: use consistent gfp flags during readahead Vladimir has noticed that we might declare memcg oom even during readahead because read_pages only uses GFP_KERNEL (with mapping_gfp restriction) while __do_page_cache_readahead uses page_cache_alloc_readahead which adds __GFP_NORETRY to prevent from OOMs. This gfp mask discrepancy is really unfortunate and easily fixable. Drop page_cache_alloc_readahead() which only has one user and outsource the gfp_mask logic into readahead_gfp_mask and propagate this mask from __do_page_cache_readahead down to read_pages. This alone would have only very limited impact as most filesystems are implementing ->readpages and the common implementation mpage_readpages does GFP_KERNEL (with mapping_gfp restriction) again. We can tell it to use readahead_gfp_mask instead as this function is called only during readahead as well. The same applies to read_cache_pages. ext4 has its own ext4_mpage_readpages but the path which has pages != NULL can use the same gfp mask. Btrfs, cifs, f2fs and orangefs are doing a very similar pattern to mpage_readpages so the same can be applied to them as well. [akpm@linux-foundation.org: coding-style fixes] [mhocko@suse.com: restrict gfp mask in mpage_alloc] Link: http://lkml.kernel.org/r/20160610074223.GC32285@dhcp22.suse.cz Link: http://lkml.kernel.org/r/1465301556-26431-1-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Vladimir Davydov Cc: Chris Mason Cc: Steve French Cc: Theodore Ts'o Cc: Jan Kara Cc: Mike Marshall Cc: Jaegeuk Kim Cc: Changman Lee Cc: Chao Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 97354102794d..81363b834900 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -209,10 +209,10 @@ static inline struct page *page_cache_alloc_cold(struct address_space *x) return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD); } -static inline struct page *page_cache_alloc_readahead(struct address_space *x) +static inline gfp_t readahead_gfp_mask(struct address_space *x) { - return __page_cache_alloc(mapping_gfp_mask(x) | - __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN); + return mapping_gfp_mask(x) | + __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(void *, struct page *); -- cgit v1.2.3 From 70652f6ec0566ae6b4147d88c6d043c68484227f Mon Sep 17 00:00:00 2001 From: Ebru Akagunduz Date: Tue, 26 Jul 2016 15:24:59 -0700 Subject: mm: make optimistic check for swapin readahead Introduce a new sysfs integer knob /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap which makes optimistic check for swapin readahead to increase thp collapse rate. Before getting swapped out pages to memory, checks them and allows up to a certain number. It also prints out using tracepoints amount of unmapped ptes. [vdavydov@parallels.com: fix scan not aborted on SCAN_EXCEED_SWAP_PTE] [sfr@canb.auug.org.au: build fix] Link: http://lkml.kernel.org/r/20160616154503.65806e12@canb.auug.org.au Signed-off-by: Ebru Akagunduz Acked-by: Rik van Riel Cc: Kirill A. Shutemov Cc: Naoya Horiguchi Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Xie XiuQi Cc: Cyrill Gorcunov Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Hugh Dickins Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/huge_memory.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 551ba4acde4d..fad6539c9d68 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -28,7 +28,8 @@ EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \ EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ - EMe( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") + EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ + EMe( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") #undef EM #undef EMe @@ -45,9 +46,9 @@ SCAN_STATUS TRACE_EVENT(mm_khugepaged_scan_pmd, TP_PROTO(struct mm_struct *mm, struct page *page, bool writable, - bool referenced, int none_or_zero, int status), + bool referenced, int none_or_zero, int status, int unmapped), - TP_ARGS(mm, page, writable, referenced, none_or_zero, status), + TP_ARGS(mm, page, writable, referenced, none_or_zero, status, unmapped), TP_STRUCT__entry( __field(struct mm_struct *, mm) @@ -56,6 +57,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, __field(bool, referenced) __field(int, none_or_zero) __field(int, status) + __field(int, unmapped) ), TP_fast_assign( @@ -65,15 +67,17 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, __entry->referenced = referenced; __entry->none_or_zero = none_or_zero; __entry->status = status; + __entry->unmapped = unmapped; ), - TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s", + TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s, unmapped=%d", __entry->mm, __entry->pfn, __entry->writable, __entry->referenced, __entry->none_or_zero, - __print_symbolic(__entry->status, SCAN_STATUS)) + __print_symbolic(__entry->status, SCAN_STATUS), + __entry->unmapped) ); TRACE_EVENT(mm_collapse_huge_page, -- cgit v1.2.3 From 8a966ed746d63c8103d496da85973eeeec01d77f Mon Sep 17 00:00:00 2001 From: Ebru Akagunduz Date: Tue, 26 Jul 2016 15:25:03 -0700 Subject: mm: make swapin readahead to improve thp collapse rate This patch makes swapin readahead to improve thp collapse rate. When khugepaged scanned pages, there can be a few of the pages in swap area. With the patch THP can collapse 4kB pages into a THP when there are up to max_ptes_swap swap ptes in a 2MB range. The patch was tested with a test program that allocates 400B of memory, writes to it, and then sleeps. I force the system to swap out all. Afterwards, the test program touches the area by writing, it skips a page in each 20 pages of the area. Without the patch, system did not swap in readahead. THP rate was %65 of the program of the memory, it did not change over time. With this patch, after 10 minutes of waiting khugepaged had collapsed %99 of the program's memory. [kirill.shutemov@linux.intel.com: trivial cleanup of exit path of the function] [kirill.shutemov@linux.intel.com: __collapse_huge_page_swapin(): drop unused 'pte' parameter] [kirill.shutemov@linux.intel.com: do not hold anon_vma lock during swap in] Signed-off-by: Ebru Akagunduz Acked-by: Rik van Riel Cc: Naoya Horiguchi Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Xie XiuQi Cc: Cyrill Gorcunov Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Hugh Dickins Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/huge_memory.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index fad6539c9d68..bda21183eb05 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -135,5 +135,29 @@ TRACE_EVENT(mm_collapse_huge_page_isolate, __print_symbolic(__entry->status, SCAN_STATUS)) ); +TRACE_EVENT(mm_collapse_huge_page_swapin, + + TP_PROTO(struct mm_struct *mm, int swapped_in, int ret), + + TP_ARGS(mm, swapped_in, ret), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(int, swapped_in) + __field(int, ret) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->swapped_in = swapped_in; + __entry->ret = ret; + ), + + TP_printk("mm=%p, swapped_in=%d, ret=%d", + __entry->mm, + __entry->swapped_in, + __entry->ret) +); + #endif /* __HUGE_MEMORY_H */ #include -- cgit v1.2.3 From dcddffd41d3f1d3bdcc1dce3f1cd142779b6d4c1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:18 -0700 Subject: mm: do not pass mm_struct into handle_mm_fault We always have vma->vm_mm around. Link: http://lkml.kernel.org/r/1466021202-61880-8-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6c9a394b2979..646bc36b4d1b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1215,15 +1215,14 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU -extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, unsigned int flags); +extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, + unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); #else -static inline int handle_mm_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - unsigned int flags) +static inline int handle_mm_fault(struct vm_area_struct *vma, + unsigned long address, unsigned int flags) { /* should never happen if there's no MMU */ BUG(); -- cgit v1.2.3 From bae473a423f65e480db83c85b5e92254f6dfcb28 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:20 -0700 Subject: mm: introduce fault_env The idea borrowed from Peter's patch from patchset on speculative page faults[1]: Instead of passing around the endless list of function arguments, replace the lot with a single structure so we can change context without endless function signature changes. The changes are mostly mechanical with exception of faultaround code: filemap_map_pages() got reworked a bit. This patch is preparation for the next one. [1] http://lkml.kernel.org/r/20141020222841.302891540@infradead.org Link: http://lkml.kernel.org/r/1466021202-61880-9-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 20 +++++--------------- include/linux/mm.h | 34 ++++++++++++++++++++++++++-------- include/linux/userfaultfd_k.h | 8 ++------ 3 files changed, 33 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f0a7a0320300..9bed9249156f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,20 +1,12 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H -extern int do_huge_pmd_anonymous_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - unsigned int flags); +extern int do_huge_pmd_anonymous_page(struct fault_env *fe); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma); -extern void huge_pmd_set_accessed(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pmd_t orig_pmd, int dirty); -extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, - pmd_t orig_pmd); +extern void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd); +extern int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd); extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, @@ -134,8 +126,7 @@ static inline int hpage_nr_pages(struct page *page) return 1; } -extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, pmd_t *pmdp); +extern int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd); extern struct page *huge_zero_page; @@ -196,8 +187,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, return NULL; } -static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, pmd_t *pmdp) +static inline int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd) { return 0; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 646bc36b4d1b..8bd74558c0e4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -309,10 +309,27 @@ struct vm_fault { * VM_FAULT_DAX_LOCKED and fill in * entry here. */ - /* for ->map_pages() only */ - pgoff_t max_pgoff; /* map pages for offset from pgoff till - * max_pgoff inclusive */ - pte_t *pte; /* pte entry associated with ->pgoff */ +}; + +/* + * Page fault context: passes though page fault handler instead of endless list + * of function arguments. + */ +struct fault_env { + struct vm_area_struct *vma; /* Target VMA */ + unsigned long address; /* Faulting virtual address */ + unsigned int flags; /* FAULT_FLAG_xxx flags */ + pmd_t *pmd; /* Pointer to pmd entry matching + * the 'address' + */ + pte_t *pte; /* Pointer to pte entry matching + * the 'address'. NULL if the page + * table hasn't been allocated. + */ + spinlock_t *ptl; /* Page table lock. + * Protects pte page table if 'pte' + * is not NULL, otherwise pmd. + */ }; /* @@ -327,7 +344,8 @@ struct vm_operations_struct { int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); int (*pmd_fault)(struct vm_area_struct *, unsigned long address, pmd_t *, unsigned int flags); - void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf); + void (*map_pages)(struct fault_env *fe, + pgoff_t start_pgoff, pgoff_t end_pgoff); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -600,8 +618,7 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -void do_set_pte(struct vm_area_struct *vma, unsigned long address, - struct page *page, pte_t *pte, bool write, bool anon); +void do_set_pte(struct fault_env *fe, struct page *page); #endif /* @@ -2062,7 +2079,8 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); -extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf); +extern void filemap_map_pages(struct fault_env *fe, + pgoff_t start_pgoff, pgoff_t end_pgoff); extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); /* mm/page-writeback.c */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 587480ad41b7..dd66a952e8cd 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -27,8 +27,7 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int handle_userfault(struct vm_area_struct *vma, unsigned long address, - unsigned int flags, unsigned long reason); +extern int handle_userfault(struct fault_env *fe, unsigned long reason); extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len); @@ -56,10 +55,7 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) #else /* CONFIG_USERFAULTFD */ /* mm helpers */ -static inline int handle_userfault(struct vm_area_struct *vma, - unsigned long address, - unsigned int flags, - unsigned long reason) +static inline int handle_userfault(struct fault_env *fe, unsigned long reason) { return VM_FAULT_SIGBUS; } -- cgit v1.2.3 From 7267ec008b5cd8b3579e188b1ff238815643e372 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:23 -0700 Subject: mm: postpone page table allocation until we have page to map The idea (and most of code) is borrowed again: from Hugh's patchset on huge tmpfs[1]. Instead of allocation pte page table upfront, we postpone this until we have page to map in hands. This approach opens possibility to map the page as huge if filesystem supports this. Comparing to Hugh's patch I've pushed page table allocation a bit further: into do_set_pte(). This way we can postpone allocation even in faultaround case without moving do_fault_around() after __do_fault(). do_set_pte() got renamed to alloc_set_pte() as it can allocate page table if required. [1] http://lkml.kernel.org/r/alpine.LSU.2.11.1502202015090.14414@eggly.anvils Link: http://lkml.kernel.org/r/1466021202-61880-10-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8bd74558c0e4..192c1bbe5fcd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -330,6 +330,13 @@ struct fault_env { * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ + pgtable_t prealloc_pte; /* Pre-allocated pte page table. + * vm_ops->map_pages() calls + * alloc_set_pte() from atomic context. + * do_fault_around() pre-allocates + * page table to avoid allocation from + * atomic context. + */ }; /* @@ -618,7 +625,8 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -void do_set_pte(struct fault_env *fe, struct page *page); +int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg, + struct page *page); #endif /* -- cgit v1.2.3 From dd78fedde4b99b322f2dc849d467d365a82e23ca Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:26 -0700 Subject: rmap: support file thp Naive approach: on mapping/unmapping the page as compound we update ->_mapcount on each 4k page. That's not efficient, but it's not obvious how we can optimize this. We can look into optimization later. PG_double_map optimization doesn't work for file pages since lifecycle of file pages is different comparing to anon pages: file page can be mapped again at any time. Link: http://lkml.kernel.org/r/1466021202-61880-11-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 2b0fad83683f..b46bb5620a76 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -165,7 +165,7 @@ void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); -void page_add_file_rmap(struct page *); +void page_add_file_rmap(struct page *, bool); void page_remove_rmap(struct page *, bool); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, -- cgit v1.2.3 From 1010245964415bb7403463115bab2cd26244b445 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:29 -0700 Subject: mm: introduce do_set_pmd() With postponed page table allocation we have chance to setup huge pages. do_set_pte() calls do_set_pmd() if following criteria met: - page is compound; - pmd entry in pmd_none(); - vma has suitable size and alignment; Link: http://lkml.kernel.org/r/1466021202-61880-12-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9bed9249156f..254aac4c3963 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -143,6 +143,8 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) struct page *get_huge_zero_page(void); void put_huge_zero_page(void); +#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) -- cgit v1.2.3 From 95ecedcd6abbb05d8177331e2fa697888dcd634b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:31 -0700 Subject: thp, vmstats: add counters for huge file pages THP_FILE_ALLOC: how many times huge page was allocated and put page cache. THP_FILE_MAPPED: how many times file huge page was mapped. Link: http://lkml.kernel.org/r/1466021202-61880-13-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index ec084321fe09..42604173f122 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -70,6 +70,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_FAULT_FALLBACK, THP_COLLAPSE_ALLOC, THP_COLLAPSE_ALLOC_FAILED, + THP_FILE_ALLOC, + THP_FILE_MAPPED, THP_SPLIT_PAGE, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, @@ -100,4 +102,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NR_VM_EVENT_ITEMS }; +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +#define THP_FILE_ALLOC ({ BUILD_BUG(); 0; }) +#define THP_FILE_MAPPED ({ BUILD_BUG(); 0; }) +#endif + #endif /* VM_EVENT_ITEM_H_INCLUDED */ -- cgit v1.2.3 From 9a73f61bdb8acdc01bbaf72a3fe0a8854f2463ad Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:53 -0700 Subject: thp, mlock: do not mlock PTE-mapped file huge pages As with anon THP, we only mlock file huge pages if we can prove that the page is not mapped with PTE. This way we can avoid mlock leak into non-mlocked vma on split. We rely on PageDoubleMap() under lock_page() to check if the the page may be PTE mapped. PG_double_map is set by page_add_file_rmap() when the page mapped with PTEs. Link: http://lkml.kernel.org/r/1466021202-61880-21-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 7c8e82ac2eb7..8cf09639185a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -581,6 +581,17 @@ static inline int PageDoubleMap(struct page *page) return PageHead(page) && test_bit(PG_double_map, &page[1].flags); } +static inline void SetPageDoubleMap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + set_bit(PG_double_map, &page[1].flags); +} + +static inline void ClearPageDoubleMap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageHead(page), page); + clear_bit(PG_double_map, &page[1].flags); +} static inline int TestSetPageDoubleMap(struct page *page) { VM_BUG_ON_PAGE(!PageHead(page), page); @@ -598,7 +609,7 @@ TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) -TESTPAGEFLAG_FALSE(DoubleMap) +PAGEFLAG_FALSE(DoubleMap) TESTSETFLAG_FALSE(DoubleMap) TESTCLEARFLAG_FALSE(DoubleMap) #endif -- cgit v1.2.3 From e2f0a0db95979a4aa951d883248da9d361507abf Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:59 -0700 Subject: page-flags: relax policy for PG_mappedtodisk and PG_reclaim These flags are in use for file THP. Link: http://lkml.kernel.org/r/1466021202-61880-23-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8cf09639185a..74e4dda91238 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -295,11 +295,11 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) */ TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) -PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND) +PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ -PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND) - TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND) +PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) + TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) -- cgit v1.2.3 From c78c66d1ddfdbd2353f3fcfeba0268524537b096 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:02 -0700 Subject: radix-tree: implement radix_tree_maybe_preload_order() The new helper is similar to radix_tree_maybe_preload(), but tries to preload number of nodes required to insert (1 << order) continuous naturally-aligned elements. This is required to push huge pages into pagecache. Link: http://lkml.kernel.org/r/1466021202-61880-24-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov 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 eca6f626c16e..cbfee507c839 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -291,6 +291,7 @@ unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); +int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag); -- cgit v1.2.3 From 65c453778aea374a46597f4d9826274d1eaf7338 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:10 -0700 Subject: mm, rmap: account shmem thp pages Let's add ShmemHugePages and ShmemPmdMapped fields into meminfo and smaps. It indicates how many times we allocate and map shmem THP. NR_ANON_TRANSPARENT_HUGEPAGES is renamed to NR_ANON_THPS. Link: http://lkml.kernel.org/r/1466021202-61880-27-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3d7ab30d4940..19425e988bdc 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -154,7 +154,9 @@ enum zone_stat_item { WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_NODERECLAIM, - NR_ANON_TRANSPARENT_HUGEPAGES, + NR_ANON_THPS, + NR_SHMEM_THPS, + NR_SHMEM_PMDMAPPED, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; -- cgit v1.2.3 From 5a6e75f8110c97e2a5488894d4e922187e6cb343 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:13 -0700 Subject: shmem: prepare huge= mount option and sysfs knob This patch adds new mount option "huge=". It can have following values: - "always": Attempt to allocate huge pages every time we need a new page; - "never": Do not allocate huge pages; - "within_size": Only allocate huge page if it will be fully within i_size. Also respect fadvise()/madvise() hints; - "advise: Only allocate huge pages if requested with fadvise()/madvise(); Default is "never" for now. "mount -o remount,huge= /mountpoint" works fine after mount: remounting huge=never will not attempt to break up huge pages at all, just stop more from being allocated. No new config option: put this under CONFIG_TRANSPARENT_HUGEPAGE, which is the appropriate option to protect those who don't want the new bloat, and with which we shall share some pmd code. Prohibit the option when !CONFIG_TRANSPARENT_HUGEPAGE, just as mpol is invalid without CONFIG_NUMA (was hidden in mpol_parse_str(): make it explicit). Allow enabling THP only if the machine has_transparent_hugepage(). But what about Shmem with no user-visible mount? SysV SHM, memfds, shared anonymous mmaps (of /dev/zero or MAP_ANONYMOUS), GPU drivers' DRM objects, Ashmem. Though unlikely to suit all usages, provide sysfs knob /sys/kernel/mm/transparent_hugepage/shmem_enabled to experiment with huge on those. And allow shmem_enabled two further values: - "deny": For use in emergencies, to force the huge option off from all mounts; - "force": Force the huge option on for all - very useful for testing; Based on patch by Hugh Dickins. Link: http://lkml.kernel.org/r/1466021202-61880-28-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ include/linux/shmem_fs.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 254aac4c3963..2f757132662a 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -41,6 +41,8 @@ enum transparent_hugepage_flag { #endif }; +extern struct kobj_attribute shmem_enabled_attr; + #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1< Date: Tue, 26 Jul 2016 15:26:15 -0700 Subject: shmem: get_unmapped_area align huge page Provide a shmem_get_unmapped_area method in file_operations, called at mmap time to decide the mapping address. It could be conditional on CONFIG_TRANSPARENT_HUGEPAGE, but save #ifdefs in other places by making it unconditional. shmem_get_unmapped_area() first calls the usual mm->get_unmapped_area (which we treat as a black box, highly dependent on architecture and config and executable layout). Lots of conditions, and in most cases it just goes with the address that chose; but when our huge stars are rightly aligned, yet that did not provide a suitable address, go back to ask for a larger arena, within which to align the mapping suitably. There have to be some direct calls to shmem_get_unmapped_area(), not via the file_operations: because of the way shmem_zero_setup() is called to create a shmem object late in the mmap sequence, when MAP_SHARED is requested with MAP_ANONYMOUS or /dev/zero. Though this only matters when /proc/sys/vm/shmem_huge has been set. Link: http://lkml.kernel.org/r/1466021202-61880-29-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Hugh Dickins Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 466f18c73a49..ff2de4bab61f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -50,6 +50,8 @@ extern struct file *shmem_file_setup(const char *name, extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); +extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); -- cgit v1.2.3 From 800d8c63b2e989c2e349632d1648119bf5862f01 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:18 -0700 Subject: shmem: add huge pages support Here's basic implementation of huge pages support for shmem/tmpfs. It's all pretty streight-forward: - shmem_getpage() allcoates huge page if it can and try to inserd into radix tree with shmem_add_to_page_cache(); - shmem_add_to_page_cache() puts the page onto radix-tree if there's space for it; - shmem_undo_range() removes huge pages, if it fully within range. Partial truncate of huge pages zero out this part of THP. This have visible effect on fallocate(FALLOC_FL_PUNCH_HOLE) behaviour. As we don't really create hole in this case, lseek(SEEK_HOLE) may have inconsistent results depending what pages happened to be allocated. - no need to change shmem_fault: core-mm will map an compound page as huge if VMA is suitable; Link: http://lkml.kernel.org/r/1466021202-61880-30-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ include/linux/shmem_fs.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2f757132662a..7b7406e9fedf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -156,6 +156,8 @@ void put_huge_zero_page(void); #define transparent_hugepage_enabled(__vma) 0 +static inline void prep_transhuge_page(struct page *page) {} + #define transparent_hugepage_flags 0UL static inline int split_huge_page_to_list(struct page *page, struct list_head *list) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ff2de4bab61f..94eaaa2c6ad9 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -71,6 +71,9 @@ static inline struct page *shmem_read_mapping_page( mapping_gfp_mask(mapping)); } +extern bool shmem_charge(struct inode *inode, long pages); +extern void shmem_uncharge(struct inode *inode, long pages); + #ifdef CONFIG_TMPFS extern int shmem_add_seals(struct file *file, unsigned int seals); -- cgit v1.2.3 From b46e756f5e47031c67658ff036e5ffe27062fa43 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:24 -0700 Subject: thp: extract khugepaged from mm/huge_memory.c khugepaged implementation grew to the point when it deserve separate file in source. Let's move it to mm/khugepaged.c. Link: http://lkml.kernel.org/r/1466021202-61880-32-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 10 ++++++++++ include/linux/khugepaged.h | 5 +++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7b7406e9fedf..92ce91c03cd0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -41,6 +41,16 @@ enum transparent_hugepage_flag { #endif }; +struct kobject; +struct kobj_attribute; + +extern ssize_t single_hugepage_flag_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count, + enum transparent_hugepage_flag flag); +extern ssize_t single_hugepage_flag_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf, + enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index eeb307985715..1e032a1ddb3e 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -4,6 +4,11 @@ #include /* MMF_VM_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern struct attribute_group khugepaged_attr_group; + +extern int khugepaged_init(void); +extern void khugepaged_destroy(void); +extern int start_stop_khugepaged(void); extern int __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, -- cgit v1.2.3 From f3f0e1d2150b2b99da2cbdfaad000089efe9bf30 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:32 -0700 Subject: khugepaged: add support of collapse for tmpfs/shmem pages This patch extends khugepaged to support collapse of tmpfs/shmem pages. We share fair amount of infrastructure with anon-THP collapse. Few design points: - First we are looking for VMA which can be suitable for mapping huge page; - If the VMA maps shmem file, the rest scan/collapse operations operates on page cache, not on page tables as in anon VMA case. - khugepaged_scan_shmem() finds a range which is suitable for huge page. The scan is lockless and shouldn't disturb system too much. - once the candidate for collapse is found, collapse_shmem() attempts to create a huge page: + scan over radix tree, making the range point to new huge page; + new huge page is not-uptodate, locked and freezed (refcount is 0), so nobody can touch them until we say so. + we swap in pages during the scan. khugepaged_scan_shmem() filters out ranges with more than khugepaged_max_ptes_swap swapped out pages. It's HPAGE_PMD_NR/8 by default. + old pages are isolated, unmapped and put to local list in case to be restored back if collapse failed. - if collapse succeed, we retract pte page tables from VMAs where huge pages mapping is possible. The huge page will be mapped as PMD on next minor fault into the range. Link: http://lkml.kernel.org/r/1466021202-61880-35-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 23 +++++++++++++++++++++++ include/trace/events/huge_memory.h | 3 ++- 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 94eaaa2c6ad9..0890f700a546 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -54,6 +54,7 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern bool shmem_mapping(struct address_space *mapping); +extern bool shmem_huge_enabled(struct vm_area_struct *vma); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); @@ -64,6 +65,19 @@ extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); +/* Flag allocation requirements to shmem_getpage */ +enum sgp_type { + SGP_READ, /* don't exceed i_size, don't allocate page */ + SGP_CACHE, /* don't exceed i_size, may allocate page */ + SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */ + SGP_HUGE, /* like SGP_CACHE, huge pages preferred */ + SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ + SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ +}; + +extern int shmem_getpage(struct inode *inode, pgoff_t index, + struct page **pagep, enum sgp_type sgp); + static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { @@ -71,6 +85,15 @@ static inline struct page *shmem_read_mapping_page( mapping_gfp_mask(mapping)); } +static inline bool shmem_file(struct file *file) +{ + if (!IS_ENABLED(CONFIG_SHMEM)) + return false; + if (!file || !file->f_mapping) + return false; + return shmem_mapping(file->f_mapping); +} + extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index bda21183eb05..830d47d5ca41 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -29,7 +29,8 @@ EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ - EMe( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") + EM( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") \ + EMe(SCAN_TRUNCATED, "truncated") \ #undef EM #undef EMe -- cgit v1.2.3 From e496cf3d782135c1cca0d154d4b924517ff58de0 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:35 -0700 Subject: thp: introduce CONFIG_TRANSPARENT_HUGE_PAGECACHE For file mappings, we don't deposit page tables on THP allocation because it's not strictly required to implement split_huge_pmd(): we can just clear pmd and let following page faults to reconstruct the page table. But Power makes use of deposited page table to address MMU quirk. Let's hide THP page cache, including huge tmpfs, under separate config option, so it can be forbidden on Power. We can revert the patch later once solution for Power found. Link: http://lkml.kernel.org/r/1466021202-61880-36-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Aneesh Kumar K.V Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0890f700a546..54fa28dfbd89 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -54,7 +54,6 @@ extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern bool shmem_mapping(struct address_space *mapping); -extern bool shmem_huge_enabled(struct vm_area_struct *vma); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); @@ -112,4 +111,13 @@ static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a) #endif +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE +extern bool shmem_huge_enabled(struct vm_area_struct *vma); +#else +static inline bool shmem_huge_enabled(struct vm_area_struct *vma) +{ + return false; +} +#endif + #endif -- cgit v1.2.3 From 779750d20b93bb2e0c75dfe924f31b02f6a78bfa Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:26:38 -0700 Subject: shmem: split huge pages beyond i_size under memory pressure Even if user asked to allocate huge pages always (huge=always), we should be able to free up some memory by splitting pages which are partly byound i_size if memory presure comes or once we hit limit on filesystem size (-o size=). In order to do this we maintain per-superblock list of inodes, which potentially have huge pages on the border of file size. Per-fs shrinker can reclaim memory by splitting such pages. If we hit -ENOSPC during shmem_getpage_gfp(), we try to split a page to free up space on the filesystem and retry allocation if it succeed. Link: http://lkml.kernel.org/r/1466021202-61880-37-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 54fa28dfbd89..ff078e7043b6 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -16,8 +16,9 @@ struct shmem_inode_info { unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ - struct shared_policy policy; /* NUMA memory alloc policy */ + struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ + struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ struct inode vfs_inode; }; @@ -33,6 +34,9 @@ struct shmem_sb_info { kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ struct mempolicy *mpol; /* default memory policy for mappings */ + spinlock_t shrinklist_lock; /* Protects shrinklist */ + struct list_head shrinklist; /* List of shinkable inodes */ + unsigned long shrinklist_len; /* Length of shrinklist */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) -- cgit v1.2.3 From 0db501f7a34c11d3b964205e5b6d00692a648035 Mon Sep 17 00:00:00 2001 From: Ebru Akagunduz Date: Tue, 26 Jul 2016 15:26:46 -0700 Subject: mm, thp: convert from optimistic swapin collapsing to conservative To detect whether khugepaged swapin is worthwhile, this patch checks the amount of young pages. There should be at least half of HPAGE_PMD_NR to swapin. Link: http://lkml.kernel.org/r/1468109451-1615-1-git-send-email-ebru.akagunduz@gmail.com Signed-off-by: Ebru Akagunduz Suggested-by: Minchan Kim Acked-by: Rik van Riel Cc: Hugh Dickins Cc: Kirill A. Shutemov Cc: Naoya Horiguchi Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Cyrill Gorcunov Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Johannes Weiner Cc: Michal Hocko Cc: Boaz Harrosh Cc: Hillf Danton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/huge_memory.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 830d47d5ca41..04f58acda8e8 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -13,7 +13,7 @@ EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \ EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \ EM( SCAN_PAGE_RO, "no_writable_page") \ - EM( SCAN_NO_REFERENCED_PAGE, "no_referenced_page") \ + EM( SCAN_LACK_REFERENCED_PAGE, "lack_referenced_page") \ EM( SCAN_PAGE_NULL, "page_null") \ EM( SCAN_SCAN_ABORT, "scan_aborted") \ EM( SCAN_PAGE_COUNT, "not_suitable_page_count") \ @@ -47,7 +47,7 @@ SCAN_STATUS TRACE_EVENT(mm_khugepaged_scan_pmd, TP_PROTO(struct mm_struct *mm, struct page *page, bool writable, - bool referenced, int none_or_zero, int status, int unmapped), + int referenced, int none_or_zero, int status, int unmapped), TP_ARGS(mm, page, writable, referenced, none_or_zero, status, unmapped), @@ -55,7 +55,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd, __field(struct mm_struct *, mm) __field(unsigned long, pfn) __field(bool, writable) - __field(bool, referenced) + __field(int, referenced) __field(int, none_or_zero) __field(int, status) __field(int, unmapped) @@ -108,14 +108,14 @@ TRACE_EVENT(mm_collapse_huge_page, TRACE_EVENT(mm_collapse_huge_page_isolate, TP_PROTO(struct page *page, int none_or_zero, - bool referenced, bool writable, int status), + int referenced, bool writable, int status), TP_ARGS(page, none_or_zero, referenced, writable, status), TP_STRUCT__entry( __field(unsigned long, pfn) __field(int, none_or_zero) - __field(bool, referenced) + __field(int, referenced) __field(bool, writable) __field(int, status) ), @@ -138,25 +138,28 @@ TRACE_EVENT(mm_collapse_huge_page_isolate, TRACE_EVENT(mm_collapse_huge_page_swapin, - TP_PROTO(struct mm_struct *mm, int swapped_in, int ret), + TP_PROTO(struct mm_struct *mm, int swapped_in, int referenced, int ret), - TP_ARGS(mm, swapped_in, ret), + TP_ARGS(mm, swapped_in, referenced, ret), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(int, swapped_in) + __field(int, referenced) __field(int, ret) ), TP_fast_assign( __entry->mm = mm; __entry->swapped_in = swapped_in; + __entry->referenced = referenced; __entry->ret = ret; ), - TP_printk("mm=%p, swapped_in=%d, ret=%d", + TP_printk("mm=%p, swapped_in=%d, referenced=%d, ret=%d", __entry->mm, __entry->swapped_in, + __entry->referenced, __entry->ret) ); -- cgit v1.2.3 From dd4123f324bbaec7618b677b7bce2b11aee9594e Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 26 Jul 2016 15:26:50 -0700 Subject: mm: fix build warnings in Randy reported below build error. > In file included from ../include/linux/balloon_compaction.h:48:0, > from ../mm/balloon_compaction.c:11: > ../include/linux/compaction.h:237:51: warning: 'struct node' declared inside parameter list [enabled by default] > static inline int compaction_register_node(struct node *node) > ../include/linux/compaction.h:237:51: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default] > ../include/linux/compaction.h:242:54: warning: 'struct node' declared inside parameter list [enabled by default] > static inline void compaction_unregister_node(struct node *node) > It was caused by non-lru page migration which needs compaction.h but compaction.h doesn't include any header to be standalone. I think proper header for non-lru page migration is migrate.h rather than compaction.h because migrate.h has already headers needed to work non-lru page migration indirectly like isolate_mode_t, migrate_mode MIGRATEPAGE_SUCCESS. [akpm@linux-foundation.org: revert mm-balloon-use-general-non-lru-movable-page-feature-fix.patch temp fix] Link: http://lkml.kernel.org/r/20160610003304.GE29779@bbox Signed-off-by: Minchan Kim Reported-by: Randy Dunlap Cc: Konstantin Khlebnikov Cc: Vlastimil Babka Cc: Gioh Kim Cc: Rafael Aquini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/balloon_compaction.h | 3 +-- include/linux/compaction.h | 16 ---------------- include/linux/migrate.h | 15 +++++++++++++++ 3 files changed, 16 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 504bd724e6ab..79542b2698ec 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -45,8 +45,7 @@ #define _LINUX_BALLOON_COMPACTION_H #include #include -#include -#include +#include #include #include #include diff --git a/include/linux/compaction.h b/include/linux/compaction.h index c6b47c861cea..1a02dab16646 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -54,9 +54,6 @@ enum compact_result { struct alloc_context; /* in mm/internal.h */ #ifdef CONFIG_COMPACTION -extern int PageMovable(struct page *page); -extern void __SetPageMovable(struct page *page, struct address_space *mapping); -extern void __ClearPageMovable(struct page *page); extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); @@ -154,19 +151,6 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else -static inline int PageMovable(struct page *page) -{ - return 0; -} -static inline void __SetPageMovable(struct page *page, - struct address_space *mapping) -{ -} - -static inline void __ClearPageMovable(struct page *page) -{ -} - static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, int alloc_flags, const struct alloc_context *ac, diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 404fbfefeb33..ae8d475a9385 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -71,6 +71,21 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_COMPACTION +extern int PageMovable(struct page *page); +extern void __SetPageMovable(struct page *page, struct address_space *mapping); +extern void __ClearPageMovable(struct page *page); +#else +static inline int PageMovable(struct page *page) { return 0; }; +static inline void __SetPageMovable(struct page *page, + struct address_space *mapping) +{ +} +static inline void __ClearPageMovable(struct page *page) +{ +} +#endif + #ifdef CONFIG_NUMA_BALANCING extern bool pmd_trans_migrating(pmd_t pmd); extern int migrate_misplaced_page(struct page *page, -- cgit v1.2.3 From bf262dcec6383188a3324192c4a7e405b3b1ad23 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 12 Apr 2016 05:02:09 +0930 Subject: module: fix noreturn attribute for __module_put_and_exit() __module_put_and_exit() is makred noreturn in module.h declaration, but is lacking the attribute in the definition, which makes some tools (such as sparse) unhappy. Amend the definition with the attribute as well (and reformat the declaration so that it uses more common format). Signed-off-by: Jiri Kosina Signed-off-by: Rusty Russell --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index 3daf2b3a09d2..f777164c238b 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -575,8 +575,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -extern void __module_put_and_exit(struct module *mod, long code) - __attribute__((noreturn)); +extern void __noreturn __module_put_and_exit(struct module *mod, + long code); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD -- cgit v1.2.3 From b07b58a3e435a3d18004815e8364ec26c4236721 Mon Sep 17 00:00:00 2001 From: Tony Camuso Date: Wed, 22 Jun 2016 14:22:28 -0400 Subject: ipmi: remove trydefaults parameter and default init Parameter trydefaults=1 causes the ipmi_init to initialize ipmi through the legacy port io space that was designated for ipmi. Architectures that do not map legacy port io can panic when trydefaults=1. Rather than implement build-time conditional exceptions for each architecture that does not map legacy port io, we have removed legacy port io from the driver. Parameter 'trydefaults' has been removed. Attempts to use it hereafter will evoke the "Unknown symbol in module, or unknown parameter" message. The patch was built against a number of architectures and tested for regressions and functionality on x86_64 and ARM64. Signed-off-by: Tony Camuso Removed the config entry and the address source entry for default, since neither were used any more. Signed-off-by: Corey Minyard --- include/linux/ipmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 838dbfa3c331..78c5d5ae3857 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -277,7 +277,7 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len); */ enum ipmi_addr_src { SI_INVALID = 0, SI_HOTMOD, SI_HARDCODED, SI_SPMI, SI_ACPI, SI_SMBIOS, - SI_PCI, SI_DEVICETREE, SI_DEFAULT + SI_PCI, SI_DEVICETREE, SI_LAST }; const char *ipmi_addr_src_to_str(enum ipmi_addr_src src); -- cgit v1.2.3 From 4097461897df91041382ff6fcd2bfa7ee6b2448c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 25 Jul 2016 11:36:54 -0700 Subject: Input: i8042 - break load dependency between atkbd/psmouse and i8042 As explained in 1407814240-4275-1-git-send-email-decui@microsoft.com we have a hard load dependency between i8042 and atkbd which prevents keyboard from working on Gen2 Hyper-V VMs. > hyperv_keyboard invokes serio_interrupt(), which needs a valid serio > driver like atkbd.c. atkbd.c depends on libps2.c because it invokes > ps2_command(). libps2.c depends on i8042.c because it invokes > i8042_check_port_owner(). As a result, hyperv_keyboard actually > depends on i8042.c. > > For a Generation 2 Hyper-V VM (meaning no i8042 device emulated), if a > Linux VM (like Arch Linux) happens to configure CONFIG_SERIO_I8042=m > rather than =y, atkbd.ko can't load because i8042.ko can't load(due to > no i8042 device emulated) and finally hyperv_keyboard can't work and > the user can't input: https://bugs.archlinux.org/task/39820 > (Ubuntu/RHEL/SUSE aren't affected since they use CONFIG_SERIO_I8042=y) To break the dependency we move away from using i8042_check_port_owner() and instead allow serio port owner specify a mutex that clients should use to serialize PS/2 command stream. Reported-by: Mark Laws Tested-by: Mark Laws Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- include/linux/i8042.h | 6 ------ include/linux/serio.h | 24 +++++++++++++++++++----- 2 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 0f9bafa17a02..d98780ca9604 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -62,7 +62,6 @@ struct serio; void i8042_lock_chip(void); void i8042_unlock_chip(void); int i8042_command(unsigned char *param, int command); -bool i8042_check_port_owner(const struct serio *); int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)); int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, @@ -83,11 +82,6 @@ static inline int i8042_command(unsigned char *param, int command) return -ENODEV; } -static inline bool i8042_check_port_owner(const struct serio *serio) -{ - return false; -} - static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)) { diff --git a/include/linux/serio.h b/include/linux/serio.h index df4ab5de1586..c733cff44e18 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -31,7 +31,8 @@ struct serio { struct serio_device_id id; - spinlock_t lock; /* protects critical sections from port's interrupt handler */ + /* Protects critical sections from port's interrupt handler */ + spinlock_t lock; int (*write)(struct serio *, unsigned char); int (*open)(struct serio *); @@ -40,16 +41,29 @@ struct serio { void (*stop)(struct serio *); struct serio *parent; - struct list_head child_node; /* Entry in parent->children list */ + /* Entry in parent->children list */ + struct list_head child_node; struct list_head children; - unsigned int depth; /* level of nesting in serio hierarchy */ + /* Level of nesting in serio hierarchy */ + unsigned int depth; - struct serio_driver *drv; /* accessed from interrupt, must be protected by serio->lock and serio->sem */ - struct mutex drv_mutex; /* protects serio->drv so attributes can pin driver */ + /* + * serio->drv is accessed from interrupt handlers; when modifying + * caller should acquire serio->drv_mutex and serio->lock. + */ + struct serio_driver *drv; + /* Protects serio->drv so attributes can pin current driver */ + struct mutex drv_mutex; struct device dev; struct list_head node; + + /* + * For use by PS/2 layer when several ports share hardware and + * may get indigestion when exposed to concurrent access (i8042). + */ + struct mutex *ps2_cmd_mutex; }; #define to_serio_port(d) container_of(d, struct serio, dev) -- cgit v1.2.3 From b2aa5d0bc86cb901cc6c8737cfff66360cbff00c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 7 Jun 2016 21:57:15 +0200 Subject: libceph: fix some missing includes - decode.h needs slab.h for kmalloc() - osd_client.h needs msgpool.h for struct ceph_msgpool - msgpool.h doesn't need messenger.h Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 1 + include/linux/ceph/msgpool.h | 1 - include/linux/ceph/osd_client.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index 19e9932f3e77..e83f3c81ef43 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -3,6 +3,7 @@ #include #include +#include #include #include diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h index 4b0d38960726..ddd0d48d0384 100644 --- a/include/linux/ceph/msgpool.h +++ b/include/linux/ceph/msgpool.h @@ -2,7 +2,6 @@ #define _FS_CEPH_MSGPOOL #include -#include /* * we use memory pools for preallocating messages we may receive, to diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 1b3b6e155392..858932304260 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 281dbe5db81c6137def9757e07a7aea14b1ed86e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 26 Jul 2016 15:22:35 +0200 Subject: libceph: add an ONSTACK initializer for oids An on-stack oid in ceph_ioctl_get_dataloc() is not initialized, resulting in a WARN and a NULL pointer dereference later on. We will have more of these on-stack in the future, so fix it with a convenience macro. Fixes: d30291b985d1 ("libceph: variable-sized ceph_object_id") Signed-off-by: Ilya Dryomov --- include/linux/ceph/osdmap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 9ccf4dbe55f8..21d7f048959f 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -115,6 +115,11 @@ static inline void ceph_oid_init(struct ceph_object_id *oid) oid->name_len = 0; } +#define CEPH_OID_INIT_ONSTACK(oid) \ + ({ ceph_oid_init(&oid); oid; }) +#define CEPH_DEFINE_OID_ONSTACK(oid) \ + struct ceph_object_id oid = CEPH_OID_INIT_ONSTACK(oid) + static inline bool ceph_oid_empty(const struct ceph_object_id *oid) { return oid->name == oid->inline_name && !oid->name_len; -- cgit v1.2.3 From 22748f9d617b8cd0a915c3a4c656c7232645b3b5 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 2 Jun 2016 14:23:32 +0200 Subject: libceph: add start en/decoding block helpers Add ceph_start_encoding() and ceph_start_decoding(), the equivalent of ENCODE_START and DECODE_START in the userspace ceph code. This is based on a patch from Mike Christie . Signed-off-by: Ilya Dryomov --- include/linux/ceph/decode.h | 54 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) (limited to 'include') diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index e83f3c81ef43..f990f2cc907a 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -218,6 +218,60 @@ static inline void ceph_encode_string(void **p, void *end, *p += len; } +/* + * version and length starting block encoders/decoders + */ + +/* current code version (u8) + compat code version (u8) + len of struct (u32) */ +#define CEPH_ENCODING_START_BLK_LEN 6 + +/** + * ceph_start_encoding - start encoding block + * @struct_v: current (code) version of the encoding + * @struct_compat: oldest code version that can decode it + * @struct_len: length of struct encoding + */ +static inline void ceph_start_encoding(void **p, u8 struct_v, u8 struct_compat, + u32 struct_len) +{ + ceph_encode_8(p, struct_v); + ceph_encode_8(p, struct_compat); + ceph_encode_32(p, struct_len); +} + +/** + * ceph_start_decoding - start decoding block + * @v: current version of the encoding that the code supports + * @name: name of the struct (free-form) + * @struct_v: out param for the encoding version + * @struct_len: out param for the length of struct encoding + * + * Validates the length of struct encoding, so unsafe ceph_decode_* + * variants can be used for decoding. + */ +static inline int ceph_start_decoding(void **p, void *end, u8 v, + const char *name, u8 *struct_v, + u32 *struct_len) +{ + u8 struct_compat; + + ceph_decode_need(p, end, CEPH_ENCODING_START_BLK_LEN, bad); + *struct_v = ceph_decode_8(p); + struct_compat = ceph_decode_8(p); + if (v < struct_compat) { + pr_warn("got struct_v %d struct_compat %d > %d of %s\n", + *struct_v, struct_compat, v, name); + return -EINVAL; + } + + *struct_len = ceph_decode_32(p); + ceph_decode_need(p, end, *struct_len, bad); + return 0; + +bad: + return -ERANGE; +} + #define ceph_encode_need(p, end, n, bad) \ do { \ if (!likely(ceph_has_room(p, end, n))) \ -- cgit v1.2.3 From 7627151ea30bce2051e3cb27d7bb2c30083f86a5 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Wed, 3 Feb 2016 21:24:49 +0800 Subject: libceph: define new ceph_file_layout structure Define new ceph_file_layout structure and rename old ceph_file_layout to ceph_file_layout_legacy. This is preparation for adding namespace to ceph_file_layout structure. Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 50 +++++++++++++++++++------------------------- 1 file changed, 21 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index dfce616002ad..e5a5fb9ca3f5 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -34,9 +34,9 @@ #define CEPH_MAX_MON 31 /* - * ceph_file_layout - describe data layout for a file/inode + * legacy ceph_file_layoute */ -struct ceph_file_layout { +struct ceph_file_layout_legacy { /* file -> object mapping */ __le32 fl_stripe_unit; /* stripe unit, in bytes. must be multiple of page size. */ @@ -53,33 +53,25 @@ struct ceph_file_layout { __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ } __attribute__ ((packed)); -#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) -#define ceph_file_layout_stripe_count(l) \ - ((__s32)le32_to_cpu((l).fl_stripe_count)) -#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) -#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) -#define ceph_file_layout_object_su(l) \ - ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) -#define ceph_file_layout_pg_pool(l) \ - ((__s32)le32_to_cpu((l).fl_pg_pool)) - -static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_stripe_unit) * - le32_to_cpu(l->fl_stripe_count); -} - -/* "period" == bytes before i start on a new set of objects */ -static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_object_size) * - le32_to_cpu(l->fl_stripe_count); -} +/* + * ceph_file_layout - describe data layout for a file/inode + */ +struct ceph_file_layout { + /* file -> object mapping */ + u32 stripe_unit; /* stripe unit, in bytes */ + u32 stripe_count; /* over this many objects */ + u32 object_size; /* until objects are this big */ + s64 pool_id; /* rados pool id */ +}; + +extern int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); +extern void ceph_file_layout_from_legacy(struct ceph_file_layout *fl, + struct ceph_file_layout_legacy *legacy); +extern void ceph_file_layout_to_legacy(struct ceph_file_layout *fl, + struct ceph_file_layout_legacy *legacy); #define CEPH_MIN_STRIPE_UNIT 65536 -int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); - struct ceph_dir_layout { __u8 dl_dir_hash; /* see ceph_hash.h for ids */ __u8 dl_unused1; @@ -399,7 +391,7 @@ union ceph_mds_request_args { __le32 flags; } __attribute__ ((packed)) setxattr; struct { - struct ceph_file_layout layout; + struct ceph_file_layout_legacy layout; } __attribute__ ((packed)) setlayout; struct { __u8 rule; /* currently fcntl or flock */ @@ -478,7 +470,7 @@ struct ceph_mds_reply_inode { __le64 version; /* inode version */ __le64 xattr_version; /* version for xattr blob */ struct ceph_mds_reply_cap cap; /* caps issued for this inode */ - struct ceph_file_layout layout; + struct ceph_file_layout_legacy layout; struct ceph_timespec ctime, mtime, atime; __le32 time_warp_seq; __le64 size, max_size, truncate_size; @@ -673,7 +665,7 @@ struct ceph_mds_caps { __le64 size, max_size, truncate_size; __le32 truncate_seq; struct ceph_timespec mtime, atime, ctime; - struct ceph_file_layout layout; + struct ceph_file_layout_legacy layout; __le32 time_warp_seq; } __attribute__ ((packed)); -- cgit v1.2.3 From 51e9273796a57c08801f45580d3db3c51987a0cb Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 5 Feb 2016 15:36:22 +0800 Subject: libceph: introduce reference counted string The data structure is for storing namesapce string. It allows namespace string to be shared between cephfs inodes with same layout. This data structure can also be referenced by OSD request. Signed-off-by: Yan, Zheng --- include/linux/ceph/libceph.h | 1 + include/linux/ceph/string_table.h | 62 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 include/linux/ceph/string_table.h (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 690985daad1c..6afc5d98fad1 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -21,6 +21,7 @@ #include #include #include +#include /* * mount options diff --git a/include/linux/ceph/string_table.h b/include/linux/ceph/string_table.h new file mode 100644 index 000000000000..1b02c96daf75 --- /dev/null +++ b/include/linux/ceph/string_table.h @@ -0,0 +1,62 @@ +#ifndef _FS_CEPH_STRING_TABLE_H +#define _FS_CEPH_STRING_TABLE_H + +#include +#include +#include +#include + +struct ceph_string { + struct kref kref; + union { + struct rb_node node; + struct rcu_head rcu; + }; + size_t len; + char str[]; +}; + +extern void ceph_release_string(struct kref *ref); +extern struct ceph_string *ceph_find_or_create_string(const char *str, + size_t len); +extern bool ceph_strings_empty(void); + +static inline struct ceph_string *ceph_get_string(struct ceph_string *str) +{ + kref_get(&str->kref); + return str; +} + +static inline void ceph_put_string(struct ceph_string *str) +{ + if (!str) + return; + kref_put(&str->kref, ceph_release_string); +} + +static inline int ceph_compare_string(struct ceph_string *cs, + const char* str, size_t len) +{ + size_t cs_len = cs ? cs->len : 0; + if (cs_len != len) + return cs_len - len; + if (len == 0) + return 0; + return strncmp(cs->str, str, len); +} + +#define ceph_try_get_string(x) \ +({ \ + struct ceph_string *___str; \ + rcu_read_lock(); \ + for (;;) { \ + ___str = rcu_dereference(x); \ + if (!___str || \ + kref_get_unless_zero(&___str->kref)) \ + break; \ + } \ + rcu_read_unlock(); \ + (___str); \ +}) + +#endif -- cgit v1.2.3 From 30c156d9951e0aa88202707d80c583b0a09d3167 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sun, 14 Feb 2016 11:24:31 +0800 Subject: libceph: rados pool namespace support Add pool namesapce pointer to struct ceph_file_layout and struct ceph_object_locator. Pool namespace is used by when mapping object to PG, it's also used when composing OSD request. The namespace pointer in struct ceph_file_layout is RCU protected. So libceph can read namespace without taking lock. Signed-off-by: Yan, Zheng [idryomov@gmail.com: ceph_oloc_destroy(), misc minor changes] Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 ++ include/linux/ceph/osdmap.h | 10 +++++----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index e5a5fb9ca3f5..08b8fd72261e 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -53,6 +53,7 @@ struct ceph_file_layout_legacy { __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ } __attribute__ ((packed)); +struct ceph_string; /* * ceph_file_layout - describe data layout for a file/inode */ @@ -62,6 +63,7 @@ struct ceph_file_layout { u32 stripe_count; /* over this many objects */ u32 object_size; /* until objects are this big */ s64 pool_id; /* rados pool id */ + struct ceph_string __rcu *pool_ns; /* rados pool namespace */ }; extern int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 21d7f048959f..9a9041784dcf 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -63,11 +63,13 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool) struct ceph_object_locator { s64 pool; + struct ceph_string *pool_ns; }; static inline void ceph_oloc_init(struct ceph_object_locator *oloc) { oloc->pool = -1; + oloc->pool_ns = NULL; } static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc) @@ -75,11 +77,9 @@ static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc) return oloc->pool == -1; } -static inline void ceph_oloc_copy(struct ceph_object_locator *dest, - const struct ceph_object_locator *src) -{ - dest->pool = src->pool; -} +void ceph_oloc_copy(struct ceph_object_locator *dest, + const struct ceph_object_locator *src); +void ceph_oloc_destroy(struct ceph_object_locator *oloc); /* * Maximum supported by kernel client object name length -- cgit v1.2.3 From 774a6a118c70f8c11fcfe636032b5016ad71a746 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 6 Jun 2016 16:01:39 +0800 Subject: ceph: reduce i_nr_by_mode array size Track usage count for individual fmode bit. This can reduce the array size by half. Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 08b8fd72261e..6bc7730d22ac 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -525,7 +525,7 @@ struct ceph_filelock { #define CEPH_FILE_MODE_WR 2 #define CEPH_FILE_MODE_RDWR 3 /* RD | WR */ #define CEPH_FILE_MODE_LAZY 4 /* lazy io */ -#define CEPH_FILE_MODE_NUM 8 /* bc these are bit fields.. mostly */ +#define CEPH_FILE_MODE_BITS 4 int ceph_flags_to_mode(int flags); -- cgit v1.2.3 From 0cabbd94ff52c4803fc0ad9ad0ad5e43df493ab0 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Thu, 7 Apr 2016 11:34:43 +0800 Subject: libceph: fsmap.user subscription support Signed-off-by: Yan, Zheng Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 1 + include/linux/ceph/mon_client.h | 7 ++++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 6bc7730d22ac..7868d602c0a0 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -121,6 +121,7 @@ struct ceph_dir_layout { /* client <-> mds */ #define CEPH_MSG_MDS_MAP 21 +#define CEPH_MSG_FS_MAP_USER 103 #define CEPH_MSG_CLIENT_SESSION 22 #define CEPH_MSG_CLIENT_RECONNECT 23 diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index e2a92df08b47..24d704d1ea5c 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -95,7 +95,7 @@ struct ceph_mon_client { struct ceph_mon_subscribe_item item; bool want; u32 have; /* epoch */ - } subs[3]; + } subs[4]; int fs_cluster_id; /* "mdsmap." sub */ #ifdef CONFIG_DEBUG_FS @@ -111,9 +111,10 @@ extern int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl); extern void ceph_monc_stop(struct ceph_mon_client *monc); enum { - CEPH_SUB_MDSMAP = 0, - CEPH_SUB_MONMAP, + CEPH_SUB_MONMAP = 0, CEPH_SUB_OSDMAP, + CEPH_SUB_FSMAP, + CEPH_SUB_MDSMAP, }; extern const char *ceph_sub_str[]; -- cgit v1.2.3 From a24532f8d17b7211dfb0259920edfcffc8306606 Mon Sep 17 00:00:00 2001 From: Rob Rice Date: Thu, 30 Jun 2016 15:59:23 -0400 Subject: mailbox: Add Broadcom PDC mailbox driver The Broadcom PDC mailbox driver is a mailbox controller that manages data transfers to and from one or more offload engines. Signed-off-by: Rob Rice Reviewed-by: Scott Branden Reviewed-by: Ray Jui Signed-off-by: Jassi Brar --- include/linux/mailbox/brcm-message.h | 56 ++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/mailbox/brcm-message.h (limited to 'include') diff --git a/include/linux/mailbox/brcm-message.h b/include/linux/mailbox/brcm-message.h new file mode 100644 index 000000000000..6b55c938b401 --- /dev/null +++ b/include/linux/mailbox/brcm-message.h @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2016 Broadcom + * + * 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. + * + * Common header for Broadcom mailbox messages which is shared across + * Broadcom SoCs and Broadcom mailbox client drivers. + */ + +#ifndef _LINUX_BRCM_MESSAGE_H_ +#define _LINUX_BRCM_MESSAGE_H_ + +#include + +enum brcm_message_type { + BRCM_MESSAGE_UNKNOWN = 0, + BRCM_MESSAGE_SPU, + BRCM_MESSAGE_SBA, + BRCM_MESSAGE_MAX, +}; + +struct brcm_sba_command { + u64 cmd; +#define BRCM_SBA_CMD_TYPE_A BIT(0) +#define BRCM_SBA_CMD_TYPE_B BIT(1) +#define BRCM_SBA_CMD_TYPE_C BIT(2) +#define BRCM_SBA_CMD_HAS_RESP BIT(3) +#define BRCM_SBA_CMD_HAS_OUTPUT BIT(4) + u64 flags; + dma_addr_t input; + size_t input_len; + dma_addr_t resp; + size_t resp_len; + dma_addr_t output; + size_t output_len; +}; + +struct brcm_message { + enum brcm_message_type type; + union { + struct { + struct scatterlist *src; + struct scatterlist *dst; + } spu; + struct { + struct brcm_sba_command *cmds; + unsigned int cmds_count; + } sba; + }; + void *ctx; + int error; +}; + +#endif /* _LINUX_BRCM_MESSAGE_H_ */ -- cgit v1.2.3 From a0f2b65275413b3438e9f55b1427273cd893c3b2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 13 Jun 2016 15:04:56 +0200 Subject: ceph: fix symbol versioning for ceph_monc_do_statfs The genksyms helper in the kernel cannot parse a type definition like "typeof(((type *)0)->keyfld)" that is used in the DEFINE_RB_FUNCS helper, causing the following EXPORT_SYMBOL() statement to be ignored when computing the crcs, and triggering a warning about this: WARNING: "ceph_monc_do_statfs" [fs/ceph/ceph.ko] has no CRC To work around the problem, we can rewrite the type to reference an undefined 'extern' symbol instead of a NULL pointer. This is evidently ok for genksyms, and it no longer complains about the line when calling it with 'genksyms -w'. I've looked briefly into extending genksyms instead, but it seems really hard to do. Jan Beulich introduced basic support for 'typeof' a while ago in dc53324060f3 ("genksyms: fix typeof() handling"), but that is not sufficient for the expression we have here. Signed-off-by: Arnd Bergmann Fixes: fcd00b68bbe2 ("libceph: DEFINE_RB_FUNCS macro") Cc: Jan Beulich Cc: Michal Marek Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 6afc5d98fad1..83fc1fff7061 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -215,8 +215,9 @@ static void erase_##name(struct rb_root *root, type *t) \ } #define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ +extern type __lookup_##name##_key; \ static type *lookup_##name(struct rb_root *root, \ - typeof(((type *)0)->keyfld) key) \ + typeof(__lookup_##name##_key.keyfld) key) \ { \ struct rb_node *n = root->rb_node; \ \ -- cgit v1.2.3 From 4fae16dffb812f0e0d98a0b2b0856ca48ca63e6c Mon Sep 17 00:00:00 2001 From: Richard Cochran Date: Wed, 27 Jul 2016 11:08:18 +0200 Subject: timers/core: Correct callback order during CPU hot plug On the tear-down path, the dead CPU callback for the timers was misplaced within the 'cpuhp_state' enumeration. There is a hidden dependency between the timers and block multiqueue. The timers callback must happen before the block multiqueue callback otherwise a RCU stall occurs. Move the timers callback to the proper place in the state machine. Reported-and-tested-by: Jon Hunter Reported-by: kbuild test robot Fixes: 24f73b99716a ("timers/core: Convert to hotplug state machine") Signed-off-by: Richard Cochran Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Rasmus Villemoes Cc: John Stultz Cc: rt@linutronix.de Cc: Oleg Nesterov Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1469610498-25914-1-git-send-email-rcochran@linutronix.de Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/cpuhotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6d405db6fb12..242bf530edfc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -20,9 +20,9 @@ enum cpuhp_state { CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, - CPUHP_TIMERS_DEAD, CPUHP_RCUTREE_PREP, CPUHP_NOTIFY_PREPARE, + CPUHP_TIMERS_DEAD, CPUHP_BRINGUP_CPU, CPUHP_AP_IDLE_DEAD, CPUHP_AP_OFFLINE, -- cgit v1.2.3 From 44a70adec910d6929689e42b6e5cee5b7d202d20 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:44:43 -0700 Subject: mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj oom_score_adj is shared for the thread groups (via struct signal) but this is not sufficient to cover processes sharing mm (CLONE_VM without CLONE_SIGHAND) and so we can easily end up in a situation when some processes update their oom_score_adj and confuse the oom killer. In the worst case some of those processes might hide from the oom killer altogether via OOM_SCORE_ADJ_MIN while others are eligible. OOM killer would then pick up those eligible but won't be allowed to kill others sharing the same mm so the mm wouldn't release the mm and so the memory. It would be ideal to have the oom_score_adj per mm_struct because that is the natural entity OOM killer considers. But this will not work because some programs are doing vfork() set_oom_adj() exec() We can achieve the same though. oom_score_adj write handler can set the oom_score_adj for all processes sharing the same mm if the task is not in the middle of vfork. As a result all the processes will share the same oom_score_adj. The current implementation is rather pessimistic and checks all the existing processes by default if there is more than 1 holder of the mm but we do not have any reliable way to check for external users yet. Link: http://lkml.kernel.org/r/1466426628-15074-5-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 192c1bbe5fcd..c606fe4f9a7f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2284,6 +2284,8 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) } #endif /* __HAVE_ARCH_GATE_AREA */ +extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); + #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, -- cgit v1.2.3 From b18dc5f291c07ddaf31562b9f27b3a122f1f9b7e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:44:46 -0700 Subject: mm, oom: skip vforked tasks from being selected vforked tasks are not really sitting on any memory. They are sharing the mm with parent until they exec into a new code. Until then it is just pinning the address space. OOM killer will kill the vforked task along with its parent but we still can end up selecting vforked task when the parent wouldn't be selected. E.g. init doing vfork to launch a task or vforked being a child of oom unkillable task with an updated oom_score_adj to be killable. Add a new helper to check whether a task is in the vfork sharing memory with its parent and use it in oom_badness to skip over these tasks. Link: http://lkml.kernel.org/r/1466426628-15074-6-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index d99218a1e043..c0efd80ba40f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1949,6 +1949,32 @@ static inline int tsk_nr_cpus_allowed(struct task_struct *p) #define TNF_FAULT_LOCAL 0x08 #define TNF_MIGRATE_FAIL 0x10 +static inline bool in_vfork(struct task_struct *tsk) +{ + bool ret; + + /* + * need RCU to access ->real_parent if CLONE_VM was used along with + * CLONE_PARENT. + * + * We check real_parent->mm == tsk->mm because CLONE_VFORK does not + * imply CLONE_VM + * + * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus + * ->real_parent is not necessarily the task doing vfork(), so in + * theory we can't rely on task_lock() if we want to dereference it. + * + * And in this case we can't trust the real_parent->mm == tsk->mm + * check, it can be false negative. But we do not care, if init or + * another oom-unkillable task does this it should blame itself. + */ + rcu_read_lock(); + ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; + rcu_read_unlock(); + + return ret; +} + #ifdef CONFIG_NUMA_BALANCING extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); -- cgit v1.2.3 From 1af8bb43269563e458ebcf0ece812e9a970864b3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:44:52 -0700 Subject: mm, oom: fortify task_will_free_mem() task_will_free_mem is rather weak. It doesn't really tell whether the task has chance to drop its mm. 98748bd72200 ("oom: consider multi-threaded tasks in task_will_free_mem") made a first step into making it more robust for multi-threaded applications so now we know that the whole process is going down and probably drop the mm. This patch builds on top for more complex scenarios where mm is shared between different processes - CLONE_VM without CLONE_SIGHAND, or in kernel use_mm(). Make sure that all processes sharing the mm are killed or exiting. This will allow us to replace try_oom_reaper by wake_oom_reaper because task_will_free_mem implies the task is reapable now. Therefore all paths which bypass the oom killer are now reapable and so they shouldn't lock up the oom killer. Link: http://lkml.kernel.org/r/1466426628-15074-8-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/oom.h b/include/linux/oom.h index 606137b3b778..5bc0457ee3a8 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -73,9 +73,9 @@ static inline bool oom_task_origin(const struct task_struct *p) extern void mark_oom_victim(struct task_struct *tsk); #ifdef CONFIG_MMU -extern void try_oom_reaper(struct task_struct *tsk); +extern void wake_oom_reaper(struct task_struct *tsk); #else -static inline void try_oom_reaper(struct task_struct *tsk) +static inline void wake_oom_reaper(struct task_struct *tsk) { } #endif @@ -107,27 +107,7 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); -static inline bool task_will_free_mem(struct task_struct *task) -{ - struct signal_struct *sig = task->signal; - - /* - * A coredumping process may sleep for an extended period in exit_mm(), - * so the oom killer cannot assume that the process will promptly exit - * and release memory. - */ - if (sig->flags & SIGNAL_GROUP_COREDUMP) - return false; - - if (!(task->flags & PF_EXITING)) - return false; - - /* Make sure that the whole thread group is going down */ - if (!thread_group_empty(task) && !(sig->flags & SIGNAL_GROUP_EXIT)) - return false; - - return true; -} +bool task_will_free_mem(struct task_struct *task); /* sysctls */ extern int sysctl_oom_dump_tasks; -- cgit v1.2.3 From 11a410d516e89320fe0817606eeab58f36c22968 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Thu, 28 Jul 2016 15:44:58 -0700 Subject: mm, oom_reaper: do not attempt to reap a task more than twice oom_reaper relies on the mmap_sem for read to do its job. Many places which might block readers have been converted to use down_write_killable and that has reduced chances of the contention a lot. Some paths where the mmap_sem is held for write can take other locks and they might either be not prepared to fail due to fatal signal pending or too impractical to be changed. This patch introduces MMF_OOM_NOT_REAPABLE flag which gets set after the first attempt to reap a task's mm fails. If the flag is present after the failure then we set MMF_OOM_REAPED to hide this mm from the oom killer completely so it can go and chose another victim. As a result a risk of OOM deadlock when the oom victim would be blocked indefinetly and so the oom killer cannot make any progress should be mitigated considerably while we still try really hard to perform all reclaim attempts and stay predictable in the behavior. Link: http://lkml.kernel.org/r/1466426628-15074-10-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Oleg Nesterov Cc: Vladimir Davydov Cc: David Rientjes Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index c0efd80ba40f..553af2923824 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -523,6 +523,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HAS_UPROBES 19 /* has uprobes */ #define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ #define MMF_OOM_REAPED 21 /* mm has been already reaped */ +#define MMF_OOM_NOT_REAPABLE 22 /* mm couldn't be reaped */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) -- cgit v1.2.3 From 55779ec759ccc3c12b917b3712a7716e1140c652 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 28 Jul 2016 15:45:10 -0700 Subject: mm: fix vm-scalability regression in cgroup-aware workingset code Commit 23047a96d7cf ("mm: workingset: per-cgroup cache thrash detection") added a page->mem_cgroup lookup to the cache eviction, refault, and activation paths, as well as locking to the activation path, and the vm-scalability tests showed a regression of -23%. While the test in question is an artificial worst-case scenario that doesn't occur in real workloads - reading two sparse files in parallel at full CPU speed just to hammer the LRU paths - there is still some optimizations that can be done in those paths. Inline the lookup functions to eliminate calls. Also, page->mem_cgroup doesn't need to be stabilized when counting an activation; we merely need to hold the RCU lock to prevent the memcg from being freed. This cuts down on overhead quite a bit: 23047a96d7cfcfca 063f6715e77a7be5770d6081fe ---------------- -------------------------- %stddev %change %stddev \ | \ 21621405 +- 0% +11.3% 24069657 +- 2% vm-scalability.throughput [linux@roeck-us.net: drop unnecessary include file] [hannes@cmpxchg.org: add WARN_ON_ONCE()s] Link: http://lkml.kernel.org/r/20160707194024.GA26580@cmpxchg.org Link: http://lkml.kernel.org/r/20160624175101.GA3024@cmpxchg.org Reported-by: Ye Xiaolong Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Guenter Roeck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 43 ++++++++++++++++++++++++++++++++++++++++++- include/linux/mm.h | 10 ++++++++++ 2 files changed, 52 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 71aff733a497..1c4df4420258 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -314,7 +314,48 @@ void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); -struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); +static inline struct mem_cgroup_per_zone * +mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) +{ + int nid = zone_to_nid(zone); + int zid = zone_idx(zone); + + return &memcg->nodeinfo[nid]->zoneinfo[zid]; +} + +/** + * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg + * @zone: zone of the wanted lruvec + * @memcg: memcg of the wanted lruvec + * + * Returns the lru list vector holding pages for the given @zone and + * @mem. This can be the global zone lruvec, if the memory controller + * is disabled. + */ +static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, + struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_zone *mz; + struct lruvec *lruvec; + + if (mem_cgroup_disabled()) { + lruvec = &zone->lruvec; + goto out; + } + + mz = mem_cgroup_zone_zoneinfo(memcg, zone); + lruvec = &mz->lruvec; +out: + /* + * Since a node can be onlined after the mem_cgroup was created, + * we have to be prepared to initialize lruvec->zone here; + * and if offlined then reonlined, we need to reinitialize it. + */ + if (unlikely(lruvec->zone != zone)) + lruvec->zone = zone; + return lruvec; +} + struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); diff --git a/include/linux/mm.h b/include/linux/mm.h index c606fe4f9a7f..97065e1f0237 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -973,11 +973,21 @@ static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return READ_ONCE(page->mem_cgroup); +} #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return NULL; +} #endif /* -- cgit v1.2.3 From 75ef7184053989118d3814c558a9af62e7376a58 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:24 -0700 Subject: mm, vmstat: add infrastructure for per-node vmstats Patchset: "Move LRU page reclaim from zones to nodes v9" This series moves LRUs from the zones to the node. While this is a current rebase, the test results were based on mmotm as of June 23rd. Conceptually, this series is simple but there are a lot of details. Some of the broad motivations for this are; 1. The residency of a page partially depends on what zone the page was allocated from. This is partially combatted by the fair zone allocation policy but that is a partial solution that introduces overhead in the page allocator paths. 2. Currently, reclaim on node 0 behaves slightly different to node 1. For example, direct reclaim scans in zonelist order and reclaims even if the zone is over the high watermark regardless of the age of pages in that LRU. Kswapd on the other hand starts reclaim on the highest unbalanced zone. A difference in distribution of file/anon pages due to when they were allocated results can result in a difference in again. While the fair zone allocation policy mitigates some of the problems here, the page reclaim results on a multi-zone node will always be different to a single-zone node. it was scheduled on as a result. 3. kswapd and the page allocator scan zones in the opposite order to avoid interfering with each other but it's sensitive to timing. This mitigates the page allocator using pages that were allocated very recently in the ideal case but it's sensitive to timing. When kswapd is allocating from lower zones then it's great but during the rebalancing of the highest zone, the page allocator and kswapd interfere with each other. It's worse if the highest zone is small and difficult to balance. 4. slab shrinkers are node-based which makes it harder to identify the exact relationship between slab reclaim and LRU reclaim. The reason we have zone-based reclaim is that we used to have large highmem zones in common configurations and it was necessary to quickly find ZONE_NORMAL pages for reclaim. Today, this is much less of a concern as machines with lots of memory will (or should) use 64-bit kernels. Combinations of 32-bit hardware and 64-bit hardware are rare. Machines that do use highmem should have relatively low highmem:lowmem ratios than we worried about in the past. Conceptually, moving to node LRUs should be easier to understand. The page allocator plays fewer tricks to game reclaim and reclaim behaves similarly on all nodes. The series has been tested on a 16 core UMA machine and a 2-socket 48 core NUMA machine. The UMA results are presented in most cases as the NUMA machine behaved similarly. pagealloc --------- This is a microbenchmark that shows the benefit of removing the fair zone allocation policy. It was tested uip to order-4 but only orders 0 and 1 are shown as the other orders were comparable. 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 nodelru-v9 Min total-odr0-1 490.00 ( 0.00%) 457.00 ( 6.73%) Min total-odr0-2 347.00 ( 0.00%) 329.00 ( 5.19%) Min total-odr0-4 288.00 ( 0.00%) 273.00 ( 5.21%) Min total-odr0-8 251.00 ( 0.00%) 239.00 ( 4.78%) Min total-odr0-16 234.00 ( 0.00%) 222.00 ( 5.13%) Min total-odr0-32 223.00 ( 0.00%) 211.00 ( 5.38%) Min total-odr0-64 217.00 ( 0.00%) 208.00 ( 4.15%) Min total-odr0-128 214.00 ( 0.00%) 204.00 ( 4.67%) Min total-odr0-256 250.00 ( 0.00%) 230.00 ( 8.00%) Min total-odr0-512 271.00 ( 0.00%) 269.00 ( 0.74%) Min total-odr0-1024 291.00 ( 0.00%) 282.00 ( 3.09%) Min total-odr0-2048 303.00 ( 0.00%) 296.00 ( 2.31%) Min total-odr0-4096 311.00 ( 0.00%) 309.00 ( 0.64%) Min total-odr0-8192 316.00 ( 0.00%) 314.00 ( 0.63%) Min total-odr0-16384 317.00 ( 0.00%) 315.00 ( 0.63%) Min total-odr1-1 742.00 ( 0.00%) 712.00 ( 4.04%) Min total-odr1-2 562.00 ( 0.00%) 530.00 ( 5.69%) Min total-odr1-4 457.00 ( 0.00%) 433.00 ( 5.25%) Min total-odr1-8 411.00 ( 0.00%) 381.00 ( 7.30%) Min total-odr1-16 381.00 ( 0.00%) 356.00 ( 6.56%) Min total-odr1-32 372.00 ( 0.00%) 346.00 ( 6.99%) Min total-odr1-64 372.00 ( 0.00%) 343.00 ( 7.80%) Min total-odr1-128 375.00 ( 0.00%) 351.00 ( 6.40%) Min total-odr1-256 379.00 ( 0.00%) 351.00 ( 7.39%) Min total-odr1-512 385.00 ( 0.00%) 355.00 ( 7.79%) Min total-odr1-1024 386.00 ( 0.00%) 358.00 ( 7.25%) Min total-odr1-2048 390.00 ( 0.00%) 362.00 ( 7.18%) Min total-odr1-4096 390.00 ( 0.00%) 362.00 ( 7.18%) Min total-odr1-8192 388.00 ( 0.00%) 363.00 ( 6.44%) This shows a steady improvement throughout. The primary benefit is from reduced system CPU usage which is obvious from the overall times; 4.7.0-rc4 4.7.0-rc4 mmotm-20160623nodelru-v8 User 189.19 191.80 System 2604.45 2533.56 Elapsed 2855.30 2786.39 The vmstats also showed that the fair zone allocation policy was definitely removed as can be seen here; 4.7.0-rc3 4.7.0-rc3 mmotm-20160623 nodelru-v8 DMA32 allocs 28794729769 0 Normal allocs 48432501431 77227309877 Movable allocs 0 0 tiobench on ext4 ---------------- tiobench is a benchmark that artifically benefits if old pages remain resident while new pages get reclaimed. The fair zone allocation policy mitigates this problem so pages age fairly. While the benchmark has problems, it is important that tiobench performance remains constant as it implies that page aging problems that the fair zone allocation policy fixes are not re-introduced. 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 nodelru-v9 Min PotentialReadSpeed 89.65 ( 0.00%) 90.21 ( 0.62%) Min SeqRead-MB/sec-1 82.68 ( 0.00%) 82.01 ( -0.81%) Min SeqRead-MB/sec-2 72.76 ( 0.00%) 72.07 ( -0.95%) Min SeqRead-MB/sec-4 75.13 ( 0.00%) 74.92 ( -0.28%) Min SeqRead-MB/sec-8 64.91 ( 0.00%) 65.19 ( 0.43%) Min SeqRead-MB/sec-16 62.24 ( 0.00%) 62.22 ( -0.03%) Min RandRead-MB/sec-1 0.88 ( 0.00%) 0.88 ( 0.00%) Min RandRead-MB/sec-2 0.95 ( 0.00%) 0.92 ( -3.16%) Min RandRead-MB/sec-4 1.43 ( 0.00%) 1.34 ( -6.29%) Min RandRead-MB/sec-8 1.61 ( 0.00%) 1.60 ( -0.62%) Min RandRead-MB/sec-16 1.80 ( 0.00%) 1.90 ( 5.56%) Min SeqWrite-MB/sec-1 76.41 ( 0.00%) 76.85 ( 0.58%) Min SeqWrite-MB/sec-2 74.11 ( 0.00%) 73.54 ( -0.77%) Min SeqWrite-MB/sec-4 80.05 ( 0.00%) 80.13 ( 0.10%) Min SeqWrite-MB/sec-8 72.88 ( 0.00%) 73.20 ( 0.44%) Min SeqWrite-MB/sec-16 75.91 ( 0.00%) 76.44 ( 0.70%) Min RandWrite-MB/sec-1 1.18 ( 0.00%) 1.14 ( -3.39%) Min RandWrite-MB/sec-2 1.02 ( 0.00%) 1.03 ( 0.98%) Min RandWrite-MB/sec-4 1.05 ( 0.00%) 0.98 ( -6.67%) Min RandWrite-MB/sec-8 0.89 ( 0.00%) 0.92 ( 3.37%) Min RandWrite-MB/sec-16 0.92 ( 0.00%) 0.93 ( 1.09%) 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 approx-v9 User 645.72 525.90 System 403.85 331.75 Elapsed 6795.36 6783.67 This shows that the series has little or not impact on tiobench which is desirable and a reduction in system CPU usage. It indicates that the fair zone allocation policy was removed in a manner that didn't reintroduce one class of page aging bug. There were only minor differences in overall reclaim activity 4.7.0-rc4 4.7.0-rc4 mmotm-20160623nodelru-v8 Minor Faults 645838 647465 Major Faults 573 640 Swap Ins 0 0 Swap Outs 0 0 DMA allocs 0 0 DMA32 allocs 46041453 44190646 Normal allocs 78053072 79887245 Movable allocs 0 0 Allocation stalls 24 67 Stall zone DMA 0 0 Stall zone DMA32 0 0 Stall zone Normal 0 2 Stall zone HighMem 0 0 Stall zone Movable 0 65 Direct pages scanned 10969 30609 Kswapd pages scanned 93375144 93492094 Kswapd pages reclaimed 93372243 93489370 Direct pages reclaimed 10969 30609 Kswapd efficiency 99% 99% Kswapd velocity 13741.015 13781.934 Direct efficiency 100% 100% Direct velocity 1.614 4.512 Percentage direct scans 0% 0% kswapd activity was roughly comparable. There were differences in direct reclaim activity but negligible in the context of the overall workload (velocity of 4 pages per second with the patches applied, 1.6 pages per second in the baseline kernel). pgbench read-only large configuration on ext4 --------------------------------------------- pgbench is a database benchmark that can be sensitive to page reclaim decisions. This also checks if removing the fair zone allocation policy is safe pgbench Transactions 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 nodelru-v8 Hmean 1 188.26 ( 0.00%) 189.78 ( 0.81%) Hmean 5 330.66 ( 0.00%) 328.69 ( -0.59%) Hmean 12 370.32 ( 0.00%) 380.72 ( 2.81%) Hmean 21 368.89 ( 0.00%) 369.00 ( 0.03%) Hmean 30 382.14 ( 0.00%) 360.89 ( -5.56%) Hmean 32 428.87 ( 0.00%) 432.96 ( 0.95%) Negligible differences again. As with tiobench, overall reclaim activity was comparable. bonnie++ on ext4 ---------------- No interesting performance difference, negligible differences on reclaim stats. paralleldd on ext4 ------------------ This workload uses varying numbers of dd instances to read large amounts of data from disk. 4.7.0-rc3 4.7.0-rc3 mmotm-20160623 nodelru-v9 Amean Elapsd-1 186.04 ( 0.00%) 189.41 ( -1.82%) Amean Elapsd-3 192.27 ( 0.00%) 191.38 ( 0.46%) Amean Elapsd-5 185.21 ( 0.00%) 182.75 ( 1.33%) Amean Elapsd-7 183.71 ( 0.00%) 182.11 ( 0.87%) Amean Elapsd-12 180.96 ( 0.00%) 181.58 ( -0.35%) Amean Elapsd-16 181.36 ( 0.00%) 183.72 ( -1.30%) 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 nodelru-v9 User 1548.01 1552.44 System 8609.71 8515.08 Elapsed 3587.10 3594.54 There is little or no change in performance but some drop in system CPU usage. 4.7.0-rc3 4.7.0-rc3 mmotm-20160623 nodelru-v9 Minor Faults 362662 367360 Major Faults 1204 1143 Swap Ins 22 0 Swap Outs 2855 1029 DMA allocs 0 0 DMA32 allocs 31409797 28837521 Normal allocs 46611853 49231282 Movable allocs 0 0 Direct pages scanned 0 0 Kswapd pages scanned 40845270 40869088 Kswapd pages reclaimed 40830976 40855294 Direct pages reclaimed 0 0 Kswapd efficiency 99% 99% Kswapd velocity 11386.711 11369.769 Direct efficiency 100% 100% Direct velocity 0.000 0.000 Percentage direct scans 0% 0% Page writes by reclaim 2855 1029 Page writes file 0 0 Page writes anon 2855 1029 Page reclaim immediate 771 1628 Sector Reads 293312636 293536360 Sector Writes 18213568 18186480 Page rescued immediate 0 0 Slabs scanned 128257 132747 Direct inode steals 181 56 Kswapd inode steals 59 1131 It basically shows that kswapd was active at roughly the same rate in both kernels. There was also comparable slab scanning activity and direct reclaim was avoided in both cases. There appears to be a large difference in numbers of inodes reclaimed but the workload has few active inodes and is likely a timing artifact. stutter ------- stutter simulates a simple workload. One part uses a lot of anonymous memory, a second measures mmap latency and a third copies a large file. The primary metric is checking for mmap latency. stutter 4.7.0-rc4 4.7.0-rc4 mmotm-20160623 nodelru-v8 Min mmap 16.6283 ( 0.00%) 13.4258 ( 19.26%) 1st-qrtle mmap 54.7570 ( 0.00%) 34.9121 ( 36.24%) 2nd-qrtle mmap 57.3163 ( 0.00%) 46.1147 ( 19.54%) 3rd-qrtle mmap 58.9976 ( 0.00%) 47.1882 ( 20.02%) Max-90% mmap 59.7433 ( 0.00%) 47.4453 ( 20.58%) Max-93% mmap 60.1298 ( 0.00%) 47.6037 ( 20.83%) Max-95% mmap 73.4112 ( 0.00%) 82.8719 (-12.89%) Max-99% mmap 92.8542 ( 0.00%) 88.8870 ( 4.27%) Max mmap 1440.6569 ( 0.00%) 121.4201 ( 91.57%) Mean mmap 59.3493 ( 0.00%) 42.2991 ( 28.73%) Best99%Mean mmap 57.2121 ( 0.00%) 41.8207 ( 26.90%) Best95%Mean mmap 55.9113 ( 0.00%) 39.9620 ( 28.53%) Best90%Mean mmap 55.6199 ( 0.00%) 39.3124 ( 29.32%) Best50%Mean mmap 53.2183 ( 0.00%) 33.1307 ( 37.75%) Best10%Mean mmap 45.9842 ( 0.00%) 20.4040 ( 55.63%) Best5%Mean mmap 43.2256 ( 0.00%) 17.9654 ( 58.44%) Best1%Mean mmap 32.9388 ( 0.00%) 16.6875 ( 49.34%) This shows a number of improvements with the worst-case outlier greatly improved. Some of the vmstats are interesting 4.7.0-rc4 4.7.0-rc4 mmotm-20160623nodelru-v8 Swap Ins 163 502 Swap Outs 0 0 DMA allocs 0 0 DMA32 allocs 618719206 1381662383 Normal allocs 891235743 564138421 Movable allocs 0 0 Allocation stalls 2603 1 Direct pages scanned 216787 2 Kswapd pages scanned 50719775 41778378 Kswapd pages reclaimed 41541765 41777639 Direct pages reclaimed 209159 0 Kswapd efficiency 81% 99% Kswapd velocity 16859.554 14329.059 Direct efficiency 96% 0% Direct velocity 72.061 0.001 Percentage direct scans 0% 0% Page writes by reclaim 6215049 0 Page writes file 6215049 0 Page writes anon 0 0 Page reclaim immediate 70673 90 Sector Reads 81940800 81680456 Sector Writes 100158984 98816036 Page rescued immediate 0 0 Slabs scanned 1366954 22683 While this is not guaranteed in all cases, this particular test showed a large reduction in direct reclaim activity. It's also worth noting that no page writes were issued from reclaim context. This series is not without its hazards. There are at least three areas that I'm concerned with even though I could not reproduce any problems in that area. 1. Reclaim/compaction is going to be affected because the amount of reclaim is no longer targetted at a specific zone. Compaction works on a per-zone basis so there is no guarantee that reclaiming a few THP's worth page pages will have a positive impact on compaction success rates. 2. The Slab/LRU reclaim ratio is affected because the frequency the shrinkers are called is now different. This may or may not be a problem but if it is, it'll be because shrinkers are not called enough and some balancing is required. 3. The anon/file reclaim ratio may be affected. Pages about to be dirtied are distributed between zones and the fair zone allocation policy used to do something very similar for anon. The distribution is now different but not necessarily in any way that matters but it's still worth bearing in mind. VM statistic counters for reclaim decisions are zone-based. If the kernel is to reclaim on a per-node basis then we need to track per-node statistics but there is no infrastructure for that. The most notable change is that the old node_page_state is renamed to sum_zone_node_page_state. The new node_page_state takes a pglist_data and uses per-node stats but none exist yet. There is some renaming such as vm_stat to vm_zone_stat and the addition of vm_node_stat and the renaming of mod_state to mod_zone_state. Otherwise, this is mostly a mechanical patch with no functional change. There is a lot of similarity between the node and zone helpers which is unfortunate but there was no obvious way of reusing the code and maintaining type safety. Link: http://lkml.kernel.org/r/1467970510-21195-2-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Rik van Riel Cc: Vlastimil Babka Cc: Johannes Weiner Cc: Minchan Kim Cc: Joonsoo Kim Cc: Hillf Danton Cc: Michal Hocko Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 +++ include/linux/mmzone.h | 13 +++++++ include/linux/vmstat.h | 92 +++++++++++++++++++++++++++++++++++++++++++------- 3 files changed, 98 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 97065e1f0237..08ed53eeedd5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -933,6 +933,11 @@ static inline struct zone *page_zone(const struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } +static inline pg_data_t *page_pgdat(const struct page *page) +{ + return NODE_DATA(page_to_nid(page)); +} + #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 19425e988bdc..078ecb81e209 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -160,6 +160,10 @@ enum zone_stat_item { NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; +enum node_stat_item { + NR_VM_NODE_STAT_ITEMS +}; + /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in @@ -267,6 +271,11 @@ struct per_cpu_pageset { #endif }; +struct per_cpu_nodestat { + s8 stat_threshold; + s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; +}; + #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { @@ -695,6 +704,10 @@ typedef struct pglist_data { struct list_head split_queue; unsigned long split_queue_len; #endif + + /* Per-node vmstats */ + struct per_cpu_nodestat __percpu *per_cpu_nodestats; + atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d2da8e053210..d1744aa3ab9c 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -106,20 +106,38 @@ static inline void vm_events_fold_cpu(int cpu) zone_idx(zone), delta) /* - * Zone based page accounting with per cpu differentials. + * Zone and node-based page accounting with per cpu differentials. */ -extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; +extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; +extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); - atomic_long_add(x, &vm_stat[item]); + atomic_long_add(x, &vm_zone_stat[item]); +} + +static inline void node_page_state_add(long x, struct pglist_data *pgdat, + enum node_stat_item item) +{ + atomic_long_add(x, &pgdat->vm_stat[item]); + atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_page_state(enum zone_stat_item item) { - long x = atomic_long_read(&vm_stat[item]); + long x = atomic_long_read(&vm_zone_stat[item]); +#ifdef CONFIG_SMP + if (x < 0) + x = 0; +#endif + return x; +} + +static inline unsigned long global_node_page_state(enum node_stat_item item) +{ + long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -161,31 +179,44 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA - -extern unsigned long node_page_state(int node, enum zone_stat_item item); - +extern unsigned long sum_zone_node_page_state(int node, + enum zone_stat_item item); +extern unsigned long node_page_state(struct pglist_data *pgdat, + enum node_stat_item item); #else - -#define node_page_state(node, item) global_page_state(item) - +#define sum_zone_node_page_state(node, item) global_page_state(item) +#define node_page_state(node, item) global_node_page_state(item) #endif /* CONFIG_NUMA */ #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d) #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) +#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d) +#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d)) #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); +void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); +void __inc_node_page_state(struct page *, enum node_stat_item); +void __dec_node_page_state(struct page *, enum node_stat_item); + void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); +void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); +void inc_node_page_state(struct page *, enum node_stat_item); +void dec_node_page_state(struct page *, enum node_stat_item); + extern void inc_zone_state(struct zone *, enum zone_stat_item); +extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); +extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); +extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); @@ -213,16 +244,34 @@ static inline void __mod_zone_page_state(struct zone *zone, zone_page_state_add(delta, zone, item); } +static inline void __mod_node_page_state(struct pglist_data *pgdat, + enum node_stat_item item, int delta) +{ + node_page_state_add(delta, pgdat, item); +} + static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); - atomic_long_inc(&vm_stat[item]); + atomic_long_inc(&vm_zone_stat[item]); +} + +static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + atomic_long_inc(&pgdat->vm_stat[item]); + atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); - atomic_long_dec(&vm_stat[item]); + atomic_long_dec(&vm_zone_stat[item]); +} + +static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) +{ + atomic_long_dec(&pgdat->vm_stat[item]); + atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, @@ -231,12 +280,26 @@ static inline void __inc_zone_page_state(struct page *page, __inc_zone_state(page_zone(page), item); } +static inline void __inc_node_page_state(struct page *page, + enum node_stat_item item) +{ + __inc_node_state(page_pgdat(page), item); +} + + static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } +static inline void __dec_node_page_state(struct page *page, + enum node_stat_item item) +{ + __dec_node_state(page_pgdat(page), item); +} + + /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. @@ -245,7 +308,12 @@ static inline void __dec_zone_page_state(struct page *page, #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state +#define inc_node_page_state __inc_node_page_state +#define dec_node_page_state __dec_node_page_state +#define mod_node_page_state __mod_node_page_state + #define inc_zone_state __inc_zone_state +#define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } -- cgit v1.2.3 From a52633d8e9c35832f1409dc5fa166019048a3f1f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:28 -0700 Subject: mm, vmscan: move lru_lock to the node Node-based reclaim requires node-based LRUs and locking. This is a preparation patch that just moves the lru_lock to the node so later patches are easier to review. It is a mechanical change but note this patch makes contention worse because the LRU lock is hotter and direct reclaim and kswapd can contend on the same lock even when reclaiming from different zones. Link: http://lkml.kernel.org/r/1467970510-21195-3-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mmzone.h | 10 ++++++++-- 2 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 79472b22d23f..903200f4ec41 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -118,7 +118,7 @@ struct page { */ union { struct list_head lru; /* Pageout list, eg. active_list - * protected by zone->lru_lock ! + * protected by zone_lru_lock ! * Can be used as a generic list * by the page owner. */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 078ecb81e209..cfa870107abe 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -93,7 +93,7 @@ struct free_area { struct pglist_data; /* - * zone->lock and zone->lru_lock are two of the hottest locks in the kernel. + * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. * So add a wild amount of padding here to ensure that they fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. @@ -496,7 +496,6 @@ struct zone { /* Write-intensive fields used by page reclaim */ /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; struct lruvec lruvec; /* @@ -690,6 +689,9 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + /* Write-intensive fields used by page reclaim */ + ZONE_PADDING(_pad1_) + spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* @@ -721,6 +723,10 @@ typedef struct pglist_data { #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) +static inline spinlock_t *zone_lru_lock(struct zone *zone) +{ + return &zone->zone_pgdat->lru_lock; +} static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { -- cgit v1.2.3 From 599d0c954f91d0689c9bb421b5bc04ea02437a41 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:31 -0700 Subject: mm, vmscan: move LRU lists to node This moves the LRU lists from the zone to the node and related data such as counters, tracing, congestion tracking and writeback tracking. Unfortunately, due to reclaim and compaction retry logic, it is necessary to account for the number of LRU pages on both zone and node logic. Most reclaim logic is based on the node counters but the retry logic uses the zone counters which do not distinguish inactive and active sizes. It would be possible to leave the LRU counters on a per-zone basis but it's a heavier calculation across multiple cache lines that is much more frequent than the retry checks. Other than the LRU counters, this is mostly a mechanical patch but note that it introduces a number of anomalies. For example, the scans are per-zone but using per-node counters. We also mark a node as congested when a zone is congested. This causes weird problems that are fixed later but is easier to review. In the event that there is excessive overhead on 32-bit systems due to the nodes being on LRU then there are two potential solutions 1. Long-term isolation of highmem pages when reclaim is lowmem When pages are skipped, they are immediately added back onto the LRU list. If lowmem reclaim persisted for long periods of time, the same highmem pages get continually scanned. The idea would be that lowmem keeps those pages on a separate list until a reclaim for highmem pages arrives that splices the highmem pages back onto the LRU. It potentially could be implemented similar to the UNEVICTABLE list. That would reduce the skip rate with the potential corner case is that highmem pages have to be scanned and reclaimed to free lowmem slab pages. 2. Linear scan lowmem pages if the initial LRU shrink fails This will break LRU ordering but may be preferable and faster during memory pressure than skipping LRU pages. Link: http://lkml.kernel.org/r/1467970510-21195-4-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 2 +- include/linux/memcontrol.h | 18 ++++++------ include/linux/mm_inline.h | 21 ++++++++----- include/linux/mmzone.h | 68 ++++++++++++++++++++++++++----------------- include/linux/swap.h | 1 + include/linux/vm_event_item.h | 10 +++---- include/linux/vmstat.h | 17 +++++++++++ include/trace/events/vmscan.h | 12 ++++---- 8 files changed, 93 insertions(+), 56 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c82794f20110..491a91717788 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(struct zone *zone, int sync, long timeout); +long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); int pdflush_proc_obsolete(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1c4df4420258..6d2321c148cd 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -339,7 +339,7 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = &zone->lruvec; + lruvec = zone_lruvec(zone); goto out; } @@ -348,15 +348,15 @@ static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, out: /* * Since a node can be onlined after the mem_cgroup was created, - * we have to be prepared to initialize lruvec->zone here; + * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->zone != zone)) - lruvec->zone = zone; + if (unlikely(lruvec->pgdat != zone->zone_pgdat)) + lruvec->pgdat = zone->zone_pgdat; return lruvec; } -struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); +struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); @@ -437,7 +437,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - int nr_pages); + enum zone_type zid, int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); @@ -612,13 +612,13 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, struct mem_cgroup *memcg) { - return &zone->lruvec; + return zone_lruvec(zone); } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct zone *zone) + struct pglist_data *pgdat) { - return &zone->lruvec; + return &pgdat->lruvec; } static inline bool mm_match_cgroup(struct mm_struct *mm, diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 5bd29ba4f174..9aadcc781857 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -23,25 +23,32 @@ static inline int page_is_file_cache(struct page *page) } static __always_inline void __update_lru_size(struct lruvec *lruvec, - enum lru_list lru, int nr_pages) + enum lru_list lru, enum zone_type zid, + int nr_pages) { - __mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages); + struct pglist_data *pgdat = lruvec_pgdat(lruvec); + + __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); + __mod_zone_page_state(&pgdat->node_zones[zid], + NR_ZONE_LRU_BASE + !!is_file_lru(lru), + nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, - enum lru_list lru, int nr_pages) + enum lru_list lru, enum zone_type zid, + int nr_pages) { #ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, nr_pages); + mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #else - __update_lru_size(lruvec, lru, nr_pages); + __update_lru_size(lruvec, lru, zid, nr_pages); #endif } static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { - update_lru_size(lruvec, lru, hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page)); list_add(&page->lru, &lruvec->lists[lru]); } @@ -49,7 +56,7 @@ static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec, enum lru_list lru) { list_del(&page->lru); - update_lru_size(lruvec, lru, -hpage_nr_pages(page)); + update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page)); } /** diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index cfa870107abe..d4f5cac0a8c3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -111,12 +111,9 @@ enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ALLOC_BATCH, - NR_LRU_BASE, - NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ - NR_ACTIVE_ANON, /* " " " " " */ - NR_INACTIVE_FILE, /* " " " " " */ - NR_ACTIVE_FILE, /* " " " " " */ - NR_UNEVICTABLE, /* " " " " " */ + NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ + NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, + NR_ZONE_LRU_FILE, NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_ANON_PAGES, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. @@ -134,12 +131,9 @@ enum zone_stat_item { NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ - NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ - NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif @@ -161,6 +155,15 @@ enum zone_stat_item { NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { + NR_LRU_BASE, + NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ + NR_ACTIVE_ANON, /* " " " " " */ + NR_INACTIVE_FILE, /* " " " " " */ + NR_ACTIVE_FILE, /* " " " " " */ + NR_UNEVICTABLE, /* " " " " " */ + NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ + NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ NR_VM_NODE_STAT_ITEMS }; @@ -219,7 +222,7 @@ struct lruvec { /* Evictions & activations on the inactive file list */ atomic_long_t inactive_age; #ifdef CONFIG_MEMCG - struct zone *zone; + struct pglist_data *pgdat; #endif }; @@ -357,13 +360,6 @@ struct zone { #ifdef CONFIG_NUMA int node; #endif - - /* - * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on - * this zone's LRU. Maintained by the pageout code. - */ - unsigned int inactive_ratio; - struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; @@ -495,9 +491,6 @@ struct zone { /* Write-intensive fields used by page reclaim */ - /* Fields commonly accessed by the page reclaim scanner */ - struct lruvec lruvec; - /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter @@ -537,17 +530,20 @@ struct zone { enum zone_flags { ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ - ZONE_CONGESTED, /* zone has many dirty pages backed by + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ +}; + +enum pgdat_flags { + PGDAT_CONGESTED, /* pgdat has many dirty pages backed by * a congested BDI */ - ZONE_DIRTY, /* reclaim scanning has recently found + PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ - ZONE_WRITEBACK, /* reclaim scanning has recently found + PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ - ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ }; static inline unsigned long zone_end_pfn(const struct zone *zone) @@ -707,6 +703,19 @@ typedef struct pglist_data { unsigned long split_queue_len; #endif + /* Fields commonly accessed by the page reclaim scanner */ + struct lruvec lruvec; + + /* + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this node's LRU. Maintained by the pageout code. + */ + unsigned int inactive_ratio; + + unsigned long flags; + + ZONE_PADDING(_pad2_) + /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; @@ -728,6 +737,11 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone) return &zone->zone_pgdat->lru_lock; } +static inline struct lruvec *zone_lruvec(struct zone *zone) +{ + return &zone->zone_pgdat->lruvec; +} + static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; @@ -779,12 +793,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, extern void lruvec_init(struct lruvec *lruvec); -static inline struct zone *lruvec_zone(struct lruvec *lruvec) +static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG - return lruvec->zone; + return lruvec->pgdat; #else - return container_of(lruvec, struct zone, lruvec); + return container_of(lruvec, struct pglist_data, lruvec); #endif } diff --git a/include/linux/swap.h b/include/linux/swap.h index 0af2bb2028fd..c82f916008b7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -317,6 +317,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page, /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); +extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); extern int __isolate_lru_page(struct page *page, isolate_mode_t mode); diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 42604173f122..1798ff542517 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -26,11 +26,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGFREE, PGACTIVATE, PGDEACTIVATE, PGFAULT, PGMAJFAULT, PGLAZYFREED, - FOR_ALL_ZONES(PGREFILL), - FOR_ALL_ZONES(PGSTEAL_KSWAPD), - FOR_ALL_ZONES(PGSTEAL_DIRECT), - FOR_ALL_ZONES(PGSCAN_KSWAPD), - FOR_ALL_ZONES(PGSCAN_DIRECT), + PGREFILL, + PGSTEAL_KSWAPD, + PGSTEAL_DIRECT, + PGSCAN_KSWAPD, + PGSCAN_DIRECT, PGSCAN_DIRECT_THROTTLE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d1744aa3ab9c..fee321c98550 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -178,6 +178,23 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, return x; } +static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat, + enum node_stat_item item) +{ + long x = atomic_long_read(&pgdat->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + + #ifdef CONFIG_NUMA extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 0101ef37f1ee..897f1aa1ee5f 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -352,15 +352,14 @@ TRACE_EVENT(mm_vmscan_writepage, TRACE_EVENT(mm_vmscan_lru_shrink_inactive, - TP_PROTO(struct zone *zone, + TP_PROTO(int nid, unsigned long nr_scanned, unsigned long nr_reclaimed, int priority, int file), - TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file), + TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file), TP_STRUCT__entry( __field(int, nid) - __field(int, zid) __field(unsigned long, nr_scanned) __field(unsigned long, nr_reclaimed) __field(int, priority) @@ -368,16 +367,15 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, ), TP_fast_assign( - __entry->nid = zone_to_nid(zone); - __entry->zid = zone_idx(zone); + __entry->nid = nid; __entry->nr_scanned = nr_scanned; __entry->nr_reclaimed = nr_reclaimed; __entry->priority = priority; __entry->reclaim_flags = trace_shrink_flags(file); ), - TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", - __entry->nid, __entry->zid, + TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s", + __entry->nid, __entry->nr_scanned, __entry->nr_reclaimed, __entry->priority, show_reclaim_flags(__entry->reclaim_flags)) -- cgit v1.2.3 From 0f66114893997f781029c109b0974b7f61130df7 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:34 -0700 Subject: mm, mmzone: clarify the usage of zone padding Zone padding separates write-intensive fields used by page allocation, compaction and vmstats but the comments are a little misleading and need clarification. Link: http://lkml.kernel.org/r/1467970510-21195-5-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4f5cac0a8c3..edafdaf62e90 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -477,20 +477,21 @@ struct zone { unsigned long wait_table_hash_nr_entries; unsigned long wait_table_bits; + /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) + /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; /* zone flags, see below */ unsigned long flags; - /* Write-intensive fields used from the page allocator */ + /* Primarily protects free_area */ spinlock_t lock; + /* Write-intensive fields used by compaction and vmstats. */ ZONE_PADDING(_pad2_) - /* Write-intensive fields used by page reclaim */ - /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter -- cgit v1.2.3 From 31483b6ad205784d3a82240865135bef5c97c105 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:46 -0700 Subject: mm, vmscan: remove balance gap The balance gap was introduced to apply equal pressure to all zones when reclaiming for a higher zone. With node-based LRU, the need for the balance gap is removed and the code is dead so remove it. [vbabka@suse.cz: Also remove KSWAPD_ZONE_BALANCE_GAP_RATIO] Link: http://lkml.kernel.org/r/1467970510-21195-9-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index c82f916008b7..916e2eddecd6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -157,15 +157,6 @@ enum { #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX -/* - * Ratio between zone->managed_pages and the "gap" that above the per-zone - * "high_wmark". While balancing nodes, We allow kswapd to shrink zones that - * do not meet the (high_wmark + gap) watermark, even which already met the - * high_wmark, in order to provide better per-zone lru behavior. We are ok to - * spend not more than 1% of the memory for this zone balancing "gap". - */ -#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100 - #define SWAP_MAP_MAX 0x3e /* Max duplication count, in first swap_map */ #define SWAP_MAP_BAD 0x3f /* Note pageblock is bad, in first swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ -- cgit v1.2.3 From 38087d9b0360987a6db46c2c2c4ece37cd048abe Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:49 -0700 Subject: mm, vmscan: simplify the logic deciding whether kswapd sleeps kswapd goes through some complex steps trying to figure out if it should stay awake based on the classzone_idx and the requested order. It is unnecessarily complex and passes in an invalid classzone_idx to balance_pgdat(). What matters most of all is whether a larger order has been requsted and whether kswapd successfully reclaimed at the previous order. This patch irons out the logic to check just that and the end result is less headache inducing. Link: http://lkml.kernel.org/r/1467970510-21195-10-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index edafdaf62e90..4062fa74526f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -668,8 +668,9 @@ typedef struct pglist_data { wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ - int kswapd_max_order; - enum zone_type classzone_idx; + int kswapd_order; + enum zone_type kswapd_classzone_idx; + #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_classzone_idx; -- cgit v1.2.3 From a9dd0a83104c01269ea36a9b4ec42b51edf85427 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:02 -0700 Subject: mm, vmscan: make shrink_node decisions more node-centric Earlier patches focused on having direct reclaim and kswapd use data that is node-centric for reclaiming but shrink_node() itself still uses too much zone information. This patch removes unnecessary zone-based information with the most important decision being whether to continue reclaim or not. Some memcg APIs are adjusted as a result even though memcg itself still uses some zone information. [mgorman@techsingularity.net: optimization] Link: http://lkml.kernel.org/r/1468588165-12461-2-git-send-email-mgorman@techsingularity.net Link: http://lkml.kernel.org/r/1467970510-21195-14-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 19 ++++++++++--------- include/linux/mmzone.h | 4 ++-- include/linux/swap.h | 2 +- 3 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6d2321c148cd..f4963ee4fdbc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -324,22 +324,23 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) } /** - * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg + * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone + * @node: node of the wanted lruvec * @zone: zone of the wanted lruvec * @memcg: memcg of the wanted lruvec * - * Returns the lru list vector holding pages for the given @zone and - * @mem. This can be the global zone lruvec, if the memory controller + * Returns the lru list vector holding pages for a given @node or a given + * @memcg and @zone. This can be the node lruvec, if the memory controller * is disabled. */ -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, + struct zone *zone, struct mem_cgroup *memcg) { struct mem_cgroup_per_zone *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { - lruvec = zone_lruvec(zone); + lruvec = node_lruvec(pgdat); goto out; } @@ -609,10 +610,10 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } -static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone, - struct mem_cgroup *memcg) +static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, + struct zone *zone, struct mem_cgroup *memcg) { - return zone_lruvec(zone); + return node_lruvec(pgdat); } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4062fa74526f..895c365e3259 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -739,9 +739,9 @@ static inline spinlock_t *zone_lru_lock(struct zone *zone) return &zone->zone_pgdat->lru_lock; } -static inline struct lruvec *zone_lruvec(struct zone *zone) +static inline struct lruvec *node_lruvec(struct pglist_data *pgdat) { - return &zone->zone_pgdat->lruvec; + return &pgdat->lruvec; } static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) diff --git a/include/linux/swap.h b/include/linux/swap.h index 916e2eddecd6..0ad616d7c381 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -316,7 +316,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap); -extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, +extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, struct zone *zone, unsigned long *nr_scanned); -- cgit v1.2.3 From ef8f2327996b5c20f11420f64e439e87c7a01604 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:05 -0700 Subject: mm, memcg: move memcg limit enforcement from zones to nodes Memcg needs adjustment after moving LRUs to the node. Limits are tracked per memcg but the soft-limit excess is tracked per zone. As global page reclaim is based on the node, it is easy to imagine a situation where a zone soft limit is exceeded even though the memcg limit is fine. This patch moves the soft limit tree the node. Technically, all the variable names should also change but people are already familiar by the meaning of "mz" even if "mn" would be a more appropriate name now. Link: http://lkml.kernel.org/r/1467970510-21195-15-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Michal Hocko Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 38 +++++++++++++++----------------------- include/linux/swap.h | 2 +- 2 files changed, 16 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f4963ee4fdbc..b759827b2f1e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -60,7 +60,7 @@ enum mem_cgroup_stat_index { }; struct mem_cgroup_reclaim_cookie { - struct zone *zone; + pg_data_t *pgdat; int priority; unsigned int generation; }; @@ -118,7 +118,7 @@ struct mem_cgroup_reclaim_iter { /* * per-zone information in memory controller. */ -struct mem_cgroup_per_zone { +struct mem_cgroup_per_node { struct lruvec lruvec; unsigned long lru_size[NR_LRU_LISTS]; @@ -132,10 +132,6 @@ struct mem_cgroup_per_zone { /* use container_of */ }; -struct mem_cgroup_per_node { - struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; -}; - struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; @@ -314,19 +310,15 @@ void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); -static inline struct mem_cgroup_per_zone * -mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) +static struct mem_cgroup_per_node * +mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { - int nid = zone_to_nid(zone); - int zid = zone_idx(zone); - - return &memcg->nodeinfo[nid]->zoneinfo[zid]; + return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone * @node: node of the wanted lruvec - * @zone: zone of the wanted lruvec * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @node or a given @@ -334,9 +326,9 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) * is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct zone *zone, struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { @@ -344,7 +336,7 @@ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, goto out; } - mz = mem_cgroup_zone_zoneinfo(memcg, zone); + mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* @@ -352,8 +344,8 @@ out: * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ - if (unlikely(lruvec->pgdat != zone->zone_pgdat)) - lruvec->pgdat = zone->zone_pgdat; + if (unlikely(lruvec->pgdat != pgdat)) + lruvec->pgdat = pgdat; return lruvec; } @@ -446,9 +438,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { - struct mem_cgroup_per_zone *mz; + struct mem_cgroup_per_node *mz; - mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->lru_size[lru]; } @@ -519,7 +511,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, mem_cgroup_update_page_stat(page, idx, -1); } -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); @@ -611,7 +603,7 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new) } static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, - struct zone *zone, struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { return node_lruvec(pgdat); } @@ -723,7 +715,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, } static inline -unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, +unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 0ad616d7c381..2a23ddc96edd 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -318,7 +318,7 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, bool may_swap); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, - struct zone *zone, + pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -- cgit v1.2.3 From 1e6b10857f91685c60c341703ece4ae9bb775cf3 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:08 -0700 Subject: mm, workingset: make working set detection node-aware Working set and refault detection is still zone-based, fix it. Link: http://lkml.kernel.org/r/1467970510-21195-16-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++--- include/linux/vmstat.h | 1 - 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 895c365e3259..62f477d6cfe8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -145,9 +145,6 @@ enum zone_stat_item { NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif - WORKINGSET_REFAULT, - WORKINGSET_ACTIVATE, - WORKINGSET_NODERECLAIM, NR_ANON_THPS, NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, @@ -164,6 +161,9 @@ enum node_stat_item { NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ NR_PAGES_SCANNED, /* pages scanned since last reclaim */ + WORKINGSET_REFAULT, + WORKINGSET_ACTIVATE, + WORKINGSET_NODERECLAIM, NR_VM_NODE_STAT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index fee321c98550..6b7975cd98aa 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -227,7 +227,6 @@ void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); -extern void inc_zone_state(struct zone *, enum zone_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); -- cgit v1.2.3 From 281e37265f2826ed401d84d6790226448ef3f0e8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:11 -0700 Subject: mm, page_alloc: consider dirtyable memory in terms of nodes Historically dirty pages were spread among zones but now that LRUs are per-node it is more appropriate to consider dirty pages in a node. Link: http://lkml.kernel.org/r/1467970510-21195-17-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Signed-off-by: Johannes Weiner Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Hillf Danton Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 12 ++++++------ include/linux/writeback.h | 2 +- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 62f477d6cfe8..fae2fe3c6942 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -363,12 +363,6 @@ struct zone { struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; - /* - * This is a per-zone reserve of pages that are not available - * to userspace allocations. - */ - unsigned long totalreserve_pages; - #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. @@ -687,6 +681,12 @@ typedef struct pglist_data { /* Number of pages migrated during the rate limiting time interval */ unsigned long numabalancing_migrate_nr_pages; #endif + /* + * This is a per-node reserve of pages that are not available + * to userspace allocations. + */ + unsigned long totalreserve_pages; + /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 717e6149e753..fc1e16c25a29 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data); static inline void laptop_sync_completion(void) { } #endif void throttle_vm_writeout(gfp_t gfp_mask); -bool zone_dirty_ok(struct zone *zone); +bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom); -- cgit v1.2.3 From 50658e2e04c12d5cd628381c1b9cb69d0093a9c0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:14 -0700 Subject: mm: move page mapped accounting to the node Reclaim makes decisions based on the number of pages that are mapped but it's mixing node and zone information. Account NR_FILE_MAPPED and NR_ANON_PAGES pages on the node. Link: http://lkml.kernel.org/r/1467970510-21195-18-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fae2fe3c6942..95d34d1e1fb5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -115,9 +115,6 @@ enum zone_stat_item { NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, NR_ZONE_LRU_FILE, NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_ANON_PAGES, /* Mapped anonymous pages */ - NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. - only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, @@ -164,6 +161,9 @@ enum node_stat_item { WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_NODERECLAIM, + NR_ANON_PAGES, /* Mapped anonymous pages */ + NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. + only modified from process context */ NR_VM_NODE_STAT_ITEMS }; -- cgit v1.2.3 From 4b9d0fab7166c9323f06d708518a35cf3a90426c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:17 -0700 Subject: mm: rename NR_ANON_PAGES to NR_ANON_MAPPED NR_FILE_PAGES is the number of file pages. NR_FILE_MAPPED is the number of mapped file pages. NR_ANON_PAGES is the number of mapped anon pages. This is unhelpful naming as it's easy to confuse NR_FILE_MAPPED and NR_ANON_PAGES for mapped pages. This patch renames NR_ANON_PAGES so we have NR_FILE_PAGES is the number of file pages. NR_FILE_MAPPED is the number of mapped file pages. NR_ANON_MAPPED is the number of mapped anon pages. Link: http://lkml.kernel.org/r/1467970510-21195-19-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 95d34d1e1fb5..2d4a8804eafa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,7 +161,7 @@ enum node_stat_item { WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_NODERECLAIM, - NR_ANON_PAGES, /* Mapped anonymous pages */ + NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_VM_NODE_STAT_ITEMS -- cgit v1.2.3 From 11fb998986a72aa7e997d96d63d52582a01228c5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:20 -0700 Subject: mm: move most file-based accounting to the node There are now a number of accounting oddities such as mapped file pages being accounted for on the node while the total number of file pages are accounted on the zone. This can be coped with to some extent but it's confusing so this patch moves the relevant file-based accounted. Due to throttling logic in the page allocator for reliable OOM detection, it is still necessary to track dirty and writeback pages on a per-zone basis. [mgorman@techsingularity.net: fix NR_ZONE_WRITE_PENDING accounting] Link: http://lkml.kernel.org/r/1468404004-5085-5-git-send-email-mgorman@techsingularity.net Link: http://lkml.kernel.org/r/1467970510-21195-20-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 19 ++++++++++--------- include/trace/events/writeback.h | 6 +++--- 2 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2d4a8804eafa..acd4665c3025 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,21 +114,16 @@ enum zone_stat_item { NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, NR_ZONE_LRU_FILE, + NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ - NR_FILE_PAGES, - NR_FILE_DIRTY, - NR_WRITEBACK, NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_KERNEL_STACK, /* Second 128 byte cacheline */ - NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ - NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ - NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ #if IS_ENABLED(CONFIG_ZSMALLOC) @@ -142,9 +137,6 @@ enum zone_stat_item { NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif - NR_ANON_THPS, - NR_SHMEM_THPS, - NR_SHMEM_PMDMAPPED, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; @@ -164,6 +156,15 @@ enum node_stat_item { NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ + NR_FILE_PAGES, + NR_FILE_DIRTY, + NR_WRITEBACK, + NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ + NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ + NR_SHMEM_THPS, + NR_SHMEM_PMDMAPPED, + NR_ANON_THPS, + NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 531f5811ff6b..ad20f2d2b1f9 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -412,9 +412,9 @@ TRACE_EVENT(global_dirty_state, ), TP_fast_assign( - __entry->nr_dirty = global_page_state(NR_FILE_DIRTY); - __entry->nr_writeback = global_page_state(NR_WRITEBACK); - __entry->nr_unstable = global_page_state(NR_UNSTABLE_NFS); + __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); + __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); + __entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS); __entry->nr_dirtied = global_page_state(NR_DIRTIED); __entry->nr_written = global_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; -- cgit v1.2.3 From c4a25635b60d08853a3e4eaae3ab34419a36cfa2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:23 -0700 Subject: mm: move vmscan writes and file write accounting to the node As reclaim is now node-based, it follows that page write activity due to page reclaim should also be accounted for on the node. For consistency, also account page writes and page dirtying on a per-node basis. After this patch, there are a few remaining zone counters that may appear strange but are fine. NUMA stats are still per-zone as this is a user-space interface that tools consume. NR_MLOCK, NR_SLAB_*, NR_PAGETABLE, NR_KERNEL_STACK and NR_BOUNCE are all allocations that potentially pin low memory and cannot trivially be reclaimed on demand. This information is still useful for debugging a page allocation failure warning. Link: http://lkml.kernel.org/r/1467970510-21195-21-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 8 ++++---- include/trace/events/writeback.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index acd4665c3025..e3d6d42722a0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -122,10 +122,6 @@ enum zone_stat_item { NR_KERNEL_STACK, /* Second 128 byte cacheline */ NR_BOUNCE, - NR_VMSCAN_WRITE, - NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ - NR_DIRTIED, /* page dirtyings since bootup */ - NR_WRITTEN, /* page writings since bootup */ #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif @@ -165,6 +161,10 @@ enum node_stat_item { NR_SHMEM_PMDMAPPED, NR_ANON_THPS, NR_UNSTABLE_NFS, /* NFS unstable pages */ + NR_VMSCAN_WRITE, + NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ + NR_DIRTIED, /* page dirtyings since bootup */ + NR_WRITTEN, /* page writings since bootup */ NR_VM_NODE_STAT_ITEMS }; diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index ad20f2d2b1f9..2ccd9ccbf9ef 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -415,8 +415,8 @@ TRACE_EVENT(global_dirty_state, __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_unstable = global_node_page_state(NR_UNSTABLE_NFS); - __entry->nr_dirtied = global_page_state(NR_DIRTIED); - __entry->nr_written = global_page_state(NR_WRITTEN); + __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); + __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; -- cgit v1.2.3 From a5f5f91da6ad647fb0cc7fce0e17343c0d1c5a9a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:32 -0700 Subject: mm: convert zone_reclaim to node_reclaim As reclaim is now per-node based, convert zone_reclaim to be node_reclaim. It is possible that a node will be reclaimed multiple times if it has multiple zones but this is unavoidable without caching all nodes traversed so far. The documentation and interface to userspace is the same from a configuration perspective and will will be similar in behaviour unless the node-local allocation requests were also limited to lower zones. Link: http://lkml.kernel.org/r/1467970510-21195-24-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 18 +++++++++--------- include/linux/swap.h | 9 +++++---- include/linux/topology.h | 2 +- 3 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e3d6d42722a0..e19c081c794e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -372,14 +372,6 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_NUMA - /* - * zone reclaim becomes active if more unmapped pages exist. - */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif /* CONFIG_NUMA */ - /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -525,7 +517,6 @@ struct zone { } ____cacheline_internodealigned_in_smp; enum zone_flags { - ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ }; @@ -540,6 +531,7 @@ enum pgdat_flags { PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ + PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; static inline unsigned long zone_end_pfn(const struct zone *zone) @@ -688,6 +680,14 @@ typedef struct pglist_data { */ unsigned long totalreserve_pages; +#ifdef CONFIG_NUMA + /* + * zone reclaim becomes active if more unmapped pages exist. + */ + unsigned long min_unmapped_pages; + unsigned long min_slab_pages; +#endif /* CONFIG_NUMA */ + /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; diff --git a/include/linux/swap.h b/include/linux/swap.h index 2a23ddc96edd..b17cc4830fa6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -326,13 +326,14 @@ extern int remove_mapping(struct address_space *mapping, struct page *page); extern unsigned long vm_total_pages; #ifdef CONFIG_NUMA -extern int zone_reclaim_mode; +extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; -extern int zone_reclaim(struct zone *, gfp_t, unsigned int); +extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); #else -#define zone_reclaim_mode 0 -static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) +#define node_reclaim_mode 0 +static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, + unsigned int order) { return 0; } diff --git a/include/linux/topology.h b/include/linux/topology.h index afce69296ac0..cb0775e1ee4b 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -54,7 +54,7 @@ int arch_update_cpu_topology(void); /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) - * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim() + * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 -- cgit v1.2.3 From e5146b12e2d02af04608301c958d95b2fc47a0f9 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:47 -0700 Subject: mm, vmscan: add classzone information to tracepoints This is convenient when tracking down why the skip count is high because it'll show what classzone kswapd woke up at and what zones are being isolated. Link: http://lkml.kernel.org/r/1467970510-21195-29-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 51 ++++++++++++++++++++++++++----------------- 1 file changed, 31 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 897f1aa1ee5f..c88fd0934e7e 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -55,21 +55,23 @@ TRACE_EVENT(mm_vmscan_kswapd_sleep, TRACE_EVENT(mm_vmscan_kswapd_wake, - TP_PROTO(int nid, int order), + TP_PROTO(int nid, int zid, int order), - TP_ARGS(nid, order), + TP_ARGS(nid, zid, order), TP_STRUCT__entry( __field( int, nid ) + __field( int, zid ) __field( int, order ) ), TP_fast_assign( __entry->nid = nid; + __entry->zid = zid; __entry->order = order; ), - TP_printk("nid=%d order=%d", __entry->nid, __entry->order) + TP_printk("nid=%d zid=%d order=%d", __entry->nid, __entry->zid, __entry->order) ); TRACE_EVENT(mm_vmscan_wakeup_kswapd, @@ -98,47 +100,50 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, - TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx), - TP_ARGS(order, may_writepage, gfp_flags), + TP_ARGS(order, may_writepage, gfp_flags, classzone_idx), TP_STRUCT__entry( __field( int, order ) __field( int, may_writepage ) __field( gfp_t, gfp_flags ) + __field( int, classzone_idx ) ), TP_fast_assign( __entry->order = order; __entry->may_writepage = may_writepage; __entry->gfp_flags = gfp_flags; + __entry->classzone_idx = classzone_idx; ), - TP_printk("order=%d may_writepage=%d gfp_flags=%s", + TP_printk("order=%d may_writepage=%d gfp_flags=%s classzone_idx=%d", __entry->order, __entry->may_writepage, - show_gfp_flags(__entry->gfp_flags)) + show_gfp_flags(__entry->gfp_flags), + __entry->classzone_idx) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin, - TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx), - TP_ARGS(order, may_writepage, gfp_flags) + TP_ARGS(order, may_writepage, gfp_flags, classzone_idx) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, - TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx), - TP_ARGS(order, may_writepage, gfp_flags) + TP_ARGS(order, may_writepage, gfp_flags, classzone_idx) ); DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, - TP_PROTO(int order, int may_writepage, gfp_t gfp_flags), + TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx), - TP_ARGS(order, may_writepage, gfp_flags) + TP_ARGS(order, may_writepage, gfp_flags, classzone_idx) ); DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template, @@ -266,16 +271,18 @@ TRACE_EVENT(mm_shrink_slab_end, DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, - TP_PROTO(int order, + TP_PROTO(int classzone_idx, + int order, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file), + TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file), TP_STRUCT__entry( + __field(int, classzone_idx) __field(int, order) __field(unsigned long, nr_requested) __field(unsigned long, nr_scanned) @@ -285,6 +292,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, ), TP_fast_assign( + __entry->classzone_idx = classzone_idx; __entry->order = order; __entry->nr_requested = nr_requested; __entry->nr_scanned = nr_scanned; @@ -293,8 +301,9 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, __entry->file = file; ), - TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d", + TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d", __entry->isolate_mode, + __entry->classzone_idx, __entry->order, __entry->nr_requested, __entry->nr_scanned, @@ -304,27 +313,29 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, - TP_PROTO(int order, + TP_PROTO(int classzone_idx, + int order, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) + TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) ); DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, - TP_PROTO(int order, + TP_PROTO(int classzone_idx, + int order, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) + TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) ); -- cgit v1.2.3 From e6cbd7f2efb433d717af72aa8510a9db6f7a7e05 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:50 -0700 Subject: mm, page_alloc: remove fair zone allocation policy The fair zone allocation policy interleaves allocation requests between zones to avoid an age inversion problem whereby new pages are reclaimed to balance a zone. Reclaim is now node-based so this should no longer be an issue and the fair zone allocation policy is not free. This patch removes it. Link: http://lkml.kernel.org/r/1467970510-21195-30-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e19c081c794e..bd33e6f1bed0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -110,7 +110,6 @@ struct zone_padding { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, - NR_ALLOC_BATCH, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, NR_ZONE_LRU_FILE, @@ -516,10 +515,6 @@ struct zone { atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; -enum zone_flags { - ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ -}; - enum pgdat_flags { PGDAT_CONGESTED, /* pgdat has many dirty pages backed by * a congested BDI -- cgit v1.2.3 From 16709d1de1954475356a65848f80a01581b4903c Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:56 -0700 Subject: mm: vmstat: replace __count_zone_vm_events with a zone id equivalent This is partially a preparation patch for more vmstat work but it also has the slight advantage that __count_zid_vm_events is cheaper to calculate than __count_zone_vm_events(). Link: http://lkml.kernel.org/r/1467970510-21195-32-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 6b7975cd98aa..613771909b6e 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -101,9 +101,8 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_vmacache_event(x) do {} while (0) #endif -#define __count_zone_vm_events(item, zone, delta) \ - __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ - zone_idx(zone), delta) +#define __count_zid_vm_events(item, zid, delta) \ + __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. -- cgit v1.2.3 From 7cc30fcfd2a894589d832a192cac3dc5cd302bb8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:46:59 -0700 Subject: mm: vmstat: account per-zone stalls and pages skipped during reclaim The vmstat allocstall was fairly useful in the general sense but node-based LRUs change that. It's important to know if a stall was for an address-limited allocation request as this will require skipping pages from other zones. This patch adds pgstall_* counters to replace allocstall. The sum of the counters will equal the old allocstall so it can be trivially recalculated. A high number of address-limited allocation requests may result in a lot of useless LRU scanning for suitable pages. As address-limited allocations require pages to be skipped, it's important to know how much useless LRU scanning took place so this patch adds pgskip* counters. This yields the following model 1. The number of address-space limited stalls can be accounted for (pgstall) 2. The amount of useless work required to reclaim the data is accounted (pgskip) 3. The total number of scans is available from pgscan_kswapd and pgscan_direct so from that the ratio of useful to useless scans can be calculated. [mgorman@techsingularity.net: s/pgstall/allocstall/] Link: http://lkml.kernel.org/r/1468404004-5085-3-git-send-email-mgorman@techsingularity.netLink: http://lkml.kernel.org/r/1467970510-21195-33-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Hillf Danton Acked-by: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 1798ff542517..4d6ec58a8d45 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -23,6 +23,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), + FOR_ALL_ZONES(ALLOCSTALL), + FOR_ALL_ZONES(PGSCAN_SKIP), PGFREE, PGACTIVATE, PGDEACTIVATE, PGFAULT, PGMAJFAULT, PGLAZYFREED, @@ -37,7 +39,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, - PAGEOUTRUN, ALLOCSTALL, PGROTATED, + PAGEOUTRUN, PGROTATED, DROP_PAGECACHE, DROP_SLAB, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, -- cgit v1.2.3 From bca6759258dbef378bcf5b872177bcd2259ceb68 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:47:05 -0700 Subject: mm, vmstat: remove zone and node double accounting by approximating retries The number of LRU pages, dirty pages and writeback pages must be accounted for on both zones and nodes because of the reclaim retry logic, compaction retry logic and highmem calculations all depending on per-zone stats. Many lowmem allocations are immune from OOM kill due to a check in __alloc_pages_may_oom for (ac->high_zoneidx < ZONE_NORMAL) since commit 03668b3ceb0c ("oom: avoid oom killer for lowmem allocations"). The exception is costly high-order allocations or allocations that cannot fail. If the __alloc_pages_may_oom avoids OOM-kill for low-order lowmem allocations then it would fall through to __alloc_pages_direct_compact. This patch will blindly retry reclaim for zone-constrained allocations in should_reclaim_retry up to MAX_RECLAIM_RETRIES. This is not ideal but without per-zone stats there are not many alternatives. The impact it that zone-constrained allocations may delay before considering the OOM killer. As there is no guarantee enough memory can ever be freed to satisfy compaction, this patch avoids retrying compaction for zone-contrained allocations. In combination, that means that the per-node stats can be used when deciding whether to continue reclaim using a rough approximation. While it is possible this will make the wrong decision on occasion, it will not infinite loop as the number of reclaim attempts is capped by MAX_RECLAIM_RETRIES. The final step is calculating the number of dirtyable highmem pages. As those calculations only care about the global count of file pages in highmem. This patch uses a global counter used instead of per-zone stats as it is sufficient. In combination, this allows the per-zone LRU and dirty state counters to be removed. [mgorman@techsingularity.net: fix acct_highmem_file_pages()] Link: http://lkml.kernel.org/r/1468853426-12858-4-git-send-email-mgorman@techsingularity.netLink: http://lkml.kernel.org/r/1467970510-21195-35-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Suggested by: Michal Hocko Acked-by: Hillf Danton Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 20 +++++++++++++++++--- include/linux/mmzone.h | 4 ---- include/linux/swap.h | 1 - 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 9aadcc781857..dd22b08c47be 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -4,6 +4,22 @@ #include #include +#ifdef CONFIG_HIGHMEM +extern atomic_t highmem_file_pages; + +static inline void acct_highmem_file_pages(int zid, enum lru_list lru, + int nr_pages) +{ + if (is_highmem_idx(zid) && is_file_lru(lru)) + atomic_add(nr_pages, &highmem_file_pages); +} +#else +static inline void acct_highmem_file_pages(int zid, enum lru_list lru, + int nr_pages) +{ +} +#endif + /** * page_is_file_cache - should the page be on a file LRU or anon LRU? * @page: the page to test @@ -29,9 +45,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, struct pglist_data *pgdat = lruvec_pgdat(lruvec); __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); - __mod_zone_page_state(&pgdat->node_zones[zid], - NR_ZONE_LRU_BASE + !!is_file_lru(lru), - nr_pages); + acct_highmem_file_pages(zid, lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bd33e6f1bed0..a3b7f45aac56 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -110,10 +110,6 @@ struct zone_padding { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, - NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ - NR_ZONE_LRU_ANON = NR_ZONE_LRU_BASE, - NR_ZONE_LRU_FILE, - NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, diff --git a/include/linux/swap.h b/include/linux/swap.h index b17cc4830fa6..cc753c639e3d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,7 +307,6 @@ extern void lru_cache_add_active_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ -extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -- cgit v1.2.3 From 7ee36a14f06cc937f6b2c2932c2e48f590970581 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:47:17 -0700 Subject: mm, vmscan: Update all zone LRU sizes before updating memcg Minchan Kim reported setting the following warning on a 32-bit system although it can affect 64-bit systems. WARNING: CPU: 4 PID: 1322 at mm/memcontrol.c:998 mem_cgroup_update_lru_size+0x103/0x110 mem_cgroup_update_lru_size(f44b4000, 1, -7): zid 1 lru_size 1 but empty Modules linked in: CPU: 4 PID: 1322 Comm: cp Not tainted 4.7.0-rc4-mm1+ #143 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x76/0xaf __warn+0xea/0x110 ? mem_cgroup_update_lru_size+0x103/0x110 warn_slowpath_fmt+0x3b/0x40 mem_cgroup_update_lru_size+0x103/0x110 isolate_lru_pages.isra.61+0x2e2/0x360 shrink_active_list+0xac/0x2a0 ? __delay+0xe/0x10 shrink_node_memcg+0x53c/0x7a0 shrink_node+0xab/0x2a0 do_try_to_free_pages+0xc6/0x390 try_to_free_pages+0x245/0x590 LRU list contents and counts are updated separately. Counts are updated before pages are added to the LRU and updated after pages are removed. The warning above is from a check in mem_cgroup_update_lru_size that ensures that list sizes of zero are empty. The problem is that node-lru needs to account for highmem pages if CONFIG_HIGHMEM is set. One impact of the implementation is that the sizes are updated in multiple passes when pages from multiple zones were isolated. This happens whether HIGHMEM is set or not. When multiple zones are isolated, it's possible for a debugging check in memcg to be tripped. This patch forces all the zone counts to be updated before the memcg function is called. Link: http://lkml.kernel.org/r/1468588165-12461-6-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Tested-by: Minchan Kim Reported-by: Minchan Kim Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- include/linux/mm_inline.h | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b759827b2f1e..5147e650287a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -430,7 +430,7 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg) int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, - enum zone_type zid, int nr_pages); + int nr_pages); unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index dd22b08c47be..bcc4ed07fa90 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -52,10 +52,9 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, int nr_pages) { -#ifdef CONFIG_MEMCG - mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); -#else __update_lru_size(lruvec, lru, zid, nr_pages); +#ifdef CONFIG_MEMCG + mem_cgroup_update_lru_size(lruvec, lru, nr_pages); #endif } -- cgit v1.2.3 From 71c799f4982d340fff86e751898841322f07f235 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Jul 2016 15:47:26 -0700 Subject: mm: add per-zone lru list stat When I did stress test with hackbench, I got OOM message frequently which didn't ever happen in zone-lru. gfp_mask=0x26004c0(GFP_KERNEL|__GFP_REPEAT|__GFP_NOTRACK), order=0 .. .. __alloc_pages_nodemask+0xe52/0xe60 ? new_slab+0x39c/0x3b0 new_slab+0x39c/0x3b0 ___slab_alloc.constprop.87+0x6da/0x840 ? __alloc_skb+0x3c/0x260 ? _raw_spin_unlock_irq+0x27/0x60 ? trace_hardirqs_on_caller+0xec/0x1b0 ? finish_task_switch+0xa6/0x220 ? poll_select_copy_remaining+0x140/0x140 __slab_alloc.isra.81.constprop.86+0x40/0x6d ? __alloc_skb+0x3c/0x260 kmem_cache_alloc+0x22c/0x260 ? __alloc_skb+0x3c/0x260 __alloc_skb+0x3c/0x260 alloc_skb_with_frags+0x4e/0x1a0 sock_alloc_send_pskb+0x16a/0x1b0 ? wait_for_unix_gc+0x31/0x90 ? alloc_set_pte+0x2ad/0x310 unix_stream_sendmsg+0x28d/0x340 sock_sendmsg+0x2d/0x40 sock_write_iter+0x6c/0xc0 __vfs_write+0xc0/0x120 vfs_write+0x9b/0x1a0 ? __might_fault+0x49/0xa0 SyS_write+0x44/0x90 do_fast_syscall_32+0xa6/0x1e0 sysenter_past_esp+0x45/0x74 Mem-Info: active_anon:104698 inactive_anon:105791 isolated_anon:192 active_file:433 inactive_file:283 isolated_file:22 unevictable:0 dirty:0 writeback:296 unstable:0 slab_reclaimable:6389 slab_unreclaimable:78927 mapped:474 shmem:0 pagetables:101426 bounce:0 free:10518 free_pcp:334 free_cma:0 Node 0 active_anon:418792kB inactive_anon:423164kB active_file:1732kB inactive_file:1132kB unevictable:0kB isolated(anon):768kB isolated(file):88kB mapped:1896kB dirty:0kB writeback:1184kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:1478632 all_unreclaimable? yes DMA free:3304kB min:68kB low:84kB high:100kB present:15992kB managed:15916kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:4088kB kernel_stack:0kB pagetables:2480kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB lowmem_reserve[]: 0 809 1965 1965 Normal free:3436kB min:3604kB low:4504kB high:5404kB present:897016kB managed:858460kB mlocked:0kB slab_reclaimable:25556kB slab_unreclaimable:311712kB kernel_stack:164608kB pagetables:30844kB bounce:0kB free_pcp:620kB local_pcp:104kB free_cma:0kB lowmem_reserve[]: 0 0 9247 9247 HighMem free:33808kB min:512kB low:1796kB high:3080kB present:1183736kB managed:1183736kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:372252kB bounce:0kB free_pcp:428kB local_pcp:72kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 DMA: 2*4kB (UM) 2*8kB (UM) 0*16kB 1*32kB (U) 1*64kB (U) 2*128kB (UM) 1*256kB (U) 1*512kB (M) 0*1024kB 1*2048kB (U) 0*4096kB = 3192kB Normal: 33*4kB (MH) 79*8kB (ME) 11*16kB (M) 4*32kB (M) 2*64kB (ME) 2*128kB (EH) 7*256kB (EH) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 3244kB HighMem: 2590*4kB (UM) 1568*8kB (UM) 491*16kB (UM) 60*32kB (UM) 6*64kB (M) 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 33064kB Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB 25121 total pagecache pages 24160 pages in swap cache Swap cache stats: add 86371, delete 62211, find 42865/60187 Free swap = 4015560kB Total swap = 4192252kB 524186 pages RAM 295934 pages HighMem/MovableOnly 9658 pages reserved 0 pages cma reserved The order-0 allocation for normal zone failed while there are a lot of reclaimable memory(i.e., anonymous memory with free swap). I wanted to analyze the problem but it was hard because we removed per-zone lru stat so I couldn't know how many of anonymous memory there are in normal/dma zone. When we investigate OOM problem, reclaimable memory count is crucial stat to find a problem. Without it, it's hard to parse the OOM message so I believe we should keep it. With per-zone lru stat, gfp_mask=0x26004c0(GFP_KERNEL|__GFP_REPEAT|__GFP_NOTRACK), order=0 Mem-Info: active_anon:101103 inactive_anon:102219 isolated_anon:0 active_file:503 inactive_file:544 isolated_file:0 unevictable:0 dirty:0 writeback:34 unstable:0 slab_reclaimable:6298 slab_unreclaimable:74669 mapped:863 shmem:0 pagetables:100998 bounce:0 free:23573 free_pcp:1861 free_cma:0 Node 0 active_anon:404412kB inactive_anon:409040kB active_file:2012kB inactive_file:2176kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:3452kB dirty:0kB writeback:136kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:1320845 all_unreclaimable? yes DMA free:3296kB min:68kB low:84kB high:100kB active_anon:5540kB inactive_anon:0kB active_file:0kB inactive_file:0kB present:15992kB managed:15916kB mlocked:0kB slab_reclaimable:248kB slab_unreclaimable:2628kB kernel_stack:792kB pagetables:2316kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB lowmem_reserve[]: 0 809 1965 1965 Normal free:3600kB min:3604kB low:4504kB high:5404kB active_anon:86304kB inactive_anon:0kB active_file:160kB inactive_file:376kB present:897016kB managed:858524kB mlocked:0kB slab_reclaimable:24944kB slab_unreclaimable:296048kB kernel_stack:163832kB pagetables:35892kB bounce:0kB free_pcp:3076kB local_pcp:656kB free_cma:0kB lowmem_reserve[]: 0 0 9247 9247 HighMem free:86156kB min:512kB low:1796kB high:3080kB active_anon:312852kB inactive_anon:410024kB active_file:1924kB inactive_file:2012kB present:1183736kB managed:1183736kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:365784kB bounce:0kB free_pcp:3868kB local_pcp:720kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 DMA: 8*4kB (UM) 8*8kB (UM) 4*16kB (M) 2*32kB (UM) 2*64kB (UM) 1*128kB (M) 3*256kB (UME) 2*512kB (UE) 1*1024kB (E) 0*2048kB 0*4096kB = 3296kB Normal: 240*4kB (UME) 160*8kB (UME) 23*16kB (ME) 3*32kB (UE) 3*64kB (UME) 2*128kB (ME) 1*256kB (U) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 3408kB HighMem: 10942*4kB (UM) 3102*8kB (UM) 866*16kB (UM) 76*32kB (UM) 11*64kB (UM) 4*128kB (UM) 1*256kB (M) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 86344kB Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB 54409 total pagecache pages 53215 pages in swap cache Swap cache stats: add 300982, delete 247765, find 157978/226539 Free swap = 3803244kB Total swap = 4192252kB 524186 pages RAM 295934 pages HighMem/MovableOnly 9642 pages reserved 0 pages cma reserved With that, we can see normal zone has a 86M reclaimable memory so we can know something goes wrong(I will fix the problem in next patch) in reclaim. [mgorman@techsingularity.net: rename zone LRU stats in /proc/vmstat] Link: http://lkml.kernel.org/r/20160725072300.GK10438@techsingularity.net Link: http://lkml.kernel.org/r/1469110261-7365-2-git-send-email-mgorman@techsingularity.net Signed-off-by: Minchan Kim Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 2 ++ include/linux/mmzone.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index bcc4ed07fa90..9cc130f5feb2 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -45,6 +45,8 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, struct pglist_data *pgdat = lruvec_pgdat(lruvec); __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); + __mod_zone_page_state(&pgdat->node_zones[zid], + NR_ZONE_LRU_BASE + lru, nr_pages); acct_highmem_file_pages(zid, lru, nr_pages); } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a3b7f45aac56..1a813ad335f4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -110,6 +110,12 @@ struct zone_padding { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, + NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ + NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, + NR_ZONE_ACTIVE_ANON, + NR_ZONE_INACTIVE_FILE, + NR_ZONE_ACTIVE_FILE, + NR_ZONE_UNEVICTABLE, NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, -- cgit v1.2.3 From bb4cc2bea6df7854d629bff114ca03237cc718d6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:47:29 -0700 Subject: mm, vmscan: remove highmem_file_pages With the reintroduction of per-zone LRU stats, highmem_file_pages is redundant so remove it. [mgorman@techsingularity.net: wrong stat is being accumulated in highmem_dirtyable_memory] Link: http://lkml.kernel.org/r/20160725092324.GM10438@techsingularity.netLink: http://lkml.kernel.org/r/1469110261-7365-3-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Cc: Minchan Kim Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_inline.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 9cc130f5feb2..71613e8a720f 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -4,22 +4,6 @@ #include #include -#ifdef CONFIG_HIGHMEM -extern atomic_t highmem_file_pages; - -static inline void acct_highmem_file_pages(int zid, enum lru_list lru, - int nr_pages) -{ - if (is_highmem_idx(zid) && is_file_lru(lru)) - atomic_add(nr_pages, &highmem_file_pages); -} -#else -static inline void acct_highmem_file_pages(int zid, enum lru_list lru, - int nr_pages) -{ -} -#endif - /** * page_is_file_cache - should the page be on a file LRU or anon LRU? * @page: the page to test @@ -47,7 +31,6 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec, __mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); - acct_highmem_file_pages(zid, lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, -- cgit v1.2.3 From 5a1c84b404a7176b8b36e2a0041b6f0adb3151a3 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:47:31 -0700 Subject: mm: remove reclaim and compaction retry approximations If per-zone LRU accounting is available then there is no point approximating whether reclaim and compaction should retry based on pgdat statistics. This is effectively a revert of "mm, vmstat: remove zone and node double accounting by approximating retries" with the difference that inactive/active stats are still available. This preserves the history of why the approximation was retried and why it had to be reverted to handle OOM kills on 32-bit systems. Link: http://lkml.kernel.org/r/1469110261-7365-4-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Minchan Kim Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/swap.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1a813ad335f4..ca0fbc483441 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -116,6 +116,7 @@ enum zone_stat_item { NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, + NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, diff --git a/include/linux/swap.h b/include/linux/swap.h index cc753c639e3d..b17cc4830fa6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,6 +307,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page, struct vm_area_struct *vma); /* linux/mm/vmscan.c */ +extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -- cgit v1.2.3 From 319904ad40d413a0e721ed35fcb2374657db6aaa Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 28 Jul 2016 15:48:03 -0700 Subject: mm, THP: clean up return value of madvise_free_huge_pmd The definition of return value of madvise_free_huge_pmd is not clear before. According to the suggestion of Minchan Kim, change the type of return value to bool and return true if we do MADV_FREE successfully on entire pmd page, otherwise, return false. Comments are added too. Link: http://lkml.kernel.org/r/1467135452-16688-2-git-send-email-ying.huang@intel.com Signed-off-by: "Huang, Ying" Acked-by: Minchan Kim Cc: "Kirill A. Shutemov" Cc: Jerome Marchand Cc: Vlastimil Babka Cc: Dan Williams Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Ebru Akagunduz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 92ce91c03cd0..6f14de45b5ce 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -11,7 +11,7 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); -extern int madvise_free_huge_pmd(struct mmu_gather *tlb, +extern bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); extern int zap_huge_pmd(struct mmu_gather *tlb, -- cgit v1.2.3 From 11db04864336f20e19e16b64ade781eeefc3f6d3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 28 Jul 2016 15:48:11 -0700 Subject: mm: cleanup ifdef guards for vmem_altmap Now that ZONE_DEVICE depends on SPARSEMEM_VMEMMAP we can simplify some ifdef guards to just ZONE_DEVICE. Link: http://lkml.kernel.org/r/146687646788.39261.8020536391978771940.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams Reported-by: Vlastimil Babka Cc: Eric Sandeen Cc: Jeff Moyer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index bcaa634139a9..93416196ba64 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,7 +26,7 @@ struct vmem_altmap { unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); -#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE) +#ifdef CONFIG_ZONE_DEVICE struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); #else static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) -- cgit v1.2.3 From d30dd8be06a5ae640766b20ea9ae288832bd12ac Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 28 Jul 2016 15:48:14 -0700 Subject: mm: track NR_KERNEL_STACK in KiB instead of number of stacks Currently, NR_KERNEL_STACK tracks the number of kernel stacks in a zone. This only makes sense if each kernel stack exists entirely in one zone, and allowing vmapped stacks could break this assumption. Since frv has THREAD_SIZE < PAGE_SIZE, we need to track kernel stack allocations in a unit that divides both THREAD_SIZE and PAGE_SIZE on all architectures. Keep it simple and use KiB. Link: http://lkml.kernel.org/r/083c71e642c5fa5f1b6898902e1b2db7b48940d4.1468523549.git.luto@kernel.org Signed-off-by: Andy Lutomirski Cc: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Reviewed-by: Josh Poimboeuf Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ca0fbc483441..f2e4e90621ec 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -121,7 +121,7 @@ enum zone_stat_item { NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ - NR_KERNEL_STACK, + NR_KERNEL_STACK_KB, /* measured in KiB */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) -- cgit v1.2.3 From efdc94907977d2db84b4b00cb9bd98ca011f6819 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 28 Jul 2016 15:48:17 -0700 Subject: mm: fix memcg stack accounting for sub-page stacks We should account for stacks regardless of stack size, and we need to account in sub-page units if THREAD_SIZE < PAGE_SIZE. Change the units to kilobytes and Move it into account_kernel_stack(). Fixes: 12580e4b54ba8 ("mm: memcontrol: report kernel stack usage in cgroup2 memory.stat") Link: http://lkml.kernel.org/r/9b5314e3ee5eda61b0317ec1563768602c1ef438.1468523549.git.luto@kernel.org Signed-off-by: Andy Lutomirski Cc: Vladimir Davydov Acked-by: Johannes Weiner Cc: Michal Hocko Reviewed-by: Josh Poimboeuf Reviewed-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 5147e650287a..5d8ca6e02e39 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,7 +52,7 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */ MEM_CGROUP_STAT_NSTATS, /* default hierarchy stats */ - MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS, + MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS, MEMCG_SLAB_RECLAIMABLE, MEMCG_SLAB_UNRECLAIMABLE, MEMCG_SOCK, -- cgit v1.2.3 From e558af65be65713ef2e8b2aa637c6263caeed172 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 28 Jul 2016 15:48:20 -0700 Subject: kdb: use task_cpu() instead of task_thread_info()->cpu We'll need this cleanup to make the cpu field in thread_info be optional. Link: http://lkml.kernel.org/r/da298328dc77ea494576c2f20a934218e758a6fa.1468523549.git.luto@kernel.org Signed-off-by: Andy Lutomirski Cc: Jason Wessel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kdb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index a19bcf9e762e..410decacff8f 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -177,7 +177,7 @@ extern int kdb_get_kbd_char(void); static inline int kdb_process_cpu(const struct task_struct *p) { - unsigned int cpu = task_thread_info(p)->cpu; + unsigned int cpu = task_cpu(p); if (cpu > num_possible_cpus()) cpu = 0; return cpu; -- cgit v1.2.3 From a571d4eb55d83ff538d98870fa8a8497b24d39bc Mon Sep 17 00:00:00 2001 From: Dennis Chen Date: Thu, 28 Jul 2016 15:48:26 -0700 Subject: mm/memblock.c: add new infrastructure to address the mem limit issue In some cases, memblock is queried by kernel to determine whether a specified address is RAM or not. For example, the ACPI core needs this information to determine which attributes to use when mapping ACPI regions(acpi_os_ioremap). Use of incorrect memory types can result in faults, data corruption, or other issues. Removing memory with memblock_enforce_memory_limit() throws away this information, and so a kernel booted with 'mem=' may suffer from the issues described above. To avoid this, we need to keep those NOMAP regions instead of removing all above the limit, which preserves the information we need while preventing other use of those regions. This patch adds new infrastructure to retain all NOMAP memblock regions while removing others, to cater for this. Link: http://lkml.kernel.org/r/1468475036-5852-2-git-send-email-dennis.chen@arm.com Signed-off-by: Dennis Chen Acked-by: Steve Capper Cc: Catalin Marinas Cc: Ard Biesheuvel Cc: Pekka Enberg Cc: Mel Gorman Cc: Tang Chen Cc: Tony Luck Cc: Ingo Molnar Cc: Rafael J. Wysocki Cc: Will Deacon Cc: Mark Rutland Cc: Matt Fleming Cc: Kaly Xin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 6c14b6179727..2925da23505d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -332,6 +332,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); +void memblock_mem_limit_remove_map(phys_addr_t limit); bool memblock_is_memory(phys_addr_t addr); int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -- cgit v1.2.3 From c146a2b98eb5898eb0fab15a332257a4102ecae9 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 28 Jul 2016 15:49:04 -0700 Subject: mm, kasan: account for object redzone in SLUB's nearest_obj() When looking up the nearest SLUB object for a given address, correctly calculate its offset if SLAB_RED_ZONE is enabled for that cache. Previously, when KASAN had detected an error on an object from a cache with SLAB_RED_ZONE set, the actual start address of the object was miscalculated, which led to random stacks having been reported. When looking up the nearest SLUB object for a given address, correctly calculate its offset if SLAB_RED_ZONE is enabled for that cache. Fixes: 7ed2f9e663854db ("mm, kasan: SLAB support") Link: http://lkml.kernel.org/r/1468347165-41906-2-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Christoph Lameter Cc: Dmitry Vyukov Cc: Steven Rostedt (Red Hat) Cc: Joonsoo Kim Cc: Kostya Serebryany Cc: Andrey Ryabinin Cc: Kuthonuzo Luruo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 5624c1f3eb0a..cf501cf8e6db 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -119,15 +119,17 @@ static inline void sysfs_slab_remove(struct kmem_cache *s) void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason); +void *fixup_red_left(struct kmem_cache *s, void *p); + static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, void *x) { void *object = x - (x - page_address(page)) % cache->size; void *last_object = page_address(page) + (page->objects - 1) * cache->size; - if (unlikely(object > last_object)) - return last_object; - else - return object; + void *result = (unlikely(object > last_object)) ? last_object : object; + + result = fixup_red_left(cache, result); + return result; } #endif /* _LINUX_SLUB_DEF_H */ -- cgit v1.2.3 From 80a9201a5965f4715d5c09790862e0df84ce0614 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 28 Jul 2016 15:49:07 -0700 Subject: mm, kasan: switch SLUB to stackdepot, enable memory quarantine for SLUB For KASAN builds: - switch SLUB allocator to using stackdepot instead of storing the allocation/deallocation stacks in the objects; - change the freelist hook so that parts of the freelist can be put into the quarantine. [aryabinin@virtuozzo.com: fixes] Link: http://lkml.kernel.org/r/1468601423-28676-1-git-send-email-aryabinin@virtuozzo.com Link: http://lkml.kernel.org/r/1468347165-41906-3-git-send-email-glider@google.com Signed-off-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Christoph Lameter Cc: Dmitry Vyukov Cc: Steven Rostedt (Red Hat) Cc: Joonsoo Kim Cc: Kostya Serebryany Cc: Andrey Ryabinin Cc: Kuthonuzo Luruo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 ++ include/linux/slab_def.h | 3 ++- include/linux/slub_def.h | 4 ++++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ac4b3c46a84d..c9cf374445d8 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -77,6 +77,7 @@ void kasan_free_shadow(const struct vm_struct *vm); size_t ksize(const void *); static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); } +size_t kasan_metadata_size(struct kmem_cache *cache); #else /* CONFIG_KASAN */ @@ -121,6 +122,7 @@ static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } static inline void kasan_free_shadow(const struct vm_struct *vm) {} static inline void kasan_unpoison_slab(const void *ptr) { } +static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } #endif /* CONFIG_KASAN */ diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 339ba027ade9..4ad2c5a26399 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -88,7 +88,8 @@ struct kmem_cache { }; static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, - void *x) { + void *x) +{ void *object = x - (x - page->s_mem) % cache->size; void *last_object = page->s_mem + (cache->num - 1) * cache->size; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index cf501cf8e6db..75f56c2ef2d4 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -104,6 +104,10 @@ struct kmem_cache { unsigned int *random_seq; #endif +#ifdef CONFIG_KASAN + struct kasan_cache kasan_info; +#endif + struct kmem_cache_node *node[MAX_NUMNODES]; }; -- cgit v1.2.3 From 2516035499b9555f6acd373c9f12e44bcb50dbec Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 28 Jul 2016 15:49:25 -0700 Subject: mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocations After the previous patch, we can distinguish costly allocations that should be really lightweight, such as THP page faults, with __GFP_NORETRY. This means we don't need to recognize khugepaged allocations via PF_KTHREAD anymore. We can also change THP page faults in areas where madvise(MADV_HUGEPAGE) was used to try as hard as khugepaged, as the process has indicated that it benefits from THP's and is willing to pay some initial latency costs. We can also make the flags handling less cryptic by distinguishing GFP_TRANSHUGE_LIGHT (no reclaim at all, default mode in page fault) from GFP_TRANSHUGE (only direct reclaim, khugepaged default). Adding __GFP_NORETRY or __GFP_KSWAPD_RECLAIM is done where needed. The patch effectively changes the current GFP_TRANSHUGE users as follows: * get_huge_zero_page() - the zero page lifetime should be relatively long and it's shared by multiple users, so it's worth spending some effort on it. We use GFP_TRANSHUGE, and __GFP_NORETRY is not added. This also restores direct reclaim to this allocation, which was unintentionally removed by commit e4a49efe4e7e ("mm: thp: set THP defrag by default to madvise and add a stall-free defrag option") * alloc_hugepage_khugepaged_gfpmask() - this is khugepaged, so latency is not an issue. So if khugepaged "defrag" is enabled (the default), do reclaim via GFP_TRANSHUGE without __GFP_NORETRY. We can remove the PF_KTHREAD check from page alloc. As a side-effect, khugepaged will now no longer check if the initial compaction was deferred or contended. This is OK, as khugepaged sleep times between collapsion attempts are long enough to prevent noticeable disruption, so we should allow it to spend some effort. * migrate_misplaced_transhuge_page() - already was masking out __GFP_RECLAIM, so just convert to GFP_TRANSHUGE_LIGHT which is equivalent. * alloc_hugepage_direct_gfpmask() - vma's with VM_HUGEPAGE (via madvise) are now allocating without __GFP_NORETRY. Other vma's keep using __GFP_NORETRY if direct reclaim/compaction is at all allowed (by default it's allowed only for madvised vma's). The rest is conversion to GFP_TRANSHUGE(_LIGHT). [mhocko@suse.com: suggested GFP_TRANSHUGE_LIGHT] Link: http://lkml.kernel.org/r/20160721073614.24395-7-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 14 ++++++++------ include/trace/events/mmflags.h | 1 + 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c29e9d347bc6..f8041f9de31e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -237,9 +237,11 @@ struct vm_area_struct; * are expected to be movable via page reclaim or page migration. Typically, * pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE. * - * GFP_TRANSHUGE is used for THP allocations. They are compound allocations - * that will fail quickly if memory is not available and will not wake - * kswapd on failure. + * GFP_TRANSHUGE and GFP_TRANSHUGE_LIGHT are used for THP allocations. They are + * compound allocations that will generally fail quickly if memory is not + * available and will not wake kswapd/kcompactd on failure. The _LIGHT + * version does not attempt reclaim/compaction at all and is by default used + * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) @@ -254,9 +256,9 @@ struct vm_area_struct; #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) -#define GFP_TRANSHUGE ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \ - ~__GFP_RECLAIM) +#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) +#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 43cedbf0c759..5a81ab48a2fb 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -11,6 +11,7 @@ #define __def_gfpflag_names \ {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ + {(unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ {(unsigned long)GFP_USER, "GFP_USER"}, \ -- cgit v1.2.3 From a5508cd83f10f663e05d212cb81f600a3af46e40 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 28 Jul 2016 15:49:28 -0700 Subject: mm, compaction: introduce direct compaction priority In the context of direct compaction, for some types of allocations we would like the compaction to either succeed or definitely fail while trying as hard as possible. Current async/sync_light migration mode is insufficient, as there are heuristics such as caching scanner positions, marking pageblocks as unsuitable or deferring compaction for a zone. At least the final compaction attempt should be able to override these heuristics. To communicate how hard compaction should try, we replace migration mode with a new enum compact_priority and change the relevant function signatures. In compact_zone_order() where struct compact_control is constructed, the priority is mapped to suitable control flags. This patch itself has no functional change, as the current priority levels are mapped back to the same migration modes as before. Expanding them will be done next. Note that !CONFIG_COMPACTION variant of try_to_compact_pages() is removed, as the only caller exists under CONFIG_COMPACTION. Link: http://lkml.kernel.org/r/20160721073614.24395-8-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 22 +++++++++++++--------- include/trace/events/compaction.h | 12 ++++++------ 2 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 1a02dab16646..0980a6ce4436 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -1,6 +1,18 @@ #ifndef _LINUX_COMPACTION_H #define _LINUX_COMPACTION_H +/* + * Determines how hard direct compaction should try to succeed. + * Lower value means higher priority, analogically to reclaim priority. + */ +enum compact_priority { + COMPACT_PRIO_SYNC_LIGHT, + MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, + DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT, + COMPACT_PRIO_ASYNC, + INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC +}; + /* Return values for compact_zone() and try_to_compact_pages() */ /* When adding new states, please adjust include/trace/events/compaction.h */ enum compact_result { @@ -66,7 +78,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, - enum migrate_mode mode, int *contended); + enum compact_priority prio, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, @@ -151,14 +163,6 @@ extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx); #else -static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask, - unsigned int order, int alloc_flags, - const struct alloc_context *ac, - enum migrate_mode mode, int *contended) -{ - return COMPACT_CONTINUE; -} - static inline void compact_pgdat(pg_data_t *pgdat, int order) { } diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 36e2d6fb1360..c2ba402ab256 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -226,26 +226,26 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_PROTO( int order, gfp_t gfp_mask, - enum migrate_mode mode), + int prio), - TP_ARGS(order, gfp_mask, mode), + TP_ARGS(order, gfp_mask, prio), TP_STRUCT__entry( __field(int, order) __field(gfp_t, gfp_mask) - __field(enum migrate_mode, mode) + __field(int, prio) ), TP_fast_assign( __entry->order = order; __entry->gfp_mask = gfp_mask; - __entry->mode = mode; + __entry->prio = prio; ), - TP_printk("order=%d gfp_mask=0x%x mode=%d", + TP_printk("order=%d gfp_mask=0x%x priority=%d", __entry->order, __entry->gfp_mask, - (int)__entry->mode) + __entry->prio) ); DECLARE_EVENT_CLASS(mm_compaction_suitable_template, -- cgit v1.2.3 From c3486f5376696034d0fcbef8ba70c70cfcb26f51 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 28 Jul 2016 15:49:30 -0700 Subject: mm, compaction: simplify contended compaction handling Async compaction detects contention either due to failing trylock on zone->lock or lru_lock, or by need_resched(). Since 1f9efdef4f3f ("mm, compaction: khugepaged should not give up due to need_resched()") the code got quite complicated to distinguish these two up to the __alloc_pages_slowpath() level, so different decisions could be taken for khugepaged allocations. After the recent changes, khugepaged allocations don't check for contended compaction anymore, so we again don't need to distinguish lock and sched contention, and simplify the current convoluted code a lot. However, I believe it's also possible to simplify even more and completely remove the check for contended compaction after the initial async compaction for costly orders, which was originally aimed at THP page fault allocations. There are several reasons why this can be done now: - with the new defaults, THP page faults no longer do reclaim/compaction at all, unless the system admin has overridden the default, or application has indicated via madvise that it can benefit from THP's. In both cases, it means that the potential extra latency is expected and worth the benefits. - even if reclaim/compaction proceeds after this patch where it previously wouldn't, the second compaction attempt is still async and will detect the contention and back off, if the contention persists - there are still heuristics like deferred compaction and pageblock skip bits in place that prevent excessive THP page fault latencies Link: http://lkml.kernel.org/r/20160721073614.24395-9-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 0980a6ce4436..d4e106b5dc27 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -55,14 +55,6 @@ enum compact_result { COMPACT_PARTIAL, }; -/* Used to signal whether compaction detected need_sched() or lock contention */ -/* No contention detected */ -#define COMPACT_CONTENDED_NONE 0 -/* Either need_sched() was true or fatal signal pending */ -#define COMPACT_CONTENDED_SCHED 1 -/* Zone lock or lru_lock was contended in async compaction */ -#define COMPACT_CONTENDED_LOCK 2 - struct alloc_context; /* in mm/internal.h */ #ifdef CONFIG_COMPACTION @@ -76,9 +68,8 @@ extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, - unsigned int order, - unsigned int alloc_flags, const struct alloc_context *ac, - enum compact_priority prio, int *contended); + unsigned int order, unsigned int alloc_flags, + const struct alloc_context *ac, enum compact_priority prio); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, -- cgit v1.2.3 From 44d1240d006c9cd0249263b5449c8e4752500f6a Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 13 Jun 2016 11:11:26 +0200 Subject: drm: add generic zpos property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit version 8: - move drm_blend.o from drm-y to drm_kms_helper-y to avoid EXPORT_SYMBOL(drm_atomic_helper_normalize_zpos) - remove dead function declarations in drm_crtc.h version 7: - remove useless EXPORT_SYMBOL() - better z-order wording in Documentation version 6: - add zpos in gpu documentation file - merge Ville patch about zpos initial value and API improvement. I have split Ville patch between zpos core and drivers version 5: - remove zpos range check and comeback to 0 to N-1 normalization algorithm version 4: - make sure that normalized zpos value is stay in the defined property range and warn user if not This patch adds support for generic plane's zpos property property with well-defined semantics: - added zpos properties to plane and plane state structures - added helpers for normalizing zpos properties of given set of planes - well defined semantics: planes are sorted by zpos values and then plane id value if zpos equals Normalized zpos values are calculated automatically when generic muttable zpos property has been initialized. Drivers can simply use plane_state->normalized_zpos in their atomic_check and/or plane_update callbacks without any additional calls to DRM core. Signed-off-by: Marek Szyprowski Compare to Marek's original patch zpos property is now specific to each plane and no more to the core. Normalize function take care of the range of per plane defined range before set normalized_zpos. Signed-off-by: Benjamin Gaignard Reviewed-by: Ville Syrjälä Acked-by: Laurent Pinchart Tested-by: Laurent Pinchart Cc: Inki Dae Cc: Daniel Vetter Cc: Ville Syrjala Cc: Joonyoung Shim Cc: Seung-Woo Kim Cc: Andrzej Hajda Cc: Krzysztof Kozlowski Cc: Bartlomiej Zolnierkiewicz Cc: Tobias Jakobi Cc: Gustavo Padovan Cc: vincent.abriou@st.com Cc: fabien.dessenne@st.com Cc: Laurent Pinchart --- include/drm/drm_crtc.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 3edeaf88ebc0..44e070800b6d 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -308,6 +308,7 @@ struct drm_plane_helper_funcs; * @mode_changed: crtc_state->mode or crtc_state->enable has been changed * @active_changed: crtc_state->active has been toggled. * @connectors_changed: connectors to this crtc have been updated + * @zpos_changed: zpos values of planes on this crtc have been updated * @color_mgmt_changed: color management properties have changed (degamma or * gamma LUT or CSC matrix) * @plane_mask: bitmask of (1 << drm_plane_index(plane)) of attached planes @@ -344,6 +345,7 @@ struct drm_crtc_state { bool mode_changed : 1; bool active_changed : 1; bool connectors_changed : 1; + bool zpos_changed : 1; bool color_mgmt_changed : 1; /* attached planes bitmask: @@ -1409,6 +1411,9 @@ struct drm_connector { * @src_w: width of visible portion of plane (in 16.16) * @src_h: height of visible portion of plane (in 16.16) * @rotation: rotation of the plane + * @zpos: priority of the given plane on crtc (optional) + * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1 + * where N is the number of active planes for given crtc * @state: backpointer to global drm_atomic_state */ struct drm_plane_state { @@ -1429,6 +1434,10 @@ struct drm_plane_state { /* Plane rotation */ unsigned int rotation; + /* Plane zpos */ + unsigned int zpos; + unsigned int normalized_zpos; + struct drm_atomic_state *state; }; @@ -1688,6 +1697,7 @@ enum drm_plane_type { * @properties: property tracking for this plane * @type: type of plane (overlay, primary, cursor) * @state: current atomic state for this plane + * @zpos_property: zpos property for this plane * @helper_private: mid-layer private data */ struct drm_plane { @@ -1732,6 +1742,8 @@ struct drm_plane { const struct drm_plane_helper_funcs *helper_private; struct drm_plane_state *state; + + struct drm_property *zpos_property; }; /** @@ -2958,6 +2970,14 @@ extern void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc, uint degamma_lut_size, bool has_ctm, uint gamma_lut_size); + +int drm_plane_create_zpos_property(struct drm_plane *plane, + unsigned int zpos, + unsigned int min, unsigned int max); + +int drm_plane_create_zpos_immutable_property(struct drm_plane *plane, + unsigned int zpos); + /* Helpers */ struct drm_mode_object *drm_mode_object_find(struct drm_device *dev, uint32_t id, uint32_t type); -- cgit v1.2.3 From d72d9e2a5d7ec04a1f92925c5ac633d8031fa7fc Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 29 Jul 2016 14:10:57 +0200 Subject: mm: export filemap_check_errors() to modules Can be used by fuse, btrfs and f2fs to replace opencoded variants. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..6f2536a3a916 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2507,6 +2507,7 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); +extern int filemap_check_errors(struct address_space *mapping); extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); -- cgit v1.2.3 From 20d00ee829428ea6aab77fa3acca048a6f57d3bc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 29 Jul 2016 12:17:52 -0700 Subject: Revert "vfs: add lookup_hash() helper" This reverts commit 3c9fe8cdff1b889a059a30d22f130372f2b3885f. As Miklos points out in commit c1b2cc1a765a, the "lookup_hash()" helper is now unused, and in fact, with the hash salting changes, since the hash of a dentry name now depends on the directory dentry it is in, the helper function isn't even really likely to be useful. So rather than keep it around in case somebody else might end up finding a use for it, let's just remove the helper and not trick people into thinking it might be a useful thing. For example, I had obviously completely missed how the helper didn't follow the normal dentry hashing patterns, and how the hash salting patch broke overlayfs. Things would quietly build and look sane, but not work. Suggested-by: Miklos Szeredi Signed-off-by: Linus Torvalds --- include/linux/namei.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/namei.h b/include/linux/namei.h index d3d0398f2a1b..f29abda31e6d 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -81,8 +81,6 @@ extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); -struct qstr; -extern struct dentry *lookup_hash(const struct qstr *, struct dentry *); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From 6fa67e707559303e086303aeecc9e8b91ef497d5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 31 Jul 2016 16:37:25 -0400 Subject: get rid of 'parent' argument of ->d_compare() Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 98044a8d1487..107d9abe7166 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -130,7 +130,7 @@ struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); - int (*d_compare)(const struct dentry *, const struct dentry *, + int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); -- cgit v1.2.3 From 0dc696bcf2e86f48a23fb95ca2f40c8708241e7e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 28 Jul 2016 10:57:30 +0800 Subject: elf: Add powerpc specific core note sections This patch adds twelve ELF core note sections for powerpc architecture for various registers and register sets which need to be accessed from ptrace interface and then gdb. These additions include special purpose registers like TAR, PPR, DSCR, TM running and checkpointed state for various register sets, EBB related register set, performance monitor register set etc. Addition of these new ELF core note sections extends the existing ELF ABI on powerpc arch without affecting it in any manner. Signed-off-by: Anshuman Khandual Signed-off-by: Simon Guo Signed-off-by: Michael Ellerman --- include/uapi/linux/elf.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index cb4a72f888d5..1be3c5f6183b 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -381,6 +381,19 @@ typedef struct elf64_shdr { #define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ #define NT_PPC_SPE 0x101 /* PowerPC SPE/EVR registers */ #define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ +#define NT_PPC_TAR 0x103 /* Target Address Register */ +#define NT_PPC_PPR 0x104 /* Program Priority Register */ +#define NT_PPC_DSCR 0x105 /* Data Stream Control Register */ +#define NT_PPC_EBB 0x106 /* Event Based Branch Registers */ +#define NT_PPC_PMU 0x107 /* Performance Monitor Registers */ +#define NT_PPC_TM_CGPR 0x108 /* TM checkpointed GPR Registers */ +#define NT_PPC_TM_CFPR 0x109 /* TM checkpointed FPR Registers */ +#define NT_PPC_TM_CVMX 0x10a /* TM checkpointed VMX Registers */ +#define NT_PPC_TM_CVSX 0x10b /* TM checkpointed VSX Registers */ +#define NT_PPC_TM_SPR 0x10c /* TM Special Purpose Registers */ +#define NT_PPC_TM_CTAR 0x10d /* TM checkpointed Target Address Register */ +#define NT_PPC_TM_CPPR 0x10e /* TM checkpointed Program Priority Register */ +#define NT_PPC_TM_CDSCR 0x10f /* TM checkpointed Data Stream Control Register */ #define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ #define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ #define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ -- cgit v1.2.3 From 23528bb21ee2c9b27f3feddd77a2a3351a8df148 Mon Sep 17 00:00:00 2001 From: Sam Bobroff Date: Wed, 20 Jul 2016 13:41:36 +1000 Subject: KVM: PPC: Introduce KVM_CAP_PPC_HTM Introduce a new KVM capability, KVM_CAP_PPC_HTM, that can be queried to determine if a PowerPC KVM guest should use HTM (Hardware Transactional Memory). This will be used by QEMU to populate the pa-features bits in the guest's device tree. Signed-off-by: Sam Bobroff Reviewed-by: David Gibson Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 8f2756c263d4..e98bb4cce639 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -869,6 +869,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_X2APIC_API 129 #define KVM_CAP_S390_USER_INSTR0 130 #define KVM_CAP_MSI_DEVID 131 +#define KVM_CAP_PPC_HTM 132 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 1a937693993ff10d7e80cca6ddd55f3000aa6376 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 18 Apr 2016 12:58:14 +0300 Subject: virtio: new feature to detect IOMMU device quirk The interaction between virtio and IOMMUs is messy. On most systems with virtio, physical addresses match bus addresses, and it doesn't particularly matter which one we use to program the device. On some systems, including Xen and any system with a physical device that speaks virtio behind a physical IOMMU, we must program the IOMMU for virtio DMA to work at all. On other systems, including SPARC and PPC64, virtio-pci devices are enumerated as though they are behind an IOMMU, but the virtio host ignores the IOMMU, so we must either pretend that the IOMMU isn't there or somehow map everything as the identity. Add a feature bit to detect that quirk: VIRTIO_F_IOMMU_PLATFORM. Any device with this feature bit set to 0 needs a quirk and has to be passed physical addresses (as opposed to bus addresses) even though the device is behind an IOMMU. Note: it has to be a per-device quirk because for example, there could be a mix of passed-through and virtual virtio devices. As another example, some devices could be implemented by an out of process hypervisor backend (in case of qemu vhost, or vhost-user) and so support for an IOMMU needs to be coded up separately. It would be cleanest to handle this in IOMMU core code, but that needs per-device DMA ops. While we are waiting for that to be implemented, use a work-around in virtio core. Note: a "noiommu" feature is a quirk - add a wrapper to make that clear. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 13 +++++++++++++ include/uapi/linux/virtio_config.h | 10 +++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 6e6cb0c9d7cb..26c155bb639b 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -149,6 +149,19 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, return __virtio_test_bit(vdev, fbit); } +/** + * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * @vdev: the device + */ +static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +{ + /* + * Note the reverse polarity of the quirk feature (compared to most + * other features), this is for compatibility with legacy systems. + */ + return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + static inline struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *c, const char *n) diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 4cb65bbfa654..308e2096291f 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -49,7 +49,7 @@ * transport being used (eg. virtio_ring), the rest are per-device feature * bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 33 +#define VIRTIO_TRANSPORT_F_END 34 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -63,4 +63,12 @@ /* v1.0 compliant. */ #define VIRTIO_F_VERSION_1 32 +/* + * If clear - device has the IOMMU bypass quirk feature. + * If set - use platform tools to detect the IOMMU. + * + * Note the reverse polarity (compared to most other features), + * this is for compatibility with legacy systems. + */ +#define VIRTIO_F_IOMMU_PLATFORM 33 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */ -- cgit v1.2.3 From df7e88f6cad8cc4e02c9275018a572fab59562c0 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sat, 30 Jul 2016 20:00:45 +0800 Subject: sctp: change to use TCP_CLOSE_WAIT as SCTP_SS_CLOSING Prior to this patch, sctp defined TCP_CLOSING as SCTP_SS_CLOSING. TCP_CLOSING is such a special sk state in TCP that inet common codes even exclude it. For instance, inet_accept thinks the accept sk's state never be TCP_CLOSING, or it will give a WARN_ON. TCP works well with that while SCTP may trigger the call trace, as CLOSING state in SCTP has different meaning from TCP. This fix is to change to use TCP_CLOSE_WAIT as SCTP_SS_CLOSING, instead of TCP_CLOSING. Some side-effects could be expected, regardless of not being used before. inet_accept will accept it now. I did all the func_tests in lksctp-tools and ran sctp codnomicon fuzzer tests against this patch, no regression or failure found. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/constants.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 8c337cd0e1e4..5b847e49f7e9 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -214,7 +214,7 @@ typedef enum { SCTP_SS_LISTENING = TCP_LISTEN, SCTP_SS_ESTABLISHING = TCP_SYN_SENT, SCTP_SS_ESTABLISHED = TCP_ESTABLISHED, - SCTP_SS_CLOSING = TCP_CLOSING, + SCTP_SS_CLOSING = TCP_CLOSE_WAIT, } sctp_sock_state_t; /* These functions map various type to printable names. */ -- cgit v1.2.3 From 0b01aeb3d2fbf16787f0c9629f4ca52ae792f732 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 28 Jul 2016 15:36:30 +0100 Subject: VSOCK: transport-specific vsock_transport functions struct vsock_transport contains function pointers called by AF_VSOCK core code. The transport may want its own transport-specific function pointers and they can be added after struct vsock_transport. Allow the transport to fetch vsock_transport. It can downcast it to access transport-specific function pointers. The virtio transport will use this. Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/net/af_vsock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index e9eb2d6791b3..23f55259b60d 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -165,6 +165,9 @@ static inline int vsock_core_init(const struct vsock_transport *t) } void vsock_core_exit(void); +/* The transport may downcast this to access transport-specific functions */ +const struct vsock_transport *vsock_core_get_transport(void); + /**** UTILS ****/ void vsock_release_pending(struct sock *pending); -- cgit v1.2.3 From 6773b7dc39f165bd9d824b50ac52cbb3f87d53c8 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 28 Jul 2016 15:36:31 +0100 Subject: VSOCK: defer sock removal to transports The virtio transport will implement graceful shutdown and the related SO_LINGER socket option. This requires orphaning the sock but keeping it in the table of connections after .release(). This patch adds the vsock_remove_sock() function and leaves it up to the transport when to remove the sock. Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/net/af_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 23f55259b60d..3af0b224f754 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -180,6 +180,7 @@ void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); +void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); #endif /* __AF_VSOCK_H__ */ -- cgit v1.2.3 From 06a8fc78367d070720af960dcecec917d3ae5f3b Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 28 Jul 2016 15:36:32 +0100 Subject: VSOCK: Introduce virtio_vsock_common.ko This module contains the common code and header files for the following virtio_transporto and vhost_vsock kernel modules. Signed-off-by: Asias He Signed-off-by: Claudio Imbrenda Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_vsock.h | 154 +++++++++++++++++++++ include/net/af_vsock.h | 2 + .../trace/events/vsock_virtio_transport_common.h | 144 +++++++++++++++++++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_vsock.h | 94 +++++++++++++ 6 files changed, 396 insertions(+) create mode 100644 include/linux/virtio_vsock.h create mode 100644 include/trace/events/vsock_virtio_transport_common.h create mode 100644 include/uapi/linux/virtio_vsock.h (limited to 'include') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h new file mode 100644 index 000000000000..9638bfeb0d1f --- /dev/null +++ b/include/linux/virtio_vsock.h @@ -0,0 +1,154 @@ +#ifndef _LINUX_VIRTIO_VSOCK_H +#define _LINUX_VIRTIO_VSOCK_H + +#include +#include +#include +#include + +#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 +#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) +#define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL +#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) + +enum { + VSOCK_VQ_RX = 0, /* for host to guest data */ + VSOCK_VQ_TX = 1, /* for guest to host data */ + VSOCK_VQ_EVENT = 2, + VSOCK_VQ_MAX = 3, +}; + +/* Per-socket state (accessed via vsk->trans) */ +struct virtio_vsock_sock { + struct vsock_sock *vsk; + + /* Protected by lock_sock(sk_vsock(trans->vsk)) */ + u32 buf_size; + u32 buf_size_min; + u32 buf_size_max; + + spinlock_t tx_lock; + spinlock_t rx_lock; + + /* Protected by tx_lock */ + u32 tx_cnt; + u32 buf_alloc; + u32 peer_fwd_cnt; + u32 peer_buf_alloc; + + /* Protected by rx_lock */ + u32 fwd_cnt; + u32 rx_bytes; + struct list_head rx_queue; +}; + +struct virtio_vsock_pkt { + struct virtio_vsock_hdr hdr; + struct work_struct work; + struct list_head list; + void *buf; + u32 len; + u32 off; + bool reply; +}; + +struct virtio_vsock_pkt_info { + u32 remote_cid, remote_port; + struct msghdr *msg; + u32 pkt_len; + u16 type; + u16 op; + u32 flags; + bool reply; +}; + +struct virtio_transport { + /* This must be the first field */ + struct vsock_transport transport; + + /* Takes ownership of the packet */ + int (*send_pkt)(struct virtio_vsock_pkt *pkt); +}; + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, + int type); +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk); +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now); +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_available_now); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); +bool virtio_transport_stream_is_active(struct vsock_sock *vsk); +bool virtio_transport_stream_allow(u32 cid, u32 port); +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr); +bool virtio_transport_dgram_allow(u32 cid, u32 port); + +int virtio_transport_connect(struct vsock_sock *vsk); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode); + +void virtio_transport_release(struct vsock_sock *vsk); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t len); + +void virtio_transport_destruct(struct vsock_sock *vsk); + +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); + +#endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3af0b224f754..f2758964ce6f 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -63,6 +63,8 @@ struct vsock_sock { struct list_head accept_queue; bool rejected; struct delayed_work dwork; + struct delayed_work close_work; + bool close_work_scheduled; u32 peer_shutdown; bool sent_request; bool ignore_connecting_rst; diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h new file mode 100644 index 000000000000..b7f1d6278280 --- /dev/null +++ b/include/trace/events/vsock_virtio_transport_common.h @@ -0,0 +1,144 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vsock + +#if !defined(_TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H) || \ + defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H + +#include + +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM); + +#define show_type(val) \ + __print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }) + +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RESPONSE); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RST); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_SHUTDOWN); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RW); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_CREDIT_UPDATE); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_CREDIT_REQUEST); + +#define show_op(val) \ + __print_symbolic(val, \ + { VIRTIO_VSOCK_OP_INVALID, "INVALID" }, \ + { VIRTIO_VSOCK_OP_REQUEST, "REQUEST" }, \ + { VIRTIO_VSOCK_OP_RESPONSE, "RESPONSE" }, \ + { VIRTIO_VSOCK_OP_RST, "RST" }, \ + { VIRTIO_VSOCK_OP_SHUTDOWN, "SHUTDOWN" }, \ + { VIRTIO_VSOCK_OP_RW, "RW" }, \ + { VIRTIO_VSOCK_OP_CREDIT_UPDATE, "CREDIT_UPDATE" }, \ + { VIRTIO_VSOCK_OP_CREDIT_REQUEST, "CREDIT_REQUEST" }) + +TRACE_EVENT(virtio_transport_alloc_pkt, + TP_PROTO( + __u32 src_cid, __u32 src_port, + __u32 dst_cid, __u32 dst_port, + __u32 len, + __u16 type, + __u16 op, + __u32 flags + ), + TP_ARGS( + src_cid, src_port, + dst_cid, dst_port, + len, + type, + op, + flags + ), + TP_STRUCT__entry( + __field(__u32, src_cid) + __field(__u32, src_port) + __field(__u32, dst_cid) + __field(__u32, dst_port) + __field(__u32, len) + __field(__u16, type) + __field(__u16, op) + __field(__u32, flags) + ), + TP_fast_assign( + __entry->src_cid = src_cid; + __entry->src_port = src_port; + __entry->dst_cid = dst_cid; + __entry->dst_port = dst_port; + __entry->len = len; + __entry->type = type; + __entry->op = op; + __entry->flags = flags; + ), + TP_printk("%u:%u -> %u:%u len=%u type=%s op=%s flags=%#x", + __entry->src_cid, __entry->src_port, + __entry->dst_cid, __entry->dst_port, + __entry->len, + show_type(__entry->type), + show_op(__entry->op), + __entry->flags) +); + +TRACE_EVENT(virtio_transport_recv_pkt, + TP_PROTO( + __u32 src_cid, __u32 src_port, + __u32 dst_cid, __u32 dst_port, + __u32 len, + __u16 type, + __u16 op, + __u32 flags, + __u32 buf_alloc, + __u32 fwd_cnt + ), + TP_ARGS( + src_cid, src_port, + dst_cid, dst_port, + len, + type, + op, + flags, + buf_alloc, + fwd_cnt + ), + TP_STRUCT__entry( + __field(__u32, src_cid) + __field(__u32, src_port) + __field(__u32, dst_cid) + __field(__u32, dst_port) + __field(__u32, len) + __field(__u16, type) + __field(__u16, op) + __field(__u32, flags) + __field(__u32, buf_alloc) + __field(__u32, fwd_cnt) + ), + TP_fast_assign( + __entry->src_cid = src_cid; + __entry->src_port = src_port; + __entry->dst_cid = dst_cid; + __entry->dst_port = dst_port; + __entry->len = len; + __entry->type = type; + __entry->op = op; + __entry->flags = flags; + __entry->buf_alloc = buf_alloc; + __entry->fwd_cnt = fwd_cnt; + ), + TP_printk("%u:%u -> %u:%u len=%u type=%s op=%s flags=%#x " + "buf_alloc=%u fwd_cnt=%u", + __entry->src_cid, __entry->src_port, + __entry->dst_cid, __entry->dst_port, + __entry->len, + show_type(__entry->type), + show_op(__entry->op), + __entry->flags, + __entry->buf_alloc, + __entry->fwd_cnt) +); + +#endif /* _TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H */ + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE vsock_virtio_transport_common + +/* This part must be outside protection */ +#include diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index ec10cfef166a..3cf0116d9c2b 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -453,6 +453,7 @@ header-y += virtio_ring.h header-y += virtio_rng.h header-y += virtio_scsi.h header-y += virtio_types.h +header-y += virtio_vsock.h header-y += vm_sockets.h header-y += vt.h header-y += wait.h diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 77925f587b15..3228d582234a 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -41,5 +41,6 @@ #define VIRTIO_ID_CAIF 12 /* Virtio caif */ #define VIRTIO_ID_GPU 16 /* virtio GPU */ #define VIRTIO_ID_INPUT 18 /* virtio input */ +#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h new file mode 100644 index 000000000000..6b011c19b50f --- /dev/null +++ b/include/uapi/linux/virtio_vsock.h @@ -0,0 +1,94 @@ +/* + * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so + * anyone can use the definitions to implement compatible drivers/servers: + * + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * Copyright (C) Red Hat, Inc., 2013-2015 + * Copyright (C) Asias He , 2013 + * Copyright (C) Stefan Hajnoczi , 2015 + */ + +#ifndef _UAPI_LINUX_VIRTIO_VSOCK_H +#define _UAPI_LINUX_VIRTIO_VOSCK_H + +#include +#include +#include + +struct virtio_vsock_config { + __le64 guest_cid; +} __attribute__((packed)); + +enum virtio_vsock_event_id { + VIRTIO_VSOCK_EVENT_TRANSPORT_RESET = 0, +}; + +struct virtio_vsock_event { + __le32 id; +} __attribute__((packed)); + +struct virtio_vsock_hdr { + __le64 src_cid; + __le64 dst_cid; + __le32 src_port; + __le32 dst_port; + __le32 len; + __le16 type; /* enum virtio_vsock_type */ + __le16 op; /* enum virtio_vsock_op */ + __le32 flags; + __le32 buf_alloc; + __le32 fwd_cnt; +} __attribute__((packed)); + +enum virtio_vsock_type { + VIRTIO_VSOCK_TYPE_STREAM = 1, +}; + +enum virtio_vsock_op { + VIRTIO_VSOCK_OP_INVALID = 0, + + /* Connect operations */ + VIRTIO_VSOCK_OP_REQUEST = 1, + VIRTIO_VSOCK_OP_RESPONSE = 2, + VIRTIO_VSOCK_OP_RST = 3, + VIRTIO_VSOCK_OP_SHUTDOWN = 4, + + /* To send payload */ + VIRTIO_VSOCK_OP_RW = 5, + + /* Tell the peer our credit info */ + VIRTIO_VSOCK_OP_CREDIT_UPDATE = 6, + /* Request the peer to send the credit info to us */ + VIRTIO_VSOCK_OP_CREDIT_REQUEST = 7, +}; + +/* VIRTIO_VSOCK_OP_SHUTDOWN flags values */ +enum virtio_vsock_shutdown { + VIRTIO_VSOCK_SHUTDOWN_RCV = 1, + VIRTIO_VSOCK_SHUTDOWN_SEND = 2, +}; + +#endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From 433fc58e6bf2c8bd97e57153ed28e64fd78207b8 Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 28 Jul 2016 15:36:34 +0100 Subject: VSOCK: Introduce vhost_vsock.ko VM sockets vhost transport implementation. This driver runs on the host. Signed-off-by: Asias He Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 61a8777178c6..c4400b267716 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -175,4 +175,9 @@ struct vhost_scsi_target { #define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32) #define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32) +/* VHOST_VSOCK specific defines */ + +#define VHOST_VSOCK_SET_GUEST_CID _IOW(VHOST_VIRTIO, 0x60, __u64) +#define VHOST_VSOCK_SET_RUNNING _IOW(VHOST_VIRTIO, 0x61, int) + #endif -- cgit v1.2.3 From 6b1e6cc7855b09a0a9bfa1d9f30172ba366f161c Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 23 Jun 2016 02:04:32 -0400 Subject: vhost: new device IOTLB API This patch tries to implement an device IOTLB for vhost. This could be used with userspace(qemu) implementation of DMA remapping to emulate an IOMMU for the guest. The idea is simple, cache the translation in a software device IOTLB (which is implemented as an interval tree) in vhost and use vhost_net file descriptor for reporting IOTLB miss and IOTLB update/invalidation. When vhost meets an IOTLB miss, the fault address, size and access can be read from the file. After userspace finishes the translation, it writes the translated address to the vhost_net file to update the device IOTLB. When device IOTLB is enabled by setting VIRTIO_F_IOMMU_PLATFORM all vq addresses set by ioctl are treated as iova instead of virtual address and the accessing can only be done through IOTLB instead of direct userspace memory access. Before each round or vq processing, all vq metadata is prefetched in device IOTLB to make sure no translation fault happens during vq processing. In most cases, virtqueues are contiguous even in virtual address space. The IOTLB translation for virtqueue itself may make it a little slower. We might add fast path cache on top of this patch. Signed-off-by: Jason Wang [mst: use virtio feature bit: VHOST_F_DEVICE_IOTLB -> VIRTIO_F_IOMMU_PLATFORM ] [mst: fix build warnings ] Signed-off-by: Michael S. Tsirkin [ weiyj.lk: missing unlock on error ] Signed-off-by: Wei Yongjun --- include/uapi/linux/vhost.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index c4400b267716..56b7ab584cc0 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -47,6 +47,32 @@ struct vhost_vring_addr { __u64 log_guest_addr; }; +/* no alignment requirement */ +struct vhost_iotlb_msg { + __u64 iova; + __u64 size; + __u64 uaddr; +#define VHOST_ACCESS_RO 0x1 +#define VHOST_ACCESS_WO 0x2 +#define VHOST_ACCESS_RW 0x3 + __u8 perm; +#define VHOST_IOTLB_MISS 1 +#define VHOST_IOTLB_UPDATE 2 +#define VHOST_IOTLB_INVALIDATE 3 +#define VHOST_IOTLB_ACCESS_FAIL 4 + __u8 type; +}; + +#define VHOST_IOTLB_MSG 0x1 + +struct vhost_msg { + int type; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -146,6 +172,8 @@ struct vhost_memory { #define VHOST_F_LOG_ALL 26 /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 +/* Vhost have device IOTLB */ +#define VHOST_F_DEVICE_IOTLB 63 /* VHOST_SCSI specific definitions */ -- cgit v1.2.3 From f8181697fd09bb3b6d857cef31d9af93ea2b0758 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 1 Jul 2016 16:00:49 -0700 Subject: IB/hfi1: Clean up port state structure definition The definition of port state changed mid development and the old structure was kept accidentally. Remove this dead code. Reviewed-by: Dennis Dalessandro Signed-off-by: Ira Weiny Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/opa_port_info.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') diff --git a/include/rdma/opa_port_info.h b/include/rdma/opa_port_info.h index 2b95c2c336eb..9303e0e4f508 100644 --- a/include/rdma/opa_port_info.h +++ b/include/rdma/opa_port_info.h @@ -33,11 +33,6 @@ #if !defined(OPA_PORT_INFO_H) #define OPA_PORT_INFO_H -/* Temporary until HFI driver is updated */ -#ifndef USE_PI_LED_ENABLE -#define USE_PI_LED_ENABLE 0 -#endif - #define OPA_PORT_LINK_MODE_NOP 0 /* No change */ #define OPA_PORT_LINK_MODE_OPA 4 /* Port mode is OPA */ @@ -274,23 +269,12 @@ enum port_info_field_masks { OPA_PI_MASK_MTU_CAP = 0x0F, }; -#if USE_PI_LED_ENABLE struct opa_port_states { u8 reserved; u8 ledenable_offlinereason; /* 1 res, 1 bit, 6 bits */ u8 reserved2; u8 portphysstate_portstate; /* 4 bits, 4 bits */ }; -#define PI_LED_ENABLE_SUP 1 -#else -struct opa_port_states { - u8 reserved; - u8 offline_reason; /* 2 res, 6 bits */ - u8 reserved2; - u8 portphysstate_portstate; /* 4 bits, 4 bits */ -}; -#define PI_LED_ENABLE_SUP 0 -#endif struct opa_port_state_info { struct opa_port_states port_states; -- cgit v1.2.3 From 632bc3f65081dd1e2e5394a9161580a0f78e8839 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 21 Jul 2016 13:03:30 -0700 Subject: IB/core, RDMA RW API: Do not exceed QP SGE send limit Compute the SGE limit for RDMA READ and WRITE requests in ib_create_qp(). Use that limit in the RDMA RW API implementation. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Steve Wise Cc: Parav Pandit Cc: Nicholas Bellinger Cc: Laurence Oberman Cc: #v4.7+ Reviewed-by: Christoph Hellwig Signed-off-by: Doug Ledford --- include/rdma/ib_verbs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 7e440d41487a..e694f02d42e3 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1428,6 +1428,10 @@ struct ib_srq { } ext; }; +/* + * @max_write_sge: Maximum SGE elements per RDMA WRITE request. + * @max_read_sge: Maximum SGE elements per RDMA READ request. + */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; @@ -1449,6 +1453,8 @@ struct ib_qp { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; + u32 max_write_sge; + u32 max_read_sge; enum ib_qp_type qp_type; }; -- cgit v1.2.3 From afcf8f7647780aa147ad68be48d223cd50311b9a Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Fri, 1 Jul 2016 16:02:07 -0700 Subject: IB/rdmavt: Add data structures and routines for table driven post send Add flexibility for driver dependent operations in post send because different drivers will have differing post send operation support. This includes data structure definitions to support a table driven scheme along with the necessary validation routine using the new table. Reviewed-by: Ashutosh Dixit Reviewed-by: Jianxin Xiong Reviewed-by: Dennis Dalessandro Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/rdma_vt.h | 3 +++ include/rdma/rdmavt_qp.h | 28 ++++++++++++++++++++++++---- 2 files changed, 27 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 9c9a27d42aaa..3a70dc047314 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -351,6 +351,9 @@ struct rvt_dev_info { /* Driver specific properties */ struct rvt_driver_params dparms; + /* post send table */ + const struct rvt_operation_params *post_parms; + struct rvt_mregion __rcu *dma_mr; struct rvt_lkey_table lkey_table; diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 6d23b879416a..a90d1e941504 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -228,11 +228,31 @@ struct rvt_ack_entry { #define RC_QP_SCALING_INTERVAL 5 -/* - * Variables prefixed with s_ are for the requester (sender). - * Variables prefixed with r_ are for the responder (receiver). - * Variables prefixed with ack_ are for responder replies. +#define RVT_OPERATION_PRIV 0x00000001 +#define RVT_OPERATION_ATOMIC 0x00000002 +#define RVT_OPERATION_ATOMIC_SGE 0x00000004 + +#define RVT_OPERATION_MAX (IB_WR_RESERVED10 + 1) + +/** + * rvt_operation_params - op table entry + * @length - the length to copy into the swqe entry + * @qpt_support - a bit mask indicating QP type support + * @flags - RVT_OPERATION flags (see above) + * + * This supports table driven post send so that + * the driver can have differing an potentially + * different sets of operations. * + **/ + +struct rvt_operation_params { + size_t length; + u32 qpt_support; + u32 flags; +}; + +/* * Common variables are protected by both r_rq.lock and s_lock in that order * which only happens in modify_qp() or changing the QP 'state'. */ -- cgit v1.2.3 From e8f8b098a44a66d3da81e460aed465f26693e120 Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Mon, 25 Jul 2016 13:38:19 -0700 Subject: IB/rdmavt: Add mechanism to invalidate MR keys In order to support extended memory management, add the mechanism to invalidate MR keys. This includes a flag "lkey_invalid" in the MR data structure that is to be checked when validating access to the MR via the associated key, and two utility functions to perform fast memory registration and memory key invalidate operations. Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Signed-off-by: Jianxin Xiong Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/rdma_vt.h | 3 +++ include/rdma/rdmavt_mr.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 3a70dc047314..7fdba92d4c05 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -487,6 +487,9 @@ void rvt_unregister_device(struct rvt_dev_info *rvd); int rvt_check_ah(struct ib_device *ibdev, struct ib_ah_attr *ah_attr); int rvt_init_port(struct rvt_dev_info *rdi, struct rvt_ibport *port, int port_index, u16 *pkey_table); +int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key, + int access); +int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey); int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge, u32 len, u64 vaddr, u32 rkey, int acc); int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd, diff --git a/include/rdma/rdmavt_mr.h b/include/rdma/rdmavt_mr.h index 5edffdca8c53..6b3c6c8b6b77 100644 --- a/include/rdma/rdmavt_mr.h +++ b/include/rdma/rdmavt_mr.h @@ -81,6 +81,7 @@ struct rvt_mregion { u32 mapsz; /* size of the map array */ u8 page_shift; /* 0 - non unform/non powerof2 sizes */ u8 lkey_published; /* in global table */ + atomic_t lkey_invalid; /* true if current lkey is invalid */ struct completion comp; /* complete when refcount goes to zero */ atomic_t refcount; struct rvt_segarray *map[0]; /* the segments */ -- cgit v1.2.3 From d9f8723924d5955979d05cb7f4f10d9ebac39b7d Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Mon, 25 Jul 2016 13:38:25 -0700 Subject: IB/rdmavt: Handle local operations in post send Some work requests are local operations, such as IB_WR_REG_MR and IB_WR_LOCAL_INV. They differ from non-local operations in that: (1) Local operations can be processed immediately without being posted to the send queue if neither fencing nor completion generation is needed. However, to ensure correct ordering, once a local operation is posted to the work queue due to fencing or completion requiement, all subsequent local operations must also be posted to the work queue until all the local operations on the work queue have completed. (2) Local operations don't send packets over the wire and thus don't need (and shouldn't update) the packet sequence numbers. Define a new a flag bit for the post send table to identify local operations. Add a new field to the QP structure to track the number of local operations on the send queue to determine if direct processing of new local operations should be enabled/disabled. Reviewed-by: Mike Marciniszyn Reviewed-by: Dennis Dalessandro Signed-off-by: Jianxin Xiong Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/rdmavt_qp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index a90d1e941504..b0ab12b30f1e 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -231,6 +231,7 @@ struct rvt_ack_entry { #define RVT_OPERATION_PRIV 0x00000001 #define RVT_OPERATION_ATOMIC 0x00000002 #define RVT_OPERATION_ATOMIC_SGE 0x00000004 +#define RVT_OPERATION_LOCAL 0x00000008 #define RVT_OPERATION_MAX (IB_WR_RESERVED10 + 1) @@ -363,6 +364,8 @@ struct rvt_qp { struct rvt_sge_state s_ack_rdma_sge; struct timer_list s_timer; + atomic_t local_ops_pending; /* number of fast_reg/local_inv reqs */ + /* * This sge list MUST be last. Do not add anything below here. */ -- cgit v1.2.3 From 856cc4c237add46510c8ae91764f4eda31a9e1cf Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Mon, 25 Jul 2016 13:39:39 -0700 Subject: IB/hfi1: Add the capability for reserved operations This fix allows for support of in-kernel reserved operations without impacting the ULP user. The low level driver can register a non-zero value which will be transparently added to the send queue size and hidden from the ULP in every respect. ULP post sends will never see a full queue due to a reserved post send and reserved operations will never exceed that registered value. The s_avail will continue to track the ULP swqe availability and the difference between the reserved value and the reserved in use will track reserved availabity. Reviewed-by: Ashutosh Dixit Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/rdma_vt.h | 1 + include/rdma/rdmavt_qp.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/rdma/rdma_vt.h b/include/rdma/rdma_vt.h index 7fdba92d4c05..e31502107a58 100644 --- a/include/rdma/rdma_vt.h +++ b/include/rdma/rdma_vt.h @@ -158,6 +158,7 @@ struct rvt_driver_params { u32 max_mad_size; u8 qos_shift; u8 max_rdma_atomic; + u8 reserved_operations; }; /* Protection domain */ diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index b0ab12b30f1e..56adcfcabe0b 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -144,6 +144,11 @@ #define RVT_PROCESS_OR_FLUSH_SEND \ (RVT_PROCESS_SEND_OK | RVT_FLUSH_SEND) +/* + * Internal send flags + */ +#define RVT_SEND_RESERVE_USED IB_SEND_RESERVED_START + /* * Send work request queue entry. * The size of the sg_list is determined when the QP is created and stored @@ -232,6 +237,7 @@ struct rvt_ack_entry { #define RVT_OPERATION_ATOMIC 0x00000002 #define RVT_OPERATION_ATOMIC_SGE 0x00000004 #define RVT_OPERATION_LOCAL 0x00000008 +#define RVT_OPERATION_USE_RESERVE 0x00000010 #define RVT_OPERATION_MAX (IB_WR_RESERVED10 + 1) @@ -328,6 +334,7 @@ struct rvt_qp { u32 s_next_psn; /* PSN for next request */ u32 s_avail; /* number of entries avail */ u32 s_ssn; /* SSN of tail entry */ + atomic_t s_reserved_used; /* reserved entries in use */ spinlock_t s_lock ____cacheline_aligned_in_smp; u32 s_flags; @@ -459,6 +466,49 @@ static inline struct rvt_rwqe *rvt_get_rwqe_ptr(struct rvt_rq *rq, unsigned n) rq->max_sge * sizeof(struct ib_sge)) * n); } +/** + * rvt_qp_wqe_reserve - reserve operation + * @qp - the rvt qp + * @wqe - the send wqe + * + * This routine used in post send to record + * a wqe relative reserved operation use. + */ +static inline void rvt_qp_wqe_reserve( + struct rvt_qp *qp, + struct rvt_swqe *wqe) +{ + wqe->wr.send_flags |= RVT_SEND_RESERVE_USED; + atomic_inc(&qp->s_reserved_used); +} + +/** + * rvt_qp_wqe_unreserve - clean reserved operation + * @qp - the rvt qp + * @wqe - the send wqe + * + * This decrements the reserve use count. + * + * This call MUST precede the change to + * s_last to insure that post send sees a stable + * s_avail. + * + * An smp_mp__after_atomic() is used to insure + * the compiler does not juggle the order of the s_last + * ring index and the decrementing of s_reserved_used. + */ +static inline void rvt_qp_wqe_unreserve( + struct rvt_qp *qp, + struct rvt_swqe *wqe) +{ + if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) { + wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED; + atomic_dec(&qp->s_reserved_used); + /* insure no compiler re-order up to s_last change */ + smp_mb__after_atomic(); + } +} + extern const int ib_rvt_state_ops[]; struct rvt_dev_info; -- cgit v1.2.3 From d9b13c203003cfb78c1f216049a204d385ccaeff Mon Sep 17 00:00:00 2001 From: Jianxin Xiong Date: Mon, 25 Jul 2016 13:39:45 -0700 Subject: IB/rdmavt, hfi1: Fix NFSoRDMA failure with FRMR enabled Hanging has been observed while writing a file over NFSoRDMA. Dmesg on the server contains messages like these: [ 931.992501] svcrdma: Error -22 posting RDMA_READ [ 952.076879] svcrdma: Error -22 posting RDMA_READ [ 982.154127] svcrdma: Error -22 posting RDMA_READ [ 1012.235884] svcrdma: Error -22 posting RDMA_READ [ 1042.319194] svcrdma: Error -22 posting RDMA_READ Here is why: With the base memory management extension enabled, FRMR is used instead of FMR. The xprtrdma server issues each RDMA read request as the following bundle: (1)IB_WR_REG_MR, signaled; (2)IB_WR_RDMA_READ, signaled; (3)IB_WR_LOCAL_INV, signaled & fencing. These requests are signaled. In order to generate completion, the fast register work request is processed by the hfi1 send engine after being posted to the work queue, and the corresponding lkey is not valid until the request is processed. However, the rdmavt driver validates lkey when the RDMA read request is posted and thus it fails immediately with error -EINVAL (-22). This patch changes the work flow of local operations (fast register and local invalidate) so that fast register work requests are always processed immediately to ensure that the corresponding lkey is valid when subsequent work requests are posted. Local invalidate requests are processed immediately if fencing is not required and no previous local invalidate request is pending. To allow completion generation for signaled local operations that have been processed before posting to the work queue, an internal send flag RVT_SEND_COMPLETION_ONLY is added. The hfi1 send engine checks this flag and only generates completion for such requests. Reviewed-by: Mike Marciniszyn Signed-off-by: Jianxin Xiong Signed-off-by: Dennis Dalessandro Signed-off-by: Doug Ledford --- include/rdma/rdmavt_qp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 56adcfcabe0b..13902dd319a9 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -148,6 +148,7 @@ * Internal send flags */ #define RVT_SEND_RESERVE_USED IB_SEND_RESERVED_START +#define RVT_SEND_COMPLETION_ONLY (IB_SEND_RESERVED_START << 1) /* * Send work request queue entry. -- cgit v1.2.3 From 6608804b3d7f0552a38641b03a4e3aa1852df15b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 18 May 2016 11:57:29 +0300 Subject: drm/dp: Add drm_dp_psr_setup_time() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a small helper to parse the PSR setup time from the DPCD PSR capabilities and return the value in microseconds. v2: Don't waste so many bytes on the psr_setup_time_us[] table Cc: Daniel Vetter Reviewed-by: Daniel Vetter Signed-off-by: Ville Syrjälä Signed-off-by: Dave Airlie --- include/drm/drm_dp_helper.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 72dee1213268..63b8bd502444 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -657,6 +657,8 @@ struct edp_vsc_psr { #define EDP_VSC_PSR_UPDATE_RFB (1<<1) #define EDP_VSC_PSR_CRC_VALUES_VALID (1<<2) +int drm_dp_psr_setup_time(const u8 psr_cap[EDP_PSR_RECEIVER_CAP_SIZE]); + static inline int drm_dp_max_link_rate(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) { -- cgit v1.2.3 From b3cbd9bf77cd1888114dbee1653e79aa23fd4068 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 2 Aug 2016 14:02:52 -0700 Subject: mm/kasan: get rid of ->state in struct kasan_alloc_meta The state of object currently tracked in two places - shadow memory, and the ->state field in struct kasan_alloc_meta. We can get rid of the latter. The will save us a little bit of memory. Also, this allow us to move free stack into struct kasan_alloc_meta, without increasing memory consumption. So now we should always know when the last time the object was freed. This may be useful for long delayed use-after-free bugs. As a side effect this fixes following UBSAN warning: UBSAN: Undefined behaviour in mm/kasan/quarantine.c:102:13 member access within misaligned address ffff88000d1efebc for type 'struct qlist_node' which requires 8 byte alignment Link: http://lkml.kernel.org/r/1470062715-14077-5-git-send-email-aryabinin@virtuozzo.com Reported-by: kernel test robot Signed-off-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index c9cf374445d8..d600303306eb 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -56,6 +56,7 @@ void kasan_cache_destroy(struct kmem_cache *cache); void kasan_poison_slab(struct page *page); void kasan_unpoison_object_data(struct kmem_cache *cache, void *object); void kasan_poison_object_data(struct kmem_cache *cache, void *object); +void kasan_init_slab_obj(struct kmem_cache *cache, const void *object); void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags); void kasan_kfree_large(const void *ptr); @@ -102,6 +103,8 @@ static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_object_data(struct kmem_cache *cache, void *object) {} +static inline void kasan_init_slab_obj(struct kmem_cache *cache, + const void *object) {} static inline void kasan_kmalloc_large(void *ptr, size_t size, gfp_t flags) {} static inline void kasan_kfree_large(const void *ptr) {} -- cgit v1.2.3 From bd721ea73e1f965569b40620538c942001f76294 Mon Sep 17 00:00:00 2001 From: Fabian Frederick Date: Tue, 2 Aug 2016 14:03:33 -0700 Subject: treewide: replace obsolete _refok by __ref There was only one use of __initdata_refok and __exit_refok __init_refok was used 46 times against 82 for __ref. Those definitions are obsolete since commit 312b1485fb50 ("Introduce new section reference annotations tags: __ref, __refdata, __refconst") This patch removes the following compatibility definitions and replaces them treewide. /* compatibility defines */ #define __init_refok __ref #define __initdata_refok __refdata #define __exit_refok __ref I can also provide separate patches if necessary. (One patch per tree and check in 1 month or 2 to remove old definitions) [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1466796271-3043-1-git-send-email-fabf@skynet.be Signed-off-by: Fabian Frederick Cc: Ingo Molnar Cc: Sam Ravnborg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/acpi/acpi_io.h | 2 +- include/linux/init.h | 6 ------ include/net/net_namespace.h | 2 +- 3 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h index dd86c5fc102d..d7d0f495a34e 100644 --- a/include/acpi/acpi_io.h +++ b/include/acpi/acpi_io.h @@ -13,7 +13,7 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, } #endif -void __iomem *__init_refok +void __iomem *__ref acpi_os_map_iomem(acpi_physical_address phys, acpi_size size); void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size); void __iomem *acpi_os_get_iomem(acpi_physical_address phys, unsigned int size); diff --git a/include/linux/init.h b/include/linux/init.h index aedb254abc37..6935d02474aa 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -77,12 +77,6 @@ #define __refdata __section(.ref.data) #define __refconst __constsection(.ref.rodata) -/* compatibility defines */ -#define __init_refok __ref -#define __initdata_refok __refdata -#define __exit_refok __ref - - #ifdef MODULE #define __exitused #else diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 4089abc6e9c0..0933c7455a30 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -275,7 +275,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet) #define __net_initconst #else #define __net_init __init -#define __net_exit __exit_refok +#define __net_exit __ref #define __net_initdata __initdata #define __net_initconst __initconst #endif -- cgit v1.2.3 From db3f60012482756f46cc4d7d9ad7d793ae30360c Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 2 Aug 2016 14:03:36 -0700 Subject: uapi: move forward declarations of internal structures Don't user forward declarations of internal kernel structures in headers exported to userspace. Move "struct completion;". Move "struct task_struct;". Link: http://lkml.kernel.org/r/20160713215808.GA22486@p183.telecom.by Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/capability.h | 1 + include/linux/sysctl.h | 1 + include/uapi/linux/capability.h | 2 -- include/uapi/linux/sysctl.h | 2 -- 4 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index 5f3c63dde2d5..dbc21c719ce6 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -38,6 +38,7 @@ struct cpu_vfs_cap_data { struct file; struct inode; struct dentry; +struct task_struct; struct user_namespace; extern const kernel_cap_t __cap_empty_set; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index fa7bc29925c9..697e160c78d0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -28,6 +28,7 @@ #include /* For the /proc/sys support */ +struct completion; struct ctl_table; struct nsproxy; struct ctl_table_root; diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 12c37a197d24..49bc06295398 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -15,8 +15,6 @@ #include -struct task_struct; - /* User-level do most of the mapping between kernel and user capabilities based on the version tag given by the kernel. The kernel might be somewhat backwards compatible, but don't bet on diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 0956373b56db..d2b12152e358 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -26,8 +26,6 @@ #include #include -struct completion; - #define CTL_MAXNAME 10 /* how many path components do we allow in a call to sysctl? In other words, what is the largest acceptable value for the nlen -- cgit v1.2.3 From 949bed2f5764435715e3d6dd3ab6dd4dbd890a71 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Tue, 2 Aug 2016 14:03:42 -0700 Subject: include: mman: use bool instead of int for the return value of arch_validate_prot For pure bool function's return value, bool is a little better more or less than int. Link: http://lkml.kernel.org/r/1469331815-2026-1-git-send-email-chengang@emindsoft.com.cn Signed-off-by: Chen Gang Acked-by: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mman.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mman.h b/include/linux/mman.h index 33e17f6a327a..634c4c51fe3a 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -49,7 +49,7 @@ static inline void vm_unacct_memory(long pages) * * Returns true if the prot flags are valid */ -static inline int arch_validate_prot(unsigned long prot) +static inline bool arch_validate_prot(unsigned long prot) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } -- cgit v1.2.3 From 9d5059c959ac739dbf837cec14586e58e7a67292 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Tue, 2 Aug 2016 14:03:47 -0700 Subject: dynamic_debug: only add header when used kernel.h header doesn't directly use dynamic debug, instead we can include it in module.c (which used it via kernel.h). printk.h only uses it if CONFIG_DYNAMIC_DEBUG is on, changing the inclusion to only happen in that case. Link: http://lkml.kernel.org/r/1468429793-16917-1-git-send-email-luisbg@osg.samsung.com [luisbg@osg.samsung.com: include dynamic_debug.h in drb_int.h] Link: http://lkml.kernel.org/r/1468447828-18558-2-git-send-email-luisbg@osg.samsung.com Signed-off-by: Luis de Bethencourt Cc: Rusty Russell Cc: Hidehiro Kawai Cc: Borislav Petkov Cc: Michal Nazarewicz Cc: Rasmus Villemoes Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 - include/linux/printk.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index c42082112ec8..d96a6118d26a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include diff --git a/include/linux/printk.h b/include/linux/printk.h index f136b22c7772..987c65ed34e5 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -289,10 +289,11 @@ extern asmlinkage void dump_stack(void) __cold; no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif -#include /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) +#include + /* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) -- cgit v1.2.3 From 874f9c7da9a4acbc1b9e12ca722579fb50e4d142 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 2 Aug 2016 14:03:53 -0700 Subject: printk: create pr_ functions Using functions instead of macros can reduce overall code size by eliminating unnecessary "KERN_SOH" prefixes from format strings. defconfig x86-64: $ size vmlinux* text data bss dec hex filename 10193570 4331464 1105920 15630954 ee826a vmlinux.new 10192623 4335560 1105920 15634103 ee8eb7 vmlinux.old As the return value are unimportant and unused in the kernel tree, these new functions return void. Miscellanea: - change pr_ macros to call new __pr_ functions - change vprintk_nmi and vprintk_default to add LOGLEVEL_ argument [akpm@linux-foundation.org: fix LOGLEVEL_INFO, per Joe] Link: http://lkml.kernel.org/r/e16cc34479dfefcae37c98b481e6646f0f69efc3.1466718827.git.joe@perches.com Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 48 +++++++++++++++++++++++++++++++++--------------- 1 file changed, 33 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 987c65ed34e5..c2158f0f1499 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -257,21 +257,39 @@ extern asmlinkage void dump_stack(void) __cold; * and other debug macros are compiled out unless either DEBUG is defined * or CONFIG_DYNAMIC_DEBUG is set. */ -#define pr_emerg(fmt, ...) \ - printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) \ - printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) \ - printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) \ - printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning(fmt, ...) \ - printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn pr_warning -#define pr_notice(fmt, ...) \ - printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) \ - printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) + +#ifdef CONFIG_PRINTK + +asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...); +asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...); + +#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__) + +#else + +#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) + +#endif + +#define pr_warning pr_warn + /* * Like KERN_CONT, pr_cont() should only be used when continuing * a line with no newline ('\n') enclosed. Otherwise it defaults -- cgit v1.2.3 From 6b1d174b0c27b5de421eda55c2731f32b6bd9852 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 2 Aug 2016 14:04:04 -0700 Subject: ratelimit: extend to print suppressed messages on release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend the ratelimiting facility to print the amount of suppressed lines when it is being released. This use case is aimed at short-termed, burst-like users for which we want to output the suppressed lines stats only once, after it has been disposed of. For an example, see /dev/kmsg usage in a follow-on patch. Also, change the printk() line we issue on release to not use "callbacks" as it is misleading: we're not suppressing callbacks but printk() calls. This has been separated from a previous patch by Linus. Link: http://lkml.kernel.org/r/20160716061745.15795-2-bp@alien8.de Signed-off-by: Borislav Petkov Cc: Dave Young Cc: Franck Bui Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Uwe Kleine-König Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ratelimit.h | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 18102529254e..57c9e0622a38 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -2,11 +2,15 @@ #define _LINUX_RATELIMIT_H #include +#include #include #define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) #define DEFAULT_RATELIMIT_BURST 10 +/* issue num suppressed message on exit */ +#define RATELIMIT_MSG_ON_RELEASE BIT(0) + struct ratelimit_state { raw_spinlock_t lock; /* protect the state */ @@ -15,6 +19,7 @@ struct ratelimit_state { int printed; int missed; unsigned long begin; + unsigned long flags; }; #define RATELIMIT_STATE_INIT(name, interval_init, burst_init) { \ @@ -34,12 +39,35 @@ struct ratelimit_state { static inline void ratelimit_state_init(struct ratelimit_state *rs, int interval, int burst) { + memset(rs, 0, sizeof(*rs)); + raw_spin_lock_init(&rs->lock); - rs->interval = interval; - rs->burst = burst; - rs->printed = 0; - rs->missed = 0; - rs->begin = 0; + rs->interval = interval; + rs->burst = burst; +} + +static inline void ratelimit_default_init(struct ratelimit_state *rs) +{ + return ratelimit_state_init(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); +} + +static inline void ratelimit_state_exit(struct ratelimit_state *rs) +{ + if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) + return; + + if (rs->missed) { + pr_warn("%s: %d output lines suppressed due to ratelimiting\n", + current->comm, rs->missed); + rs->missed = 0; + } +} + +static inline void +ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags) +{ + rs->flags = flags; } extern struct ratelimit_state printk_ratelimit_state; -- cgit v1.2.3 From 750afe7babd117daabebf4855da18e4418ea845e Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 2 Aug 2016 14:04:07 -0700 Subject: printk: add kernel parameter to control writes to /dev/kmsg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a "printk.devkmsg" kernel command line parameter which controls how userspace writes into /dev/kmsg. It has three options: * ratelimit - ratelimit logging from userspace. * on - unlimited logging from userspace * off - logging from userspace gets ignored The default setting is to ratelimit the messages written to it. This changes the kernel default setting of "on" to "ratelimit" and we do that because we want to keep userspace spamming /dev/kmsg to sane levels. This is especially moot when a small kernel log buffer wraps around and messages get lost. So the ratelimiting setting should be a sane setting where kernel messages should have a bit higher chance of survival from all the spamming. It additionally does not limit logging to /dev/kmsg while the system is booting if we haven't disabled it on the command line. Furthermore, we can control the logging from a lower priority sysctl interface - kernel.printk_devkmsg. That interface will succeed only if printk.devkmsg *hasn't* been supplied on the command line. If it has, then printk.devkmsg is a one-time setting which remains for the duration of the system lifetime. This "locking" of the setting is to prevent userspace from changing the logging on us through sysctl(2). This patch is based on previous patches from Linus and Steven. [bp@suse.de: fixes] Link: http://lkml.kernel.org/r/20160719072344.GC25563@nazgul.tnic Link: http://lkml.kernel.org/r/20160716061745.15795-3-bp@alien8.de Signed-off-by: Borislav Petkov Cc: Dave Young Cc: Franck Bui Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Uwe Kleine-König Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index c2158f0f1499..8dc155dab3ed 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -61,6 +61,11 @@ static inline void console_verbose(void) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } +/* strlen("ratelimit") + 1 */ +#define DEVKMSG_STR_MAX_SIZE 10 +extern char devkmsg_log_str[]; +struct ctl_table; + struct va_format { const char *fmt; va_list *va; @@ -175,6 +180,10 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; +extern int +devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void __user *buf, + size_t *lenp, loff_t *ppos); + extern void wake_up_klogd(void); char *log_buf_addr_get(void); -- cgit v1.2.3 From a23216a2f1f8a30a3b6588c743681651e4a6aa94 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Tue, 2 Aug 2016 14:04:19 -0700 Subject: radix-tree: fix comment about "exceptional" bits The bottom two bits of radix tree entries are reserved for special use by the radix tree code itself. A comment detailing their usage was added by commit 3bcadd6fa6c4 ("radix-tree: free up the bottom bit of exceptional entries for reuse") This comment states that if the bottom two bits are '11', this means that this is a locked exceptional entry. It turns out that this bit combination was never actually used. Radix tree locking for DAX was indeed implemented, but it actually used the third LSB: /* We use lowest available exceptional entry bit for locking */ #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) This locking code was also made specific to the DAX code instead of being generally implemented in radix-tree.h. So, fix the comment. Link: http://lkml.kernel.org/r/1468997731-2155-1-git-send-email-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Reviewed-by: Johannes Thumshirn Cc: Dave Chinner Cc: Jan Kara Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index cbfee507c839..4c45105dece3 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -35,7 +35,7 @@ * 00 - data pointer * 01 - internal entry * 10 - exceptional entry - * 11 - locked exceptional entry + * 11 - this bit combination is currently unused/reserved * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved -- cgit v1.2.3 From a098ecd2fa7db8fa4fcc178a43627b29b226edb9 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 2 Aug 2016 14:04:28 -0700 Subject: firmware: support loading into a pre-allocated buffer Some systems are memory constrained but they need to load very large firmwares. The firmware subsystem allows drivers to request this firmware be loaded from the filesystem, but this requires that the entire firmware be loaded into kernel memory first before it's provided to the driver. This can lead to a situation where we map the firmware twice, once to load the firmware into kernel memory and once to copy the firmware into the final resting place. This creates needless memory pressure and delays loading because we have to copy from kernel memory to somewhere else. Let's add a request_firmware_into_buf() API that allows drivers to request firmware be loaded directly into a pre-allocated buffer. This skips the intermediate step of allocating a buffer in kernel memory to hold the firmware image while it's read from the filesystem. It also requires that drivers know how much memory they'll require before requesting the firmware and negates any benefits of firmware caching because the firmware layer doesn't manage the buffer lifetime. For a 16MB buffer, about half the time is spent performing a memcpy from the buffer to the final resting place. I see loading times go from 0.081171 seconds to 0.047696 seconds after applying this patch. Plus the vmalloc pressure is reduced. This is based on a patch from Vikram Mulukutla on codeaurora.org: https://www.codeaurora.org/cgit/quic/la/kernel/msm-3.18/commit/drivers/base/firmware_class.c?h=rel/msm-3.18&id=0a328c5f6cd999f5c591f172216835636f39bcb5 Link: http://lkml.kernel.org/r/20160607164741.31849-4-stephen.boyd@linaro.org Signed-off-by: Stephen Boyd Cc: Mimi Zohar Cc: Vikram Mulukutla Cc: Mark Brown Cc: Ming Lei Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/firmware.h | 8 ++++++++ include/linux/fs.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 5c41c5e75b5c..b1f9f0ccb8ac 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -47,6 +47,8 @@ int request_firmware_nowait( void (*cont)(const struct firmware *fw, void *context)); int request_firmware_direct(const struct firmware **fw, const char *name, struct device *device); +int request_firmware_into_buf(const struct firmware **firmware_p, + const char *name, struct device *device, void *buf, size_t size); void release_firmware(const struct firmware *fw); #else @@ -75,5 +77,11 @@ static inline int request_firmware_direct(const struct firmware **fw, return -EINVAL; } +static inline int request_firmware_into_buf(const struct firmware **firmware_p, + const char *name, struct device *device, void *buf, size_t size) +{ + return -EINVAL; +} + #endif #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 577365a77b47..f3f0b4c8e8ac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2652,6 +2652,7 @@ extern int do_pipe_flags(int *, int); #define __kernel_read_file_id(id) \ id(UNKNOWN, unknown) \ id(FIRMWARE, firmware) \ + id(FIRMWARE_PREALLOC_BUFFER, firmware) \ id(MODULE, kernel-module) \ id(KEXEC_IMAGE, kexec-image) \ id(KEXEC_INITRAMFS, kexec-initramfs) \ -- cgit v1.2.3 From e63e88bc53bac7e4c3f592f8126c51a7569be673 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 2 Aug 2016 14:05:30 -0700 Subject: nilfs2: move ioctl interface and disk layout to uapi separately The header file "include/linux/nilfs2_fs.h" is composed of parts for ioctl and disk format, and both are intended to be shared with user space programs. This moves them to the uapi directory "include/uapi/linux" splitting the file to "nilfs2_api.h" and "nilfs2_ondisk.h". The following minor changes are accompanied by this migration: - nilfs_direct_node struct in nilfs2/direct.h is converged to nilfs2_ondisk.h because it's an on-disk structure. - inline functions nilfs_rec_len_from_disk() and nilfs_rec_len_to_disk() are moved to nilfs2/dir.c. Link: http://lkml.kernel.org/r/1465825507-3407-4-git-send-email-konishi.ryusuke@lab.ntt.co.jp Signed-off-by: Ryusuke Konishi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nilfs2_fs.h | 934 ------------------------------------- include/uapi/linux/nilfs2_api.h | 292 ++++++++++++ include/uapi/linux/nilfs2_ondisk.h | 650 ++++++++++++++++++++++++++ 3 files changed, 942 insertions(+), 934 deletions(-) delete mode 100644 include/linux/nilfs2_fs.h create mode 100644 include/uapi/linux/nilfs2_api.h create mode 100644 include/uapi/linux/nilfs2_ondisk.h (limited to 'include') diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h deleted file mode 100644 index 5988dd57ba66..000000000000 --- a/include/linux/nilfs2_fs.h +++ /dev/null @@ -1,934 +0,0 @@ -/* - * nilfs2_fs.h - NILFS2 on-disk structures and common declarations. - * - * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 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 Lesser General Public License for more details. - * - * Written by Koji Sato and Ryusuke Konishi. - */ -/* - * linux/include/linux/ext2_fs.h - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/include/linux/minix_fs.h - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -#ifndef _LINUX_NILFS_FS_H -#define _LINUX_NILFS_FS_H - -#include -#include -#include -#include - - -#define NILFS_INODE_BMAP_SIZE 7 -/** - * struct nilfs_inode - structure of an inode on disk - * @i_blocks: blocks count - * @i_size: size in bytes - * @i_ctime: creation time (seconds) - * @i_mtime: modification time (seconds) - * @i_ctime_nsec: creation time (nano seconds) - * @i_mtime_nsec: modification time (nano seconds) - * @i_uid: user id - * @i_gid: group id - * @i_mode: file mode - * @i_links_count: links count - * @i_flags: file flags - * @i_bmap: block mapping - * @i_xattr: extended attributes - * @i_generation: file generation (for NFS) - * @i_pad: padding - */ -struct nilfs_inode { - __le64 i_blocks; - __le64 i_size; - __le64 i_ctime; - __le64 i_mtime; - __le32 i_ctime_nsec; - __le32 i_mtime_nsec; - __le32 i_uid; - __le32 i_gid; - __le16 i_mode; - __le16 i_links_count; - __le32 i_flags; - __le64 i_bmap[NILFS_INODE_BMAP_SIZE]; -#define i_device_code i_bmap[0] - __le64 i_xattr; - __le32 i_generation; - __le32 i_pad; -}; - -#define NILFS_MIN_INODE_SIZE 128 - -/** - * struct nilfs_super_root - structure of super root - * @sr_sum: check sum - * @sr_bytes: byte count of the structure - * @sr_flags: flags (reserved) - * @sr_nongc_ctime: write time of the last segment not for cleaner operation - * @sr_dat: DAT file inode - * @sr_cpfile: checkpoint file inode - * @sr_sufile: segment usage file inode - */ -struct nilfs_super_root { - __le32 sr_sum; - __le16 sr_bytes; - __le16 sr_flags; - __le64 sr_nongc_ctime; - struct nilfs_inode sr_dat; - struct nilfs_inode sr_cpfile; - struct nilfs_inode sr_sufile; -}; - -#define NILFS_SR_MDT_OFFSET(inode_size, i) \ - ((unsigned long)&((struct nilfs_super_root *)0)->sr_dat + \ - (inode_size) * (i)) -#define NILFS_SR_DAT_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 0) -#define NILFS_SR_CPFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 1) -#define NILFS_SR_SUFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 2) -#define NILFS_SR_BYTES(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 3) - -/* - * Maximal mount counts - */ -#define NILFS_DFL_MAX_MNT_COUNT 50 /* 50 mounts */ - -/* - * File system states (sbp->s_state, nilfs->ns_mount_state) - */ -#define NILFS_VALID_FS 0x0001 /* Unmounted cleanly */ -#define NILFS_ERROR_FS 0x0002 /* Errors detected */ -#define NILFS_RESIZE_FS 0x0004 /* Resize required */ - -/* - * Mount flags (sbi->s_mount_opt) - */ -#define NILFS_MOUNT_ERROR_MODE 0x0070 /* Error mode mask */ -#define NILFS_MOUNT_ERRORS_CONT 0x0010 /* Continue on errors */ -#define NILFS_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */ -#define NILFS_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */ -#define NILFS_MOUNT_BARRIER 0x1000 /* Use block barriers */ -#define NILFS_MOUNT_STRICT_ORDER 0x2000 /* - * Apply strict in-order - * semantics also for data - */ -#define NILFS_MOUNT_NORECOVERY 0x4000 /* - * Disable write access during - * mount-time recovery - */ -#define NILFS_MOUNT_DISCARD 0x8000 /* Issue DISCARD requests */ - - -/** - * struct nilfs_super_block - structure of super block on disk - */ -struct nilfs_super_block { -/*00*/ __le32 s_rev_level; /* Revision level */ - __le16 s_minor_rev_level; /* minor revision level */ - __le16 s_magic; /* Magic signature */ - - __le16 s_bytes; /* - * Bytes count of CRC calculation - * for this structure. s_reserved - * is excluded. - */ - __le16 s_flags; /* flags */ - __le32 s_crc_seed; /* Seed value of CRC calculation */ -/*10*/ __le32 s_sum; /* Check sum of super block */ - - __le32 s_log_block_size; /* - * Block size represented as follows - * blocksize = - * 1 << (s_log_block_size + 10) - */ - __le64 s_nsegments; /* Number of segments in filesystem */ -/*20*/ __le64 s_dev_size; /* block device size in bytes */ - __le64 s_first_data_block; /* 1st seg disk block number */ -/*30*/ __le32 s_blocks_per_segment; /* number of blocks per full segment */ - __le32 s_r_segments_percentage; /* Reserved segments percentage */ - - __le64 s_last_cno; /* Last checkpoint number */ -/*40*/ __le64 s_last_pseg; /* disk block addr pseg written last */ - __le64 s_last_seq; /* seq. number of seg written last */ -/*50*/ __le64 s_free_blocks_count; /* Free blocks count */ - - __le64 s_ctime; /* - * Creation time (execution time of - * newfs) - */ -/*60*/ __le64 s_mtime; /* Mount time */ - __le64 s_wtime; /* Write time */ -/*70*/ __le16 s_mnt_count; /* Mount count */ - __le16 s_max_mnt_count; /* Maximal mount count */ - __le16 s_state; /* File system state */ - __le16 s_errors; /* Behaviour when detecting errors */ - __le64 s_lastcheck; /* time of last check */ - -/*80*/ __le32 s_checkinterval; /* max. time between checks */ - __le32 s_creator_os; /* OS */ - __le16 s_def_resuid; /* Default uid for reserved blocks */ - __le16 s_def_resgid; /* Default gid for reserved blocks */ - __le32 s_first_ino; /* First non-reserved inode */ - -/*90*/ __le16 s_inode_size; /* Size of an inode */ - __le16 s_dat_entry_size; /* Size of a dat entry */ - __le16 s_checkpoint_size; /* Size of a checkpoint */ - __le16 s_segment_usage_size; /* Size of a segment usage */ - -/*98*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ -/*A8*/ char s_volume_name[80]; /* volume name */ - -/*F8*/ __le32 s_c_interval; /* Commit interval of segment */ - __le32 s_c_block_max; /* - * Threshold of data amount for - * the segment construction - */ -/*100*/ __le64 s_feature_compat; /* Compatible feature set */ - __le64 s_feature_compat_ro; /* Read-only compatible feature set */ - __le64 s_feature_incompat; /* Incompatible feature set */ - __u32 s_reserved[186]; /* padding to the end of the block */ -}; - -/* - * Codes for operating systems - */ -#define NILFS_OS_LINUX 0 -/* Codes from 1 to 4 are reserved to keep compatibility with ext2 creator-OS */ - -/* - * Revision levels - */ -#define NILFS_CURRENT_REV 2 /* current major revision */ -#define NILFS_MINOR_REV 0 /* minor revision */ -#define NILFS_MIN_SUPP_REV 2 /* minimum supported revision */ - -/* - * Feature set definitions - * - * If there is a bit set in the incompatible feature set that the kernel - * doesn't know about, it should refuse to mount the filesystem. - */ -#define NILFS_FEATURE_COMPAT_RO_BLOCK_COUNT 0x00000001ULL - -#define NILFS_FEATURE_COMPAT_SUPP 0ULL -#define NILFS_FEATURE_COMPAT_RO_SUPP NILFS_FEATURE_COMPAT_RO_BLOCK_COUNT -#define NILFS_FEATURE_INCOMPAT_SUPP 0ULL - -/* - * Bytes count of super_block for CRC-calculation - */ -#define NILFS_SB_BYTES \ - ((long)&((struct nilfs_super_block *)0)->s_reserved) - -/* - * Special inode number - */ -#define NILFS_ROOT_INO 2 /* Root file inode */ -#define NILFS_DAT_INO 3 /* DAT file */ -#define NILFS_CPFILE_INO 4 /* checkpoint file */ -#define NILFS_SUFILE_INO 5 /* segment usage file */ -#define NILFS_IFILE_INO 6 /* ifile */ -#define NILFS_ATIME_INO 7 /* Atime file (reserved) */ -#define NILFS_XATTR_INO 8 /* Xattribute file (reserved) */ -#define NILFS_SKETCH_INO 10 /* Sketch file */ -#define NILFS_USER_INO 11 /* Fisrt user's file inode number */ - -#define NILFS_SB_OFFSET_BYTES 1024 /* byte offset of nilfs superblock */ - -#define NILFS_SEG_MIN_BLOCKS 16 /* - * Minimum number of blocks in - * a full segment - */ -#define NILFS_PSEG_MIN_BLOCKS 2 /* - * Minimum number of blocks in - * a partial segment - */ -#define NILFS_MIN_NRSVSEGS 8 /* - * Minimum number of reserved - * segments - */ - -/* - * We call DAT, cpfile, and sufile root metadata files. Inodes of - * these files are written in super root block instead of ifile, and - * garbage collector doesn't keep any past versions of these files. - */ -#define NILFS_ROOT_METADATA_FILE(ino) \ - ((ino) >= NILFS_DAT_INO && (ino) <= NILFS_SUFILE_INO) - -/* - * bytes offset of secondary super block - */ -#define NILFS_SB2_OFFSET_BYTES(devsize) ((((devsize) >> 12) - 1) << 12) - -/* - * Maximal count of links to a file - */ -#define NILFS_LINK_MAX 32000 - -/* - * Structure of a directory entry - * (Same as ext2) - */ - -#define NILFS_NAME_LEN 255 - -/* - * Block size limitations - */ -#define NILFS_MIN_BLOCK_SIZE 1024 -#define NILFS_MAX_BLOCK_SIZE 65536 - -/* - * The new version of the directory entry. Since V0 structures are - * stored in intel byte order, and the name_len field could never be - * bigger than 255 chars, it's safe to reclaim the extra byte for the - * file_type field. - */ -struct nilfs_dir_entry { - __le64 inode; /* Inode number */ - __le16 rec_len; /* Directory entry length */ - __u8 name_len; /* Name length */ - __u8 file_type; /* Dir entry type (file, dir, etc) */ - char name[NILFS_NAME_LEN]; /* File name */ - char pad; -}; - -/* - * NILFS directory file types. Only the low 3 bits are used. The - * other bits are reserved for now. - */ -enum { - NILFS_FT_UNKNOWN, - NILFS_FT_REG_FILE, - NILFS_FT_DIR, - NILFS_FT_CHRDEV, - NILFS_FT_BLKDEV, - NILFS_FT_FIFO, - NILFS_FT_SOCK, - NILFS_FT_SYMLINK, - NILFS_FT_MAX -}; - -/* - * NILFS_DIR_PAD defines the directory entries boundaries - * - * NOTE: It must be a multiple of 8 - */ -#define NILFS_DIR_PAD 8 -#define NILFS_DIR_ROUND (NILFS_DIR_PAD - 1) -#define NILFS_DIR_REC_LEN(name_len) (((name_len) + 12 + NILFS_DIR_ROUND) & \ - ~NILFS_DIR_ROUND) -#define NILFS_MAX_REC_LEN ((1<<16)-1) - -static inline unsigned int nilfs_rec_len_from_disk(__le16 dlen) -{ - unsigned int len = le16_to_cpu(dlen); - -#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) - if (len == NILFS_MAX_REC_LEN) - return 1 << 16; -#endif - return len; -} - -static inline __le16 nilfs_rec_len_to_disk(unsigned int len) -{ -#if !defined(__KERNEL__) || (PAGE_SIZE >= 65536) - if (len == (1 << 16)) - return cpu_to_le16(NILFS_MAX_REC_LEN); - else if (len > (1 << 16)) - BUG(); -#endif - return cpu_to_le16(len); -} - -/** - * struct nilfs_finfo - file information - * @fi_ino: inode number - * @fi_cno: checkpoint number - * @fi_nblocks: number of blocks (including intermediate blocks) - * @fi_ndatablk: number of file data blocks - */ -struct nilfs_finfo { - __le64 fi_ino; - __le64 fi_cno; - __le32 fi_nblocks; - __le32 fi_ndatablk; - /* array of virtual block numbers */ -}; - -/** - * struct nilfs_binfo_v - information for the block to which a virtual block number is assigned - * @bi_vblocknr: virtual block number - * @bi_blkoff: block offset - */ -struct nilfs_binfo_v { - __le64 bi_vblocknr; - __le64 bi_blkoff; -}; - -/** - * struct nilfs_binfo_dat - information for the block which belongs to the DAT file - * @bi_blkoff: block offset - * @bi_level: level - * @bi_pad: padding - */ -struct nilfs_binfo_dat { - __le64 bi_blkoff; - __u8 bi_level; - __u8 bi_pad[7]; -}; - -/** - * union nilfs_binfo: block information - * @bi_v: nilfs_binfo_v structure - * @bi_dat: nilfs_binfo_dat structure - */ -union nilfs_binfo { - struct nilfs_binfo_v bi_v; - struct nilfs_binfo_dat bi_dat; -}; - -/** - * struct nilfs_segment_summary - segment summary header - * @ss_datasum: checksum of data - * @ss_sumsum: checksum of segment summary - * @ss_magic: magic number - * @ss_bytes: size of this structure in bytes - * @ss_flags: flags - * @ss_seq: sequence number - * @ss_create: creation timestamp - * @ss_next: next segment - * @ss_nblocks: number of blocks - * @ss_nfinfo: number of finfo structures - * @ss_sumbytes: total size of segment summary in bytes - * @ss_pad: padding - * @ss_cno: checkpoint number - */ -struct nilfs_segment_summary { - __le32 ss_datasum; - __le32 ss_sumsum; - __le32 ss_magic; - __le16 ss_bytes; - __le16 ss_flags; - __le64 ss_seq; - __le64 ss_create; - __le64 ss_next; - __le32 ss_nblocks; - __le32 ss_nfinfo; - __le32 ss_sumbytes; - __le32 ss_pad; - __le64 ss_cno; - /* array of finfo structures */ -}; - -#define NILFS_SEGSUM_MAGIC 0x1eaffa11 /* segment summary magic number */ - -/* - * Segment summary flags - */ -#define NILFS_SS_LOGBGN 0x0001 /* begins a logical segment */ -#define NILFS_SS_LOGEND 0x0002 /* ends a logical segment */ -#define NILFS_SS_SR 0x0004 /* has super root */ -#define NILFS_SS_SYNDT 0x0008 /* includes data only updates */ -#define NILFS_SS_GC 0x0010 /* segment written for cleaner operation */ - -/** - * struct nilfs_btree_node - B-tree node - * @bn_flags: flags - * @bn_level: level - * @bn_nchildren: number of children - * @bn_pad: padding - */ -struct nilfs_btree_node { - __u8 bn_flags; - __u8 bn_level; - __le16 bn_nchildren; - __le32 bn_pad; -}; - -/* flags */ -#define NILFS_BTREE_NODE_ROOT 0x01 - -/* level */ -#define NILFS_BTREE_LEVEL_DATA 0 -#define NILFS_BTREE_LEVEL_NODE_MIN (NILFS_BTREE_LEVEL_DATA + 1) -#define NILFS_BTREE_LEVEL_MAX 14 /* Max level (exclusive) */ - -/** - * struct nilfs_palloc_group_desc - block group descriptor - * @pg_nfrees: number of free entries in block group - */ -struct nilfs_palloc_group_desc { - __le32 pg_nfrees; -}; - -/** - * struct nilfs_dat_entry - disk address translation entry - * @de_blocknr: block number - * @de_start: start checkpoint number - * @de_end: end checkpoint number - * @de_rsv: reserved for future use - */ -struct nilfs_dat_entry { - __le64 de_blocknr; - __le64 de_start; - __le64 de_end; - __le64 de_rsv; -}; - -#define NILFS_MIN_DAT_ENTRY_SIZE 32 - -/** - * struct nilfs_snapshot_list - snapshot list - * @ssl_next: next checkpoint number on snapshot list - * @ssl_prev: previous checkpoint number on snapshot list - */ -struct nilfs_snapshot_list { - __le64 ssl_next; - __le64 ssl_prev; -}; - -/** - * struct nilfs_checkpoint - checkpoint structure - * @cp_flags: flags - * @cp_checkpoints_count: checkpoints count in a block - * @cp_snapshot_list: snapshot list - * @cp_cno: checkpoint number - * @cp_create: creation timestamp - * @cp_nblk_inc: number of blocks incremented by this checkpoint - * @cp_inodes_count: inodes count - * @cp_blocks_count: blocks count - * @cp_ifile_inode: inode of ifile - */ -struct nilfs_checkpoint { - __le32 cp_flags; - __le32 cp_checkpoints_count; - struct nilfs_snapshot_list cp_snapshot_list; - __le64 cp_cno; - __le64 cp_create; - __le64 cp_nblk_inc; - __le64 cp_inodes_count; - __le64 cp_blocks_count; - - /* - * Do not change the byte offset of ifile inode. - * To keep the compatibility of the disk format, - * additional fields should be added behind cp_ifile_inode. - */ - struct nilfs_inode cp_ifile_inode; -}; - -#define NILFS_MIN_CHECKPOINT_SIZE (64 + NILFS_MIN_INODE_SIZE) - -/* checkpoint flags */ -enum { - NILFS_CHECKPOINT_SNAPSHOT, - NILFS_CHECKPOINT_INVALID, - NILFS_CHECKPOINT_SKETCH, - NILFS_CHECKPOINT_MINOR, -}; - -#define NILFS_CHECKPOINT_FNS(flag, name) \ -static inline void \ -nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp) \ -{ \ - cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) | \ - (1UL << NILFS_CHECKPOINT_##flag)); \ -} \ -static inline void \ -nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp) \ -{ \ - cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) & \ - ~(1UL << NILFS_CHECKPOINT_##flag)); \ -} \ -static inline int \ -nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ -{ \ - return !!(le32_to_cpu(cp->cp_flags) & \ - (1UL << NILFS_CHECKPOINT_##flag)); \ -} - -NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot) -NILFS_CHECKPOINT_FNS(INVALID, invalid) -NILFS_CHECKPOINT_FNS(MINOR, minor) - -/** - * struct nilfs_cpinfo - checkpoint information - * @ci_flags: flags - * @ci_pad: padding - * @ci_cno: checkpoint number - * @ci_create: creation timestamp - * @ci_nblk_inc: number of blocks incremented by this checkpoint - * @ci_inodes_count: inodes count - * @ci_blocks_count: blocks count - * @ci_next: next checkpoint number in snapshot list - */ -struct nilfs_cpinfo { - __u32 ci_flags; - __u32 ci_pad; - __u64 ci_cno; - __u64 ci_create; - __u64 ci_nblk_inc; - __u64 ci_inodes_count; - __u64 ci_blocks_count; - __u64 ci_next; -}; - -#define NILFS_CPINFO_FNS(flag, name) \ -static inline int \ -nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo) \ -{ \ - return !!(cpinfo->ci_flags & (1UL << NILFS_CHECKPOINT_##flag)); \ -} - -NILFS_CPINFO_FNS(SNAPSHOT, snapshot) -NILFS_CPINFO_FNS(INVALID, invalid) -NILFS_CPINFO_FNS(MINOR, minor) - - -/** - * struct nilfs_cpfile_header - checkpoint file header - * @ch_ncheckpoints: number of checkpoints - * @ch_nsnapshots: number of snapshots - * @ch_snapshot_list: snapshot list - */ -struct nilfs_cpfile_header { - __le64 ch_ncheckpoints; - __le64 ch_nsnapshots; - struct nilfs_snapshot_list ch_snapshot_list; -}; - -#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET \ - ((sizeof(struct nilfs_cpfile_header) + \ - sizeof(struct nilfs_checkpoint) - 1) / \ - sizeof(struct nilfs_checkpoint)) - -/** - * struct nilfs_segment_usage - segment usage - * @su_lastmod: last modified timestamp - * @su_nblocks: number of blocks in segment - * @su_flags: flags - */ -struct nilfs_segment_usage { - __le64 su_lastmod; - __le32 su_nblocks; - __le32 su_flags; -}; - -#define NILFS_MIN_SEGMENT_USAGE_SIZE 16 - -/* segment usage flag */ -enum { - NILFS_SEGMENT_USAGE_ACTIVE, - NILFS_SEGMENT_USAGE_DIRTY, - NILFS_SEGMENT_USAGE_ERROR, - - /* ... */ -}; - -#define NILFS_SEGMENT_USAGE_FNS(flag, name) \ -static inline void \ -nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su) \ -{ \ - su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) | \ - (1UL << NILFS_SEGMENT_USAGE_##flag));\ -} \ -static inline void \ -nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su) \ -{ \ - su->su_flags = \ - cpu_to_le32(le32_to_cpu(su->su_flags) & \ - ~(1UL << NILFS_SEGMENT_USAGE_##flag)); \ -} \ -static inline int \ -nilfs_segment_usage_##name(const struct nilfs_segment_usage *su) \ -{ \ - return !!(le32_to_cpu(su->su_flags) & \ - (1UL << NILFS_SEGMENT_USAGE_##flag)); \ -} - -NILFS_SEGMENT_USAGE_FNS(ACTIVE, active) -NILFS_SEGMENT_USAGE_FNS(DIRTY, dirty) -NILFS_SEGMENT_USAGE_FNS(ERROR, error) - -static inline void -nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su) -{ - su->su_lastmod = cpu_to_le64(0); - su->su_nblocks = cpu_to_le32(0); - su->su_flags = cpu_to_le32(0); -} - -static inline int -nilfs_segment_usage_clean(const struct nilfs_segment_usage *su) -{ - return !le32_to_cpu(su->su_flags); -} - -/** - * struct nilfs_sufile_header - segment usage file header - * @sh_ncleansegs: number of clean segments - * @sh_ndirtysegs: number of dirty segments - * @sh_last_alloc: last allocated segment number - */ -struct nilfs_sufile_header { - __le64 sh_ncleansegs; - __le64 sh_ndirtysegs; - __le64 sh_last_alloc; - /* ... */ -}; - -#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET \ - ((sizeof(struct nilfs_sufile_header) + \ - sizeof(struct nilfs_segment_usage) - 1) / \ - sizeof(struct nilfs_segment_usage)) - -/** - * nilfs_suinfo - segment usage information - * @sui_lastmod: timestamp of last modification - * @sui_nblocks: number of written blocks in segment - * @sui_flags: segment usage flags - */ -struct nilfs_suinfo { - __u64 sui_lastmod; - __u32 sui_nblocks; - __u32 sui_flags; -}; - -#define NILFS_SUINFO_FNS(flag, name) \ -static inline int \ -nilfs_suinfo_##name(const struct nilfs_suinfo *si) \ -{ \ - return si->sui_flags & (1UL << NILFS_SEGMENT_USAGE_##flag); \ -} - -NILFS_SUINFO_FNS(ACTIVE, active) -NILFS_SUINFO_FNS(DIRTY, dirty) -NILFS_SUINFO_FNS(ERROR, error) - -static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si) -{ - return !si->sui_flags; -} - -/* ioctl */ -/** - * nilfs_suinfo_update - segment usage information update - * @sup_segnum: segment number - * @sup_flags: flags for which fields are active in sup_sui - * @sup_reserved: reserved necessary for alignment - * @sup_sui: segment usage information - */ -struct nilfs_suinfo_update { - __u64 sup_segnum; - __u32 sup_flags; - __u32 sup_reserved; - struct nilfs_suinfo sup_sui; -}; - -enum { - NILFS_SUINFO_UPDATE_LASTMOD, - NILFS_SUINFO_UPDATE_NBLOCKS, - NILFS_SUINFO_UPDATE_FLAGS, - __NR_NILFS_SUINFO_UPDATE_FIELDS, -}; - -#define NILFS_SUINFO_UPDATE_FNS(flag, name) \ -static inline void \ -nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup) \ -{ \ - sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag; \ -} \ -static inline void \ -nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup) \ -{ \ - sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag); \ -} \ -static inline int \ -nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup) \ -{ \ - return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\ -} - -NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod) -NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks) -NILFS_SUINFO_UPDATE_FNS(FLAGS, flags) - -enum { - NILFS_CHECKPOINT, - NILFS_SNAPSHOT, -}; - -/** - * struct nilfs_cpmode - change checkpoint mode structure - * @cm_cno: checkpoint number - * @cm_mode: mode of checkpoint - * @cm_pad: padding - */ -struct nilfs_cpmode { - __u64 cm_cno; - __u32 cm_mode; - __u32 cm_pad; -}; - -/** - * struct nilfs_argv - argument vector - * @v_base: pointer on data array from userspace - * @v_nmembs: number of members in data array - * @v_size: size of data array in bytes - * @v_flags: flags - * @v_index: start number of target data items - */ -struct nilfs_argv { - __u64 v_base; - __u32 v_nmembs; /* number of members */ - __u16 v_size; /* size of members */ - __u16 v_flags; - __u64 v_index; -}; - -/** - * struct nilfs_period - period of checkpoint numbers - * @p_start: start checkpoint number (inclusive) - * @p_end: end checkpoint number (exclusive) - */ -struct nilfs_period { - __u64 p_start; - __u64 p_end; -}; - -/** - * struct nilfs_cpstat - checkpoint statistics - * @cs_cno: checkpoint number - * @cs_ncps: number of checkpoints - * @cs_nsss: number of snapshots - */ -struct nilfs_cpstat { - __u64 cs_cno; - __u64 cs_ncps; - __u64 cs_nsss; -}; - -/** - * struct nilfs_sustat - segment usage statistics - * @ss_nsegs: number of segments - * @ss_ncleansegs: number of clean segments - * @ss_ndirtysegs: number of dirty segments - * @ss_ctime: creation time of the last segment - * @ss_nongc_ctime: creation time of the last segment not for GC - * @ss_prot_seq: least sequence number of segments which must not be reclaimed - */ -struct nilfs_sustat { - __u64 ss_nsegs; - __u64 ss_ncleansegs; - __u64 ss_ndirtysegs; - __u64 ss_ctime; - __u64 ss_nongc_ctime; - __u64 ss_prot_seq; -}; - -/** - * struct nilfs_vinfo - virtual block number information - * @vi_vblocknr: virtual block number - * @vi_start: start checkpoint number (inclusive) - * @vi_end: end checkpoint number (exclusive) - * @vi_blocknr: disk block number - */ -struct nilfs_vinfo { - __u64 vi_vblocknr; - __u64 vi_start; - __u64 vi_end; - __u64 vi_blocknr; -}; - -/** - * struct nilfs_vdesc - descriptor of virtual block number - * @vd_ino: inode number - * @vd_cno: checkpoint number - * @vd_vblocknr: virtual block number - * @vd_period: period of checkpoint numbers - * @vd_blocknr: disk block number - * @vd_offset: logical block offset inside a file - * @vd_flags: flags (data or node block) - * @vd_pad: padding - */ -struct nilfs_vdesc { - __u64 vd_ino; - __u64 vd_cno; - __u64 vd_vblocknr; - struct nilfs_period vd_period; - __u64 vd_blocknr; - __u64 vd_offset; - __u32 vd_flags; - __u32 vd_pad; -}; - -/** - * struct nilfs_bdesc - descriptor of disk block number - * @bd_ino: inode number - * @bd_oblocknr: disk block address (for skipping dead blocks) - * @bd_blocknr: disk block address - * @bd_offset: logical block offset inside a file - * @bd_level: level in the b-tree organization - * @bd_pad: padding - */ -struct nilfs_bdesc { - __u64 bd_ino; - __u64 bd_oblocknr; - __u64 bd_blocknr; - __u64 bd_offset; - __u32 bd_level; - __u32 bd_pad; -}; - -#define NILFS_IOCTL_IDENT 'n' - -#define NILFS_IOCTL_CHANGE_CPMODE \ - _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode) -#define NILFS_IOCTL_DELETE_CHECKPOINT \ - _IOW(NILFS_IOCTL_IDENT, 0x81, __u64) -#define NILFS_IOCTL_GET_CPINFO \ - _IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv) -#define NILFS_IOCTL_GET_CPSTAT \ - _IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat) -#define NILFS_IOCTL_GET_SUINFO \ - _IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv) -#define NILFS_IOCTL_GET_SUSTAT \ - _IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat) -#define NILFS_IOCTL_GET_VINFO \ - _IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv) -#define NILFS_IOCTL_GET_BDESCS \ - _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv) -#define NILFS_IOCTL_CLEAN_SEGMENTS \ - _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5]) -#define NILFS_IOCTL_SYNC \ - _IOR(NILFS_IOCTL_IDENT, 0x8A, __u64) -#define NILFS_IOCTL_RESIZE \ - _IOW(NILFS_IOCTL_IDENT, 0x8B, __u64) -#define NILFS_IOCTL_SET_ALLOC_RANGE \ - _IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2]) -#define NILFS_IOCTL_SET_SUINFO \ - _IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv) - -#endif /* _LINUX_NILFS_FS_H */ diff --git a/include/uapi/linux/nilfs2_api.h b/include/uapi/linux/nilfs2_api.h new file mode 100644 index 000000000000..ef4c1de89b11 --- /dev/null +++ b/include/uapi/linux/nilfs2_api.h @@ -0,0 +1,292 @@ +/* + * nilfs2_api.h - NILFS2 user space API + * + * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as published + * by the Free Software Foundation; either version 2.1 of the License, or + * (at your option) any later version. + */ + +#ifndef _LINUX_NILFS2_API_H +#define _LINUX_NILFS2_API_H + +#include +#include + +/** + * struct nilfs_cpinfo - checkpoint information + * @ci_flags: flags + * @ci_pad: padding + * @ci_cno: checkpoint number + * @ci_create: creation timestamp + * @ci_nblk_inc: number of blocks incremented by this checkpoint + * @ci_inodes_count: inodes count + * @ci_blocks_count: blocks count + * @ci_next: next checkpoint number in snapshot list + */ +struct nilfs_cpinfo { + __u32 ci_flags; + __u32 ci_pad; + __u64 ci_cno; + __u64 ci_create; + __u64 ci_nblk_inc; + __u64 ci_inodes_count; + __u64 ci_blocks_count; + __u64 ci_next; +}; + +/* checkpoint flags */ +enum { + NILFS_CPINFO_SNAPSHOT, + NILFS_CPINFO_INVALID, + NILFS_CPINFO_SKETCH, + NILFS_CPINFO_MINOR, +}; + +#define NILFS_CPINFO_FNS(flag, name) \ +static inline int \ +nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo) \ +{ \ + return !!(cpinfo->ci_flags & (1UL << NILFS_CPINFO_##flag)); \ +} + +NILFS_CPINFO_FNS(SNAPSHOT, snapshot) +NILFS_CPINFO_FNS(INVALID, invalid) +NILFS_CPINFO_FNS(MINOR, minor) + +/** + * nilfs_suinfo - segment usage information + * @sui_lastmod: timestamp of last modification + * @sui_nblocks: number of written blocks in segment + * @sui_flags: segment usage flags + */ +struct nilfs_suinfo { + __u64 sui_lastmod; + __u32 sui_nblocks; + __u32 sui_flags; +}; + +/* segment usage flags */ +enum { + NILFS_SUINFO_ACTIVE, + NILFS_SUINFO_DIRTY, + NILFS_SUINFO_ERROR, +}; + +#define NILFS_SUINFO_FNS(flag, name) \ +static inline int \ +nilfs_suinfo_##name(const struct nilfs_suinfo *si) \ +{ \ + return si->sui_flags & (1UL << NILFS_SUINFO_##flag); \ +} + +NILFS_SUINFO_FNS(ACTIVE, active) +NILFS_SUINFO_FNS(DIRTY, dirty) +NILFS_SUINFO_FNS(ERROR, error) + +static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si) +{ + return !si->sui_flags; +} + +/** + * nilfs_suinfo_update - segment usage information update + * @sup_segnum: segment number + * @sup_flags: flags for which fields are active in sup_sui + * @sup_reserved: reserved necessary for alignment + * @sup_sui: segment usage information + */ +struct nilfs_suinfo_update { + __u64 sup_segnum; + __u32 sup_flags; + __u32 sup_reserved; + struct nilfs_suinfo sup_sui; +}; + +enum { + NILFS_SUINFO_UPDATE_LASTMOD, + NILFS_SUINFO_UPDATE_NBLOCKS, + NILFS_SUINFO_UPDATE_FLAGS, + __NR_NILFS_SUINFO_UPDATE_FIELDS, +}; + +#define NILFS_SUINFO_UPDATE_FNS(flag, name) \ +static inline void \ +nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup) \ +{ \ + sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag; \ +} \ +static inline void \ +nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup) \ +{ \ + sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag); \ +} \ +static inline int \ +nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup) \ +{ \ + return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\ +} + +NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod) +NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks) +NILFS_SUINFO_UPDATE_FNS(FLAGS, flags) + +enum { + NILFS_CHECKPOINT, + NILFS_SNAPSHOT, +}; + +/** + * struct nilfs_cpmode - change checkpoint mode structure + * @cm_cno: checkpoint number + * @cm_mode: mode of checkpoint + * @cm_pad: padding + */ +struct nilfs_cpmode { + __u64 cm_cno; + __u32 cm_mode; + __u32 cm_pad; +}; + +/** + * struct nilfs_argv - argument vector + * @v_base: pointer on data array from userspace + * @v_nmembs: number of members in data array + * @v_size: size of data array in bytes + * @v_flags: flags + * @v_index: start number of target data items + */ +struct nilfs_argv { + __u64 v_base; + __u32 v_nmembs; /* number of members */ + __u16 v_size; /* size of members */ + __u16 v_flags; + __u64 v_index; +}; + +/** + * struct nilfs_period - period of checkpoint numbers + * @p_start: start checkpoint number (inclusive) + * @p_end: end checkpoint number (exclusive) + */ +struct nilfs_period { + __u64 p_start; + __u64 p_end; +}; + +/** + * struct nilfs_cpstat - checkpoint statistics + * @cs_cno: checkpoint number + * @cs_ncps: number of checkpoints + * @cs_nsss: number of snapshots + */ +struct nilfs_cpstat { + __u64 cs_cno; + __u64 cs_ncps; + __u64 cs_nsss; +}; + +/** + * struct nilfs_sustat - segment usage statistics + * @ss_nsegs: number of segments + * @ss_ncleansegs: number of clean segments + * @ss_ndirtysegs: number of dirty segments + * @ss_ctime: creation time of the last segment + * @ss_nongc_ctime: creation time of the last segment not for GC + * @ss_prot_seq: least sequence number of segments which must not be reclaimed + */ +struct nilfs_sustat { + __u64 ss_nsegs; + __u64 ss_ncleansegs; + __u64 ss_ndirtysegs; + __u64 ss_ctime; + __u64 ss_nongc_ctime; + __u64 ss_prot_seq; +}; + +/** + * struct nilfs_vinfo - virtual block number information + * @vi_vblocknr: virtual block number + * @vi_start: start checkpoint number (inclusive) + * @vi_end: end checkpoint number (exclusive) + * @vi_blocknr: disk block number + */ +struct nilfs_vinfo { + __u64 vi_vblocknr; + __u64 vi_start; + __u64 vi_end; + __u64 vi_blocknr; +}; + +/** + * struct nilfs_vdesc - descriptor of virtual block number + * @vd_ino: inode number + * @vd_cno: checkpoint number + * @vd_vblocknr: virtual block number + * @vd_period: period of checkpoint numbers + * @vd_blocknr: disk block number + * @vd_offset: logical block offset inside a file + * @vd_flags: flags (data or node block) + * @vd_pad: padding + */ +struct nilfs_vdesc { + __u64 vd_ino; + __u64 vd_cno; + __u64 vd_vblocknr; + struct nilfs_period vd_period; + __u64 vd_blocknr; + __u64 vd_offset; + __u32 vd_flags; + __u32 vd_pad; +}; + +/** + * struct nilfs_bdesc - descriptor of disk block number + * @bd_ino: inode number + * @bd_oblocknr: disk block address (for skipping dead blocks) + * @bd_blocknr: disk block address + * @bd_offset: logical block offset inside a file + * @bd_level: level in the b-tree organization + * @bd_pad: padding + */ +struct nilfs_bdesc { + __u64 bd_ino; + __u64 bd_oblocknr; + __u64 bd_blocknr; + __u64 bd_offset; + __u32 bd_level; + __u32 bd_pad; +}; + +#define NILFS_IOCTL_IDENT 'n' + +#define NILFS_IOCTL_CHANGE_CPMODE \ + _IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode) +#define NILFS_IOCTL_DELETE_CHECKPOINT \ + _IOW(NILFS_IOCTL_IDENT, 0x81, __u64) +#define NILFS_IOCTL_GET_CPINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv) +#define NILFS_IOCTL_GET_CPSTAT \ + _IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat) +#define NILFS_IOCTL_GET_SUINFO \ + _IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv) +#define NILFS_IOCTL_GET_SUSTAT \ + _IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat) +#define NILFS_IOCTL_GET_VINFO \ + _IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv) +#define NILFS_IOCTL_GET_BDESCS \ + _IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv) +#define NILFS_IOCTL_CLEAN_SEGMENTS \ + _IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5]) +#define NILFS_IOCTL_SYNC \ + _IOR(NILFS_IOCTL_IDENT, 0x8A, __u64) +#define NILFS_IOCTL_RESIZE \ + _IOW(NILFS_IOCTL_IDENT, 0x8B, __u64) +#define NILFS_IOCTL_SET_ALLOC_RANGE \ + _IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2]) +#define NILFS_IOCTL_SET_SUINFO \ + _IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv) + +#endif /* _LINUX_NILFS2_API_H */ diff --git a/include/uapi/linux/nilfs2_ondisk.h b/include/uapi/linux/nilfs2_ondisk.h new file mode 100644 index 000000000000..2a8a3addb675 --- /dev/null +++ b/include/uapi/linux/nilfs2_ondisk.h @@ -0,0 +1,650 @@ +/* + * nilfs2_ondisk.h - NILFS2 on-disk structures + * + * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as published + * by the Free Software Foundation; either version 2.1 of the License, or + * (at your option) any later version. + */ +/* + * linux/include/linux/ext2_fs.h + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +#ifndef _LINUX_NILFS2_ONDISK_H +#define _LINUX_NILFS2_ONDISK_H + +#include +#include + + +#define NILFS_INODE_BMAP_SIZE 7 + +/** + * struct nilfs_inode - structure of an inode on disk + * @i_blocks: blocks count + * @i_size: size in bytes + * @i_ctime: creation time (seconds) + * @i_mtime: modification time (seconds) + * @i_ctime_nsec: creation time (nano seconds) + * @i_mtime_nsec: modification time (nano seconds) + * @i_uid: user id + * @i_gid: group id + * @i_mode: file mode + * @i_links_count: links count + * @i_flags: file flags + * @i_bmap: block mapping + * @i_xattr: extended attributes + * @i_generation: file generation (for NFS) + * @i_pad: padding + */ +struct nilfs_inode { + __le64 i_blocks; + __le64 i_size; + __le64 i_ctime; + __le64 i_mtime; + __le32 i_ctime_nsec; + __le32 i_mtime_nsec; + __le32 i_uid; + __le32 i_gid; + __le16 i_mode; + __le16 i_links_count; + __le32 i_flags; + __le64 i_bmap[NILFS_INODE_BMAP_SIZE]; +#define i_device_code i_bmap[0] + __le64 i_xattr; + __le32 i_generation; + __le32 i_pad; +}; + +#define NILFS_MIN_INODE_SIZE 128 + +/** + * struct nilfs_super_root - structure of super root + * @sr_sum: check sum + * @sr_bytes: byte count of the structure + * @sr_flags: flags (reserved) + * @sr_nongc_ctime: write time of the last segment not for cleaner operation + * @sr_dat: DAT file inode + * @sr_cpfile: checkpoint file inode + * @sr_sufile: segment usage file inode + */ +struct nilfs_super_root { + __le32 sr_sum; + __le16 sr_bytes; + __le16 sr_flags; + __le64 sr_nongc_ctime; + struct nilfs_inode sr_dat; + struct nilfs_inode sr_cpfile; + struct nilfs_inode sr_sufile; +}; + +#define NILFS_SR_MDT_OFFSET(inode_size, i) \ + ((unsigned long)&((struct nilfs_super_root *)0)->sr_dat + \ + (inode_size) * (i)) +#define NILFS_SR_DAT_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 0) +#define NILFS_SR_CPFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 1) +#define NILFS_SR_SUFILE_OFFSET(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 2) +#define NILFS_SR_BYTES(inode_size) NILFS_SR_MDT_OFFSET(inode_size, 3) + +/* + * Maximal mount counts + */ +#define NILFS_DFL_MAX_MNT_COUNT 50 /* 50 mounts */ + +/* + * File system states (sbp->s_state, nilfs->ns_mount_state) + */ +#define NILFS_VALID_FS 0x0001 /* Unmounted cleanly */ +#define NILFS_ERROR_FS 0x0002 /* Errors detected */ +#define NILFS_RESIZE_FS 0x0004 /* Resize required */ + +/* + * Mount flags (sbi->s_mount_opt) + */ +#define NILFS_MOUNT_ERROR_MODE 0x0070 /* Error mode mask */ +#define NILFS_MOUNT_ERRORS_CONT 0x0010 /* Continue on errors */ +#define NILFS_MOUNT_ERRORS_RO 0x0020 /* Remount fs ro on errors */ +#define NILFS_MOUNT_ERRORS_PANIC 0x0040 /* Panic on errors */ +#define NILFS_MOUNT_BARRIER 0x1000 /* Use block barriers */ +#define NILFS_MOUNT_STRICT_ORDER 0x2000 /* + * Apply strict in-order + * semantics also for data + */ +#define NILFS_MOUNT_NORECOVERY 0x4000 /* + * Disable write access during + * mount-time recovery + */ +#define NILFS_MOUNT_DISCARD 0x8000 /* Issue DISCARD requests */ + + +/** + * struct nilfs_super_block - structure of super block on disk + */ +struct nilfs_super_block { +/*00*/ __le32 s_rev_level; /* Revision level */ + __le16 s_minor_rev_level; /* minor revision level */ + __le16 s_magic; /* Magic signature */ + + __le16 s_bytes; /* + * Bytes count of CRC calculation + * for this structure. s_reserved + * is excluded. + */ + __le16 s_flags; /* flags */ + __le32 s_crc_seed; /* Seed value of CRC calculation */ +/*10*/ __le32 s_sum; /* Check sum of super block */ + + __le32 s_log_block_size; /* + * Block size represented as follows + * blocksize = + * 1 << (s_log_block_size + 10) + */ + __le64 s_nsegments; /* Number of segments in filesystem */ +/*20*/ __le64 s_dev_size; /* block device size in bytes */ + __le64 s_first_data_block; /* 1st seg disk block number */ +/*30*/ __le32 s_blocks_per_segment; /* number of blocks per full segment */ + __le32 s_r_segments_percentage; /* Reserved segments percentage */ + + __le64 s_last_cno; /* Last checkpoint number */ +/*40*/ __le64 s_last_pseg; /* disk block addr pseg written last */ + __le64 s_last_seq; /* seq. number of seg written last */ +/*50*/ __le64 s_free_blocks_count; /* Free blocks count */ + + __le64 s_ctime; /* + * Creation time (execution time of + * newfs) + */ +/*60*/ __le64 s_mtime; /* Mount time */ + __le64 s_wtime; /* Write time */ +/*70*/ __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le64 s_lastcheck; /* time of last check */ + +/*80*/ __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + __le32 s_first_ino; /* First non-reserved inode */ + +/*90*/ __le16 s_inode_size; /* Size of an inode */ + __le16 s_dat_entry_size; /* Size of a dat entry */ + __le16 s_checkpoint_size; /* Size of a checkpoint */ + __le16 s_segment_usage_size; /* Size of a segment usage */ + +/*98*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ +/*A8*/ char s_volume_name[80]; /* volume name */ + +/*F8*/ __le32 s_c_interval; /* Commit interval of segment */ + __le32 s_c_block_max; /* + * Threshold of data amount for + * the segment construction + */ +/*100*/ __le64 s_feature_compat; /* Compatible feature set */ + __le64 s_feature_compat_ro; /* Read-only compatible feature set */ + __le64 s_feature_incompat; /* Incompatible feature set */ + __u32 s_reserved[186]; /* padding to the end of the block */ +}; + +/* + * Codes for operating systems + */ +#define NILFS_OS_LINUX 0 +/* Codes from 1 to 4 are reserved to keep compatibility with ext2 creator-OS */ + +/* + * Revision levels + */ +#define NILFS_CURRENT_REV 2 /* current major revision */ +#define NILFS_MINOR_REV 0 /* minor revision */ +#define NILFS_MIN_SUPP_REV 2 /* minimum supported revision */ + +/* + * Feature set definitions + * + * If there is a bit set in the incompatible feature set that the kernel + * doesn't know about, it should refuse to mount the filesystem. + */ +#define NILFS_FEATURE_COMPAT_RO_BLOCK_COUNT 0x00000001ULL + +#define NILFS_FEATURE_COMPAT_SUPP 0ULL +#define NILFS_FEATURE_COMPAT_RO_SUPP NILFS_FEATURE_COMPAT_RO_BLOCK_COUNT +#define NILFS_FEATURE_INCOMPAT_SUPP 0ULL + +/* + * Bytes count of super_block for CRC-calculation + */ +#define NILFS_SB_BYTES \ + ((long)&((struct nilfs_super_block *)0)->s_reserved) + +/* + * Special inode number + */ +#define NILFS_ROOT_INO 2 /* Root file inode */ +#define NILFS_DAT_INO 3 /* DAT file */ +#define NILFS_CPFILE_INO 4 /* checkpoint file */ +#define NILFS_SUFILE_INO 5 /* segment usage file */ +#define NILFS_IFILE_INO 6 /* ifile */ +#define NILFS_ATIME_INO 7 /* Atime file (reserved) */ +#define NILFS_XATTR_INO 8 /* Xattribute file (reserved) */ +#define NILFS_SKETCH_INO 10 /* Sketch file */ +#define NILFS_USER_INO 11 /* Fisrt user's file inode number */ + +#define NILFS_SB_OFFSET_BYTES 1024 /* byte offset of nilfs superblock */ + +#define NILFS_SEG_MIN_BLOCKS 16 /* + * Minimum number of blocks in + * a full segment + */ +#define NILFS_PSEG_MIN_BLOCKS 2 /* + * Minimum number of blocks in + * a partial segment + */ +#define NILFS_MIN_NRSVSEGS 8 /* + * Minimum number of reserved + * segments + */ + +/* + * We call DAT, cpfile, and sufile root metadata files. Inodes of + * these files are written in super root block instead of ifile, and + * garbage collector doesn't keep any past versions of these files. + */ +#define NILFS_ROOT_METADATA_FILE(ino) \ + ((ino) >= NILFS_DAT_INO && (ino) <= NILFS_SUFILE_INO) + +/* + * bytes offset of secondary super block + */ +#define NILFS_SB2_OFFSET_BYTES(devsize) ((((devsize) >> 12) - 1) << 12) + +/* + * Maximal count of links to a file + */ +#define NILFS_LINK_MAX 32000 + +/* + * Structure of a directory entry + * (Same as ext2) + */ + +#define NILFS_NAME_LEN 255 + +/* + * Block size limitations + */ +#define NILFS_MIN_BLOCK_SIZE 1024 +#define NILFS_MAX_BLOCK_SIZE 65536 + +/* + * The new version of the directory entry. Since V0 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct nilfs_dir_entry { + __le64 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; /* Dir entry type (file, dir, etc) */ + char name[NILFS_NAME_LEN]; /* File name */ + char pad; +}; + +/* + * NILFS directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +enum { + NILFS_FT_UNKNOWN, + NILFS_FT_REG_FILE, + NILFS_FT_DIR, + NILFS_FT_CHRDEV, + NILFS_FT_BLKDEV, + NILFS_FT_FIFO, + NILFS_FT_SOCK, + NILFS_FT_SYMLINK, + NILFS_FT_MAX +}; + +/* + * NILFS_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 8 + */ +#define NILFS_DIR_PAD 8 +#define NILFS_DIR_ROUND (NILFS_DIR_PAD - 1) +#define NILFS_DIR_REC_LEN(name_len) (((name_len) + 12 + NILFS_DIR_ROUND) & \ + ~NILFS_DIR_ROUND) +#define NILFS_MAX_REC_LEN ((1 << 16) - 1) + +/** + * struct nilfs_finfo - file information + * @fi_ino: inode number + * @fi_cno: checkpoint number + * @fi_nblocks: number of blocks (including intermediate blocks) + * @fi_ndatablk: number of file data blocks + */ +struct nilfs_finfo { + __le64 fi_ino; + __le64 fi_cno; + __le32 fi_nblocks; + __le32 fi_ndatablk; +}; + +/** + * struct nilfs_binfo_v - information on a data block (except DAT) + * @bi_vblocknr: virtual block number + * @bi_blkoff: block offset + */ +struct nilfs_binfo_v { + __le64 bi_vblocknr; + __le64 bi_blkoff; +}; + +/** + * struct nilfs_binfo_dat - information on a DAT node block + * @bi_blkoff: block offset + * @bi_level: level + * @bi_pad: padding + */ +struct nilfs_binfo_dat { + __le64 bi_blkoff; + __u8 bi_level; + __u8 bi_pad[7]; +}; + +/** + * union nilfs_binfo: block information + * @bi_v: nilfs_binfo_v structure + * @bi_dat: nilfs_binfo_dat structure + */ +union nilfs_binfo { + struct nilfs_binfo_v bi_v; + struct nilfs_binfo_dat bi_dat; +}; + +/** + * struct nilfs_segment_summary - segment summary header + * @ss_datasum: checksum of data + * @ss_sumsum: checksum of segment summary + * @ss_magic: magic number + * @ss_bytes: size of this structure in bytes + * @ss_flags: flags + * @ss_seq: sequence number + * @ss_create: creation timestamp + * @ss_next: next segment + * @ss_nblocks: number of blocks + * @ss_nfinfo: number of finfo structures + * @ss_sumbytes: total size of segment summary in bytes + * @ss_pad: padding + * @ss_cno: checkpoint number + */ +struct nilfs_segment_summary { + __le32 ss_datasum; + __le32 ss_sumsum; + __le32 ss_magic; + __le16 ss_bytes; + __le16 ss_flags; + __le64 ss_seq; + __le64 ss_create; + __le64 ss_next; + __le32 ss_nblocks; + __le32 ss_nfinfo; + __le32 ss_sumbytes; + __le32 ss_pad; + __le64 ss_cno; + /* array of finfo structures */ +}; + +#define NILFS_SEGSUM_MAGIC 0x1eaffa11 /* segment summary magic number */ + +/* + * Segment summary flags + */ +#define NILFS_SS_LOGBGN 0x0001 /* begins a logical segment */ +#define NILFS_SS_LOGEND 0x0002 /* ends a logical segment */ +#define NILFS_SS_SR 0x0004 /* has super root */ +#define NILFS_SS_SYNDT 0x0008 /* includes data only updates */ +#define NILFS_SS_GC 0x0010 /* segment written for cleaner operation */ + +/** + * struct nilfs_btree_node - header of B-tree node block + * @bn_flags: flags + * @bn_level: level + * @bn_nchildren: number of children + * @bn_pad: padding + */ +struct nilfs_btree_node { + __u8 bn_flags; + __u8 bn_level; + __le16 bn_nchildren; + __le32 bn_pad; +}; + +/* flags */ +#define NILFS_BTREE_NODE_ROOT 0x01 + +/* level */ +#define NILFS_BTREE_LEVEL_DATA 0 +#define NILFS_BTREE_LEVEL_NODE_MIN (NILFS_BTREE_LEVEL_DATA + 1) +#define NILFS_BTREE_LEVEL_MAX 14 /* Max level (exclusive) */ + +/** + * struct nilfs_direct_node - header of built-in bmap array + * @dn_flags: flags + * @dn_pad: padding + */ +struct nilfs_direct_node { + __u8 dn_flags; + __u8 pad[7]; +}; + +/** + * struct nilfs_palloc_group_desc - block group descriptor + * @pg_nfrees: number of free entries in block group + */ +struct nilfs_palloc_group_desc { + __le32 pg_nfrees; +}; + +/** + * struct nilfs_dat_entry - disk address translation entry + * @de_blocknr: block number + * @de_start: start checkpoint number + * @de_end: end checkpoint number + * @de_rsv: reserved for future use + */ +struct nilfs_dat_entry { + __le64 de_blocknr; + __le64 de_start; + __le64 de_end; + __le64 de_rsv; +}; + +#define NILFS_MIN_DAT_ENTRY_SIZE 32 + +/** + * struct nilfs_snapshot_list - snapshot list + * @ssl_next: next checkpoint number on snapshot list + * @ssl_prev: previous checkpoint number on snapshot list + */ +struct nilfs_snapshot_list { + __le64 ssl_next; + __le64 ssl_prev; +}; + +/** + * struct nilfs_checkpoint - checkpoint structure + * @cp_flags: flags + * @cp_checkpoints_count: checkpoints count in a block + * @cp_snapshot_list: snapshot list + * @cp_cno: checkpoint number + * @cp_create: creation timestamp + * @cp_nblk_inc: number of blocks incremented by this checkpoint + * @cp_inodes_count: inodes count + * @cp_blocks_count: blocks count + * @cp_ifile_inode: inode of ifile + */ +struct nilfs_checkpoint { + __le32 cp_flags; + __le32 cp_checkpoints_count; + struct nilfs_snapshot_list cp_snapshot_list; + __le64 cp_cno; + __le64 cp_create; + __le64 cp_nblk_inc; + __le64 cp_inodes_count; + __le64 cp_blocks_count; + + /* + * Do not change the byte offset of ifile inode. + * To keep the compatibility of the disk format, + * additional fields should be added behind cp_ifile_inode. + */ + struct nilfs_inode cp_ifile_inode; +}; + +#define NILFS_MIN_CHECKPOINT_SIZE (64 + NILFS_MIN_INODE_SIZE) + +/* checkpoint flags */ +enum { + NILFS_CHECKPOINT_SNAPSHOT, + NILFS_CHECKPOINT_INVALID, + NILFS_CHECKPOINT_SKETCH, + NILFS_CHECKPOINT_MINOR, +}; + +#define NILFS_CHECKPOINT_FNS(flag, name) \ +static inline void \ +nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp) \ +{ \ + cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) | \ + (1UL << NILFS_CHECKPOINT_##flag)); \ +} \ +static inline void \ +nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp) \ +{ \ + cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) & \ + ~(1UL << NILFS_CHECKPOINT_##flag)); \ +} \ +static inline int \ +nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp) \ +{ \ + return !!(le32_to_cpu(cp->cp_flags) & \ + (1UL << NILFS_CHECKPOINT_##flag)); \ +} + +NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot) +NILFS_CHECKPOINT_FNS(INVALID, invalid) +NILFS_CHECKPOINT_FNS(MINOR, minor) + +/** + * struct nilfs_cpfile_header - checkpoint file header + * @ch_ncheckpoints: number of checkpoints + * @ch_nsnapshots: number of snapshots + * @ch_snapshot_list: snapshot list + */ +struct nilfs_cpfile_header { + __le64 ch_ncheckpoints; + __le64 ch_nsnapshots; + struct nilfs_snapshot_list ch_snapshot_list; +}; + +#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET \ + ((sizeof(struct nilfs_cpfile_header) + \ + sizeof(struct nilfs_checkpoint) - 1) / \ + sizeof(struct nilfs_checkpoint)) + +/** + * struct nilfs_segment_usage - segment usage + * @su_lastmod: last modified timestamp + * @su_nblocks: number of blocks in segment + * @su_flags: flags + */ +struct nilfs_segment_usage { + __le64 su_lastmod; + __le32 su_nblocks; + __le32 su_flags; +}; + +#define NILFS_MIN_SEGMENT_USAGE_SIZE 16 + +/* segment usage flag */ +enum { + NILFS_SEGMENT_USAGE_ACTIVE, + NILFS_SEGMENT_USAGE_DIRTY, + NILFS_SEGMENT_USAGE_ERROR, +}; + +#define NILFS_SEGMENT_USAGE_FNS(flag, name) \ +static inline void \ +nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su) \ +{ \ + su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) | \ + (1UL << NILFS_SEGMENT_USAGE_##flag));\ +} \ +static inline void \ +nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su) \ +{ \ + su->su_flags = \ + cpu_to_le32(le32_to_cpu(su->su_flags) & \ + ~(1UL << NILFS_SEGMENT_USAGE_##flag)); \ +} \ +static inline int \ +nilfs_segment_usage_##name(const struct nilfs_segment_usage *su) \ +{ \ + return !!(le32_to_cpu(su->su_flags) & \ + (1UL << NILFS_SEGMENT_USAGE_##flag)); \ +} + +NILFS_SEGMENT_USAGE_FNS(ACTIVE, active) +NILFS_SEGMENT_USAGE_FNS(DIRTY, dirty) +NILFS_SEGMENT_USAGE_FNS(ERROR, error) + +static inline void +nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su) +{ + su->su_lastmod = cpu_to_le64(0); + su->su_nblocks = cpu_to_le32(0); + su->su_flags = cpu_to_le32(0); +} + +static inline int +nilfs_segment_usage_clean(const struct nilfs_segment_usage *su) +{ + return !le32_to_cpu(su->su_flags); +} + +/** + * struct nilfs_sufile_header - segment usage file header + * @sh_ncleansegs: number of clean segments + * @sh_ndirtysegs: number of dirty segments + * @sh_last_alloc: last allocated segment number + */ +struct nilfs_sufile_header { + __le64 sh_ncleansegs; + __le64 sh_ndirtysegs; + __le64 sh_last_alloc; + /* ... */ +}; + +#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET \ + ((sizeof(struct nilfs_sufile_header) + \ + sizeof(struct nilfs_segment_usage) - 1) / \ + sizeof(struct nilfs_segment_usage)) + +#endif /* _LINUX_NILFS2_ONDISK_H */ -- cgit v1.2.3 From 7e7814180b334dff97ef8f56c7c40c277ad4531c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 2 Aug 2016 14:05:36 -0700 Subject: signal: consolidate {TS,TLF}_RESTORE_SIGMASK code In general, there's no need for the "restore sigmask" flag to live in ti->flags. alpha, ia64, microblaze, powerpc, sh, sparc (64-bit only), tile, and x86 use essentially identical alternative implementations, placing the flag in ti->status. Replace those optimized implementations with an equally good common implementation that stores it in a bitfield in struct task_struct and drop the custom implementations. Additional architectures can opt in by removing their TIF_RESTORE_SIGMASK defines. Link: http://lkml.kernel.org/r/8a14321d64a28e40adfddc90e18a96c086a6d6f9.1468522723.git.luto@kernel.org Signed-off-by: Andy Lutomirski Tested-by: Michael Ellerman [powerpc] Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Tony Luck Cc: Fenghua Yu Cc: Michal Simek Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Yoshinori Sato Cc: Rich Felker Cc: "David S. Miller" Cc: Chris Metcalf Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Brian Gerst Cc: Dmitry Safonov Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 63 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/thread_info.h | 41 ----------------------------- 2 files changed, 63 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 553af2923824..62c68e513e39 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1547,6 +1547,9 @@ struct task_struct { /* unserialized, strictly 'current' */ unsigned in_execve:1; /* bit to tell LSMs we're in execve */ unsigned in_iowait:1; +#if !defined(TIF_RESTORE_SIGMASK) + unsigned restore_sigmask:1; +#endif #ifdef CONFIG_MEMCG unsigned memcg_may_oom:1; #ifndef CONFIG_SLOB @@ -2680,6 +2683,66 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +#ifdef TIF_RESTORE_SIGMASK +/* + * Legacy restore_sigmask accessors. These are inefficient on + * SMP architectures because they require atomic operations. + */ + +/** + * set_restore_sigmask() - make sure saved_sigmask processing gets done + * + * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code + * will run before returning to user mode, to process the flag. For + * all callers, TIF_SIGPENDING is already set or it's no harm to set + * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the + * arch code will notice on return to user mode, in case those bits + * are scarce. We set TIF_SIGPENDING here to ensure that the arch + * signal code always gets run when TIF_RESTORE_SIGMASK is set. + */ +static inline void set_restore_sigmask(void) +{ + set_thread_flag(TIF_RESTORE_SIGMASK); + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + clear_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_restore_sigmask(void) +{ + return test_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_and_clear_restore_sigmask(void) +{ + return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); +} + +#else /* TIF_RESTORE_SIGMASK */ + +/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ +static inline void set_restore_sigmask(void) +{ + current->restore_sigmask = true; + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + current->restore_sigmask = false; +} +static inline bool test_restore_sigmask(void) +{ + return current->restore_sigmask; +} +static inline bool test_and_clear_restore_sigmask(void) +{ + if (!current->restore_sigmask) + return false; + current->restore_sigmask = false; + return true; +} +#endif + static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index b4c2a485b28a..352b1542f5cc 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -105,47 +105,6 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) -#if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK -/* - * An arch can define its own version of set_restore_sigmask() to get the - * job done however works, with or without TIF_RESTORE_SIGMASK. - */ -#define HAVE_SET_RESTORE_SIGMASK 1 - -/** - * set_restore_sigmask() - make sure saved_sigmask processing gets done - * - * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code - * will run before returning to user mode, to process the flag. For - * all callers, TIF_SIGPENDING is already set or it's no harm to set - * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the - * arch code will notice on return to user mode, in case those bits - * are scarce. We set TIF_SIGPENDING here to ensure that the arch - * signal code always gets run when TIF_RESTORE_SIGMASK is set. - */ -static inline void set_restore_sigmask(void) -{ - set_thread_flag(TIF_RESTORE_SIGMASK); - WARN_ON(!test_thread_flag(TIF_SIGPENDING)); -} -static inline void clear_restore_sigmask(void) -{ - clear_thread_flag(TIF_RESTORE_SIGMASK); -} -static inline bool test_restore_sigmask(void) -{ - return test_thread_flag(TIF_RESTORE_SIGMASK); -} -static inline bool test_and_clear_restore_sigmask(void) -{ - return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); -} -#endif /* TIF_RESTORE_SIGMASK && !HAVE_SET_RESTORE_SIGMASK */ - -#ifndef HAVE_SET_RESTORE_SIGMASK -#error "no set_restore_sigmask() provided and default one won't work" -#endif - #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From b06fb415331a7beb841f3d20d0fe60f6f0787dba Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 2 Aug 2016 14:05:42 -0700 Subject: cpumask: fix code comment Fix code comment for cpumask_parse(). Link: http://lkml.kernel.org/r/71aae2c60ae5dae0cf554199ce6aea8f88c69347.1465380581.git.geliangtang@gmail.com Signed-off-by: Geliang Tang Acked-by: Rusty Russell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index e828cf65d7df..da7fbf1cdd56 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -579,7 +579,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, } /** - * cpumask_parse - extract a cpumask from from a string + * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * -- cgit v1.2.3 From dc5cccacf4272da4aba20a1fc0804d59d985ab32 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 2 Aug 2016 14:05:54 -0700 Subject: kexec: don't invoke OOM-killer for control page allocation If we are unable to find a suitable page when allocating the control page, do not invoke the OOM-killer: killing processes probably isn't going to help. Link: http://lkml.kernel.org/r/E1b8ko9-0004HG-R5@rmk-PC.armlinux.org.uk Signed-off-by: Russell King Reviewed-by: Pratyush Anand Acked-by: Baoquan He Cc: Keerthy Cc: Vitaly Andrianov Cc: Eric Biederman Cc: Dave Young Cc: Vivek Goyal Cc: Simon Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index e8acb2b43dd9..ce2fe197f583 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -41,7 +41,7 @@ #endif #ifndef KEXEC_CONTROL_MEMORY_GFP -#define KEXEC_CONTROL_MEMORY_GFP GFP_KERNEL +#define KEXEC_CONTROL_MEMORY_GFP (GFP_KERNEL | __GFP_NORETRY) #endif #ifndef KEXEC_CONTROL_PAGE_SIZE -- cgit v1.2.3 From dae28018f56645b61f5beb84d5831346d3c5e457 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 2 Aug 2016 14:06:00 -0700 Subject: kdump: arrange for paddr_vmcoreinfo_note() to return phys_addr_t On PAE systems (eg, ARM LPAE) the vmcore note may be located above 4GB physical on 32-bit architectures, so we need a wider type than "unsigned long" here. Arrange for paddr_vmcoreinfo_note() to return a phys_addr_t, thereby allowing it to be located above 4GB. This makes no difference for kexec-tools, as they already assume a 64-bit type when reading from this file. Link: http://lkml.kernel.org/r/E1b8koK-0004HS-K9@rmk-PC.armlinux.org.uk Signed-off-by: Russell King Reviewed-by: Pratyush Anand Acked-by: Baoquan He Cc: Keerthy Cc: Vitaly Andrianov Cc: Eric Biederman Cc: Dave Young Cc: Vivek Goyal Cc: Simon Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index ce2fe197f583..555227f0029f 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -233,7 +233,7 @@ void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) void vmcoreinfo_append_str(const char *fmt, ...); -unsigned long paddr_vmcoreinfo_note(void); +phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_OSRELEASE(value) \ vmcoreinfo_append_str("OSRELEASE=%s\n", value) -- cgit v1.2.3 From 43546d8669d62d75fa69ca9a45d2f586665f56bd Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 2 Aug 2016 14:06:04 -0700 Subject: kexec: allow architectures to override boot mapping kexec physical addresses are the boot-time view of the system. For certain ARM systems (such as Keystone 2), the boot view of the system does not match the kernel's view of the system: the boot view uses a special alias in the lower 4GB of the physical address space. To cater for these kinds of setups, we need to translate between the boot view physical addresses and the normal kernel view physical addresses. This patch extracts the current transation points into linux/kexec.h, and allows an architecture to override the functions. Due to the translations required, we unfortunately end up with six translation functions, which are reduced down to four that the architecture can override. [akpm@linux-foundation.org: kexec.h needs asm/io.h for phys_to_virt()] Link: http://lkml.kernel.org/r/E1b8koP-0004HZ-Vf@rmk-PC.armlinux.org.uk Signed-off-by: Russell King Cc: Keerthy Cc: Pratyush Anand Cc: Vitaly Andrianov Cc: Eric Biederman Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Simon Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 555227f0029f..23e14a460cfb 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -14,6 +14,8 @@ #if !defined(__ASSEMBLY__) +#include + #include #ifdef CONFIG_KEXEC_CORE @@ -318,6 +320,44 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, void arch_kexec_protect_crashkres(void); void arch_kexec_unprotect_crashkres(void); +#ifndef page_to_boot_pfn +static inline unsigned long page_to_boot_pfn(struct page *page) +{ + return page_to_pfn(page); +} +#endif + +#ifndef boot_pfn_to_page +static inline struct page *boot_pfn_to_page(unsigned long boot_pfn) +{ + return pfn_to_page(boot_pfn); +} +#endif + +#ifndef phys_to_boot_phys +static inline unsigned long phys_to_boot_phys(phys_addr_t phys) +{ + return phys; +} +#endif + +#ifndef boot_phys_to_phys +static inline phys_addr_t boot_phys_to_phys(unsigned long boot_phys) +{ + return boot_phys; +} +#endif + +static inline unsigned long virt_to_boot_phys(void *addr) +{ + return phys_to_boot_phys(__pa((unsigned long)addr)); +} + +static inline void *boot_phys_to_virt(unsigned long entry) +{ + return phys_to_virt(boot_phys_to_phys(entry)); +} + #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; -- cgit v1.2.3 From 21db79e8bb054d0351a6b1b464f1c9c47a2e6e8d Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Tue, 2 Aug 2016 14:06:16 -0700 Subject: kexec: add a kexec_crash_loaded() function Provide a wrapper function to be used by kernel code to check whether a crash kernel is loaded. It returns the same value that can be seen in /sys/kernel/kexec_crash_loaded by userspace programs. I'm exporting the function, because it will be used by Xen, and it is possible to compile Xen modules separately to enable the use of PV drivers with unmodified bare-metal kernels. Link: http://lkml.kernel.org/r/20160713121955.14969.69080.stgit@hananiah.suse.cz Signed-off-by: Petr Tesarik Cc: Juergen Gross Cc: Josh Triplett Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Boris Ostrovsky Cc: "Paul E. McKenney" Cc: Dave Young Cc: David Vrabel Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 23e14a460cfb..d7437777baaa 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -230,6 +230,7 @@ extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); +int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); @@ -364,6 +365,7 @@ struct task_struct; static inline void __crash_kexec(struct pt_regs *regs) { } static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } +static inline int kexec_crash_loaded(void) { return 0; } #define kexec_in_progress false #endif /* CONFIG_KEXEC_CORE */ -- cgit v1.2.3 From b6e8d4aa1110306378af0f3472a6b85a1f039a16 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 2 Aug 2016 14:06:25 -0700 Subject: rapidio: add RapidIO channelized messaging driver Add channelized messaging driver to support native RapidIO messaging exchange between multiple senders/recipients on devices that use kernel RapidIO subsystem services. This device driver is the result of collaboration within the RapidIO.org Software Task Group (STG) between Texas Instruments, Prodrive Technologies, Nokia Networks, BAE and IDT. Additional input was received from other members of RapidIO.org. The objective was to create a character mode driver interface which exposes messaging capabilities of RapidIO endpoint devices (mports) directly to applications, in a manner that allows the numerous and varied RapidIO implementations to interoperate. This char mode device driver allows user-space applications to setup messaging communication channels using single shared RapidIO messaging mailbox. By default this driver uses RapidIO MBOX_1 (MBOX_0 is reserved for use by RIONET Ethernet emulation driver). [weiyj.lk@gmail.com: rapidio/rio_cm: fix return value check in riocm_init()] Link: http://lkml.kernel.org/r/1469198221-21970-1-git-send-email-alexandre.bounine@idt.com Link: http://lkml.kernel.org/r/1468952862-18056-1-git-send-email-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Tested-by: Barry Wood Cc: Matt Porter Cc: Aurelien Jacquiot Cc: Andre van Herk Cc: Barry Wood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/Kbuild | 1 + include/uapi/linux/rio_cm_cdev.h | 78 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+) create mode 100644 include/uapi/linux/rio_cm_cdev.h (limited to 'include') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 6d4e92ccdc91..c44747c0796a 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -357,6 +357,7 @@ header-y += reiserfs_fs.h header-y += reiserfs_xattr.h header-y += resource.h header-y += rfkill.h +header-y += rio_cm_cdev.h header-y += rio_mport_cdev.h header-y += romfs_fs.h header-y += rose.h diff --git a/include/uapi/linux/rio_cm_cdev.h b/include/uapi/linux/rio_cm_cdev.h new file mode 100644 index 000000000000..6edb900d318d --- /dev/null +++ b/include/uapi/linux/rio_cm_cdev.h @@ -0,0 +1,78 @@ +/* + * Copyright (c) 2015, Integrated Device Technology Inc. + * Copyright (c) 2015, Prodrive Technologies + * Copyright (c) 2015, RapidIO Trade Association + * All rights reserved. + * + * This software is available to you under a choice of one of two licenses. + * You may choose to be licensed under the terms of the GNU General Public + * License(GPL) Version 2, or the BSD-3 Clause license below: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright notice, + * this list of conditions and the following disclaimer. + * + * 2. Redistributions in binary form must reproduce the above copyright notice, + * this list of conditions and the following disclaimer in the documentation + * and/or other materials provided with the distribution. + * + * 3. Neither the name of the copyright holder nor the names of its contributors + * may be used to endorse or promote products derived from this software without + * specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, + * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR + * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, + * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, + * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; + * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, + * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR + * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF + * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _RIO_CM_CDEV_H_ +#define _RIO_CM_CDEV_H_ + +#include + +struct rio_cm_channel { + __u16 id; + __u16 remote_channel; + __u16 remote_destid; + __u8 mport_id; +}; + +struct rio_cm_msg { + __u16 ch_num; + __u16 size; + __u32 rxto; /* receive timeout in mSec. 0 = blocking */ + __u64 msg; +}; + +struct rio_cm_accept { + __u16 ch_num; + __u16 pad0; + __u32 wait_to; /* accept timeout in mSec. 0 = blocking */ +}; + +/* RapidIO Channelized Messaging Driver IOCTLs */ +#define RIO_CM_IOC_MAGIC 'c' + +#define RIO_CM_EP_GET_LIST_SIZE _IOWR(RIO_CM_IOC_MAGIC, 1, __u32) +#define RIO_CM_EP_GET_LIST _IOWR(RIO_CM_IOC_MAGIC, 2, __u32) +#define RIO_CM_CHAN_CREATE _IOWR(RIO_CM_IOC_MAGIC, 3, __u16) +#define RIO_CM_CHAN_CLOSE _IOW(RIO_CM_IOC_MAGIC, 4, __u16) +#define RIO_CM_CHAN_BIND _IOW(RIO_CM_IOC_MAGIC, 5, struct rio_cm_channel) +#define RIO_CM_CHAN_LISTEN _IOW(RIO_CM_IOC_MAGIC, 6, __u16) +#define RIO_CM_CHAN_ACCEPT _IOWR(RIO_CM_IOC_MAGIC, 7, struct rio_cm_accept) +#define RIO_CM_CHAN_CONNECT _IOW(RIO_CM_IOC_MAGIC, 8, struct rio_cm_channel) +#define RIO_CM_CHAN_SEND _IOW(RIO_CM_IOC_MAGIC, 9, struct rio_cm_msg) +#define RIO_CM_CHAN_RECEIVE _IOWR(RIO_CM_IOC_MAGIC, 10, struct rio_cm_msg) +#define RIO_CM_MPORT_GET_LIST _IOWR(RIO_CM_IOC_MAGIC, 11, __u32) + +#endif /* _RIO_CM_CDEV_H_ */ -- cgit v1.2.3 From a057a52e94e15d89be8af557584e0144a496b6c6 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 2 Aug 2016 14:06:54 -0700 Subject: rapidio: change inbound window size type to u64 Current definition of map_inb() mport operations callback uses u32 type to specify required inbound window (IBW) size. This is limiting factor because existing hardware - tsi721 and fsl_rio, both support IBW size up to 16GB. Changing type of size parameter to u64 to allow IBW size configurations larger than 4GB. [alexandre.bounine@idt.com: remove compiler warning about size of constant] Link: http://lkml.kernel.org/r/20160802184856.2566-1-alexandre.bounine@idt.com Link: http://lkml.kernel.org/r/1469125134-16523-11-git-send-email-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Cc: Matt Porter Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Andre van Herk Cc: Barry Wood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index aa2323893e8d..f7ec35b48800 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -425,7 +425,7 @@ struct rio_ops { int (*add_inb_buffer)(struct rio_mport *mport, int mbox, void *buf); void *(*get_inb_message)(struct rio_mport *mport, int mbox); int (*map_inb)(struct rio_mport *mport, dma_addr_t lstart, - u64 rstart, u32 size, u32 flags); + u64 rstart, u64 size, u32 flags); void (*unmap_inb)(struct rio_mport *mport, dma_addr_t lstart); int (*query_mport)(struct rio_mport *mport, struct rio_mport_attr *attr); -- cgit v1.2.3 From 1ae842de1dd8051cbb65b396b6f029d07f992641 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 2 Aug 2016 14:06:57 -0700 Subject: rapidio: modify for rev.3 specification changes Implement changes made in RapidIO specification rev.3 to LP-Serial Physical Layer register definitions: - use per-port register offset calculations based on LP-Serial Extended Features Block (EFB) Register Map type (I or II) with different per-port offset step (0x20 vs 0x40 respectfully). - remove deprecated Parallel Physical layer definitions and related code. [alexandre.bounine@idt.com: fix DocBook warning for gen3 update] Link: http://lkml.kernel.org/r/1469191173-19338-1-git-send-email-alexandre.bounine@idt.com Link: http://lkml.kernel.org/r/1469125134-16523-12-git-send-email-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Tested-by: Barry Wood Cc: Matt Porter Cc: Andre van Herk Cc: Barry Wood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 11 ++-- include/linux/rio_regs.h | 167 +++++++++++++++++++++++++++++++++++++---------- 2 files changed, 136 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index f7ec35b48800..37b95c4af99d 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -163,6 +163,7 @@ enum rio_device_state { * @dst_ops: Destination operation capabilities * @comp_tag: RIO component tag * @phys_efptr: RIO device extended features pointer + * @phys_rmap: LP-Serial Register Map Type (1 or 2) * @em_efptr: RIO Error Management features pointer * @dma_mask: Mask of bits of RIO address this device implements * @driver: Driver claiming this device @@ -193,6 +194,7 @@ struct rio_dev { u32 dst_ops; u32 comp_tag; u32 phys_efptr; + u32 phys_rmap; u32 em_efptr; u64 dma_mask; struct rio_driver *driver; /* RIO driver claiming this device */ @@ -237,11 +239,6 @@ struct rio_dbell { void *dev_id; }; -enum rio_phy_type { - RIO_PHY_PARALLEL, - RIO_PHY_SERIAL, -}; - /** * struct rio_mport - RIO master port info * @dbells: List of doorbell events @@ -259,8 +256,8 @@ enum rio_phy_type { * @id: Port ID, unique among all ports * @index: Port index, unique among all port interfaces of the same type * @sys_size: RapidIO common transport system size - * @phy_type: RapidIO phy type * @phys_efptr: RIO port extended features pointer + * @phys_rmap: LP-Serial EFB Register Mapping type (1 or 2). * @name: Port name string * @dev: device structure associated with an mport * @priv: Master port private data @@ -289,8 +286,8 @@ struct rio_mport { * 0 - Small size. 256 devices. * 1 - Large size, 65536 devices. */ - enum rio_phy_type phy_type; /* RapidIO phy type */ u32 phys_efptr; + u32 phys_rmap; unsigned char name[RIO_MAX_MPORT_NAME]; struct device dev; void *priv; /* Master port private data */ diff --git a/include/linux/rio_regs.h b/include/linux/rio_regs.h index 1063ae382bc2..40c04efe7409 100644 --- a/include/linux/rio_regs.h +++ b/include/linux/rio_regs.h @@ -42,9 +42,11 @@ #define RIO_PEF_INB_MBOX2 0x00200000 /* [II, <= 1.2] Mailbox 2 */ #define RIO_PEF_INB_MBOX3 0x00100000 /* [II, <= 1.2] Mailbox 3 */ #define RIO_PEF_INB_DOORBELL 0x00080000 /* [II, <= 1.2] Doorbells */ +#define RIO_PEF_DEV32 0x00001000 /* [III] PE supports Common TRansport Dev32 */ #define RIO_PEF_EXT_RT 0x00000200 /* [III, 1.3] Extended route table support */ #define RIO_PEF_STD_RT 0x00000100 /* [III, 1.3] Standard route table support */ -#define RIO_PEF_CTLS 0x00000010 /* [III] CTLS */ +#define RIO_PEF_CTLS 0x00000010 /* [III] Common Transport Large System (< rev.3) */ +#define RIO_PEF_DEV16 0x00000010 /* [III] PE Supports Common Transport Dev16 (rev.3) */ #define RIO_PEF_EXT_FEATURES 0x00000008 /* [I] EFT_PTR valid */ #define RIO_PEF_ADDR_66 0x00000004 /* [I] 66 bits */ #define RIO_PEF_ADDR_50 0x00000002 /* [I] 50 bits */ @@ -194,70 +196,101 @@ #define RIO_GET_BLOCK_ID(x) (x & RIO_EFB_ID_MASK) /* Extended Feature Block IDs */ -#define RIO_EFB_PAR_EP_ID 0x0001 /* [IV] LP/LVDS EP Devices */ -#define RIO_EFB_PAR_EP_REC_ID 0x0002 /* [IV] LP/LVDS EP Recovery Devices */ -#define RIO_EFB_PAR_EP_FREE_ID 0x0003 /* [IV] LP/LVDS EP Free Devices */ -#define RIO_EFB_SER_EP_ID_V13P 0x0001 /* [VI] LP/Serial EP Devices, RapidIO Spec ver 1.3 and above */ -#define RIO_EFB_SER_EP_REC_ID_V13P 0x0002 /* [VI] LP/Serial EP Recovery Devices, RapidIO Spec ver 1.3 and above */ -#define RIO_EFB_SER_EP_FREE_ID_V13P 0x0003 /* [VI] LP/Serial EP Free Devices, RapidIO Spec ver 1.3 and above */ -#define RIO_EFB_SER_EP_ID 0x0004 /* [VI] LP/Serial EP Devices */ -#define RIO_EFB_SER_EP_REC_ID 0x0005 /* [VI] LP/Serial EP Recovery Devices */ -#define RIO_EFB_SER_EP_FREE_ID 0x0006 /* [VI] LP/Serial EP Free Devices */ -#define RIO_EFB_SER_EP_FREC_ID 0x0009 /* [VI] LP/Serial EP Free Recovery Devices */ +#define RIO_EFB_SER_EP_M1_ID 0x0001 /* [VI] LP-Serial EP Devices, Map I */ +#define RIO_EFB_SER_EP_SW_M1_ID 0x0002 /* [VI] LP-Serial EP w SW Recovery Devices, Map I */ +#define RIO_EFB_SER_EPF_M1_ID 0x0003 /* [VI] LP-Serial EP Free Devices, Map I */ +#define RIO_EFB_SER_EP_ID 0x0004 /* [VI] LP-Serial EP Devices, RIO 1.2 */ +#define RIO_EFB_SER_EP_REC_ID 0x0005 /* [VI] LP-Serial EP w SW Recovery Devices, RIO 1.2 */ +#define RIO_EFB_SER_EP_FREE_ID 0x0006 /* [VI] LP-Serial EP Free Devices, RIO 1.2 */ #define RIO_EFB_ERR_MGMNT 0x0007 /* [VIII] Error Management Extensions */ +#define RIO_EFB_SER_EPF_SW_M1_ID 0x0009 /* [VI] LP-Serial EP Free w SW Recovery Devices, Map I */ +#define RIO_EFB_SW_ROUTING_TBL 0x000E /* [III] Switch Routing Table Block */ +#define RIO_EFB_SER_EP_M2_ID 0x0011 /* [VI] LP-Serial EP Devices, Map II */ +#define RIO_EFB_SER_EP_SW_M2_ID 0x0012 /* [VI] LP-Serial EP w SW Recovery Devices, Map II */ +#define RIO_EFB_SER_EPF_M2_ID 0x0013 /* [VI] LP-Serial EP Free Devices, Map II */ +#define RIO_EFB_ERR_MGMNT_HS 0x0017 /* [VIII] Error Management Extensions, Hot-Swap only */ +#define RIO_EFB_SER_EPF_SW_M2_ID 0x0019 /* [VI] LP-Serial EP Free w SW Recovery Devices, Map II */ /* - * Physical 8/16 LP-LVDS - * ID=0x0001, Generic End Point Devices - * ID=0x0002, Generic End Point Devices, software assisted recovery option - * ID=0x0003, Generic End Point Free Devices - * - * Physical LP-Serial - * ID=0x0004, Generic End Point Devices - * ID=0x0005, Generic End Point Devices, software assisted recovery option - * ID=0x0006, Generic End Point Free Devices + * Physical LP-Serial Registers Definitions + * Parameters in register macros: + * n - port number, m - Register Map Type (1 or 2) */ #define RIO_PORT_MNT_HEADER 0x0000 #define RIO_PORT_REQ_CTL_CSR 0x0020 -#define RIO_PORT_RSP_CTL_CSR 0x0024 /* 0x0001/0x0002 */ -#define RIO_PORT_LINKTO_CTL_CSR 0x0020 /* Serial */ -#define RIO_PORT_RSPTO_CTL_CSR 0x0024 /* Serial */ +#define RIO_PORT_RSP_CTL_CSR 0x0024 +#define RIO_PORT_LINKTO_CTL_CSR 0x0020 +#define RIO_PORT_RSPTO_CTL_CSR 0x0024 #define RIO_PORT_GEN_CTL_CSR 0x003c #define RIO_PORT_GEN_HOST 0x80000000 #define RIO_PORT_GEN_MASTER 0x40000000 #define RIO_PORT_GEN_DISCOVERED 0x20000000 -#define RIO_PORT_N_MNT_REQ_CSR(x) (0x0040 + x*0x20) /* 0x0002 */ +#define RIO_PORT_N_MNT_REQ_CSR(n, m) (0x40 + (n) * (0x20 * (m))) #define RIO_MNT_REQ_CMD_RD 0x03 /* Reset-device command */ #define RIO_MNT_REQ_CMD_IS 0x04 /* Input-status command */ -#define RIO_PORT_N_MNT_RSP_CSR(x) (0x0044 + x*0x20) /* 0x0002 */ +#define RIO_PORT_N_MNT_RSP_CSR(n, m) (0x44 + (n) * (0x20 * (m))) #define RIO_PORT_N_MNT_RSP_RVAL 0x80000000 /* Response Valid */ #define RIO_PORT_N_MNT_RSP_ASTAT 0x000007e0 /* ackID Status */ #define RIO_PORT_N_MNT_RSP_LSTAT 0x0000001f /* Link Status */ -#define RIO_PORT_N_ACK_STS_CSR(x) (0x0048 + x*0x20) /* 0x0002 */ +#define RIO_PORT_N_ACK_STS_CSR(n) (0x48 + (n) * 0x20) /* Only in RM-I */ #define RIO_PORT_N_ACK_CLEAR 0x80000000 #define RIO_PORT_N_ACK_INBOUND 0x3f000000 #define RIO_PORT_N_ACK_OUTSTAND 0x00003f00 #define RIO_PORT_N_ACK_OUTBOUND 0x0000003f -#define RIO_PORT_N_CTL2_CSR(x) (0x0054 + x*0x20) +#define RIO_PORT_N_CTL2_CSR(n, m) (0x54 + (n) * (0x20 * (m))) #define RIO_PORT_N_CTL2_SEL_BAUD 0xf0000000 -#define RIO_PORT_N_ERR_STS_CSR(x) (0x0058 + x*0x20) -#define RIO_PORT_N_ERR_STS_PW_OUT_ES 0x00010000 /* Output Error-stopped */ -#define RIO_PORT_N_ERR_STS_PW_INP_ES 0x00000100 /* Input Error-stopped */ +#define RIO_PORT_N_ERR_STS_CSR(n, m) (0x58 + (n) * (0x20 * (m))) +#define RIO_PORT_N_ERR_STS_OUT_ES 0x00010000 /* Output Error-stopped */ +#define RIO_PORT_N_ERR_STS_INP_ES 0x00000100 /* Input Error-stopped */ #define RIO_PORT_N_ERR_STS_PW_PEND 0x00000010 /* Port-Write Pending */ +#define RIO_PORT_N_ERR_STS_PORT_UA 0x00000008 /* Port Unavailable */ #define RIO_PORT_N_ERR_STS_PORT_ERR 0x00000004 #define RIO_PORT_N_ERR_STS_PORT_OK 0x00000002 #define RIO_PORT_N_ERR_STS_PORT_UNINIT 0x00000001 -#define RIO_PORT_N_CTL_CSR(x) (0x005c + x*0x20) +#define RIO_PORT_N_CTL_CSR(n, m) (0x5c + (n) * (0x20 * (m))) #define RIO_PORT_N_CTL_PWIDTH 0xc0000000 #define RIO_PORT_N_CTL_PWIDTH_1 0x00000000 #define RIO_PORT_N_CTL_PWIDTH_4 0x40000000 #define RIO_PORT_N_CTL_IPW 0x38000000 /* Initialized Port Width */ #define RIO_PORT_N_CTL_P_TYP_SER 0x00000001 #define RIO_PORT_N_CTL_LOCKOUT 0x00000002 -#define RIO_PORT_N_CTL_EN_RX_SER 0x00200000 -#define RIO_PORT_N_CTL_EN_TX_SER 0x00400000 -#define RIO_PORT_N_CTL_EN_RX_PAR 0x08000000 -#define RIO_PORT_N_CTL_EN_TX_PAR 0x40000000 +#define RIO_PORT_N_CTL_EN_RX 0x00200000 +#define RIO_PORT_N_CTL_EN_TX 0x00400000 +#define RIO_PORT_N_OB_ACK_CSR(n) (0x60 + (n) * 0x40) /* Only in RM-II */ +#define RIO_PORT_N_OB_ACK_CLEAR 0x80000000 +#define RIO_PORT_N_OB_ACK_OUTSTD 0x00fff000 +#define RIO_PORT_N_OB_ACK_OUTBND 0x00000fff +#define RIO_PORT_N_IB_ACK_CSR(n) (0x64 + (n) * 0x40) /* Only in RM-II */ +#define RIO_PORT_N_IB_ACK_INBND 0x00000fff + +/* + * Device-based helper macros for serial port register access. + * d - pointer to rapidio device object, n - port number + */ + +#define RIO_DEV_PORT_N_MNT_REQ_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_MNT_REQ_CSR(n, d->phys_rmap)) + +#define RIO_DEV_PORT_N_MNT_RSP_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_MNT_RSP_CSR(n, d->phys_rmap)) + +#define RIO_DEV_PORT_N_ACK_STS_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_ACK_STS_CSR(n)) + +#define RIO_DEV_PORT_N_CTL2_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_CTL2_CSR(n, d->phys_rmap)) + +#define RIO_DEV_PORT_N_ERR_STS_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_ERR_STS_CSR(n, d->phys_rmap)) + +#define RIO_DEV_PORT_N_CTL_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_CTL_CSR(n, d->phys_rmap)) + +#define RIO_DEV_PORT_N_OB_ACK_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_OB_ACK_CSR(n)) + +#define RIO_DEV_PORT_N_IB_ACK_CSR(d, n) \ + (d->phys_efptr + RIO_PORT_N_IB_ACK_CSR(n)) /* * Error Management Extensions (RapidIO 1.3+, Part 8) @@ -268,6 +301,7 @@ /* General EM Registers (Common for all Ports) */ #define RIO_EM_EFB_HEADER 0x000 /* Error Management Extensions Block Header */ +#define RIO_EM_EMHS_CAR 0x004 /* EM Functionality CAR */ #define RIO_EM_LTL_ERR_DETECT 0x008 /* Logical/Transport Layer Error Detect CSR */ #define RIO_EM_LTL_ERR_EN 0x00c /* Logical/Transport Layer Error Enable CSR */ #define REM_LTL_ERR_ILLTRAN 0x08000000 /* Illegal Transaction decode */ @@ -278,15 +312,33 @@ #define RIO_EM_LTL_ADDR_CAP 0x014 /* Logical/Transport Layer Address Capture CSR */ #define RIO_EM_LTL_DEVID_CAP 0x018 /* Logical/Transport Layer Device ID Capture CSR */ #define RIO_EM_LTL_CTRL_CAP 0x01c /* Logical/Transport Layer Control Capture CSR */ +#define RIO_EM_LTL_DID32_CAP 0x020 /* Logical/Transport Layer Dev32 DestID Capture CSR */ +#define RIO_EM_LTL_SID32_CAP 0x024 /* Logical/Transport Layer Dev32 source ID Capture CSR */ #define RIO_EM_PW_TGT_DEVID 0x028 /* Port-write Target deviceID CSR */ +#define RIO_EM_PW_TGT_DEVID_D16M 0xff000000 /* Port-write Target DID16 MSB */ +#define RIO_EM_PW_TGT_DEVID_D8 0x00ff0000 /* Port-write Target DID16 LSB or DID8 */ +#define RIO_EM_PW_TGT_DEVID_DEV16 0x00008000 /* Port-write Target DID16 LSB or DID8 */ +#define RIO_EM_PW_TGT_DEVID_DEV32 0x00004000 /* Port-write Target DID16 LSB or DID8 */ #define RIO_EM_PKT_TTL 0x02c /* Packet Time-to-live CSR */ +#define RIO_EM_PKT_TTL_VAL 0xffff0000 /* Packet Time-to-live value */ +#define RIO_EM_PW_TGT32_DEVID 0x030 /* Port-write Dev32 Target deviceID CSR */ +#define RIO_EM_PW_TX_CTRL 0x034 /* Port-write Transmission Control CSR */ +#define RIO_EM_PW_TX_CTRL_PW_DIS 0x00000001 /* Port-write Transmission Disable bit */ /* Per-Port EM Registers */ #define RIO_EM_PN_ERR_DETECT(x) (0x040 + x*0x40) /* Port N Error Detect CSR */ #define REM_PED_IMPL_SPEC 0x80000000 +#define REM_PED_LINK_OK2U 0x40000000 /* Link OK to Uninit transition */ +#define REM_PED_LINK_UPDA 0x20000000 /* Link Uninit Packet Discard Active */ +#define REM_PED_LINK_U2OK 0x10000000 /* Link Uninit to OK transition */ #define REM_PED_LINK_TO 0x00000001 + #define RIO_EM_PN_ERRRATE_EN(x) (0x044 + x*0x40) /* Port N Error Rate Enable CSR */ +#define RIO_EM_PN_ERRRATE_EN_OK2U 0x40000000 /* Enable notification for OK2U */ +#define RIO_EM_PN_ERRRATE_EN_UPDA 0x20000000 /* Enable notification for UPDA */ +#define RIO_EM_PN_ERRRATE_EN_U2OK 0x10000000 /* Enable notification for U2OK */ + #define RIO_EM_PN_ATTRIB_CAP(x) (0x048 + x*0x40) /* Port N Attributes Capture CSR */ #define RIO_EM_PN_PKT_CAP_0(x) (0x04c + x*0x40) /* Port N Packet/Control Symbol Capture 0 CSR */ #define RIO_EM_PN_PKT_CAP_1(x) (0x050 + x*0x40) /* Port N Packet Capture 1 CSR */ @@ -294,5 +346,50 @@ #define RIO_EM_PN_PKT_CAP_3(x) (0x058 + x*0x40) /* Port N Packet Capture 3 CSR */ #define RIO_EM_PN_ERRRATE(x) (0x068 + x*0x40) /* Port N Error Rate CSR */ #define RIO_EM_PN_ERRRATE_TR(x) (0x06c + x*0x40) /* Port N Error Rate Threshold CSR */ +#define RIO_EM_PN_LINK_UDT(x) (0x070 + x*0x40) /* Port N Link Uninit Discard Timer CSR */ +#define RIO_EM_PN_LINK_UDT_TO 0xffffff00 /* Link Uninit Timeout value */ + +/* + * Switch Routing Table Register Block ID=0x000E (RapidIO 3.0+, part 3) + * Register offsets are defined from beginning of the block. + */ + +/* Broadcast Routing Table Control CSR */ +#define RIO_BC_RT_CTL_CSR 0x020 +#define RIO_RT_CTL_THREE_LVL 0x80000000 +#define RIO_RT_CTL_DEV32_RT_CTRL 0x40000000 +#define RIO_RT_CTL_MC_MASK_SZ 0x03000000 /* 3.0+ Part 11: Multicast */ + +/* Broadcast Level 0 Info CSR */ +#define RIO_BC_RT_LVL0_INFO_CSR 0x030 +#define RIO_RT_L0I_NUM_GR 0xff000000 +#define RIO_RT_L0I_GR_PTR 0x00fffc00 + +/* Broadcast Level 1 Info CSR */ +#define RIO_BC_RT_LVL1_INFO_CSR 0x034 +#define RIO_RT_L1I_NUM_GR 0xff000000 +#define RIO_RT_L1I_GR_PTR 0x00fffc00 + +/* Broadcast Level 2 Info CSR */ +#define RIO_BC_RT_LVL2_INFO_CSR 0x038 +#define RIO_RT_L2I_NUM_GR 0xff000000 +#define RIO_RT_L2I_GR_PTR 0x00fffc00 + +/* Per-Port Routing Table registers. + * Register fields defined in the broadcast section above are + * applicable to the corresponding registers below. + */ +#define RIO_SPx_RT_CTL_CSR(x) (0x040 + (0x20 * x)) +#define RIO_SPx_RT_LVL0_INFO_CSR(x) (0x50 + (0x20 * x)) +#define RIO_SPx_RT_LVL1_INFO_CSR(x) (0x54 + (0x20 * x)) +#define RIO_SPx_RT_LVL2_INFO_CSR(x) (0x58 + (0x20 * x)) + +/* Register Formats for Routing Table Group entry. + * Register offsets are calculated using GR_PTR field in the corresponding + * table Level_N and group/entry numbers (see RapidIO 3.0+ Part 3). + */ +#define RIO_RT_Ln_ENTRY_IMPL_DEF 0xf0000000 +#define RIO_RT_Ln_ENTRY_RTE_VAL 0x000003ff +#define RIO_RT_ENTRY_DROP_PKT 0x300 #endif /* LINUX_RIO_REGS_H */ -- cgit v1.2.3 From 0b9364b5cf11c6e504f4b77e24b15a0dc8a82df0 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Tue, 2 Aug 2016 14:07:03 -0700 Subject: rapidio/switches: add driver for IDT gen3 switches Add RapidIO switch driver for IDT Gen3 switch devices: RXS1632 and RXS2448. [alexandre.bounine@idt.com: fixup for original driver patch] Link: http://lkml.kernel.org/r/1469137596-18241-1-git-send-email-alexandre.bounine@idt.com Link: http://lkml.kernel.org/r/1469125134-16523-14-git-send-email-alexandre.bounine@idt.com Signed-off-by: Alexandre Bounine Tested-by: Barry Wood Cc: Matt Porter Cc: Andre van Herk Cc: Barry Wood Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 2543bc163d54..334c576c151c 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -38,5 +38,7 @@ #define RIO_DID_IDTVPS1616 0x0377 #define RIO_DID_IDTSPS1616 0x0378 #define RIO_DID_TSI721 0x80ab +#define RIO_DID_IDTRXS1632 0x80e5 +#define RIO_DID_IDTRXS2448 0x80e6 #endif /* LINUX_RIO_IDS_H */ -- cgit v1.2.3 From 3bd080e4d8f2351ee3e143f0ec9307cc95ae6639 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 2 Aug 2016 14:07:32 -0700 Subject: ipc: delete "nr_ipc_ns" Write-only variable. Link: http://lkml.kernel.org/r/20160708214356.GA6785@p183.telecom.by Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 1eee6bcfcf76..d10e54f03c09 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -63,8 +63,6 @@ struct ipc_namespace { }; extern struct ipc_namespace init_ipc_ns; -extern atomic_t nr_ipc_ns; - extern spinlock_t mq_lock; #ifdef CONFIG_SYSVIPC -- cgit v1.2.3 From fe508272c963d62de4183c32b6883c3d54c557ef Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 27 Jul 2016 21:07:36 -0400 Subject: IB/rdmavt: Eliminate redundant opcode test in mr ref clear The use of the specific opcode test is redundant since all ack entry users correctly manipulate the mr pointer to selectively trigger the reference clearing. The overly specific test hinders the use of implementation specific operations. The change needs to get rid of the union to insure that an atomic value is not seen as an MR pointer. Reviewed-by: Ashutosh Dixit Signed-off-by: Mike Marciniszyn Signed-off-by: Ira Weiny Signed-off-by: Doug Ledford --- include/rdma/rdmavt_qp.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 13902dd319a9..bd34d0b56bf7 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -222,14 +222,12 @@ struct rvt_mmap_info { * to send a RDMA read response or atomic operation. */ struct rvt_ack_entry { - u8 opcode; - u8 sent; + struct rvt_sge rdma_sge; + u64 atomic_data; u32 psn; u32 lpsn; - union { - struct rvt_sge rdma_sge; - u64 atomic_data; - }; + u8 opcode; + u8 sent; }; #define RC_QP_SCALING_INTERVAL 5 -- cgit v1.2.3 From c49298026908a8ce9dcf01ed68734ad171cef98b Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 27 Jul 2016 21:08:42 -0400 Subject: IB/hfi1: Allow for non-double word multiple message sizes for user SDMA The driver pads non-double word multiple message sizes but it doesn't account for this padding when the packet length is calculated. Also, the data length is miscalculated for message sizes less than 4 bytes due to the bit representation in LRH. And there's a check for non-double word multiple message sizes that prevents these messages from being sent. This patch fixes length miscalculations and enables the functionality to send non-double word multiple message sizes. Reviewed-by: Harish Chegondi Signed-off-by: Sebastian Sanchez Signed-off-by: Ira Weiny Signed-off-by: Doug Ledford --- include/uapi/rdma/hfi/hfi1_user.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h index 98bebf8bef55..d15e7289d835 100644 --- a/include/uapi/rdma/hfi/hfi1_user.h +++ b/include/uapi/rdma/hfi/hfi1_user.h @@ -75,7 +75,7 @@ * may not be implemented; the user code must deal with this if it * cares, or it must abort after initialization reports the difference. */ -#define HFI1_USER_SWMINOR 1 +#define HFI1_USER_SWMINOR 2 /* * We will encode the major/minor inside a single 32bit version number. -- cgit v1.2.3 From 3e5a4c94a4f88b545d64bbfc7647b06b92c66e98 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 3 Aug 2016 13:44:27 +0200 Subject: vfs: remove file_needs_remove_privs() This function is now unused. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..3888341913ef 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2726,10 +2726,6 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); extern int dentry_needs_remove_privs(struct dentry *dentry); -static inline int file_needs_remove_privs(struct file *file) -{ - return dentry_needs_remove_privs(file->f_path.dentry); -} extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) -- cgit v1.2.3 From f0fce87c36aec5c4a895c78b76396f5727047b93 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 3 Aug 2016 13:44:27 +0200 Subject: vfs: make dentry_needs_remove_privs() internal Only used by the vfs. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3888341913ef..448641bcafc5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2725,7 +2725,6 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); -extern int dentry_needs_remove_privs(struct dentry *dentry); extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) -- cgit v1.2.3 From 0ef7653797addea8ba1bf97f8208a54a62498d94 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 27 Jul 2016 12:06:34 +0930 Subject: exceptions: fork exception table content from module.h into extable.h For historical reasons (i.e. pre-git) the exception table stuff was buried in the middle of the module.h file. I noticed this while doing an audit for needless includes of module.h and found core kernel files (both arch specific and arch independent) were just including module.h for this. The converse is also true, in that conventional drivers, be they for filesystems or actual hardware peripherals or similar, do not normally care about the exception tables. Here we fork the exception table content out of module.h into a new file called extable.h -- and temporarily include it into the module.h itself. Then we will work our way across the arch independent and arch specific files needing just exception table content, and move them off module.h and onto extable.h Once that is done, we can remove the extable.h from module.h and in doing it like this, we avoid introducing build failures into the git history. The gain here is that module.h gets a bit smaller, across all modular drivers that we build for allmodconfig. Also the core files that only need exception table stuff don't have an include of module.h that brings in lots of extra stuff and just looks generally out of place. Cc: Andrew Morton Cc: Linus Torvalds Signed-off-by: Paul Gortmaker Signed-off-by: Rusty Russell --- include/linux/extable.h | 30 ++++++++++++++++++++++++++++++ include/linux/module.h | 27 ++------------------------- 2 files changed, 32 insertions(+), 25 deletions(-) create mode 100644 include/linux/extable.h (limited to 'include') diff --git a/include/linux/extable.h b/include/linux/extable.h new file mode 100644 index 000000000000..2c71dccd1bc3 --- /dev/null +++ b/include/linux/extable.h @@ -0,0 +1,30 @@ +#ifndef _LINUX_EXTABLE_H +#define _LINUX_EXTABLE_H + +struct module; +struct exception_table_entry; + +const struct exception_table_entry * +search_extable(const struct exception_table_entry *first, + const struct exception_table_entry *last, + unsigned long value); +void sort_extable(struct exception_table_entry *start, + struct exception_table_entry *finish); +void sort_main_extable(void); +void trim_init_extable(struct module *m); + +/* Given an address, look for it in the exception tables */ +const struct exception_table_entry *search_exception_tables(unsigned long add); + +#ifdef CONFIG_MODULES +/* For extable.c to search modules' exception tables. */ +const struct exception_table_entry *search_module_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_module_extables(unsigned long addr) +{ + return NULL; +} +#endif /*CONFIG_MODULES*/ + +#endif /* _LINUX_EXTABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index f777164c238b..f95ed243a4de 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -18,6 +18,7 @@ #include #include #include +#include /* only as arch move module.h -> extable.h */ #include #include @@ -37,6 +38,7 @@ struct modversion_info { }; struct module; +struct exception_table_entry; struct module_kobject { struct kobject kobj; @@ -155,18 +157,6 @@ extern void cleanup_module(void); #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ -/* Archs provide a method of finding the correct exception table. */ -struct exception_table_entry; - -const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, - unsigned long value); -void sort_extable(struct exception_table_entry *start, - struct exception_table_entry *finish); -void sort_main_extable(void); -void trim_init_extable(struct module *m); - /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) @@ -268,9 +258,6 @@ extern const typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -/* Given an address, look for it in the exception tables */ -const struct exception_table_entry *search_exception_tables(unsigned long add); - struct notifier_block; #ifdef CONFIG_MODULES @@ -630,9 +617,6 @@ const char *module_address_lookup(unsigned long addr, int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); -/* For extable.c to search modules' exception tables. */ -const struct exception_table_entry *search_module_extables(unsigned long addr); - int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); @@ -657,13 +641,6 @@ static inline bool is_livepatch_module(struct module *mod) #else /* !CONFIG_MODULES... */ -/* Given an address, look for it in the exception tables. */ -static inline const struct exception_table_entry * -search_module_extables(unsigned long addr) -{ - return NULL; -} - static inline struct module *__module_address(unsigned long addr) { return NULL; -- cgit v1.2.3 From 444d13ff10fb13bc3e64859c3cf9ce43dcfeb075 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 27 Jul 2016 12:06:21 +0930 Subject: modules: add ro_after_init support Add ro_after_init support for modules by adding a new page-aligned section in the module layout (after rodata) for ro_after_init data and enabling RO protection for that section after module init runs. Signed-off-by: Jessica Yu Acked-by: Kees Cook Signed-off-by: Rusty Russell --- include/linux/module.h | 6 ++++-- include/uapi/linux/elf.h | 1 + 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index f95ed243a4de..0c3207d26ac0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -298,6 +298,8 @@ struct module_layout { unsigned int text_size; /* Size of RO section of the module (text+rodata) */ unsigned int ro_size; + /* Size of RO after init section */ + unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -765,12 +767,12 @@ extern int module_sysfs_initialized; #ifdef CONFIG_DEBUG_SET_MODULE_RONX extern void set_all_modules_text_rw(void); extern void set_all_modules_text_ro(void); -extern void module_enable_ro(const struct module *mod); +extern void module_enable_ro(const struct module *mod, bool after_init); extern void module_disable_ro(const struct module *mod); #else static inline void set_all_modules_text_rw(void) { } static inline void set_all_modules_text_ro(void) { } -static inline void module_enable_ro(const struct module *mod) { } +static inline void module_enable_ro(const struct module *mod, bool after_init) { } static inline void module_disable_ro(const struct module *mod) { } #endif diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index cb4a72f888d5..70b172ba41ce 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -286,6 +286,7 @@ typedef struct elf64_phdr { #define SHF_ALLOC 0x2 #define SHF_EXECINSTR 0x4 #define SHF_RELA_LIVEPATCH 0x00100000 +#define SHF_RO_AFTER_INIT 0x00200000 #define SHF_MASKPROC 0xf0000000 /* special section indexes */ -- cgit v1.2.3 From 49aadcf1b6f4240751921dad52e86c760d70a5f1 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 27 Jul 2016 23:11:47 -0400 Subject: extable.h: add stddef.h so "NULL" definition is not implicit While not an issue now, eventually we will have independent users of the extable.h file and we will stop sourcing it via module.h header. In testing that pending work, with very sparse builds, characteristic of an "allnoconfig" on various architectures, we can sometimes hit an instance where the very basic standard definitions aren't present, resulting in: include/linux/extable.h:26:9: error: 'NULL' undeclared (first use in this function) To be clear, this isn't a regression, since currently extable.h is only used by module.h -- however, we will need this addition present before we start migrating exception table users off module.h and onto extable.h during the next release cycle. Cc: Rusty Russell Signed-off-by: Paul Gortmaker Signed-off-by: Rusty Russell --- include/linux/extable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/extable.h b/include/linux/extable.h index 2c71dccd1bc3..7effea4b257d 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -1,6 +1,8 @@ #ifndef _LINUX_EXTABLE_H #define _LINUX_EXTABLE_H +#include /* for NULL */ + struct module; struct exception_table_entry; -- cgit v1.2.3 From c7c122ed67e47a7d8033ae21f0cb22a21686194a Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:56 +0300 Subject: net/mlx4: Add diagnostic counters capability bit Add a bit that indicates if the firmware supports per port diagnostic counters. Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 80dec87a94f8..680d110aff05 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -220,6 +220,7 @@ enum { MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32, MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, + MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, }; enum { -- cgit v1.2.3 From bfaf31687c2628ebb95c58a472d46db3f94c554f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:57 +0300 Subject: net/mlx4: Query performance and diagnostics counters Add a function to query diagnostics counters from the firmware. Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 680d110aff05..abcce821ac00 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1381,6 +1381,9 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); +int mlx4_query_diag_counters(struct mlx4_dev *dev, u8 op_modifier, + const u32 offset[], u32 value[], + size_t array_len, u8 port); u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port); bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector); struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port); -- cgit v1.2.3 From 3f85f2aaabf785e53bbcd242cb92aeda28990ef5 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:58 +0300 Subject: IB/mlx4: Add diagnostic hardware counters Expose IB diagnostic hardware counters. The counters count IB events and are applicable for IB and RoCE. The counters can be divided into two groups, per device and per port. Device counters are always exposed. Port counters are exposed only if the firmware supports per port counters. rq_num_dup and sq_num_to are only exposed if we have firmware support for them, if we do, we expose them per device and per port. rq_num_udsdprd and num_cqovf are device only counters. rq - denotes responder. sq - denotes requester. |-----------------------|---------------------------------------| | Name | Description | |-----------------------|---------------------------------------| |rq_num_lle | Number of local length errors | |-----------------------|---------------------------------------| |sq_num_lle | number of local length errors | |-----------------------|---------------------------------------| |rq_num_lqpoe | Number of local QP operation errors | |-----------------------|---------------------------------------| |sq_num_lqpoe | Number of local QP operation errors | |-----------------------|---------------------------------------| |rq_num_lpe | Number of local protection errors | |-----------------------|---------------------------------------| |sq_num_lpe | Number of local protection errors | |-----------------------|---------------------------------------| |rq_num_wrfe | Number of CQEs with error | |-----------------------|---------------------------------------| |sq_num_wrfe | Number of CQEs with error | |-----------------------|---------------------------------------| |sq_num_mwbe | Number of Memory Window bind errors | |-----------------------|---------------------------------------| |sq_num_bre | Number of bad response errors | |-----------------------|---------------------------------------| |sq_num_rire | Number of Remote Invalid request | | | errors | |-----------------------|---------------------------------------| |rq_num_rire | Number of Remote Invalid request | | | errors | |-----------------------|---------------------------------------| |sq_num_rae | Number of remote access errors | |-----------------------|---------------------------------------| |rq_num_rae | Number of remote access errors | |-----------------------|---------------------------------------| |sq_num_roe | Number of remote operation errors | |-----------------------|---------------------------------------| |sq_num_tree | Number of transport retries exceeded | | | errors | |-----------------------|---------------------------------------| |sq_num_rree | Number of RNR NAK retries exceeded | | | errors | |-----------------------|---------------------------------------| |rq_num_rnr | Number of RNR NAKs sent | |-----------------------|---------------------------------------| |sq_num_rnr | Number of RNR NAKs received | |-----------------------|---------------------------------------| |rq_num_oos | Number of Out of Sequence requests | | | received | |-----------------------|---------------------------------------| |sq_num_oos | Number of Out of Sequence NAKs | | | received | |-----------------------|---------------------------------------| |rq_num_udsdprd | Number of UD packets silently | | | discarded on the Receive Queue due to | | | lack of receive descriptor | |-----------------------|---------------------------------------| |rq_num_dup | Number of duplicate requests received | |-----------------------|---------------------------------------| |sq_num_to | Number of time out received | |-----------------------|---------------------------------------| |num_cqovf | Number of CQ overflows | |-----------------------|---------------------------------------| Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index abcce821ac00..d73d8e4d3e09 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1341,6 +1341,9 @@ enum { VXLAN_STEER_BY_INNER_VLAN = 1 << 4, }; +enum { + MLX4_OP_MOD_QUERY_TRANSPORT_CI_ERRORS = 0x2, +}; int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); -- cgit v1.2.3 From ab15c95a17b3fe8c0e01bb7ce1dd0b657598eb61 Mon Sep 17 00:00:00 2001 From: Alex Vesker Date: Wed, 6 Jul 2016 16:36:35 +0300 Subject: IB/core: Support for CMA multicast join flags Added UCMA and CMA support for multicast join flags. Flags are passed using UCMA CM join command previously reserved fields. Currently supporting two join flags indicating two different multicast JoinStates: 1. Full Member: The initiator creates the Multicast group(MCG) if it wasn't previously created, can send Multicast messages to the group and receive messages from the MCG. 2. Send Only Full Member: The initiator creates the Multicast group(MCG) if it wasn't previously created, can send Multicast messages to the group but doesn't receive any messages from the MCG. IB: Send Only Full Member requires a query of ClassPortInfo to determine if SM/SA supports this option. If SM/SA doesn't support Send-Only there will be no join request sent and an error will be returned. ETH: When Send Only Full Member is requested no IGMP join will be sent. Signed-off-by: Alex Vesker Reviewed by: Hal Rosenstock Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/rdma/ib_sa.h | 13 +++++++++++++ include/rdma/rdma_cm.h | 4 +++- include/uapi/rdma/rdma_user_cm.h | 9 ++++++++- 3 files changed, 24 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h index 384041669489..5ee7aab95eb8 100644 --- a/include/rdma/ib_sa.h +++ b/include/rdma/ib_sa.h @@ -94,6 +94,19 @@ enum ib_sa_selector { IB_SA_BEST = 3 }; +/* + * There are 4 types of join states: + * FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember. + * The order corresponds to JoinState bits in MCMemberRecord. + */ +enum ib_sa_mc_join_states { + FULLMEMBER_JOIN, + NONMEMBER_JOIN, + SENDONLY_NONMEBER_JOIN, + SENDONLY_FULLMEMBER_JOIN, + NUM_JOIN_MEMBERSHIP_TYPES, +}; + #define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT BIT(12) /* diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index afe44fde72a5..81fb1d15e8bb 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -333,11 +333,13 @@ int rdma_disconnect(struct rdma_cm_id *id); * address. * @id: Communication identifier associated with the request. * @addr: Multicast address identifying the group to join. + * @join_state: Multicast JoinState bitmap requested by port. + * Bitmap is based on IB_SA_MCMEMBER_REC_JOIN_STATE bits. * @context: User-defined context associated with the join request, returned * to the user through the private_data pointer in multicast events. */ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, - void *context); + u8 join_state, void *context); /** * rdma_leave_multicast - Leave the multicast group specified by the given diff --git a/include/uapi/rdma/rdma_user_cm.h b/include/uapi/rdma/rdma_user_cm.h index 3066718eb120..01923d463673 100644 --- a/include/uapi/rdma/rdma_user_cm.h +++ b/include/uapi/rdma/rdma_user_cm.h @@ -244,12 +244,19 @@ struct rdma_ucm_join_ip_mcast { __u32 id; }; +/* Multicast join flags */ +enum { + RDMA_MC_JOIN_FLAG_FULLMEMBER, + RDMA_MC_JOIN_FLAG_SENDONLY_FULLMEMBER, + RDMA_MC_JOIN_FLAG_RESERVED, +}; + struct rdma_ucm_join_mcast { __u64 response; /* rdma_ucma_create_id_resp */ __u64 uid; __u32 id; __u16 addr_size; - __u16 reserved; + __u16 join_flags; struct sockaddr_storage addr; }; -- cgit v1.2.3 From 97f2645f358b411ba2afb22e5966753f0ad92916 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 3 Aug 2016 13:45:50 -0700 Subject: tree-wide: replace config_enabled() with IS_ENABLED() The use of config_enabled() against config options is ambiguous. In practical terms, config_enabled() is equivalent to IS_BUILTIN(), but the author might have used it for the meaning of IS_ENABLED(). Using IS_ENABLED(), IS_BUILTIN(), IS_MODULE() etc. makes the intention clearer. This commit replaces config_enabled() with IS_ENABLED() where possible. This commit is only touching bool config options. I noticed two cases where config_enabled() is used against a tristate option: - config_enabled(CONFIG_HWMON) [ drivers/net/wireless/ath/ath10k/thermal.c ] - config_enabled(CONFIG_BACKLIGHT_CLASS_DEVICE) [ drivers/gpu/drm/gma500/opregion.c ] I did not touch them because they should be converted to IS_BUILTIN() in order to keep the logic, but I was not sure it was the authors' intention. Link: http://lkml.kernel.org/r/1465215656-20569-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Kees Cook Cc: Stas Sergeev Cc: Matt Redfearn Cc: Joshua Kinard Cc: Jiri Slaby Cc: Bjorn Helgaas Cc: Borislav Petkov Cc: Markos Chandras Cc: "Dmitry V. Levin" Cc: yu-cheng yu Cc: James Hogan Cc: Brian Gerst Cc: Johannes Berg Cc: Peter Zijlstra Cc: Al Viro Cc: Will Drewry Cc: Nikolay Martynov Cc: Huacai Chen Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Daniel Borkmann Cc: Leonid Yegoshin Cc: Rafal Milecki Cc: James Cowgill Cc: Greg Kroah-Hartman Cc: Ralf Baechle Cc: Alex Smith Cc: Adam Buchbinder Cc: Qais Yousef Cc: Jiang Liu Cc: Mikko Rapeli Cc: Paul Gortmaker Cc: Denys Vlasenko Cc: Brian Norris Cc: Hidehiro Kawai Cc: "Luis R. Rodriguez" Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Dave Hansen Cc: "Kirill A. Shutemov" Cc: Roland McGrath Cc: Paul Burton Cc: Kalle Valo Cc: Viresh Kumar Cc: Tony Wu Cc: Huaitong Han Cc: Sumit Semwal Cc: Alexei Starovoitov Cc: Juergen Gross Cc: Jason Cooper Cc: "David S. Miller" Cc: Oleg Nesterov Cc: Andrea Gelmini Cc: David Woodhouse Cc: Marc Zyngier Cc: Rabin Vincent Cc: "Maciej W. Rozycki" Cc: David Daney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fence.h | 2 +- include/linux/ww_mutex.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fence.h b/include/linux/fence.h index 523ea3fbbddd..8cc719a63728 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -358,7 +358,7 @@ u64 fence_context_alloc(unsigned num); #define FENCE_TRACE(f, fmt, args...) \ do { \ struct fence *__ff = (f); \ - if (config_enabled(CONFIG_FENCE_TRACE)) \ + if (IS_ENABLED(CONFIG_FENCE_TRACE)) \ pr_info("f %llu#%u: " fmt, \ __ff->context, __ff->seqno, ##args); \ } while (0) diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 760399a470bd..2bb5deb0012e 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -173,14 +173,14 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) mutex_release(&ctx->dep_map, 0, _THIS_IP_); DEBUG_LOCKS_WARN_ON(ctx->acquired); - if (!config_enabled(CONFIG_PROVE_LOCKING)) + if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) /* * lockdep will normally handle this, * but fail without anyway */ ctx->done_acquire = 1; - if (!config_enabled(CONFIG_DEBUG_LOCK_ALLOC)) + if (!IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC)) /* ensure ww_acquire_fini will still fail if called twice */ ctx->acquired = ~0U; #endif -- cgit v1.2.3 From 4b9d314ce9168b37a2824e6d7820aa6e66f52642 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 3 Aug 2016 13:45:54 -0700 Subject: include/linux/bitmap.h: cleanup Remove two unneeded `else's. Cc: David Hildenbrand Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 27bfc0b631a9..598bc999f4c2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -266,13 +266,12 @@ static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) - return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); + return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); #ifdef CONFIG_S390 - else if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) return !memcmp(src1, src2, nbits / 8); #endif - else - return __bitmap_equal(src1, src2, nbits); + return __bitmap_equal(src1, src2, nbits); } static inline int bitmap_intersects(const unsigned long *src1, -- cgit v1.2.3 From 00085f1efa387a8ce100e3734920f7639c80caa3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 3 Aug 2016 13:46:00 -0700 Subject: dma-mapping: use unsigned long for dma_attrs The dma-mapping core and the implementations do not change the DMA attributes passed by pointer. Thus the pointer can point to const data. However the attributes do not have to be a bitfield. Instead unsigned long will do fine: 1. This is just simpler. Both in terms of reading the code and setting attributes. Instead of initializing local attributes on the stack and passing pointer to it to dma_set_attr(), just set the bits. 2. It brings safeness and checking for const correctness because the attributes are passed by value. Semantic patches for this change (at least most of them): virtual patch virtual context @r@ identifier f, attrs; @@ f(..., - struct dma_attrs *attrs + unsigned long attrs , ...) { ... } @@ identifier r.f; @@ f(..., - NULL + 0 ) and // Options: --all-includes virtual patch virtual context @r@ identifier f, attrs; type t; @@ t f(..., struct dma_attrs *attrs); @@ identifier r.f; @@ f(..., - NULL + 0 ) Link: http://lkml.kernel.org/r/1468399300-5399-2-git-send-email-k.kozlowski@samsung.com Signed-off-by: Krzysztof Kozlowski Acked-by: Vineet Gupta Acked-by: Robin Murphy Acked-by: Hans-Christian Noren Egtvedt Acked-by: Mark Salter [c6x] Acked-by: Jesper Nilsson [cris] Acked-by: Daniel Vetter [drm] Reviewed-by: Bart Van Assche Acked-by: Joerg Roedel [iommu] Acked-by: Fabien Dessenne [bdisp] Reviewed-by: Marek Szyprowski [vb2-core] Acked-by: David Vrabel [xen] Acked-by: Konrad Rzeszutek Wilk [xen swiotlb] Acked-by: Joerg Roedel [iommu] Acked-by: Richard Kuo [hexagon] Acked-by: Geert Uytterhoeven [m68k] Acked-by: Gerald Schaefer [s390] Acked-by: Bjorn Andersson Acked-by: Hans-Christian Noren Egtvedt [avr32] Acked-by: Vineet Gupta [arc] Acked-by: Robin Murphy [arm64 and dma-iommu] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-attrs.h | 71 ------------------- include/linux/dma-iommu.h | 6 +- include/linux/dma-mapping.h | 128 +++++++++++++++++++++++------------ include/linux/swiotlb.h | 10 +-- include/media/videobuf2-core.h | 6 +- include/media/videobuf2-dma-contig.h | 2 - include/rdma/ib_verbs.h | 17 ++--- include/xen/swiotlb-xen.h | 12 ++-- 8 files changed, 110 insertions(+), 142 deletions(-) delete mode 100644 include/linux/dma-attrs.h (limited to 'include') diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h deleted file mode 100644 index 5246239a4953..000000000000 --- a/include/linux/dma-attrs.h +++ /dev/null @@ -1,71 +0,0 @@ -#ifndef _DMA_ATTR_H -#define _DMA_ATTR_H - -#include -#include -#include - -/** - * an enum dma_attr represents an attribute associated with a DMA - * mapping. The semantics of each attribute should be defined in - * Documentation/DMA-attributes.txt. - */ -enum dma_attr { - DMA_ATTR_WRITE_BARRIER, - DMA_ATTR_WEAK_ORDERING, - DMA_ATTR_WRITE_COMBINE, - DMA_ATTR_NON_CONSISTENT, - DMA_ATTR_NO_KERNEL_MAPPING, - DMA_ATTR_SKIP_CPU_SYNC, - DMA_ATTR_FORCE_CONTIGUOUS, - DMA_ATTR_ALLOC_SINGLE_PAGES, - DMA_ATTR_MAX, -}; - -#define __DMA_ATTRS_LONGS BITS_TO_LONGS(DMA_ATTR_MAX) - -/** - * struct dma_attrs - an opaque container for DMA attributes - * @flags - bitmask representing a collection of enum dma_attr - */ -struct dma_attrs { - unsigned long flags[__DMA_ATTRS_LONGS]; -}; - -#define DEFINE_DMA_ATTRS(x) \ - struct dma_attrs x = { \ - .flags = { [0 ... __DMA_ATTRS_LONGS-1] = 0 }, \ - } - -static inline void init_dma_attrs(struct dma_attrs *attrs) -{ - bitmap_zero(attrs->flags, __DMA_ATTRS_LONGS); -} - -/** - * dma_set_attr - set a specific attribute - * @attr: attribute to set - * @attrs: struct dma_attrs (may be NULL) - */ -static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs) -{ - if (attrs == NULL) - return; - BUG_ON(attr >= DMA_ATTR_MAX); - __set_bit(attr, attrs->flags); -} - -/** - * dma_get_attr - check for a specific attribute - * @attr: attribute to set - * @attrs: struct dma_attrs (may be NULL) - */ -static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs) -{ - if (attrs == NULL) - return 0; - BUG_ON(attr >= DMA_ATTR_MAX); - return test_bit(attr, attrs->flags); -} - -#endif /* _DMA_ATTR_H */ diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 8443bbb5c071..81c5c8d167ad 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -39,7 +39,7 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent); * the arch code to take care of attributes and cache maintenance */ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, - struct dma_attrs *attrs, int prot, dma_addr_t *handle, + unsigned long attrs, int prot, dma_addr_t *handle, void (*flush_page)(struct device *, const void *, phys_addr_t)); void iommu_dma_free(struct device *dev, struct page **pages, size_t size, dma_addr_t *handle); @@ -56,9 +56,9 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * directly as DMA mapping callbacks for simplicity */ void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, unsigned long attrs); void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, unsigned long attrs); int iommu_dma_supported(struct device *dev, u64 mask); int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 71c1b215ef66..66533e18276c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -5,13 +5,58 @@ #include #include #include -#include #include #include #include #include #include +/** + * List of possible attributes associated with a DMA mapping. The semantics + * of each attribute should be defined in Documentation/DMA-attributes.txt. + * + * DMA_ATTR_WRITE_BARRIER: DMA to a memory region with this attribute + * forces all pending DMA writes to complete. + */ +#define DMA_ATTR_WRITE_BARRIER (1UL << 0) +/* + * DMA_ATTR_WEAK_ORDERING: Specifies that reads and writes to the mapping + * may be weakly ordered, that is that reads and writes may pass each other. + */ +#define DMA_ATTR_WEAK_ORDERING (1UL << 1) +/* + * DMA_ATTR_WRITE_COMBINE: Specifies that writes to the mapping may be + * buffered to improve performance. + */ +#define DMA_ATTR_WRITE_COMBINE (1UL << 2) +/* + * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either + * consistent or non-consistent memory as it sees fit. + */ +#define DMA_ATTR_NON_CONSISTENT (1UL << 3) +/* + * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel + * virtual mapping for the allocated buffer. + */ +#define DMA_ATTR_NO_KERNEL_MAPPING (1UL << 4) +/* + * DMA_ATTR_SKIP_CPU_SYNC: Allows platform code to skip synchronization of + * the CPU cache for the given buffer assuming that it has been already + * transferred to 'device' domain. + */ +#define DMA_ATTR_SKIP_CPU_SYNC (1UL << 5) +/* + * DMA_ATTR_FORCE_CONTIGUOUS: Forces contiguous allocation of the buffer + * in physical memory. + */ +#define DMA_ATTR_FORCE_CONTIGUOUS (1UL << 6) +/* + * DMA_ATTR_ALLOC_SINGLE_PAGES: This is a hint to the DMA-mapping subsystem + * that it's probably not worth the time to try to allocate memory to in a way + * that gives better TLB efficiency. + */ +#define DMA_ATTR_ALLOC_SINGLE_PAGES (1UL << 7) + /* * A dma_addr_t can hold any valid DMA or bus address for the platform. * It can be given to a device to use as a DMA source or target. A CPU cannot @@ -21,34 +66,35 @@ struct dma_map_ops { void* (*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs); + unsigned long attrs); void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); + unsigned long attrs); int (*mmap)(struct device *, struct vm_area_struct *, - void *, dma_addr_t, size_t, struct dma_attrs *attrs); + void *, dma_addr_t, size_t, + unsigned long attrs); int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *, - dma_addr_t, size_t, struct dma_attrs *attrs); + dma_addr_t, size_t, unsigned long attrs); dma_addr_t (*map_page)(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); /* * map_sg returns 0 on error and a value > 0 on success. * It should never return a value < 0. */ int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir); @@ -123,7 +169,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; @@ -142,7 +188,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -158,7 +204,7 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, */ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); int i, ents; @@ -176,7 +222,7 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -195,7 +241,7 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, kmemcheck_mark_initialized(page_address(page) + offset, size); BUG_ON(!valid_dma_direction(dir)); - addr = ops->map_page(dev, page, offset, size, dir, NULL); + addr = ops->map_page(dev, page, offset, size, dir, 0); debug_dma_map_page(dev, page, offset, size, dir, addr, false); return addr; @@ -208,7 +254,7 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) - ops->unmap_page(dev, addr, size, dir, NULL); + ops->unmap_page(dev, addr, size, dir, 0); debug_dma_unmap_page(dev, addr, size, dir, false); } @@ -289,10 +335,10 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } -#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL) -#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL) -#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL) -#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL) +#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) +#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) +#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) +#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0) extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size); @@ -321,7 +367,7 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); */ static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); @@ -330,7 +376,7 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); } -#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL) +#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, @@ -338,7 +384,8 @@ dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); @@ -348,7 +395,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size); } -#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL) +#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) #ifndef arch_dma_alloc_attrs #define arch_dma_alloc_attrs(dev, flag) (true) @@ -356,7 +403,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, static inline void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; @@ -378,7 +425,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, static inline void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -398,31 +445,27 @@ static inline void dma_free_attrs(struct device *dev, size_t size, static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { - return dma_alloc_attrs(dev, size, dma_handle, flag, NULL); + return dma_alloc_attrs(dev, size, dma_handle, flag, 0); } static inline void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { - return dma_free_attrs(dev, size, cpu_addr, dma_handle, NULL); + return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - DEFINE_DMA_ATTRS(attrs); - - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs); - return dma_alloc_attrs(dev, size, dma_handle, gfp, &attrs); + return dma_alloc_attrs(dev, size, dma_handle, gfp, + DMA_ATTR_NON_CONSISTENT); } static inline void dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { - DEFINE_DMA_ATTRS(attrs); - - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs); - dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs); + dma_free_attrs(dev, size, cpu_addr, dma_handle, + DMA_ATTR_NON_CONSISTENT); } static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -646,9 +689,8 @@ static inline void dmam_release_declared_memory(struct device *dev) static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs); + return dma_alloc_attrs(dev, size, dma_addr, gfp, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_alloc_writecombine #define dma_alloc_writecombine dma_alloc_wc @@ -657,9 +699,8 @@ static inline void *dma_alloc_wc(struct device *dev, size_t size, static inline void dma_free_wc(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs); + return dma_free_attrs(dev, size, cpu_addr, dma_addr, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_free_writecombine #define dma_free_writecombine dma_free_wc @@ -670,9 +711,8 @@ static inline int dma_mmap_wc(struct device *dev, void *cpu_addr, dma_addr_t dma_addr, size_t size) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs); + return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_mmap_writecombine #define dma_mmap_writecombine dma_mmap_wc diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 017fced60242..5f81f8a187f2 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -6,7 +6,6 @@ #include struct device; -struct dma_attrs; struct page; struct scatterlist; @@ -68,10 +67,10 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, @@ -83,12 +82,13 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, + unsigned long attrs); extern void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 946340ce7701..a4a9a55a0c42 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -98,7 +98,7 @@ struct vb2_threadio_data; * #) Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, map_dmabuf, unmap_dmabuf. */ struct vb2_mem_ops { - void *(*alloc)(struct device *dev, const struct dma_attrs *attrs, + void *(*alloc)(struct device *dev, unsigned long attrs, unsigned long size, enum dma_data_direction dma_dir, gfp_t gfp_flags); void (*put)(void *buf_priv); @@ -408,7 +408,7 @@ struct vb2_buf_ops { * @io_modes: supported io methods (see vb2_io_modes enum) * @dev: device to use for the default allocation context if the driver * doesn't fill in the @alloc_devs array. - * @dma_attrs: DMA attributes to use for the DMA. May be NULL. + * @dma_attrs: DMA attributes to use for the DMA. * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver @@ -476,7 +476,7 @@ struct vb2_queue { unsigned int type; unsigned int io_modes; struct device *dev; - const struct dma_attrs *dma_attrs; + unsigned long dma_attrs; unsigned fileio_read_once:1; unsigned fileio_write_immediately:1; unsigned allow_zero_bytesused:1; diff --git a/include/media/videobuf2-dma-contig.h b/include/media/videobuf2-dma-contig.h index df2aabee3401..5604818d137e 100644 --- a/include/media/videobuf2-dma-contig.h +++ b/include/media/videobuf2-dma-contig.h @@ -16,8 +16,6 @@ #include #include -struct dma_attrs; - static inline dma_addr_t vb2_dma_contig_plane_dma_addr(struct vb2_buffer *vb, unsigned int plane_no) { diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 7e440d41487a..a8137dcf5a00 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2819,19 +2819,19 @@ static inline void ib_dma_unmap_single(struct ib_device *dev, static inline u64 ib_dma_map_single_attrs(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { return dma_map_single_attrs(dev->dma_device, cpu_addr, size, - direction, attrs); + direction, dma_attrs); } static inline void ib_dma_unmap_single_attrs(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { return dma_unmap_single_attrs(dev->dma_device, addr, size, - direction, attrs); + direction, dma_attrs); } /** @@ -2906,17 +2906,18 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev, static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { - return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, attrs); + return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, + dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, - struct dma_attrs *attrs) + unsigned long dma_attrs) { - dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, attrs); + dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_sg_dma_address - Return the DMA address from a scatter/gather entry diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h index 8b2eb93ae8ba..7c35e279d1e3 100644 --- a/include/xen/swiotlb-xen.h +++ b/include/xen/swiotlb-xen.h @@ -9,30 +9,30 @@ extern int xen_swiotlb_init(int verbose, bool early); extern void *xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, - struct dma_attrs *attrs); + unsigned long attrs); extern void xen_swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); + unsigned long attrs); extern dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern int xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void xen_swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void xen_swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, -- cgit v1.2.3 From 1f69bf9c6137602cd028c96b4f8329121ec89231 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 3 Aug 2016 13:46:36 -0700 Subject: jump_label: remove bug.h, atomic.h dependencies for HAVE_JUMP_LABEL The current jump_label.h includes bug.h for things such as WARN_ON(). This makes the header problematic for inclusion by kernel.h or any headers that kernel.h includes, since bug.h includes kernel.h (circular dependency). The inclusion of atomic.h is similarly problematic. Thus, this should make jump_label.h 'includable' from most places. Link: http://lkml.kernel.org/r/7060ce35ddd0d20b33bf170685e6b0fab816bdf2.1467837322.git.jbaron@akamai.com Signed-off-by: Jason Baron Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Heiko Carstens Cc: Joe Perches Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jump_label.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 68904469fba1..661af564fae8 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -76,7 +76,6 @@ #include #include -#include extern bool static_key_initialized; @@ -115,20 +114,8 @@ enum jump_label_type { struct module; -#include - #ifdef HAVE_JUMP_LABEL -static inline int static_key_count(struct static_key *key) -{ - /* - * -1 means the first static_key_slow_inc() is in progress. - * static_key_enabled() must return true, so return 1 here. - */ - int n = atomic_read(&key->enabled); - return n >= 0 ? n : 1; -} - #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_MASK 1UL @@ -157,16 +144,29 @@ extern int jump_label_text_reserved(void *start, void *end); extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern void jump_label_apply_nops(struct module *mod); +extern int static_key_count(struct static_key *key); +extern void static_key_enable(struct static_key *key); +extern void static_key_disable(struct static_key *key); +/* + * We should be using ATOMIC_INIT() for initializing .enabled, but + * the inclusion of atomic.h is problematic for inclusion of jump_label.h + * in 'low-level' headers. Thus, we are initializing .enabled with a + * raw value, but have added a BUILD_BUG_ON() to catch any issues in + * jump_label_init() see: kernel/jump_label.c. + */ #define STATIC_KEY_INIT_TRUE \ - { .enabled = ATOMIC_INIT(1), \ + { .enabled = { 1 }, \ .entries = (void *)JUMP_TYPE_TRUE } #define STATIC_KEY_INIT_FALSE \ - { .enabled = ATOMIC_INIT(0), \ + { .enabled = { 0 }, \ .entries = (void *)JUMP_TYPE_FALSE } #else /* !HAVE_JUMP_LABEL */ +#include +#include + static inline int static_key_count(struct static_key *key) { return atomic_read(&key->enabled); @@ -216,14 +216,6 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } -#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } - -#endif /* HAVE_JUMP_LABEL */ - -#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE -#define jump_label_enabled static_key_enabled - static inline void static_key_enable(struct static_key *key) { int count = static_key_count(key); @@ -244,6 +236,14 @@ static inline void static_key_disable(struct static_key *key) static_key_slow_dec(key); } +#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } +#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } + +#endif /* HAVE_JUMP_LABEL */ + +#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE +#define jump_label_enabled static_key_enabled + /* -------------------------------------------------------------------------- */ /* -- cgit v1.2.3 From 9049fc745300c5e2236cbfc69f5e8cadb6f1f57c Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 3 Aug 2016 13:46:39 -0700 Subject: dynamic_debug: add jump label support Although dynamic debug is often only used for debug builds, sometimes its enabled for production builds as well. Minimize its impact by using jump labels. This reduces the text section by 7000+ bytes in the kernel image below. It does increase data, but this should only be referenced when changing the direction of the branches, and hence usually not in cache. text data bss dec hex filename 8194852 4879776 925696 14000324 d5a0c4 vmlinux.pre 8187337 4960224 925696 14073257 d6bda9 vmlinux.post Link: http://lkml.kernel.org/r/d165b465e8c89bc582d973758d40be44c33f018b.1467837322.git.jbaron@akamai.com Signed-off-by: Jason Baron Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Heiko Carstens Cc: Joe Perches Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dynamic_debug.h | 60 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 54 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4f1bbc68cd1b..546d68057e3b 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,6 +1,10 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +#include +#endif + /* * An instance of this structure is created in a special * ELF section at every dynamic debug callsite. At runtime, @@ -33,6 +37,12 @@ struct _ddebug { #define _DPRINTK_FLAGS_DEFAULT 0 #endif unsigned int flags:8; +#ifdef HAVE_JUMP_LABEL + union { + struct static_key_true dd_key_true; + struct static_key_false dd_key_false; + } key; +#endif } __attribute__((aligned(8))); @@ -60,7 +70,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor, const struct net_device *dev, const char *fmt, ...); -#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ +#define DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, key, init) \ static struct _ddebug __aligned(8) \ __attribute__((section("__verbose"))) name = { \ .modname = KBUILD_MODNAME, \ @@ -68,13 +78,51 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor, .filename = __FILE__, \ .format = (fmt), \ .lineno = __LINE__, \ - .flags = _DPRINTK_FLAGS_DEFAULT, \ + .flags = _DPRINTK_FLAGS_DEFAULT, \ + dd_key_init(key, init) \ } +#ifdef HAVE_JUMP_LABEL + +#define dd_key_init(key, init) key = (init) + +#ifdef DEBUG +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, .key.dd_key_true, \ + (STATIC_KEY_TRUE_INIT)) + +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + static_branch_likely(&descriptor.key.dd_key_true) +#else +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, .key.dd_key_false, \ + (STATIC_KEY_FALSE_INIT)) + +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + static_branch_unlikely(&descriptor.key.dd_key_false) +#endif + +#else + +#define dd_key_init(key, init) + +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, 0, 0) + +#ifdef DEBUG +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + likely(descriptor.flags & _DPRINTK_FLAGS_PRINT) +#else +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) +#endif + +#endif + #define dynamic_pr_debug(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) @@ -82,7 +130,7 @@ do { \ #define dynamic_dev_dbg(dev, fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_dev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) @@ -90,7 +138,7 @@ do { \ #define dynamic_netdev_dbg(dev, fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_netdev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) @@ -100,7 +148,7 @@ do { \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, \ __builtin_constant_p(prefix_str) ? prefix_str : "hexdump");\ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ print_hex_dump(KERN_DEBUG, prefix_str, \ prefix_type, rowsize, groupsize, \ buf, len, ascii); \ -- cgit v1.2.3 From 8700e3e7c4857d28ebaa824509934556da0b3e76 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Thu, 16 Jun 2016 16:45:23 +0300 Subject: Soft RoCE driver Soft RoCE (RXE) - The software RoCE driver ib_rxe implements the RDMA transport and registers to the RDMA core device as a kernel verbs provider. It also implements the packet IO layer. On the other hand ib_rxe registers to the Linux netdev stack as a udp encapsulating protocol, in that case RDMA, for sending and receiving packets over any Ethernet device. This yields a RDMA transport over the UDP/Ethernet network layer forming a RoCEv2 compatible device. The configuration procedure of the Soft RoCE drivers requires binding to any existing Ethernet network device. This is done with /sys interface. A userspace Soft RoCE library (librxe) provides user applications the ability to run with Soft RoCE devices. The use of rxe verbs ins user space requires the inclusion of librxe as a device specifics plug-in to libibverbs. librxe is packaged separately. Architecture: +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ +---------------------------------------------------------------+ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Soft RoCE resources: [1[ https://github.com/SoftRoCE/librxe-dev librxe - source code in Github [2] https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home - Soft RoCE Wiki page [3] https://github.com/SoftRoCE/librxe-dev - Soft RoCE userspace library Signed-off-by: Kamal Heib Signed-off-by: Amir Vadai Signed-off-by: Moni Shoua Reviewed-by: Haggai Eran Signed-off-by: Doug Ledford --- include/uapi/rdma/Kbuild | 1 + include/uapi/rdma/rdma_user_rxe.h | 144 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 145 insertions(+) create mode 100644 include/uapi/rdma/rdma_user_rxe.h (limited to 'include') diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild index 231901b08f6c..4edb0f2b4f9f 100644 --- a/include/uapi/rdma/Kbuild +++ b/include/uapi/rdma/Kbuild @@ -6,3 +6,4 @@ header-y += ib_user_verbs.h header-y += rdma_netlink.h header-y += rdma_user_cm.h header-y += hfi/ +header-y += rdma_user_rxe.h diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h new file mode 100644 index 000000000000..1de99cfdaf7d --- /dev/null +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef RDMA_USER_RXE_H +#define RDMA_USER_RXE_H + +#include + +union rxe_gid { + __u8 raw[16]; + struct { + __be64 subnet_prefix; + __be64 interface_id; + } global; +}; + +struct rxe_global_route { + union rxe_gid dgid; + __u32 flow_label; + __u8 sgid_index; + __u8 hop_limit; + __u8 traffic_class; +}; + +struct rxe_av { + __u8 port_num; + __u8 network_type; + struct rxe_global_route grh; + union { + struct sockaddr _sockaddr; + struct sockaddr_in _sockaddr_in; + struct sockaddr_in6 _sockaddr_in6; + } sgid_addr, dgid_addr; +}; + +struct rxe_send_wr { + __u64 wr_id; + __u32 num_sge; + __u32 opcode; + __u32 send_flags; + union { + __be32 imm_data; + __u32 invalidate_rkey; + } ex; + union { + struct { + __u64 remote_addr; + __u32 rkey; + } rdma; + struct { + __u64 remote_addr; + __u64 compare_add; + __u64 swap; + __u32 rkey; + } atomic; + struct { + __u32 remote_qpn; + __u32 remote_qkey; + __u16 pkey_index; + } ud; + struct { + struct ib_mr *mr; + __u32 key; + int access; + } reg; + } wr; +}; + +struct rxe_sge { + __u64 addr; + __u32 length; + __u32 lkey; +}; + +struct mminfo { + __u64 offset; + __u32 size; + __u32 pad; +}; + +struct rxe_dma_info { + __u32 length; + __u32 resid; + __u32 cur_sge; + __u32 num_sge; + __u32 sge_offset; + union { + __u8 inline_data[0]; + struct rxe_sge sge[0]; + }; +}; + +struct rxe_send_wqe { + struct rxe_send_wr wr; + struct rxe_av av; + __u32 status; + __u32 state; + __u64 iova; + __u32 mask; + __u32 first_psn; + __u32 last_psn; + __u32 ack_length; + __u32 ssn; + __u32 has_rd_atomic; + struct rxe_dma_info dma; +}; + +struct rxe_recv_wqe { + __u64 wr_id; + __u32 num_sge; + __u32 padding; + struct rxe_dma_info dma; +}; + +#endif /* RDMA_USER_RXE_H */ -- cgit v1.2.3 From 20bd723ec6a3261df5e02250cd3a1fbb09a343f2 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Wed, 27 Jul 2016 07:22:05 +0200 Subject: block: add missing group association in bio-cloning functions When a bio is cloned, the newly created bio must be associated with the same blkcg as the original bio (if BLK_CGROUP is enabled). If this operation is not performed, then the new bio is not associated with any group, and the group of the current task is returned when the group of the bio is requested. Depending on the cloning frequency, this may cause a large percentage of the bios belonging to a given group to be treated as if belonging to other groups (in most cases as if belonging to the root group). The expected group isolation may thereby be broken. This commit adds the missing association in bio-cloning functions. Fixes: da2f0f74cf7d ("Btrfs: add support for blkio controllers") Cc: stable@vger.kernel.org # v4.3+ Signed-off-by: Paolo Valente Reviewed-by: Nikolay Borisov Reviewed-by: Jeff Moyer Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index 583c10810e32..e09a8895fc31 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,11 +470,14 @@ extern unsigned int bvec_nr_vecs(unsigned short idx); int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM -- cgit v1.2.3 From df08c32ce3be5be138c1dbfcba203314a3a7cd6f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 31 Jul 2016 11:15:13 -0700 Subject: block: fix bdi vs gendisk lifetime mismatch The name for a bdi of a gendisk is derived from the gendisk's devt. However, since the gendisk is destroyed before the bdi it leaves a window where a new gendisk could dynamically reuse the same devt while a bdi with the same name is still live. Arrange for the bdi to hold a reference against its "owner" disk device while it is registered. Otherwise we can hit sysfs duplicate name collisions like the following: WARNING: CPU: 10 PID: 2078 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x80 sysfs: cannot create duplicate filename '/devices/virtual/bdi/259:1' Hardware name: HP ProLiant DL580 Gen8, BIOS P79 05/06/2015 0000000000000286 0000000002c04ad5 ffff88006f24f970 ffffffff8134caec ffff88006f24f9c0 0000000000000000 ffff88006f24f9b0 ffffffff8108c351 0000001f0000000c ffff88105d236000 ffff88105d1031e0 ffff8800357427f8 Call Trace: [] dump_stack+0x63/0x87 [] __warn+0xd1/0xf0 [] warn_slowpath_fmt+0x5f/0x80 [] sysfs_warn_dup+0x64/0x80 [] sysfs_create_dir_ns+0x7e/0x90 [] kobject_add_internal+0xaa/0x320 [] ? vsnprintf+0x34e/0x4d0 [] kobject_add+0x75/0xd0 [] ? mutex_lock+0x12/0x2f [] device_add+0x125/0x610 [] device_create_groups_vargs+0xd8/0x100 [] device_create_vargs+0x1c/0x20 [] bdi_register+0x8c/0x180 [] bdi_register_dev+0x27/0x30 [] add_disk+0x175/0x4a0 Cc: Reported-by: Yi Zhang Tested-by: Yi Zhang Signed-off-by: Dan Williams Fixed up missing 0 return in bdi_register_owner(). Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + include/linux/backing-dev.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 3f103076d0bf..c357f27d5483 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -163,6 +163,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 491a91717788..43b93a947e61 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -24,6 +24,7 @@ __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -- cgit v1.2.3 From 6d25ec147e3a71858bed5439c92accd7f739a0a3 Mon Sep 17 00:00:00 2001 From: John Pittman Date: Mon, 1 Aug 2016 16:35:53 -0400 Subject: Include: blkdev: Removed duplicate 'struct request;' declaration. In include/linux/blkdev.h duplicate declarations of the request struct exist. Cleaned up by removing the second, unneeded declaration. Signed-off-by: John Pittman Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index adf33079771e..de7935961c27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -47,7 +47,6 @@ struct pr_ops; */ #define BLKCG_MAX_POLS 2 -struct request; typedef void (rq_end_io_fn)(struct request *, int); #define BLK_RL_SYNCFULL (1U << 0) -- cgit v1.2.3 From abf545484d31b68777a85c5c8f5b4bcde08283eb Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 4 Aug 2016 14:23:34 -0600 Subject: mm/block: convert rw_page users to bio op use The rw_page users were not converted to use bio/req ops. As a result bdev_write_page is not passing down REQ_OP_WRITE and the IOs will be sent down as reads. Signed-off-by: Mike Christie Fixes: 4e1b2d52a80d ("block, fs, drivers: remove REQ_OP compat defs and related code") Modified by me to: 1) Drop op_flags passing into ->rw_page(), as we don't use it. 2) Make op_is_write() and friends safe to use for !CONFIG_BLOCK Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 22 +++++++++++----------- include/linux/blkdev.h | 2 +- include/linux/fs.h | 3 ++- include/linux/pagemap.h | 2 +- 4 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb264924..14b28ff2caf8 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,6 +18,17 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ +}; + +#define REQ_OP_BITS 3 + #ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and @@ -228,17 +239,6 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ -}; - -#define REQ_OP_BITS 3 - typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index de7935961c27..ccd68c0d01de 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1672,7 +1672,7 @@ struct blk_dax_ctl { struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); + int (*rw_page)(struct block_device *, sector_t, struct page *, int op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, diff --git a/include/linux/fs.h b/include/linux/fs.h index f3f0b4c8e8ac..498255e6914e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2480,12 +2480,13 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK static inline bool op_is_write(unsigned int op) { return op == REQ_OP_READ ? false : true; } +#ifdef CONFIG_BLOCK + /* * return data direction, READ or WRITE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 81363b834900..45786374abbd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -void page_endio(struct page *page, int rw, int err); +void page_endio(struct page *page, int op, int err); /* * Add an arbitrary waiter to a page's wait queue -- cgit v1.2.3 From 34b58355ad1d9987267f071265a7de6c8e00662a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Fri, 5 Aug 2016 18:36:10 +0900 Subject: drm/ttm: Wait for a BO to become idle before unbinding it from GTT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes hangs under memory pressure, e.g. running the piglit test tex3d-maxsize concurrently with other tests. Fixes: 17d33bc9d6ef ("drm/ttm: drop waiting for idle in ttm_bo_evict.") Reviewed-by: Christian König Signed-off-by: Michel Dänzer Signed-off-by: Alex Deucher --- include/drm/ttm/ttm_bo_driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 4348d6d5877a..99c6d01d24f2 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -962,6 +962,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev, * * @bo: A pointer to a struct ttm_buffer_object. * @evict: 1: This is an eviction. Don't try to pipeline. + * @interruptible: Sleep interruptible if waiting. * @no_wait_gpu: Return immediately if the GPU is busy. * @new_mem: struct ttm_mem_reg indicating where to move. * @@ -976,7 +977,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev, */ extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo, - bool evict, bool no_wait_gpu, + bool evict, bool interruptible, bool no_wait_gpu, struct ttm_mem_reg *new_mem); /** -- cgit v1.2.3 From 3851f1cdb2b8d507b10395fc110d4c37d6121285 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 4 Aug 2016 00:08:45 -0400 Subject: SUNRPC: Limit the reconnect backoff timer to the max RPC message timeout ...and ensure that we propagate it to new transports on the same client. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5e3e1b63dbb3..a16070dd03ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -218,7 +218,8 @@ struct rpc_xprt { struct work_struct task_cleanup; struct timer_list timer; unsigned long last_used, - idle_timeout; + idle_timeout, + max_reconnect_timeout; /* * Send stuff -- cgit v1.2.3 From 8d480326c3d6921ff5f1cc988c993bd572248deb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 5 Aug 2016 19:03:31 -0400 Subject: NFSv4: Cap the transport reconnection timer at 1/2 lease period We don't want to miss a lease period renewal due to the TCP connection failing to reconnect in a timely fashion. To ensure this doesn't happen, cap the reconnection timer so that we retry the connection attempt at least every 1/2 lease period. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b6810c92b8bb..5c02b0691587 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -195,6 +195,8 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); +void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + unsigned long timeo); const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ -- cgit v1.2.3 From c11f0c0b5bb949673e4fc16c742f0316ae4ced20 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2016 08:11:04 -0600 Subject: block/mm: make bdev_ops->rw_page() take a bool for read/write Commit abf545484d31 changed it from an 'rw' flags type to the newer ops based interface, but now we're effectively leaking some bdev internals to the rest of the kernel. Since we only care about whether it's a read or a write at that level, just pass in a bool 'is_write' parameter instead. Then we can also move op_is_write() and friends back under CONFIG_BLOCK protection. Reviewed-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 22 +++++++++++----------- include/linux/blkdev.h | 2 +- include/linux/fs.h | 3 +-- include/linux/pagemap.h | 2 +- 4 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 14b28ff2caf8..f254eb264924 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,17 +18,6 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ -}; - -#define REQ_OP_BITS 3 - #ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and @@ -239,6 +228,17 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ +}; + +#define REQ_OP_BITS 3 + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ccd68c0d01de..2c210b6a7bcf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1672,7 +1672,7 @@ struct blk_dax_ctl { struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, int op); + int (*rw_page)(struct block_device *, sector_t, struct page *, bool); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, diff --git a/include/linux/fs.h b/include/linux/fs.h index 33f0e96db06f..3523bf62f328 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2480,13 +2480,12 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); +#ifdef CONFIG_BLOCK static inline bool op_is_write(unsigned int op) { return op == REQ_OP_READ ? false : true; } -#ifdef CONFIG_BLOCK - /* * return data direction, READ or WRITE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 45786374abbd..66a1260b33de 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -void page_endio(struct page *page, int op, int err); +void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue -- cgit v1.2.3 From 1eff9d322a444245c67515edb52bc0eb68374aa8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2016 15:35:16 -0600 Subject: block: rename bio bi_rw to bi_opf Since commit 63a4cc24867d, bio->bi_rw contains flags in the lower portion and the op code in the higher portions. This means that old code that relies on manually setting bi_rw is most likely going to be broken. Instead of letting that brokeness linger, rename the member, to force old and out-of-tree code to break at compile time instead of at runtime. No intended functional changes in this commit. Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- include/linux/blk-cgroup.h | 4 ++-- include/linux/blk_types.h | 15 ++++++++------- include/trace/events/bcache.h | 8 ++++---- include/trace/events/block.h | 14 +++++++------- 5 files changed, 23 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/bio.h b/include/linux/bio.h index e09a8895fc31..59ffaa68b11b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -95,7 +95,7 @@ static inline bool bio_is_rw(struct bio *bio) static inline bool bio_mergeable(struct bio *bio) { - if (bio->bi_rw & REQ_NOMERGE_FLAGS) + if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; @@ -318,7 +318,7 @@ struct bio_integrity_payload { static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { - if (bio->bi_rw & REQ_INTEGRITY) + if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f77150a4a96a..10648e300c93 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -714,9 +714,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_rw, + blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_rw, 1); + blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1); } rcu_read_unlock(); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb264924..436f43f87da9 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -27,8 +27,9 @@ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; int bi_error; - unsigned int bi_rw; /* bottom bits req flags, - * top bits REQ_OP + unsigned int bi_opf; /* bottom bits req flags, + * top bits REQ_OP. Use + * accessors. */ unsigned short bi_flags; /* status, command, etc */ unsigned short bi_ioprio; @@ -89,13 +90,13 @@ struct bio { }; #define BIO_OP_SHIFT (8 * sizeof(unsigned int) - REQ_OP_BITS) -#define bio_op(bio) ((bio)->bi_rw >> BIO_OP_SHIFT) +#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) #define bio_set_op_attrs(bio, op, op_flags) do { \ WARN_ON(op >= (1 << REQ_OP_BITS)); \ - (bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1); \ - (bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT); \ - (bio)->bi_rw |= op_flags; \ + (bio)->bi_opf &= ((1 << BIO_OP_SHIFT) - 1); \ + (bio)->bi_opf |= ((unsigned int) (op) << BIO_OP_SHIFT); \ + (bio)->bi_opf |= op_flags; \ } while (0) #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) @@ -138,7 +139,7 @@ struct bio { /* * Request flags. For use in the cmd_flags field of struct request, and in - * bi_rw of struct bio. Note that some flags are only valid in either one. + * bi_opf of struct bio. Note that some flags are only valid in either one. */ enum rq_flag_bits { /* common flags */ diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index 65673d8b81ac..d336b890e31f 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -27,7 +27,7 @@ DECLARE_EVENT_CLASS(bcache_request, __entry->sector = bio->bi_iter.bi_sector; __entry->orig_sector = bio->bi_iter.bi_sector - 16; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -102,7 +102,7 @@ DECLARE_EVENT_CLASS(bcache_bio, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -138,7 +138,7 @@ TRACE_EVENT(bcache_read, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); __entry->cache_hit = hit; __entry->bypass = bypass; @@ -170,7 +170,7 @@ TRACE_EVENT(bcache_write, __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); __entry->writeback = writeback; __entry->bypass = bypass; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 5a2a7592068f..8f3a163b8166 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -274,7 +274,7 @@ TRACE_EVENT(block_bio_bounce, bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -313,7 +313,7 @@ TRACE_EVENT(block_bio_complete, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = error; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -341,7 +341,7 @@ DECLARE_EVENT_CLASS(block_bio_merge, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -409,7 +409,7 @@ TRACE_EVENT(block_bio_queue, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -439,7 +439,7 @@ DECLARE_EVENT_CLASS(block_get_rq, __entry->sector = bio ? bio->bi_iter.bi_sector : 0; __entry->nr_sector = bio ? bio_sectors(bio) : 0; blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0, - bio ? bio->bi_rw : 0, __entry->nr_sector); + bio ? bio->bi_opf : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -573,7 +573,7 @@ TRACE_EVENT(block_split, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -617,7 +617,7 @@ TRACE_EVENT(block_bio_remap, __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), -- cgit v1.2.3 From 202b52b7fbf70858609ec20829c7d69a13ffa351 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 3 Aug 2016 16:04:09 +0100 Subject: drm: Track drm_mm nodes with an interval tree In addition to the last-in/first-out stack for accessing drm_mm nodes, we occasionally and in the future often want to find a drm_mm_node by an address. To do so efficiently we need to track the nodes in an interval tree - lookups for a particular address will then be O(lg(N)), where N is the number of nodes in the range manager as opposed to O(N). Insertion however gains an extra O(lg(N)) step for all nodes irrespective of whether the interval tree is in use. For future i915 patches, eliminating the linear walk is a significant improvement. v2: Use generic interval-tree template for u64 and faster insertion. Signed-off-by: Chris Wilson Cc: David Herrmann Cc: dri-devel@lists.freedesktop.org Reviewed-by: David Herrmann Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470236651-678-1-git-send-email-chris@chris-wilson.co.uk --- include/drm/drm_mm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index fc65118e5077..205ddcf6d55d 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -37,6 +37,7 @@ * Generic range manager structs */ #include +#include #include #include #include @@ -61,6 +62,7 @@ enum drm_mm_allocator_flags { struct drm_mm_node { struct list_head node_list; struct list_head hole_stack; + struct rb_node rb; unsigned hole_follows : 1; unsigned scanned_block : 1; unsigned scanned_prev_free : 1; @@ -70,6 +72,7 @@ struct drm_mm_node { unsigned long color; u64 start; u64 size; + u64 __subtree_last; struct drm_mm *mm; }; @@ -79,6 +82,9 @@ struct drm_mm { /* head_node.node_list is the list of all memory nodes, ordered * according to the (increasing) start address of the memory node. */ struct drm_mm_node head_node; + /* Keep an interval_tree for fast lookup of drm_mm_nodes by address. */ + struct rb_root interval_tree; + unsigned int scan_check_range : 1; unsigned scan_alignment; unsigned long scan_color; @@ -295,6 +301,12 @@ void drm_mm_init(struct drm_mm *mm, void drm_mm_takedown(struct drm_mm *mm); bool drm_mm_clean(struct drm_mm *mm); +struct drm_mm_node * +drm_mm_interval_first(struct drm_mm *mm, u64 start, u64 last); + +struct drm_mm_node * +drm_mm_interval_next(struct drm_mm_node *node, u64 start, u64 last); + void drm_mm_init_scan(struct drm_mm *mm, u64 size, unsigned alignment, -- cgit v1.2.3 From db2395eccf0829de5eb54625167f6cbc3faa1418 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 3 Aug 2016 16:04:10 +0100 Subject: drm: Convert drm_vma_manager to embedded interval-tree in drm_mm Having added an interval-tree to struct drm_mm, we can replace the auxiliary rb-tree inside the drm_vma_manager with it. Signed-off-by: Chris Wilson Cc: David Herrmann Cc: dri-devel@lists.freedesktop.org Reviewed-by: David Herrmann Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470236651-678-2-git-send-email-chris@chris-wilson.co.uk --- include/drm/drm_vma_manager.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 06ea8e077ec2..afba6fcac853 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -40,13 +40,11 @@ struct drm_vma_offset_file { struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; - struct rb_node vm_rb; struct rb_root vm_files; }; struct drm_vma_offset_manager { rwlock_t vm_lock; - struct rb_root vm_addr_space_rb; struct drm_mm vm_addr_space_mm; }; -- cgit v1.2.3 From a3ccc461668951c14b7c656233b993f0dea326ce Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Wed, 3 Aug 2016 20:04:25 +0200 Subject: drm: rename DRM_MINOR_LEGACY to DRM_MINOR_PRIMARY The minor referred to by "DRM_MINOR_LEGACY" is called 'dev->primary' and gets 'cardX' as name assigned. Lets reduce this magnificent number of names for the same concept by one and rename DRM_MINOR_LEGACY to DRM_MINOR_PRIMARY (to match the actual struct-member name). Furthermore, this is in no way a legacy node, so lets not call it that. Signed-off-by: David Herrmann Reviewed-by: Frank Binns Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20160803180432.1341-2-dh.herrmann@gmail.com --- include/drm/drmP.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index d3778652e462..d488a7230b93 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -642,7 +642,7 @@ struct drm_driver { }; enum drm_minor_type { - DRM_MINOR_LEGACY, + DRM_MINOR_PRIMARY, DRM_MINOR_CONTROL, DRM_MINOR_RENDER, DRM_MINOR_CNT, @@ -856,7 +856,7 @@ static inline bool drm_is_control_client(const struct drm_file *file_priv) static inline bool drm_is_primary_client(const struct drm_file *file_priv) { - return file_priv->minor->type == DRM_MINOR_LEGACY; + return file_priv->minor->type == DRM_MINOR_PRIMARY; } /******************************************************************/ -- cgit v1.2.3 From 3cbf6a5deb2f4a469de7a90a3cc169e8fcba95e2 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 3 Aug 2016 21:11:09 +0200 Subject: drm: Mark up legacy/dri1 drivers with DRM_LEGACY It's super confusing that new drivers need to be marked with DRIVER_MODESET when really it means DRIVER_MODERN. Much better to invert the meaning and rename it to something that's suitably off-putting. Since there's over 100 places using DRIVER_MODESET we need to roll out this change without a flag day. v2: Update docs. Reviewed-by: Frank Binns Reviewed-by: David Herrmann Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470251470-30830-1-git-send-email-daniel.vetter@ffwll.ch --- include/drm/drmP.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index d488a7230b93..856c174bd730 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -146,6 +146,7 @@ void drm_err(const char *format, ...); /* driver capabilities and requirements mask */ #define DRIVER_USE_AGP 0x1 +#define DRIVER_LEGACY 0x2 #define DRIVER_PCI_DMA 0x8 #define DRIVER_SG 0x10 #define DRIVER_HAVE_DMA 0x20 -- cgit v1.2.3 From d72daa0d75e8fe71368113350254b9da2c64b235 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lothar=20Wa=C3=9Fmann?= Date: Tue, 12 Jul 2016 15:30:02 +0200 Subject: drm: add a helper function to extract 'de-active' and 'pixelclk-active' from DT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit add a helper function to extract information about pixel clock and DE polarity from DT for use by of_get_drm_display_mode(). While at it, convert spaces to tabs in indentation in drm_modes.h. Signed-off-by: Lothar Waßmann Signed-off-by: Philipp Zabel --- include/drm/drm_modes.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index ff481770d76b..a8164d2336e6 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -434,7 +434,7 @@ struct drm_cmdline_mode; struct drm_display_mode *drm_mode_create(struct drm_device *dev); void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode); void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out, - const struct drm_display_mode *in); + const struct drm_display_mode *in); int drm_mode_convert_umode(struct drm_display_mode *out, const struct drm_mode_modeinfo *in); void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode); @@ -457,6 +457,7 @@ void drm_display_mode_from_videomode(const struct videomode *vm, struct drm_display_mode *dmode); void drm_display_mode_to_videomode(const struct drm_display_mode *dmode, struct videomode *vm); +void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags); int of_get_drm_display_mode(struct device_node *np, struct drm_display_mode *dmode, int index); -- cgit v1.2.3 From fafc79ef2e9148d0085585b6b71bc7154c14ebb6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lothar=20Wa=C3=9Fmann?= Date: Tue, 12 Jul 2016 15:30:03 +0200 Subject: drm/imx: convey the pixelclk-active and de-active flags from DT to the ipu-di driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The 'de-active' and 'pixelclk-active' DT properties are evaluated by of_parse_display_timing() called from of_get_drm_display_mode(), but later lost in the conversion from videomode.flags to drm_display_mode.flags. Enhance of_get_drm_display_mode() to also return the bus flags in a separate variable, so that they can be passed on to the ipu-di driver. Signed-off-by: Lothar Waßmann Signed-off-by: Philipp Zabel --- include/drm/drm_modes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index a8164d2336e6..48e1a56ea283 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -459,7 +459,7 @@ void drm_display_mode_to_videomode(const struct drm_display_mode *dmode, struct videomode *vm); void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags); int of_get_drm_display_mode(struct device_node *np, - struct drm_display_mode *dmode, + struct drm_display_mode *dmode, u32 *bus_flags, int index); void drm_mode_set_name(struct drm_display_mode *mode); -- cgit v1.2.3 From e5e8690ff0cd88e42153fbefcbfcbdb726a1a283 Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Tue, 19 Jul 2016 18:11:00 -0700 Subject: gpu: ipu-cpmem: Add ipu_cpmem_set_uv_offset() Adds ipu_cpmem_set_uv_offset(), to set planar U/V offsets. Signed-off-by: Steve Longerbeam Signed-off-by: Philipp Zabel --- include/video/imx-ipu-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 7adeaae06961..69c86585452a 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -184,6 +184,7 @@ void ipu_cpmem_set_resolution(struct ipuv3_channel *ch, int xres, int yres); void ipu_cpmem_set_stride(struct ipuv3_channel *ch, int stride); void ipu_cpmem_set_high_priority(struct ipuv3_channel *ch); void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf); +void ipu_cpmem_set_uv_offset(struct ipuv3_channel *ch, u32 u_off, u32 v_off); void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride); void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id); void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize); -- cgit v1.2.3 From 03085911d7bbe1132977302fe45ec4efea29cd3d Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Tue, 19 Jul 2016 18:11:01 -0700 Subject: gpu: ipu-cpmem: Add ipu_cpmem_get_burstsize() Adds ipu_cpmem_get_burstsize(). Signed-off-by: Steve Longerbeam Signed-off-by: Philipp Zabel --- include/video/imx-ipu-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 69c86585452a..8c4312ddc46c 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -187,6 +187,7 @@ void ipu_cpmem_set_buffer(struct ipuv3_channel *ch, int bufnum, dma_addr_t buf); void ipu_cpmem_set_uv_offset(struct ipuv3_channel *ch, u32 u_off, u32 v_off); void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride); void ipu_cpmem_set_axi_id(struct ipuv3_channel *ch, u32 id); +int ipu_cpmem_get_burstsize(struct ipuv3_channel *ch); void ipu_cpmem_set_burstsize(struct ipuv3_channel *ch, int burstsize); void ipu_cpmem_set_block_mode(struct ipuv3_channel *ch); void ipu_cpmem_set_rotation(struct ipuv3_channel *ch, -- cgit v1.2.3 From 572a7615aeddc881057a4653658731c8bfac7d86 Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Tue, 19 Jul 2016 18:11:02 -0700 Subject: gpu: ipu-v3: Add ipu_get_num() Adds of-alias id to ipu_soc and retrieve with ipu_get_num(). Signed-off-by: Steve Longerbeam Signed-off-by: Philipp Zabel --- include/video/imx-ipu-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index 8c4312ddc46c..ef54634652e9 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -138,6 +138,7 @@ int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel, /* * IPU Common functions */ +int ipu_get_num(struct ipu_soc *ipu); void ipu_set_csi_src_mux(struct ipu_soc *ipu, int csi_id, bool mipi_csi2); void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi); void ipu_dump(struct ipu_soc *ipu); -- cgit v1.2.3 From 97afc25c4392105ea031e6f643f659058161c7dc Mon Sep 17 00:00:00 2001 From: Steve Longerbeam Date: Tue, 19 Jul 2016 18:11:05 -0700 Subject: gpu: ipu-v3: Add VDI input IDMAC channels Adds the VDIC field input IDMAC channels. These channels transfer fields F(n-1), F(n), and F(N+1) from memory to the VDIC (channels 8, 9, 10 respectively). Signed-off-by: Steve Longerbeam Signed-off-by: Philipp Zabel --- include/video/imx-ipu-v3.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index ef54634652e9..c4ccc7944cef 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -97,6 +97,9 @@ enum ipu_channel_irq { #define IPUV3_CHANNEL_CSI2 2 #define IPUV3_CHANNEL_CSI3 3 #define IPUV3_CHANNEL_VDI_MEM_IC_VF 5 +#define IPUV3_CHANNEL_MEM_VDI_PREV 8 +#define IPUV3_CHANNEL_MEM_VDI_CUR 9 +#define IPUV3_CHANNEL_MEM_VDI_NEXT 10 #define IPUV3_CHANNEL_MEM_IC_PP 11 #define IPUV3_CHANNEL_MEM_IC_PRP_VF 12 #define IPUV3_CHANNEL_G_MEM_IC_PRP_VF 14 -- cgit v1.2.3 From bc0a338750bb3940bf274c728a32f96da542dafc Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 30 Jul 2014 14:10:51 +0200 Subject: gpu: ipu-v3: Add missing IDMAC channel names This patch adds the remaining missing IDMAC channel names: VDIC channels for combining, the separate alpha channels for the MEM->IC and MEM->DC ASYNC channels, and the DC read, command, and output mask channels. Signed-off-by: Philipp Zabel --- include/video/imx-ipu-v3.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h index c4ccc7944cef..c3de7406474b 100644 --- a/include/video/imx-ipu-v3.h +++ b/include/video/imx-ipu-v3.h @@ -102,18 +102,29 @@ enum ipu_channel_irq { #define IPUV3_CHANNEL_MEM_VDI_NEXT 10 #define IPUV3_CHANNEL_MEM_IC_PP 11 #define IPUV3_CHANNEL_MEM_IC_PRP_VF 12 +#define IPUV3_CHANNEL_VDI_MEM_RECENT 13 #define IPUV3_CHANNEL_G_MEM_IC_PRP_VF 14 #define IPUV3_CHANNEL_G_MEM_IC_PP 15 +#define IPUV3_CHANNEL_G_MEM_IC_PRP_VF_ALPHA 17 +#define IPUV3_CHANNEL_G_MEM_IC_PP_ALPHA 18 +#define IPUV3_CHANNEL_MEM_VDI_PLANE1_COMB_ALPHA 19 #define IPUV3_CHANNEL_IC_PRP_ENC_MEM 20 #define IPUV3_CHANNEL_IC_PRP_VF_MEM 21 #define IPUV3_CHANNEL_IC_PP_MEM 22 #define IPUV3_CHANNEL_MEM_BG_SYNC 23 #define IPUV3_CHANNEL_MEM_BG_ASYNC 24 +#define IPUV3_CHANNEL_MEM_VDI_PLANE1_COMB 25 +#define IPUV3_CHANNEL_MEM_VDI_PLANE3_COMB 26 #define IPUV3_CHANNEL_MEM_FG_SYNC 27 #define IPUV3_CHANNEL_MEM_DC_SYNC 28 #define IPUV3_CHANNEL_MEM_FG_ASYNC 29 #define IPUV3_CHANNEL_MEM_FG_SYNC_ALPHA 31 +#define IPUV3_CHANNEL_MEM_FG_ASYNC_ALPHA 33 +#define IPUV3_CHANNEL_DC_MEM_READ 40 #define IPUV3_CHANNEL_MEM_DC_ASYNC 41 +#define IPUV3_CHANNEL_MEM_DC_COMMAND 42 +#define IPUV3_CHANNEL_MEM_DC_COMMAND2 43 +#define IPUV3_CHANNEL_MEM_DC_OUTPUT_MASK 44 #define IPUV3_CHANNEL_MEM_ROT_ENC 45 #define IPUV3_CHANNEL_MEM_ROT_VF 46 #define IPUV3_CHANNEL_MEM_ROT_PP 47 @@ -121,6 +132,7 @@ enum ipu_channel_irq { #define IPUV3_CHANNEL_ROT_VF_MEM 49 #define IPUV3_CHANNEL_ROT_PP_MEM 50 #define IPUV3_CHANNEL_MEM_BG_SYNC_ALPHA 51 +#define IPUV3_CHANNEL_MEM_BG_ASYNC_ALPHA 52 int ipu_map_irq(struct ipu_soc *ipu, int irq); int ipu_idmac_channel_irq(struct ipu_soc *ipu, struct ipuv3_channel *channel, -- cgit v1.2.3 From fe4a11c935ca675021b30051f08f3c5ab066f5bb Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Fri, 22 Jul 2016 12:20:47 +0200 Subject: drm/atomic-helper: Add atomic_mode_set helper callback Some encoders need more information from crtc and connector state or connector display info than just the mode during mode setting. This patch adds an atomic encoder mode setting variant that passes the crtc state (which contains the modes) and the connector state. atomic_enable/disable variants that additionally pass crtc and connector state don't seem to be necessary for any current driver. mode_fixup already has an atomic equivalent in atomic_check. Signed-off-by: Philipp Zabel Reviewed-by: Daniel Vetter --- include/drm/drm_modeset_helper_vtables.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index b55f21857a98..686feec6b4c8 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -523,11 +523,40 @@ struct drm_encoder_helper_funcs { * * This callback is used both by the legacy CRTC helpers and the atomic * modeset helpers. It is optional in the atomic helpers. + * + * NOTE: + * + * If the driver uses the atomic modeset helpers and needs to inspect + * the connector state or connector display info during mode setting, + * @atomic_mode_set can be used instead. */ void (*mode_set)(struct drm_encoder *encoder, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); + /** + * @atomic_mode_set: + * + * This callback is used to update the display mode of an encoder. + * + * Note that the display pipe is completely off when this function is + * called. Drivers which need hardware to be running before they program + * the new display mode (because they implement runtime PM) should not + * use this hook, because the helper library calls it only once and not + * every time the display pipeline is suspended using either DPMS or the + * new "ACTIVE" property. Such drivers should instead move all their + * encoder setup into the ->enable() callback. + * + * This callback is used by the atomic modeset helpers in place of the + * @mode_set callback, if set by the driver. It is optional and should + * be used instead of @mode_set if the driver needs to inspect the + * connector state or display info, since there is no direct way to + * go from the encoder to the current connector. + */ + void (*atomic_mode_set)(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state); + /** * @get_crtc: * -- cgit v1.2.3 From 31ad61e4afa53a7b2e364f7c021546fbc6ce0d85 Mon Sep 17 00:00:00 2001 From: Joonas Lahtinen Date: Fri, 29 Jul 2016 08:50:05 +0300 Subject: drm: BIT(DRM_ROTATE_?) -> DRM_ROTATE_? MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only property creation uses the rotation as an index, so convert the to figure the index when needed. v2: Use the new defines to build the _MASK defines (Sean) Cc: intel-gfx@lists.freedesktop.org Cc: linux-arm-msm@vger.kernel.org Cc: freedreno@lists.freedesktop.org Cc: malidp@foss.arm.com Cc: David Airlie Cc: Daniel Vetter Cc: Ville Syrjälä Cc: Liviu Dudau Cc: Sean Paul Acked-by: Liviu Dudau Reviewed-by: Ville Syrjälä (v1) Signed-off-by: Joonas Lahtinen Signed-off-by: Sean Paul Link: http://patchwork.freedesktop.org/patch/msgid/1469771405-17653-1-git-send-email-joonas.lahtinen@linux.intel.com --- include/drm/drm_crtc.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 44e070800b6d..6c12fec20e37 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -83,14 +83,15 @@ static inline uint64_t I642U64(int64_t val) * specified amount in degrees in counter clockwise direction. DRM_REFLECT_X and * DRM_REFLECT_Y reflects the image along the specified axis prior to rotation */ -#define DRM_ROTATE_MASK 0x0f -#define DRM_ROTATE_0 0 -#define DRM_ROTATE_90 1 -#define DRM_ROTATE_180 2 -#define DRM_ROTATE_270 3 -#define DRM_REFLECT_MASK (~DRM_ROTATE_MASK) -#define DRM_REFLECT_X 4 -#define DRM_REFLECT_Y 5 +#define DRM_ROTATE_0 BIT(0) +#define DRM_ROTATE_90 BIT(1) +#define DRM_ROTATE_180 BIT(2) +#define DRM_ROTATE_270 BIT(3) +#define DRM_ROTATE_MASK (DRM_ROTATE_0 | DRM_ROTATE_90 | \ + DRM_ROTATE_180 | DRM_ROTATE_270) +#define DRM_REFLECT_X BIT(4) +#define DRM_REFLECT_Y BIT(5) +#define DRM_REFLECT_MASK (DRM_REFLECT_X | DRM_REFLECT_Y) enum drm_connector_force { DRM_FORCE_UNSPECIFIED, -- cgit v1.2.3 From d7da824d9edeb7d83676c11d800b8243d87eafbf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 26 Jul 2016 19:06:57 +0300 Subject: drm: Store clipped src/dst coordinatee in drm_plane_state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pretty much all driver will have need for the clipped plane coordinates, so let's stuff then into drm_plane_state. Signed-off-by: Ville Syrjälä Signed-off-by: Sean Paul Link: http://patchwork.freedesktop.org/patch/msgid/1469549224-1860-3-git-send-email-ville.syrjala@linux.intel.com --- include/drm/drm_crtc.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 6c12fec20e37..b618b506b04d 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -35,6 +35,7 @@ #include #include #include +#include struct drm_device; struct drm_mode_set; @@ -1415,6 +1416,9 @@ struct drm_connector { * @zpos: priority of the given plane on crtc (optional) * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1 * where N is the number of active planes for given crtc + * @src: clipped source coordinates of the plane (in 16.16) + * @dst: clipped destination coordinates of the plane + * @visible: visibility of the plane * @state: backpointer to global drm_atomic_state */ struct drm_plane_state { @@ -1439,6 +1443,15 @@ struct drm_plane_state { unsigned int zpos; unsigned int normalized_zpos; + /* Clipped coordinates */ + struct drm_rect src, dst; + + /* + * Is the plane actually visible? Can be false even + * if fb!=NULL and crtc!=NULL, due to clipping. + */ + bool visible; + struct drm_atomic_state *state; }; -- cgit v1.2.3 From df86af9133b4958a04c44828d29617eb1a6ff31c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Mon, 8 Aug 2016 10:55:10 +0300 Subject: drm/plane-helper: Add drm_plane_helper_check_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a version of drm_plane_helper_check_update() which takes a plane state instead of having the caller pass in everything. And to reduce code duplication, let's reimplement drm_plane_helper_check_update() in terms of the new function, by having a tempororary plane state on the stack. v2: Add a note that the functions modifies the state (Chris) v3: Fix drm_plane_helper_check_update() y coordinates (Daniel Kurtz) Cc: Daniel Kurtz Cc: Chris Wilson Signed-off-by: Ville Syrjälä Reviewed-by: Sean Paul (v2) Signed-off-by: Ville Syrjälä Signed-off-by: Sean Paul Link: http://patchwork.freedesktop.org/patch/msgid/1470642910-14073-1-git-send-email-ville.syrjala@linux.intel.com --- include/drm/drm_plane_helper.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h index 0e0c3573cce0..fbc8ecb3e5e8 100644 --- a/include/drm/drm_plane_helper.h +++ b/include/drm/drm_plane_helper.h @@ -40,6 +40,11 @@ int drm_crtc_init(struct drm_device *dev, struct drm_crtc *crtc, const struct drm_crtc_funcs *funcs); +int drm_plane_helper_check_state(struct drm_plane_state *state, + const struct drm_rect *clip, + int min_scale, int max_scale, + bool can_position, + bool can_update_disabled); int drm_plane_helper_check_update(struct drm_plane *plane, struct drm_crtc *crtc, struct drm_framebuffer *fb, -- cgit v1.2.3 From 1bd4403d86a1c06cb6cc9ac87664a0c9d3413d51 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Aug 2016 13:02:01 -0700 Subject: unsafe_[get|put]_user: change interface to use a error target label When I initially added the unsafe_[get|put]_user() helpers in commit 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses"), I made the mistake of modeling the interface on our traditional __[get|put]_user() functions, which return zero on success, or -EFAULT on failure. That interface is fairly easy to use, but it's actually fairly nasty for good code generation, since it essentially forces the caller to check the error value for each access. In particular, since the error handling is already internally implemented with an exception handler, and we already use "asm goto" for various other things, we could fairly easily make the error cases just jump directly to an error label instead, and avoid the need for explicit checking after each operation. So switch the interface to pass in an error label, rather than checking the error value in the caller. Best do it now before we start growing more users (the signal handling code in particular would be a good place to use the new interface). So rather than if (unsafe_get_user(x, ptr)) ... handle error .. the interface is now unsafe_get_user(x, ptr, label); where an error during the user mode fetch will now just cause a jump to 'label' in the caller. Right now the actual _implementation_ of this all still ends up being a "if (err) goto label", and does not take advantage of any exception label tricks, but for "unsafe_put_user()" in particular it should be fairly straightforward to convert to using the exception table model. Note that "unsafe_get_user()" is much harder to convert to a clever exception table model, because current versions of gcc do not allow the use of "asm goto" (for the exception) with output values (for the actual value to be fetched). But that is hopefully not a limitation in the long term. [ Also note that it might be a good idea to switch unsafe_get_user() to actually _return_ the value it fetches from user space, but this commit only changes the error handling semantics ] Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 349557825428..f30c187ed785 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -114,8 +114,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin() do { } while (0) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr) __get_user(x, ptr) -#define unsafe_put_user(x, ptr) __put_user(x, ptr) +#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) +#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) #endif #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From cbd74e1bc8129efb9908f130a8a6e60fd95d2106 Mon Sep 17 00:00:00 2001 From: Philippe Bergheaud Date: Fri, 5 Aug 2016 14:02:00 +0200 Subject: cxl: Use fixed width predefined types in data structure. This patch fixes a regression introduced by commit b810253bd934 ("cxl: Add mechanism for delivering AFU driver specific events"). It changes the type u8 to __u8 in the uapi header cxl.h, because the former is a kernel internal type, and may not be defined in userland build environments, in particular when cross-compiling libcxl on x86_64 linux machines (RHEL6.7 and Ubuntu 16.04). This patch also changes the size of the field data_size, and makes it constant, to support 32-bit userland applications running on big-endian ppc64 kernels transparently. mpe: This is an ABI change, however the ABI was only added during the 4.8 merge window so has never been part of a released kernel - therefore we give ourselves permission to change it. Fixes: b810253bd934 ("cxl: Add mechanism for delivering AFU driver specific events") Signed-off-by: Philippe Bergheaud Reviewed-by: Frederic Barrat Signed-off-by: Michael Ellerman --- include/uapi/misc/cxl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index cbae529b7ce0..180d526a55c3 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -136,8 +136,8 @@ struct cxl_event_afu_driver_reserved { * * Of course the contents will be ABI, but that's up the AFU driver. */ - size_t data_size; - u8 data[]; + __u32 data_size; + __u8 data[]; }; struct cxl_event { -- cgit v1.2.3 From f3b0946d629c8bfbd3e5f038e30cb9c711a35f10 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Jul 2016 17:18:33 +0100 Subject: genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada Reported-and-tested-by: Foster Snowhill Reported-by: Matthias Prager Reported-by: Jason Taylor Signed-off-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/msi.h b/include/linux/msi.h index 4f0bfe5912b2..e8c81fbd5f9c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -270,6 +270,8 @@ enum { MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ MSI_FLAG_PCI_MSIX = (1 << 3), + /* Needs early activate, required for PCI */ + MSI_FLAG_ACTIVATE_EARLY = (1 << 4), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, -- cgit v1.2.3 From 28ad55578b8a76390d966b09da8c7fa3644f5140 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Fri, 5 Aug 2016 13:52:09 +0100 Subject: virtio-vsock: fix include guard typo Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_vsock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 6b011c19b50f..1d57ed3d84d2 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -32,7 +32,7 @@ */ #ifndef _UAPI_LINUX_VIRTIO_VSOCK_H -#define _UAPI_LINUX_VIRTIO_VOSCK_H +#define _UAPI_LINUX_VIRTIO_VSOCK_H #include #include -- cgit v1.2.3 From c87edb36118664f1fa275107c1138b6f47793240 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 5 Aug 2016 12:41:52 -0400 Subject: tracing: Fix tick_stop tracepoint symbols for user export The symbols used in the tick_stop tracepoint were not being converted properly into integers in the trace_stop format file. Instead we had this: print fmt: "success=%d dependency=%s", REC->success, __print_symbolic(REC->dependency, { 0, "NONE" }, { (1 << TICK_DEP_BIT_POSIX_TIMER), "POSIX_TIMER" }, { (1 << TICK_DEP_BIT_PERF_EVENTS), "PERF_EVENTS" }, { (1 << TICK_DEP_BIT_SCHED), "SCHED" }, { (1 << TICK_DEP_BIT_CLOCK_UNSTABLE), "CLOCK_UNSTABLE" }) User space tools have no idea how to parse "TICK_DEP_BIT_SCHED" or the other symbols used to do the bit shifting. The reason is that the conversion was done with using the TICK_DEP_MASK_* symbols which are just macros that convert to the BIT shift itself (with the exception of NONE, which was converted properly, because it doesn't use bits, and is defined as zero). The TICK_DEP_BIT_* needs to be denoted by TRACE_DEFINE_ENUM() in order to have this properly converted for user space tools to parse this event. Cc: stable@vger.kernel.org Cc: Frederic Weisbecker Fixes: e6e6cc22e067 ("nohz: Use enum code for tick stop failure tracing message") Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Signed-off-by: Steven Rostedt --- include/trace/events/timer.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 51440131d337..28c5da6fdfac 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -330,24 +330,32 @@ TRACE_EVENT(itimer_expire, #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ - tick_dep_name(NONE) \ + tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name_end(CLOCK_UNSTABLE) #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end -#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); -#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* The MASK will convert to their bits and they need to be processed too */ +#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* NONE only has a mask defined for it */ +#define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, +#define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ -- cgit v1.2.3 From 27528c667a210845b35a1f49c810dba469bced52 Mon Sep 17 00:00:00 2001 From: Lyude Date: Fri, 5 Aug 2016 20:30:38 -0400 Subject: drm: Add ratelimited versions of the DRM_DEBUG* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's a couple of places where this would be useful for drivers (such as reporting DP aux transaction timeouts). Signed-off-by: Lyude Reviewed-by: Christian König Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470443443-27252-7-git-send-email-cpaul@redhat.com --- include/drm/drmP.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 856c174bd730..f8e87fde611b 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -232,6 +232,36 @@ void drm_err(const char *format, ...); drm_ut_debug_printk(__func__, fmt, ##args); \ } while (0) +#define _DRM_DEFINE_DEBUG_RATELIMITED(level, fmt, args...) \ + do { \ + if (unlikely(drm_debug & DRM_UT_ ## level)) { \ + static DEFINE_RATELIMIT_STATE( \ + _rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&_rs)) { \ + drm_ut_debug_printk(__func__, fmt, \ + ##args); \ + } \ + } \ + } while (0) + +/** + * Rate limited debug output. Like DRM_DEBUG() but won't flood the log. + * + * \param fmt printf() like format string. + * \param arg arguments + */ +#define DRM_DEBUG_RATELIMITED(fmt, args...) \ + _DRM_DEFINE_DEBUG_RATELIMITED(CORE, fmt, ##args) +#define DRM_DEBUG_DRIVER_RATELIMITED(fmt, args...) \ + _DRM_DEFINE_DEBUG_RATELIMITED(DRIVER, fmt, ##args) +#define DRM_DEBUG_KMS_RATELIMITED(fmt, args...) \ + _DRM_DEFINE_DEBUG_RATELIMITED(KMS, fmt, ##args) +#define DRM_DEBUG_PRIME_RATELIMITED(fmt, args...) \ + _DRM_DEFINE_DEBUG_RATELIMITED(PRIME, fmt, ##args) + /*@}*/ /***********************************************************************/ -- cgit v1.2.3 From a0cba2179ea4c1820fce2ee046b6ed90ecc56196 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 Aug 2016 10:48:18 -0700 Subject: Revert "printk: create pr_ functions" This reverts commit 874f9c7da9a4acbc1b9e12ca722579fb50e4d142. Geert Uytterhoeven reports: "This change seems to have an (unintendent?) side-effect. Before, pr_*() calls without a trailing newline characters would be printed with a newline character appended, both on the console and in the output of the dmesg command. After this commit, no new line character is appended, and the output of the next pr_*() call of the same type may be appended, like in: - Truncating RAM at 0x0000000040000000-0x00000000c0000000 to -0x0000000070000000 - Ignoring RAM at 0x0000000200000000-0x0000000240000000 (!CONFIG_HIGHMEM) + Truncating RAM at 0x0000000040000000-0x00000000c0000000 to -0x0000000070000000Ignoring RAM at 0x0000000200000000-0x0000000240000000 (!CONFIG_HIGHMEM)" Joe Perches says: "No, that is not intentional. The newline handling code inside vprintk_emit is a bit involved and for now I suggest a revert until this has all the same behavior as earlier" Reported-by: Geert Uytterhoeven Requested-by: Joe Perches Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 48 +++++++++++++++--------------------------------- 1 file changed, 15 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 8dc155dab3ed..696a56be7d3e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -266,39 +266,21 @@ extern asmlinkage void dump_stack(void) __cold; * and other debug macros are compiled out unless either DEBUG is defined * or CONFIG_DYNAMIC_DEBUG is set. */ - -#ifdef CONFIG_PRINTK - -asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...); - -#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__) - -#else - -#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) - -#endif - -#define pr_warning pr_warn - +#define pr_emerg(fmt, ...) \ + printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert(fmt, ...) \ + printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit(fmt, ...) \ + printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) \ + printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn pr_warning +#define pr_notice(fmt, ...) \ + printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* * Like KERN_CONT, pr_cont() should only be used when continuing * a line with no newline ('\n') enclosed. Otherwise it defaults -- cgit v1.2.3 From db4a835601b73cf8d6cd8986381d966b8e13d2d9 Mon Sep 17 00:00:00 2001 From: David Carrillo-Cisneros Date: Tue, 2 Aug 2016 00:48:12 -0700 Subject: perf/core: Set cgroup in CPU contexts for new cgroup events There's a perf stat bug easy to observer on a machine with only one cgroup: $ perf stat -e cycles -I 1000 -C 0 -G / # time counts unit events 1.000161699 cycles / 2.000355591 cycles / 3.000565154 cycles / 4.000951350 cycles / We'd expect some output there. The underlying problem is that there is an optimization in perf_cgroup_sched_{in,out}() that skips the switch of cgroup events if the old and new cgroups in a task switch are the same. This optimization interacts with the current code in two ways that cause a CPU context's cgroup (cpuctx->cgrp) to be NULL even if a cgroup event matches the current task. These are: 1. On creation of the first cgroup event in a CPU: In current code, cpuctx->cpu is only set in perf_cgroup_sched_in, but due to the aforesaid optimization, perf_cgroup_sched_in will run until the next cgroup switches in that CPU. This may happen late or never happen, depending on system's number of cgroups, CPU load, etc. 2. On deletion of the last cgroup event in a cpuctx: In list_del_event, cpuctx->cgrp is set NULL. Any new cgroup event will not be sched in because cpuctx->cgrp == NULL until a cgroup switch occurs and perf_cgroup_sched_in is executed (updating cpuctx->cgrp). This patch fixes both problems by setting cpuctx->cgrp in list_add_event, mirroring what list_del_event does when removing a cgroup event from CPU context, as introduced in: commit 68cacd29167b ("perf_events: Fix stale ->cgrp pointer in update_cgrp_time_from_cpuctx()") With this patch, cpuctx->cgrp is always set/clear when installing/removing the first/last cgroup event in/from the CPU context. With cpuctx->cgrp correctly set, event_filter_match works as intended when events are sched in/out. After the fix, the output is as expected: $ perf stat -e cycles -I 1000 -a -G / # time counts unit events 1.004699159 627342882 cycles / 2.007397156 615272690 cycles / 3.010019057 616726074 cycles / Signed-off-by: David Carrillo-Cisneros Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Paul Turner Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vegard Nossum Cc: Vince Weaver Link: http://lkml.kernel.org/r/1470124092-113192-1-git-send-email-davidcc@google.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8ed4326164cc..2b6b43cc0dd5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,7 +743,9 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; +#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ +#endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; @@ -769,7 +771,9 @@ struct perf_cpu_context { unsigned int hrtimer_active; struct pmu *unique_pmu; +#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { -- cgit v1.2.3 From 2db34e8bf9a22f4e38b29deccee57457bc0e7d74 Mon Sep 17 00:00:00 2001 From: pan xinhui Date: Mon, 18 Jul 2016 17:47:39 +0800 Subject: locking/qrwlock: Fix write unlock bug on big endian systems This patch aims to get rid of endianness in queued_write_unlock(). We want to set __qrwlock->wmode to NULL, however the address is not &lock->cnts in big endian machine. That causes queued_write_unlock() write NULL to the wrong field of __qrwlock. So implement __qrwlock_write_byte() which returns the correct __qrwlock->wmode address. 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: Waiman.Long@hpe.com Cc: arnd@arndb.de Cc: boqun.feng@gmail.com Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1468835259-4486-1-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/asm-generic/qrwlock.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 54a8e65e18b6..7d026bf27713 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -25,7 +25,20 @@ #include /* - * Writer states & reader shift and bias + * Writer states & reader shift and bias. + * + * | +0 | +1 | +2 | +3 | + * ----+----+----+----+----+ + * LE | 78 | 56 | 34 | 12 | 0x12345678 + * ----+----+----+----+----+ + * | wr | rd | + * +----+----+----+----+ + * + * ----+----+----+----+----+ + * BE | 12 | 34 | 56 | 78 | 0x12345678 + * ----+----+----+----+----+ + * | rd | wr | + * +----+----+----+----+ */ #define _QW_WAITING 1 /* A writer is waiting */ #define _QW_LOCKED 0xff /* A writer holds the lock */ @@ -133,13 +146,23 @@ static inline void queued_read_unlock(struct qrwlock *lock) (void)atomic_sub_return_release(_QR_BIAS, &lock->cnts); } +/** + * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: the write byte address of a queue rwlock + */ +static inline u8 *__qrwlock_write_byte(struct qrwlock *lock) +{ + return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN); +} + /** * queued_write_unlock - release write lock of a queue rwlock * @lock : Pointer to queue rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { - smp_store_release((u8 *)&lock->cnts, 0); + smp_store_release(__qrwlock_write_byte(lock), 0); } /* -- cgit v1.2.3 From e1aaf311dbe82221910cc0e0809c988de210cc3c Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Fri, 5 Aug 2016 10:39:34 -0300 Subject: dma-buf/fence-array: add fence_is_array() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add helper to check if fence is array. v2: Comments from Chris Wilson - remove ternary if from ops comparison - add EXPORT_SYMBOL(fence_array_ops) Cc: Chris Wilson Cc: Christian König Signed-off-by: Gustavo Padovan Reviewed-by: Chris Wilson Reviewed-by: Christian König Signed-off-by: Sumit Semwal --- include/linux/fence-array.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/fence-array.h b/include/linux/fence-array.h index 86baaa45567c..a44794e508df 100644 --- a/include/linux/fence-array.h +++ b/include/linux/fence-array.h @@ -51,6 +51,16 @@ struct fence_array { extern const struct fence_ops fence_array_ops; +/** + * fence_is_array - check if a fence is from the array subsclass + * + * Return true if it is a fence_array and false otherwise. + */ +static inline bool fence_is_array(struct fence *fence) +{ + return fence->ops == &fence_array_ops; +} + /** * to_fence_array - cast a fence to a fence_array * @fence: fence to cast to a fence_array -- cgit v1.2.3 From a02b9dc90d844cc7df7b63264e7920cc425052d9 Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Fri, 5 Aug 2016 10:39:35 -0300 Subject: dma-buf/sync_file: refactor fence storage in struct sync_file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Create sync_file->fence to abstract the type of fence we are using for each sync_file. If only one fence is present we use a normal struct fence but if there is more fences to be added to the sync_file a fence_array is created. This change cleans up sync_file a bit. We don't need to have sync_file_cb array anymore. Instead, as we always have one fence, only one fence callback is registered per sync_file. v2: Comments from Chris Wilson and Christian König - Not using fence_ops anymore - fence_is_array() was created to differentiate fence from fence_array - fence_array_teardown() is now exported and used under fence_is_array() - struct sync_file lost num_fences member v3: Comments from Chris Wilson and Christian König - struct sync_file lost status member in favor of fence_is_signaled() - drop use of fence_array_teardown() - use sizeof(*fence) to allocate only an array on fence pointers v4: Comments from Chris Wilson - use sizeof(*fence) to reallocate array - fix typo in comments - protect num_fences sum against overflows - use array->base instead of casting the to struct fence v5: fixes checkpatch warnings v6: fix case where all fences are signaled. Signed-off-by: Gustavo Padovan Reviewed-by: Chris Wilson Acked-by: Christian König Acked-by: Greg Kroah-Hartman Signed-off-by: Sumit Semwal --- include/linux/sync_file.h | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index c6ffe8b0725c..2efc5ec60575 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -19,12 +19,7 @@ #include #include #include - -struct sync_file_cb { - struct fence_cb cb; - struct fence *fence; - struct sync_file *sync_file; -}; +#include /** * struct sync_file - sync file to export to the userspace @@ -32,10 +27,9 @@ struct sync_file_cb { * @kref: reference count on fence. * @name: name of sync_file. Useful for debugging * @sync_file_list: membership in global file list - * @num_fences: number of sync_pts in the fence * @wq: wait queue for fence signaling - * @status: 0: signaled, >0:active, <0: error - * @cbs: sync_pts callback information + * @fence: fence with the fences in the sync_file + * @cb: fence callback information */ struct sync_file { struct file *file; @@ -44,12 +38,11 @@ struct sync_file { #ifdef CONFIG_DEBUG_FS struct list_head sync_file_list; #endif - int num_fences; wait_queue_head_t wq; - atomic_t status; - struct sync_file_cb cbs[]; + struct fence *fence; + struct fence_cb cb; }; struct sync_file *sync_file_create(struct fence *fence); -- cgit v1.2.3 From 972526a4093243fdaf77dd7c6f8b11fba5b15864 Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Fri, 5 Aug 2016 10:39:36 -0300 Subject: dma-buf/sync_file: add sync_file_get_fence() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Creates a function that given an sync file descriptor returns a fence containing all fences in the sync_file. v2: Comments by Daniel Vetter - Adapt to new version of fence_collection_init() - Hold a reference for the fence we return v3: - Adapt to use fput() directly - rename to sync_file_get_fence() as we always return one fence v4: Adapt to use fence_array v5: set fence through fence_get() Signed-off-by: Gustavo Padovan Reviewed-by: Chris Wilson Acked-by: Christian König Signed-off-by: Sumit Semwal --- include/linux/sync_file.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 2efc5ec60575..f7de5a0b3d12 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -46,5 +46,6 @@ struct sync_file { }; struct sync_file *sync_file_create(struct fence *fence); +struct fence *sync_file_get_fence(int fd); #endif /* _LINUX_SYNC_H */ -- cgit v1.2.3 From e24165537312723e2900831dd6e7415b8d85278c Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Fri, 5 Aug 2016 10:39:38 -0300 Subject: dma-buf/sync_file: only enable fence signalling on poll() Signalling doesn't need to be enabled at sync_file creation, it is only required if userspace waiting the fence to signal through poll(). Thus we delay fence_add_callback() until poll is called. It only adds the callback the first time poll() is called. This avoid re-adding the same callback multiple times. v2: rebase and update to work with new fence support for sync_file v3: use atomic operation to set enabled and protect fence_add_callback() v4: use user bit from fence flags (comment from Chris Wilson) v5: use ternary if on poll return (comment from Chris Wilson) Signed-off-by: Gustavo Padovan Reviewed-by: Chris Wilson Signed-off-by: Sumit Semwal [sumits: remove unused var status] Link: http://patchwork.freedesktop.org/patch/msgid/1470404378-27961-1-git-send-email-gustavo@padovan.org --- include/linux/sync_file.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index f7de5a0b3d12..aa17ccfc2f57 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -45,6 +45,8 @@ struct sync_file { struct fence_cb cb; }; +#define POLL_ENABLED FENCE_FLAG_USER_BITS + struct sync_file *sync_file_create(struct fence *fence); struct fence *sync_file_get_fence(int fd); -- cgit v1.2.3 From 1ea049b2de5d803374fdbf43add23c8d1c518e7b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 11 Aug 2016 10:15:56 +0200 Subject: bvec: avoid variable shadowing warning Due to the (indirect) nesting of min(..., min(...)), sparse will show a variable shadowing warning whenever bvec.h is included. Avoid that by assigning the inner min() to a temporary variable first. Signed-off-by: Johannes Berg Signed-off-by: Jens Axboe --- include/linux/bvec.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 701b64a3b7c5..89b65b82d98f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -74,7 +74,8 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, "Attempted to advance past end of bvec iter\n"); while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + unsigned iter_len = bvec_iter_len(bv, *iter); + unsigned len = min(bytes, iter_len); bytes -= len; iter->bi_size -= len; -- cgit v1.2.3 From 44adece57e2604cec8527a499b48e4d584ab53b8 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 10 Aug 2016 18:52:34 +0200 Subject: drm/fb-helper: Add a dummy remove_conflicting_framebuffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Lots of drivers don't properly compile without this when CONFIG_FB=n. It's kinda a hack, but since CONFIG_FB doesn't stub any fucntions when it's disabled I think it makes sense to add it to drm_fb_helper.h. Long term we probably need to rethink all the logic to unload firmware framebuffer drivers, at least if we want to be able to move away from CONFIG_FB and fbcon. v2: Unfortunately just stubbing out remove_conflicting_framebuffers in drm_fb_helper.h upset gcc about static vs. non-static declarations, so a new wrapper it needs to be. Means more churn :( Cc: Tobias Jakobi Cc: Noralf Trønnes Cc: tomi.valkeinen@ti.com Cc: dh.herrmann@gmail.com Reviewed-by: Alex Deucher Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470847958-28465-2-git-send-email-daniel.vetter@ffwll.ch --- include/drm/drm_fb_helper.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index db8d4780eaa2..130c324f1aee 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -32,6 +32,7 @@ struct drm_fb_helper; +#include #include enum mode_set_atomic { @@ -282,6 +283,12 @@ drm_pick_cmdline_mode(struct drm_fb_helper_connector *fb_helper_conn, int drm_fb_helper_add_one_connector(struct drm_fb_helper *fb_helper, struct drm_connector *connector); int drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper, struct drm_connector *connector); +static inline int +drm_fb_helper_remove_conflicting_framebuffers(struct apertures_struct *a, + const char *name, bool primary) +{ + return remove_conflicting_framebuffers(a, name, primary); +} #else static inline int drm_fb_helper_modinit(void) { @@ -475,5 +482,12 @@ drm_fb_helper_remove_one_connector(struct drm_fb_helper *fb_helper, { return 0; } + +static inline int +drm_fb_helper_remove_conflicting_framebuffers(struct apertures_struct *a, + const char *name, bool primary) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 023e9fddc3616b005c3753fc1bb6526388cd7a30 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 9 Aug 2016 19:13:00 +0200 Subject: KVM: PPC: Move xics_debugfs_init out of create MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As we are about to hold the kvm->lock during the create operation on KVM devices, we should move the call to xics_debugfs_init into its own function, since holding a mutex over extended amounts of time might not be a good idea. Introduce an init operation on the kvm_device_ops struct which cannot fail and call this, if configured, after the device has been created. Signed-off-by: Christoffer Dall Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01e908ac4a39..d3c9b82812c3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1115,6 +1115,12 @@ struct kvm_device_ops { const char *name; int (*create)(struct kvm_device *dev, u32 type); + /* + * init is called after create if create is successful and is called + * outside of holding kvm->lock. + */ + void (*init)(struct kvm_device *dev); + /* * Destroy is responsible for freeing dev. * -- cgit v1.2.3 From a28ebea2adc4a2bef5989a5a181ec238f59fbcad Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 9 Aug 2016 19:13:01 +0200 Subject: KVM: Protect device ops->create and list_add with kvm->lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM devices were manipulating list data structures without any form of synchronization, and some implementations of the create operations also suffered from a lack of synchronization. Now when we've split the xics create operation into create and init, we can hold the kvm->lock mutex while calling the create operation and when manipulating the devices list. The error path in the generic code gets slightly ugly because we have to take the mutex again and delete the device from the list, but holding the mutex during anon_inode_getfd or releasing/locking the mutex in the common non-error path seemed wrong. Signed-off-by: Christoffer Dall Reviewed-by: Paolo Bonzini Acked-by: Christian Borntraeger Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d3c9b82812c3..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,6 +1113,12 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); /* -- cgit v1.2.3 From 0951e458d2ebd06e5e83fbb8a67f52dd3146d594 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Thu, 11 Aug 2016 16:17:57 +0530 Subject: dma-buf/fence: kerneldoc: remove unused struct members Commit 0431b9065f28ecf6c320fefebe0241620049984f ("staging/android: bring struct sync_pt back") removed child_list and active_list from struct fence, but left it in kernel doc. Delete them. Fixes: 0431b9065f28 ("staging/android: bring struct sync_pt back") Signed-off-by: Sumit Semwal Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470912480-32304-2-git-send-email-sumit.semwal@linaro.org --- include/linux/fence.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/fence.h b/include/linux/fence.h index 8cc719a63728..2ac6fa5f4712 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,8 +49,6 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. - * @child_list: list of children fences - * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most -- cgit v1.2.3 From 3590d50e2313644cd192ff55e83df76dea232319 Mon Sep 17 00:00:00 2001 From: Sumit Semwal Date: Thu, 11 Aug 2016 16:17:58 +0530 Subject: dma-buf/fence: kerneldoc: remove spurious section header Commit e941759c74a44d6ac2eed21bb0a38b21fe4559e2 ("fence: dma-buf cross-device synchronization (v18)") had a spurious kerneldoc section header that caused Sphinx to complain. Fix it. Fixes: e941759c74a4 ("fence: dma-buf cross-device synchronization (v18)") Signed-off-by: Sumit Semwal Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1470912480-32304-3-git-send-email-sumit.semwal@linaro.org --- include/linux/fence.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fence.h b/include/linux/fence.h index 2ac6fa5f4712..0d763053f97a 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -60,7 +60,7 @@ struct fence_cb; * implementer of the fence for its own purposes. Can be used in different * ways by different fence implementers, so do not rely on this. * - * *) Since atomic bitops are used, this is not guaranteed to be the case. + * Since atomic bitops are used, this is not guaranteed to be the case. * Particularly, if the bit was set, but fence_signal was called right * before this bit was set, it would have been able to set the * FENCE_FLAG_SIGNALED_BIT, before enable_signaling was called. -- cgit v1.2.3