From 9e8925b67a809bb27ce4b7d352d67f25cf1d7fc5 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 16 Nov 2015 09:49:34 -0500 Subject: locks: Allow disabling mandatory locking at compile time Mandatory locking appears to be almost unused and buggy and there appears no real interest in doing anything with it. Since effectively no one uses the code and since the code is buggy let's allow it to be disabled at compile time. I would just suggest removing the code but undoubtedly that will break some piece of userspace code somewhere. For the distributions that don't care about this piece of code this gives a nice starting point to make mandatory locking go away. Cc: Benjamin Coddington Cc: Dmitry Vyukov Cc: Jeff Layton Cc: J. Bruce Fields Signed-off-by: "Eric W. Biederman" Signed-off-by: Jeff Layton --- include/linux/fs.h | 74 +++++++++++++++++++++++++++++------------------------- 1 file changed, 40 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..cbf08d5c246e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2030,7 +2030,7 @@ extern struct kobject *fs_kobj; #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 -#ifdef CONFIG_FILE_LOCKING +#ifdef CONFIG_MANDATORY_FILE_LOCKING extern int locks_mandatory_locked(struct file *); extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t); @@ -2075,6 +2075,45 @@ static inline int locks_verify_truncate(struct inode *inode, return 0; } +#else /* !CONFIG_MANDATORY_FILE_LOCKING */ + +static inline int locks_mandatory_locked(struct file *file) +{ + return 0; +} + +static inline int locks_mandatory_area(int rw, struct inode *inode, + struct file *filp, loff_t offset, + size_t count) +{ + return 0; +} + +static inline int __mandatory_lock(struct inode *inode) +{ + return 0; +} + +static inline int mandatory_lock(struct inode *inode) +{ + return 0; +} + +static inline int locks_verify_locked(struct file *file) +{ + return 0; +} + +static inline int locks_verify_truncate(struct inode *inode, struct file *filp, + size_t size) +{ + return 0; +} + +#endif /* CONFIG_MANDATORY_FILE_LOCKING */ + + +#ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { /* @@ -2136,39 +2175,6 @@ static inline int break_layout(struct inode *inode, bool wait) } #else /* !CONFIG_FILE_LOCKING */ -static inline int locks_mandatory_locked(struct file *file) -{ - return 0; -} - -static inline int locks_mandatory_area(int rw, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) -{ - return 0; -} - -static inline int __mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int mandatory_lock(struct inode *inode) -{ - return 0; -} - -static inline int locks_verify_locked(struct file *file) -{ - return 0; -} - -static inline int locks_verify_truncate(struct inode *inode, struct file *filp, - size_t size) -{ - return 0; -} - static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; -- cgit v1.2.3 From 4d4142696e18cf30af319031d47bba46853a4605 Mon Sep 17 00:00:00 2001 From: Guillaume Gomez Date: Wed, 23 Sep 2015 12:34:30 +0200 Subject: percpu: Remove unneeded return from void function Signed-off-by: Guillaume Gomez Acked-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu-refcount.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 12c9b485beb7..84f542df7ff5 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -116,7 +116,7 @@ void percpu_ref_reinit(struct percpu_ref *ref); */ static inline void percpu_ref_kill(struct percpu_ref *ref) { - return percpu_ref_kill_and_confirm(ref, NULL); + percpu_ref_kill_and_confirm(ref, NULL); } /* -- cgit v1.2.3 From b916b785af99088916a122cb37de1bda3fa7f70e Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 28 Oct 2015 12:32:17 +0000 Subject: drivers/perf: kill armpmu_register Nothing outside of drivers/perf/arm_pmu.c should call armpmu_register any more, so it no longer needs to be in include/linux/perf/arm_pmu.h. Additionally, by folding it in to arm_pmu_device_probe we can allow drivers to override struct pmu fields without getting blatted by the armpmu code. This patch folds armpmu_register into arm_pmu_device_probe. The logging to the console is moved to after the PMU is successfully registered with the core perf code. Signed-off-by: Mark Rutland Suggested-by: Will Deacon Cc: Drew Richardson Cc: Pawel Moll Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index bfa673bb822d..83b5e34c6580 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -111,8 +111,6 @@ struct arm_pmu { #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) -int armpmu_register(struct arm_pmu *armpmu, int type); - u64 armpmu_event_update(struct perf_event *event); int armpmu_event_set_period(struct perf_event *event); -- cgit v1.2.3 From 18fc93fd64129c96432812cb44f59c963871889b Mon Sep 17 00:00:00 2001 From: Jungseok Lee Date: Wed, 4 Nov 2015 13:26:07 +0000 Subject: percpu: remove PERCPU_ENOUGH_ROOM which is stale definition As pure cleanup, this patch removes PERCPU_ENOUGH_ROOM which is not used any more. That is, no code refers to the definition. Acked-by: Christoph Lameter Signed-off-by: Jungseok Lee Signed-off-by: Tejun Heo --- include/linux/percpu.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index caebf2a758dc..4bc6dafb703e 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -18,12 +18,6 @@ #define PERCPU_MODULE_RESERVE 0 #endif -#ifndef PERCPU_ENOUGH_ROOM -#define PERCPU_ENOUGH_ROOM \ - (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \ - PERCPU_MODULE_RESERVE) -#endif - /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) -- cgit v1.2.3 From 67e9c74b8a873408c27ac9a8e4c1d1c8d72c93ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 16 Nov 2015 11:13:34 -0500 Subject: cgroup: replace __DEVEL__sane_behavior with cgroup2 fs type With major controllers - cpu, memory and io - shaping up for the unified hierarchy, cgroup2 is about ready to be, gradually, released into the wild. Replace __DEVEL__sane_behavior flag which was used to select the unified hierarchy with a separate filesystem type "cgroup2" so that unified hierarchy can be mounted as follows. mount -t cgroup2 none $MOUNT_POINT The cgroup2 fs has its own magic number - 0x63677270 ("cgrp"). v2: Assign a different magic number to cgroup2 fs. Signed-off-by: Tejun Heo Acked-by: Li Zefan Cc: Johannes Weiner --- include/linux/cgroup-defs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 869fd4a3d28e..80e2ae655208 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -66,7 +66,6 @@ enum { /* cgroup_root->flags */ enum { - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ }; -- cgit v1.2.3 From eb4b0ec75ec34e90bd1594c665f16de0cb4e3bf9 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 16 Nov 2015 08:35:53 -0200 Subject: [media] include/media: move platform_data to linux/platform_data/media Let's not mix platform_data headers with the core headers. Instead, let's create a subdir at linux/platform_data and move the headers to that common place, adding it to MAINTAINERS. The headers were moved with: mkdir include/linux/platform_data/media/; git mv include/media/gpio-ir-recv.h include/media/ir-rx51.h include/media/mmp-camera.h include/media/omap1_camera.h include/media/omap4iss.h include/media/s5p_hdmi.h include/media/si4713.h include/media/sii9234.h include/media/smiapp.h include/media/soc_camera.h include/media/soc_camera_platform.h include/media/timb_radio.h include/media/timb_video.h include/linux/platform_data/media/ And the references fixed with this script: MAIN_DIR="linux/platform_data/" PREV_DIR="media/" DIRS="media/" echo "Checking affected files" >&2 for i in $DIRS; do for j in $(find include/$MAIN_DIR/$i -type f -name '*.h'); do n=`basename $j` git grep -l $n done done|sort|uniq >files && ( echo "Handling files..." >&2; echo "for i in \$(cat files|grep -v Documentation); do cat \$i | \\"; ( cd include/$MAIN_DIR; for j in $DIRS; do for i in $(ls $j); do echo "perl -ne 's,(include [\\\"\\<])$PREV_DIR($i)([\\\"\\>]),\1$MAIN_DIR$j\2\3,; print \$_' |\\"; done; done; echo "cat > a && mv a \$i; done"; ); echo "Handling documentation..." >&2; echo "for i in MAINTAINERS \$(cat files); do cat \$i | \\"; ( cd include/$MAIN_DIR; for j in $DIRS; do for i in $(ls $j); do echo " perl -ne 's,include/$PREV_DIR($i)\b,include/$MAIN_DIR$j\1,; print \$_' |\\"; done; done; echo "cat > a && mv a \$i; done" ); ) >script && . ./script Signed-off-by: Mauro Carvalho Chehab Acked-by: Arnd Bergmann Acked-by: Lee Jones Acked-by: Krzysztof Kozlowski --- include/linux/platform_data/media/gpio-ir-recv.h | 23 ++++++ include/linux/platform_data/media/ir-rx51.h | 10 +++ include/linux/platform_data/media/mmp-camera.h | 9 +++ include/linux/platform_data/media/omap1_camera.h | 35 +++++++++ include/linux/platform_data/media/omap4iss.h | 65 +++++++++++++++++ include/linux/platform_data/media/s5p_hdmi.h | 36 ++++++++++ include/linux/platform_data/media/si4713.h | 48 +++++++++++++ include/linux/platform_data/media/sii9234.h | 24 +++++++ .../platform_data/media/soc_camera_platform.h | 83 ++++++++++++++++++++++ include/linux/platform_data/media/timb_radio.h | 30 ++++++++ include/linux/platform_data/media/timb_video.h | 33 +++++++++ 11 files changed, 396 insertions(+) create mode 100644 include/linux/platform_data/media/gpio-ir-recv.h create mode 100644 include/linux/platform_data/media/ir-rx51.h create mode 100644 include/linux/platform_data/media/mmp-camera.h create mode 100644 include/linux/platform_data/media/omap1_camera.h create mode 100644 include/linux/platform_data/media/omap4iss.h create mode 100644 include/linux/platform_data/media/s5p_hdmi.h create mode 100644 include/linux/platform_data/media/si4713.h create mode 100644 include/linux/platform_data/media/sii9234.h create mode 100644 include/linux/platform_data/media/soc_camera_platform.h create mode 100644 include/linux/platform_data/media/timb_radio.h create mode 100644 include/linux/platform_data/media/timb_video.h (limited to 'include/linux') diff --git a/include/linux/platform_data/media/gpio-ir-recv.h b/include/linux/platform_data/media/gpio-ir-recv.h new file mode 100644 index 000000000000..0c298f569d5a --- /dev/null +++ b/include/linux/platform_data/media/gpio-ir-recv.h @@ -0,0 +1,23 @@ +/* Copyright (c) 2012, Code Aurora Forum. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __GPIO_IR_RECV_H__ +#define __GPIO_IR_RECV_H__ + +struct gpio_ir_recv_platform_data { + int gpio_nr; + bool active_low; + u64 allowed_protos; + const char *map_name; +}; + +#endif /* __GPIO_IR_RECV_H__ */ diff --git a/include/linux/platform_data/media/ir-rx51.h b/include/linux/platform_data/media/ir-rx51.h new file mode 100644 index 000000000000..104aa892f31b --- /dev/null +++ b/include/linux/platform_data/media/ir-rx51.h @@ -0,0 +1,10 @@ +#ifndef _LIRC_RX51_H +#define _LIRC_RX51_H + +struct lirc_rx51_platform_data { + int pwm_timer; + + int(*set_max_mpu_wakeup_lat)(struct device *dev, long t); +}; + +#endif diff --git a/include/linux/platform_data/media/mmp-camera.h b/include/linux/platform_data/media/mmp-camera.h new file mode 100644 index 000000000000..7611963a257f --- /dev/null +++ b/include/linux/platform_data/media/mmp-camera.h @@ -0,0 +1,9 @@ +/* + * Information for the Marvell Armada MMP camera + */ + +struct mmp_camera_platform_data { + struct platform_device *i2c_device; + int sensor_power_gpio; + int sensor_reset_gpio; +}; diff --git a/include/linux/platform_data/media/omap1_camera.h b/include/linux/platform_data/media/omap1_camera.h new file mode 100644 index 000000000000..819767cf04d4 --- /dev/null +++ b/include/linux/platform_data/media/omap1_camera.h @@ -0,0 +1,35 @@ +/* + * Header for V4L2 SoC Camera driver for OMAP1 Camera Interface + * + * Copyright (C) 2010, Janusz Krzysztofik + * + * 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 __MEDIA_OMAP1_CAMERA_H_ +#define __MEDIA_OMAP1_CAMERA_H_ + +#include + +#define OMAP1_CAMERA_IOSIZE 0x1c + +enum omap1_cam_vb_mode { + OMAP1_CAM_DMA_CONTIG = 0, + OMAP1_CAM_DMA_SG, +}; + +#define OMAP1_CAMERA_MIN_BUF_COUNT(x) ((x) == OMAP1_CAM_DMA_CONTIG ? 3 : 2) + +struct omap1_cam_platform_data { + unsigned long camexclk_khz; + unsigned long lclk_khz_max; + unsigned long flags; +}; + +#define OMAP1_CAMERA_LCLK_RISING BIT(0) +#define OMAP1_CAMERA_RST_LOW BIT(1) +#define OMAP1_CAMERA_RST_HIGH BIT(2) + +#endif /* __MEDIA_OMAP1_CAMERA_H_ */ diff --git a/include/linux/platform_data/media/omap4iss.h b/include/linux/platform_data/media/omap4iss.h new file mode 100644 index 000000000000..0d7620db5e32 --- /dev/null +++ b/include/linux/platform_data/media/omap4iss.h @@ -0,0 +1,65 @@ +#ifndef ARCH_ARM_PLAT_OMAP4_ISS_H +#define ARCH_ARM_PLAT_OMAP4_ISS_H + +#include + +struct iss_device; + +enum iss_interface_type { + ISS_INTERFACE_CSI2A_PHY1, + ISS_INTERFACE_CSI2B_PHY2, +}; + +/** + * struct iss_csiphy_lane: CSI2 lane position and polarity + * @pos: position of the lane + * @pol: polarity of the lane + */ +struct iss_csiphy_lane { + u8 pos; + u8 pol; +}; + +#define ISS_CSIPHY1_NUM_DATA_LANES 4 +#define ISS_CSIPHY2_NUM_DATA_LANES 1 + +/** + * struct iss_csiphy_lanes_cfg - CSI2 lane configuration + * @data: Configuration of one or two data lanes + * @clk: Clock lane configuration + */ +struct iss_csiphy_lanes_cfg { + struct iss_csiphy_lane data[ISS_CSIPHY1_NUM_DATA_LANES]; + struct iss_csiphy_lane clk; +}; + +/** + * struct iss_csi2_platform_data - CSI2 interface platform data + * @crc: Enable the cyclic redundancy check + * @vpclk_div: Video port output clock control + */ +struct iss_csi2_platform_data { + unsigned crc:1; + unsigned vpclk_div:2; + struct iss_csiphy_lanes_cfg lanecfg; +}; + +struct iss_subdev_i2c_board_info { + struct i2c_board_info *board_info; + int i2c_adapter_id; +}; + +struct iss_v4l2_subdevs_group { + struct iss_subdev_i2c_board_info *subdevs; + enum iss_interface_type interface; + union { + struct iss_csi2_platform_data csi2; + } bus; /* gcc < 4.6.0 chokes on anonymous union initializers */ +}; + +struct iss_platform_data { + struct iss_v4l2_subdevs_group *subdevs; + void (*set_constraints)(struct iss_device *iss, bool enable); +}; + +#endif diff --git a/include/linux/platform_data/media/s5p_hdmi.h b/include/linux/platform_data/media/s5p_hdmi.h new file mode 100644 index 000000000000..bb9cacb0cbb0 --- /dev/null +++ b/include/linux/platform_data/media/s5p_hdmi.h @@ -0,0 +1,36 @@ +/* + * Driver header for S5P HDMI chip. + * + * Copyright (c) 2011 Samsung Electronics, Co. Ltd + * Contact: Tomasz Stanislawski + * + * 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 S5P_HDMI_H +#define S5P_HDMI_H + +struct i2c_board_info; + +/** + * @hdmiphy_bus: controller id for HDMIPHY bus + * @hdmiphy_info: template for HDMIPHY I2C device + * @mhl_bus: controller id for MHL control bus + * @mhl_info: template for MHL I2C device + * @hpd_gpio: GPIO for Hot-Plug-Detect pin + * + * NULL pointer for *_info fields indicates that + * the corresponding chip is not present + */ +struct s5p_hdmi_platform_data { + int hdmiphy_bus; + struct i2c_board_info *hdmiphy_info; + int mhl_bus; + struct i2c_board_info *mhl_info; + int hpd_gpio; +}; + +#endif /* S5P_HDMI_H */ diff --git a/include/linux/platform_data/media/si4713.h b/include/linux/platform_data/media/si4713.h new file mode 100644 index 000000000000..932668ad54f7 --- /dev/null +++ b/include/linux/platform_data/media/si4713.h @@ -0,0 +1,48 @@ +/* + * include/linux/platform_data/media/si4713.h + * + * Board related data definitions for Si4713 i2c device driver. + * + * Copyright (c) 2009 Nokia Corporation + * Contact: Eduardo Valentin + * + * 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 SI4713_H +#define SI4713_H + +/* The SI4713 I2C sensor chip has a fixed slave address of 0xc6 or 0x22. */ +#define SI4713_I2C_ADDR_BUSEN_HIGH 0x63 +#define SI4713_I2C_ADDR_BUSEN_LOW 0x11 + +/* + * Platform dependent definition + */ +struct si4713_platform_data { + bool is_platform_device; +}; + +/* + * Structure to query for Received Noise Level (RNL). + */ +struct si4713_rnl { + __u32 index; /* modulator index */ + __u32 frequency; /* frequency to peform rnl measurement */ + __s32 rnl; /* result of measurement in dBuV */ + __u32 reserved[4]; /* drivers and apps must init this to 0 */ +}; + +/* + * This is the ioctl number to query for rnl. Users must pass a + * struct si4713_rnl pointer specifying desired frequency in 'frequency' field + * following driver capabilities (i.e V4L2_TUNER_CAP_LOW). + * Driver must return measured value in the same struture, filling 'rnl' field. + */ +#define SI4713_IOC_MEASURE_RNL _IOWR('V', BASE_VIDIOC_PRIVATE + 0, \ + struct si4713_rnl) + +#endif /* ifndef SI4713_H*/ diff --git a/include/linux/platform_data/media/sii9234.h b/include/linux/platform_data/media/sii9234.h new file mode 100644 index 000000000000..6a4a809fe9a3 --- /dev/null +++ b/include/linux/platform_data/media/sii9234.h @@ -0,0 +1,24 @@ +/* + * Driver header for SII9234 MHL converter chip. + * + * Copyright (c) 2011 Samsung Electronics, Co. Ltd + * Contact: Tomasz Stanislawski + * + * 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 SII9234_H +#define SII9234_H + +/** + * @gpio_n_reset: GPIO driving nRESET pin + */ + +struct sii9234_platform_data { + int gpio_n_reset; +}; + +#endif /* SII9234_H */ diff --git a/include/linux/platform_data/media/soc_camera_platform.h b/include/linux/platform_data/media/soc_camera_platform.h new file mode 100644 index 000000000000..1e5065dab430 --- /dev/null +++ b/include/linux/platform_data/media/soc_camera_platform.h @@ -0,0 +1,83 @@ +/* + * Generic Platform Camera Driver Header + * + * Copyright (C) 2008 Magnus Damm + * + * 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 __SOC_CAMERA_H__ +#define __SOC_CAMERA_H__ + +#include +#include +#include + +struct device; + +struct soc_camera_platform_info { + const char *format_name; + unsigned long format_depth; + struct v4l2_mbus_framefmt format; + unsigned long mbus_param; + enum v4l2_mbus_type mbus_type; + struct soc_camera_device *icd; + int (*set_capture)(struct soc_camera_platform_info *info, int enable); +}; + +static inline void soc_camera_platform_release(struct platform_device **pdev) +{ + *pdev = NULL; +} + +static inline int soc_camera_platform_add(struct soc_camera_device *icd, + struct platform_device **pdev, + struct soc_camera_link *plink, + void (*release)(struct device *dev), + int id) +{ + struct soc_camera_subdev_desc *ssdd = + (struct soc_camera_subdev_desc *)plink; + struct soc_camera_platform_info *info = ssdd->drv_priv; + int ret; + + if (&icd->sdesc->subdev_desc != ssdd) + return -ENODEV; + + if (*pdev) + return -EBUSY; + + *pdev = platform_device_alloc("soc_camera_platform", id); + if (!*pdev) + return -ENOMEM; + + info->icd = icd; + + (*pdev)->dev.platform_data = info; + (*pdev)->dev.release = release; + + ret = platform_device_add(*pdev); + if (ret < 0) { + platform_device_put(*pdev); + *pdev = NULL; + info->icd = NULL; + } + + return ret; +} + +static inline void soc_camera_platform_del(const struct soc_camera_device *icd, + struct platform_device *pdev, + const struct soc_camera_link *plink) +{ + const struct soc_camera_subdev_desc *ssdd = + (const struct soc_camera_subdev_desc *)plink; + if (&icd->sdesc->subdev_desc != ssdd || !pdev) + return; + + platform_device_unregister(pdev); +} + +#endif /* __SOC_CAMERA_H__ */ diff --git a/include/linux/platform_data/media/timb_radio.h b/include/linux/platform_data/media/timb_radio.h new file mode 100644 index 000000000000..a40a6a348d21 --- /dev/null +++ b/include/linux/platform_data/media/timb_radio.h @@ -0,0 +1,30 @@ +/* + * timb_radio.h Platform struct for the Timberdale radio driver + * Copyright (c) 2009 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. + * + * 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., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _TIMB_RADIO_ +#define _TIMB_RADIO_ 1 + +#include + +struct timb_radio_platform_data { + int i2c_adapter; /* I2C adapter where the tuner and dsp are attached */ + struct i2c_board_info *tuner; + struct i2c_board_info *dsp; +}; + +#endif diff --git a/include/linux/platform_data/media/timb_video.h b/include/linux/platform_data/media/timb_video.h new file mode 100644 index 000000000000..70ae43970a49 --- /dev/null +++ b/include/linux/platform_data/media/timb_video.h @@ -0,0 +1,33 @@ +/* + * timb_video.h Platform struct for the Timberdale video driver + * Copyright (c) 2009-2010 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. + * + * 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., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _TIMB_VIDEO_ +#define _TIMB_VIDEO_ 1 + +#include + +struct timb_video_platform_data { + int dma_channel; + int i2c_adapter; /* The I2C adapter where the encoder is attached */ + struct { + const char *module_name; + struct i2c_board_info *info; + } encoder; +}; + +#endif -- cgit v1.2.3 From 52bd2d62ce6758d811edcbd2256eb9ea7f6a56cb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:30:50 -0800 Subject: net: better skb->sender_cpu and skb->napi_id cohabitation skb->sender_cpu and skb->napi_id share a common storage, and we had various bugs about this. We had to call skb_sender_cpu_clear() in some places to not leave a prior skb->napi_id and fool netdev_pick_tx() As suggested by Alexei, we could split the space so that these errors can not happen. 0 value being reserved as the common (not initialized) value, let's reserve [1 .. NR_CPUS] range for valid sender_cpu, and [NR_CPUS+1 .. ~0U] for valid napi_id. This will allow proper busy polling support over tunnels. Signed-off-by: Eric Dumazet Suggested-by: Alexei Starovoitov Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4355129fff91..c9c394bf0771 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1082,9 +1082,6 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline void skb_sender_cpu_clear(struct sk_buff *skb) { -#ifdef CONFIG_XPS - skb->sender_cpu = 0; -#endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET -- cgit v1.2.3 From 02d62e86fe892c59a1259d089d4d16ac76977a37 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:30:52 -0800 Subject: net: un-inline sk_busy_loop() There is really little gain from inlining this big function. We'll soon make it even bigger in following patches. This means we no longer need to export napi_by_id() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67bfac1abfc1..2020a89df12b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -460,15 +460,6 @@ static inline void napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } -/** - * napi_by_id - lookup a NAPI by napi_id - * @napi_id: hashed napi_id - * - * lookup @napi_id in napi_hash table - * must be called under rcu_read_lock() - */ -struct napi_struct *napi_by_id(unsigned int napi_id); - /** * napi_hash_add - add a NAPI to global hashtable * @napi: napi context -- cgit v1.2.3 From d64b5e85bfe2fe4c790abcbd16d9ae32391ddd7e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:00 -0800 Subject: net: add netif_tx_napi_add() netif_tx_napi_add() is a variant of netif_napi_add() It should be used by drivers that use a napi structure to exclusively poll TX. We do not want to add this kind of napi in napi_hash[] in following patches, adding generic busy polling to all NAPI drivers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2020a89df12b..838935d1cdbb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -326,7 +326,8 @@ enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_HASHED, /* In NAPI hash */ + NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ + NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ }; enum gro_result { @@ -1938,6 +1939,26 @@ static inline void *netdev_priv(const struct net_device *dev) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); +/** + * netif_tx_napi_add - initialize a napi context + * @dev: network device + * @napi: napi context + * @poll: polling function + * @weight: default weight + * + * This variant of netif_napi_add() should be used from drivers using NAPI + * to exclusively poll a TX queue. + * This will avoid we add it into napi_hash[], thus polluting this hash table. + */ +static inline void netif_tx_napi_add(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) +{ + set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); + netif_napi_add(dev, napi, poll, weight); +} + /** * netif_napi_del - remove a napi context * @napi: napi context -- cgit v1.2.3 From 6180d9de61a5c461f9e3efef5417a844701dbbb2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:01 -0800 Subject: net: move napi_hash[] into read mostly section We do not often add/delete a napi context. Moving napi_hash[] into read mostly section avoids potential false sharing. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/hashtable.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hashtable.h b/include/linux/hashtable.h index 519b6e2d769e..661e5c2a8e2a 100644 --- a/include/linux/hashtable.h +++ b/include/linux/hashtable.h @@ -16,6 +16,10 @@ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } +#define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ + struct hlist_head name[1 << (bits)] __read_mostly = \ + { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } + #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] -- cgit v1.2.3 From 34cbe27e811c591c854a39c0dee1b461bb796953 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:02 -0800 Subject: net: napi_hash_del() returns a boolean status napi_hash_del() will soon be used from both drivers (if they want) or core networking stack. Callers are responsibles to ensure an RCU grace period is respected before freeing napi structure : napi_hash_del() can signal if this RCU grace period is needed or not. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 838935d1cdbb..e5c33b29471b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -474,9 +474,10 @@ void napi_hash_add(struct napi_struct *napi); * @napi: napi context * * Warning: caller must observe rcu grace period - * before freeing memory containing @napi + * before freeing memory containing @napi, if + * this function returns true. */ -void napi_hash_del(struct napi_struct *napi); +bool napi_hash_del(struct napi_struct *napi); /** * napi_disable - prevent NAPI from scheduling -- cgit v1.2.3 From 93d05d4a320cb16712bb3d57a9658f395d8cecb9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 06:31:03 -0800 Subject: net: provide generic busy polling to all NAPI drivers NAPI drivers no longer need to observe a particular protocol to benefit from busy polling (CONFIG_NET_RX_BUSY_POLL=y) napi_hash_add() and napi_hash_del() are automatically called from core networking stack, respectively from netif_napi_add() and netif_napi_del() This patch depends on free_netdev() and netif_napi_del() being called from process context, which seems to be the norm. Drivers might still prefer to call napi_hash_del() on their own, since they might combine all the rcu grace periods into a single one, knowing their NAPI structures lifetime, while core networking stack has no idea of a possible combining. Once this patch proves to not bring serious regressions, we will cleanup drivers to either remove napi_hash_del() or provide appropriate rcu grace periods combining. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e5c33b29471b..7d2d1d7aaec7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -466,6 +466,9 @@ static inline void napi_complete(struct napi_struct *n) * @napi: napi context * * generate a new napi_id and store a @napi under it in napi_hash + * Used for busy polling (CONFIG_NET_RX_BUSY_POLL) + * Note: This is normally automatically done from netif_napi_add(), + * so might disappear in a future linux version. */ void napi_hash_add(struct napi_struct *napi); @@ -476,6 +479,10 @@ void napi_hash_add(struct napi_struct *napi); * Warning: caller must observe rcu grace period * before freeing memory containing @napi, if * this function returns true. + * Note: core networking stack automatically calls it + * from netif_napi_del() + * Drivers might want to call this helper to combine all + * the needed rcu grace periods into a single one. */ bool napi_hash_del(struct napi_struct *napi); -- cgit v1.2.3 From a71daaa10ec2e325f34d172b2782f2d68209b08d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Nov 2015 07:11:13 -0200 Subject: [media] move media platform data to linux/platform_data/media Now that media has its own subdirectory inside platform_data, let's move the headers that are already there to such subdir. After moving those files, the references were adjusted using this script: MAIN_DIR="linux/platform_data/" PREV_DIR="linux/platform_data/" DIRS="media/" echo "Checking affected files" >&2 for i in $DIRS; do for j in $(find include/$MAIN_DIR/$i -type f -name '*.h'); do n=`basename $j` git grep -l $n done done|sort|uniq >files && ( echo "Handling files..." >&2; echo "for i in \$(cat files|grep -v Documentation); do cat \$i | \\"; ( cd include/$MAIN_DIR; for j in $DIRS; do for i in $(ls $j); do echo "perl -ne 's,(include [\\\"\\<])$PREV_DIR($i)([\\\"\\>]),\1$MAIN_DIR$j\2\3,; print \$_' |\\"; done; done; echo "cat > a && mv a \$i; done"; ); echo "Handling documentation..." >&2; echo "for i in MAINTAINERS \$(cat files); do cat \$i | \\"; ( cd include/$MAIN_DIR; for j in $DIRS; do for i in $(ls $j); do echo " perl -ne 's,include/$PREV_DIR($i)\b,include/$MAIN_DIR$j\1,; print \$_' |\\"; done; done; echo "cat > a && mv a \$i; done" ); ) >script && . ./script Suggested-by: Arnd Bergmann Acked-by: Arnd Bergmann Acked-by: Mark Brown Acked-by: Robert Jarzmik Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/camera-mx2.h | 44 --------------------- include/linux/platform_data/camera-mx3.h | 52 ------------------------- include/linux/platform_data/camera-pxa.h | 44 --------------------- include/linux/platform_data/camera-rcar.h | 25 ------------ include/linux/platform_data/coda.h | 18 --------- include/linux/platform_data/media/camera-mx2.h | 44 +++++++++++++++++++++ include/linux/platform_data/media/camera-mx3.h | 52 +++++++++++++++++++++++++ include/linux/platform_data/media/camera-pxa.h | 44 +++++++++++++++++++++ include/linux/platform_data/media/camera-rcar.h | 25 ++++++++++++ include/linux/platform_data/media/coda.h | 18 +++++++++ 10 files changed, 183 insertions(+), 183 deletions(-) delete mode 100644 include/linux/platform_data/camera-mx2.h delete mode 100644 include/linux/platform_data/camera-mx3.h delete mode 100644 include/linux/platform_data/camera-pxa.h delete mode 100644 include/linux/platform_data/camera-rcar.h delete mode 100644 include/linux/platform_data/coda.h create mode 100644 include/linux/platform_data/media/camera-mx2.h create mode 100644 include/linux/platform_data/media/camera-mx3.h create mode 100644 include/linux/platform_data/media/camera-pxa.h create mode 100644 include/linux/platform_data/media/camera-rcar.h create mode 100644 include/linux/platform_data/media/coda.h (limited to 'include/linux') diff --git a/include/linux/platform_data/camera-mx2.h b/include/linux/platform_data/camera-mx2.h deleted file mode 100644 index 7ded6f1f74bc..000000000000 --- a/include/linux/platform_data/camera-mx2.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - * mx2-cam.h - i.MX27/i.MX25 camera driver header file - * - * Copyright (C) 2003, Intel Corporation - * Copyright (C) 2008, Sascha Hauer - * Copyright (C) 2010, Baruch Siach - * - * 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., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - */ - -#ifndef __MACH_MX2_CAM_H_ -#define __MACH_MX2_CAM_H_ - -#define MX2_CAMERA_EXT_VSYNC (1 << 1) -#define MX2_CAMERA_CCIR (1 << 2) -#define MX2_CAMERA_CCIR_INTERLACE (1 << 3) -#define MX2_CAMERA_HSYNC_HIGH (1 << 4) -#define MX2_CAMERA_GATED_CLOCK (1 << 5) -#define MX2_CAMERA_INV_DATA (1 << 6) -#define MX2_CAMERA_PCLK_SAMPLE_RISING (1 << 7) - -/** - * struct mx2_camera_platform_data - optional platform data for mx2_camera - * @flags: any combination of MX2_CAMERA_* - * @clk: clock rate of the csi block / 2 - */ -struct mx2_camera_platform_data { - unsigned long flags; - unsigned long clk; -}; - -#endif /* __MACH_MX2_CAM_H_ */ diff --git a/include/linux/platform_data/camera-mx3.h b/include/linux/platform_data/camera-mx3.h deleted file mode 100644 index a910dadc8258..000000000000 --- a/include/linux/platform_data/camera-mx3.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * mx3_camera.h - i.MX3x camera driver header file - * - * Copyright (C) 2008, Guennadi Liakhovetski, DENX Software Engineering, - * - * 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 _MX3_CAMERA_H_ -#define _MX3_CAMERA_H_ - -#include - -#define MX3_CAMERA_CLK_SRC 1 -#define MX3_CAMERA_EXT_VSYNC 2 -#define MX3_CAMERA_DP 4 -#define MX3_CAMERA_PCP 8 -#define MX3_CAMERA_HSP 0x10 -#define MX3_CAMERA_VSP 0x20 -#define MX3_CAMERA_DATAWIDTH_4 0x40 -#define MX3_CAMERA_DATAWIDTH_8 0x80 -#define MX3_CAMERA_DATAWIDTH_10 0x100 -#define MX3_CAMERA_DATAWIDTH_15 0x200 - -#define MX3_CAMERA_DATAWIDTH_MASK (MX3_CAMERA_DATAWIDTH_4 | MX3_CAMERA_DATAWIDTH_8 | \ - MX3_CAMERA_DATAWIDTH_10 | MX3_CAMERA_DATAWIDTH_15) - -struct v4l2_async_subdev; - -/** - * struct mx3_camera_pdata - i.MX3x camera platform data - * @flags: MX3_CAMERA_* flags - * @mclk_10khz: master clock frequency in 10kHz units - * @dma_dev: IPU DMA device to match against in channel allocation - */ -struct mx3_camera_pdata { - unsigned long flags; - unsigned long mclk_10khz; - struct device *dma_dev; - struct v4l2_async_subdev **asd; /* Flat array, arranged in groups */ - int *asd_sizes; /* 0-terminated array of asd group sizes */ -}; - -#endif diff --git a/include/linux/platform_data/camera-pxa.h b/include/linux/platform_data/camera-pxa.h deleted file mode 100644 index 6709b1cd7c77..000000000000 --- a/include/linux/platform_data/camera-pxa.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - camera.h - PXA camera driver header file - - Copyright (C) 2003, Intel Corporation - Copyright (C) 2008, Guennadi Liakhovetski - - 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., 675 Mass Ave, Cambridge, MA 02139, USA. -*/ - -#ifndef __ASM_ARCH_CAMERA_H_ -#define __ASM_ARCH_CAMERA_H_ - -#define PXA_CAMERA_MASTER 1 -#define PXA_CAMERA_DATAWIDTH_4 2 -#define PXA_CAMERA_DATAWIDTH_5 4 -#define PXA_CAMERA_DATAWIDTH_8 8 -#define PXA_CAMERA_DATAWIDTH_9 0x10 -#define PXA_CAMERA_DATAWIDTH_10 0x20 -#define PXA_CAMERA_PCLK_EN 0x40 -#define PXA_CAMERA_MCLK_EN 0x80 -#define PXA_CAMERA_PCP 0x100 -#define PXA_CAMERA_HSP 0x200 -#define PXA_CAMERA_VSP 0x400 - -struct pxacamera_platform_data { - unsigned long flags; - unsigned long mclk_10khz; -}; - -extern void pxa_set_camera_info(struct pxacamera_platform_data *); - -#endif /* __ASM_ARCH_CAMERA_H_ */ diff --git a/include/linux/platform_data/camera-rcar.h b/include/linux/platform_data/camera-rcar.h deleted file mode 100644 index dfc83c581593..000000000000 --- a/include/linux/platform_data/camera-rcar.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Platform data for Renesas R-Car VIN soc-camera driver - * - * Copyright (C) 2011-2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc., - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#ifndef __CAMERA_RCAR_H_ -#define __CAMERA_RCAR_H_ - -#define RCAR_VIN_HSYNC_ACTIVE_LOW (1 << 0) -#define RCAR_VIN_VSYNC_ACTIVE_LOW (1 << 1) -#define RCAR_VIN_BT601 (1 << 2) -#define RCAR_VIN_BT656 (1 << 3) - -struct rcar_vin_platform_data { - unsigned int flags; -}; - -#endif /* __CAMERA_RCAR_H_ */ diff --git a/include/linux/platform_data/coda.h b/include/linux/platform_data/coda.h deleted file mode 100644 index 6ad4410d9e20..000000000000 --- a/include/linux/platform_data/coda.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Copyright (C) 2013 Philipp Zabel, Pengutronix - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ -#ifndef PLATFORM_CODA_H -#define PLATFORM_CODA_H - -struct device; - -struct coda_platform_data { - struct device *iram_dev; -}; - -#endif diff --git a/include/linux/platform_data/media/camera-mx2.h b/include/linux/platform_data/media/camera-mx2.h new file mode 100644 index 000000000000..7ded6f1f74bc --- /dev/null +++ b/include/linux/platform_data/media/camera-mx2.h @@ -0,0 +1,44 @@ +/* + * mx2-cam.h - i.MX27/i.MX25 camera driver header file + * + * Copyright (C) 2003, Intel Corporation + * Copyright (C) 2008, Sascha Hauer + * Copyright (C) 2010, Baruch Siach + * + * 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., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#ifndef __MACH_MX2_CAM_H_ +#define __MACH_MX2_CAM_H_ + +#define MX2_CAMERA_EXT_VSYNC (1 << 1) +#define MX2_CAMERA_CCIR (1 << 2) +#define MX2_CAMERA_CCIR_INTERLACE (1 << 3) +#define MX2_CAMERA_HSYNC_HIGH (1 << 4) +#define MX2_CAMERA_GATED_CLOCK (1 << 5) +#define MX2_CAMERA_INV_DATA (1 << 6) +#define MX2_CAMERA_PCLK_SAMPLE_RISING (1 << 7) + +/** + * struct mx2_camera_platform_data - optional platform data for mx2_camera + * @flags: any combination of MX2_CAMERA_* + * @clk: clock rate of the csi block / 2 + */ +struct mx2_camera_platform_data { + unsigned long flags; + unsigned long clk; +}; + +#endif /* __MACH_MX2_CAM_H_ */ diff --git a/include/linux/platform_data/media/camera-mx3.h b/include/linux/platform_data/media/camera-mx3.h new file mode 100644 index 000000000000..a910dadc8258 --- /dev/null +++ b/include/linux/platform_data/media/camera-mx3.h @@ -0,0 +1,52 @@ +/* + * mx3_camera.h - i.MX3x camera driver header file + * + * Copyright (C) 2008, Guennadi Liakhovetski, DENX Software Engineering, + * + * 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 _MX3_CAMERA_H_ +#define _MX3_CAMERA_H_ + +#include + +#define MX3_CAMERA_CLK_SRC 1 +#define MX3_CAMERA_EXT_VSYNC 2 +#define MX3_CAMERA_DP 4 +#define MX3_CAMERA_PCP 8 +#define MX3_CAMERA_HSP 0x10 +#define MX3_CAMERA_VSP 0x20 +#define MX3_CAMERA_DATAWIDTH_4 0x40 +#define MX3_CAMERA_DATAWIDTH_8 0x80 +#define MX3_CAMERA_DATAWIDTH_10 0x100 +#define MX3_CAMERA_DATAWIDTH_15 0x200 + +#define MX3_CAMERA_DATAWIDTH_MASK (MX3_CAMERA_DATAWIDTH_4 | MX3_CAMERA_DATAWIDTH_8 | \ + MX3_CAMERA_DATAWIDTH_10 | MX3_CAMERA_DATAWIDTH_15) + +struct v4l2_async_subdev; + +/** + * struct mx3_camera_pdata - i.MX3x camera platform data + * @flags: MX3_CAMERA_* flags + * @mclk_10khz: master clock frequency in 10kHz units + * @dma_dev: IPU DMA device to match against in channel allocation + */ +struct mx3_camera_pdata { + unsigned long flags; + unsigned long mclk_10khz; + struct device *dma_dev; + struct v4l2_async_subdev **asd; /* Flat array, arranged in groups */ + int *asd_sizes; /* 0-terminated array of asd group sizes */ +}; + +#endif diff --git a/include/linux/platform_data/media/camera-pxa.h b/include/linux/platform_data/media/camera-pxa.h new file mode 100644 index 000000000000..6709b1cd7c77 --- /dev/null +++ b/include/linux/platform_data/media/camera-pxa.h @@ -0,0 +1,44 @@ +/* + camera.h - PXA camera driver header file + + Copyright (C) 2003, Intel Corporation + Copyright (C) 2008, Guennadi Liakhovetski + + 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., 675 Mass Ave, Cambridge, MA 02139, USA. +*/ + +#ifndef __ASM_ARCH_CAMERA_H_ +#define __ASM_ARCH_CAMERA_H_ + +#define PXA_CAMERA_MASTER 1 +#define PXA_CAMERA_DATAWIDTH_4 2 +#define PXA_CAMERA_DATAWIDTH_5 4 +#define PXA_CAMERA_DATAWIDTH_8 8 +#define PXA_CAMERA_DATAWIDTH_9 0x10 +#define PXA_CAMERA_DATAWIDTH_10 0x20 +#define PXA_CAMERA_PCLK_EN 0x40 +#define PXA_CAMERA_MCLK_EN 0x80 +#define PXA_CAMERA_PCP 0x100 +#define PXA_CAMERA_HSP 0x200 +#define PXA_CAMERA_VSP 0x400 + +struct pxacamera_platform_data { + unsigned long flags; + unsigned long mclk_10khz; +}; + +extern void pxa_set_camera_info(struct pxacamera_platform_data *); + +#endif /* __ASM_ARCH_CAMERA_H_ */ diff --git a/include/linux/platform_data/media/camera-rcar.h b/include/linux/platform_data/media/camera-rcar.h new file mode 100644 index 000000000000..dfc83c581593 --- /dev/null +++ b/include/linux/platform_data/media/camera-rcar.h @@ -0,0 +1,25 @@ +/* + * Platform data for Renesas R-Car VIN soc-camera driver + * + * Copyright (C) 2011-2013 Renesas Solutions Corp. + * Copyright (C) 2013 Cogent Embedded, Inc., + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __CAMERA_RCAR_H_ +#define __CAMERA_RCAR_H_ + +#define RCAR_VIN_HSYNC_ACTIVE_LOW (1 << 0) +#define RCAR_VIN_VSYNC_ACTIVE_LOW (1 << 1) +#define RCAR_VIN_BT601 (1 << 2) +#define RCAR_VIN_BT656 (1 << 3) + +struct rcar_vin_platform_data { + unsigned int flags; +}; + +#endif /* __CAMERA_RCAR_H_ */ diff --git a/include/linux/platform_data/media/coda.h b/include/linux/platform_data/media/coda.h new file mode 100644 index 000000000000..6ad4410d9e20 --- /dev/null +++ b/include/linux/platform_data/media/coda.h @@ -0,0 +1,18 @@ +/* + * Copyright (C) 2013 Philipp Zabel, Pengutronix + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef PLATFORM_CODA_H +#define PLATFORM_CODA_H + +struct device; + +struct coda_platform_data { + struct device *iram_dev; +}; + +#endif -- cgit v1.2.3 From 22bc8625682d4f5ff45cab19ea39245352c57a39 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 7 Oct 2015 07:39:36 -0300 Subject: [media] rcar_vin: Remove obsolete platform data support Since commit 3d7608e4c169af03 ("ARM: shmobile: bockw: remove legacy board file and config"), Renesas R-Car SoCs are only supported in generic DT-only ARM multi-platform builds. The driver doesn't need to use platform data anymore, hence remove platform data configuration. Signed-off-by: Geert Uytterhoeven Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/media/camera-rcar.h | 25 ------------------------- 1 file changed, 25 deletions(-) delete mode 100644 include/linux/platform_data/media/camera-rcar.h (limited to 'include/linux') diff --git a/include/linux/platform_data/media/camera-rcar.h b/include/linux/platform_data/media/camera-rcar.h deleted file mode 100644 index dfc83c581593..000000000000 --- a/include/linux/platform_data/media/camera-rcar.h +++ /dev/null @@ -1,25 +0,0 @@ -/* - * Platform data for Renesas R-Car VIN soc-camera driver - * - * Copyright (C) 2011-2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc., - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - */ - -#ifndef __CAMERA_RCAR_H_ -#define __CAMERA_RCAR_H_ - -#define RCAR_VIN_HSYNC_ACTIVE_LOW (1 << 0) -#define RCAR_VIN_VSYNC_ACTIVE_LOW (1 << 1) -#define RCAR_VIN_BT601 (1 << 2) -#define RCAR_VIN_BT656 (1 << 3) - -struct rcar_vin_platform_data { - unsigned int flags; -}; - -#endif /* __CAMERA_RCAR_H_ */ -- cgit v1.2.3 From a8acce6aa584aa731a2bed240bcd8dc955f01414 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 19 Nov 2015 12:53:21 +0100 Subject: ppp: remove PPPOX_ZOMBIE socket state PPPOX_ZOMBIE is never set anymore. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/linux/if_pppox.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h index b49cf923becc..ba7a9b0c7c57 100644 --- a/include/linux/if_pppox.h +++ b/include/linux/if_pppox.h @@ -91,7 +91,6 @@ enum { PPPOX_CONNECTED = 1, /* connection established ==TCP_ESTABLISHED */ PPPOX_BOUND = 2, /* bound to ppp device */ PPPOX_RELAY = 4, /* forwarding is enabled */ - PPPOX_ZOMBIE = 8, /* dead, but still bound to ppp device */ PPPOX_DEAD = 16 /* dead, useless, please clean me up!*/ }; -- cgit v1.2.3 From b11cfb5807e30333b36c02701382b820b7dcf0d5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Nov 2015 15:55:52 -0500 Subject: cgroup: record ancestor IDs and reimplement cgroup_is_descendant() using it cgroup_is_descendant() currently walks up the hierarchy and compares each ancestor to the cgroup in question. While enough for cgroup core usages, this can't be used in hot paths to test cgroup membership. This patch adds cgroup->ancestor_ids[] which records the IDs of all ancestors including self and cgroup->level for the nesting level. This allows testing whether a given cgroup is a descendant of another in three finite steps - testing whether the two belong to the same hierarchy, whether the descendant candidate is at the same or a higher level than the ancestor and comparing the recorded ancestor_id at the matching level. cgroup_is_descendant() is accordingly reimplmented and made inline. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 14 ++++++++++++++ include/linux/cgroup.h | 18 +++++++++++++++++- 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 60d44b26276d..504d8591b6d3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -234,6 +234,14 @@ struct cgroup { */ int id; + /* + * The depth this cgroup is at. The root is at depth zero and each + * step down the hierarchy increments the level. This along with + * ancestor_ids[] can determine whether a given cgroup is a + * descendant of another without traversing the hierarchy. + */ + int level; + /* * Each non-empty css_set associated with this cgroup contributes * one to populated_cnt. All children with non-zero popuplated_cnt @@ -289,6 +297,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + + /* ids of the ancestors at each level including self */ + int ancestor_ids[]; }; /* @@ -308,6 +319,9 @@ struct cgroup_root { /* The root cgroup. Root is destroyed on its release. */ struct cgroup cgrp; + /* for cgrp->ancestor_ids[0] */ + int cgrp_ancestor_id_storage; + /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 22e3754f89c5..b5ee2c4210f9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -81,7 +81,6 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); -bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); @@ -459,6 +458,23 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } +/** + * cgroup_is_descendant - test ancestry + * @cgrp: the cgroup to be tested + * @ancestor: possible ancestor of @cgrp + * + * Test whether @cgrp is a descendant of @ancestor. It also returns %true + * if @cgrp == @ancestor. This function is safe to call as long as @cgrp + * and @ancestor are accessible. + */ +static inline bool cgroup_is_descendant(struct cgroup *cgrp, + struct cgroup *ancestor) +{ + if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) + return false; + return cgrp->ancestor_ids[ancestor->level] == ancestor->id; +} + /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { -- cgit v1.2.3 From bd96f76a2454c6b97d70945902e30b4c31510678 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Nov 2015 15:55:52 -0500 Subject: kernfs: implement kernfs_walk_and_get() Implement kernfs_walk_and_get() which is similar to kernfs_find_and_get() but can walk a path instead of just a name. v2: Use strlcpy() instead of strlen() + memcpy() as suggested by David. Signed-off-by: Tejun Heo Acked-by: Greg Kroah-Hartman Cc: David Miller --- include/linux/kernfs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5d4e9c4b821d..af51df35d749 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -274,6 +274,8 @@ void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns); +struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, + const char *path, const void *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); @@ -350,6 +352,10 @@ static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { return NULL; } +static inline struct kernfs_node * +kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, + const void *ns) +{ return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } static inline void kernfs_put(struct kernfs_node *kn) { } @@ -430,6 +436,12 @@ kernfs_find_and_get(struct kernfs_node *kn, const char *name) return kernfs_find_and_get_ns(kn, name, NULL); } +static inline struct kernfs_node * +kernfs_walk_and_get(struct kernfs_node *kn, const char *path) +{ + return kernfs_walk_and_get_ns(kn, path, NULL); +} + static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) -- cgit v1.2.3 From 16af439645455fbf36984ca5e72f31073ee19ab7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 20 Nov 2015 15:55:52 -0500 Subject: cgroup: implement cgroup_get_from_path() and expose cgroup_put() Implement cgroup_get_from_path() using kernfs_walk_and_get() which obtains a default hierarchy cgroup from its path. This will be used to allow cgroup path based matching from outside cgroup proper - e.g. networking and perf. v2: Add EXPORT_SYMBOL_GPL(cgroup_get_from_path). Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b5ee2c4210f9..4c3ffab81ba7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -81,6 +81,8 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, 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); + int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); @@ -351,6 +353,11 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } +static inline void cgroup_put(struct cgroup *cgrp) +{ + css_put(&cgrp->self); +} + /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for -- cgit v1.2.3 From 69e51e92a394088fc3266ed5136903074b44f3c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 23 Oct 2015 14:32:34 +0200 Subject: sched/wait: Document waitqueue_active() Kosuku reports that there were a fair number of buggy waitqueue_active() users and this function deserves a big comment in order to avoid growing more. Reported-by: Kosuke Tatsukawa Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/wait.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 1e1bf9f963a9..f3bac30587f7 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -102,6 +102,36 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) q->func = func; } +/** + * waitqueue_active -- locklessly test for waiters on the queue + * @q: the waitqueue to test for waiters + * + * returns true if the wait list is not empty + * + * NOTE: this function is lockless and requires care, incorrect usage _will_ + * lead to sporadic and non-obvious failure. + * + * Use either while holding wait_queue_head_t::lock or when used for wakeups + * with an extra smp_mb() like: + * + * CPU0 - waker CPU1 - waiter + * + * for (;;) { + * @cond = true; prepare_to_wait(&wq, &wait, state); + * smp_mb(); // smp_mb() from set_current_state() + * if (waitqueue_active(wq)) if (@cond) + * wake_up(wq); break; + * schedule(); + * } + * finish_wait(&wq, &wait); + * + * Because without the explicit smp_mb() it's possible for the + * waitqueue_active() load to get hoisted over the @cond store such that we'll + * observe an empty wait list while the waiter might not observe @cond. + * + * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), + * which (when the lock is uncontended) are of roughly equal cost. + */ static inline int waitqueue_active(wait_queue_head_t *q) { return !list_empty(&q->task_list); -- cgit v1.2.3 From 525705d15e63b7455977408e4601e76e6bc41524 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Tue, 10 Nov 2015 09:36:02 +0900 Subject: sched/fair: Consider missed ticks in NOHZ_FULL in update_cpu_load_nohz() Usually the tick can be stopped for an idle CPU in NOHZ. However in NOHZ_FULL mode, a non-idle CPU's tick can also be stopped. However, update_cpu_load_nohz() does not consider the case a non-idle CPU's tick has been stopped at all. This patch makes the update_cpu_load_nohz() know if the calling path comes from NOHZ_FULL or idle NOHZ. Signed-off-by: Byungchul Park Signed-off-by: Peter Zijlstra (Intel) Acked-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447115762-19734-3-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..f425aac63317 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -177,9 +177,9 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void update_cpu_load_nohz(void); +extern void update_cpu_load_nohz(int active); #else -static inline void update_cpu_load_nohz(void) { } +static inline void update_cpu_load_nohz(int active) { } #endif extern unsigned long get_parent_ip(unsigned long addr); -- cgit v1.2.3 From 1b034bd989aa4a396c13d305759c376c52595a97 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 17 Nov 2015 18:05:23 +0100 Subject: stop_machine: Make cpu_stop_queue_work() and stop_one_cpu_nowait() return bool Change cpu_stop_queue_work() to return true if the work was queued and change stop_one_cpu_nowait() to return the result of cpu_stop_queue_work(). This makes it more useful, for example now you can alloc cpu_stop_work for stop_one_cpu_nowait() and free it in the callback or if stop_one_cpu_nowait() fails, currently this is impossible because you can't know if @fn will be called or not. Also, this allows to kill cpu_stop_done->executed, see the next changes. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Cc: Linus Torvalds Cc: Mike Galbraith Cc: Milos Vyletel Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20151117170523.GA13955@redhat.com Signed-off-by: Ingo Molnar --- include/linux/stop_machine.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0adedca24c5b..9ef42e1f0b3a 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -29,7 +29,7 @@ struct cpu_stop_work { int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg); -void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, +bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); @@ -65,7 +65,7 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work) preempt_enable(); } -static inline void stop_one_cpu_nowait(unsigned int cpu, +static inline bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { @@ -74,7 +74,10 @@ static inline void stop_one_cpu_nowait(unsigned int cpu, work_buf->fn = fn; work_buf->arg = arg; schedule_work(&work_buf->work); + return true; } + + return false; } static inline int stop_cpus(const struct cpumask *cpumask, -- cgit v1.2.3 From f7ccdb96fa31305d480678b1ba81225907dd81ef Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 11 Nov 2015 20:17:37 -0200 Subject: netfilter: nf_ct_sctp: move ip_ct_sctp away from UAPI ip_ct_sctp is an internal structure, embedded by the union nf_conntrack_proto to store sctp-specific information at conntrack entries. It has no business with UAPI. This patch moves it from UAPI to a saner place, together with similar structs for other protocols. Signed-off-by: Marcelo Ricardo Leitner Acked-by: Neil Horman Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_sctp.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/netfilter/nf_conntrack_sctp.h (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h new file mode 100644 index 000000000000..22a16a23cd8a --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_sctp.h @@ -0,0 +1,13 @@ +#ifndef _NF_CONNTRACK_SCTP_H +#define _NF_CONNTRACK_SCTP_H +/* SCTP tracking. */ + +#include + +struct ip_ct_sctp { + enum sctp_conntrack state; + + __be32 vtag[IP_CT_DIR_MAX]; +}; + +#endif /* _NF_CONNTRACK_SCTP_H */ -- cgit v1.2.3 From 1c97be677f72b3c338312aecd36d8fff20322f32 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 20 Sep 2015 22:02:17 -0700 Subject: list: Use WRITE_ONCE() when adding to lists and hlists Code that does lockless emptiness testing of non-RCU lists is relying on the list-addition code to write the list head's ->next pointer atomically. This commit therefore adds WRITE_ONCE() to list-addition pointer stores that could affect the head's ->next pointer. Reported-by: Dmitry Vyukov Signed-off-by: Paul E. McKenney --- include/linux/list.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 993395a2e55c..d7e31fe398b3 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -42,7 +42,7 @@ static inline void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } #else extern void __list_add(struct list_head *new, @@ -642,7 +642,7 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) n->next = first; if (first) first->pprev = &n->next; - h->first = n; + WRITE_ONCE(h->first, n); n->pprev = &h->first; } @@ -653,14 +653,14 @@ static inline void hlist_add_before(struct hlist_node *n, n->pprev = next->pprev; n->next = next; next->pprev = &n->next; - *(n->pprev) = n; + WRITE_ONCE(*(n->pprev), n); } static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; - prev->next = n; + WRITE_ONCE(prev->next, n); n->pprev = &prev->next; if (n->next) -- cgit v1.2.3 From 1658d35ead5d8dd76f2b2d6ad0e32c08d123faa2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 20 Sep 2015 17:03:16 -0700 Subject: list: Use READ_ONCE() when testing for empty lists Most of the list-empty-check macros (list_empty(), hlist_empty(), hlist_bl_empty(), hlist_nulls_empty(), and hlist_nulls_empty()) use an unadorned load to check the list header. Given that these macros are sometimes invoked without the protection of a lock, this is not sufficient. This commit therefore adds READ_ONCE() calls to them. This commit does not touch llist_empty() because it already has the needed ACCESS_ONCE(). Reported-by: Dmitry Vyukov Signed-off-by: Paul E. McKenney --- include/linux/list.h | 4 ++-- include/linux/list_bl.h | 2 +- include/linux/list_nulls.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index d7e31fe398b3..06c2d887a918 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -186,7 +186,7 @@ static inline int list_is_last(const struct list_head *list, */ static inline int list_empty(const struct list_head *head) { - return head->next == head; + return READ_ONCE(head->next) == head; } /** @@ -608,7 +608,7 @@ static inline int hlist_unhashed(const struct hlist_node *h) static inline int hlist_empty(const struct hlist_head *h) { - return !h->first; + return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 8132214e8efd..ee7229a6c06a 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -70,7 +70,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, static inline int hlist_bl_empty(const struct hlist_bl_head *h) { - return !((unsigned long)h->first & ~LIST_BL_LOCKMASK); + return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 444d2b1313bd..b01fe1009084 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -57,7 +57,7 @@ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { - return is_a_nulls(h->first); + return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, -- cgit v1.2.3 From ed11a7f1b3bd482bd7d6ef7bc2859c41fb43b9ee Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 12 Nov 2015 12:59:01 -0800 Subject: context_tracking: Switch to new static_branch API This is much less error-prone than the old code. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/812df7e64f120c5c7c08481f36a8caa9f53b2199.1447361906.git.luto@kernel.org Signed-off-by: Ingo Molnar --- include/linux/context_tracking_state.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index ee956c528fab..1d34fe68f48a 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -22,12 +22,12 @@ struct context_tracking { }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; +extern struct static_key_false context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_is_enabled(void) { - return static_key_false(&context_tracking_enabled); + return static_branch_unlikely(&context_tracking_enabled); } static inline bool context_tracking_cpu_is_enabled(void) -- cgit v1.2.3 From f9551a9c083b8acc1db38e234a630655bae8e771 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 24 Nov 2015 15:49:40 +0100 Subject: irqchip/renesas-intc-irqpin: Remove obsolete platform data support Since commit 4baadb9e05c68962 ("ARM: shmobile: r8a7778: remove obsolete setup code"), all Renesas SoCs with a renesas-intc-irqpin module are only supported in generic DT-only ARM multi-platform builds. The driver doesn't need to use platform data anymore, hence remove platform data configuration. Signed-off-by: Geert Uytterhoeven Acked-by: Marc Zyngier Acked-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1448376581-9202-2-git-send-email-geert+renesas@glider.be Signed-off-by: Jason Cooper --- .../linux/platform_data/irq-renesas-intc-irqpin.h | 29 ---------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/platform_data/irq-renesas-intc-irqpin.h (limited to 'include/linux') diff --git a/include/linux/platform_data/irq-renesas-intc-irqpin.h b/include/linux/platform_data/irq-renesas-intc-irqpin.h deleted file mode 100644 index e4cb911066a6..000000000000 --- a/include/linux/platform_data/irq-renesas-intc-irqpin.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Renesas INTC External IRQ Pin Driver - * - * Copyright (C) 2013 Magnus Damm - * - * 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 - * - * 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 - */ - -#ifndef __IRQ_RENESAS_INTC_IRQPIN_H__ -#define __IRQ_RENESAS_INTC_IRQPIN_H__ - -struct renesas_intc_irqpin_config { - unsigned int sense_bitfield_width; - unsigned int irq_base; - bool control_parent; -}; - -#endif /* __IRQ_RENESAS_INTC_IRQPIN_H__ */ -- cgit v1.2.3 From abdb080f7ac8a85547f5e0246362790043bbd3f2 Mon Sep 17 00:00:00 2001 From: Andrey Smetanin Date: Tue, 10 Nov 2015 15:36:31 +0300 Subject: kvm/irqchip: kvm_arch_irq_routing_update renaming split Actually kvm_arch_irq_routing_update() should be kvm_arch_post_irq_routing_update() as it's called at the end of irq routing update. This renaming frees kvm_arch_irq_routing_update function name. kvm_arch_irq_routing_update() weak function which will be used to update mappings for arch-specific irq routing entries (in particular, the upcoming Hyper-V synthetic interrupts). Signed-off-by: Andrey Smetanin Reviewed-by: Roman Kagan Signed-off-by: Denis V. Lunev CC: Gleb Natapov CC: Paolo Bonzini CC: Roman Kagan CC: Denis V. Lunev CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c923350ca20a..23555c0f4f2d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -484,12 +484,12 @@ void vcpu_put(struct kvm_vcpu *vcpu); #ifdef __KVM_HAVE_IOAPIC void kvm_vcpu_request_scan_ioapic(struct kvm *kvm); -void kvm_arch_irq_routing_update(struct kvm *kvm); +void kvm_arch_post_irq_routing_update(struct kvm *kvm); #else static inline void kvm_vcpu_request_scan_ioapic(struct kvm *kvm) { } -static inline void kvm_arch_irq_routing_update(struct kvm *kvm) +static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm) { } #endif @@ -1091,6 +1091,7 @@ static inline void kvm_irq_routing_update(struct kvm *kvm) { } #endif +void kvm_arch_irq_routing_update(struct kvm *kvm); static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { -- cgit v1.2.3 From 5c919412fe61c35947816fdbd5f7bd09fe0dd073 Mon Sep 17 00:00:00 2001 From: Andrey Smetanin Date: Tue, 10 Nov 2015 15:36:34 +0300 Subject: kvm/x86: Hyper-V synthetic interrupt controller SynIC (synthetic interrupt controller) is a lapic extension, which is controlled via MSRs and maintains for each vCPU - 16 synthetic interrupt "lines" (SINT's); each can be configured to trigger a specific interrupt vector optionally with auto-EOI semantics - a message page in the guest memory with 16 256-byte per-SINT message slots - an event flag page in the guest memory with 16 2048-bit per-SINT event flag areas The host triggers a SINT whenever it delivers a new message to the corresponding slot or flips an event flag bit in the corresponding area. The guest informs the host that it can try delivering a message by explicitly asserting EOI in lapic or writing to End-Of-Message (EOM) MSR. The userspace (qemu) triggers interrupts and receives EOM notifications via irqfd with resampler; for that, a GSI is allocated for each configured SINT, and irq_routing api is extended to support GSI-SINT mapping. Changes v4: * added activation of SynIC by vcpu KVM_ENABLE_CAP * added per SynIC active flag * added deactivation of APICv upon SynIC activation Changes v3: * added KVM_CAP_HYPERV_SYNIC and KVM_IRQ_ROUTING_HV_SINT notes into docs Changes v2: * do not use posted interrupts for Hyper-V SynIC AutoEOI vectors * add Hyper-V SynIC vectors into EOI exit bitmap * Hyper-V SyniIC SINT msr write logic simplified Signed-off-by: Andrey Smetanin Reviewed-by: Roman Kagan Signed-off-by: Denis V. Lunev CC: Gleb Natapov CC: Paolo Bonzini CC: Roman Kagan CC: Denis V. Lunev CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 23555c0f4f2d..ebaf2f82f712 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -318,6 +318,11 @@ struct kvm_s390_adapter_int { u32 adapter_id; }; +struct kvm_hv_sint { + u32 vcpu; + u32 sint; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -331,6 +336,7 @@ struct kvm_kernel_irq_routing_entry { } irqchip; struct msi_msg msi; struct kvm_s390_adapter_int adapter; + struct kvm_hv_sint hv_sint; }; struct hlist_node link; }; -- cgit v1.2.3 From db3975717ac5e2c2761bae7b90c4f2e0abb5ef22 Mon Sep 17 00:00:00 2001 From: Andrey Smetanin Date: Tue, 10 Nov 2015 15:36:35 +0300 Subject: kvm/x86: Hyper-V kvm exit A new vcpu exit is introduced to notify the userspace of the changes in Hyper-V SynIC configuration triggered by guest writing to the corresponding MSRs. Changes v4: * exit into userspace only if guest writes into SynIC MSR's Changes v3: * added KVM_EXIT_HYPERV types and structs notes into docs Signed-off-by: Andrey Smetanin Reviewed-by: Roman Kagan Signed-off-by: Denis V. Lunev CC: Gleb Natapov CC: Paolo Bonzini CC: Roman Kagan CC: Denis V. Lunev CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ebaf2f82f712..14f95969b0f3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -143,6 +143,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_HV_CRASH 27 #define KVM_REQ_IOAPIC_EOI_EXIT 28 #define KVM_REQ_HV_RESET 29 +#define KVM_REQ_HV_EXIT 30 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 33e941547923283f7f1022f3c35359ea9403d9a4 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Sat, 14 Nov 2015 11:21:06 +0800 Subject: KVM: kvm_is_visible_gfn can be boolean This patch makes kvm_is_visible_gfn return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 14f95969b0f3..29119193a19f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -641,7 +641,7 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); -int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); +bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); -- cgit v1.2.3 From 08ff0d5e63b4f360091dd171b0ede1a3361227a1 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Sat, 14 Nov 2015 11:21:07 +0800 Subject: KVM: kvm_para_has_feature can be boolean This patch makes kvm_para_has_feature return bool due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Paolo Bonzini --- include/linux/kvm_para.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h index 00a97bb905db..35e568f04b1e 100644 --- a/include/linux/kvm_para.h +++ b/include/linux/kvm_para.h @@ -4,10 +4,8 @@ #include -static inline int kvm_para_has_feature(unsigned int feature) +static inline bool kvm_para_has_feature(unsigned int feature) { - if (kvm_arch_para_features() & (1UL << feature)) - return 1; - return 0; + return !!(kvm_arch_para_features() & (1UL << feature)); } #endif /* __LINUX_KVM_PARA_H */ -- cgit v1.2.3 From 9458ceab49179b7fd2d5192fd9dcf316ca195dc0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 24 Nov 2015 15:30:21 -0800 Subject: net: phy: bcm7xxx: Add entry for Broadcom BCM7435 Add a PHY entry for the Broadcom BCM7435 chips, this is a 40nm generation Ethernet PHY which is analogous to its 7425 and 7429 counter parts. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 59f4a7304419..f0ba9c2ec639 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -26,6 +26,7 @@ #define PHY_ID_BCM7366 0x600d8490 #define PHY_ID_BCM7425 0x600d86b0 #define PHY_ID_BCM7429 0x600d8730 +#define PHY_ID_BCM7435 0x600d8750 #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 -- cgit v1.2.3 From 02a392a0439ffdc62b4d8f17bd18d68736b166a9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 25 Nov 2015 12:50:47 -0500 Subject: ftrace: Add new type to distinguish what kind of ftrace_bug() The ftrace function hook utility has several internal checks to make sure that whatever it modifies is exactly what it expects to be modifying. This is essential as modifying running code can be extremely dangerous to the system. When an anomaly is detected, ftrace_bug() is called which sends a splat to the console and disables function tracing. There's some extra information that is printed to help diagnose the issue. One thing that is missing though is output of what ftrace was doing at the time of the crash. Was it updating a call site or perhaps converting a call site to a nop? A new global enum variable is created to state what ftrace was doing at the time of the anomaly, and this is reported in ftrace_bug(). Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eae6548efbf0..870c8eea38cd 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -296,6 +296,15 @@ int ftrace_arch_code_modify_post_process(void); struct dyn_ftrace; +enum ftrace_bug_type { + FTRACE_BUG_UNKNOWN, + FTRACE_BUG_INIT, + FTRACE_BUG_NOP, + FTRACE_BUG_CALL, + FTRACE_BUG_UPDATE, +}; +extern enum ftrace_bug_type ftrace_bug_type; + void ftrace_bug(int err, struct dyn_ftrace *rec); struct seq_file; -- cgit v1.2.3 From b05086c77a162dd8ef79606cb4723f1fc1448bb1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 25 Nov 2015 14:13:11 -0500 Subject: ftrace: Add variable ftrace_expected for archs to show expected code When an anomaly is found while modifying function code, ftrace_bug() is called which disables the function tracing infrastructure and reports information about what failed. If the code that is to be replaced does not match what is expected, then actual code is shown. Currently there is no arch generic way to show what was expected. Add a new variable pointer calld ftrace_expected that the arch code can set to point to what it expected so that ftrace_bug() can report the actual text as well as the text that was expected to be there. Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 870c8eea38cd..134f8d45b35b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -305,6 +305,12 @@ enum ftrace_bug_type { }; extern enum ftrace_bug_type ftrace_bug_type; +/* + * Archs can set this to point to a variable that holds the value that was + * expected at the call site before calling ftrace_bug(). + */ +extern const void *ftrace_expected; + void ftrace_bug(int err, struct dyn_ftrace *rec); struct seq_file; -- cgit v1.2.3 From 09a9982016499daeb3fbee5ac8d87797310a565a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 19 Nov 2015 11:43:09 +0100 Subject: timekeeping: Lift clocksource cacheline restriction We cache all hotpath members of a clocksource in the time keeper core. So there is no requirement in general to cache line align struct clocksource. Remove the enforces alignment. That allows users which need to wrap struct clocksource into their own struct to align the struct without getting extra padding. Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Russell King - ARM Linux Cc: Marc Gonzalez Cc: Daniel Lezcano Cc: Mans Rullgard Cc: Viresh Kumar Cc: Nicolas Pitre Cc: Tony Lindgren Cc: Sebastian Frias Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1511191209000.3898@nanos --- include/linux/clocksource.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 7784b597e959..6013021a3b39 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -62,12 +62,18 @@ struct module; * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary * @owner: module reference, must be set by clocksource in modules + * + * Note: This struct is not used in hotpathes of the timekeeping code + * because the timekeeper caches the hot path fields in its own data + * structure, so no line cache alignment is required, + * + * The pointer to the clocksource itself is handed to the read + * callback. If you need extra information there you can wrap struct + * clocksource into your own struct. Depending on the amount of + * information you need you should consider to cache line align that + * structure. */ struct clocksource { - /* - * Hotpath data, fits in a single cache line when the - * clocksource itself is cacheline aligned. - */ cycle_t (*read)(struct clocksource *cs); cycle_t mask; u32 mult; @@ -95,7 +101,7 @@ struct clocksource { cycle_t wd_last; #endif struct module *owner; -} ____cacheline_aligned; +}; /* * Clock source flags bits:: -- cgit v1.2.3 From c896939f7cff767091b5d84587cd144e5d3613b7 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 5 Nov 2015 09:55:08 +0100 Subject: KVM: use heuristic for fast VCPU lookup by id Usually, VCPU ids match the array index. So let's try a fast lookup first before falling back to the slow iteration. Suggested-by: Christian Borntraeger Reviewed-by: Dominik Dingel Reviewed-by: Christian Borntraeger Signed-off-by: David Hildenbrand Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 29119193a19f..a754fc08e194 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -472,6 +472,11 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) struct kvm_vcpu *vcpu; int i; + if (id < 0 || id >= KVM_MAX_VCPUS) + return NULL; + vcpu = kvm_get_vcpu(kvm, id); + if (vcpu && vcpu->vcpu_id == id) + return vcpu; kvm_for_each_vcpu(i, vcpu, kvm) if (vcpu->vcpu_id == id) return vcpu; -- cgit v1.2.3 From 4bd33b568855f5483a6c6d7e4706ef507ab8586b Mon Sep 17 00:00:00 2001 From: Janosch Frank Date: Wed, 14 Oct 2015 12:37:35 +0200 Subject: KVM: Remove unnecessary debugfs dentry references KVM creates debugfs files to export VM statistics to userland. To be able to remove them on kvm exit it tracks the files' dentries. Since their parent directory is also tracked and since each parent direntry knows its children we can easily remove them by using debugfs_remove_recursive(kvm_debugfs_dir). Therefore we don't need the extra tracking in the kvm_stats_debugfs_item anymore. Signed-off-by: Janosch Frank Reviewed-By: Sascha Silbe Acked-by: Christian Borntraeger Signed-off-by: Christian Borntraeger --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a754fc08e194..590c46e672df 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1016,7 +1016,6 @@ struct kvm_stats_debugfs_item { const char *name; int offset; enum kvm_stat_kind kind; - struct dentry *dentry; }; extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; -- cgit v1.2.3 From 1ce0bf50ae2233c7115a18c0c623662d177b434c Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 26 Nov 2015 13:55:39 +0800 Subject: net: Generalise wq_has_sleeper helper The memory barrier in the helper wq_has_sleeper is needed by just about every user of waitqueue_active. This patch generalises it by making it take a wait_queue_head_t directly. The existing helper is renamed to skwq_has_sleeper. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/wait.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 1e1bf9f963a9..6aa09a875fbd 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -107,6 +107,27 @@ static inline int waitqueue_active(wait_queue_head_t *q) return !list_empty(&q->task_list); } +/** + * wq_has_sleeper - check if there are any waiting processes + * @wq: wait queue head + * + * Returns true if wq has waiting processes + * + * Please refer to the comment for waitqueue_active. + */ +static inline bool wq_has_sleeper(wait_queue_head_t *wq) +{ + /* + * We need to be sure we are in sync with the + * add_wait_queue modifications to the wait queue. + * + * This memory barrier should be paired with one on the + * waiting side. + */ + smp_mb(); + return waitqueue_active(wq); +} + extern void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); extern void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait); extern void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait); -- cgit v1.2.3 From 06bd6c0370bb88a2256c6763a32bc4e4ade06521 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 26 Nov 2015 15:23:45 +0100 Subject: net: ipmr: remove unused MFC_NOTIFY flag and make the flags enum MFC_NOTIFY was introduced in kernel 2.1.68 but afaik it hasn't been used and I couldn't find any users currently so just remove it. Only MFC_STATIC is left, so move it into an enum, add a description and use BIT(). Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 79aaa9fc1a15..fa66ebc1fed6 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -64,6 +64,13 @@ struct vif_device { #define VIFF_STATIC 0x8000 +/* mfc_flags: + * MFC_STATIC - the entry was added statically (not by a routing daemon) + */ +enum { + MFC_STATIC = BIT(0), +}; + struct mfc_cache { struct list_head list; __be32 mfc_mcastgrp; /* Group the entry belongs to */ @@ -89,9 +96,6 @@ struct mfc_cache { struct rcu_head rcu; }; -#define MFC_STATIC 1 -#define MFC_NOTIFY 2 - #define MFC_LINES 64 #ifdef __BIG_ENDIAN -- cgit v1.2.3 From 520191bb404c4b7b4cdb70a5480ada974b0c2d60 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 26 Nov 2015 15:23:46 +0100 Subject: net: ipmr: adjust mroute.h style and drop extern Remove extra spaces and tabs, adjust function definitions, remove an unnecessary ifdef (already used below, just move code) and drop extern from the functions. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 47 +++++++++++++++++++++-------------------------- 1 file changed, 21 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index fa66ebc1fed6..7c567a2679ce 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -9,38 +9,28 @@ #ifdef CONFIG_IP_MROUTE static inline int ip_mroute_opt(int opt) { - return (opt >= MRT_BASE) && (opt <= MRT_MAX); + return opt >= MRT_BASE && opt <= MRT_MAX; } -#else -static inline int ip_mroute_opt(int opt) -{ - return 0; -} -#endif -#ifdef CONFIG_IP_MROUTE -extern int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); -extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); -extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); -extern int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); -extern int ip_mr_init(void); +int ip_mroute_setsockopt(struct sock *, int, char __user *, unsigned int); +int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); +int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); +int ip_mr_init(void); #else -static inline -int ip_mroute_setsockopt(struct sock *sock, - int optname, char __user *optval, unsigned int optlen) +static inline int ip_mroute_setsockopt(struct sock *sock, int optname, + char __user *optval, unsigned int optlen) { return -ENOPROTOOPT; } -static inline -int ip_mroute_getsockopt(struct sock *sock, - int optname, char __user *optval, int __user *optlen) +static inline int ip_mroute_getsockopt(struct sock *sock, int optname, + char __user *optval, int __user *optlen) { return -ENOPROTOOPT; } -static inline -int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) +static inline int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) { return -ENOIOCTLCMD; } @@ -49,6 +39,11 @@ static inline int ip_mr_init(void) { return 0; } + +static inline int ip_mroute_opt(int opt) +{ + return 0; +} #endif struct vif_device { @@ -96,16 +91,16 @@ struct mfc_cache { struct rcu_head rcu; }; -#define MFC_LINES 64 +#define MFC_LINES 64 #ifdef __BIG_ENDIAN #define MFC_HASH(a,b) (((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1)) #else #define MFC_HASH(a,b) ((((__force u32)(__be32)a)^(((__force u32)(__be32)b)>>2))&(MFC_LINES-1)) -#endif +#endif struct rtmsg; -extern int ipmr_get_route(struct net *net, struct sk_buff *skb, - __be32 saddr, __be32 daddr, - struct rtmsg *rtm, int nowait); +int ipmr_get_route(struct net *net, struct sk_buff *skb, + __be32 saddr, __be32 daddr, + struct rtmsg *rtm, int nowait); #endif -- cgit v1.2.3 From 5ea1f13299d8b8edcb2969eda4c81f8e3264b706 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 26 Nov 2015 15:23:47 +0100 Subject: net: ipmr: move struct mr_table and VIF_EXISTS to mroute.h Move the definitions of VIF_EXISTS() and struct mr_table to mroute.h Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/mroute.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 7c567a2679ce..bf9b322cb0b0 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -59,6 +59,25 @@ struct vif_device { #define VIFF_STATIC 0x8000 +#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) +#define MFC_LINES 64 + +struct mr_table { + struct list_head list; + possible_net_t net; + u32 id; + struct sock __rcu *mroute_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc_unres_queue; + struct list_head mfc_cache_array[MFC_LINES]; + struct vif_device vif_table[MAXVIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + bool mroute_do_assert; + bool mroute_do_pim; + int mroute_reg_vif_num; +}; + /* mfc_flags: * MFC_STATIC - the entry was added statically (not by a routing daemon) */ @@ -91,8 +110,6 @@ struct mfc_cache { struct rcu_head rcu; }; -#define MFC_LINES 64 - #ifdef __BIG_ENDIAN #define MFC_HASH(a,b) (((((__force u32)(__be32)a)>>24)^(((__force u32)(__be32)b)>>26))&(MFC_LINES-1)) #else -- cgit v1.2.3 From 1973a4ea6ceaa47671227c3077f90508ea30897b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 26 Nov 2015 15:23:48 +0100 Subject: net: ipmr: move pimsm_enabled to pim.h and rename Move the inline pimsm_enabled() to pim.h and rename it to ipmr_pimsm_enabled to show it's for the ipv4 ipmr code since pim.h is used by IPv6 too. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/pim.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pim.h b/include/linux/pim.h index 252bf6644c51..e1d756f81348 100644 --- a/include/linux/pim.h +++ b/include/linux/pim.h @@ -13,6 +13,11 @@ #define PIM_NULL_REGISTER cpu_to_be32(0x40000000) +static inline bool ipmr_pimsm_enabled(void) +{ + return IS_BUILTIN(CONFIG_IP_PIMSM_V1) || IS_BUILTIN(CONFIG_IP_PIMSM_V2); +} + /* PIMv2 register message header layout (ietf-draft-idmr-pimvsm-v2-00.ps */ struct pimreghdr { -- cgit v1.2.3 From a6baa3deaf7aaec5f1c5233128b5285c4c7074e0 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Mon, 30 Nov 2015 16:20:15 +0100 Subject: regmap: Fix leftover from struct reg_default to struct reg_sequence change In 8019ff6cfc04 ("regmap: Use reg_sequence for multi_reg_write / register_patch") struct reg_default was renamed to struct reg_secquence, which missed one place to fix up. Reported-by: kbuild test robot Signed-off-by: Daniel Wagner Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index d68bb402120e..4d9a1a04647b 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1021,7 +1021,7 @@ static inline void regmap_async_complete(struct regmap *map) } static inline int regmap_register_patch(struct regmap *map, - const struct reg_default *regs, + const struct reg_sequence *regs, int num_regs) { WARN_ONCE(1, "regmap API is disabled"); -- cgit v1.2.3 From 29732938a6289a15e907da234d6692a2ead71855 Mon Sep 17 00:00:00 2001 From: Zach Brown Date: Tue, 10 Nov 2015 16:53:30 -0500 Subject: vfs: add copy_file_range syscall and vfs helper Add a copy_file_range() system call for offloading copies between regular files. This gives an interface to underlying layers of the storage stack which can copy without reading and writing all the data. There are a few candidates that should support copy offloading in the nearer term: - btrfs shares extent references with its clone ioctl - NFS has patches to add a COPY command which copies on the server - SCSI has a family of XCOPY commands which copy in the device This system call avoids the complexity of also accelerating the creation of the destination file by operating on an existing destination file descriptor, not a path. Currently the high level vfs entry point limits copy offloading to files on the same mount and super (and not in the same file). This can be relaxed if we get implementations which can copy between file systems safely. Signed-off-by: Zach Brown [Anna Schumaker: Change -EINVAL to -EBADF during file verification, Change flags parameter from int to unsigned int, Add function to include/linux/syscalls.h, Check copy len after file open mode, Don't forbid ranges inside the same file, Use rw_verify_area() to veriy ranges, Use file_out rather than file_in, Add COPY_FR_REFLINK flag] Signed-off-by: Anna Schumaker Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 +++ include/linux/syscalls.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..e8a736242b1a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1629,6 +1629,7 @@ struct file_operations { #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); }; struct inode_operations { @@ -1680,6 +1681,8 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *); +extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, + loff_t, size_t, unsigned int); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c2b66a277e98..185815c96433 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -886,6 +886,9 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *envp, int flags); asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in, + int fd_out, loff_t __user *off_out, + size_t len, unsigned int flags); asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); -- cgit v1.2.3 From 91420b83baa046ada1a899c97f3b2c52a9045705 Mon Sep 17 00:00:00 2001 From: Sudarsana Kalluru Date: Mon, 30 Nov 2015 12:25:03 +0200 Subject: qed: Add support for changing LED state Physical LEDs are being controlled by the management FW. This adds the qed functionality required to request management FW to change the LED configuration, as well as the necessary APIs for this functionality to later be used by the protocol drivers. Signed-off-by: Sudarsana Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index dc9a1353f971..d4a32e878180 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -25,6 +25,12 @@ #include #include +enum qed_led_mode { + QED_LED_MODE_OFF, + QED_LED_MODE_ON, + QED_LED_MODE_RESTORE +}; + #define DIRECT_REG_WR(reg_addr, val) writel((u32)val, \ (void __iomem *)(reg_addr)) @@ -252,6 +258,17 @@ struct qed_common_ops { void (*chain_free)(struct qed_dev *cdev, struct qed_chain *p_chain); + +/** + * @brief set_led - Configure LED mode + * + * @param cdev + * @param mode - LED mode + * + * @return 0 on success, error otherwise. + */ + int (*set_led)(struct qed_dev *cdev, + enum qed_led_mode mode); }; /** -- cgit v1.2.3 From c0eb454034aab783dc602739237a63b30867f5bd Mon Sep 17 00:00:00 2001 From: KY Srinivasan Date: Tue, 1 Dec 2015 16:43:10 -0800 Subject: hv_netvsc: Don't ask for additional head room in the skb The rndis header is 116 bytes big and can be placed in the default head room that will be available in the skb. Since the netvsc packet is less than 48 bytes, we can use the skb control buffer for the netvsc packet. With these changes we don't need to ask for additional head room. Signed-off-by: K. Y. Srinivasan Reviewed-by: Haiyang Zhang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7d2d1d7aaec7..fcbc5259c630 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -132,7 +132,9 @@ static inline bool dev_xmit_complete(int rc) * used. */ -#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) +#if defined(CONFIG_HYPERV_NET) +# define LL_MAX_HEADER 128 +#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else -- cgit v1.2.3 From 255379ae9af8c04788c171fa050949ab2ac3f356 Mon Sep 17 00:00:00 2001 From: Jim Snow Date: Thu, 3 Dec 2015 10:48:51 +0100 Subject: EDAC: Add DDR4 flag Make EDAC aware of DDR4/RDDR4 mem types. Signed-off-by: Jim Snow Cc: Mauro Carvalho Chehab Cc: linux-edac Cc: lukasz.anaczkowski@intel.com Link: http://lkml.kernel.org/r/1449136134-23706-2-git-send-email-hubert.chrzaniuk@intel.com [ Rebase to 4.4-rc3. ] Signed-off-by: Hubert Chrzaniuk Signed-off-by: Borislav Petkov --- include/linux/edac.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 4fe67b853de0..da6964873dcf 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -237,8 +237,10 @@ enum mem_type { #define MEM_FLAG_FB_DDR2 BIT(MEM_FB_DDR2) #define MEM_FLAG_RDDR2 BIT(MEM_RDDR2) #define MEM_FLAG_XDR BIT(MEM_XDR) -#define MEM_FLAG_DDR3 BIT(MEM_DDR3) -#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) +#define MEM_FLAG_DDR3 BIT(MEM_DDR3) +#define MEM_FLAG_RDDR3 BIT(MEM_RDDR3) +#define MEM_FLAG_DDR4 BIT(MEM_DDR4) +#define MEM_FLAG_RDDR4 BIT(MEM_RDDR4) /** * enum edac-type - Error Detection and Correction capabilities and mode -- cgit v1.2.3 From b53202e6308939d33ba0c78712e850f891b4e76f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 3 Dec 2015 10:24:08 -0500 Subject: cgroup: kill cgrp_ss_priv[CGROUP_CANFORK_COUNT] and friends Now that nobody use the "priv" arg passed to can_fork/cancel_fork/fork we can kill CGROUP_CANFORK_COUNT/SUBSYS_TAG/etc and cgrp_ss_priv[] in copy_process(). Signed-off-by: Oleg Nesterov Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 12 +++--------- include/linux/cgroup.h | 19 ++++++------------- include/linux/cgroup_subsys.h | 18 ------------------ 3 files changed, 9 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 678cd5e4e881..8cfbc9dfd650 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -34,17 +34,12 @@ struct seq_file; /* define the enumeration of all cgroup subsystems */ #define SUBSYS(_x) _x ## _cgrp_id, -#define SUBSYS_TAG(_t) CGROUP_ ## _t, \ - __unused_tag_ ## _t = CGROUP_ ## _t - 1, enum cgroup_subsys_id { #include CGROUP_SUBSYS_COUNT, }; -#undef SUBSYS_TAG #undef SUBSYS -#define CGROUP_CANFORK_COUNT (CGROUP_CANFORK_END - CGROUP_CANFORK_START) - /* bits in struct cgroup_subsys_state flags field */ enum { CSS_NO_REF = (1 << 0), /* no reference counting for this css */ @@ -424,9 +419,9 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); - int (*can_fork)(struct task_struct *task, void **priv_p); - void (*cancel_fork)(struct task_struct *task, void *priv); - void (*fork)(struct task_struct *task, void *priv); + int (*can_fork)(struct task_struct *task); + void (*cancel_fork)(struct task_struct *task); + void (*fork)(struct task_struct *task); void (*exit)(struct task_struct *task); void (*free)(struct task_struct *task); void (*bind)(struct cgroup_subsys_state *root_css); @@ -512,7 +507,6 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) #else /* CONFIG_CGROUPS */ -#define CGROUP_CANFORK_COUNT 0 #define CGROUP_SUBSYS_COUNT 0 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {} diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cb91b44f5f78..2b3e231448ca 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -96,12 +96,9 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); -extern int cgroup_can_fork(struct task_struct *p, - void *ss_priv[CGROUP_CANFORK_COUNT]); -extern void cgroup_cancel_fork(struct task_struct *p, - void *ss_priv[CGROUP_CANFORK_COUNT]); -extern void cgroup_post_fork(struct task_struct *p, - void *old_ss_priv[CGROUP_CANFORK_COUNT]); +extern int cgroup_can_fork(struct task_struct *p); +extern void cgroup_cancel_fork(struct task_struct *p); +extern void cgroup_post_fork(struct task_struct *p); void cgroup_exit(struct task_struct *p); void cgroup_free(struct task_struct *p); @@ -539,13 +536,9 @@ static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} -static inline int cgroup_can_fork(struct task_struct *p, - void *ss_priv[CGROUP_CANFORK_COUNT]) -{ return 0; } -static inline void cgroup_cancel_fork(struct task_struct *p, - void *ss_priv[CGROUP_CANFORK_COUNT]) {} -static inline void cgroup_post_fork(struct task_struct *p, - void *ss_priv[CGROUP_CANFORK_COUNT]) {} +static inline int cgroup_can_fork(struct task_struct *p) { return 0; } +static inline void cgroup_cancel_fork(struct task_struct *p) {} +static inline void cgroup_post_fork(struct task_struct *p) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 1a96fdaa33d5..0df0336acee9 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -6,14 +6,8 @@ /* * This file *must* be included with SUBSYS() defined. - * SUBSYS_TAG() is a noop if undefined. */ -#ifndef SUBSYS_TAG -#define __TMP_SUBSYS_TAG -#define SUBSYS_TAG(_x) -#endif - #if IS_ENABLED(CONFIG_CPUSETS) SUBSYS(cpuset) #endif @@ -58,17 +52,10 @@ SUBSYS(net_prio) SUBSYS(hugetlb) #endif -/* - * Subsystems that implement the can_fork() family of callbacks. - */ -SUBSYS_TAG(CANFORK_START) - #if IS_ENABLED(CONFIG_CGROUP_PIDS) SUBSYS(pids) #endif -SUBSYS_TAG(CANFORK_END) - /* * The following subsystems are not supported on the default hierarchy. */ @@ -76,11 +63,6 @@ SUBSYS_TAG(CANFORK_END) SUBSYS(debug) #endif -#ifdef __TMP_SUBSYS_TAG -#undef __TMP_SUBSYS_TAG -#undef SUBSYS_TAG -#endif - /* * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS. */ -- cgit v1.2.3 From c981e4213e9d2d4ec79501bd607722ec712742a2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:06 +0100 Subject: net: add netif_is_team_master helper Similar to other helpers, caller can use this to find out if device is team master. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fcbc5259c630..2b889be65d88 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1273,6 +1273,7 @@ struct net_device_ops { * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device + * @IFF_TEAM: device is a team device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1299,6 +1300,7 @@ enum netdev_priv_flags { IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, IFF_L3MDEV_SLAVE = 1<<23, + IFF_TEAM = 1<<24, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1325,6 +1327,7 @@ enum netdev_priv_flags { #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE +#define IFF_TEAM IFF_TEAM /** * struct net_device - The DEVICE structure. @@ -3889,6 +3892,11 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } +static inline bool netif_is_team_master(struct net_device *dev) +{ + return dev->priv_flags & IFF_TEAM; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From f7f019ee6d117de5007d0b10e7960696bbf111eb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:07 +0100 Subject: net: add netif_is_team_port helper Similar to other helpers, caller can use this to find out if device is team port. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2b889be65d88..b3601f8a9b42 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3897,6 +3897,11 @@ static inline bool netif_is_team_master(struct net_device *dev) return dev->priv_flags & IFF_TEAM; } +static inline bool netif_is_team_port(struct net_device *dev) +{ + return dev->priv_flags & IFF_TEAM_PORT; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 7be61833042e7757745345eedc7b0efee240c189 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:08 +0100 Subject: net: add netif_is_lag_master helper Some code does not mind if the master is bond or team and treats them the same, as generic LAG. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b3601f8a9b42..3ca083efa560 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3902,6 +3902,11 @@ static inline bool netif_is_team_port(struct net_device *dev) return dev->priv_flags & IFF_TEAM_PORT; } +static inline bool netif_is_lag_master(struct net_device *dev) +{ + return netif_is_bond_master(dev) || netif_is_team_master(dev); +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From e0ba1414f310c83bf425fe26fa2cd5f1befcd6dc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:09 +0100 Subject: net: add netif_is_lag_port helper Some code does not mind if a device is bond slave or team port and treats them the same, as generic LAG ports. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ca083efa560..1506be58c59a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3907,6 +3907,11 @@ static inline bool netif_is_lag_master(struct net_device *dev) return netif_is_bond_master(dev) || netif_is_team_master(dev); } +static inline bool netif_is_lag_port(struct net_device *dev) +{ + return netif_is_bond_slave(dev) || netif_is_team_port(dev); +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { -- cgit v1.2.3 From 6dffb0447c25476f499d205dfceb1972e8dae919 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:10 +0100 Subject: net: propagate upper priv via netdev_master_upper_dev_link Eliminate netdev_master_upper_dev_link_private and pass priv directly as a parameter of netdev_master_upper_dev_link. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1506be58c59a..939b8f3de810 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3619,10 +3619,8 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); int netdev_master_upper_dev_link(struct net_device *dev, - struct net_device *upper_dev); -int netdev_master_upper_dev_link_private(struct net_device *dev, - struct net_device *upper_dev, - void *private); + struct net_device *upper_dev, + void *upper_priv); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); -- cgit v1.2.3 From 29bf24afb29042f568fa67b1b0eee46796725ed2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:11 +0100 Subject: net: add possibility to pass information about upper device via notifier Sometimes the drivers and other code would find it handy to know some internal information about upper device being changed. So allow upper-code to pass information down to notifier listeners during linking. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 939b8f3de810..aea556c64f2c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2163,6 +2163,7 @@ struct netdev_notifier_changeupper_info { struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ bool linking; /* is the nofication for link or unlink */ + void *upper_info; /* upper dev info */ }; static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, @@ -3620,7 +3621,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, - void *upper_priv); + void *upper_priv, void *upper_info); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); -- cgit v1.2.3 From 764f5e544118508add420724789f46e04dba91eb Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:12 +0100 Subject: net: add info struct for LAG changeupper This struct will be shared by bonding and team to pass internal information to notifier listeners. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index aea556c64f2c..3ab90ea0ed03 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2110,6 +2110,19 @@ struct pcpu_sw_netstats { #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL); +enum netdev_lag_tx_type { + NETDEV_LAG_TX_TYPE_UNKNOWN, + NETDEV_LAG_TX_TYPE_RANDOM, + NETDEV_LAG_TX_TYPE_BROADCAST, + NETDEV_LAG_TX_TYPE_ROUNDROBIN, + NETDEV_LAG_TX_TYPE_ACTIVEBACKUP, + NETDEV_LAG_TX_TYPE_HASH, +}; + +struct netdev_lag_upper_info { + enum netdev_lag_tx_type tx_type; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink -- cgit v1.2.3 From 8fd728566a354f7bc9cb6e781f185b8c39cf505b Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:13 +0100 Subject: team: fill-up LAG changeupper info struct and pass it along Initialize netdev_lag_upper_info structure by TX type according to current team mode and pass it along via netdev_master_upper_dev_link. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_team.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_team.h b/include/linux/if_team.h index a6aa970758a2..b84e49c3a738 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -164,6 +164,7 @@ struct team_mode { size_t priv_size; size_t port_priv_size; const struct team_mode_ops *ops; + enum netdev_lag_tx_type lag_tx_type; }; #define TEAM_PORT_HASHBITS 4 -- cgit v1.2.3 From 04d482660a07039fc4e9a42bb3517db236d98f96 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:15 +0100 Subject: net: introduce change lower state notifier When lower device like bonding slave, team/bridge port, etc changes its state, it is useful for others to notice this change. Currently this is implemented specificly for bonding as NETDEV_BONDING_INFO notifier. This patch aims to replace this specific usage and make this more generic to be used for all upper-lower devices. Introduce NETDEV_CHANGELOWERSTATE netdev notifier type and netdev_lower_state_changed() helper. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ab90ea0ed03..ad69f237aa78 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2158,6 +2158,7 @@ struct netdev_lag_upper_info { #define NETDEV_CHANGEINFODATA 0x0018 #define NETDEV_BONDING_INFO 0x0019 #define NETDEV_PRECHANGEUPPER 0x001A +#define NETDEV_CHANGELOWERSTATE 0x001B int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); @@ -2179,6 +2180,11 @@ struct netdev_notifier_changeupper_info { void *upper_info; /* upper dev info */ }; +struct netdev_notifier_changelowerstate_info { + struct netdev_notifier_info info; /* must be first */ + void *lower_state_info; /* is lower dev state */ +}; + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -3640,6 +3646,8 @@ void netdev_upper_dev_unlink(struct net_device *dev, void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); 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); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 -- cgit v1.2.3 From fb1b2e3ce53aef80b3cef71f3885d584cdbdc6b8 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Dec 2015 12:12:16 +0100 Subject: net: introduce lower state changed info structure for LAG lowers This is shared info structure for bonding and team. Serves to pass down info about link state and port activity to notification listeners. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ad69f237aa78..fa84b59eb197 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2123,6 +2123,11 @@ struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; }; +struct netdev_lag_lower_state_info { + u8 link_up : 1, + tx_enabled : 1; +}; + #include /* netdevice notifier chain. Please remember to update the rtnetlink -- cgit v1.2.3 From fc50db98ff872372f266695858f87a12eb1b4f05 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 1 Dec 2015 18:03:09 +0200 Subject: net/mlx5_core: Add base sriov support This patch adds SRIOV base support for mlx5 supported devices. The same driver is used for both PFs and VFs; VFs are identified by the driver through the flag MLX5_PCI_DEV_IS_VF added to the pci table entries. Virtual functions are created as usual through writing a value to the sriov_numvs sysfs file of the PF device. Upon instantiating VFs, they will all be probed by the driver on the hypervisor. One can gracefully unbind them through /sys/bus/pci/drivers/mlx5_core/unbind. mlx5_wait_for_vf_pages() was added to ensure that when a VF dies without executing proper teardown, the hypervisor driver waits till all of the pages that were allocated at the hypervisor to maintain its operation are returned. In order for the VF to be operational, the PF needs to call enable_hca for it. This can be done before the VFs are created through a call to pci_enable_sriov. If the there are VFs assigned to a VMs when the driver of the PF is unloaded, all the VF will experience system error and PF driver unloads cleanly; in this case pci_disable_sriov is not called and the devices will show when running lspci. Once the PF driver is reloaded, it will sync its data structures which maintain state on its VFs. Signed-off-by: Eli Cohen Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 24 ++++++++++++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5c857f2a20d7..efebb87163c8 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -426,6 +426,16 @@ struct mlx5_mr_table { struct radix_tree_root tree; }; +struct mlx5_vf_context { + int enabled; +}; + +struct mlx5_core_sriov { + struct mlx5_vf_context *vfs_ctx; + int num_vfs; + int enabled_vfs; +}; + struct mlx5_irq_info { cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; @@ -447,6 +457,7 @@ struct mlx5_priv { int fw_pages; atomic_t reg_pages; struct list_head free_list; + int vfs_pages; struct mlx5_core_health health; @@ -485,6 +496,8 @@ struct mlx5_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; + struct mlx5_core_sriov sriov; + unsigned long pci_dev_data; }; enum mlx5_device_state { @@ -739,6 +752,8 @@ void mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); int mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); +int mlx5_sriov_init(struct mlx5_core_dev *dev); +int mlx5_sriov_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); @@ -884,6 +899,15 @@ struct mlx5_profile { } mr_cache[MAX_MR_CACHE_ENTRIES]; }; +enum { + MLX5_PCI_DEV_IS_VF = 1 << 0, +}; + +static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) +{ + return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); +} + static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1565324eb620..9b76fddd696b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -665,7 +665,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_17[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 reserved_18[0x4]; + u8 reserved_18_0; + u8 early_vf_enable; + u8 reserved_18[0x2]; u8 local_ca_ack_delay[0x5]; u8 reserved_19[0x6]; u8 port_type[0x2]; -- cgit v1.2.3 From 54f0a411ec72cb437d57d0c9654dcbd0f198ff3a Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:10 +0200 Subject: net/mlx5: Add HW capabilities and structs for SR-IOV E-Switch Update HCA capabilities and HW struct to include needed capabilities for upcoming Ethernet Switch (SR-IOV E-Switch). Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 9b76fddd696b..836cf0e43174 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -665,7 +665,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_17[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; - u8 reserved_18_0; + u8 eswitch_flow_table[0x1]; u8 early_vf_enable; u8 reserved_18[0x2]; u8 local_ca_ack_delay[0x5]; @@ -789,22 +789,30 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_60[0x1b]; u8 log_max_wq_sz[0x5]; - u8 reserved_61[0xa0]; - + u8 nic_vport_change_event[0x1]; + u8 reserved_61[0xa]; + u8 log_max_vlan_list[0x5]; u8 reserved_62[0x3]; + u8 log_max_current_mc_list[0x5]; + u8 reserved_63[0x3]; + u8 log_max_current_uc_list[0x5]; + + u8 reserved_64[0x80]; + + u8 reserved_65[0x3]; u8 log_max_l2_table[0x5]; - u8 reserved_63[0x8]; + u8 reserved_66[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_64[0x100]; + u8 reserved_67[0xe0]; - u8 reserved_65[0x1f]; + u8 reserved_68[0x1f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_66[0x220]; + u8 reserved_69[0x220]; }; enum { @@ -2135,10 +2143,6 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_wq_bits wq; }; -enum { - MLX5_NIC_VPORT_CONTEXT_ALLOWED_LIST_TYPE_CURRENT_UC_MAC_ADDRESS = 0x0, -}; - struct mlx5_ifc_nic_vport_context_bits { u8 reserved_0[0x1f]; u8 roce_en[0x1]; -- cgit v1.2.3 From e1d7d349c69d12721c420f1fe673ce9aa462aadd Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:11 +0200 Subject: net/mlx5: Update access functions to Query/Modify vport MAC address In preparation for SR-IOV we add here an API to enable each e-switch client (PF/VF) to configure its L2 MAC addresses and for the e-switch manager (usually the PF) to access them in order to be able to configure them into the e-switch. Therefore we now pass vport num parameter to mlx5_query_nic_vport_context, so PF can access other vports contexts. preperation for ethernet sriov and l2 table management. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/vport.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 967e0fd06e89..43e82d9f5463 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,7 +36,10 @@ #include u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); -void mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u8 *addr); +int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, + u16 vport, u8 *addr); +int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, + u16 vport, u8 *addr); int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, u16 vf_num, u16 gid_index, union ib_gid *gid); -- cgit v1.2.3 From e16aea2744abea612c27ee0eef606c6a6a8204de Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:12 +0200 Subject: net/mlx5: Introduce access functions to modify/query vport mac lists Those functions are needed to notify the upcoming L2 table and SR-IOV E-Switch(FDB) manager(PF), of the NIC vport (vf) UC/MC mac lists changes. preperation for ethernet sriov and l2 table management. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 6 ++++++ include/linux/mlx5/vport.h | 10 ++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0b473cbfa7ef..0d2f0435a9f0 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1102,6 +1102,12 @@ enum { MLX5_FLOW_CONTEXT_DEST_TYPE_TIR = 2, }; +enum mlx5_list_type { + MLX5_NVPRT_LIST_TYPE_UC = 0x0, + MLX5_NVPRT_LIST_TYPE_MC = 0x1, + MLX5_NVPRT_LIST_TYPE_VLAN = 0x2, +}; + enum { MLX5_RQC_RQ_TYPE_MEMORY_RQ_INLINE = 0x0, MLX5_RQC_RQ_TYPE_MEMORY_RQ_RPM = 0x1, diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 43e82d9f5463..00bbec8d9527 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -34,6 +34,7 @@ #define __MLX5_VPORT_H__ #include +#include u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, @@ -54,5 +55,14 @@ int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev, u64 *sys_image_guid); int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, u64 *node_guid); +int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, + u32 vport, + enum mlx5_list_type list_type, + u8 addr_list[][ETH_ALEN], + int *list_size); +int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, + enum mlx5_list_type list_type, + u8 addr_list[][ETH_ALEN], + int list_size); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From e75465148b7df7f2796c75bf98bf33f171edeb2b Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:13 +0200 Subject: net/mlx5: Introduce access functions to modify/query vport state In preparation for SR-IOV we add here an API to enable each e-switch manager (PF) to configure its VFs link states in e-switch preparation for ethernet sriov. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 1 + include/linux/mlx5/vport.h | 6 +++++- 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 836cf0e43174..655184702ea2 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2946,6 +2946,7 @@ struct mlx5_ifc_query_vport_state_out_bits { enum { MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT = 0x0, + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT = 0x1, }; struct mlx5_ifc_query_vport_state_in_bits { diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 00bbec8d9527..c1bba5948851 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,7 +36,11 @@ #include #include -u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod); +u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); +u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, + u16 vport); +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); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, -- cgit v1.2.3 From d82b73186dab70d6d332dd2afdb48608be2e5230 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:14 +0200 Subject: net/mlx5: Introduce access functions to modify/query vport promisc mode Those functions are needed to notify the upcoming SR-IOV E-Switch(FDB) manager(PF), of the NIC vport (vf) promisc mode changes. Preperation for ethernet sriov and l2 table management. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 28 +++++++++++++++++++++++----- include/linux/mlx5/vport.h | 9 +++++++++ 2 files changed, 32 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 655184702ea2..2728b5f6c017 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2147,16 +2147,31 @@ struct mlx5_ifc_nic_vport_context_bits { u8 reserved_0[0x1f]; u8 roce_en[0x1]; - u8 reserved_1[0x760]; + u8 arm_change_event[0x1]; + u8 reserved_1[0x1a]; + u8 event_on_mtu[0x1]; + u8 event_on_promisc_change[0x1]; + u8 event_on_vlan_change[0x1]; + u8 event_on_mc_address_change[0x1]; + u8 event_on_uc_address_change[0x1]; - u8 reserved_2[0x5]; + u8 reserved_2[0xf0]; + + u8 mtu[0x10]; + + u8 reserved_3[0x640]; + + u8 promisc_uc[0x1]; + u8 promisc_mc[0x1]; + u8 promisc_all[0x1]; + u8 reserved_4[0x2]; u8 allowed_list_type[0x3]; - u8 reserved_3[0xc]; + u8 reserved_5[0xc]; u8 allowed_list_size[0xc]; struct mlx5_ifc_mac_address_layout_bits permanent_address; - u8 reserved_4[0x20]; + u8 reserved_6[0x20]; u8 current_uc_mac_address[0][0x40]; }; @@ -4235,7 +4250,10 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits { }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_0[0x1c]; + u8 reserved_0[0x19]; + u8 mtu[0x1]; + u8 change_event[0x1]; + u8 promisc[0x1]; u8 permanent_address[0x1]; u8 addresses_list[0x1]; u8 roce_en[0x1]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index c1bba5948851..dbbaed9f975a 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -68,5 +68,14 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int list_size); +int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, + u32 vport, + int *promisc_uc, + int *promisc_mc, + int *promisc_all); +int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, + int promisc_uc, + int promisc_mc, + int promisc_all); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From c0046cf7b81ac55b8bf056c71918ec04edd99379 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:15 +0200 Subject: net/mlx5: Introduce access functions to modify/query vport vlans Those functions are needed to notify the upcoming L2 table and SR-IOV E-Switch(FDB) manager(PF), of the NIC vport (vf) vlan table changes. preperation for ethernet sriov and l2 table management. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 7 +++++++ include/linux/mlx5/vport.h | 7 +++++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2728b5f6c017..39487d0c305d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -910,6 +910,13 @@ struct mlx5_ifc_mac_address_layout_bits { u8 mac_addr_31_0[0x20]; }; +struct mlx5_ifc_vlan_layout_bits { + u8 reserved_0[0x14]; + u8 vlan[0x0c]; + + u8 reserved_1[0x20]; +}; + struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { u8 reserved_0[0xa0]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index dbbaed9f975a..638f2ca7a527 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -77,5 +77,12 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, int promisc_uc, int promisc_mc, int promisc_all); +int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, + u32 vport, + u16 vlans[], + int *size); +int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, + u16 vlans[], + int list_size); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 073bb189a41d7bbad509b576a690611c46c4858f Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:18 +0200 Subject: net/mlx5: Introducing E-Switch and l2 table E-Switch is the software entity that represents and manages ConnectX4 inter-HCA ethernet l2 switching. E-Switch has its own Virtual Ports, each Vport/vNIC/VF can be connected to the device through a vport of an e-switch. Each e-switch is managed by one vNIC identified by HCA_CAP.vport_group_manager (usually it is the PF/vport[0]), and its main responsibility is to forward each packet to the right vport. e-Switch needs to manage its own l2-table and FDB tables. L2 table is a flow table that is managed by FW, it is needed for Multi-host (Multi PF) configuration for inter HCA switching between PFs. FDB table is a flow table that is totally managed by e-Switch driver, its main responsibility is to switch packets between e-Swtich internal vports and uplink vport that belong to the same. This patch introduces only e-Swtich l2 table management, FDB managemnt will come later when ethernet SRIOV/VFs will be enabled. preperation for ethernet sriov and l2 table management. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 8 ++++++++ include/linux/mlx5/driver.h | 4 ++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0d2f0435a9f0..90a4cb6dc4cb 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -251,6 +251,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_REQUEST = 0xb, MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, + MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, }; enum { @@ -520,6 +521,12 @@ struct mlx5_eqe_page_fault { __be32 flags_qpn; } __packed; +struct mlx5_eqe_vport_change { + u8 rsvd0[2]; + __be16 vport_num; + __be32 rsvd1[6]; +} __packed; + union ev_data { __be32 raw[7]; struct mlx5_eqe_cmd cmd; @@ -532,6 +539,7 @@ union ev_data { struct mlx5_eqe_stall_vl stall_vl; struct mlx5_eqe_page_req req_pages; struct mlx5_eqe_page_fault page_fault; + struct mlx5_eqe_vport_change vport_change; } __packed; struct mlx5_eqe { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index efebb87163c8..ac098b6b97bf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -441,6 +441,8 @@ struct mlx5_irq_info { char name[MLX5_MAX_IRQ_NAME]; }; +struct mlx5_eswitch; + struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; @@ -496,6 +498,8 @@ struct mlx5_priv { struct list_head dev_list; struct list_head ctx_list; spinlock_t ctx_lock; + + struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; unsigned long pci_dev_data; }; -- cgit v1.2.3 From 495716b191f607b2cb2175f7499966daef79f663 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:19 +0200 Subject: net/mlx5: E-Switch, Introduce FDB hardware capabilities Define needed hardware structures and capabilities needed for E-Switch FDB flow tables and read them on driver load. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 15 +++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 13 +++++++++++++ 2 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 90a4cb6dc4cb..bce9caed1eed 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1138,6 +1138,7 @@ enum mlx5_cap_type { MLX5_CAP_IPOIB_OFFLOADS, MLX5_CAP_EOIB_OFFLOADS, MLX5_CAP_FLOW_TABLE, + MLX5_CAP_ESWITCH_FLOW_TABLE, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1175,6 +1176,20 @@ enum mlx5_cap_type { #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_nic_cap, mdev->hca_caps_max[MLX5_CAP_FLOW_TABLE], cap) +#define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ + MLX5_GET(flow_table_eswitch_cap, \ + mdev->hca_caps_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + +#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \ + MLX5_GET(flow_table_eswitch_cap, \ + mdev->hca_caps_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + +#define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap) + +#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \ + MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 39487d0c305d..ae7c08adba4a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -447,6 +447,18 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 reserved_3[0x7200]; }; +struct mlx5_ifc_flow_table_eswitch_cap_bits { + u8 reserved_0[0x200]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_ingress; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; + + u8 reserved_1[0x7800]; +}; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 csum_cap[0x1]; u8 vlan_cap[0x1]; @@ -1846,6 +1858,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_roce_cap_bits roce_cap; struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; + struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; u8 reserved_0[0x8000]; }; -- cgit v1.2.3 From 81848731ff4070a3e4136efa6a99d507177a53fe Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:20 +0200 Subject: net/mlx5: E-Switch, Add SR-IOV (FDB) support Enabling E-Switch SRIOV for nvfs+1 vports. Create E-Switch FDB for L2 UC/MC mac steering between VFs/PF and external vport (Uplink). FDB contains forwarding rules such as: UC MAC0 -> vport0(PF). UC MAC1 -> vport1. UC MAC2 -> vport2. MC MACX -> vport0, vport2, Uplink. MC MACY -> vport1, Uplink. For unmatched traffic FDB has the following default rules: Unmached Traffic (src vport != Uplink) -> Uplink. Unmached Traffic (src vport == Uplink) -> vport0(PF). FDB rules population: Each NIC vport (VF) will notify E-Switch manager of its UC/MC vport context changes via modify vport context command, which will be translated to an event that will be handled by E-Switch manager (PF) which will update FDB table accordingly. Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 6 ++++++ include/linux/mlx5/flow_table.h | 9 +++++++++ include/linux/mlx5/mlx5_ifc.h | 7 ++++--- 3 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bce9caed1eed..88eb4490a8b3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1074,6 +1074,12 @@ enum { VPORT_STATE_UP = 0x1, }; +enum { + MLX5_ESW_VPORT_ADMIN_STATE_DOWN = 0x0, + MLX5_ESW_VPORT_ADMIN_STATE_UP = 0x1, + MLX5_ESW_VPORT_ADMIN_STATE_AUTO = 0x2, +}; + enum { MLX5_L3_PROT_TYPE_IPV4 = 0, MLX5_L3_PROT_TYPE_IPV6 = 1, diff --git a/include/linux/mlx5/flow_table.h b/include/linux/mlx5/flow_table.h index 5f922c6d4fc2..0f2a15cf3317 100644 --- a/include/linux/mlx5/flow_table.h +++ b/include/linux/mlx5/flow_table.h @@ -41,6 +41,15 @@ struct mlx5_flow_table_group { u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; }; +struct mlx5_flow_destination { + enum mlx5_flow_destination_type type; + union { + u32 tir_num; + void *ft; + u32 vport_num; + }; +}; + void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, u16 num_groups, struct mlx5_flow_table_group *group); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ae7c08adba4a..a81b008738fd 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -827,9 +827,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_69[0x220]; }; -enum { - MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_FLOW_TABLE_ = 0x1, - MLX5_DEST_FORMAT_STRUCT_DESTINATION_TYPE_TIR = 0x2, +enum mlx5_flow_destination_type { + MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, + MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, }; struct mlx5_ifc_dest_format_struct_bits { -- cgit v1.2.3 From d6666753c6e85834f1669c7b831cc2b7fc9e4390 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 1 Dec 2015 18:03:22 +0200 Subject: net/mlx5: E-Switch, Introduce HCA cap and E-Switch vport context E-Switch vport context is unlike NIC vport context, managed by the E-Switch manager or vport_group_manager and not by the NIC(VF) driver. The E-Switch manager can access (read/modify) any of its vports E-Switch context. Currently E-Switch vport context includes only clietnt and server vlan insertion and striping data (for later support of VST mode). Signed-off-by: Saeed Mahameed Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 9 +++++ include/linux/mlx5/mlx5_ifc.h | 90 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 99 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 88eb4490a8b3..7d3a85faefb7 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1145,6 +1145,7 @@ enum mlx5_cap_type { MLX5_CAP_EOIB_OFFLOADS, MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, + MLX5_CAP_ESWITCH, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1196,6 +1197,14 @@ enum mlx5_cap_type { #define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap) +#define MLX5_CAP_ESW(mdev, cap) \ + MLX5_GET(e_switch_cap, \ + mdev->hca_caps_cur[MLX5_CAP_ESWITCH], cap) + +#define MLX5_CAP_ESW_MAX(mdev, cap) \ + MLX5_GET(e_switch_cap, \ + mdev->hca_caps_max[MLX5_CAP_ESWITCH], cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->hca_caps_cur[MLX5_CAP_ODP], cap) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index a81b008738fd..f5d94495758a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -459,6 +459,17 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 reserved_1[0x7800]; }; +struct mlx5_ifc_e_switch_cap_bits { + u8 vport_svlan_strip[0x1]; + u8 vport_cvlan_strip[0x1]; + u8 vport_svlan_insert[0x1]; + u8 vport_cvlan_insert_if_not_exist[0x1]; + u8 vport_cvlan_insert_overwrite[0x1]; + u8 reserved_0[0x1b]; + + u8 reserved_1[0x7e0]; +}; + struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 csum_cap[0x1]; u8 vlan_cap[0x1]; @@ -1860,6 +1871,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps; struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; + struct mlx5_ifc_e_switch_cap_bits e_switch_cap; u8 reserved_0[0x8000]; }; @@ -2305,6 +2317,26 @@ struct mlx5_ifc_hca_vport_context_bits { u8 reserved_6[0xca0]; }; +struct mlx5_ifc_esw_vport_context_bits { + u8 reserved_0[0x3]; + u8 vport_svlan_strip[0x1]; + u8 vport_cvlan_strip[0x1]; + u8 vport_svlan_insert[0x1]; + u8 vport_cvlan_insert[0x2]; + u8 reserved_1[0x18]; + + u8 reserved_2[0x20]; + + u8 svlan_cfi[0x1]; + u8 svlan_pcp[0x3]; + u8 svlan_id[0xc]; + u8 cvlan_cfi[0x1]; + u8 cvlan_pcp[0x3]; + u8 cvlan_id[0xc]; + + u8 reserved_3[0x7a0]; +}; + enum { MLX5_EQC_STATUS_OK = 0x0, MLX5_EQC_STATUS_EQ_WRITE_FAILURE = 0xa, @@ -3743,6 +3775,64 @@ struct mlx5_ifc_query_flow_group_in_bits { u8 reserved_5[0x120]; }; +struct mlx5_ifc_query_esw_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; + + struct mlx5_ifc_esw_vport_context_bits esw_vport_context; +}; + +struct mlx5_ifc_query_esw_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_modify_esw_vport_context_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_esw_vport_context_fields_select_bits { + u8 reserved[0x1c]; + u8 vport_cvlan_insert[0x1]; + u8 vport_svlan_insert[0x1]; + u8 vport_cvlan_strip[0x1]; + u8 vport_svlan_strip[0x1]; +}; + +struct mlx5_ifc_modify_esw_vport_context_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 other_vport[0x1]; + u8 reserved_2[0xf]; + u8 vport_number[0x10]; + + struct mlx5_ifc_esw_vport_context_fields_select_bits field_select; + + struct mlx5_ifc_esw_vport_context_bits esw_vport_context; +}; + struct mlx5_ifc_query_eq_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; -- cgit v1.2.3 From 2d1e0254ef8310e4f0756130a7ffc007ad1d58df Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 1 Dec 2015 14:55:21 +0000 Subject: pci_ids: add Netronome Systems vendor Add PCI vendor id for Netronome Systems. Signed-off-by: Jakub Kicinski Signed-off-by: Rolf Neugebauer Signed-off-by: David S. Miller --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d9ba49cedc5d..1acbefc4bbda 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2495,6 +2495,8 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF2 0x1700 #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff +#define PCI_VENDOR_ID_NETRONOME 0x19ee + #define PCI_VENDOR_ID_QMI 0x1a32 #define PCI_VENDOR_ID_AZWAVE 0x1a3b -- cgit v1.2.3 From 80a19e338d458abb5a700df3fd00795c51361f06 Mon Sep 17 00:00:00 2001 From: Asias He Date: Wed, 2 Dec 2015 14:44:00 +0800 Subject: VSOCK: Introduce virtio-vsock-common.ko This module contains the common code and header files for the following virtio-vsock and virtio-vhost kernel modules. Signed-off-by: Asias He Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 209 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 209 insertions(+) create mode 100644 include/linux/virtio_vsock.h (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h new file mode 100644 index 000000000000..a5f3ecc038f7 --- /dev/null +++ b/include/linux/virtio_vsock.h @@ -0,0 +1,209 @@ +/* + * 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 _LINUX_VIRTIO_VSOCK_H +#define _LINUX_VIRTIO_VSOCK_H + +#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) +#define VIRTIO_VSOCK_MAX_TX_BUF_SIZE (1024 * 1024 * 16) +#define VIRTIO_VSOCK_MAX_DGRAM_SIZE (1024 * 64) + +struct vsock_transport_recv_notify_data; +struct vsock_transport_send_notify_data; +struct sockaddr_vm; +struct vsock_sock; + +enum { + VSOCK_VQ_CTRL = 0, + VSOCK_VQ_RX = 1, /* for host to guest data */ + VSOCK_VQ_TX = 2, /* for guest to host data */ + VSOCK_VQ_MAX = 3, +}; + +/* virtio transport socket state */ +struct virtio_transport { + struct virtio_transport_pkt_ops *ops; + struct vsock_sock *vsk; + + u32 buf_size; + u32 buf_size_min; + u32 buf_size_max; + + struct mutex tx_lock; + struct mutex rx_lock; + + struct list_head rx_queue; + u32 rx_bytes; + + /* Protected by trans->tx_lock */ + u32 tx_cnt; + u32 buf_alloc; + u32 peer_fwd_cnt; + u32 peer_buf_alloc; + /* Protected by trans->rx_lock */ + u32 fwd_cnt; + + /* Protected by sk_lock */ + u16 dgram_id; + struct list_head incomplete_dgrams; /* dgram fragments */ +}; + +struct virtio_vsock_pkt { + struct virtio_vsock_hdr hdr; + struct virtio_transport *trans; + struct work_struct work; + struct list_head list; + void *buf; + u32 len; + u32 off; +}; + +struct virtio_vsock_pkt_info { + u32 remote_cid, remote_port; + struct msghdr *msg; + u32 pkt_len; + u16 type; + u16 op; + u32 flags; + u16 dgram_id; + u16 dgram_len; +}; + +struct virtio_transport_pkt_ops { + int (*send_pkt)(struct vsock_sock *vsk, + struct virtio_vsock_pkt_info *info); +}; + +void virtio_vsock_dumppkt(const char *func, + const struct virtio_vsock_pkt *pkt); + +struct sock * +virtio_transport_get_pending(struct sock *listener, + struct virtio_vsock_pkt *pkt); +struct virtio_vsock_pkt * +virtio_transport_alloc_pkt(struct vsock_sock *vsk, + struct virtio_vsock_pkt_info *info, + size_t len, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port); +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_pkt *pkt); +void virtio_transport_dec_tx_pkt(struct virtio_vsock_pkt *pkt); +u32 virtio_transport_get_credit(struct virtio_transport *trans, u32 wanted); +void virtio_transport_put_credit(struct virtio_transport *trans, u32 credit); +#endif /* _LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From b3e0b1b6d841a4b2f64fc09ea728913da8218424 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 16 Oct 2015 14:39:38 +0200 Subject: locking, sched: Introduce smp_cond_acquire() and use it Introduce smp_cond_acquire() which combines a control dependency and a read barrier to form acquire semantics. This primitive has two benefits: - it documents control dependencies, - its typically cheaper than using smp_load_acquire() in a loop. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..00b042c49ccd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -299,6 +299,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) +/** + * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering + * @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. + * + * 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) + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 7098c1eac75dc03fdbb7249171a6e68ce6044a5a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:30 +0100 Subject: sched/cputime: Clarify vtime symbols and document them VTIME_SLEEPING state happens either when: 1) The task is sleeping and no tickless delta is to be added on the task cputime stats. 2) The CPU isn't running vtime at all, so the same properties of 1) applies. Lets rename the vtime symbol to reflect both states. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f425aac63317..3533168fe7d1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1522,8 +1522,11 @@ struct task_struct { seqlock_t vtime_seqlock; unsigned long long vtime_snap; enum { - VTIME_SLEEPING = 0, + /* Task is sleeping or running in a CPU with VTIME inactive */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active */ VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active */ VTIME_SYS, } vtime_snap_whence; #endif -- cgit v1.2.3 From 55dbdcfa05533f44c9416070b8a9f6432b22314a Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:32 +0100 Subject: sched/cputime: Rename vtime_accounting_enabled() to vtime_accounting_cpu_enabled() vtime_accounting_enabled() checks if vtime is running on the current CPU and is as such a misnomer. Lets rename it to a function that reflect its locality. We are going to need the current name for a function that tells if vtime runs at all on some CPU. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-6-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/context_tracking.h | 4 ++-- include/linux/vtime.h | 14 +++++++------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 68b575afe5f5..d259274238db 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -86,7 +86,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -100,7 +100,7 @@ static inline void guest_exit(void) if (context_tracking_is_enabled()) __context_tracking_exit(CONTEXT_GUEST); - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/vtime.h b/include/linux/vtime.h index c5165fd256f9..ca23e8348f70 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -10,14 +10,14 @@ struct task_struct; /* - * vtime_accounting_enabled() definitions/declarations + * vtime_accounting_cpu_enabled() definitions/declarations */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } +static inline bool vtime_accounting_cpu_enabled(void) { return true; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static inline bool vtime_accounting_enabled(void) +static inline bool vtime_accounting_cpu_enabled(void) { if (context_tracking_is_enabled()) { if (context_tracking_cpu_is_enabled()) @@ -29,7 +29,7 @@ static inline bool vtime_accounting_enabled(void) #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #ifndef CONFIG_VIRT_CPU_ACCOUNTING -static inline bool vtime_accounting_enabled(void) { return false; } +static inline bool vtime_accounting_cpu_enabled(void) { return false; } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -44,7 +44,7 @@ extern void vtime_task_switch(struct task_struct *prev); extern void vtime_common_task_switch(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_task_switch(prev); } #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ @@ -59,7 +59,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk); 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_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_account_irq_enter(tsk); } #endif /* __ARCH_HAS_VTIME_ACCOUNT */ @@ -78,7 +78,7 @@ 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_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_gen_account_irq_exit(tsk); } -- cgit v1.2.3 From e592539466380279a9e6e6fdfe4545aa54f22593 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:33 +0100 Subject: sched/cputime: Introduce vtime accounting check for readers Readers need to know if vtime runs at all on some CPU somewhere, this is a fast-path check to determine if we need to check further the need to add up any tickless cputime delta. This fast path check uses context tracking state because vtime is tied to context tracking as of now. This check appears to be confusing though so lets use a vtime function that deals with context tracking details in vtime implementation instead. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-7-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/vtime.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vtime.h b/include/linux/vtime.h index ca23e8348f70..fa2196990f84 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -17,9 +17,20 @@ static inline bool vtime_accounting_cpu_enabled(void) { return true; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef 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. + * For now vtime state is tied to context tracking. We might want to decouple + * those later if necessary. + */ +static inline bool vtime_accounting_enabled(void) +{ + return context_tracking_is_enabled(); +} + static inline bool vtime_accounting_cpu_enabled(void) { - if (context_tracking_is_enabled()) { + if (vtime_accounting_enabled()) { if (context_tracking_cpu_is_enabled()) return true; } -- cgit v1.2.3 From b7ce2277f087fd052e7e1bbf432f7fecbee82bb6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 19 Nov 2015 16:47:34 +0100 Subject: sched/cputime: Convert vtime_seqlock to seqcount The cputime can only be updated by the current task itself, even in vtime case. So we can safely use seqcount instead of seqlock as there is no writer concurrency involved. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Cc: Chris Metcalf Cc: Christoph Lameter Cc: Hiroshi Shimamoto Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E . McKenney Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1447948054-28668-8-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 2 +- include/linux/sched.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1c1ff7e4faa4..f2cb8d45513d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -150,7 +150,7 @@ extern struct task_group root_task_group; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ .vtime_snap = 0, \ .vtime_snap_whence = VTIME_SYS, #else diff --git a/include/linux/sched.h b/include/linux/sched.h index 3533168fe7d1..3b0de68bce41 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1519,7 +1519,7 @@ struct task_struct { cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_t vtime_seqlock; + seqcount_t vtime_seqcount; unsigned long long vtime_snap; enum { /* Task is sleeping or running in a CPU with VTIME inactive */ -- cgit v1.2.3 From 991ce92f8de24cde063d531246602b6e14d3fef2 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 4 Dec 2015 10:38:59 -0200 Subject: [media] use https://linuxtv.org for LinuxTV URLs While https was always supported on linuxtv.org, only in Dec 3 2015 the website is using valid certificates. As we're planning to drop pure http support on some future, change all references at the media subsystem to point to the https URL instead. Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h index 73ea2fb04731..16c0ed6c50a7 100644 --- a/include/linux/videodev2.h +++ b/include/linux/videodev2.h @@ -46,7 +46,7 @@ * All kernel-specific stuff were moved to media/v4l2-dev.h, so * no #if __KERNEL tests are allowed here * - * See http://linuxtv.org for more info + * See https://linuxtv.org for more info * * Author: Bill Dirks * Justin Schoeman -- cgit v1.2.3 From 5a9be7c628c5273f84abacebf7faf2488376e0f0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 24 Nov 2015 15:44:06 -0800 Subject: rcu: Add rcu_normal kernel parameter to suppress expediting Although expedited grace periods can be quite useful, and although their OS jitter has been greatly reduced, they can still pose problems for extreme real-time workloads. This commit therefore adds a rcu_normal kernel boot parameter (which can also be manipulated via sysfs) to suppress expedited grace periods, that is, to treat requests for expedited grace periods as if they were requests for normal grace periods. If both rcu_expedited and rcu_normal are specified, rcu_normal wins. This means that if you are relying on expedited grace periods to speed up boot, you will want to specify rcu_expedited on the kernel command line, and then specify rcu_normal via sysfs once boot completes. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a0189ba67fde..98d9f30c02d4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -49,9 +49,14 @@ #include extern int rcu_expedited; /* for sysctl */ +extern int rcu_normal; /* also for sysctl */ #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ { return false; @@ -65,6 +70,7 @@ static inline void rcu_unexpedite_gp(void) { } #else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ void rcu_expedite_gp(void); void rcu_unexpedite_gp(void); -- cgit v1.2.3 From 46a5d164db53ba6066b11889abb7fa6bddbe5cf7 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 7 Oct 2015 09:10:48 -0700 Subject: rcu: Stop disabling interrupts in scheduler fastpaths We need the scheduler's fastpaths to be, well, fast, and unnecessarily disabling and re-enabling interrupts is not necessarily consistent with this goal. Especially given that there are regions of the scheduler that already have interrupts disabled. This commit therefore moves the call to rcu_note_context_switch() to one of the interrupts-disabled regions of the scheduler, and removes the now-redundant disabling and re-enabling of interrupts from rcu_note_context_switch() and the functions it calls. Reported-by: Peter Zijlstra Signed-off-by: Paul E. McKenney [ paulmck: Shift rcu_note_context_switch() to avoid deadlock, as suggested by Peter Zijlstra. ] --- include/linux/rcutree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 60d15a080d7c..9d3eda39bcd2 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,7 @@ void rcu_cpu_stall_reset(void); /* * Note a virtualization-based context switch. This is simply a * wrapper around rcu_note_context_switch(), which allows TINY_RCU - * to save a few bytes. + * to save a few bytes. The caller must have disabled interrupts. */ static inline void rcu_virt_note_context_switch(int cpu) { -- cgit v1.2.3 From 7d86dccf28a3ae2f790f399fc82d4c82521fd078 Mon Sep 17 00:00:00 2001 From: Petko Manolov Date: Mon, 12 Oct 2015 18:23:51 +0300 Subject: list: Introduces generic list_splice_tail_init_rcu() The list_splice_init_rcu() can be used as a stack onto which full lists are pushed, but queue-like behavior is now needed by some security policies. This requires a list_splice_tail_init_rcu(). This commit therefore supplies a list_splice_tail_init_rcu() by pulling code common it and to list_splice_init_rcu() into a new __list_splice_init_rcu() function. This new function is based on the existing list_splice_init_rcu() implementation. Signed-off-by: Petko Manolov Cc: Mimi Zohar Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 69 +++++++++++++++++++++++++++++++++++-------------- 1 file changed, 49 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 5ed540986019..e99d834545b6 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -179,32 +179,31 @@ static inline void list_replace_rcu(struct list_head *old, } /** - * list_splice_init_rcu - splice an RCU-protected list into an existing list. + * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice - * @head: the place in the list to splice the first list into + * @prev: points to the last element of the existing list + * @next: points to the first element of the existing list * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... * - * @head can be RCU-read traversed concurrently with this function. + * The list pointed to by @prev and @next can be RCU-read traversed + * concurrently with this function. * * Note that this function blocks. * - * Important note: the caller must take whatever action is necessary to - * prevent any other updates to @head. In principle, it is possible - * to modify the list as soon as sync() begins execution. - * If this sort of thing becomes necessary, an alternative version - * based on call_rcu() could be created. But only if -really- - * needed -- there is no shortage of RCU API members. + * Important note: the caller must take whatever action is necessary to prevent + * any other updates to the existing list. In principle, it is possible to + * modify the list as soon as sync() begins execution. If this sort of thing + * becomes necessary, an alternative version based on call_rcu() could be + * created. But only if -really- needed -- there is no shortage of RCU API + * members. */ -static inline void list_splice_init_rcu(struct list_head *list, - struct list_head *head, - void (*sync)(void)) +static inline void __list_splice_init_rcu(struct list_head *list, + struct list_head *prev, + struct list_head *next, + void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; - struct list_head *at = head->next; - - if (list_empty(list)) - return; /* * "first" and "last" tracking list, so initialize it. RCU readers @@ -231,10 +230,40 @@ static inline void list_splice_init_rcu(struct list_head *list, * this function. */ - last->next = at; - rcu_assign_pointer(list_next_rcu(head), first); - first->prev = head; - at->prev = last; + last->next = next; + rcu_assign_pointer(list_next_rcu(prev), first); + first->prev = prev; + next->prev = last; +} + +/** + * list_splice_init_rcu - splice an RCU-protected list into an existing list, + * designed for stacks. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head, head->next, sync); +} + +/** + * list_splice_tail_init_rcu - splice an RCU-protected list into an existing + * list, designed for queues. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_tail_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head->prev, head, sync); } /** -- cgit v1.2.3 From 2f073848c3cc8aff2655ab7c46d8c0de90cf4e50 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 12 Oct 2015 16:56:42 -0700 Subject: list: Use WRITE_ONCE() when initializing list_head structures Code that does lockless emptiness testing of non-RCU lists is relying on INIT_LIST_HEAD() to write the list head's ->next pointer atomically, particularly when INIT_LIST_HEAD() is invoked from list_del_init(). This commit therefore adds WRITE_ONCE() to this function's pointer stores that could affect the head's ->next pointer. Reported-by: Andrey Konovalov Signed-off-by: Paul E. McKenney --- include/linux/list.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 06c2d887a918..5356f4d661a7 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -24,7 +24,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { - list->next = list; + WRITE_ONCE(list->next, list); list->prev = list; } -- cgit v1.2.3 From 2f8364a291e8adde25c93f97a76abbcaf4b1ed3f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 3 Dec 2015 21:12:31 +0100 Subject: WAN: HDLC: Call notifiers before and after changing device type An HDLC device can change type when the protocol driver is changed. Calling the notifier change allows potential users of the interface know about this planned change, and even block it. After the change has occurred, send a second notification to users can evaluate the new device type etc. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/hdlc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index 1acb1445e05f..e31bcd4c7859 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -101,7 +101,7 @@ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev); int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, size_t size); /* May be used by hardware driver to gain control over HDLC device */ -void detach_hdlc_protocol(struct net_device *dev); +int detach_hdlc_protocol(struct net_device *dev); static __inline__ __be16 hdlc_type_trans(struct sk_buff *skb, struct net_device *dev) -- cgit v1.2.3 From b618aaa91b5870e7bd139987ac4b7bf0851142d0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 4 Dec 2015 15:01:31 +0100 Subject: net: constify netif_is_* helpers net_device param As suggested by Eric, these helpers should have const dev param. Suggested-by: Eric Dumazet Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- include/linux/netdevice.h | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 67ce5bd3b56a..05f5879821b8 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); -static inline bool is_vlan_dev(struct net_device *dev) +static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3efe017fe419..1bb21ff0fa64 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3661,7 +3661,7 @@ extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN]; void netdev_rss_key_fill(void *buffer, size_t len); int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(struct net_device *dev)); + bool (*type_check)(const struct net_device *dev)); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); @@ -3858,32 +3858,32 @@ static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, skb->mac_len = mac_len; } -static inline bool netif_is_macvlan(struct net_device *dev) +static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; } -static inline bool netif_is_macvlan_port(struct net_device *dev) +static inline bool netif_is_macvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN_PORT; } -static inline bool netif_is_ipvlan(struct net_device *dev) +static inline bool netif_is_ipvlan(const struct net_device *dev) { return dev->priv_flags & IFF_IPVLAN_SLAVE; } -static inline bool netif_is_ipvlan_port(struct net_device *dev) +static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_IPVLAN_MASTER; } -static inline bool netif_is_bond_master(struct net_device *dev) +static inline bool netif_is_bond_master(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; } -static inline bool netif_is_bond_slave(struct net_device *dev) +static inline bool netif_is_bond_slave(const struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } @@ -3918,22 +3918,22 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_is_team_master(struct net_device *dev) +static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; } -static inline bool netif_is_team_port(struct net_device *dev) +static inline bool netif_is_team_port(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM_PORT; } -static inline bool netif_is_lag_master(struct net_device *dev) +static inline bool netif_is_lag_master(const struct net_device *dev) { return netif_is_bond_master(dev) || netif_is_team_master(dev); } -static inline bool netif_is_lag_port(struct net_device *dev) +static inline bool netif_is_lag_port(const struct net_device *dev) { return netif_is_bond_slave(dev) || netif_is_team_port(dev); } -- cgit v1.2.3 From 8dd3303001976aa8583bf20f6b93590c74114308 Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Fri, 4 Dec 2015 14:07:05 +0100 Subject: x86/mm: Introduce max_possible_pfn max_possible_pfn will be used for tracking max possible PFN for memory that isn't present in E820 table and could be hotplugged later. By default max_possible_pfn is initialized with max_pfn, but later it could be updated with highest PFN of hotpluggable memory ranges declared in ACPI SRAT table if any present. Signed-off-by: Igor Mammedov Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akataria@vmware.com Cc: fujita.tomonori@lab.ntt.co.jp Cc: konrad.wilk@oracle.com Cc: pbonzini@redhat.com Cc: revers@redhat.com Cc: riel@redhat.com Link: http://lkml.kernel.org/r/1449234426-273049-2-git-send-email-imammedo@redhat.com Signed-off-by: Ingo Molnar --- include/linux/bootmem.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index f589222bfa87..35b22f94d2d2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -19,6 +19,10 @@ extern unsigned long min_low_pfn; * highest page */ extern unsigned long max_pfn; +/* + * highest possible page + */ +extern unsigned long long max_possible_pfn; #ifndef CONFIG_NO_BOOTMEM /* -- cgit v1.2.3 From bd2a634d9e852b9b6100f9ae9c3c790b0ff91ce0 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 1 Dec 2015 17:00:58 -0800 Subject: tracepoints: Move struct tracepoint to new tracepoint-defs.h header Steven recommended open coding access to tracepoint->key to add trace points to headers. Unfortunately this is difficult for some headers (such as x86 asm/msr.h) because including tracepoint.h includes so many other headers that it causes include loops. The main problem is the include of linux/rcupdate.h, which pulls in a lot of other headers. The rcu header is only needed when actually defining trace points. Move the struct tracepoint into a separate tracepoint-defs.h header that can be included without pulling in all of RCU. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1449018060-1742-2-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- include/linux/tracepoint-defs.h | 27 +++++++++++++++++++++++++++ include/linux/tracepoint.h | 16 +--------------- 2 files changed, 28 insertions(+), 15 deletions(-) create mode 100644 include/linux/tracepoint-defs.h (limited to 'include/linux') diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h new file mode 100644 index 000000000000..e1ee97c713bf --- /dev/null +++ b/include/linux/tracepoint-defs.h @@ -0,0 +1,27 @@ +#ifndef TRACEPOINT_DEFS_H +#define TRACEPOINT_DEFS_H 1 + +/* + * File can be included directly by headers who only want to access + * tracepoint->key to guard out of line trace calls. Otherwise + * linux/tracepoint.h should be used. + */ + +#include +#include + +struct tracepoint_func { + void *func; + void *data; + int prio; +}; + +struct tracepoint { + const char *name; /* Tracepoint name */ + struct static_key key; + void (*regfunc)(void); + void (*unregfunc)(void); + struct tracepoint_func __rcu *funcs; +}; + +#endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..f7c732bd5cbd 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,26 +17,12 @@ #include #include #include -#include +#include struct module; struct tracepoint; struct notifier_block; -struct tracepoint_func { - void *func; - void *data; - int prio; -}; - -struct tracepoint { - const char *name; /* Tracepoint name */ - struct static_key key; - void (*regfunc)(void); - void (*unregfunc)(void); - struct tracepoint_func __rcu *funcs; -}; - struct trace_enum_map { const char *system; const char *enum_string; -- cgit v1.2.3 From fae9e2e07af07baabb8c26a31b3f7d8fdf89809e Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 18 Apr 2014 22:10:32 +0100 Subject: component: remove old add_components method Now that drivers create an array of component matches at probe time, we can retire the old methods. This involves removing the add_components master method, and removing component_master_add_child() from public view. We also remove component_add_master() as that interface is no longer useful. Acked-by: Andrew Lunn Signed-off-by: Russell King --- include/linux/component.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/component.h b/include/linux/component.h index c00dcc302611..71c434a6a5ee 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -17,18 +17,13 @@ void component_unbind_all(struct device *, void *); struct master; struct component_master_ops { - int (*add_components)(struct device *, struct master *); int (*bind)(struct device *); void (*unbind)(struct device *); }; -int component_master_add(struct device *, const struct component_master_ops *); void component_master_del(struct device *, const struct component_master_ops *); -int component_master_add_child(struct master *master, - int (*compare)(struct device *, void *), void *compare_data); - struct component_match; int component_master_add_with_match(struct device *, -- cgit v1.2.3 From ce657b1cddf1f88c56ae683efa7130341c92808b Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 17 Nov 2015 12:08:01 +0000 Subject: component: add support for releasing match data The component helper treats the void match data pointer as an opaque object which needs no further management. When device nodes being passed, this is not true: the caller should pass its refcount to the component helper, and there should be a way to drop the refcount when the matching information is destroyed. This patch provides a per-match release method in addition to the match method to solve this issue. Rather than using component_match_add(), users should use component_match_add_release() which takes an additional function pointer for releasing this reference. Signed-off-by: Russell King --- include/linux/component.h | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/component.h b/include/linux/component.h index 71c434a6a5ee..a559eebc0e0f 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -1,24 +1,28 @@ #ifndef COMPONENT_H #define COMPONENT_H +#include + struct device; struct component_ops { - int (*bind)(struct device *, struct device *, void *); - void (*unbind)(struct device *, struct device *, void *); + int (*bind)(struct device *comp, struct device *master, + void *master_data); + void (*unbind)(struct device *comp, struct device *master, + void *master_data); }; int component_add(struct device *, const struct component_ops *); void component_del(struct device *, const struct component_ops *); -int component_bind_all(struct device *, void *); -void component_unbind_all(struct device *, void *); +int component_bind_all(struct device *master, void *master_data); +void component_unbind_all(struct device *master, void *master_data); struct master; struct component_master_ops { - int (*bind)(struct device *); - void (*unbind)(struct device *); + int (*bind)(struct device *master); + void (*unbind)(struct device *master); }; void component_master_del(struct device *, @@ -28,7 +32,17 @@ struct component_match; int component_master_add_with_match(struct device *, const struct component_master_ops *, struct component_match *); -void component_match_add(struct device *, struct component_match **, +void component_match_add_release(struct device *master, + struct component_match **matchptr, + void (*release)(struct device *, void *), int (*compare)(struct device *, void *), void *compare_data); +static inline void component_match_add(struct device *master, + struct component_match **matchptr, + int (*compare)(struct device *, void *), void *compare_data) +{ + component_match_add_release(master, matchptr, NULL, compare, + compare_data); +} + #endif -- cgit v1.2.3 From 318a1971826103ecf560875b17236dd4a93e8c88 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Nov 2015 17:11:31 +0200 Subject: device property: refactor built-in properties support Instead of using the type and nval fields we will use length (in bytes) of the value. The sanity check is done in the accessors. The built-in property accessors are split in the same way such as device tree. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 0a3705a7c9f2..c29460a0e521 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -144,14 +144,12 @@ static inline int fwnode_property_read_u64(struct fwnode_handle *fwnode, /** * struct property_entry - "Built-in" device property representation. * @name: Name of the property. - * @type: Type of the property. - * @nval: Number of items of type @type making up the value. - * @value: Value of the property (an array of @nval items of type @type). + * @length: Length of data making up the value. + * @value: Value of the property (an array of items of the given type). */ struct property_entry { const char *name; - enum dev_prop_type type; - size_t nval; + size_t length; union { void *raw_data; u8 *u8_data; -- cgit v1.2.3 From 66586baba56679baa2da1a10a96ccf15b1e96b95 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Nov 2015 17:11:32 +0200 Subject: device property: keep single value inplace We may save a lot of lines of code and space by keeping single values inside the struct property_entry. Refactor the implementation to do so. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index c29460a0e521..69a8a0817fd3 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -145,19 +145,34 @@ static inline int fwnode_property_read_u64(struct fwnode_handle *fwnode, * struct property_entry - "Built-in" device property representation. * @name: Name of the property. * @length: Length of data making up the value. - * @value: Value of the property (an array of items of the given type). + * @is_array: True when the property is an array. + * @is_string: True when property is a string. + * @pointer: Pointer to the property (an array of items of the given type). + * @value: Value of the property (when it is a single item of the given type). */ struct property_entry { const char *name; size_t length; + bool is_array; + bool is_string; union { - void *raw_data; - u8 *u8_data; - u16 *u16_data; - u32 *u32_data; - u64 *u64_data; - const char **str; - } value; + union { + void *raw_data; + u8 *u8_data; + u16 *u16_data; + u32 *u32_data; + u64 *u64_data; + const char **str; + } pointer; + union { + unsigned long long raw_data; + u8 u8_data; + u16 u16_data; + u32 u32_data; + u64 u64_data; + const char *str; + } value; + }; }; /** -- cgit v1.2.3 From a85f420475334caed12b057ddcaa0b58e0b1ebb7 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 30 Nov 2015 17:11:33 +0200 Subject: device property: helper macros for property entry creation Marcos for easier creation of build-in property entries. Signed-off-by: Heikki Krogerus Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 69a8a0817fd3..e4f29d8b9ceb 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -175,6 +175,61 @@ struct property_entry { }; }; +#define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_) \ +{ \ + .name = _name_, \ + .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ + .is_array = true, \ + .pointer._type_##_data = _val_, \ +} + +#define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u8, _val_) +#define PROPERTY_ENTRY_U16_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u16, _val_) +#define PROPERTY_ENTRY_U32_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u32, _val_) +#define PROPERTY_ENTRY_U64_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER_ARRAY(_name_, u64, _val_) + +#define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ +{ \ + .name = _name_, \ + .length = ARRAY_SIZE(_val_) * sizeof(const char *), \ + .is_array = true, \ + .is_string = true, \ + .pointer.str = _val_, \ +} + +#define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_) \ +{ \ + .name = _name_, \ + .length = sizeof(_type_), \ + .value._type_##_data = _val_, \ +} + +#define PROPERTY_ENTRY_U8(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER(_name_, u8, _val_) +#define PROPERTY_ENTRY_U16(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER(_name_, u16, _val_) +#define PROPERTY_ENTRY_U32(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER(_name_, u32, _val_) +#define PROPERTY_ENTRY_U64(_name_, _val_) \ + PROPERTY_ENTRY_INTEGER(_name_, u64, _val_) + +#define PROPERTY_ENTRY_STRING(_name_, _val_) \ +{ \ + .name = _name_, \ + .length = sizeof(_val_), \ + .is_string = true, \ + .value.str = _val_, \ +} + +#define PROPERTY_ENTRY_BOOL(_name_) \ +{ \ + .name = _name_, \ +} + /** * struct property_set - Collection of "built-in" device properties. * @fwnode: Handle to be pointed to by the fwnode field of struct device. -- cgit v1.2.3 From 1d656fb757c17e48a8a01bd576d14918701ba55c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Nov 2015 17:11:34 +0200 Subject: device property: improve readability of macros There is no functional change. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index e4f29d8b9ceb..d1cf2084c648 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -73,8 +73,8 @@ int fwnode_property_match_string(struct fwnode_handle *fwnode, struct fwnode_handle *device_get_next_child_node(struct device *dev, struct fwnode_handle *child); -#define device_for_each_child_node(dev, child) \ - for (child = device_get_next_child_node(dev, NULL); child; \ +#define device_for_each_child_node(dev, child) \ + for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) void fwnode_handle_put(struct fwnode_handle *fwnode); -- cgit v1.2.3 From 13141e1cb842ad6286c1cfa9a6b7c1577478d03b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 30 Nov 2015 17:11:37 +0200 Subject: device property: Take a copy of the property set It is convenient if the property set associated with the device secondary firmware node is a copy of the original. This allows passing property set from a stack for example for devices created dynamically. This also ties the property set lifetime to the associated device. Because of that we provide new function device_remove_property_set() that is used to disassociate and release memory allocated for the property set. Signed-off-by: Mika Westerberg Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index d1cf2084c648..3a8c7d7773e6 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -240,7 +240,8 @@ struct property_set { struct property_entry *properties; }; -void device_add_property_set(struct device *dev, struct property_set *pset); +int device_add_property_set(struct device *dev, const struct property_set *pset); +void device_remove_property_set(struct device *dev); bool device_dma_supported(struct device *dev); -- cgit v1.2.3 From 00bbc1d8e46a92ce7bd80622cf4b09c3b727a741 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 30 Nov 2015 17:11:38 +0200 Subject: driver core: platform: Add support for built-in device properties Make it possible to pass built-in device properties to platform device drivers. This is useful if the system does not have any firmware interface like Device Tree or ACPI which provides these. Properties associated with the platform device will be automatically released when the corresponding device is removed. Suggested-by: Arnd Bergmann Signed-off-by: Mika Westerberg Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/platform_device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index dc777be5f2e1..dba40b1c41dc 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -18,6 +18,7 @@ #define PLATFORM_DEVID_AUTO (-2) struct mfd_cell; +struct property_set; struct platform_device { const char *name; @@ -70,6 +71,8 @@ struct platform_device_info { const void *data; size_t size_data; u64 dma_mask; + + const struct property_set *pset; }; extern struct platform_device *platform_device_register_full( const struct platform_device_info *pdevinfo); @@ -167,6 +170,8 @@ extern int platform_device_add_resources(struct platform_device *pdev, unsigned int num); extern int platform_device_add_data(struct platform_device *pdev, const void *data, size_t size); +extern int platform_device_add_properties(struct platform_device *pdev, + const struct property_set *pset); extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); -- cgit v1.2.3 From 4d215cabc784990df11fbcca7af70adf53c9ff17 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 30 Nov 2015 17:11:40 +0200 Subject: mfd: core: propagate device properties to sub devices drivers In the similar way like we do for the platform data we propagate the device properties. For example, in case of Intel LPSS drivers we may provide a specific property to tell the actual device driver an additional information such as platform name. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/mfd/core.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 27dac3ff18b9..bc6f7e00fb3d 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -17,6 +17,7 @@ #include struct irq_domain; +struct property_set; /* Matches ACPI PNP id, either _HID or _CID, or ACPI _ADR */ struct mfd_cell_acpi_match { @@ -44,6 +45,10 @@ struct mfd_cell { /* platform data passed to the sub devices drivers */ void *platform_data; size_t pdata_size; + + /* device properties passed to the sub devices drivers */ + const struct property_set *pset; + /* * Device Tree compatible string * See: Documentation/devicetree/usage-model.txt Chapter 2.2 for details -- cgit v1.2.3 From 36f7a8a4cd2e99b7172ab8ed2130c5c841466824 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 6 Dec 2015 16:49:22 -0500 Subject: iov_iter: constify {csum_and_,}copy_to_iter() Signed-off-by: Al Viro --- include/linux/uio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 8b01e1c3c614..fd9bcfedad42 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -82,7 +82,7 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); -size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i); +size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -145,7 +145,7 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } -size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); int import_iovec(int type, const struct iovec __user * uvector, -- cgit v1.2.3 From 3e004eea56b4f2cb6768ebe9000c830eda0c71b1 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Tue, 17 Nov 2015 14:40:09 +0800 Subject: fs/block_dev.c: make sb_is_blkdev_sb return bool when CONFIG_BLOCK undefined Currently when CONFIG_BLOCK is defined sb_is_blkdev_sb returns bool, while when CONFIG_BLOCK is not defined it returns int. Let's keep consistent to make sb_is_blkdev_sb return bool as well when CONFIG_BLOCK isn't defined. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..11505af0d358 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2291,9 +2291,9 @@ static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void { } -static inline int sb_is_blkdev_sb(struct super_block *sb) +static inline bool sb_is_blkdev_sb(struct super_block *sb) { - return 0; + return false; } #endif extern int sync_filesystem(struct super_block *); -- cgit v1.2.3 From 25ab4c9b1ccb64b1433cecd3f19f28fe300c1576 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Tue, 17 Nov 2015 14:40:10 +0800 Subject: fs/namespace.c: path_is_under can be boolean This patch makes path_is_under return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 11505af0d358..aab8094656e4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2533,7 +2533,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern int is_subdir(struct dentry *, struct dentry *); -extern int path_is_under(struct path *, struct path *); +extern bool path_is_under(struct path *, struct path *); extern char *file_path(struct file *, char *, int); -- cgit v1.2.3 From a6e5787fc8fc9c88290a7bceed07aa4d14029fa7 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Tue, 17 Nov 2015 14:40:11 +0800 Subject: fs/dcache.c: is_subdir can be boolean This patch makes is_subdir return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index aab8094656e4..4b23def18aa9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2532,7 +2532,7 @@ extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -extern int is_subdir(struct dentry *, struct dentry *); +extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(struct path *, struct path *); extern char *file_path(struct file *, char *, int); -- cgit v1.2.3 From 0e3ef1fe453c9f29c30d040cd2559c5cac724e93 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 19 Nov 2015 21:00:11 +0800 Subject: fs/bad_inode.c: is_bad_inode can be boolean This patch makes is_bad_inode return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4b23def18aa9..6b33ac447612 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2371,7 +2371,7 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); -extern int is_bad_inode(struct inode *); +extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK /* -- cgit v1.2.3 From d37177bacdf7cbcdb23a513cbb475fa241f8083c Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 19 Nov 2015 21:00:12 +0800 Subject: fs/attr.c: is_sxid can be boolean This patch makes is_sxid return bool to improve readability due to this particular function only using either one or zero as its return value. No functional change. Signed-off-by: Yaowei Bai Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6b33ac447612..bd1447661e3c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2963,7 +2963,7 @@ int __init get_filesystem_list(char *buf); #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) -static inline int is_sxid(umode_t mode) +static inline bool is_sxid(umode_t mode) { return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP)); } -- cgit v1.2.3 From 80602324d5a02fea97ed1328ba04e5d7f10aaff8 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:33 +0100 Subject: vfs: Remove vfs_xattr_cmp This function was only briefly used in security/integrity/evm, between commits 66dbc325 and 15647eb3. Signed-off-by: Andreas Gruenbacher Reviewed-by: James Morris Signed-off-by: Al Viro --- include/linux/xattr.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 89474b9d260c..45fa3456a0cc 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -53,8 +53,6 @@ int generic_setxattr(struct dentry *dentry, const char *name, const void *value, int generic_removexattr(struct dentry *dentry, const char *name); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags); struct simple_xattrs { struct list_head head; -- cgit v1.2.3 From 97d79299223baab330b194437e676d301f12d5f6 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:35 +0100 Subject: posix acls: Remove duplicate xattr name definitions Remove POSIX_ACL_XATTR_{ACCESS,DEFAULT} and GFS2_POSIX_ACL_{ACCESS,DEFAULT} and replace them with the definitions in . Signed-off-by: Andreas Gruenbacher Reviewed-by: James Morris Signed-off-by: Al Viro --- include/linux/posix_acl_xattr.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 6f14ee295822..e5e8ec40278d 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -9,16 +9,12 @@ #ifndef _POSIX_ACL_XATTR_H #define _POSIX_ACL_XATTR_H +#include #include -/* Extended attribute names */ -#define POSIX_ACL_XATTR_ACCESS "system.posix_acl_access" -#define POSIX_ACL_XATTR_DEFAULT "system.posix_acl_default" - /* Supported ACL a_version fields */ #define POSIX_ACL_XATTR_VERSION 0x0002 - /* An undefined entry e_id value */ #define ACL_UNDEFINED_ID (-1) -- cgit v1.2.3 From 98e9cb5711c68223f0e4d5201b9a6add255ec550 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:36 +0100 Subject: vfs: Distinguish between full xattr names and proper prefixes Add an additional "name" field to struct xattr_handler. When the name is set, the handler matches attributes with exactly that name. When the prefix is set instead, the handler matches attributes with the given prefix and with a non-empty suffix. This patch should avoid bugs like the one fixed in commit c361016a in the future. Signed-off-by: Andreas Gruenbacher Reviewed-by: James Morris Signed-off-by: Al Viro --- include/linux/xattr.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 45fa3456a0cc..03c847fb6cc1 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -19,7 +19,13 @@ struct inode; struct dentry; +/* + * struct xattr_handler: When @name is set, match attributes with exactly that + * name. When @prefix is set instead, match attributes with that prefix and + * with a non-empty suffix. + */ struct xattr_handler { + const char *name; const char *prefix; int flags; /* fs private flags */ size_t (*list)(const struct xattr_handler *, struct dentry *dentry, @@ -54,6 +60,11 @@ int generic_removexattr(struct dentry *dentry, const char *name); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); +static inline const char *xattr_prefix(const struct xattr_handler *handler) +{ + return handler->prefix ?: handler->name; +} + struct simple_xattrs { struct list_head head; spinlock_t lock; -- cgit v1.2.3 From aa7c5241c380adb7e6913549292c1b83c1469bda Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:38 +0100 Subject: tmpfs: Use xattr handler infrastructure Use the VFS xattr handler infrastructure and get rid of similar code in the filesystem. For implementing shmem_xattr_handler_set, we need a version of simple_xattr_set which removes the attribute when value is NULL. Use this to implement kernfs_iop_removexattr as well. Signed-off-by: Andreas Gruenbacher Reviewed-by: James Morris Cc: Hugh Dickins Cc: linux-mm@kvack.org Signed-off-by: Al Viro --- include/linux/xattr.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 03c847fb6cc1..4dd40cb2c07b 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -104,9 +104,7 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name); -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, - size_t size); +ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); -- cgit v1.2.3 From 786534b92f3ce68f4afc8a761c80b76887797b0a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:39 +0100 Subject: tmpfs: listxattr should include POSIX ACL xattrs When a file on tmpfs has an ACL or a Default ACL, listxattr should include the corresponding xattr name. Signed-off-by: Andreas Gruenbacher Reviewed-by: James Morris Cc: Hugh Dickins Cc: linux-mm@kvack.org Signed-off-by: Al Viro --- include/linux/xattr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 4dd40cb2c07b..d23ce8e9af6f 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -104,7 +104,8 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, size_t size); +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, + size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); -- cgit v1.2.3 From 5f61385d2ebc2bd62bc389c7da0d8d2f263be1eb Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Sun, 6 Dec 2015 18:07:41 +0200 Subject: net/mlx4_core: Keep VLAN/MAC tables mirrored in multifunc HA mode Due to HW limitations, indexes to MAC and VLAN tables are always taken from the table of the actual port. So, if a resource holds an index to a table, it may refer to different values during the lifetime of the resource, unless the tables are mirrored. Also, even when driver is not in HA mode the policy of allocating an index to these tables is such to make sure, as much as possible, that when the time comes the mirroring will be successful. This means that in multifunction mode the allocation of a free index in a port's table tries to make sure that the same index in the other's port table is also free. Signed-off-by: Moni Shoua Reviewed-by: Jack Morgenstein Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- include/linux/mlx4/driver.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 5a06d969338e..2e8af001c5da 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -75,6 +75,11 @@ static inline int mlx4_is_bonded(struct mlx4_dev *dev) return !!(dev->flags & MLX4_FLAG_BONDED); } +static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev) +{ + return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev)); +} + struct mlx4_port_map { u8 port1; u8 port2; -- cgit v1.2.3 From ea3793ee29d3621faf857fa8ef5425e9ff9a756d Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Sun, 6 Dec 2015 21:11:34 +0000 Subject: core: enable more fine-grained datagram reception control The __skb_recv_datagram routine in core/ datagram.c provides a general skb reception factility supposed to be utilized by protocol modules providing datagram sockets. It encompasses both the actual recvmsg code and a surrounding 'sleep until data is available' loop. This is inconvenient if a protocol module has to use additional locking in order to maintain some per-socket state the generic datagram socket code is unaware of (as the af_unix code does). The patch below moves the recvmsg proper code into a new __skb_try_recv_datagram routine which doesn't sleep and renames wait_for_more_packets to __skb_wait_for_more_packets, both routines being exported interfaces. The original __skb_recv_datagram routine is reimplemented on top of these two functions such that its user-visible behaviour remains unchanged. Signed-off-by: Rainer Weikusat Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9c394bf0771..9b9b9ead7bb3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2785,6 +2785,12 @@ static inline void skb_frag_list_init(struct sk_buff *skb) #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) + +int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, + const struct sk_buff *skb); +struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, + int *peeked, int *off, int *err, + struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, int *peeked, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, -- cgit v1.2.3 From 79cfea0273876d9c438f3227b8f68c8c7ae31583 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 7 Dec 2015 13:09:52 -0800 Subject: rcu: Remove TINY_RCU bloat from pointless boot parameters The rcu_expedited, rcu_normal, and rcu_normal_after_boot kernel boot parameters are pointless in the case of TINY_RCU because in that case synchronous grace periods, both expedited and normal, are no-ops. However, these three symbols contribute several hundred bytes of bloat. This commit therefore uses CPP directives to avoid compiling this code in TINY_RCU kernels. Reported-by: kbuild test robot Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- include/linux/rcupdate.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 98d9f30c02d4..47e95b80bebd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,8 +48,10 @@ #include +#ifndef CONFIG_TINY_RCU extern int rcu_expedited; /* for sysctl */ extern int rcu_normal; /* also for sysctl */ +#endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ @@ -327,7 +329,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -void rcu_end_inkernel_boot(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); @@ -335,6 +336,12 @@ struct notifier_block; int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); +#ifndef CONFIG_TINY_RCU +void rcu_end_inkernel_boot(void); +#else /* #ifndef CONFIG_TINY_RCU */ +static inline void rcu_end_inkernel_boot(void) { } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); -- cgit v1.2.3 From 7c9906ca5e582a773fff696975e312cef58a7386 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 31 Oct 2015 00:59:01 -0700 Subject: rcu: Don't redundantly disable irqs in rcu_irq_{enter,exit}() This commit replaces a local_irq_save()/local_irq_restore() pair with a lockdep assertion that interrupts are already disabled. This should remove the corresponding overhead from the interrupt entry/exit fastpaths. This change was inspired by the fact that Iftekhar Ahmed's mutation testing showed that removing rcu_irq_enter()'s call to local_ird_restore() had no effect, which might indicate that interrupts were always enabled anyway. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 4 ++-- include/linux/rcutiny.h | 8 ++++++++ include/linux/rcutree.h | 2 ++ include/linux/tracepoint.h | 4 ++-- 4 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a0189ba67fde..f2b667df1131 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -379,9 +379,9 @@ static inline void rcu_init_nohz(void) */ #define RCU_NONIDLE(a) \ do { \ - rcu_irq_enter(); \ + rcu_irq_enter_irqson(); \ do { a; } while (0); \ - rcu_irq_exit(); \ + rcu_irq_exit_irqson(); \ } while (0) /* diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 4c1aaf9cce7b..64809aea661c 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -181,6 +181,14 @@ static inline void rcu_irq_enter(void) { } +static inline void rcu_irq_exit_irqson(void) +{ +} + +static inline void rcu_irq_enter_irqson(void) +{ +} + static inline void rcu_irq_exit(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 9d3eda39bcd2..ad1eda9fa4da 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -97,6 +97,8 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_enter_irqson(void); +void rcu_irq_exit_irqson(void); void exit_rcu(void); diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..7834a8a8bf1e 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -171,8 +171,8 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), \ - rcu_irq_enter(), \ - rcu_irq_exit()); \ + rcu_irq_enter_irqson(), \ + rcu_irq_exit_irqson()); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) -- cgit v1.2.3 From f039f0af081746933d5dec3229637a18fab791ed Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 2 Nov 2015 13:21:47 +1100 Subject: rcu: Fix comment for rcu_dereference_raw_notrace rcu_dereference_raw() calls indirectly rcu_read_lock_held() while rcu_dereference_raw_notrace() does not so fix the comment about the latter. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f2b667df1131..85aabcd8b564 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -741,7 +741,7 @@ static inline void rcu_preempt_sleep_check(void) * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * - * The tracing version of rcu_dereference_raw() must not call + * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) -- cgit v1.2.3 From 69b907297f4edf13182e3fa3adc0160df077746c Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Sat, 5 Dec 2015 18:14:19 -0800 Subject: list: Add lockless list traversal primitives Although list_for_each_entry_rcu() can in theory be used anywhere preemption is disabled, it can result in calls to lockdep, which cannot be used in certain constrained execution environments, such as exception handlers that do not map the entire kernel into their address spaces. This commit therefore adds list_entry_lockless() and list_for_each_entry_lockless(), which never invoke lockdep and can therefore safely be used from these constrained environments, but only as long as those environments are non-preemptible (or items are never deleted from the list). Use synchronize_sched(), call_rcu_sched(), or synchronize_sched_expedited() in updates for the needed grace periods. Of course, if items are never deleted from the list, there is no need to wait for grace periods. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 5ed540986019..1fad79861e14 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -304,6 +304,42 @@ static inline void list_splice_init_rcu(struct list_head *list, &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) +/** + * list_entry_lockless - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_entry_lockless(ptr, type, member) \ + container_of((typeof(ptr))lockless_dereference(ptr), type, member) + +/** + * list_for_each_entry_lockless - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_for_each_entry_lockless(pos, head, member) \ + for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) + /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. -- cgit v1.2.3 From acc15575e78e534c12549d8057a692f490a50f61 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2015 12:59:49 +0100 Subject: locks: new locks_mandatory_area calling convention Pass a loff_t end for the last byte instead of the 32-bit count parameter to allow full file clones even on 32-bit architectures. While we're at it also simplify the read/write selection. Signed-off-by: Christoph Hellwig Acked-by: J. Bruce Fields Signed-off-by: Al Viro --- include/linux/fs.h | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e8a736242b1a..4377b2df991d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2030,12 +2030,9 @@ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) -#define FLOCK_VERIFY_READ 1 -#define FLOCK_VERIFY_WRITE 2 - #ifdef CONFIG_FILE_LOCKING extern int locks_mandatory_locked(struct file *); -extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t); +extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); /* * Candidates for mandatory locking have the setgid bit set @@ -2065,17 +2062,19 @@ static inline int locks_verify_locked(struct file *file) } static inline int locks_verify_truncate(struct inode *inode, - struct file *filp, + struct file *f, loff_t size) { - if (inode->i_flctx && mandatory_lock(inode)) - return locks_mandatory_area( - FLOCK_VERIFY_WRITE, inode, filp, - size < inode->i_size ? size : inode->i_size, - (size < inode->i_size ? inode->i_size - size - : size - inode->i_size) - ); - return 0; + if (!inode->i_flctx || !mandatory_lock(inode)) + return 0; + + if (size < inode->i_size) { + return locks_mandatory_area(inode, f, size, inode->i_size - 1, + F_WRLCK); + } else { + return locks_mandatory_area(inode, f, inode->i_size, size - 1, + F_WRLCK); + } } static inline int break_lease(struct inode *inode, unsigned int mode) @@ -2144,9 +2143,8 @@ static inline int locks_mandatory_locked(struct file *file) return 0; } -static inline int locks_mandatory_area(int rw, struct inode *inode, - struct file *filp, loff_t offset, - size_t count) +static inline int locks_mandatory_area(struct inode *inode, struct file *filp, + loff_t start, loff_t end, unsigned char type) { return 0; } -- cgit v1.2.3 From 04b38d601239b4d9be641b412cf4b7456a041c67 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2015 12:59:50 +0100 Subject: vfs: pull btrfs clone API to vfs layer The btrfs clone ioctls are now adopted by other file systems, with NFS and CIFS already having support for them, and XFS being under active development. To avoid growth of various slightly incompatible implementations, add one to the VFS. Note that clones are different from file copies in several ways: - they are atomic vs other writers - they support whole file clones - they support 64-bit legth clones - they do not allow partial success (aka short writes) - clones are expected to be a fast metadata operation Because of that it would be rather cumbersome to try to piggyback them on top of the recent clone_file_range infrastructure. The converse isn't true and the clone_file_range system call could try clone file range as a first attempt to copy, something that further patches will enable. Based on earlier work from Peng Tao. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 4377b2df991d..5d987aefcf1e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1629,7 +1629,10 @@ struct file_operations { #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif - ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, + loff_t, size_t, unsigned int); + int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, + u64); }; struct inode_operations { @@ -1683,6 +1686,8 @@ extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); -- cgit v1.2.3 From ffa0160a103917defd5d9c097ae0455a59166e03 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 3 Dec 2015 12:59:52 +0100 Subject: nfsd: implement the NFSv4.2 CLONE operation This is basically a remote version of the btrfs CLONE operation, so the implementation is fairly trivial. Made even more trivial by stealing the XDR code and general framework Anna Schumaker's COPY prototype. Signed-off-by: Christoph Hellwig Acked-by: J. Bruce Fields Signed-off-by: Al Viro --- include/linux/nfs4.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index e7e78537aea2..43aeabd4b968 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -139,10 +139,10 @@ enum nfs_opnum4 { Needs to be updated if more operations are defined in future.*/ #define FIRST_NFS4_OP OP_ACCESS -#define LAST_NFS4_OP OP_WRITE_SAME #define LAST_NFS40_OP OP_RELEASE_LOCKOWNER #define LAST_NFS41_OP OP_RECLAIM_COMPLETE -#define LAST_NFS42_OP OP_WRITE_SAME +#define LAST_NFS42_OP OP_CLONE +#define LAST_NFS4_OP LAST_NFS42_OP enum nfsstat4 { NFS4_OK = 0, -- cgit v1.2.3 From f0cb32207307e9d7b3ee8117078b7a37f8d0166e Mon Sep 17 00:00:00 2001 From: Thomas Petazzoni Date: Tue, 20 Oct 2015 15:23:51 +0200 Subject: genirq: Implement irq_percpu_is_enabled() Certain interrupt controller drivers have a register set that does not make it easy to save/restore the mask of enabled/disabled interrupts at suspend/resume time. At resume time, such drivers rely on the core kernel irq subsystem to tell whether such or such interrupt is enabled or not, in order to restore the proper state in the interrupt controller register. While the irqd_irq_disabled() provides the relevant information for global interrupts, there is no similar function to query the enabled/disabled state of a per-CPU interrupt. Therefore, this commit complements the percpu_irq API with an irq_percpu_is_enabled() function. [ tglx: Simplified the implementation and added kerneldoc ] Signed-off-by: Thomas Petazzoni Cc: linux-arm-kernel@lists.infradead.org Cc: Tawfik Bayouk Cc: Nadav Haklai Cc: Lior Amsalem Cc: Andrew Lunn Cc: Sebastian Hesselbarth Cc: Gregory Clement Cc: Jason Cooper Cc: Marc Zyngier Link: http://lkml.kernel.org/r/1445347435-2333-2-git-send-email-thomas.petazzoni@free-electrons.com Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index ad16809c8596..cb30edbfe9fc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -195,6 +195,7 @@ extern void disable_irq(unsigned int irq); extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); extern void enable_percpu_irq(unsigned int irq, unsigned int type); +extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); /* The following three functions are for the core kernel use only. */ -- cgit v1.2.3 From 03e0d4610bf4d4a93bfa16b2474ed4fd5243aa71 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Dec 2015 11:28:04 -0500 Subject: watchdog: introduce touch_softlockup_watchdog_sched() touch_softlockup_watchdog() is used to tell watchdog that scheduler stall is expected. One group of usage is from paths where the task may not be able to yield for a long time such as performing slow PIO to finicky device and coming out of suspend. The other is to account for scheduler and timer going idle. For scheduler softlockup detection, there's no reason to distinguish the two cases; however, workqueue lockup detector is planned and it can use the same signals from the former group while the latter would spuriously prevent detection. This patch introduces a new function touch_softlockup_watchdog_sched() and convert the latter group to call it instead. For now, it just calls touch_softlockup_watchdog() and there's no functional difference. Signed-off-by: Tejun Heo Cc: Ulrich Obergfell Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Andrew Morton --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..d56cdde2f12c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -377,6 +377,7 @@ extern void scheduler_tick(void); extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_LOCKUP_DETECTOR +extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); @@ -387,6 +388,9 @@ extern unsigned int softlockup_panic; extern unsigned int hardlockup_panic; void lockup_detector_init(void); #else +static inline void touch_softlockup_watchdog_sched(void) +{ +} static inline void touch_softlockup_watchdog(void) { } -- cgit v1.2.3 From 82607adcf9cdf40fb7b5331269780c8f70ec6e35 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Dec 2015 11:28:04 -0500 Subject: workqueue: implement lockup detector Workqueue stalls can happen from a variety of usage bugs such as missing WQ_MEM_RECLAIM flag or concurrency managed work item indefinitely staying RUNNING. These stalls can be extremely difficult to hunt down because the usual warning mechanisms can't detect workqueue stalls and the internal state is pretty opaque. To alleviate the situation, this patch implements workqueue lockup detector. It periodically monitors all worker_pools periodically and, if any pool failed to make forward progress longer than the threshold duration, triggers warning and dumps workqueue state as follows. BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 31s! Showing busy workqueues and worker pools: workqueue events: flags=0x0 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=17/256 pending: monkey_wrench_fn, e1000_watchdog, cache_reap, vmstat_shepherd, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, cgroup_release_agent workqueue events_power_efficient: flags=0x80 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 pending: check_lifetime, neigh_periodic_work workqueue cgroup_pidlist_destroy: flags=0x0 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/1 pending: cgroup_pidlist_destroy_work_fn ... The detection mechanism is controller through kernel parameter workqueue.watchdog_thresh and can be updated at runtime through the sysfs module parameter file. v2: Decoupled from softlockup control knobs. Signed-off-by: Tejun Heo Acked-by: Don Zickus Cc: Ulrich Obergfell Cc: Michal Hocko Cc: Chris Mason Cc: Andrew Morton --- include/linux/workqueue.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0197358f1e81..0e32bc71245e 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -618,4 +618,10 @@ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ +#ifdef CONFIG_WQ_WATCHDOG +void wq_watchdog_touch(int cpu); +#else /* CONFIG_WQ_WATCHDOG */ +static inline void wq_watchdog_touch(int cpu) { } +#endif /* CONFIG_WQ_WATCHDOG */ + #endif -- cgit v1.2.3 From 14b6257a5f3dca3817b0826cb32967e3c2b935c8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 4 Dec 2015 23:49:17 +0200 Subject: device core: add BUS_NOTIFY_DRIVER_NOT_BOUND notification The users of BUS_NOTIFY_BIND_DRIVER have no chance to do any cleanup in case of a probe failure. In the result there might be problems, such as some resources that had been allocated will continue to be allocated and therefore lead to a resource leak. Introduce a new notification to inform the subscriber that ->probe() failed. Do the same in case of failed device_bind_driver() call. Signed-off-by: Andy Shevchenko Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index b8f411b57dcb..f627ba20a46c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -191,6 +191,7 @@ extern int bus_unregister_notifier(struct bus_type *bus, unbound */ #define BUS_NOTIFY_UNBOUND_DRIVER 0x00000007 /* driver is unbound from the device */ +#define BUS_NOTIFY_DRIVER_NOT_BOUND 0x00000008 /* driver fails to be bound */ extern struct kset *bus_get_kset(struct bus_type *bus); extern struct klist *bus_get_device_klist(struct bus_type *bus); -- cgit v1.2.3 From 8ac2837c89c8c0fcad557e4380aeef80580390f9 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Wed, 9 Dec 2015 10:51:12 +0800 Subject: Revert "Merge branch 'vsock-virtio'" This reverts commit 0d76d6e8b2507983a2cae4c09880798079007421 and merge commit c402293bd76fbc93e52ef8c0947ab81eea3ae019, reversing changes made to c89359a42e2a49656451569c382eed63e781153c. The virtio-vsock device specification is not finalized yet. Michael Tsirkin voiced concerned about merging this code when the hardware interface (and possibly the userspace interface) could still change. Signed-off-by: Stefan Hajnoczi Signed-off-by: David S. Miller --- include/linux/virtio_vsock.h | 209 ------------------------------------------- 1 file changed, 209 deletions(-) delete mode 100644 include/linux/virtio_vsock.h (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h deleted file mode 100644 index a5f3ecc038f7..000000000000 --- a/include/linux/virtio_vsock.h +++ /dev/null @@ -1,209 +0,0 @@ -/* - * 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 _LINUX_VIRTIO_VSOCK_H -#define _LINUX_VIRTIO_VSOCK_H - -#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) -#define VIRTIO_VSOCK_MAX_TX_BUF_SIZE (1024 * 1024 * 16) -#define VIRTIO_VSOCK_MAX_DGRAM_SIZE (1024 * 64) - -struct vsock_transport_recv_notify_data; -struct vsock_transport_send_notify_data; -struct sockaddr_vm; -struct vsock_sock; - -enum { - VSOCK_VQ_CTRL = 0, - VSOCK_VQ_RX = 1, /* for host to guest data */ - VSOCK_VQ_TX = 2, /* for guest to host data */ - VSOCK_VQ_MAX = 3, -}; - -/* virtio transport socket state */ -struct virtio_transport { - struct virtio_transport_pkt_ops *ops; - struct vsock_sock *vsk; - - u32 buf_size; - u32 buf_size_min; - u32 buf_size_max; - - struct mutex tx_lock; - struct mutex rx_lock; - - struct list_head rx_queue; - u32 rx_bytes; - - /* Protected by trans->tx_lock */ - u32 tx_cnt; - u32 buf_alloc; - u32 peer_fwd_cnt; - u32 peer_buf_alloc; - /* Protected by trans->rx_lock */ - u32 fwd_cnt; - - /* Protected by sk_lock */ - u16 dgram_id; - struct list_head incomplete_dgrams; /* dgram fragments */ -}; - -struct virtio_vsock_pkt { - struct virtio_vsock_hdr hdr; - struct virtio_transport *trans; - struct work_struct work; - struct list_head list; - void *buf; - u32 len; - u32 off; -}; - -struct virtio_vsock_pkt_info { - u32 remote_cid, remote_port; - struct msghdr *msg; - u32 pkt_len; - u16 type; - u16 op; - u32 flags; - u16 dgram_id; - u16 dgram_len; -}; - -struct virtio_transport_pkt_ops { - int (*send_pkt)(struct vsock_sock *vsk, - struct virtio_vsock_pkt_info *info); -}; - -void virtio_vsock_dumppkt(const char *func, - const struct virtio_vsock_pkt *pkt); - -struct sock * -virtio_transport_get_pending(struct sock *listener, - struct virtio_vsock_pkt *pkt); -struct virtio_vsock_pkt * -virtio_transport_alloc_pkt(struct vsock_sock *vsk, - struct virtio_vsock_pkt_info *info, - size_t len, - u32 src_cid, - u32 src_port, - u32 dst_cid, - u32 dst_port); -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_pkt *pkt); -void virtio_transport_dec_tx_pkt(struct virtio_vsock_pkt *pkt); -u32 virtio_transport_get_credit(struct virtio_transport *trans, u32 wanted); -void virtio_transport_put_credit(struct virtio_transport *trans, u32 credit); -#endif /* _LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From 2a56a1fec290bf0bc4676bbf4efdb3744953a3e7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Dec 2015 17:38:52 -0500 Subject: net: wrap sock->sk_cgrp_prioidx and ->sk_classid inside a struct Introduce sock->sk_cgrp_data which is a struct sock_cgroup_data. ->sk_cgroup_prioidx and ->sk_classid are moved into it. The struct and its accessors are defined in cgroup-defs.h. This is to prepare for overloading the fields with a cgroup pointer. This patch mostly performs equivalent conversions but the followings are noteworthy. * Equality test before updating classid is removed from sock_update_classid(). This shouldn't make any noticeable difference and a similar test will be implemented on the helper side later. * sock_update_netprioidx() now takes struct sock_cgroup_data and can be moved to netprio_cgroup.h without causing include dependency loop. Moved. * The dummy version of sock_update_netprioidx() converted to a static inline function while at it. Signed-off-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 504d8591b6d3..ed128fed0335 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -542,4 +542,40 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} #endif /* CONFIG_CGROUPS */ +#ifdef CONFIG_SOCK_CGROUP_DATA + +struct sock_cgroup_data { + u16 prioidx; + u32 classid; +}; + +static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd) +{ + return skcd->prioidx; +} + +static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) +{ + return skcd->classid; +} + +static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, + u16 prioidx) +{ + skcd->prioidx = prioidx; +} + +static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, + u32 classid) +{ + skcd->classid = classid; +} + +#else /* CONFIG_SOCK_CGROUP_DATA */ + +struct sock_cgroup_data { +}; + +#endif /* CONFIG_SOCK_CGROUP_DATA */ + #endif /* _LINUX_CGROUP_DEFS_H */ -- cgit v1.2.3 From bd1060a1d67128bb8fbe2e1384c518912cbe54e7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 7 Dec 2015 17:38:53 -0500 Subject: sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo Cc: Daniel Borkmann Cc: Daniel Wagner CC: Neil Horman Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 88 +++++++++++++++++++++++++++++++++++++++++---- include/linux/cgroup.h | 41 +++++++++++++++++++++ 2 files changed, 123 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ed128fed0335..9dc226345e4e 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -544,31 +544,107 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} #ifdef CONFIG_SOCK_CGROUP_DATA +/* + * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains + * per-socket cgroup information except for memcg association. + * + * On legacy hierarchies, net_prio and net_cls controllers directly set + * attributes on each sock which can then be tested by the network layer. + * On the default hierarchy, each sock is associated with the cgroup it was + * created in and the networking layer can match the cgroup directly. + * + * To avoid carrying all three cgroup related fields separately in sock, + * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. + * On boot, sock_cgroup_data records the cgroup that the sock was created + * in so that cgroup2 matches can be made; however, once either net_prio or + * net_cls starts being used, the area is overriden to carry prioidx and/or + * classid. The two modes are distinguished by whether the lowest bit is + * set. Clear bit indicates cgroup pointer while set bit prioidx and + * classid. + * + * While userland may start using net_prio or net_cls at any time, once + * either is used, cgroup2 matching no longer works. There is no reason to + * mix the two and this is in line with how legacy and v2 compatibility is + * handled. On mode switch, cgroup references which are already being + * pointed to by socks may be leaked. While this can be remedied by adding + * synchronization around sock_cgroup_data, given that the number of leaked + * cgroups is bound and highly unlikely to be high, this seems to be the + * better trade-off. + */ struct sock_cgroup_data { - u16 prioidx; - u32 classid; + union { +#ifdef __LITTLE_ENDIAN + struct { + u8 is_data; + u8 padding; + u16 prioidx; + u32 classid; + } __packed; +#else + struct { + u32 classid; + u16 prioidx; + u8 padding; + u8 is_data; + } __packed; +#endif + u64 val; + }; }; +/* + * There's a theoretical window where the following accessors race with + * updaters and return part of the previous pointer as the prioidx or + * classid. Such races are short-lived and the result isn't critical. + */ static inline u16 sock_cgroup_prioidx(struct sock_cgroup_data *skcd) { - return skcd->prioidx; + /* fallback to 1 which is always the ID of the root cgroup */ + return (skcd->is_data & 1) ? skcd->prioidx : 1; } static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) { - return skcd->classid; + /* fallback to 0 which is the unconfigured default classid */ + return (skcd->is_data & 1) ? skcd->classid : 0; } +/* + * If invoked concurrently, the updaters may clobber each other. The + * caller is responsible for synchronization. + */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - skcd->prioidx = prioidx; + struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + + if (sock_cgroup_prioidx(&skcd_buf) == prioidx) + return; + + if (!(skcd_buf.is_data & 1)) { + skcd_buf.val = 0; + skcd_buf.is_data = 1; + } + + skcd_buf.prioidx = prioidx; + WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - skcd->classid = classid; + struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + + if (sock_cgroup_classid(&skcd_buf) == classid) + return; + + if (!(skcd_buf.is_data & 1)) { + skcd_buf.val = 0; + skcd_buf.is_data = 1; + } + + skcd_buf.classid = classid; + WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4c3ffab81ba7..a8ba1ea0ea5a 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -578,4 +578,45 @@ static inline int cgroup_init(void) { return 0; } #endif /* !CONFIG_CGROUPS */ +/* + * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data + * definition in cgroup-defs.h. + */ +#ifdef CONFIG_SOCK_CGROUP_DATA + +#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) +extern spinlock_t cgroup_sk_update_lock; +#endif + +void cgroup_sk_alloc_disable(void); +void cgroup_sk_alloc(struct sock_cgroup_data *skcd); +void cgroup_sk_free(struct sock_cgroup_data *skcd); + +static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) +{ +#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) + unsigned long v; + + /* + * @skcd->val is 64bit but the following is safe on 32bit too as we + * just need the lower ulong to be written and read atomically. + */ + v = READ_ONCE(skcd->val); + + if (v & 1) + return &cgrp_dfl_root.cgrp; + + return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; +#else + return (struct cgroup *)(unsigned long)skcd->val; +#endif +} + +#else /* CONFIG_CGROUP_DATA */ + +static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} +static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} + +#endif /* CONFIG_CGROUP_DATA */ + #endif /* _LINUX_CGROUP_H */ -- cgit v1.2.3 From 21fc61c73c3903c4c312d0802da01ec2b323d174 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Nov 2015 01:07:57 -0500 Subject: don't put symlink bodies in pagecache into highmem kmap() in page_follow_link_light() needed to go - allowing to hold an arbitrary number of kmaps for long is a great way to deadlocking the system. new helper (inode_nohighmem(inode)) needs to be used for pagecache symlinks inodes; done for all in-tree cases. page_follow_link_light() instrumented to yell about anything missed. Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..dfeda44b9ba4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3025,5 +3025,6 @@ static inline bool dir_relax(struct inode *inode) } extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); #endif /* _LINUX_FS_H */ -- cgit v1.2.3 From 6b2553918d8b4e6de9853fd6315bec7271a2e592 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Nov 2015 10:20:54 -0500 Subject: replace ->follow_link() with new method that could stay in RCU mode new method: ->get_link(); replacement of ->follow_link(). The differences are: * inode and dentry are passed separately * might be called both in RCU and non-RCU mode; the former is indicated by passing it a NULL dentry. * when called that way it isn't allowed to block and should return ERR_PTR(-ECHILD) if it needs to be called in non-RCU mode. It's a flagday change - the old method is gone, all in-tree instances converted. Conversion isn't hard; said that, so far very few instances do not immediately bail out when called in RCU mode. That'll change in the next commits. Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dfeda44b9ba4..d2fdf09a4407 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1633,7 +1633,7 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - const char * (*follow_link) (struct dentry *, void **); + const char * (*get_link) (struct dentry *, struct inode *, void **); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); @@ -2736,7 +2736,7 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern const char *page_follow_link_light(struct dentry *, void **); +extern const char *page_get_link(struct dentry *, struct inode *, void **); extern void page_put_link(struct inode *, void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); @@ -2754,7 +2754,7 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); -const char *simple_follow_link(struct dentry *, void **); +const char *simple_get_link(struct dentry *, struct inode *, void **); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); -- cgit v1.2.3 From 0d0def49d05ae988936268b0e57d19aeef8c3ad2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 17 Nov 2015 21:14:24 -0500 Subject: teach nfs_get_link() to work in RCU mode based upon the corresponding patch from Neil's March patchset, again with kmap-related horrors removed. Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..37a3d2981352 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -359,6 +359,7 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); +extern int nfs_revalidate_mapping_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 *); -- cgit v1.2.3 From bf3d3cc580f9960883ebf9ea05868f336d9491c2 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 30 Nov 2015 13:28:15 +0100 Subject: mm/memblock: add MEMBLOCK_NOMAP attribute to memblock memory table This introduces the MEMBLOCK_NOMAP attribute and the required plumbing to make it usable as an indicator that some parts of normal memory should not be covered by the kernel direct mapping. It is up to the arch to actually honor the attribute when laying out this mapping, but the memblock code itself is modified to disregard these regions for allocations and other general use. Cc: linux-mm@kvack.org Cc: Alexander Kuleshov Cc: Andrew Morton Reviewed-by: Matt Fleming Signed-off-by: Ard Biesheuvel Signed-off-by: Will Deacon --- include/linux/memblock.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 24daf8fc4d7c..fec66f86eeff 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -25,6 +25,7 @@ enum { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ + MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ }; struct memblock_region { @@ -82,6 +83,7 @@ bool memblock_overlaps_region(struct memblock_type *type, int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); +int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); ulong choose_memblock_flags(void); /* Low level functions */ @@ -184,6 +186,11 @@ static inline bool memblock_is_mirror(struct memblock_region *m) return m->flags & MEMBLOCK_MIRROR; } +static inline bool memblock_is_nomap(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_NOMAP; +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); @@ -319,6 +326,7 @@ phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); int memblock_is_memory(phys_addr_t addr); +int memblock_is_map_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); int memblock_is_reserved(phys_addr_t addr); bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); -- cgit v1.2.3 From ad2c8c73d29702c3193f739390f6661f9a4ecad9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 9 Dec 2015 12:30:46 -0500 Subject: cgroup: fix sock_cgroup_data initialization on earlier compilers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sock_cgroup_data is a struct containing an anonymous union. sock_cgroup_set_prioidx() and sock_cgroup_set_classid() were initializing a field inside the anonymous union as follows. struct sock_ccgroup_data skcd_buf = { .val = VAL }; While this is fine on more recent compilers, gcc-4.4.7 triggers the following errors. include/linux/cgroup-defs.h: In function ‘sock_cgroup_set_prioidx’: include/linux/cgroup-defs.h:619: error: unknown field ‘val’ specified in initializer include/linux/cgroup-defs.h:619: warning: missing braces around initializer include/linux/cgroup-defs.h:619: warning: (near initialization for ‘skcd_buf.’) This is because .val belongs to the anonymous union nested inside the struct but the initializer is missing the nesting. Fix it by adding an extra pair of braces. Signed-off-by: Tejun Heo Reported-by: Alaa Hleihel Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") Signed-off-by: David S. Miller --- include/linux/cgroup-defs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9dc226345e4e..097901a68671 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -616,7 +616,7 @@ static inline u32 sock_cgroup_classid(struct sock_cgroup_data *skcd) static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; if (sock_cgroup_prioidx(&skcd_buf) == prioidx) return; @@ -633,7 +633,7 @@ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = { .val = READ_ONCE(skcd->val) }; + struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; if (sock_cgroup_classid(&skcd_buf) == classid) return; -- cgit v1.2.3 From 7de36b0aa51a5a59e28fb2da768fa3ab07de0674 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 9 Dec 2015 08:01:46 +0530 Subject: PM / OPP: Parse 'opp-supported-hw' binding OPP bindings allow a platform to enable OPPs based on the version of the hardware they are used for. Add support to the OPP-core to parse these bindings, by introducing dev_pm_opp_{set|put}_supported_hw() APIs. Signed-off-by: Viresh Kumar Tested-by: Lee Jones Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 9a2e50337af9..3a85110242f0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -55,6 +55,9 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq); int dev_pm_opp_disable(struct device *dev, unsigned long freq); struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev); +int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, + unsigned int count); +void dev_pm_opp_put_supported_hw(struct device *dev); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -129,6 +132,16 @@ static inline struct srcu_notifier_head *dev_pm_opp_get_notifier( { return ERR_PTR(-EINVAL); } + +static inline int dev_pm_opp_set_supported_hw(struct device *dev, + const u32 *versions, + unsigned int count) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -- cgit v1.2.3 From 01fb4d3c39d35b725441e8a9a26b3f3ad67793ed Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 9 Dec 2015 08:01:47 +0530 Subject: PM / OPP: Parse 'opp--' bindings OPP bindings (for few properties) allow a platform to choose a value/range among a set of available options. The options are present as opp--, where the platform needs to supply the string. The OPP properties which allow such an option are: opp-microvolt and opp-microamp. Add support to the OPP-core to parse these bindings, by introducing dev_pm_opp_{set|put}_prop_name() APIs. Signed-off-by: Viresh Kumar Tested-by: Lee Jones Signed-off-by: Rafael J. Wysocki --- include/linux/pm_opp.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 3a85110242f0..95403d2ccaf5 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -58,6 +58,8 @@ struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev); int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count); void dev_pm_opp_put_supported_hw(struct device *dev); +int dev_pm_opp_set_prop_name(struct device *dev, const char *name); +void dev_pm_opp_put_prop_name(struct device *dev); #else static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) { @@ -142,6 +144,13 @@ static inline int dev_pm_opp_set_supported_hw(struct device *dev, static inline void dev_pm_opp_put_supported_hw(struct device *dev) {} +static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name) +{ + return -EINVAL; +} + +static inline void dev_pm_opp_put_prop_name(struct device *dev) {} + #endif /* CONFIG_PM_OPP */ #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) -- cgit v1.2.3 From 37cf4dc3370fbca0344e23bb96446eb2c3548ba7 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 3 Dec 2015 22:09:31 -0500 Subject: time: Verify time values in adjtimex ADJ_SETOFFSET to avoid overflow For adjtimex()'s ADJ_SETOFFSET, make sure the tv_usec value is sane. We might multiply them later which can cause an overflow and undefined behavior. This patch introduces new helper functions to simplify the checking code and adds comments to clarify Orginally this patch was by Sasha Levin, but I've basically rewritten it, so he should get credit for finding the issue and I should get the blame for any mistakes made since. Also, credit to Richard Cochran for the phrasing used in the comment for what is considered valid here. Cc: Sasha Levin Cc: Richard Cochran Cc: Thomas Gleixner Reported-by: Sasha Levin Signed-off-by: John Stultz --- include/linux/time.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index beebe3a02d43..297f09f23896 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,32 @@ static inline bool timeval_valid(const struct timeval *tv) extern struct timespec timespec_trunc(struct timespec t, unsigned gran); +/* + * Validates if a timespec/timeval used to inject a time offset is valid. + * Offsets can be postive or negative. The value of the timeval/timespec + * is the sum of its fields, but *NOTE*: the field tv_usec/tv_nsec must + * always be non-negative. + */ +static inline bool timeval_inject_offset_valid(const struct timeval *tv) +{ + /* We don't check the tv_sec as it can be positive or negative */ + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + return true; +} + +static inline bool timespec_inject_offset_valid(const struct timespec *ts) +{ + /* We don't check the tv_sec as it can be positive or negative */ + + /* Can't have more nanoseconds then a second */ + if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + #define CURRENT_TIME (current_kernel_time()) #define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) -- cgit v1.2.3 From 666db563d3d9fffcfc019e3d1a980dac47601a71 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Thu, 10 Dec 2015 13:07:12 -0600 Subject: EDAC, mpc85xx: Make mpc85xx-pci-edac a platform device Originally the mpc85xx-pci-edac driver bound directly to the PCI controller node. Commit 905e75c46dba ("powerpc/fsl-pci: Unify pci/pcie initialization code") turned the PCI controller code into a platform device. Since we can't have two drivers binding to the same device, the EDAC code was changed to be called into as a library-style submodule. However, this doesn't work if the EDAC driver is built as a module. Commit 8d8fcba6d1ea ("EDAC: Rip out the edac_subsys reference counting") exposed another problem with this approach -- mpc85xx_pci_err_probe() was being called in the same early boot phase that the PCI controller is initialized, rather than in the device_initcall phase that the EDAC layer expects. This caused a crash on boot. To fix this, the PCI controller code now creates a child platform device specifically for EDAC, which the mpc85xx-pci-edac driver binds to. Reported-by: Michael Ellerman Reviewed-by: Johannes Thumshirn Signed-off-by: Scott Wood Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Daniel Axtens Cc: Doug Thompson Cc: Jia Hongtao Cc: Jiri Kosina Cc: Kim Phillips Cc: linux-edac Cc: linuxppc-dev@lists.ozlabs.org Cc: Masanari Iida Cc: Mauro Carvalho Chehab Cc: Paul Mackerras Cc: Randy Dunlap Cc: Rob Herring Link: http://lkml.kernel.org/r/1449774432-18593-1-git-send-email-scottwood@freescale.com Signed-off-by: Borislav Petkov --- include/linux/fsl/edac.h | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 include/linux/fsl/edac.h (limited to 'include/linux') diff --git a/include/linux/fsl/edac.h b/include/linux/fsl/edac.h new file mode 100644 index 000000000000..90d64d4ec1a9 --- /dev/null +++ b/include/linux/fsl/edac.h @@ -0,0 +1,8 @@ +#ifndef FSL_EDAC_H +#define FSL_EDAC_H + +struct mpc85xx_edac_pci_plat_data { + struct device_node *of_node; +}; + +#endif -- cgit v1.2.3 From 733476cf207faf574b132523ff2aee78b488ed6b Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 27 Nov 2015 11:40:43 +0100 Subject: EDAC: Rip out the edac_subsys reference counting This was really dumb - reference counting for the main EDAC sysfs object. While we could've simply registered it as the first thing in the module init path and then hand it around to what needs it. Do that and rip out all the code around it, thus simplifying the whole handling significantly. Move the edac_subsys node back to edac_module.c. Signed-off-by: Borislav Petkov --- include/linux/edac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index da6964873dcf..98f915dfeeac 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -33,7 +33,6 @@ extern struct bus_type edac_subsys; extern int edac_handler_set(void); extern void edac_atomic_assert_error(void); extern struct bus_type *edac_get_sysfs_subsys(void); -extern void edac_put_sysfs_subsys(void); enum { EDAC_REPORTING_ENABLED, -- cgit v1.2.3 From a97d26270169dc30ef28f0860097b7dc793206be Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Mon, 30 Nov 2015 14:15:31 +0100 Subject: EDAC: Unexport and make edac_subsys static ... and use the accessor instead. Signed-off-by: Borislav Petkov --- include/linux/edac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 98f915dfeeac..9e0d78966552 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -28,7 +28,6 @@ struct device; extern int edac_op_state; extern int edac_err_assert; extern atomic_t edac_handlers; -extern struct bus_type edac_subsys; extern int edac_handler_set(void); extern void edac_atomic_assert_error(void); -- cgit v1.2.3 From 899077791403ff7a2d8cfaa87bd1a82d729463e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 8 Dec 2015 16:32:27 +0100 Subject: netcp: try to reduce type confusion in descriptors The netcp driver produces tons of warnings when CONFIG_LPAE is enabled on ARM: drivers/net/ethernet/ti/netcp_core.c: In function 'netcp_tx_map_skb': drivers/net/ethernet/ti/netcp_core.c:1084:13: warning: passing argument 1 of 'set_words' from incompatible pointer type [-Wincompatible-pointer-types] This is the result of trying to pass a pointer to a dma_addr_t to a function that expects a u32 pointer to copy that into a DMA descriptor. Looking at that code in more detail to fix the warnings, I see multiple related problems: * The conversion functions are not endian-safe, as the DMA descriptors are almost certainly fixed-endian, but the CPU is not. * On 64-bit machines, passing a pointer through a u32 variable is a bug, accessing an indirect pointer as a u32 pointer even more so. * The handling of epib and psdata mixes native-endian and device-endian data. In this patch, I try to sort out the types for most accesses here, adding le32_to_cpu/cpu_to_le32 where appropriate, and passing pointers through two 32-bit words in the descriptor padding, to make it plausible that the driver does the right thing if compiled for big-endian or 64-bit systems. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/soc/ti/knav_dma.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index dad035c16d94..343c13ac4f71 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -144,17 +144,17 @@ struct knav_dma_cfg { * @psdata: Protocol specific */ struct knav_dma_desc { - u32 desc_info; - u32 tag_info; - u32 packet_info; - u32 buff_len; - u32 buff; - u32 next_desc; - u32 orig_len; - u32 orig_buff; - u32 epib[KNAV_DMA_NUM_EPIB_WORDS]; - u32 psdata[KNAV_DMA_NUM_PS_WORDS]; - u32 pad[4]; + __le32 desc_info; + __le32 tag_info; + __le32 packet_info; + __le32 buff_len; + __le32 buff; + __le32 next_desc; + __le32 orig_len; + __le32 orig_buff; + __le32 epib[KNAV_DMA_NUM_EPIB_WORDS]; + __le32 psdata[KNAV_DMA_NUM_PS_WORDS]; + __le32 pad[4]; } ____cacheline_aligned; #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA) -- cgit v1.2.3 From 26a8145390b36cbe97a5bd0b9e97249f21af6aea Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 10 Dec 2015 17:12:39 +0200 Subject: net/mlx5_core: Introduce flow steering firmware commands Introduce new Flow Steering (FS) firmware commands, in-order to support the new flow steering infrastructure. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 47 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 32 ++++++++++++++++++++--------- 2 files changed, 69 insertions(+), 10 deletions(-) create mode 100644 include/linux/mlx5/fs.h (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h new file mode 100644 index 000000000000..34fd8dc0b3e1 --- /dev/null +++ b/include/linux/mlx5/fs.h @@ -0,0 +1,47 @@ +/* + * Copyright (c) 2015, Mellanox Technologies. 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 _MLX5_FS_ +#define _MLX5_FS_ + +#include + +struct mlx5_flow_table; + +struct mlx5_flow_destination { + enum mlx5_flow_destination_type type; + union { + u32 tir_num; + struct mlx5_flow_table *ft; + }; +}; +#endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f5d94495758a..131a2737cfa3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -256,25 +256,27 @@ struct mlx5_ifc_flow_table_fields_supported_bits { struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_0[0x2]; + u8 flow_modify_en[0x1]; + u8 reserved_1[0x1c]; - u8 reserved_1[0x2]; + u8 reserved_2[0x2]; u8 log_max_ft_size[0x6]; - u8 reserved_2[0x10]; + u8 reserved_3[0x10]; u8 max_ft_level[0x8]; - u8 reserved_3[0x20]; + u8 reserved_4[0x20]; - u8 reserved_4[0x18]; + u8 reserved_5[0x18]; u8 log_max_ft_num[0x8]; - u8 reserved_5[0x18]; + u8 reserved_6[0x18]; u8 log_max_destination[0x8]; - u8 reserved_6[0x18]; + u8 reserved_7[0x18]; u8 log_max_flow[0x8]; - u8 reserved_7[0x40]; + u8 reserved_8[0x40]; struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; @@ -2843,6 +2845,13 @@ struct mlx5_ifc_set_hca_cap_in_bits { union mlx5_ifc_hca_cap_union_bits capability; }; +enum { + MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION = 0x0, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_TAG = 0x1, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST = 0x2, + MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS = 0x3 +}; + struct mlx5_ifc_set_fte_out_bits { u8 status[0x8]; u8 reserved_0[0x18]; @@ -2867,11 +2876,14 @@ struct mlx5_ifc_set_fte_in_bits { u8 reserved_4[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_5[0x18]; + u8 modify_enable_mask[0x8]; + + u8 reserved_6[0x20]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_7[0xe0]; struct mlx5_ifc_flow_context_bits flow_context; }; -- cgit v1.2.3 From 2530236303d9e705db6a28eb9a10c8d79b288b37 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 10 Dec 2015 17:12:43 +0200 Subject: net/mlx5_core: Flow steering tree initialization Flow steering initialization is based on static tree which illustrates the flow steering tree when the driver is loaded. The initialization considers the max supported flow table level of the device, a minimum of 2 kernel flow tables(vlan and mac) are required to have kernel flow table functionality. The tree structures when the driver is loaded: root_namespace(receive nic) | priority-0 (kernel priority) | namespace(kernel namespace) | priority-0 (flow tables priority) In the following patches, When the EN driver will use the flow steering API, it create two flow tables and their flow groups under priority-0(flow tables priority). Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/fs.h | 8 ++++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ac098b6b97bf..2fd7019f69db 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -502,6 +502,8 @@ struct mlx5_priv { 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; }; enum mlx5_device_state { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 34fd8dc0b3e1..16ae5233dc7b 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -35,6 +35,13 @@ #include +#define MLX5_FS_DEFAULT_FLOW_TAG 0x0 + +enum mlx5_flow_namespace_type { + MLX5_FLOW_NAMESPACE_KERNEL, + MLX5_FLOW_NAMESPACE_FDB, +}; + struct mlx5_flow_table; struct mlx5_flow_destination { @@ -42,6 +49,7 @@ struct mlx5_flow_destination { union { u32 tir_num; struct mlx5_flow_table *ft; + u32 vport_num; }; }; #endif -- cgit v1.2.3 From 86d722ad2c3bd2f0536b196b7fd67ae2a7e2a492 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Thu, 10 Dec 2015 17:12:44 +0200 Subject: net/mlx5: Use flow steering infrastructure for mlx5_en Expose the new flow steering API and remove the old one. Few changes are required: 1. The Ethernet flow steering follows the existing implementation, but uses the new steering API. The old flow steering implementation is removed. 2. Move the E-switch FDB management to use the new API. 3. When driver is loaded call to mlx5_init_fs which initialize the flow steering tree structure, open namespaces for NIC receive and for E-switch FDB. 4. Call to mlx5_cleanup_fs when the driver is unloaded. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/flow_table.h | 63 ----------------------------------------- include/linux/mlx5/fs.h | 38 +++++++++++++++++++++++++ 2 files changed, 38 insertions(+), 63 deletions(-) delete mode 100644 include/linux/mlx5/flow_table.h (limited to 'include/linux') diff --git a/include/linux/mlx5/flow_table.h b/include/linux/mlx5/flow_table.h deleted file mode 100644 index 0f2a15cf3317..000000000000 --- a/include/linux/mlx5/flow_table.h +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Copyright (c) 2013-2015, 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 MLX5_FLOW_TABLE_H -#define MLX5_FLOW_TABLE_H - -#include - -struct mlx5_flow_table_group { - u8 log_sz; - u8 match_criteria_enable; - u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; -}; - -struct mlx5_flow_destination { - enum mlx5_flow_destination_type type; - union { - u32 tir_num; - void *ft; - u32 vport_num; - }; -}; - -void *mlx5_create_flow_table(struct mlx5_core_dev *dev, u8 level, u8 table_type, - u16 num_groups, - struct mlx5_flow_table_group *group); -void mlx5_destroy_flow_table(void *flow_table); -int mlx5_add_flow_table_entry(void *flow_table, u8 match_criteria_enable, - void *match_criteria, void *flow_context, - u32 *flow_index); -void mlx5_del_flow_table_entry(void *flow_table, u32 flow_index); -u32 mlx5_get_flow_table_id(void *flow_table); - -#endif /* MLX5_FLOW_TABLE_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 16ae5233dc7b..bc7ad019afde 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -33,6 +33,7 @@ #ifndef _MLX5_FS_ #define _MLX5_FS_ +#include #include #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 @@ -43,6 +44,9 @@ enum mlx5_flow_namespace_type { }; struct mlx5_flow_table; +struct mlx5_flow_group; +struct mlx5_flow_rule; +struct mlx5_flow_namespace; struct mlx5_flow_destination { enum mlx5_flow_destination_type type; @@ -52,4 +56,38 @@ struct mlx5_flow_destination { u32 vport_num; }; }; + +struct mlx5_flow_namespace * +mlx5_get_flow_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type); + +struct mlx5_flow_table * +mlx5_create_flow_table(struct mlx5_flow_namespace *ns, + int prio, + int num_flow_table_entries); +int mlx5_destroy_flow_table(struct mlx5_flow_table *ft); + +/* inbox should be set with the following values: + * start_flow_index + * end_flow_index + * match_criteria_enable + * match_criteria + */ +struct mlx5_flow_group * +mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); +void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); + +/* Single destination per rule. + * Group ID is implied by the match criteria. + */ +struct mlx5_flow_rule * +mlx5_add_flow_rule(struct mlx5_flow_table *ft, + u8 match_criteria_enable, + u32 *match_criteria, + u32 *match_value, + u32 action, + u32 flow_tag, + struct mlx5_flow_destination *dest); +void mlx5_del_flow_rule(struct mlx5_flow_rule *fr); + #endif -- cgit v1.2.3 From 764a5c6b1fa4306dd7573c1d80914254909cd036 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 2 Dec 2015 14:44:43 +0100 Subject: xattr handlers: Simplify list operation Change the list operation to only return whether or not an attribute should be listed. Copying the attribute names into the buffer is moved to the callers. Since the result only depends on the dentry and not on the attribute name, we do not pass the attribute name to list operations. Signed-off-by: Andreas Gruenbacher Signed-off-by: Al Viro --- include/linux/xattr.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d23ce8e9af6f..4457541de3c9 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -28,9 +28,7 @@ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ - size_t (*list)(const struct xattr_handler *, struct dentry *dentry, - char *list, size_t list_size, const char *name, - size_t name_len); + bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, -- cgit v1.2.3 From 425a5072dcd1bd895eea90a6b495392b6358ebd0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 13 Dec 2015 18:02:22 +0100 Subject: genirq: Free irq_desc with rcu The new VMD device driver needs to iterate over a list of "demultiplexing" interrupts. Protecting that list with a lock is not possible because the list is also required in code pathes which hold irq descriptor lock. Therefor the demultiplexing interrupt handler would create a lock inversion scenario if it calls a demux handler with the list protection lock held. A solution for this is to free the irq descriptor via RCU, so the list can be walked with rcu read lock held. Signed-off-by: Thomas Gleixner Cc: Keith Busch --- include/linux/irqdesc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index a587a33363c7..dcca77c4b9d2 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -1,6 +1,8 @@ #ifndef _LINUX_IRQDESC_H #define _LINUX_IRQDESC_H +#include + /* * Core internal functions to deal with irq descriptors */ @@ -40,6 +42,7 @@ struct pt_regs; * IRQF_NO_SUSPEND set * @force_resume_depth: number of irqactions on a irq descriptor with * IRQF_FORCE_RESUME set + * @rcu: rcu head for delayed free * @dir: /proc/irq/ procfs entry * @name: flow handler name for /proc/interrupts output */ @@ -81,6 +84,9 @@ struct irq_desc { #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; +#endif +#ifdef CONFIG_SPARSE_IRQ + struct rcu_head rcu; #endif int parent_irq; struct module *owner; -- cgit v1.2.3 From bda13fed677bdb423b97dcf054f68b9eb4c6dbfb Mon Sep 17 00:00:00 2001 From: Masanari Iida Date: Sun, 13 Dec 2015 16:53:02 +0900 Subject: net: Fix typo in skb_fclone_busy This patch fix a typo found within comment of skb_fclone_busy. Signed-off-by: Masanari Iida Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9b9b9ead7bb3..af4f6ac025b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -833,7 +833,7 @@ struct sk_buff_fclones { * skb_fclone_busy - check if fclone is busy * @skb: buffer * - * Returns true is skb is a fast clone, and its clone is not freed. + * Returns true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that this didnt happen. */ -- cgit v1.2.3 From 8cfb0cdf07e2c260c4d1a102bfec35183907834f Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Thu, 3 Dec 2015 10:43:00 +0800 Subject: ACPI / debugger: Add IO interface to access debugger functionalities This patch adds /sys/kernel/debug/acpi/acpidbg, which can be used by userspace programs to access ACPICA debugger functionalities. Known issue: 1. IO flush support acpi_os_notify_command_complete() and acpi_os_wait_command_ready() can be used by acpi_dbg module to implement .flush() filesystem operation. While this patch doesn't go that far. It then becomes userspace tool's duty now to flush old commands before executing new batch mode commands. Signed-off-by: Lv Zheng Signed-off-by: Rafael J. Wysocki --- include/linux/acpi_dbg.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 include/linux/acpi_dbg.h (limited to 'include/linux') diff --git a/include/linux/acpi_dbg.h b/include/linux/acpi_dbg.h new file mode 100644 index 000000000000..60f3887ed816 --- /dev/null +++ b/include/linux/acpi_dbg.h @@ -0,0 +1,52 @@ +/* + * ACPI AML interfacing support + * + * Copyright (C) 2015, Intel Corporation + * Authors: Lv Zheng + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_ACPI_DBG_H +#define _LINUX_ACPI_DBG_H + +#include + +#ifdef CONFIG_ACPI_DEBUGGER +int __init acpi_aml_init(void); +int acpi_aml_create_thread(acpi_osd_exec_callback function, void *context); +ssize_t acpi_aml_write_log(const char *msg); +ssize_t acpi_aml_read_cmd(char *buffer, size_t buffer_length); +int acpi_aml_wait_command_ready(void); +int acpi_aml_notify_command_complete(void); +#else +static int inline acpi_aml_init(void) +{ + return 0; +} +static inline int acpi_aml_create_thread(acpi_osd_exec_callback function, + void *context) +{ + return -ENODEV; +} +static inline int acpi_aml_write_log(const char *msg) +{ + return -ENODEV; +} +static inline int acpi_aml_read_cmd(char *buffer, u32 buffer_length) +{ + return -ENODEV; +} +static inline int acpi_aml_wait_command_ready(void) +{ + return -ENODEV; +} +static inline int acpi_aml_notify_command_complete(void) +{ + return -ENODEV; +} +#endif + +#endif /* _LINUX_ACPI_DBG_H */ -- cgit v1.2.3 From 836d0830188a97d5c73e8eb514f346a857c086b9 Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Thu, 3 Dec 2015 10:43:14 +0800 Subject: ACPI / debugger: Add module support for ACPI debugger This patch converts AML debugger into a loadable module. Note that, it implements driver unloading at the level dependent on the module reference count. Which means if ACPI debugger is being used by a userspace program, "rmmod acpi_dbg" should result in failure. Signed-off-by: Lv Zheng Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/acpi_dbg.h | 52 ----------------------------------- 2 files changed, 71 insertions(+), 52 deletions(-) delete mode 100644 include/linux/acpi_dbg.h (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1991aea2ec4c..a03a05474527 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -37,6 +37,8 @@ #include #include #include +#include +#include #include #include @@ -119,6 +121,75 @@ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(struct acpi_subtable_header *header, const unsigned long end); +/* Debugger support */ + +struct acpi_debugger_ops { + int (*create_thread)(acpi_osd_exec_callback function, void *context); + ssize_t (*write_log)(const char *msg); + ssize_t (*read_cmd)(char *buffer, size_t length); + int (*wait_command_ready)(bool single_step, char *buffer, size_t length); + int (*notify_command_complete)(void); +}; + +struct acpi_debugger { + const struct acpi_debugger_ops *ops; + struct module *owner; + struct mutex lock; +}; + +#ifdef CONFIG_ACPI_DEBUGGER +int __init acpi_debugger_init(void); +int acpi_register_debugger(struct module *owner, + const struct acpi_debugger_ops *ops); +void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); +int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); +ssize_t acpi_debugger_write_log(const char *msg); +ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); +int acpi_debugger_wait_command_ready(void); +int acpi_debugger_notify_command_complete(void); +#else +static inline int acpi_debugger_init(void) +{ + return -ENODEV; +} + +static inline int acpi_register_debugger(struct module *owner, + const struct acpi_debugger_ops *ops) +{ + return -ENODEV; +} + +static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) +{ +} + +static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, + void *context) +{ + return -ENODEV; +} + +static inline int acpi_debugger_write_log(const char *msg) +{ + return -ENODEV; +} + +static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) +{ + return -ENODEV; +} + +static inline int acpi_debugger_wait_command_ready(void) +{ + return -ENODEV; +} + +static inline int acpi_debugger_notify_command_complete(void) +{ + return -ENODEV; +} +#endif + #ifdef CONFIG_ACPI_INITRD_TABLE_OVERRIDE void acpi_initrd_override(void *data, size_t size); #else diff --git a/include/linux/acpi_dbg.h b/include/linux/acpi_dbg.h deleted file mode 100644 index 60f3887ed816..000000000000 --- a/include/linux/acpi_dbg.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * ACPI AML interfacing support - * - * Copyright (C) 2015, Intel Corporation - * Authors: Lv Zheng - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef _LINUX_ACPI_DBG_H -#define _LINUX_ACPI_DBG_H - -#include - -#ifdef CONFIG_ACPI_DEBUGGER -int __init acpi_aml_init(void); -int acpi_aml_create_thread(acpi_osd_exec_callback function, void *context); -ssize_t acpi_aml_write_log(const char *msg); -ssize_t acpi_aml_read_cmd(char *buffer, size_t buffer_length); -int acpi_aml_wait_command_ready(void); -int acpi_aml_notify_command_complete(void); -#else -static int inline acpi_aml_init(void) -{ - return 0; -} -static inline int acpi_aml_create_thread(acpi_osd_exec_callback function, - void *context) -{ - return -ENODEV; -} -static inline int acpi_aml_write_log(const char *msg) -{ - return -ENODEV; -} -static inline int acpi_aml_read_cmd(char *buffer, u32 buffer_length) -{ - return -ENODEV; -} -static inline int acpi_aml_wait_command_ready(void) -{ - return -ENODEV; -} -static inline int acpi_aml_notify_command_complete(void) -{ - return -ENODEV; -} -#endif - -#endif /* _LINUX_ACPI_DBG_H */ -- cgit v1.2.3 From 364eba4b3a58a3e9af5a1355f4131a58cd1f3b8d Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 29 Oct 2015 18:33:47 +0100 Subject: time: Define dummy functions for the generic sched clock When we try to compile a clocksource driver with the COMPILE_TEST option, we can't select the GENERIC_SCHED_CLOCK because the sched_clock() symbol will be duplicated with the one defined for the x86. In order to fix that, we don't select the GENERIC_SCHED_CLOCK in the driver Kconfig's file but we define some empty functions for the different symbols in order to prevent the unresolved ones. This patch fixes the COMPILE_TEST option for the compile test coverage for the clocksource drivers. Without this patch, we can't add the COMPILE_TEST option for the clocksource drivers using the GENERIC_SCHED_CLOCK. Signed-off-by: Daniel Lezcano --- include/linux/sched_clock.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index efa931c5cef1..411b52e424e1 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -10,11 +10,17 @@ #ifdef CONFIG_GENERIC_SCHED_CLOCK extern void sched_clock_postinit(void); -#else -static inline void sched_clock_postinit(void) { } -#endif extern void sched_clock_register(u64 (*read)(void), int bits, unsigned long rate); +#else +static inline void sched_clock_postinit(void) { } + +static inline void sched_clock_register(u64 (*read)(void), int bits, + unsigned long rate) +{ + ; +} +#endif #endif -- cgit v1.2.3 From 55dc5a9f2f2afd32d7b1bda44a5fc95e67a3371f Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:40 -0800 Subject: net: Add skb_inner_transport_offset function Same thing as skb_transport_offset but returns the offset of the inner transport header (when skb->encpasulation is set). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index af4f6ac025b6..2393373c9d08 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1939,6 +1939,11 @@ static inline unsigned char *skb_inner_transport_header(const struct sk_buff return skb->head + skb->inner_transport_header; } +static inline int skb_inner_transport_offset(const struct sk_buff *skb) +{ + return skb_inner_transport_header(skb) - skb->data; +} + static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { skb->inner_transport_header = skb->data - skb->head; -- cgit v1.2.3 From 53692b1de419c1b59106909c7f6b4dd3dbc768ac Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:41 -0800 Subject: sctp: Rename NETIF_F_SCTP_CSUM to NETIF_F_SCTP_CRC The SCTP checksum is really a CRC and is very different from the standards 1's complement checksum that serves as the checksum for IP protocols. This offload interface is also very different. Rename NETIF_F_SCTP_CSUM to NETIF_F_SCTP_CRC to highlight these differences. The term CSUM should be reserved in the stack to refer to the standard 1's complement IP checksum. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index f0d87347df19..6395f8309393 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -52,7 +52,7 @@ enum { NETIF_F_GSO_TUNNEL_REMCSUM_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ - NETIF_F_SCTP_CSUM_BIT, /* SCTP checksum offload */ + NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ NETIF_F_FCOE_MTU_BIT, /* Supports max FCoE MTU, 2158 bytes*/ NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ @@ -103,7 +103,7 @@ enum { #define NETIF_F_NTUPLE __NETIF_F(NTUPLE) #define NETIF_F_RXCSUM __NETIF_F(RXCSUM) #define NETIF_F_RXHASH __NETIF_F(RXHASH) -#define NETIF_F_SCTP_CSUM __NETIF_F(SCTP_CSUM) +#define NETIF_F_SCTP_CRC __NETIF_F(SCTP_CRC) #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) -- cgit v1.2.3 From a188222b6ed29404ac2d4232d35d1fe0e77af370 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:43 -0800 Subject: net: Rename NETIF_F_ALL_CSUM to NETIF_F_CSUM_MASK The name NETIF_F_ALL_CSUM is a misnomer. This does not correspond to the set of features for offloading all checksums. This is a mask of the checksum offload related features bits. It is incorrect to set both NETIF_F_HW_CSUM and NETIF_F_IP_CSUM or NETIF_F_IPV6 at the same time for features of a device. This patch: - Changes instances of NETIF_F_ALL_CSUM to NETIF_F_CSUM_MASK (where NETIF_F_ALL_CSUM is being used as a mask). - Changes bonding, sfc/efx, ipvlan, macvlan, vlan, and team drivers to use NEITF_F_HW_CSUM in features list instead of NETIF_F_ALL_CSUM. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 7 ++++++- include/linux/netdevice.h | 6 +++--- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 6395f8309393..2c4e94ab88da 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -149,7 +149,12 @@ enum { #define NETIF_F_GEN_CSUM NETIF_F_HW_CSUM #define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM) #define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) -#define NETIF_F_ALL_CSUM (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) + +/* List of IP checksum features. Note that NETIF_HW_CSUM should not be + * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- + * this would be contradictory + */ +#define NETIF_F_CSUM_MASK (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1bb21ff0fa64..a54223a113b1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3763,12 +3763,12 @@ static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f2 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); f1 &= f2; if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); + f1 &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); return f1; } -- cgit v1.2.3 From c8cd0989bd151fda87bbf10887b3df18021284bc Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:44 -0800 Subject: net: Eliminate NETIF_F_GEN_CSUM and NETIF_F_V[46]_CSUM These netif flags are unnecessary convolutions. It is more straightforward to just use NETIF_F_HW_CSUM, NETIF_F_IP_CSUM, and NETIF_F_IPV6_CSUM directly. This patch also: - Cleans up can_checksum_protocol - Simplifies netdev_intersect_features Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 2 +- include/linux/netdev_features.h | 9 +++------ include/linux/netdevice.h | 40 +++++++++++++++++++++++++--------------- 3 files changed, 29 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 05f5879821b8..a5f6ce6b578c 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -621,7 +621,7 @@ static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c4e94ab88da..d9654f0eecb3 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -146,15 +146,12 @@ enum { #define NETIF_F_GSO_SOFTWARE (NETIF_F_TSO | NETIF_F_TSO_ECN | \ NETIF_F_TSO6 | NETIF_F_UFO) -#define NETIF_F_GEN_CSUM NETIF_F_HW_CSUM -#define NETIF_F_V4_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM) -#define NETIF_F_V6_CSUM (NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM) - -/* List of IP checksum features. Note that NETIF_HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ -#define NETIF_F_CSUM_MASK (NETIF_F_V4_CSUM | NETIF_F_V6_CSUM) +#define NETIF_F_CSUM_MASK (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ + NETIF_F_HW_CSUM) #define NETIF_F_ALL_TSO (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a54223a113b1..283984b67cd9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3691,13 +3691,24 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); + if (protocol == htons(ETH_P_FCOE)) + return !!(features & NETIF_F_FCOE_CRC); + + /* Assume this is an IP checksum (not SCTP CRC) */ + + if (features & NETIF_F_HW_CSUM) { + /* Can checksum everything */ + return true; + } + + switch (protocol) { + case htons(ETH_P_IP): + return !!(features & NETIF_F_IP_CSUM); + case htons(ETH_P_IPV6): + return !!(features & NETIF_F_IPV6_CSUM); + default: + return false; + } } #ifdef CONFIG_BUG @@ -3762,15 +3773,14 @@ void linkwatch_run_queue(void); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { - if (f1 & NETIF_F_GEN_CSUM) - f1 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); - if (f2 & NETIF_F_GEN_CSUM) - f2 |= (NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); - f1 &= f2; - if (f1 & NETIF_F_GEN_CSUM) - f1 &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_GEN_CSUM); + if ((f1 ^ f2) & NETIF_F_HW_CSUM) { + if (f1 & NETIF_F_HW_CSUM) + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + else + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + } - return f1; + return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( -- cgit v1.2.3 From 6ae23ad36253a8033c5714c52b691b84456487c5 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:46 -0800 Subject: net: Add driver helper functions to determine checksum offloadability Add skb_csum_offload_chk driver helper function to determine if a device with limited checksum offload capabilities is able to offload the checksum for a given packet. This patch includes: - The skb_csum_offload_chk function. Returns true if checksum is offloadable, else false. Optionally, in the case that the checksum is not offloable, the function can call skb_checksum_help to resolve the checksum. skb_csum_offload_chk also returns whether the checksum refers to an encapsulated checksum. - Definition of skb_csum_offl_spec structure that caller uses to indicate rules about what it can offload (e.g. IPv4/v6, TCP/UDP only, whether encapsulated checksums can be offloaded, whether checksum with IPv6 extension headers can be offloaded). - Ancilary functions called skb_csum_offload_chk_help, skb_csum_off_chk_help_cmn, skb_csum_off_chk_help_cmn_v4_only. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 78 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 283984b67cd9..9fb6395967de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2522,6 +2522,71 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } +struct skb_csum_offl_spec { + __u16 ipv4_okay:1, + ipv6_okay:1, + encap_okay:1, + ip_options_okay:1, + ext_hdrs_okay:1, + tcp_okay:1, + udp_okay:1, + sctp_okay:1, + vlan_okay:1, + no_encapped_ipv6:1, + no_not_encapped:1; +}; + +bool __skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help); + +static inline bool skb_csum_offload_chk(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec, + bool *csum_encapped, + bool csum_help) +{ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return false; + + return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); +} + +static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, + const struct skb_csum_offl_spec *spec) +{ + bool csum_encapped; + + return skb_csum_offload_chk(skb, spec, &csum_encapped, true); +} + +static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .ipv6_okay = 1, + .vlan_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + +static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) +{ + static const struct skb_csum_offl_spec csum_offl_spec = { + .ipv4_okay = 1, + .ip_options_okay = 1, + .tcp_okay = 1, + .udp_okay = 1, + .vlan_okay = 1, + }; + + return skb_csum_offload_chk_help(skb, &csum_offl_spec); +} + static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, @@ -3711,6 +3776,19 @@ static inline bool can_checksum_protocol(netdev_features_t features, } } +/* Map an ethertype into IP protocol if possible */ +static inline int eproto_to_ipproto(int eproto) +{ + switch (eproto) { + case htons(ETH_P_IP): + return IPPROTO_IP; + case htons(ETH_P_IPV6): + return IPPROTO_IPV6; + default: + return -1; + } +} + #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev); #else -- cgit v1.2.3 From 7a6ae71b2490586ed55105893a18dfc648e5fcbb Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 14 Dec 2015 11:19:47 -0800 Subject: net: Elaborate on checksum offload interface description Add specifics and details the description of the interface between the stack and drivers for doing checksum offload. This description is meant to be as specific and complete as possible. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 138 ++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 109 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2393373c9d08..6b6bd42d6134 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -39,11 +39,55 @@ #include #include -/* A. Checksumming of received packets by device. +/* The interface for checksum offload between the stack and networking drivers + * is as follows... + * + * A. IP checksum related features + * + * Drivers advertise checksum offload capabilities in the features of a device. + * From the stack's point of view these are capabilities offered by the driver, + * a driver typically only advertises features that it is capable of offloading + * to its device. + * + * The checksum related features are: + * + * NETIF_F_HW_CSUM - The driver (or its device) is able to compute one + * IP (one's complement) checksum for any combination + * of protocols or protocol layering. The checksum is + * computed and set in a packet per the CHECKSUM_PARTIAL + * interface (see below). + * + * NETIF_F_IP_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv4. These are specifically + * unencapsulated packets of the form IPv4|TCP or + * IPv4|UDP where the Protocol field in the IPv4 header + * is TCP or UDP. The IPv4 header may contain IP options + * This feature cannot be set in features for a device + * with NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain + * TCP or UDP packets over IPv6. These are specifically + * unencapsulated packets of the form IPv6|TCP or + * IPv4|UDP where the Next Header field in the IPv6 + * header is either TCP or UDP. IPv6 extension headers + * are not supported with this feature. This feature + * cannot be set in features for a device with + * NETIF_F_HW_CSUM also set. This feature is being + * DEPRECATED (see below). + * + * NETIF_F_RXCSUM - Driver (device) performs receive checksum offload. + * This flag is used only used to disable the RX checksum + * feature for a device. The stack will accept receive + * checksum indication in packets received on a device + * regardless of whether NETIF_F_RXCSUM is set. + * + * B. Checksumming of received packets by device. Indication of checksum + * verification is in set skb->ip_summed. Possible values are: * * CHECKSUM_NONE: * - * Device failed to checksum this packet e.g. due to lack of capabilities. + * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * @@ -53,9 +97,8 @@ * (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY * if their checksums are okay. skb->csum is still undefined in this case - * though. It is a bad option, but, unfortunately, nowadays most vendors do - * this. Apparently with the secret goal to sell you new devices, when you - * will add new protocol to your host, f.e. IPv6 8) + * though. A driver or device must never modify the checksum field in the + * packet even if checksum is verified. * * CHECKSUM_UNNECESSARY is applicable to following protocols: * TCP: IPv6 and IPv4. @@ -96,40 +139,77 @@ * packet that are after the checksum being offloaded are not considered to * be verified. * - * B. Checksumming on output. - * - * CHECKSUM_NONE: - * - * The skb was already checksummed by the protocol, or a checksum is not - * required. + * C. Checksumming on transmit for non-GSO. The stack requests checksum offload + * in the skb->ip_summed for a packet. Values are: * * CHECKSUM_PARTIAL: * - * The device is required to checksum the packet as seen by hard_start_xmit() + * The driver is required to checksum the packet as seen by hard_start_xmit() * from skb->csum_start up to the end, and to record/write the checksum at - * offset skb->csum_start + skb->csum_offset. + * offset skb->csum_start + skb->csum_offset. A driver may verify that the + * csum_start and csum_offset values are valid values given the length and + * offset of the packet, however they should not attempt to validate that the + * checksum refers to a legitimate transport layer checksum-- it is the + * purview of the stack to validate that csum_start and csum_offset are set + * correctly. + * + * When the stack requests checksum offload for a packet, the driver MUST + * ensure that the checksum is set correctly. A driver can either offload the + * checksum calculation to the device, or call skb_checksum_help (in the case + * that the device does not support offload for a particular checksum). + * + * NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM are being deprecated in favor of + * NETIF_F_HW_CSUM. New devices should use NETIF_F_HW_CSUM to indicate + * checksum offload capability. If a device has limited checksum capabilities + * (for instance can only perform NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM as + * described above) a helper function can be called to resolve + * CHECKSUM_PARTIAL. The helper functions are skb_csum_off_chk*. The helper + * function takes a spec argument that describes the protocol layer that is + * supported for checksum offload and can be called for each packet. If a + * packet does not match the specification for offload, skb_checksum_help + * is called to resolve the checksum. * - * The device must show its capabilities in dev->features, set up at device - * setup time, e.g. netdev_features.h: + * CHECKSUM_NONE: * - * NETIF_F_HW_CSUM - It's a clever device, it's able to checksum everything. - * NETIF_F_IP_CSUM - Device is dumb, it's able to checksum only TCP/UDP over - * IPv4. Sigh. Vendors like this way for an unknown reason. - * Though, see comment above about CHECKSUM_UNNECESSARY. 8) - * NETIF_F_IPV6_CSUM - About as dumb as the last one but does IPv6 instead. - * NETIF_F_... - Well, you get the picture. + * The skb was already checksummed by the protocol, or a checksum is not + * required. * * CHECKSUM_UNNECESSARY: * - * Normally, the device will do per protocol specific checksumming. Protocol - * implementations that do not want the NIC to perform the checksum - * calculation should use this flag in their outgoing skbs. + * This has the same meaning on as CHECKSUM_NONE for checksum offload on + * output. * - * NETIF_F_FCOE_CRC - This indicates that the device can do FCoE FC CRC - * offload. Correspondingly, the FCoE protocol driver - * stack should use CHECKSUM_UNNECESSARY. - * - * Any questions? No questions, good. --ANK + * CHECKSUM_COMPLETE: + * Not used in checksum output. If a driver observes a packet with this value + * set in skbuff, if should treat as CHECKSUM_NONE being set. + * + * D. Non-IP checksum (CRC) offloads + * + * NETIF_F_SCTP_CRC - This feature indicates that a device is capable of + * offloading the SCTP CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an SCTP checksum, a driver that supports + * both IP checksum offload and SCTP CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * NETIF_F_FCOE_CRC - This feature indicates that a device is capable of + * offloading the FCOE CRC in a packet. To perform this offload the stack + * will set ip_summed to CHECKSUM_PARTIAL and set csum_start and csum_offset + * accordingly. Note the there is no indication in the skbuff that the + * CHECKSUM_PARTIAL refers to an FCOE checksum, a driver that supports + * both IP checksum offload and FCOE CRC offload must verify which offload + * is configured for a packet presumably by inspecting packet headers. + * + * E. Checksumming on output with GSO. + * + * In the case of a GSO packet (skb_is_gso(skb) is true), checksum offload + * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the + * gso_type is SKB_GSO_TCPV4 or SKB_GSO_TCPV6, TCP checksum offload as + * part of the GSO operation is implied. If a checksum is being offloaded + * with GSO then ip_summed is CHECKSUM_PARTIAL, csum_start and csum_offset + * are set to refer to the outermost checksum being offload (two offloaded + * checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ -- cgit v1.2.3 From 3502cad73c4bbf8f6365d539e814159275252c59 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 15 Dec 2015 15:41:36 -0800 Subject: rhashtable: add function to replace an element Add the rhashtable_replace_fast function. This replaces one object in the table with another atomically. The hashes of the new and old objects must be equal. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 82 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 843ceca9a21e..77deece15fb3 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -819,4 +819,86 @@ out: return err; } +/* Internal function, please use rhashtable_replace_fast() instead */ +static inline int __rhashtable_replace_fast( + struct rhashtable *ht, struct bucket_table *tbl, + struct rhash_head *obj_old, struct rhash_head *obj_new, + const struct rhashtable_params params) +{ + struct rhash_head __rcu **pprev; + struct rhash_head *he; + spinlock_t *lock; + unsigned int hash; + int err = -ENOENT; + + /* Minimally, the old and new objects must have same hash + * (which should mean identifiers are the same). + */ + hash = rht_head_hashfn(ht, tbl, obj_old, params); + if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) + return -EINVAL; + + lock = rht_bucket_lock(tbl, hash); + + spin_lock_bh(lock); + + pprev = &tbl->buckets[hash]; + rht_for_each(he, tbl, hash) { + if (he != obj_old) { + pprev = &he->next; + continue; + } + + rcu_assign_pointer(obj_new->next, obj_old->next); + rcu_assign_pointer(*pprev, obj_new); + err = 0; + break; + } + + spin_unlock_bh(lock); + + return err; +} + +/** + * rhashtable_replace_fast - replace an object in hash table + * @ht: hash table + * @obj_old: pointer to hash head inside object being replaced + * @obj_new: pointer to hash head inside object which is new + * @params: hash table parameters + * + * Replacing an object doesn't affect the number of elements in the hash table + * or bucket, so we don't need to worry about shrinking or expanding the + * table here. + * + * Returns zero on success, -ENOENT if the entry could not be found, + * -EINVAL if hash is not the same for the old and new objects. + */ +static inline int rhashtable_replace_fast( + struct rhashtable *ht, struct rhash_head *obj_old, + struct rhash_head *obj_new, + const struct rhashtable_params params) +{ + struct bucket_table *tbl; + int err; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* Because we have already taken (and released) the bucket + * lock in old_tbl, if we find that future_tbl is not yet + * visible then that guarantees the entry to still be in + * the old tbl if it exists. + */ + while ((err = __rhashtable_replace_fast(ht, tbl, obj_old, + obj_new, params)) && + (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) + ; + + rcu_read_unlock(); + + return err; +} + #endif /* _LINUX_RHASHTABLE_H */ -- cgit v1.2.3 From fc9e50f5a5a4e1fa9ba2756f745a13e693cf6a06 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 15 Dec 2015 15:41:37 -0800 Subject: netlink: add a start callback for starting a netlink dump The start callback allows the caller to set up a context for the dump callbacks. Presumably, the context can then be destroyed in the done callback. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 639e9b8b0e4d..0b41959aab9f 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -131,6 +131,7 @@ netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; + int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); @@ -153,6 +154,7 @@ struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { + int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *skb, struct netlink_callback *); int (*done)(struct netlink_callback *); void *data; -- cgit v1.2.3 From b613f56ec9baf30edf5d9d607b822532a273dad7 Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Wed, 16 Dec 2015 12:30:02 +0900 Subject: net: diag: split inet_diag_dump_one_icsk into two Currently, inet_diag_dump_one_icsk finds a socket and then dumps its information to userspace. Split it into a part that finds the socket and a part that dumps the information. Signed-off-by: Lorenzo Colitti Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 0e707f0c1a3e..e7032f041982 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -3,6 +3,7 @@ #include +struct net; struct sock; struct inet_hashinfo; struct nlattr; @@ -41,6 +42,10 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req); +struct sock *inet_diag_find_one_icsk(struct net *net, + struct inet_hashinfo *hashinfo, + const struct inet_diag_req_v2 *req); + int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk); extern int inet_diag_register(const struct inet_diag_handler *handler); -- cgit v1.2.3 From 64be0aed59ad519d6f2160868734f7e278290ac1 Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Wed, 16 Dec 2015 12:30:03 +0900 Subject: net: diag: Add the ability to destroy a socket. This patch adds a SOCK_DESTROY operation, a destroy function pointer to sock_diag_handler, and a diag_destroy function pointer. It does not include any implementation code. Signed-off-by: Lorenzo Colitti Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/sock_diag.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h index fddebc617469..4018b48f2b3b 100644 --- a/include/linux/sock_diag.h +++ b/include/linux/sock_diag.h @@ -15,6 +15,7 @@ struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); + int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); @@ -68,4 +69,5 @@ bool sock_diag_has_destroy_listeners(const struct sock *sk) } void sock_diag_broadcast_destroy(struct sock *sk); +int sock_diag_destroy(struct sock *sk, int err); #endif -- cgit v1.2.3 From 6eb5d2e08f071c05ecbe135369c9ad418826cab2 Mon Sep 17 00:00:00 2001 From: Lorenzo Colitti Date: Wed, 16 Dec 2015 12:30:04 +0900 Subject: net: diag: Support SOCK_DESTROY for inet sockets. This passes the SOCK_DESTROY operation to the underlying protocol diag handler, or returns -EOPNOTSUPP if that handler does not define a destroy operation. Most of this patch is just renaming functions. This is not strictly necessary, but it would be fairly counterintuitive to have the code to destroy inet sockets be in a function whose name starts with inet_diag_get. Signed-off-by: Lorenzo Colitti Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index e7032f041982..7c27fa1030e8 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -24,6 +24,10 @@ struct inet_diag_handler { void (*idiag_get_info)(struct sock *sk, struct inet_diag_msg *r, void *info); + + int (*destroy)(struct sk_buff *in_skb, + const struct inet_diag_req_v2 *req); + __u16 idiag_type; __u16 idiag_info_size; }; -- cgit v1.2.3 From 541c9a84cd85203244307d9ebb821102eed82789 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Wed, 9 Dec 2015 23:36:51 +0100 Subject: ssb: pick SoC invariants code from MIPS BCM47xx arch MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is code in ssb fetching "invariants" that is basically a set of board specific data. Every host requires its own implementation of reading function. In ssb we have support for PCI, PCMCIA & SDIO. For some (historical?) reason code reading "invariants" for SoC was placed in arch code and provided by a callback. This is not needed nowadays, so lets move that into ssb. This way we keep all "invariants" functions in a single module making code cleaner. Signed-off-by: Rafał Miłecki Signed-off-by: Kalle Valo --- include/linux/ssb/ssb.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index c3d1a525bacc..26a0b3c3ce5f 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -524,13 +524,9 @@ struct ssb_init_invariants { typedef int (*ssb_invariants_func_t)(struct ssb_bus *bus, struct ssb_init_invariants *iv); -/* Register a SSB system bus. get_invariants() is called after the - * basic system devices are initialized. - * The invariants are usually fetched from some NVRAM. - * Put the invariants into the struct pointed to by iv. */ -extern int ssb_bus_ssbbus_register(struct ssb_bus *bus, - unsigned long baseaddr, - ssb_invariants_func_t get_invariants); +/* Register SoC bus. */ +extern int ssb_bus_host_soc_register(struct ssb_bus *bus, + unsigned long baseaddr); #ifdef CONFIG_SSB_PCIHOST extern int ssb_bus_pcibus_register(struct ssb_bus *bus, struct pci_dev *host_pci); -- cgit v1.2.3 From c466595c416c04036e1ba36ecdc5fe9072c76228 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 23 Nov 2015 08:26:04 +0000 Subject: irqdomain: Make irq_domain_alloc_irqs_recursive available We are soon going to need the MSI layer to call into the domain allocators. Instead of open coding this, make the standard irq_domain_alloc_irqs_recursive function available to the MSI layer. Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index d5e5c5bef28c..cf96c6a326f7 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -367,6 +367,9 @@ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false); } +extern int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs, void *arg); extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, -- cgit v1.2.3 From b2eba39bcab9d60a6c3b80c7fc2f3dacb77eeaae Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 23 Nov 2015 08:26:05 +0000 Subject: genirq/msi: Make the .prepare callback reusable The .prepare callbacks are so far only called from msi_domain_alloc_irqs. In order to reuse that code, split that code and create a msi_domain_prepare_irqs function that the existing code can call into. Signed-off-by: Marc Zyngier --- include/linux/msi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index f71a25e5fd25..1c0bb2c0b211 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -279,6 +279,10 @@ struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, irq_write_msi_msg_t write_msi_msg); void platform_msi_domain_free_irqs(struct device *dev); + +/* When an MSI domain is used as an intermediate domain */ +int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *args); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -- cgit v1.2.3 From 2145ac9310b60c1c11294b7bea10fe154009be1d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 23 Nov 2015 08:26:06 +0000 Subject: genirq/msi: Add msi_domain_populate_irqs To be able to allocate interrupts from the MSI layer down, add a new msi_domain_populate_irqs entry point. Signed-off-by: Marc Zyngier --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 1c0bb2c0b211..cee102b1916d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -283,6 +283,8 @@ void platform_msi_domain_free_irqs(struct device *dev); /* When an MSI domain is used as an intermediate domain */ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *args); +int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, + int virq, int nvec, msi_alloc_info_t *args); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -- cgit v1.2.3 From 552c494a7666c7fe490f179db1f52239a41fe734 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 23 Nov 2015 08:26:07 +0000 Subject: platform-msi: Allow creation of a MSI-based stacked irq domain We almost have all the needed bits requiredable to create a irq domain on top of a MSI domain. For this, we enable a few things: - the virq is stored in the msi_desc - device, msi_alloc_info and domain-specific data are stored in the platform_priv_data structure - we introduce a new API for platform-msi: /* Create a MSI-based domain */ struct irq_domain * platform_msi_create_device_domain(struct device *dev, unsigned int nvec, irq_write_msi_msg_t write_msi_msg, const struct irq_domain_ops *ops, void *host_data); /* Allocate MSIs in an MSI domain */ int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); /* Free MSIs from an MSI domain */ void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nvec); /* Obtain the host data passed to platform_msi_create_device_domain */ void *platform_msi_get_host_data(struct irq_domain *domain); platform_msi_create_device_domain() is a hybrid of irqdomain creation and interrupt allocation, creating a domain backed by the MSIs associated to a device. IRQs can then be allocated in that domain using platform_msi_domain_alloc(). This now allows a wired irq to MSI bridge to be created. Signed-off-by: Marc Zyngier --- include/linux/msi.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index cee102b1916d..1c6342ab8c0e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -174,6 +174,7 @@ struct msi_controller { #include struct irq_domain; +struct irq_domain_ops; struct irq_chip; struct device_node; struct fwnode_handle; @@ -285,6 +286,17 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *args); int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int virq, int nvec, msi_alloc_info_t *args); +struct irq_domain * +platform_msi_create_device_domain(struct device *dev, + unsigned int nvec, + irq_write_msi_msg_t write_msi_msg, + const struct irq_domain_ops *ops, + void *host_data); +int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nvec); +void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -- cgit v1.2.3 From 8673c1d7e8f0cc69b84c1c3356d869b74385fca7 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sat, 24 Oct 2015 00:15:52 +0200 Subject: irqchip/gic: Support RealView variant setup The ARM RealView PB11MPCore reference design has some special bits in a system controller register to set up the GIC in one of three modes: legacy, new with DCC, new without DCC. The register is also used to enable FIQ. Since the platform will not boot unless this register is set up to "new with DCC" mode, we need a special quirk to be compiled-in for the RealView platforms. If we find the right compatible string on the GIC TestChip, we enable this quirk by looking up the system controller and enabling the special bits. We depend on the CONFIG_REALVIEW_DT Kconfig symbol as the old boardfile code has the same fix hardcoded, and this is only needed for the attempts to modernize the RealView code using device tree. After fixing this, the PB11MPCore boots with device tree only. Cc: Thomas Gleixner Cc: Jason Cooper Signed-off-by: Linus Walleij Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index bae69e5d693c..d0a29db73bc7 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -103,6 +103,16 @@ struct device_node; void gic_cascade_irq(unsigned int gic_nr, unsigned int irq); int gic_cpu_if_down(unsigned int gic_nr); +/* + * Subdrivers that need some preparatory work can initialize their + * chips and call this to register their GICs. + */ +int gic_of_init(struct device_node *node, struct device_node *parent); + +/* + * Legacy platforms not converted to DT yet must use this to init + * their GIC + */ void gic_init(unsigned int nr, int start, void __iomem *dist , void __iomem *cpu); -- cgit v1.2.3 From a8170d2b9e8d38a1f3fa3b40b6f8cd34a87d5382 Mon Sep 17 00:00:00 2001 From: "Singhai, Anjali" Date: Mon, 14 Dec 2015 12:21:17 -0800 Subject: geneve: Add geneve udp port offload for ethernet devices Add ndo_ops to add/del UDP ports to a device that supports geneve offload. v2: Comment fix. Signed-off-by: Anjali Singhai Jain Signed-off-by: Kiran Patil Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9fb6395967de..81b26a543a3c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1013,6 +1013,19 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * 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 @@ -1217,7 +1230,12 @@ struct net_device_ops { 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_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, -- cgit v1.2.3 From 765eaa0f70eaa274ec8b815d8c210c20cf7b6dbc Mon Sep 17 00:00:00 2001 From: Andrey Smetanin Date: Mon, 30 Nov 2015 19:22:20 +0300 Subject: kvm/x86: Hyper-V SynIC message slot pending clearing at SINT ack The SynIC message protocol mandates that the message slot is claimed by atomically setting message type to something other than HVMSG_NONE. If another message is to be delivered while the slot is still busy, message pending flag is asserted to indicate to the guest that the hypervisor wants to be notified when the slot is released. To make sure the protocol works regardless of where the message sources are (kernel or userspace), clear the pending flag on SINT ACK notification, and let the message sources compete for the slot again. Signed-off-by: Andrey Smetanin Reviewed-by: Roman Kagan CC: Gleb Natapov CC: Paolo Bonzini CC: "K. Y. Srinivasan" CC: Haiyang Zhang CC: Vitaly Kuznetsov CC: Roman Kagan CC: Denis V. Lunev CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 590c46e672df..f44c24b81b17 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -450,6 +450,8 @@ struct kvm { #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +#define vcpu_err(vcpu, fmt, ...) \ + kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { -- cgit v1.2.3 From 1f4b34f825e8cef6f493d06b46605384785b3d16 Mon Sep 17 00:00:00 2001 From: Andrey Smetanin Date: Mon, 30 Nov 2015 19:22:21 +0300 Subject: kvm/x86: Hyper-V SynIC timers Per Hyper-V specification (and as required by Hyper-V-aware guests), SynIC provides 4 per-vCPU timers. Each timer is programmed via a pair of MSRs, and signals expiration by delivering a special format message to the configured SynIC message slot and triggering the corresponding synthetic interrupt. Note: as implemented by this patch, all periodic timers are "lazy" (i.e. if the vCPU wasn't scheduled for more than the timer period the timer events are lost), regardless of the corresponding configuration MSR. If deemed necessary, the "catch up" mode (the timer period is shortened until the timer catches up) will be implemented later. Changes v2: * Use remainder to calculate periodic timer expiration time Signed-off-by: Andrey Smetanin Reviewed-by: Roman Kagan CC: Gleb Natapov CC: Paolo Bonzini CC: "K. Y. Srinivasan" CC: Haiyang Zhang CC: Vitaly Kuznetsov CC: Roman Kagan CC: Denis V. Lunev CC: qemu-devel@nongnu.org Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f44c24b81b17..2969c474a399 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -144,6 +144,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_IOAPIC_EOI_EXIT 28 #define KVM_REQ_HV_RESET 29 #define KVM_REQ_HV_EXIT 30 +#define KVM_REQ_HV_STIMER 31 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 671d9ab38097fae45ff4f24562789b98b51d37ec Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 20 Nov 2015 19:52:12 +0100 Subject: kvm: Dump guest rIP when the guest tried something unsupported It looks like this in action: kvm [5197]: vcpu0, guest rIP: 0xffffffff810187ba unhandled rdmsr: 0xc001102 and helps to pinpoint quickly where in the guest we did the unsupported thing. Signed-off-by: Borislav Petkov Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2969c474a399..61c3e6c69f27 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -447,7 +447,8 @@ struct kvm { /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...) \ - kvm_pr_unimpl("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) + kvm_pr_unimpl("vcpu%i, guest rIP: 0x%lx " fmt, \ + (vcpu)->vcpu_id, kvm_rip_read(vcpu), ## __VA_ARGS__) #define vcpu_debug(vcpu, fmt, ...) \ kvm_debug("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) -- cgit v1.2.3 From 1717f2096b543cede7a380c858c765c41936bc35 Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Mon, 14 Dec 2015 11:19:09 +0100 Subject: panic, x86: Fix re-entrance problem due to panic on NMI If panic on NMI happens just after panic() on the same CPU, panic() is recursively called. Kernel stalls, as a result, after failing to acquire panic_lock. To avoid this problem, don't call panic() in NMI context if we've already entered panic(). For that, introduce nmi_panic() macro to reduce code duplication. In the case of panic on NMI, don't return from NMI handlers if another CPU already panicked. Signed-off-by: Hidehiro Kawai Acked-by: Michal Hocko Cc: Aaron Tomlin Cc: Andrew Morton Cc: Andy Lutomirski Cc: Baoquan He Cc: Chris Metcalf Cc: David Hildenbrand Cc: Don Zickus Cc: "Eric W. Biederman" Cc: Frederic Weisbecker Cc: Gobinda Charan Maji Cc: HATAYAMA Daisuke Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Javi Merino Cc: Jonathan Corbet Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml Cc: Masami Hiramatsu Cc: Michal Nazarewicz Cc: Nicolas Iooss Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Rasmus Villemoes Cc: Rusty Russell Cc: Seth Jennings Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Ulrich Obergfell Cc: Vitaly Kuznetsov Cc: Vivek Goyal Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner --- include/linux/kernel.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 350dfb08aee3..750cc5c7c999 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -445,6 +445,26 @@ extern int sysctl_panic_on_stackoverflow; extern bool crash_kexec_post_notifiers; +/* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * A variant of panic() called from NMI context. We return if we've already + * panicked on this CPU. + */ +#define nmi_panic(fmt, ...) \ +do { \ + int cpu = raw_smp_processor_id(); \ + \ + if (atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu) != cpu) \ + panic(fmt, ##__VA_ARGS__); \ +} while (0) + /* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. -- cgit v1.2.3 From 58c5661f2144c089bbc2e5d87c9ec1dc1d2964fe Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Mon, 14 Dec 2015 11:19:10 +0100 Subject: panic, x86: Allow CPUs to save registers even if looping in NMI context Currently, kdump_nmi_shootdown_cpus(), a subroutine of crash_kexec(), sends an NMI IPI to CPUs which haven't called panic() to stop them, save their register information and do some cleanups for crash dumping. However, if such a CPU is infinitely looping in NMI context, we fail to save its register information into the crash dump. For example, this can happen when unknown NMIs are broadcast to all CPUs as follows: CPU 0 CPU 1 =========================== ========================== receive an unknown NMI unknown_nmi_error() panic() receive an unknown NMI spin_trylock(&panic_lock) unknown_nmi_error() crash_kexec() panic() spin_trylock(&panic_lock) panic_smp_self_stop() infinite loop kdump_nmi_shootdown_cpus() issue NMI IPI -----------> blocked until IRET infinite loop... Here, since CPU 1 is in NMI context, the second NMI from CPU 0 is blocked until CPU 1 executes IRET. However, CPU 1 never executes IRET, so the NMI is not handled and the callback function to save registers is never called. In practice, this can happen on some servers which broadcast NMIs to all CPUs when the NMI button is pushed. To save registers in this case, we need to: a) Return from NMI handler instead of looping infinitely or b) Call the callback function directly from the infinite loop Inherently, a) is risky because NMI is also used to prevent corrupted data from being propagated to devices. So, we chose b). This patch does the following: 1. Move the infinite looping of CPUs which haven't called panic() in NMI context (actually done by panic_smp_self_stop()) outside of panic() to enable us to refer pt_regs. Please note that panic_smp_self_stop() is still used for normal context. 2. Call a callback of kdump_nmi_shootdown_cpus() directly to save registers and do some cleanups after setting waiting_for_crash_ipi which is used for counting down the number of CPUs which handled the callback Signed-off-by: Hidehiro Kawai Acked-by: Michal Hocko Cc: Aaron Tomlin Cc: Andrew Morton Cc: Andy Lutomirski Cc: Baoquan He Cc: Chris Metcalf Cc: Dave Young Cc: David Hildenbrand Cc: Don Zickus Cc: Eric Biederman Cc: Frederic Weisbecker Cc: Gobinda Charan Maji Cc: HATAYAMA Daisuke Cc: Hidehiro Kawai Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Javi Merino Cc: Jiang Liu Cc: Jonathan Corbet Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: lkml Cc: Masami Hiramatsu Cc: Michal Nazarewicz Cc: Nicolas Iooss Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Rasmus Villemoes Cc: Seth Jennings Cc: Stefan Lippers-Hollmann Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Ulrich Obergfell Cc: Vitaly Kuznetsov Cc: Vivek Goyal Cc: Yasuaki Ishimatsu Link: http://lkml.kernel.org/r/20151210014628.25437.75256.stgit@softrs [ Cleanup comments, fixup formatting. ] Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner --- include/linux/kernel.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 750cc5c7c999..7311c3294e25 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -255,6 +255,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic_self_stop(struct pt_regs *); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); @@ -455,14 +456,21 @@ extern atomic_t panic_cpu; /* * A variant of panic() called from NMI context. We return if we've already - * panicked on this CPU. + * panicked on this CPU. If another CPU already panicked, loop in + * nmi_panic_self_stop() which can provide architecture dependent code such + * as saving register state for crash dump. */ -#define nmi_panic(fmt, ...) \ +#define nmi_panic(regs, fmt, ...) \ do { \ - int cpu = raw_smp_processor_id(); \ + int old_cpu, cpu; \ \ - if (atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu) != cpu) \ + cpu = raw_smp_processor_id(); \ + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \ + \ + if (old_cpu == PANIC_CPU_INVALID) \ panic(fmt, ##__VA_ARGS__); \ + else if (old_cpu != cpu) \ + nmi_panic_self_stop(regs); \ } while (0) /* -- cgit v1.2.3 From 7bbee5ca3896f69f09c68be549cb8997abe6bca6 Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Mon, 14 Dec 2015 11:19:11 +0100 Subject: kexec: Fix race between panic() and crash_kexec() Currently, panic() and crash_kexec() can be called at the same time. For example (x86 case): CPU 0: oops_end() crash_kexec() mutex_trylock() // acquired nmi_shootdown_cpus() // stop other CPUs CPU 1: panic() crash_kexec() mutex_trylock() // failed to acquire smp_send_stop() // stop other CPUs infinite loop If CPU 1 calls smp_send_stop() before nmi_shootdown_cpus(), kdump fails. In another case: CPU 0: oops_end() crash_kexec() mutex_trylock() // acquired io_check_error() panic() crash_kexec() mutex_trylock() // failed to acquire infinite loop Clearly, this is an undesirable result. To fix this problem, this patch changes crash_kexec() to exclude others by using the panic_cpu atomic. Signed-off-by: Hidehiro Kawai Acked-by: Michal Hocko Cc: Andrew Morton Cc: Baoquan He Cc: Dave Young Cc: "Eric W. Biederman" Cc: HATAYAMA Daisuke Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jonathan Corbet Cc: kexec@lists.infradead.org Cc: linux-doc@vger.kernel.org Cc: Martin Schwidefsky Cc: Masami Hiramatsu Cc: Minfei Huang Cc: Peter Zijlstra Cc: Seth Jennings Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vitaly Kuznetsov Cc: Vivek Goyal Cc: x86-ml Link: http://lkml.kernel.org/r/20151210014630.25437.94161.stgit@softrs Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner --- include/linux/kexec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d140b1e9faa7..7b68d2788a56 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -237,6 +237,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image, unsigned int size, bool get_value); extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); @@ -332,6 +333,7 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; 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; } #define kexec_in_progress false -- cgit v1.2.3 From a436b6a19f57656a6557439523923d89eb4a880d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 17 Dec 2015 02:54:26 +0100 Subject: PM / runtime: Add new helper for conditional usage count incrementation Introduce a new runtime PM function, pm_runtime_get_if_in_use(), that will increment the device's runtime PM usage counter and return 1 if its status is RPM_ACTIVE and its usage counter is greater than 0 at the same time (0 will be returned otherwise). This is useful for things that should only be done if the device is active (from the runtime PM perspective) and used by somebody (as indicated by the usage counter) already and they are not worth bothering otherwise. Requested-by: Imre Deak Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3bdbb4189780..7af093d6a4dd 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -39,6 +39,7 @@ extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); +extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); @@ -143,6 +144,10 @@ static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } +static inline int pm_runtime_get_if_in_use(struct device *dev) +{ + return -EINVAL; +} static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } -- cgit v1.2.3 From 471036b2b895789c2305428fd879006468e4a758 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 10 Dec 2015 08:55:27 -0800 Subject: acpi: pci: Setup MSI domain for ACPI based pci devices This patch introduces pci_msi_register_fwnode_provider() for irqchip to register a callback, to provide a way to determine appropriate MSI domain for a pci device. It also introduces pci_host_bridge_acpi_msi_domain(), which returns the MSI domain of the specified PCI host bridge with DOMAIN_BUS_PCI_MSI bus token. Then, it is assigned to pci device. Reviewed-by: Marc Zyngier Acked-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki Signed-off-by: Suravee Suthikulpanit Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 5 +++++ include/linux/pci.h | 10 ++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index d5e5c5bef28c..a06fedacd955 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -410,6 +410,11 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) static inline void irq_dispose_mapping(unsigned int virq) { } static inline void irq_domain_activate_irq(struct irq_data *data) { } static inline void irq_domain_deactivate_irq(struct irq_data *data) { } +static inline struct irq_domain *irq_find_matching_fwnode( + struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token) +{ + return NULL; +} #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 6ae25aae88fd..d86378c226fb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1946,6 +1946,16 @@ static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } #endif /* CONFIG_OF */ +#ifdef CONFIG_ACPI +struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus); + +void +pci_msi_register_fwnode_provider(struct fwnode_handle *(*fn)(struct device *)); +#else +static inline struct irq_domain * +pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) { return NULL; } +#endif + #ifdef CONFIG_EEH static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev) { -- cgit v1.2.3 From 75aba7b0e9ac416ca53c0c97680b8e9aedf09284 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 10 Dec 2015 08:55:28 -0800 Subject: irqdomain: Introduce is_fwnode_irqchip helper Since there will be several places checking if fwnode.type is equal FWNODE_IRQCHIP, this patch adds a convenient function for this purpose. Acked-by: Marc Zyngier Signed-off-by: Suravee Suthikulpanit Signed-off-by: Marc Zyngier --- include/linux/irqdomain.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index a06fedacd955..d72fabc04437 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -211,6 +211,11 @@ static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) return node ? &node->fwnode : NULL; } +static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) +{ + return fwnode && fwnode->type == FWNODE_IRQCHIP; +} + static inline struct irq_domain *irq_find_matching_host(struct device_node *node, enum irq_domain_bus_token bus_token) { -- cgit v1.2.3 From 0644b3daca28dcb320373ae20069c269c9386304 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 10 Dec 2015 08:55:30 -0800 Subject: irqchip/gic-v2m: acpi: Introducing GICv2m ACPI support This patch introduces gicv2m_acpi_init(), which uses information in MADT GIC MSI frames structure to initialize GICv2m driver. It also exposes gicv2m_init() function, which simplifies callers to a single GICv2m init function. Reviewed-by: Marc Zyngier Tested-by: Duc Dang Acked-by: Rafael J. Wysocki Signed-off-by: Suravee Suthikulpanit Signed-off-by: Hanjun Guo Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index bae69e5d693c..febc6c312e37 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -106,7 +106,8 @@ int gic_cpu_if_down(unsigned int gic_nr); void gic_init(unsigned int nr, int start, void __iomem *dist , void __iomem *cpu); -int gicv2m_of_init(struct device_node *node, struct irq_domain *parent); +int gicv2m_init(struct fwnode_handle *parent_handle, + struct irq_domain *parent); void gic_send_sgi(unsigned int cpu_id, unsigned int irq); int gic_get_cpu_id(unsigned int cpu); -- cgit v1.2.3 From 66b3923a1a0f77a563b43f43f6ad091354abbfe9 Mon Sep 17 00:00:00 2001 From: David Woods Date: Thu, 17 Dec 2015 14:31:26 -0500 Subject: arm64: hugetlb: add support for PTE contiguous bit The arm64 MMU supports a Contiguous bit which is a hint that the TTE is one of a set of contiguous entries which can be cached in a single TLB entry. Supporting this bit adds new intermediate huge page sizes. The set of huge page sizes available depends on the base page size. Without using contiguous pages the huge page sizes are as follows. 4KB: 2MB 1GB 64KB: 512MB With a 4KB granule, the contiguous bit groups together sets of 16 pages and with a 64KB granule it groups sets of 32 pages. This enables two new huge page sizes in each case, so that the full set of available sizes is as follows. 4KB: 64KB 2MB 32MB 1GB 64KB: 2MB 512MB 16GB If a 16KB granule is used then the contiguous bit groups 128 pages at the PTE level and 32 pages at the PMD level. If the base page size is set to 64KB then 2MB pages are enabled by default. It is possible in the future to make 2MB the default huge page size for both 4KB and 64KB granules. Reviewed-by: Chris Metcalf Reviewed-by: Steve Capper Signed-off-by: David Woods Signed-off-by: Will Deacon --- include/linux/hugetlb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 685c262e0be8..b0eb06423d5e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -96,9 +96,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, struct address_space *mapping, pgoff_t idx, unsigned long address); -#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); -#endif extern int hugepages_treat_as_movable; extern int sysctl_hugetlb_shm_group; -- cgit v1.2.3 From 7b6471a968bf95e8d526393de125df3bc0c6a73a Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 5 Nov 2015 16:01:33 +0100 Subject: mmc: core: Remove MMC_CAP_RUNTIME_RESUME as it's redundant Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 8673ffe3d86e..9b04e717bb86 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -259,7 +259,6 @@ struct mmc_host { #define MMC_CAP_UHS_SDR50 (1 << 17) /* Host supports UHS SDR50 mode */ #define MMC_CAP_UHS_SDR104 (1 << 18) /* Host supports UHS SDR104 mode */ #define MMC_CAP_UHS_DDR50 (1 << 19) /* Host supports UHS DDR50 mode */ -#define MMC_CAP_RUNTIME_RESUME (1 << 20) /* Resume at runtime_resume. */ #define MMC_CAP_DRIVER_TYPE_A (1 << 23) /* Host supports Driver Type A */ #define MMC_CAP_DRIVER_TYPE_C (1 << 24) /* Host supports Driver Type C */ #define MMC_CAP_DRIVER_TYPE_D (1 << 25) /* Host supports Driver Type D */ -- cgit v1.2.3 From 8dede18e2e86c8e272cd74e66b0e86872cbe7e02 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 5 Nov 2015 16:11:12 +0100 Subject: mmc: core: Refactor code to register the MMC PM notifier Instead of checking for "#ifdef" directly in the code, let's invent a pair of mmc core functions to deal with register/unregister the MMC PM notifier block. Implement stubs for these functions when CONFIG_PM_SLEEP is unset, as in that case the PM notifiers isn't used. Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9b04e717bb86..f39888cf5017 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -212,7 +212,9 @@ struct mmc_host { u32 ocr_avail_sdio; /* SDIO-specific OCR */ u32 ocr_avail_sd; /* SD-specific OCR */ u32 ocr_avail_mmc; /* MMC-specific OCR */ +#ifdef CONFIG_PM_SLEEP struct notifier_block pm_notify; +#endif u32 max_current_330; u32 max_current_300; u32 max_current_180; @@ -433,8 +435,6 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc, int mmc_regulator_get_supply(struct mmc_host *mmc); -int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *); - static inline int mmc_card_is_removable(struct mmc_host *host) { return !(host->caps & MMC_CAP_NONREMOVABLE); -- cgit v1.2.3 From 6d91439ae2d31c45706802e0a0716e25f9f97563 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 25 Nov 2015 14:57:31 +0100 Subject: mmc: mvsdio: delete platform data header This platform data struct is only used inside the MVSDIO driver, nowhere else in the entire kernel. Move the struct into the driver and delete the external header. Cc: Nicolas Pitre Cc: Andrew Lunn Cc: Sebastian Hesselbarth Signed-off-by: Linus Walleij Acked-by: Nicolas Pitre Acked-by: Andrew Lunn Signed-off-by: Ulf Hansson --- include/linux/platform_data/mmc-mvsdio.h | 18 ------------------ 1 file changed, 18 deletions(-) delete mode 100644 include/linux/platform_data/mmc-mvsdio.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mmc-mvsdio.h b/include/linux/platform_data/mmc-mvsdio.h deleted file mode 100644 index d02704cd3695..000000000000 --- a/include/linux/platform_data/mmc-mvsdio.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * 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 __MMC_MVSDIO_H -#define __MMC_MVSDIO_H - -#include - -struct mvsdio_platform_data { - unsigned int clock; - int gpio_card_detect; - int gpio_write_protect; -}; - -#endif -- cgit v1.2.3 From 100a606d54a087cfec54efbedba72f36e5a9cdf0 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Wed, 25 Nov 2015 15:39:51 +0100 Subject: mmc: core: Introduce MMC_CAP2_NO_SDIO cap This patch introduce a new MMC_CAP2_NO_SDIO cap used to tell the mmc core to not send SDIO specific commands. Signed-off-by: Carlo Caione Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index f39888cf5017..8dd4d290ab0d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -290,6 +290,7 @@ struct mmc_host { #define MMC_CAP2_HSX00_1_2V (MMC_CAP2_HS200_1_2V_SDR | MMC_CAP2_HS400_1_2V) #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 */ mmc_pm_flag_t pm_caps; /* supported pm features */ -- cgit v1.2.3 From 260b31643691e8a58683a4ccc3bdf7abfd86f54a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 12 Nov 2015 15:14:23 +0100 Subject: mmc: dw_mmc: use resource_size_t to store physical address The dw_mmc driver stores the physical address of the MMIO registers in a pointer, which requires the use of type casts, and is actually broken if anyone ever has this device on a 32-bit SoC in registers above 4GB. Gcc warns about this possibility when the driver is built with ARM LPAE enabled: mmc/host/dw_mmc.c: In function 'dw_mci_edmac_start_dma': mmc/host/dw_mmc.c:702:17: warning: cast from pointer to integer of different size cfg.dst_addr = (dma_addr_t)(host->phy_regs + fifo_offset); ^ mmc/host/dw_mmc-pltfm.c: In function 'dw_mci_pltfm_register': mmc/host/dw_mmc-pltfm.c:63:19: warning: cast to pointer from integer of different size host->phy_regs = (void *)(regs->start); This changes the code to use resource_size_t, which gets rid of the warning, the bug and the useless casts. Signed-off-by: Arnd Bergmann Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index f67b2ec18e6d..7776afb0ffa5 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -172,7 +172,7 @@ struct dw_mci { /* For edmac */ struct dw_mci_dma_slave *dms; /* Registers's physical base address */ - void *phy_regs; + resource_size_t phy_regs; u32 cmd_status; u32 data_status; -- cgit v1.2.3 From b25472f9b96159cc0b9b7ed449448805973cd789 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 5 Dec 2015 22:04:48 -0500 Subject: new helpers: no_seek_end_llseek{,_size}() Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bd1447661e3c..fb0fa224d8e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2660,6 +2660,8 @@ extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); +extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); +extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -- cgit v1.2.3 From ba27f2bc731135a0396f3968bdddb54f3bc72e64 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 30 Nov 2015 17:23:39 -0500 Subject: ftrace: Remove use of control list and ops Currently perf has its own list function within the ftrace infrastructure that seems to be used only to allow for it to have per-cpu disabling as well as a check to make sure that it's not called while RCU is not watching. It uses something called the "control_ops" which is used to iterate over ops under it with the control_list_func(). The problem is that this control_ops and control_list_func unnecessarily complicates the code. By replacing FTRACE_OPS_FL_CONTROL with two new flags (FTRACE_OPS_FL_RCU and FTRACE_OPS_FL_PER_CPU) we can remove all the code that is special with the control ops and add the needed checks within the generic ftrace_list_func(). Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 134f8d45b35b..4736a826baf5 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -76,8 +76,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * ENABLED - set/unset when ftrace_ops is registered/unregistered * DYNAMIC - set when ftrace_ops is registered to denote dynamically * allocated ftrace_ops which need special care - * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops - * could be controled by following calls: + * PER_CPU - set manualy by ftrace_ops user to denote the ftrace_ops + * could be controlled by following calls: * ftrace_function_local_enable * ftrace_function_local_disable * SAVE_REGS - The ftrace_ops wants regs saved at each function called @@ -121,7 +121,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); enum { FTRACE_OPS_FL_ENABLED = 1 << 0, FTRACE_OPS_FL_DYNAMIC = 1 << 1, - FTRACE_OPS_FL_CONTROL = 1 << 2, + FTRACE_OPS_FL_PER_CPU = 1 << 2, FTRACE_OPS_FL_SAVE_REGS = 1 << 3, FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 4, FTRACE_OPS_FL_RECURSION_SAFE = 1 << 5, @@ -134,6 +134,7 @@ enum { FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 12, FTRACE_OPS_FL_IPMODIFY = 1 << 13, FTRACE_OPS_FL_PID = 1 << 14, + FTRACE_OPS_FL_RCU = 1 << 15, }; #ifdef CONFIG_DYNAMIC_FTRACE @@ -146,11 +147,11 @@ struct ftrace_ops_hash { #endif /* - * Note, ftrace_ops can be referenced outside of RCU protection. - * (Although, for perf, the control ops prevent that). If ftrace_ops is - * allocated and not part of kernel core data, the unregistering of it will - * perform a scheduling on all CPUs to make sure that there are no more users. - * Depending on the load of the system that may take a bit of time. + * Note, ftrace_ops can be referenced outside of RCU protection, unless + * the RCU flag is set. If ftrace_ops is allocated and not part of kernel + * core data, the unregistering of it will perform a scheduling on all CPUs + * to make sure that there are no more users. Depending on the load of the + * system that may take a bit of time. * * Any private data added must also take care not to be freed and if private * data is added to a ftrace_ops that is in core code, the user of the @@ -196,34 +197,34 @@ int unregister_ftrace_function(struct ftrace_ops *ops); void clear_ftrace_function(void); /** - * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu + * ftrace_function_local_enable - enable ftrace_ops on current cpu * * This function enables tracing on current cpu by decreasing * the per cpu control variable. * It must be called with preemption disabled and only on ftrace_ops - * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. */ static inline void ftrace_function_local_enable(struct ftrace_ops *ops) { - if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU))) return; (*this_cpu_ptr(ops->disabled))--; } /** - * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu + * ftrace_function_local_disable - disable ftrace_ops on current cpu * - * This function enables tracing on current cpu by decreasing + * This function disables tracing on current cpu by increasing * the per cpu control variable. * It must be called with preemption disabled and only on ftrace_ops - * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. */ static inline void ftrace_function_local_disable(struct ftrace_ops *ops) { - if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL))) + if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU))) return; (*this_cpu_ptr(ops->disabled))++; @@ -235,12 +236,12 @@ static inline void ftrace_function_local_disable(struct ftrace_ops *ops) * * This function returns value of ftrace_ops::disabled on current cpu. * It must be called with preemption disabled and only on ftrace_ops - * registered with FTRACE_OPS_FL_CONTROL. If called without preemption + * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled. */ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) { - WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)); + WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)); return *this_cpu_ptr(ops->disabled); } -- cgit v1.2.3 From 2701121b8f4db4d69c327c0d8f8694ff2ce30ef7 Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Mon, 14 Dec 2015 23:18:05 +0300 Subject: tracing: Introduce TRACE_EVENT_FN_COND macro TRACE_EVENT_FN can't be used in some circumstances like invoking trace functions from offlined CPU due to RCU usage. This patch adds the TRACE_EVENT_FN_COND macro to make such trace points conditional. Link: http://lkml.kernel.org/r/1450124286-4822-1-git-send-email-kda@linux-powerpc.org Signed-off-by: Denis Kirjanov Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..45b3fcf7dd3c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -493,6 +493,10 @@ extern void syscall_unregfunc(void); #define TRACE_EVENT_FN(name, proto, args, struct, \ assign, print, reg, unreg) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define TRACE_EVENT_FN_COND(name, proto, args, cond, struct, \ + assign, print, reg, unreg) \ + DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ + PARAMS(args), PARAMS(cond)) #define TRACE_EVENT_CONDITION(name, proto, args, cond, \ struct, assign, print) \ DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ -- cgit v1.2.3 From 7b8002a1511fcbcb0596cac90d67ad5c8182d0aa Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 15 Dec 2015 18:41:56 +0100 Subject: netfilter: nfnetlink: pass down netns pointer to call() and call_rcu() Adapt callsites to avoid recurrent lookup of the netns pointer. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 5646b24bfc64..ceacbf5dcb73 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -8,12 +8,12 @@ #include struct nfnl_callback { - int (*call)(struct sock *nl, struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const cda[]); - int (*call_rcu)(struct sock *nl, struct sk_buff *skb, + int (*call)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); + int (*call_rcu)(struct net *net, struct sock *nl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const cda[]); int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); -- cgit v1.2.3 From 5913beaf0d70f97135ed7191c028fd88b3848864 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 15 Dec 2015 19:41:57 +0100 Subject: netfilter: nfnetlink: pass down netns pointer to commit() and abort() callbacks Adapt callsites to avoid recurrent lookup of the netns pointer. Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index ceacbf5dcb73..ba0d9789eb6e 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -26,8 +26,8 @@ struct nfnetlink_subsystem { __u8 subsys_id; /* nfnetlink subsystem ID */ __u8 cb_count; /* number of callbacks */ const struct nfnl_callback *cb; /* callback for individual types */ - int (*commit)(struct sk_buff *skb); - int (*abort)(struct sk_buff *skb); + int (*commit)(struct net *net, struct sk_buff *skb); + int (*abort)(struct net *net, struct sk_buff *skb); }; int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n); -- cgit v1.2.3 From 7be4fb643ef2d1058b897ba9dbe17bf5ced04391 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Wed, 23 Dec 2015 23:45:24 +0100 Subject: nfc: microread: Fix header comment microread platform_data header had an NXP header. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/linux/platform_data/microread.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/microread.h b/include/linux/platform_data/microread.h index cfda59b226ee..ca13992089b8 100644 --- a/include/linux/platform_data/microread.h +++ b/include/linux/platform_data/microread.h @@ -1,5 +1,5 @@ /* - * Driver include for the PN544 NFC chip. + * Driver include for the Inside Secure microread NFC Chip. * * Copyright (C) 2011 Tieto Poland * Copyright (C) 2012 Intel Corporation. All rights reserved. -- cgit v1.2.3 From cd3417c8fc9504cc1afe944515f338aff9ec286b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 29 Dec 2015 16:03:53 -0500 Subject: kill free_page_put_link() all callers are better off with kfree_put_link() Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d2fdf09a4407..138e206df2fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2743,7 +2743,6 @@ extern int __page_symlink(struct inode *inode, const char *symname, int len, extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_put_link(struct inode *, void *); -extern void free_page_put_link(struct inode *, void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); -- cgit v1.2.3 From fceef393a538134f03b778c5d2519e670269342f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 29 Dec 2015 15:58:39 -0500 Subject: switch ->get_link() to delayed_call, kill ->put_link() Signed-off-by: Al Viro --- include/linux/delayed_call.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/fs.h | 14 ++++++++------ 2 files changed, 42 insertions(+), 6 deletions(-) create mode 100644 include/linux/delayed_call.h (limited to 'include/linux') diff --git a/include/linux/delayed_call.h b/include/linux/delayed_call.h new file mode 100644 index 000000000000..f7fa76ae1a9b --- /dev/null +++ b/include/linux/delayed_call.h @@ -0,0 +1,34 @@ +#ifndef _DELAYED_CALL_H +#define _DELAYED_CALL_H + +/* + * Poor man's closures; I wish we could've done them sanely polymorphic, + * but... + */ + +struct delayed_call { + void (*fn)(void *); + void *arg; +}; + +#define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} + +/* I really wish we had closures with sane typechecking... */ +static inline void set_delayed_call(struct delayed_call *call, + void (*fn)(void *), void *arg) +{ + call->fn = fn; + call->arg = arg; +} + +static inline void do_delayed_call(struct delayed_call *call) +{ + if (call->fn) + call->fn(call->arg); +} + +static inline void clear_delayed_call(struct delayed_call *call) +{ + call->fn = NULL; +} +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 138e206df2fc..5de5edb01e70 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -1633,12 +1634,11 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - const char * (*get_link) (struct dentry *, struct inode *, void **); + const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct inode *, void *); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); @@ -2736,13 +2736,14 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern const char *page_get_link(struct dentry *, struct inode *, void **); -extern void page_put_link(struct inode *, void *); +extern const char *page_get_link(struct dentry *, struct inode *, + struct delayed_call *); +extern void page_put_link(void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern void kfree_put_link(struct inode *, void *); +extern void kfree_link(void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); @@ -2753,7 +2754,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); -const char *simple_get_link(struct dentry *, struct inode *, void **); +const char *simple_get_link(struct dentry *, struct inode *, + struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); -- cgit v1.2.3 From f3a4094558ddf8afa8bb58250d548e15e059c65a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 30 Dec 2015 16:28:25 +0100 Subject: ethtool: Add phy statistics Ethernet PHYs can maintain statistics, for example errors while idle and receive errors. Add an ethtool mechanism to retrieve these statistics, using the same model as MAC statistics. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 05fde31b6dc6..a89cb0eef911 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -589,6 +589,12 @@ struct phy_driver { int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); + /* Get statistics from the phy using ethtool */ + int (*get_sset_count)(struct phy_device *dev); + void (*get_strings)(struct phy_device *dev, u8 *data); + void (*get_stats)(struct phy_device *dev, + struct ethtool_stats *stats, u64 *data); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) -- cgit v1.2.3 From d76eebfa175e86383324ad2bbaf472866950398b Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 1 Jan 2016 02:07:09 +0100 Subject: include/linux/property.h: fix build issues with gcc-4.4.4 gcc-4.4.4 has problems with initialization of anonymous unions: drivers/mfd/intel-lpss-acpi.c:30: error: unknown field 'value' specified in initializer work around this by crafting the initializers in a manner which the compiler can handle. Signed-off-by: Andrew Morton Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 3a8c7d7773e6..b8c4e420fe87 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -175,12 +175,19 @@ struct property_entry { }; }; +/* + * Note: the below four initializers for the anonymous union are carefully + * crafted to avoid gcc-4.4.4's problems with initialization of anon unions + * and structs. + */ + #define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_) \ { \ .name = _name_, \ .length = ARRAY_SIZE(_val_) * sizeof(_type_), \ .is_array = true, \ - .pointer._type_##_data = _val_, \ + .is_string = false, \ + { .pointer = { _type_##_data = _val_ } }, \ } #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ @@ -198,14 +205,15 @@ struct property_entry { .length = ARRAY_SIZE(_val_) * sizeof(const char *), \ .is_array = true, \ .is_string = true, \ - .pointer.str = _val_, \ + { .pointer = { .str = _val_ } }, \ } #define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_) \ { \ .name = _name_, \ .length = sizeof(_type_), \ - .value._type_##_data = _val_, \ + .is_string = false, \ + { .value = { ._type_##_data = _val_ } }, \ } #define PROPERTY_ENTRY_U8(_name_, _val_) \ @@ -222,7 +230,7 @@ struct property_entry { .name = _name_, \ .length = sizeof(_val_), \ .is_string = true, \ - .value.str = _val_, \ + { .value = {.str = _val_} }, \ } #define PROPERTY_ENTRY_BOOL(_name_) \ -- cgit v1.2.3 From aace7367bf83aef7baa021c7bcc9d2e331b040aa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 29 Dec 2015 13:07:48 +0200 Subject: device property: add spaces to PROPERTY_ENTRY_STRING macro Just a style fix, no functional changes. Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index b8c4e420fe87..b51fcd36d892 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -230,7 +230,7 @@ struct property_entry { .name = _name_, \ .length = sizeof(_val_), \ .is_string = true, \ - { .value = {.str = _val_} }, \ + { .value = { .str = _val_ } }, \ } #define PROPERTY_ENTRY_BOOL(_name_) \ -- cgit v1.2.3 From 55a93417c27c6ad1022d5f1121004c494735e8fa Mon Sep 17 00:00:00 2001 From: Christophe RICARD Date: Wed, 23 Dec 2015 23:25:33 +0100 Subject: ACPI: Rename acpi_gsi_get_irq_type to acpi_dev_get_irq_type and export symbol acpi_gsi_get_irq_type could be use out of GSI purpose. Rename and make it available as a resource function. Acked-by: Mika Westerberg Signed-off-by: Christophe Ricard Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1991aea2ec4c..42adb80f11ca 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -318,6 +318,7 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares, bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); +unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); -- cgit v1.2.3 From 41669da03060c5e55e9d3061ddede624f01d7262 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 27 Dec 2015 00:23:48 +0100 Subject: cpufreq: Make cpufreq_boost_supported() static cpufreq_boost_supported() is not used outside of cpufreq.c, so make it static. While at it, refactor it as a one-liner (which it really is). Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 177c7680c1a8..f859b728d98e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -574,7 +574,6 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); #ifdef CONFIG_CPU_FREQ int cpufreq_boost_trigger_state(int state); -int cpufreq_boost_supported(void); int cpufreq_boost_enabled(void); int cpufreq_enable_boost_support(void); bool policy_has_boost_freq(struct cpufreq_policy *policy); @@ -583,10 +582,6 @@ static inline int cpufreq_boost_trigger_state(int state) { return 0; } -static inline int cpufreq_boost_supported(void) -{ - return 0; -} static inline int cpufreq_boost_enabled(void) { return 0; -- cgit v1.2.3 From 7a6c79f2fe53dac9b7b290f3a4c56b0958e19201 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 27 Dec 2015 00:27:38 +0100 Subject: cpufreq: Simplify core code related to boost support Notice that the boost_supported field in struct cpufreq_driver is redundant, because the driver's ->set_boost callback may be left unset if "boost" is not supported. Moreover, the only driver populating the ->set_boost callback is acpi_cpufreq, so make it avoid populating that callback if "boost" is not supported, rework the core to check ->set_boost instead of boost_supported to verify "boost" support and drop boost_supported which isn't 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/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f859b728d98e..88a4215125bc 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -278,7 +278,6 @@ struct cpufreq_driver { struct freq_attr **attr; /* platform specific boost support code */ - bool boost_supported; bool boost_enabled; int (*set_boost)(int state); }; -- cgit v1.2.3 From 54dbc15172375641ef03399e8f911d7165eb90fb Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Sat, 19 Dec 2015 00:55:59 -0800 Subject: vfs: hoist the btrfs deduplication ioctl to the vfs Hoist the btrfs EXTENT_SAME ioctl up to the VFS and make the name more systematic (FIDEDUPERANGE). Signed-off-by: Darrick J. Wong Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 5d987aefcf1e..d71814b81a3c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1633,6 +1633,8 @@ struct file_operations { loff_t, size_t, unsigned int); int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, + u64); }; struct inode_operations { @@ -1688,6 +1690,8 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); +extern int vfs_dedupe_file_range(struct file *file, + struct file_dedupe_range *same); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); -- cgit v1.2.3 From 600c395bf6c4e44ec831e850d7f93ce53d7373be Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Wed, 23 Dec 2015 22:59:55 +0100 Subject: powercap: constify powercap_zone_ops and powercap_zone_constraint_ops structures The powercap_zone_ops and powercap_zone_constraint_ops structures are never modified, so declare them as const. Most of the actual changes adjust indentation to accomodate the const keyword. Done with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: Rafael J. Wysocki --- include/linux/powercap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/powercap.h b/include/linux/powercap.h index 4e250417ee30..f0a4e6257dcc 100644 --- a/include/linux/powercap.h +++ b/include/linux/powercap.h @@ -208,7 +208,7 @@ struct powercap_zone_constraint_ops { struct powercap_zone_constraint { int id; struct powercap_zone *power_zone; - struct powercap_zone_constraint_ops *ops; + const struct powercap_zone_constraint_ops *ops; }; @@ -309,7 +309,7 @@ struct powercap_zone *powercap_register_zone( struct powercap_zone *parent, const struct powercap_zone_ops *ops, int nr_constraints, - struct powercap_zone_constraint_ops *const_ops); + const struct powercap_zone_constraint_ops *const_ops); /** * powercap_unregister_zone() - Unregister a zone device -- cgit v1.2.3 From f1e80c07416adacc9ba1d9c5a4635c27b571f0df Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Wed, 7 Oct 2015 11:10:39 +0200 Subject: leds: core: Add two new LED_BLINK_ flags This patch adds LED_BLINK_BRIGHTNESS_CHANGE flag to indicate that blink brightness has changed, and LED_BLINK_DISABLE flag to indicate that blinking deactivation has been requested. In order to use the flags led_timer_function and set_brightness_delayed callbacks as well as led_set_brightness() function are being modified. The main goal of these modifications is to prepare set_brightness_work for extension of the scope of its responsibilities. Signed-off-by: Jacek Anaszewski Acked-by: Pavel Machek Acked-by: Sakari Ailus --- include/linux/leds.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index fa359c79c825..7b67450234a9 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -44,10 +44,12 @@ struct led_classdev { #define LED_BLINK_ONESHOT (1 << 17) #define LED_BLINK_ONESHOT_STOP (1 << 18) #define LED_BLINK_INVERT (1 << 19) -#define LED_SYSFS_DISABLE (1 << 20) -#define SET_BRIGHTNESS_ASYNC (1 << 21) -#define SET_BRIGHTNESS_SYNC (1 << 22) -#define LED_DEV_CAP_FLASH (1 << 23) +#define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20) +#define LED_BLINK_DISABLE (1 << 21) +#define LED_SYSFS_DISABLE (1 << 22) +#define SET_BRIGHTNESS_ASYNC (1 << 23) +#define SET_BRIGHTNESS_SYNC (1 << 24) +#define LED_DEV_CAP_FLASH (1 << 25) /* Set LED brightness level */ /* Must not sleep, use a workqueue if needed */ -- cgit v1.2.3 From 437a4240f26461610cc0d90950b1c88348d9babe Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Wed, 7 Oct 2015 11:10:40 +0200 Subject: leds: Rename brightness_set_sync op to brightness_set_blocking The initial purpose of brightness_set_sync op, introduced along with the LED flash class extension, was to add a means for setting torch LED brightness as soon as possible, which couldn't have been guaranteed by brightness_set op. This patch renames the op to brightness_set_blocking, which describes its purpose in a more generic way. It is beneficial in view of the prospective changes in the LED core, aiming at removing the need for using work queues in LED class drivers that can sleep or use delays while setting brightness. Signed-off-by: Jacek Anaszewski Acked-by: Andrew Lunn Acked-by: Pavel Machek Acked-by: Sakari Ailus --- include/linux/leds.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 7b67450234a9..403fa8690295 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -59,8 +59,8 @@ struct led_classdev { * Set LED brightness level immediately - it can block the caller for * the time required for accessing a LED device register. */ - int (*brightness_set_sync)(struct led_classdev *led_cdev, - enum led_brightness brightness); + int (*brightness_set_blocking)(struct led_classdev *led_cdev, + enum led_brightness brightness); /* Get LED brightness level */ enum led_brightness (*brightness_get)(struct led_classdev *led_cdev); -- cgit v1.2.3 From 1afcadfcd184c3b52e38bae15c247a5fa4a0e054 Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Mon, 19 Oct 2015 09:04:01 +0200 Subject: leds: core: Use set_brightness_work for the blocking op This patch makes LED core capable of setting brightness for drivers that implement brightness_set_blocking op. It removes from LED class drivers responsibility for using work queues on their own. In order to achieve this set_brightness_delayed callback is being modified to directly call one of available ops for brightness setting. led_set_brightness_async() function didn't set brightness in an asynchronous way in all cases. It was mistakenly assuming that all LED subsystem drivers used work queue in their brightness_set op, whereas only half of them did that. Since it has no users now, it is being removed. Signed-off-by: Jacek Anaszewski Acked-by: Sakari Ailus --- include/linux/leds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 403fa8690295..b35e0f5b8d6c 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -158,7 +158,7 @@ extern void led_blink_set_oneshot(struct led_classdev *led_cdev, * * Set an LED's brightness, and, if necessary, cancel the * software blink timer that implements blinking when the - * hardware doesn't. + * hardware doesn't. This function is guaranteed not to sleep. */ extern void led_set_brightness(struct led_classdev *led_cdev, enum led_brightness brightness); -- cgit v1.2.3 From 13ae79bbe4c214047f51623304d83b46eb02897d Mon Sep 17 00:00:00 2001 From: Jacek Anaszewski Date: Wed, 7 Oct 2015 11:10:43 +0200 Subject: leds: core: Drivers shouldn't enforce SYNC/ASYNC brightness setting This patch removes SET_BRIGHTNESS_ASYNC and SET_BRIGHTNESS_SYNC flags. led_set_brightness() now calls led_set_brightness_nosleep() instead of choosing between sync and async op basing on the flags defined by the driver. From now on, if a user wants to make sure that brightness will be set synchronously, they have to use led_set_brightness_sync() API. It is now being made publicly available since it has become apparent that it is a caller who should decide whether brightness is to be set in a synchronous or an asynchronous way. Signed-off-by: Jacek Anaszewski Acked-by: Sakari Ailus --- include/linux/leds.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index b35e0f5b8d6c..088f1da02bed 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -47,9 +47,7 @@ struct led_classdev { #define LED_BLINK_BRIGHTNESS_CHANGE (1 << 20) #define LED_BLINK_DISABLE (1 << 21) #define LED_SYSFS_DISABLE (1 << 22) -#define SET_BRIGHTNESS_ASYNC (1 << 23) -#define SET_BRIGHTNESS_SYNC (1 << 24) -#define LED_DEV_CAP_FLASH (1 << 25) +#define LED_DEV_CAP_FLASH (1 << 23) /* Set LED brightness level */ /* Must not sleep, use a workqueue if needed */ @@ -162,6 +160,21 @@ extern void led_blink_set_oneshot(struct led_classdev *led_cdev, */ extern void led_set_brightness(struct led_classdev *led_cdev, enum led_brightness brightness); + +/** + * led_set_brightness_sync - set LED brightness synchronously + * @led_cdev: the LED to set + * @brightness: the brightness to set it to + * + * Set an LED's brightness immediately. This function will block + * the caller for the time required for accessing device registers, + * and it can sleep. + * + * Returns: 0 on success or negative error value on failure + */ +extern int led_set_brightness_sync(struct led_classdev *led_cdev, + enum led_brightness value); + /** * led_update_brightness - update LED brightness * @led_cdev: the LED to query -- cgit v1.2.3 From 0dd756f7677a519a1d52a94e74d179e0af39e2ec Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 20 Aug 2015 12:59:45 +0200 Subject: leds: wm8350: Remove work queue Now the core implements the work queue, remove it from the drivers, and switch to using brightness_set_blocking op. Signed-off-by: Andrew Lunn Signed-off-by: Jacek Anaszewski Acked-by: Antonio Ospite Reviewed-by: Mark Brown --- include/linux/mfd/wm8350/pmic.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8350/pmic.h b/include/linux/mfd/wm8350/pmic.h index 579b50ca2e02..7a09e7f1f984 100644 --- a/include/linux/mfd/wm8350/pmic.h +++ b/include/linux/mfd/wm8350/pmic.h @@ -715,7 +715,6 @@ struct wm8350_led_platform_data { struct wm8350_led { struct platform_device *pdev; - struct mutex mutex; struct work_struct work; spinlock_t value_lock; enum led_brightness value; -- cgit v1.2.3 From 9534cc31dda2bb129480ce2db92bf7bc1ef470ed Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 2 Jan 2016 01:36:41 +0100 Subject: leds: core: add managed version of led_trigger_register Complementing devm_led_classdev_register add a managed version of led_trigger_register. I omit a managed version of led_classdev_unregister as the equivalent devm_led_classdev_unregister isn't used in the kernel as of today. Signed-off-by: Heiner Kallweit Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 088f1da02bed..bc1476fda96e 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -246,6 +246,8 @@ ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr, /* Registration functions for complex triggers */ extern int led_trigger_register(struct led_trigger *trigger); extern void led_trigger_unregister(struct led_trigger *trigger); +extern int devm_led_trigger_register(struct device *dev, + struct led_trigger *trigger); extern void led_trigger_register_simple(const char *name, struct led_trigger **trigger); -- cgit v1.2.3 From 03607ace807b414eab46323c794b6fb8fcc2d48c Mon Sep 17 00:00:00 2001 From: Pantelis Antoniou Date: Thu, 22 Oct 2015 23:30:04 +0300 Subject: configfs: implement binary attributes ConfigFS lacked binary attributes up until now. This patch introduces support for binary attributes in a somewhat similar manner of sysfs binary attributes albeit with changes that fit the configfs usage model. Problems that configfs binary attributes fix are everything that requires a binary blob as part of the configuration of a resource, such as bitstream loading for FPGAs, DTBs for dynamically created devices etc. Look at Documentation/filesystems/configfs/configfs.txt for internals and howto use them. This patch is against linux-next as of today that contains Christoph's configfs rework. Signed-off-by: Pantelis Antoniou [hch: folded a fix from Geert Uytterhoeven ] [hch: a few tiny updates based on review feedback] Signed-off-by: Christoph Hellwig --- include/linux/configfs.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) (limited to 'include/linux') diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 758a029011b1..f7300d023dbe 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -51,6 +51,7 @@ struct module; struct configfs_item_operations; struct configfs_group_operations; struct configfs_attribute; +struct configfs_bin_attribute; struct configfs_subsystem; struct config_item { @@ -84,6 +85,7 @@ struct config_item_type { struct configfs_item_operations *ct_item_ops; struct configfs_group_operations *ct_group_ops; struct configfs_attribute **ct_attrs; + struct configfs_bin_attribute **ct_bin_attrs; }; /** @@ -154,6 +156,54 @@ static struct configfs_attribute _pfx##attr_##_name = { \ .store = _pfx##_name##_store, \ } +struct file; +struct vm_area_struct; + +struct configfs_bin_attribute { + struct configfs_attribute cb_attr; /* std. attribute */ + void *cb_private; /* for user */ + size_t cb_max_size; /* max core size */ + ssize_t (*read)(struct config_item *, void *, size_t); + ssize_t (*write)(struct config_item *, const void *, size_t); +}; + +#define CONFIGFS_BIN_ATTR(_pfx, _name, _priv, _maxsz) \ +static struct configfs_bin_attribute _pfx##attr_##_name = { \ + .cb_attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO | S_IWUSR, \ + .ca_owner = THIS_MODULE, \ + }, \ + .cb_private = _priv, \ + .cb_max_size = _maxsz, \ + .read = _pfx##_name##_read, \ + .write = _pfx##_name##_write, \ +} + +#define CONFIGFS_BIN_ATTR_RO(_pfx, _name, _priv, _maxsz) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .cb_attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO, \ + .ca_owner = THIS_MODULE, \ + }, \ + .cb_private = _priv, \ + .cb_max_size = _maxsz, \ + .read = _pfx##_name##_read, \ +} + +#define CONFIGFS_BIN_ATTR_WO(_pfx, _name, _priv, _maxsz) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .cb_attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IWUSR, \ + .ca_owner = THIS_MODULE, \ + }, \ + .cb_private = _priv, \ + .cb_max_size = _maxsz, \ + .write = _pfx##_name##_write, \ +} + /* * If allow_link() exists, the item can symlink(2) out to other * items. If the item is a group, it may support mkdir(2). -- cgit v1.2.3 From e9d408e107db9a554b36c3a79f67b37dd3e16da0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 24 Dec 2015 00:06:05 -0500 Subject: new helper: memdup_user_nul() Similar to memdup_user(), except that allocated buffer is one byte longer and '\0' is stored after the copied data. Signed-off-by: Al Viro --- include/linux/string.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 9ef7795e65e4..9eebc66d957a 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -10,6 +10,7 @@ extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t); +extern void *memdup_user_nul(const void __user *, size_t); /* * Include machine specific inline routines -- cgit v1.2.3 From 98dd64f34f47ce19b388d9015f767f48393a81eb Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 4 Jan 2016 15:37:32 +0100 Subject: ARM: 8478/2: arm/arm64: add arm-smccc Adds helpers to do SMC and HVC based on ARM SMC Calling Convention. CONFIG_HAVE_ARM_SMCCC is enabled for architectures that may support the SMC or HVC instruction. It's the responsibility of the caller to know if the SMC instruction is supported by the platform. This patch doesn't provide an implementation of the declared functions. Later patches will bring in implementations and set CONFIG_HAVE_ARM_SMCCC for ARM and ARM64 respectively. Reviewed-by: Lorenzo Pieralisi Signed-off-by: Jens Wiklander Signed-off-by: Russell King --- include/linux/arm-smccc.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) create mode 100644 include/linux/arm-smccc.h (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h new file mode 100644 index 000000000000..b5abfda80465 --- /dev/null +++ b/include/linux/arm-smccc.h @@ -0,0 +1,104 @@ +/* + * Copyright (c) 2015, Linaro Limited + * + * 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 __LINUX_ARM_SMCCC_H +#define __LINUX_ARM_SMCCC_H + +#include +#include + +/* + * This file provides common defines for ARM SMC Calling Convention as + * specified in + * http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html + */ + +#define ARM_SMCCC_STD_CALL 0 +#define ARM_SMCCC_FAST_CALL 1 +#define ARM_SMCCC_TYPE_SHIFT 31 + +#define ARM_SMCCC_SMC_32 0 +#define ARM_SMCCC_SMC_64 1 +#define ARM_SMCCC_CALL_CONV_SHIFT 30 + +#define ARM_SMCCC_OWNER_MASK 0x3F +#define ARM_SMCCC_OWNER_SHIFT 24 + +#define ARM_SMCCC_FUNC_MASK 0xFFFF + +#define ARM_SMCCC_IS_FAST_CALL(smc_val) \ + ((smc_val) & (ARM_SMCCC_FAST_CALL << ARM_SMCCC_TYPE_SHIFT)) +#define ARM_SMCCC_IS_64(smc_val) \ + ((smc_val) & (ARM_SMCCC_SMC_64 << ARM_SMCCC_CALL_CONV_SHIFT)) +#define ARM_SMCCC_FUNC_NUM(smc_val) ((smc_val) & ARM_SMCCC_FUNC_MASK) +#define ARM_SMCCC_OWNER_NUM(smc_val) \ + (((smc_val) >> ARM_SMCCC_OWNER_SHIFT) & ARM_SMCCC_OWNER_MASK) + +#define ARM_SMCCC_CALL_VAL(type, calling_convention, owner, func_num) \ + (((type) << ARM_SMCCC_TYPE_SHIFT) | \ + ((calling_convention) << ARM_SMCCC_CALL_CONV_SHIFT) | \ + (((owner) & ARM_SMCCC_OWNER_MASK) << ARM_SMCCC_OWNER_SHIFT) | \ + ((func_num) & ARM_SMCCC_FUNC_MASK)) + +#define ARM_SMCCC_OWNER_ARCH 0 +#define ARM_SMCCC_OWNER_CPU 1 +#define ARM_SMCCC_OWNER_SIP 2 +#define ARM_SMCCC_OWNER_OEM 3 +#define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_TRUSTED_APP 48 +#define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 +#define ARM_SMCCC_OWNER_TRUSTED_OS 50 +#define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 + +/** + * struct arm_smccc_res - Result from SMC/HVC call + * @a0-a3 result values from registers 0 to 3 + */ +struct arm_smccc_res { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; +}; + +/** + * arm_smccc_smc() - make SMC calls + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This function is used to make SMC calls following SMC Calling Convention. + * The content of the supplied param are copied to registers 0 to 7 prior + * to the SMC instruction. The return values are updated with the content + * from register 0 to 3 on return from the SMC instruction. + */ +asmlinkage void arm_smccc_smc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res); + +/** + * arm_smccc_hvc() - make HVC calls + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This function is used to make HVC calls following SMC Calling + * Convention. The content of the supplied param are copied to registers 0 + * to 7 prior to the HVC instruction. The return values are updated with + * the content from register 0 to 3 on return from the HVC instruction. + */ +asmlinkage void arm_smccc_hvc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res); + +#endif /*__LINUX_ARM_SMCCC_H*/ -- cgit v1.2.3 From 888cc8c20cf265fcd1302f6c5d6be07628ba66c7 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Mon, 28 Dec 2015 02:07:08 +0300 Subject: sh_eth: remove EDMAC_BIG_ENDIAN Commit 71557a37adb5 ("[netdrvr] sh_eth: Add SH7619 support") added support for the big-endian EDMAC descriptors. However, it was never used and never worked right until the recent driver fixes. I think we now can just remove this support, it was only burdening the driver from the start. It should be easy to do without disturbing the SH platform code, at least for now... Signed-off-by: Sergei Shtylyov Acked-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/sh_eth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 8c9131db2b25..f2e27e078362 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -4,7 +4,7 @@ #include #include -enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; +enum {EDMAC_LITTLE_ENDIAN}; struct sh_eth_plat_data { int phy; -- cgit v1.2.3 From 538950a1b7527a0a52ccd9337e3fcd304f027f13 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Mon, 4 Jan 2016 17:41:47 -0500 Subject: soreuseport: setsockopt SO_ATTACH_REUSEPORT_[CE]BPF Expose socket options for setting a classic or extended BPF program for use when selecting sockets in an SO_REUSEPORT group. These options can be used on the first socket to belong to a group before bind or on any socket in the group after bind. This change includes refactoring of the existing sk_filter code to allow reuse of the existing BPF filter validation checks. Signed-off-by: Craig Gallek Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4165e9ac9e36..294c3cdf07b3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -447,6 +447,8 @@ void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); +int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); +int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); -- cgit v1.2.3 From 01a999e48995a35faaa513f811c335bce72917d6 Mon Sep 17 00:00:00 2001 From: Jaehoon Chung Date: Thu, 24 Dec 2015 18:41:03 +0900 Subject: mmc: dw_mmc: remove the unused quirks Removed the unused quirks. These quirks don't used anywhere. Signed-off-by: Jaehoon Chung Signed-off-by: Ulf Hansson --- include/linux/mmc/dw_mmc.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 7776afb0ffa5..89df7abedd67 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -235,16 +235,10 @@ struct dw_mci_dma_ops { }; /* IP Quirks/flags. */ -/* DTO fix for command transmission with IDMAC configured */ -#define DW_MCI_QUIRK_IDMAC_DTO BIT(0) -/* delay needed between retries on some 2.11a implementations */ -#define DW_MCI_QUIRK_RETRY_DELAY BIT(1) -/* High Speed Capable - Supports HS cards (up to 50MHz) */ -#define DW_MCI_QUIRK_HIGHSPEED BIT(2) /* Unreliable card detection */ -#define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) +#define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(0) /* Timer for broken data transfer over scheme */ -#define DW_MCI_QUIRK_BROKEN_DTO BIT(4) +#define DW_MCI_QUIRK_BROKEN_DTO BIT(1) struct dma_pdata; -- cgit v1.2.3 From 7a78479fd2acd25db7ecd1744d76f6841ec8a257 Mon Sep 17 00:00:00 2001 From: Laxman Dewangan Date: Tue, 22 Dec 2015 18:25:26 +0530 Subject: regmap: irq: add support for configuration of trigger type Some of devices supports the trigger level for interrupt like rising/falling edge specially for GPIOs. The interrupt support of such devices may have uses the generic regmap irq framework for implementation. Add support to configure the trigger type device interrupt register via regmap-irq framework. The regmap-irq framework configures the trigger register only if the details of trigger type registers are provided. [Fixed use of terery operator for legibility -- broonie] Signed-off-by: Laxman Dewangan Signed-off-by: Mark Brown --- include/linux/regmap.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index d68bb402120e..95b6636d3a59 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -788,10 +788,16 @@ int regmap_fields_update_bits(struct regmap_field *field, unsigned int id, * * @reg_offset: Offset of the status/mask register within the bank * @mask: Mask used to flag/control the register. + * @type_reg_offset: Offset register for the irq type setting. + * @type_rising_mask: Mask bit to configure RISING type irq. + * @type_falling_mask: Mask bit to configure FALLING type irq. */ struct regmap_irq { unsigned int reg_offset; unsigned int mask; + unsigned int type_reg_offset; + unsigned int type_rising_mask; + unsigned int type_falling_mask; }; #define REGMAP_IRQ_REG(_irq, _off, _mask) \ @@ -811,18 +817,23 @@ struct regmap_irq { * @ack_base: Base ack address. If zero then the chip is clear on read. * Using zero value is possible with @use_ack bit. * @wake_base: Base address for wake enables. If zero unsupported. + * @type_base: Base address for irq type. If zero unsupported. * @irq_reg_stride: Stride to use for chips where registers are not contiguous. * @init_ack_masked: Ack all masked interrupts once during initalization. * @mask_invert: Inverted mask register: cleared bits are masked out. * @use_ack: Use @ack register even if it is zero. * @ack_invert: Inverted ack register: cleared bits for ack. * @wake_invert: Inverted wake register: cleared bits are wake enabled. + * @type_invert: Invert the type flags. * @runtime_pm: Hold a runtime PM lock on the device when accessing it. * * @num_regs: Number of registers in each control bank. * @irqs: Descriptors for individual IRQs. Interrupt numbers are * assigned based on the index in the array of the interrupt. * @num_irqs: Number of descriptors. + * @num_type_reg: Number of type registers. + * @type_reg_stride: Stride to use for chips where type registers are not + * contiguous. */ struct regmap_irq_chip { const char *name; @@ -832,6 +843,7 @@ struct regmap_irq_chip { unsigned int unmask_base; unsigned int ack_base; unsigned int wake_base; + unsigned int type_base; unsigned int irq_reg_stride; bool init_ack_masked:1; bool mask_invert:1; @@ -839,11 +851,15 @@ struct regmap_irq_chip { bool ack_invert:1; bool wake_invert:1; bool runtime_pm:1; + bool type_invert:1; int num_regs; const struct regmap_irq *irqs; int num_irqs; + + int num_type_reg; + unsigned int type_reg_stride; }; struct regmap_irq_chip_data; -- cgit v1.2.3 From b0844444590e18704644f707ea88bff1b976b0e7 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Tue, 29 Dec 2015 14:58:30 +0200 Subject: net/mlx5_core: Introduce access function to read internal timer A preparation step which adds support for reading the hardware internal timer and the hardware timestamping from the CQE. In addition, advertize device_frequency_khz HCA capability. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 20 +++++++++++++++++--- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 7d3a85faefb7..df2f79ef3cac 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -443,9 +443,12 @@ struct mlx5_init_seg { __be32 rsvd1[120]; __be32 initializing; struct health_buffer health; - __be32 rsvd2[884]; + __be32 rsvd2[880]; + __be32 internal_timer_h; + __be32 internal_timer_l; + __be32 rsrv3[2]; __be32 health_counter; - __be32 rsvd3[1019]; + __be32 rsvd4[1019]; __be64 ieee1588_clk; __be32 ieee1588_clk_type; __be32 clr_intx; @@ -601,7 +604,8 @@ struct mlx5_cqe64 { __be32 imm_inval_pkey; u8 rsvd40[4]; __be32 byte_cnt; - __be64 timestamp; + __be32 timestamp_h; + __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; u8 signature; @@ -623,6 +627,16 @@ static inline int cqe_has_vlan(struct mlx5_cqe64 *cqe) return !!(cqe->l4_hdr_type_etc & 0x1); } +static inline u64 get_cqe_ts(struct mlx5_cqe64 *cqe) +{ + u32 hi, lo; + + hi = be32_to_cpu(cqe->timestamp_h); + lo = be32_to_cpu(cqe->timestamp_l); + + return (u64)lo | ((u64)hi << 32); +} + enum { CQE_L4_HDR_TYPE_NONE = 0x0, CQE_L4_HDR_TYPE_TCP_NO_ACK = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 131a2737cfa3..1780a85a8797 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -829,9 +829,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_66[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_67[0xe0]; - - u8 reserved_68[0x1f]; + u8 reserved_67[0x40]; + u8 device_frequency_khz[0x20]; + u8 reserved_68[0x5f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; -- cgit v1.2.3 From 67b9bcd36906e12a15ffec19463afbbd6a41660e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 15 Dec 2015 10:48:20 -0800 Subject: mtd: spi-nor: fix Spansion regressions (aliased with Winbond) Spansion and Winbond have occasionally used the same manufacturer ID, and they don't support the same features. Particularly, writing SR=0 seems to break read access for Spansion's s25fl064k. Unfortunately, we don't currently have a way to differentiate these Spansion and Winbond parts, so rather than regressing support for these Spansion flash, let's drop the new Winbond lock/unlock support for now. We can try to address Winbond support during the next release cycle. Original discussion: http://patchwork.ozlabs.org/patch/549173/ http://patchwork.ozlabs.org/patch/553683/ Fixes: 357ca38d4751 ("mtd: spi-nor: support lock/unlock/is_locked for Winbond") Fixes: c6fc2171b249 ("mtd: spi-nor: disable protection for Winbond flash at startup") Signed-off-by: Brian Norris Reported-by: Felix Fietkau Cc: Felix Fietkau --- include/linux/mtd/spi-nor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c8723b62c4cd..bc742dac7d3a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -25,7 +25,7 @@ #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -#define SNOR_MFR_WINBOND 0xef +#define SNOR_MFR_WINBOND 0xef /* Also used by some Spansion */ /* * Note on opcode nomenclature: some opcodes have a format like -- cgit v1.2.3 From 570f52412ae9432c56897472791ea8db420cbaf1 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Fri, 1 Jan 2016 23:03:01 +0900 Subject: sched/core: Check tgid in is_global_init() Our global init task can have sub-threads, so ->pid check is not reliable enough for is_global_init(), we need to check tgid instead. This has been spotted by Oleg and a fix was proposed by Richard a long time ago (see the link below). Oleg wrote: : Because is_global_init() is only true for the main thread of /sbin/init. : : Just look at oom_unkillable_task(). It tries to not kill init. But, say, : select_bad_process() can happily find a sub-thread of is_global_init() : and still kill it. I recently hit the problem in question; re-sending the patch (to the best of my knowledge it has never been submitted) with updated function comment. Credit goes to Oleg and Richard. Suggested-by: Richard Guy Briggs Reported-by: Oleg Nesterov Signed-off-by: Sergey Senozhatsky Signed-off-by: Peter Zijlstra (Intel) Acked-by: Serge Hallyn Cc: Andrew Morton Cc: Eric W . Biederman Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Serge E . Hallyn Cc: Sergey Senozhatsky Cc: Thomas Gleixner Link: https://www.redhat.com/archives/linux-audit/2013-December/msg00086.html Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..9cf9dd1c4cbe 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2002,7 +2002,8 @@ static inline int pid_alive(const struct task_struct *p) } /** - * is_global_init - check if a task structure is init + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. @@ -2011,7 +2012,7 @@ static inline int pid_alive(const struct task_struct *p) */ static inline int is_global_init(struct task_struct *tsk) { - return tsk->pid == 1; + return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; -- cgit v1.2.3 From be958bdc96f18bc1356177bbb79d46ea0c037b96 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 25 Nov 2015 16:02:07 +0100 Subject: sched/core: Fix unserialized r-m-w scribbling stuff Some of the sched bitfieds (notably sched_reset_on_fork) can be set on other than current, this can cause the r-m-w to race with other updates. Since all the sched bits are serialized by scheduler locks, pull them in a separate word. Reported-by: Tejun Heo Signed-off-by: Peter Zijlstra (Intel) Cc: Dmitry Vyukov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Sasha Levin Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: hannes@cmpxchg.org Cc: mhocko@kernel.org Cc: vdavydov@parallels.com Link: http://lkml.kernel.org/r/20151125150207.GM11639@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9cf9dd1c4cbe..fa39434e3fdd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1455,14 +1455,15 @@ struct task_struct { /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; - unsigned in_execve:1; /* Tell the LSMs that the process is doing an - * execve */ - unsigned in_iowait:1; - - /* Revert to default priority/policy when forking */ + /* scheduler bits, serialized by scheduler locks */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned :0; /* force alignment to the next boundary */ + + /* unserialized, strictly 'current' */ + unsigned in_execve:1; /* bit to tell LSMs we're in execve */ + unsigned in_iowait:1; #ifdef CONFIG_MEMCG unsigned memcg_may_oom:1; #endif -- cgit v1.2.3 From 5a1078043f844074cbd53981432778a8d5dd56e9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 8 Dec 2015 21:23:59 +0100 Subject: sched/core: Move sched_entity::avg into separate cache line The sched_entity::avg collides with read-mostly sched_entity data. The perf c2c tool showed many read HITM accesses across many CPUs for sched_entity's cfs_rq and my_q, while having at the same time tons of stores for avg. After placing sched_entity::avg into separate cache line, the perf bench sched pipe showed around 20 seconds speedup. NOTE I cut out all perf events except for cycles and instructions from following output. Before: $ perf stat -r 5 perf bench sched pipe -l 10000000 # Running 'sched/pipe' benchmark: # Executed 10000000 pipe operations between two processes Total time: 270.348 [sec] 27.034805 usecs/op 36989 ops/sec ... 245,537,074,035 cycles # 1.433 GHz 187,264,548,519 instructions # 0.77 insns per cycle 272.653840535 seconds time elapsed ( +- 1.31% ) After: $ perf stat -r 5 perf bench sched pipe -l 10000000 # Running 'sched/pipe' benchmark: # Executed 10000000 pipe operations between two processes Total time: 251.076 [sec] 25.107678 usecs/op 39828 ops/sec ... 244,573,513,928 cycles # 1.572 GHz 187,409,641,157 instructions # 0.76 insns per cycle 251.679315188 seconds time elapsed ( +- 0.31% ) Signed-off-by: Jiri Olsa Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Don Zickus Cc: Joe Mario Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1449606239-28602-1-git-send-email-jolsa@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 791b47e40317..0c0e78102850 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1268,8 +1268,13 @@ struct sched_entity { #endif #ifdef CONFIG_SMP - /* Per entity load average tracking */ - struct sched_avg avg; + /* + * Per entity load average tracking. + * + * Put into separate cache line so it does not + * collide with read-mostly values above. + */ + struct sched_avg avg ____cacheline_aligned_in_smp; #endif }; -- cgit v1.2.3 From cdba756f5803a2f0a8bbc6605acc166dd817979e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Jan 2016 06:53:50 -0800 Subject: net: move ndo_features_check() close to ndo_start_xmit() TX fast path uses ndo_start_xmit(), ndo_features_check() and ndo_select_queue(). Move ndo_features_check() close to ndo_start_xmit() to increase data locality. All "struct net_device_ops" should now be using C99 initializers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c20b814e46a0..8d8e5ca951b4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -812,6 +812,12 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * + * netdev_features_t (*ndo_fix_features)(struct net_device *dev, + * netdev_features_t features); + * Adjusts the requested feature flags according to device-specific + * constraints, and returns the resulting flags. Must not modify + * the device state. + * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple @@ -959,12 +965,6 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * Called to release previously enslaved netdev. * * Feature/offload setting functions. - * netdev_features_t (*ndo_fix_features)(struct net_device *dev, - * netdev_features_t features); - * Adjusts the requested feature flags according to device-specific - * constraints, and returns the resulting flags. Must not modify - * the device state. - * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). @@ -1081,8 +1081,11 @@ struct net_device_ops { void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); - netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, - struct net_device *dev); + netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, + struct net_device *dev); + netdev_features_t (*ndo_features_check)(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, void *accel_priv, @@ -1245,9 +1248,6 @@ struct net_device_ops { struct net_device *dev, void *priv); int (*ndo_get_lock_subclass)(struct net_device *dev); - netdev_features_t (*ndo_features_check) (struct sk_buff *skb, - struct net_device *dev, - netdev_features_t features); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); -- cgit v1.2.3 From c7f5d105495a38ed09e70d825f75d9d7d5407264 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 5 Nov 2015 11:34:57 -0500 Subject: net: Add eth_platform_get_mac_address() helper. A repeating pattern in drivers has become to use OF node information and, if not found, platform specific host information to extract the ethernet address for a given device. Currently this is done with a call to of_get_mac_address() and then some ifdef'd stuff for SPARC. Consolidate this into a portable routine, and provide the arch_get_platform_mac_address() weak function hook for all architectures to implement if they want. Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index eb049c622208..37ff4a6faa9a 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -29,6 +29,9 @@ #include #ifdef __KERNEL__ +struct device; +int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); +unsigned char *arch_get_platform_get_mac_address(void); u32 eth_get_headlen(void *data, unsigned int max_len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; -- cgit v1.2.3 From 4b83555d5098e73cf2c5ca7f86c17ca0ba3b968e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 6 Jan 2016 17:12:47 -0800 Subject: driver-core: platform: Add platform_irq_count() A recent patch added calls to of_irq_count() in the qcom pinctrl drivers and that caused module build failures because of_irq_count() is not an exported symbol. We shouldn't export of_irq_count() to modules because it's an internal OF API that shouldn't be used by drivers. Platform drivers should use platform device APIs instead. Therefore, add a platform_irq_count() API that mirrors the of_irq_count() API so that platform drivers can stay DT agnostic. Cc: Andy Gross Acked-by: Rob Herring Acked-by: Greg Kroah-Hartman Signed-off-by: Linus Walleij --- include/linux/platform_device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index dc777be5f2e1..6abd019c76f8 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -51,6 +51,7 @@ extern void arch_setup_pdev_archdata(struct platform_device *); extern struct resource *platform_get_resource(struct platform_device *, unsigned int, unsigned int); extern int platform_get_irq(struct platform_device *, unsigned int); +extern int platform_irq_count(struct platform_device *); extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, const char *); -- cgit v1.2.3 From 049fb9bd416077b3622d317a45796be4f2431df3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Tue, 5 Jan 2016 20:32:47 -0500 Subject: ftrace/module: Call clean up function when module init fails early If the module init code fails after calling ftrace_module_init() and before calling do_init_module(), we can suffer from a memory leak. This is because ftrace_module_init() allocates pages to store the locations that ftrace hooks are placed in the module text. If do_init_module() fails, it still calls the MODULE_GOING notifiers which will tell ftrace to do a clean up of the pages it allocated for the module. But if load_module() fails before then, the pages allocated by ftrace_module_init() will never be freed. Call ftrace_release_mod() on the module if load_module() fails before getting to do_init_module(). Link: http://lkml.kernel.org/r/567CEA31.1070507@intel.com Reported-by: "Qiu, PeiyangX" Fixes: a949ae560a511 "ftrace/module: Hardcode ftrace_module_init() call into load_module()" Cc: stable@vger.kernel.org # v2.6.38+ Acked-by: Rusty Russell Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eae6548efbf0..60048c50404e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -586,6 +586,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); -- cgit v1.2.3 From ccaa953e9fc7ebb90fba4e4815966683bef4866f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:06 +0100 Subject: phy: Consistently use addr for address on an MII bus Within phy.h, an address on an MII bus has been called both addr and phy_id. phy_id is particularly confusion, since it also means the ID found in register 3, if the device on the bus is a phy. Consistently use addr. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index a89cb0eef911..77b5e56e2a92 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -158,8 +158,8 @@ struct mii_bus { const char *name; char id[MII_BUS_ID_SIZE]; void *priv; - int (*read)(struct mii_bus *bus, int phy_id, int regnum); - int (*write)(struct mii_bus *bus, int phy_id, int regnum, u16 val); + int (*read)(struct mii_bus *bus, int addr, int regnum); + int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); int (*reset)(struct mii_bus *bus); /* -- cgit v1.2.3 From bac83c653799d7ea3f6cc4d7396d75adc5e0f778 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:07 +0100 Subject: mdio: Move mdiobus_read/write operatings into mdio.h These are logically MDIO operations, not phy operations, so move them into the mdio header. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 6 ++++++ include/linux/phy.h | 6 +----- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index b42963bc81dd..0d073c23c10d 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -11,6 +11,7 @@ #include +struct mii_bus; static inline bool mdio_phy_id_is_c45(int phy_id) { @@ -173,4 +174,9 @@ static inline u16 ethtool_adv_to_mmd_eee_adv_t(u32 adv) return reg; } +int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); +int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); +int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); + #endif /* __LINUX_MDIO_H__ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 77b5e56e2a92..8ca161a37e8a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -212,11 +213,6 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); -int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); -int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); -int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); -int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); - #define PHY_INTERRUPT_DISABLED 0x0 #define PHY_INTERRUPT_ENABLED 0x80000000 -- cgit v1.2.3 From 72ba48be3ec8e70937ad97d4420ef7144617c64b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:09 +0100 Subject: phy: Add phydev_err() and phydev_dbg() macros In preparation for moving some of the phy_device structure members, add macros for printing errors and debug information. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8ca161a37e8a..dbcf9fdd960c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -777,6 +777,12 @@ static inline int phy_read_status(struct phy_device *phydev) return phydev->drv->read_status(phydev); } +#define phydev_err(_phydev, format, args...) \ + dev_err(&_phydev->dev, format, ##args) + +#define phydev_dbg(_phydev, format, args...) \ + dev_dbg(&_phydev->dev, format, ##args) + int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From 84eff6d194df442bee62c129f2f47efb0dbd0468 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:10 +0100 Subject: phy: add phydev_name() wrapper Add a phydev_name() function, to help with moving some structure members from phy_device. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index dbcf9fdd960c..5f5cc3424b9e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -783,6 +783,11 @@ static inline int phy_read_status(struct phy_device *phydev) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->dev, format, ##args) +static inline const char *phydev_name(const struct phy_device *phydev) +{ + return dev_name(&phydev->dev); +} + int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From 053e7e169229adebbc27fc176c5369398e9f5eba Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:12 +0100 Subject: phy: phy_{read|write}_mmd_indirect: get addr from phydev The address of the device can be determined from the phydev structure, rather than passing it as a parameter. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 5f5cc3424b9e..08198ce98773 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -629,14 +629,12 @@ static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) * phy_read_mmd_indirect - reads data from the MMD registers * @phydev: The PHY device bus * @prtad: MMD Address - * @devad: MMD DEVAD * @addr: PHY address on the MII bus * * Description: it reads data from the MMD registers (clause 22 to access to * clause 45) of the specified phy address. */ -int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, - int devad, int addr); +int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad); /** * phy_read - Convenience function for reading a given PHY register @@ -735,14 +733,13 @@ static inline int phy_write_mmd(struct phy_device *phydev, int devad, * @phydev: The PHY device * @prtad: MMD Address * @devad: MMD DEVAD - * @addr: PHY address on the MII bus * @data: data to write in the MMD register * * Description: Write data from the MMD registers of the specified * phy address. */ void phy_write_mmd_indirect(struct phy_device *phydev, int prtad, - int devad, int addr, u32 data); + int devad, u32 data); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, bool is_c45, -- cgit v1.2.3 From 2220943a21e26d97d7fd8f83c004b947326b469d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:13 +0100 Subject: phy: Centralise print about attached phy Many Ethernet drivers contain the same netdev_info() print statement about the attached phy. Move it into the phy device code. Additionally add a varargs function which can be used to append additional information. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 08198ce98773..ecbf6382ba29 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -16,6 +16,7 @@ #ifndef __PHY_H #define __PHY_H +#include #include #include #include @@ -785,6 +786,9 @@ static inline const char *phydev_name(const struct phy_device *phydev) return dev_name(&phydev->dev); } +void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) + __printf(2, 3); +void phy_attached_info(struct phy_device *phydev); int genphy_config_init(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); -- cgit v1.2.3 From e7f4dc3536a40097f95103ddf98dd55b3a980f5b Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:15 +0100 Subject: mdio: Move allocation of interrupts into core Have mdio_alloc() create the array of interrupt numbers, and initialize it to POLLING. This is what most MDIO drivers want, so allowing code to be removed from the drivers. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index ecbf6382ba29..a5473c9e19de 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -189,10 +189,10 @@ struct mii_bus { u32 phy_ignore_ta_mask; /* - * Pointer to an array of interrupts, each PHY's - * interrupt at the index matching its address + * An array of interrupts, each PHY's interrupt at the index + * matching its address */ - int *irq; + int irq[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) -- cgit v1.2.3 From e5a03bfd873c29eb786655ef2e95e53ed242b404 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:16 +0100 Subject: phy: Add an mdio_device structure Not all devices attached to an MDIO bus are phys. So add an mdio_device structure to represent the generic parts of an mdio device, and place this structure into the phy_device. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/mdio.h | 9 +++++++++ include/linux/phy.h | 26 +++++++++++--------------- 2 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 0d073c23c10d..94f9f1491cde 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -13,6 +13,15 @@ struct mii_bus; +struct mdio_device { + struct device dev; + + struct mii_bus *bus; + /* Bus address of the MDIO device (0-31) */ + int addr; +}; +#define to_mdio_device(d) container_of(d, struct mdio_device, dev) + static inline bool mdio_phy_id_is_c45(int phy_id) { return (phy_id & MDIO_PHY_ID_C45) && !(phy_id & ~MDIO_PHY_ID_C45_MASK); diff --git a/include/linux/phy.h b/include/linux/phy.h index a5473c9e19de..239a0c2bc49d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -358,14 +358,12 @@ struct phy_c45_device_ids { * handling, as well as handling shifts in PHY hardware state */ struct phy_device { + struct mdio_device mdio; + /* Information about the PHY type */ /* And management functions */ struct phy_driver *drv; - struct mii_bus *bus; - - struct device dev; - u32 phy_id; struct phy_c45_device_ids c45_ids; @@ -381,9 +379,6 @@ struct phy_device { phy_interface_t interface; - /* Bus address of the PHY (0-31) */ - int addr; - /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) @@ -432,7 +427,8 @@ struct phy_device { void (*adjust_link)(struct net_device *dev); }; -#define to_phy_device(d) container_of(d, struct phy_device, dev) +#define to_phy_device(d) container_of(to_mdio_device(d), \ + struct phy_device, mdio) /* struct phy_driver: Driver structure for a particular PHY type * @@ -622,7 +618,7 @@ static inline int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) if (!phydev->is_c45) return -EOPNOTSUPP; - return mdiobus_read(phydev->bus, phydev->addr, + return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff)); } @@ -648,7 +644,7 @@ int phy_read_mmd_indirect(struct phy_device *phydev, int prtad, int devad); */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { - return mdiobus_read(phydev->bus, phydev->addr, regnum); + return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** @@ -663,7 +659,7 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum) */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { - return mdiobus_write(phydev->bus, phydev->addr, regnum, val); + return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** @@ -726,7 +722,7 @@ static inline int phy_write_mmd(struct phy_device *phydev, int devad, regnum = MII_ADDR_C45 | ((devad & 0x1f) << 16) | (regnum & 0xffff); - return mdiobus_write(phydev->bus, phydev->addr, regnum, val); + return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** @@ -776,14 +772,14 @@ static inline int phy_read_status(struct phy_device *phydev) } #define phydev_err(_phydev, format, args...) \ - dev_err(&_phydev->dev, format, ##args) + dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ - dev_dbg(&_phydev->dev, format, ##args) + dev_dbg(&_phydev->mdio.dev, format, ##args); static inline const char *phydev_name(const struct phy_device *phydev) { - return dev_name(&phydev->dev); + return dev_name(&phydev->mdio.dev); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) -- cgit v1.2.3 From 7f854420fbfe9d49afe2ffb1df052cfe8e215541 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:18 +0100 Subject: phy: Add API for {un}registering an mdio device to a bus. Rather than have drivers directly manipulate the mii_bus structure, provide and API for registering and unregistering devices on an MDIO bus, and performing lookups. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 8 ++++++++ include/linux/phy.h | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 94f9f1491cde..8cd9579e18ea 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -19,9 +19,12 @@ struct mdio_device { struct mii_bus *bus; /* Bus address of the MDIO device (0-31) */ int addr; + int flags; }; #define to_mdio_device(d) container_of(d, struct mdio_device, dev) +#define MDIO_DEVICE_FLAG_PHY 1 + static inline bool mdio_phy_id_is_c45(int phy_id) { return (phy_id & MDIO_PHY_ID_C45) && !(phy_id & ~MDIO_PHY_ID_C45_MASK); @@ -188,4 +191,9 @@ int mdiobus_read_nested(struct mii_bus *bus, int addr, u32 regnum); int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); +int mdiobus_register_device(struct mdio_device *mdiodev); +int mdiobus_unregister_device(struct mdio_device *mdiodev); +bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); +struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr); + #endif /* __LINUX_MDIO_H__ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 239a0c2bc49d..2d7beef20825 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -180,7 +180,7 @@ struct mii_bus { struct device dev; /* list of all PHYs on bus */ - struct phy_device *phy_map[PHY_MAX_ADDR]; + struct mdio_device *mdio_map[PHY_MAX_ADDR]; /* PHY addresses to be ignored when probing */ u32 phy_mask; -- cgit v1.2.3 From bc87922ff59d364a33e9bce0febdef21a7fbd2af Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:21 +0100 Subject: phy: Move PHY PM operations into phy_device The MDIO PM operations are really PHY device PM operations. So move them into phy_device. This will be needed when we support devices on the mdio bus which are not PHYs. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 8cd9579e18ea..9f844d372ed5 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -15,7 +15,7 @@ struct mii_bus; struct mdio_device { struct device dev; - + const struct dev_pm_ops *pm_ops; struct mii_bus *bus; /* Bus address of the MDIO device (0-31) */ int addr; -- cgit v1.2.3 From be01da72b1b832b89fbdf59ae6f1b60e53ca2987 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:22 +0100 Subject: phy: Centralize setting driver module owner Rather than have each driver set the driver owner field, do it once in the core code. This will also help with later changes, when the device structure will move. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 2d7beef20825..49e4418822b3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -797,8 +797,9 @@ int genphy_resume(struct phy_device *phydev); int genphy_soft_reset(struct phy_device *phydev); void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); -int phy_driver_register(struct phy_driver *new_driver); -int phy_drivers_register(struct phy_driver *new_driver, int n); +int phy_driver_register(struct phy_driver *new_driver, struct module *owner); +int phy_drivers_register(struct phy_driver *new_driver, int n, + struct module *owner); void phy_state_machine(struct work_struct *work); void phy_change(struct work_struct *work); void phy_mac_interrupt(struct phy_device *phydev, int new_link); @@ -843,7 +844,7 @@ extern struct bus_type mdio_bus_type; #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ - return phy_drivers_register(__phy_drivers, __count); \ + return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ -- cgit v1.2.3 From e76a4957c5ee5cf69cea89d450c29c536e77ce9e Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:23 +0100 Subject: phy: Move phy specific bus match into phy_device Matching a driver to a device has both generic parts, and parts which are specific to PHY devices. Move the PHY specific parts into phy_device. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 9f844d372ed5..0690359e55a5 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -17,6 +17,7 @@ struct mdio_device { struct device dev; const struct dev_pm_ops *pm_ops; struct mii_bus *bus; + int (*bus_match)(struct device *dev, struct device_driver *drv); /* Bus address of the MDIO device (0-31) */ int addr; int flags; -- cgit v1.2.3 From a9049e0c513c4521dbfaa302af8ed08b3366b41f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:26 +0100 Subject: mdio: Add support for mdio drivers. Not all devices on an MDIO bus are PHYs. Meaning not all MDIO drivers are PHY drivers. Add support for generic MDIO drivers. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phy.h | 9 +++++---- 2 files changed, 55 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 0690359e55a5..75f7fad0af4f 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -15,6 +15,7 @@ struct mii_bus; struct mdio_device { struct device dev; + const struct dev_pm_ops *pm_ops; struct mii_bus *bus; int (*bus_match)(struct device *dev, struct device_driver *drv); @@ -24,7 +25,37 @@ struct mdio_device { }; #define to_mdio_device(d) container_of(d, struct mdio_device, dev) +/* struct mdio_driver_common: Common to all MDIO drivers */ +struct mdio_driver_common { + struct device_driver driver; + int flags; +}; #define MDIO_DEVICE_FLAG_PHY 1 +#define to_mdio_common_driver(d) \ + container_of(d, struct mdio_driver_common, driver) + +/* struct mdio_driver: Generic MDIO driver */ +struct mdio_driver { + struct mdio_driver_common mdiodrv; + + /* + * Called during discovery. Used to set + * up device-specific structures, if any + */ + int (*probe)(struct mdio_device *mdiodev); + + /* Clears up any memory if needed */ + void (*remove)(struct mdio_device *mdiodev); +}; +#define to_mdio_driver(d) \ + container_of(to_mdio_common_driver(d), struct mdio_driver, mdiodrv) + +void mdio_device_free(struct mdio_device *mdiodev); +struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr); +int mdio_device_register(struct mdio_device *mdiodev); +void mdio_device_remove(struct mdio_device *mdiodev); +int mdio_driver_register(struct mdio_driver *drv); +void mdio_driver_unregister(struct mdio_driver *drv); static inline bool mdio_phy_id_is_c45(int phy_id) { @@ -197,4 +228,23 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr); +/** + * module_mdio_driver() - Helper macro for registering mdio drivers + * + * Helper macro for MDIO drivers which do not do anything special in module + * init/exit. Each module may only use this macro once, and calling it + * replaces module_init() and module_exit(). + */ +#define mdio_module_driver(_mdio_driver) \ +static int __init mdio_module_init(void) \ +{ \ + return mdio_driver_register(&_mdio_driver); \ +} \ +module_init(mdio_module_init); \ +static void __exit mdio_module_exit(void) \ +{ \ + mdio_driver_unregister(&_mdio_driver); \ +} \ +module_exit(mdio_module_exit) + #endif /* __LINUX_MDIO_H__ */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 49e4418822b3..d6f3641e7933 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -60,6 +60,7 @@ #define PHY_HAS_INTERRUPT 0x00000001 #define PHY_HAS_MAGICANEG 0x00000002 #define PHY_IS_INTERNAL 0x00000004 +#define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ typedef enum { @@ -432,6 +433,7 @@ struct phy_device { /* struct phy_driver: Driver structure for a particular PHY type * + * driver_data: static driver data * phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field @@ -441,7 +443,6 @@ struct phy_device { * by this PHY * flags: A bitfield defining certain other features this PHY * supports (like interrupts) - * driver_data: static driver data * * The drivers must implement config_aneg and read_status. All * other functions are optional. Note that none of these @@ -452,6 +453,7 @@ struct phy_device { * supported in the driver). */ struct phy_driver { + struct mdio_driver_common mdiodrv; u32 phy_id; char *name; unsigned int phy_id_mask; @@ -587,10 +589,9 @@ struct phy_driver { void (*get_strings)(struct phy_device *dev, u8 *data); void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); - - struct device_driver driver; }; -#define to_phy_driver(d) container_of(d, struct phy_driver, driver) +#define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ + struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff -- cgit v1.2.3 From 711fdba37a3dd7ee487e28767f9f0e67144cbf80 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jan 2016 20:11:27 +0100 Subject: mdio: Abstract device_remove() and device_free() Make device_free and device_remove operations in the mdio device structure, so the core code does not need to differentiate between phy devices and generic mdio devices. Signed-off-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 75f7fad0af4f..5bfd99d1a40a 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -18,7 +18,11 @@ struct mdio_device { const struct dev_pm_ops *pm_ops; struct mii_bus *bus; + int (*bus_match)(struct device *dev, struct device_driver *drv); + void (*device_free)(struct mdio_device *mdiodev); + void (*device_remove)(struct mdio_device *mdiodev); + /* Bus address of the MDIO device (0-31) */ int addr; int flags; -- cgit v1.2.3 From b7ffffbb46f205e7727a18bcc7a46c3c2b534f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Thu, 7 Jan 2016 15:40:01 -0500 Subject: ftrace: Add infrastructure for delayed enabling of module functions Qiu Peiyang pointed out that there's a race when enabling function tracing and loading a module. In order to make the modifications of converting nops in the prologue of functions into callbacks, the text needs to be converted from read-only to read-write. When enabling function tracing, the text permission is updated, the functions are modified, and then they are put back. When loading a module, the updates to convert function calls to mcount is done before the module text is set to read-only. But after it is done, the module text is visible by the function tracer. Thus we have the following race: CPU 0 CPU 1 ----- ----- start function tracing set text to read-write load_module add functions to ftrace set module text read-only update all functions to callbacks modify module functions too < Can't it's read-only > When this happens, ftrace detects the issue and disables itself till the next reboot. To fix this, a new DISABLED flag is added for ftrace records, which all module functions get when they are added. Then later, after the module code is all set, the records will have the DISABLED flag cleared, and they will be enabled if any callback wants all functions to be traced. Note, this doesn't add the delay to later. It simply changes the ftrace_module_init() to do both the setting of DISABLED records, and then immediately calls the enable code. This helps with testing this new code as it has the same behavior as previously. Another change will come after this to have the ftrace_module_enable() called after the text is set to read-only. Cc: Qiu Peiyang Signed-off-by: Steven Rostedt --- include/linux/ftrace.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 4736a826baf5..660e7c698f3b 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -357,6 +357,7 @@ bool is_ftrace_trampoline(unsigned long addr); * REGS - the record wants the function to save regs * REGS_EN - the function is set up to save regs. * IPMODIFY - the record allows for the IP address to be changed. + * DISABLED - the record is not ready to be touched yet * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flag REGS is set. When the function has been @@ -371,10 +372,11 @@ enum { FTRACE_FL_TRAMP = (1UL << 28), FTRACE_FL_TRAMP_EN = (1UL << 27), FTRACE_FL_IPMODIFY = (1UL << 26), + FTRACE_FL_DISABLED = (1UL << 25), }; -#define FTRACE_REF_MAX_SHIFT 26 -#define FTRACE_FL_BITS 6 +#define FTRACE_REF_MAX_SHIFT 25 +#define FTRACE_FL_BITS 7 #define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) #define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) -- cgit v1.2.3 From f27a0fe083bf46fef0d7045aa2e9a7e56e72d8d8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 7 Jan 2016 15:08:51 -0500 Subject: locks: pass inode pointer to locks_free_lock_context ...so we can print information about it if there are leaked locks. Signed-off-by: Jeff Layton Acked-by: "J. Bruce Fields" --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cbf08d5c246e..6c4983aceb02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1042,7 +1042,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ -void locks_free_lock_context(struct file_lock_context *ctx); +void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); @@ -1103,7 +1103,7 @@ static inline int fcntl_getlease(struct file *filp) } static inline void -locks_free_lock_context(struct file_lock_context *ctx) +locks_free_lock_context(struct inode *inode) { } -- cgit v1.2.3 From e39b2bb3b72b999a04e8d295882be3255aca5ade Mon Sep 17 00:00:00 2001 From: Danesh Petigara Date: Thu, 7 Jan 2016 16:03:33 -0800 Subject: libata: skip debounce delay on link resume The link resume logic uses a 200msec delay while debouncing the SControl register. The rationale behind that delay is to accommodate some PHYs that behave badly if their SStatus/ SControl registers are pounded immediately on resume. The Broadcom STB SATA PHY does not seem to have this issue. This patch introduces a new link flag that allows platforms to skip the debounce delay if it isn't needed. Signed-off-by: Danesh Petigara Signed-off-by: Florian Fainelli Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 83577f8fd15b..088ed924fa66 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -205,6 +205,7 @@ enum { ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ + ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ -- cgit v1.2.3 From 6c71f8ae155422a030b4c382cb985dde006ccc3f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 7 Jan 2016 14:53:46 +0100 Subject: KVM: Remove unused KVM_REQ_KICK to save a bit in vcpu->requests Suggested-by: Takuya Yoshikawa [Takuya moved all subsequent constants to fill the void, but that is useless in view of the following patches. So this change looks nothing like the original. - Paolo] Reviewed-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 61c3e6c69f27..5ac775b4dde9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -122,7 +122,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_UNHALT 6 #define KVM_REQ_MMU_SYNC 7 #define KVM_REQ_CLOCK_UPDATE 8 -#define KVM_REQ_KICK 9 +/* 9 is unused */ #define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_REQ_EVENT 11 #define KVM_REQ_APF_HALT 12 -- cgit v1.2.3 From 0cd310437255be81cd2413407c1d61eb70286fe2 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 7 Jan 2016 15:00:53 +0100 Subject: KVM: document which architecture uses each request bit Reviewed-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5ac775b4dde9..48abf6792286 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -114,12 +114,14 @@ static inline bool is_error_page(struct page *page) * vcpu->requests bit members */ #define KVM_REQ_TLB_FLUSH 0 -#define KVM_REQ_MIGRATE_TIMER 1 -#define KVM_REQ_REPORT_TPR_ACCESS 2 #define KVM_REQ_MMU_RELOAD 3 -#define KVM_REQ_TRIPLE_FAULT 4 #define KVM_REQ_PENDING_TIMER 5 #define KVM_REQ_UNHALT 6 + +/* x86-specific requests */ +#define KVM_REQ_MIGRATE_TIMER 1 +#define KVM_REQ_REPORT_TPR_ACCESS 2 +#define KVM_REQ_TRIPLE_FAULT 4 #define KVM_REQ_MMU_SYNC 7 #define KVM_REQ_CLOCK_UPDATE 8 /* 9 is unused */ @@ -130,14 +132,10 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_NMI 14 #define KVM_REQ_PMU 15 #define KVM_REQ_PMI 16 -#define KVM_REQ_WATCHDOG 17 #define KVM_REQ_MASTERCLOCK_UPDATE 18 #define KVM_REQ_MCLOCK_INPROGRESS 19 -#define KVM_REQ_EPR_EXIT 20 #define KVM_REQ_SCAN_IOAPIC 21 #define KVM_REQ_GLOBAL_CLOCK_UPDATE 22 -#define KVM_REQ_ENABLE_IBS 23 -#define KVM_REQ_DISABLE_IBS 24 #define KVM_REQ_APIC_PAGE_RELOAD 25 #define KVM_REQ_SMI 26 #define KVM_REQ_HV_CRASH 27 @@ -146,6 +144,14 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_HV_EXIT 30 #define KVM_REQ_HV_STIMER 31 +/* PPC-specific requests */ +#define KVM_REQ_WATCHDOG 17 +#define KVM_REQ_EPR_EXIT 20 + +/* s390-specific requests */ +#define KVM_REQ_ENABLE_IBS 23 +#define KVM_REQ_DISABLE_IBS 24 + #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 6662ba347b29b6df0756ffedb167fa4d89bab06f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 7 Jan 2016 15:02:44 +0100 Subject: KVM: renumber vcpu->request bits Leave room for 4 more arch-independent requests. Reviewed-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 59 ++++++++++++++++++++++++------------------------ 1 file changed, 29 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48abf6792286..b0ec0f778192 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -114,43 +114,42 @@ static inline bool is_error_page(struct page *page) * vcpu->requests bit members */ #define KVM_REQ_TLB_FLUSH 0 -#define KVM_REQ_MMU_RELOAD 3 -#define KVM_REQ_PENDING_TIMER 5 -#define KVM_REQ_UNHALT 6 +#define KVM_REQ_MMU_RELOAD 1 +#define KVM_REQ_PENDING_TIMER 2 +#define KVM_REQ_UNHALT 3 /* x86-specific requests */ -#define KVM_REQ_MIGRATE_TIMER 1 -#define KVM_REQ_REPORT_TPR_ACCESS 2 -#define KVM_REQ_TRIPLE_FAULT 4 -#define KVM_REQ_MMU_SYNC 7 -#define KVM_REQ_CLOCK_UPDATE 8 -/* 9 is unused */ -#define KVM_REQ_DEACTIVATE_FPU 10 -#define KVM_REQ_EVENT 11 -#define KVM_REQ_APF_HALT 12 -#define KVM_REQ_STEAL_UPDATE 13 -#define KVM_REQ_NMI 14 -#define KVM_REQ_PMU 15 -#define KVM_REQ_PMI 16 -#define KVM_REQ_MASTERCLOCK_UPDATE 18 -#define KVM_REQ_MCLOCK_INPROGRESS 19 -#define KVM_REQ_SCAN_IOAPIC 21 -#define KVM_REQ_GLOBAL_CLOCK_UPDATE 22 +#define KVM_REQ_MIGRATE_TIMER 8 +#define KVM_REQ_REPORT_TPR_ACCESS 9 +#define KVM_REQ_TRIPLE_FAULT 10 +#define KVM_REQ_MMU_SYNC 11 +#define KVM_REQ_CLOCK_UPDATE 12 +#define KVM_REQ_DEACTIVATE_FPU 13 +#define KVM_REQ_EVENT 14 +#define KVM_REQ_APF_HALT 15 +#define KVM_REQ_STEAL_UPDATE 16 +#define KVM_REQ_NMI 17 +#define KVM_REQ_PMU 18 +#define KVM_REQ_PMI 19 +#define KVM_REQ_SMI 20 +#define KVM_REQ_MASTERCLOCK_UPDATE 21 +#define KVM_REQ_MCLOCK_INPROGRESS 22 +#define KVM_REQ_SCAN_IOAPIC 23 +#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 #define KVM_REQ_APIC_PAGE_RELOAD 25 -#define KVM_REQ_SMI 26 -#define KVM_REQ_HV_CRASH 27 -#define KVM_REQ_IOAPIC_EOI_EXIT 28 -#define KVM_REQ_HV_RESET 29 -#define KVM_REQ_HV_EXIT 30 -#define KVM_REQ_HV_STIMER 31 +#define KVM_REQ_HV_CRASH 26 +#define KVM_REQ_IOAPIC_EOI_EXIT 27 +#define KVM_REQ_HV_RESET 28 +#define KVM_REQ_HV_EXIT 29 +#define KVM_REQ_HV_STIMER 30 /* PPC-specific requests */ -#define KVM_REQ_WATCHDOG 17 -#define KVM_REQ_EPR_EXIT 20 +#define KVM_REQ_WATCHDOG 8 +#define KVM_REQ_EPR_EXIT 9 /* s390-specific requests */ -#define KVM_REQ_ENABLE_IBS 23 -#define KVM_REQ_DISABLE_IBS 24 +#define KVM_REQ_ENABLE_IBS 8 +#define KVM_REQ_DISABLE_IBS 9 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 -- cgit v1.2.3 From 2860c4b1678646c99f5f1d77d026cd12ffd8a3a9 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 7 Jan 2016 15:05:10 +0100 Subject: KVM: move architecture-dependent requests to arch/ Since the numbers now overlap, it makes sense to enumerate them in asm/kvm_host.h rather than linux/kvm_host.h. Functions that refer to architecture-specific requests are also moved to arch/. Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 43 ++----------------------------------------- 1 file changed, 2 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index b0ec0f778192..f707f74055c3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -111,46 +111,14 @@ static inline bool is_error_page(struct page *page) } /* - * vcpu->requests bit members + * Architecture-independent vcpu->requests bit members + * Bits 4-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH 0 #define KVM_REQ_MMU_RELOAD 1 #define KVM_REQ_PENDING_TIMER 2 #define KVM_REQ_UNHALT 3 -/* x86-specific requests */ -#define KVM_REQ_MIGRATE_TIMER 8 -#define KVM_REQ_REPORT_TPR_ACCESS 9 -#define KVM_REQ_TRIPLE_FAULT 10 -#define KVM_REQ_MMU_SYNC 11 -#define KVM_REQ_CLOCK_UPDATE 12 -#define KVM_REQ_DEACTIVATE_FPU 13 -#define KVM_REQ_EVENT 14 -#define KVM_REQ_APF_HALT 15 -#define KVM_REQ_STEAL_UPDATE 16 -#define KVM_REQ_NMI 17 -#define KVM_REQ_PMU 18 -#define KVM_REQ_PMI 19 -#define KVM_REQ_SMI 20 -#define KVM_REQ_MASTERCLOCK_UPDATE 21 -#define KVM_REQ_MCLOCK_INPROGRESS 22 -#define KVM_REQ_SCAN_IOAPIC 23 -#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 -#define KVM_REQ_APIC_PAGE_RELOAD 25 -#define KVM_REQ_HV_CRASH 26 -#define KVM_REQ_IOAPIC_EOI_EXIT 27 -#define KVM_REQ_HV_RESET 28 -#define KVM_REQ_HV_EXIT 29 -#define KVM_REQ_HV_STIMER 30 - -/* PPC-specific requests */ -#define KVM_REQ_WATCHDOG 8 -#define KVM_REQ_EPR_EXIT 9 - -/* s390-specific requests */ -#define KVM_REQ_ENABLE_IBS 8 -#define KVM_REQ_DISABLE_IBS 9 - #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -689,8 +657,6 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -void kvm_make_mclock_inprogress_request(struct kvm *kvm); -void kvm_make_scan_ioapic_request(struct kvm *kvm); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); long kvm_arch_dev_ioctl(struct file *filp, @@ -1011,11 +977,6 @@ static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) return kvm_is_error_hva(hva); } -static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu) -{ - set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); -} - enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, -- cgit v1.2.3 From 66cf191f3eae4582a83cb4251b75b43bee95a999 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 7 Jan 2016 09:53:30 -0500 Subject: compat_ioctl: don't pass fd around when not needed Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..51f9f8d93d4d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2764,8 +2764,6 @@ extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_fstatat(int , const char __user *, struct kstat *, int); -extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, - unsigned long arg); extern int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, -- cgit v1.2.3 From 01dd194c387af5b3c4c1f6459d30f596565e466c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 6 Jan 2016 22:32:16 +0100 Subject: bpf: cleanup bpf_prog_run_{save,clear}_cb helpers Move the details behind the cb[] access into a small helper to decouple and make them generic for bpf_prog_run_save_cb()/bpf_prog_run_clear_cb() that was introduced via commit ff936a04e5f2 ("bpf: fix cb access in socket filter programs"). Also add a comment to better clarify what is done in bpf_skb_cb(). Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 39 +++++++++++++++++++++++++++++---------- 1 file changed, 29 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index f5b5891ed1ba..43aa1f8855c7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -350,25 +350,43 @@ struct sk_filter { #define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN + +static inline u8 *bpf_skb_cb(struct sk_buff *skb) +{ + /* eBPF programs may read/write skb->cb[] area to transfer meta + * data between tail calls. Since this also needs to work with + * tc, that scratch memory is mapped to qdisc_skb_cb's data area. + * + * In some socket filter cases, the cb unfortunately needs to be + * saved/restored so that protocol specific skb->cb[] data won't + * be lost. In any case, due to unpriviledged eBPF programs + * attached to sockets, we need to clear the bpf_skb_cb() area + * to not leak previous contents to user space. + */ + BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN); + BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != + FIELD_SIZEOF(struct qdisc_skb_cb, data)); + + return qdisc_skb_cb(skb)->data; +} + static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { - u8 *cb_data = qdisc_skb_cb(skb)->data; - u8 saved_cb[QDISC_CB_PRIV_LEN]; + u8 *cb_data = bpf_skb_cb(skb); + u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != - QDISC_CB_PRIV_LEN); - if (unlikely(prog->cb_access)) { - memcpy(saved_cb, cb_data, sizeof(saved_cb)); - memset(cb_data, 0, sizeof(saved_cb)); + memcpy(cb_saved, cb_data, sizeof(cb_saved)); + memset(cb_data, 0, sizeof(cb_saved)); } res = BPF_PROG_RUN(prog, skb); if (unlikely(prog->cb_access)) - memcpy(cb_data, saved_cb, sizeof(saved_cb)); + memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } @@ -376,10 +394,11 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { - u8 *cb_data = qdisc_skb_cb(skb)->data; + u8 *cb_data = bpf_skb_cb(skb); if (unlikely(prog->cb_access)) - memset(cb_data, 0, QDISC_CB_PRIV_LEN); + memset(cb_data, 0, BPF_SKB_CB_LEN); + return BPF_PROG_RUN(prog, skb); } -- cgit v1.2.3 From bbddca8e8fac07ece3938e03526b5d00fa791a4c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 7 Jan 2016 16:08:20 -0500 Subject: nfsd: don't hold i_mutex over userspace upcalls We need information about exports when crossing mountpoints during lookup or NFSv4 readdir. If we don't already have that information cached, we may have to ask (and wait for) rpc.mountd. In both cases we currently hold the i_mutex on the parent of the directory we're asking rpc.mountd about. We've seen situations where rpc.mountd performs some operation on that directory that tries to take the i_mutex again, resulting in deadlock. With some care, we may be able to avoid that in rpc.mountd. But it seems better just to avoid holding a mutex while waiting on userspace. It appears that lookup_one_len is pretty much the only operation that needs the i_mutex. So we could just drop the i_mutex elsewhere and do something like mutex_lock() lookup_one_len() mutex_unlock() In many cases though the lookup would have been cached and not required the i_mutex, so it's more efficient to create a lookup_one_len() variant that only takes the i_mutex when necessary. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index d8c6334cd150..d0f25d81b46a 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -77,6 +77,7 @@ extern struct dentry *kern_path_locked(const char *, struct path *); 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); extern int follow_down_one(struct path *); extern int follow_down(struct path *); -- cgit v1.2.3 From f8ffad69c9f8b8dfb0b633425d4ef4d2493ba61a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 7 Jan 2016 15:50:23 +0100 Subject: bpf: add skb_postpush_rcsum and fix dev_forward_skb occasions Add a small helper skb_postpush_rcsum() and fix up redirect locations that need CHECKSUM_COMPLETE fixups on ingress. dev_forward_skb() expects a proper csum that covers also Ethernet header, f.e. since 2c26d34bbcc0 ("net/core: Handle csum for CHECKSUM_COMPLETE VXLAN forwarding"), we also do skb_postpull_rcsum() after pulling Ethernet header off via eth_type_trans(). When using eBPF in a netns setup f.e. with vxlan in collect metadata mode, I can trigger the following csum issue with an IPv6 setup: [ 505.144065] dummy1: hw csum failure [...] [ 505.144108] Call Trace: [ 505.144112] [] dump_stack+0x44/0x5c [ 505.144134] [] netdev_rx_csum_fault+0x3a/0x40 [ 505.144142] [] __skb_checksum_complete+0xcf/0xe0 [ 505.144149] [] nf_ip6_checksum+0xb2/0x120 [ 505.144161] [] icmpv6_error+0x17e/0x328 [nf_conntrack_ipv6] [ 505.144170] [] ? ip6t_do_table+0x2fa/0x645 [ip6_tables] [ 505.144177] [] ? ipv6_get_l4proto+0x65/0xd0 [nf_conntrack_ipv6] [ 505.144189] [] nf_conntrack_in+0xc2/0x5a0 [nf_conntrack] [ 505.144196] [] ipv6_conntrack_in+0x1c/0x20 [nf_conntrack_ipv6] [ 505.144204] [] nf_iterate+0x5d/0x70 [ 505.144210] [] nf_hook_slow+0x66/0xc0 [ 505.144218] [] ipv6_rcv+0x3f2/0x4f0 [ 505.144225] [] ? ip6_make_skb+0x1b0/0x1b0 [ 505.144232] [] __netif_receive_skb_core+0x36b/0x9a0 [ 505.144239] [] ? __netif_receive_skb+0x18/0x60 [ 505.144245] [] __netif_receive_skb+0x18/0x60 [ 505.144252] [] process_backlog+0x9f/0x140 [ 505.144259] [] net_rx_action+0x145/0x320 [...] What happens is that on ingress, we push Ethernet header back in, either from cls_bpf or right before skb_do_redirect(), but without updating csum. The "hw csum failure" can be fixed by using the new skb_postpush_rcsum() helper for the dev_forward_skb() case to correct the csum diff again. Thanks to Hannes Frederic Sowa for the csum_partial() idea! Fixes: 3896d655f4d4 ("bpf: introduce bpf_clone_redirect() helper") Fixes: 27b29f63058d ("bpf: add bpf_redirect() helper") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6b6bd42d6134..07f9ccd28654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2805,6 +2805,23 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +static inline void skb_postpush_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + /* For performing the reverse operation to skb_postpull_rcsum(), + * we can instead of ... + * + * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); + * + * ... just use this equivalent version here to save a few + * instructions. Feeding csum of 0 in csum_partial() and later + * on adding skb->csum is equivalent to feed skb->csum in the + * first place. + */ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(start, len, skb->csum); +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim -- cgit v1.2.3 From 1f211a1b929c804100e138c5d3d656992cfd5622 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 7 Jan 2016 22:29:47 +0100 Subject: net, sched: add clsact qdisc This work adds a generalization of the ingress qdisc as a qdisc holding only classifiers. The clsact qdisc works on ingress, but also on egress. In both cases, it's execution happens without taking the qdisc lock, and the main difference for the egress part compared to prior version of [1] is that this can be applied with _any_ underlying real egress qdisc (also classless ones). Besides solving the use-case of [1], that is, allowing for more programmability on assigning skb->priority for the mqprio case that is supported by most popular 10G+ NICs, it also opens up a lot more flexibility for other tc applications. The main work on classification can already be done at clsact egress time if the use-case allows and state stored for later retrieval f.e. again in skb->priority with major/minors (which is checked by most classful qdiscs before consulting tc_classify()) and/or in other skb fields like skb->tc_index for some light-weight post-processing to get to the eventual classid in case of a classful qdisc. Another use case is that the clsact egress part allows to have a central egress counterpart to the ingress classifiers, so that classifiers can easily share state (e.g. in cls_bpf via eBPF maps) for ingress and egress. Currently, default setups like mq + pfifo_fast would require for this to use, for example, prio qdisc instead (to get a tc_classify() run) and to duplicate the egress classifier for each queue. With clsact, it allows for leaving the setup as is, it can additionally assign skb->priority to put the skb in one of pfifo_fast's bands and it can share state with maps. Moreover, we can access the skb's dst entry (f.e. to retrieve tclassid) w/o the need to perform a skb_dst_force() to hold on to it any longer. In lwt case, we can also use this facility to setup dst metadata via cls_bpf (bpf_skb_set_tunnel_key()) without needing a real egress qdisc just for that (case of IFF_NO_QUEUE devices, for example). The realization can be done without any changes to the scheduler core framework. All it takes is that we have two a-priori defined minors/child classes, where we can mux between ingress and egress classifier list (dev->ingress_cl_list and dev->egress_cl_list, latter stored close to dev->_tx to avoid extra cacheline miss for moderate loads). The egress part is a bit similar modelled to handle_ing() and patched to a noop in case the functionality is not used. Both handlers are now called sch_handle_ingress() and sch_handle_egress(), code sharing among the two doesn't seem practical as there are various minor differences in both paths, so that making them conditional in a single handler would rather slow things down. Full compatibility to ingress qdisc is provided as well. Since both piggyback on TC_H_CLSACT, only one of them (ingress/clsact) can exist per netdevice, and thus ingress qdisc specific behaviour can be retained for user space. This means, either a user does 'tc qdisc add dev foo ingress' and configures ingress qdisc as usual, or the 'tc qdisc add dev foo clsact' alternative, where both, ingress and egress classifier can be configured as in the below example. ingress qdisc supports attaching classifier to any minor number whereas clsact has two fixed minors for muxing between the lists, therefore to not break user space setups, they are better done as two separate qdiscs. I decided to extend the sch_ingress module with clsact functionality so that commonly used code can be reused, the module is being aliased with sch_clsact so that it can be auto-loaded properly. Alternative would have been to add a flag when initializing ingress to alter its behaviour plus aliasing to a different name (as it's more than just ingress). However, the first would end up, based on the flag, choosing the new/old behaviour by calling different function implementations to handle each anyway, the latter would require to register ingress qdisc once again under different alias. So, this really begs to provide a minimal, cleaner approach to have Qdisc_ops and Qdisc_class_ops by its own that share callbacks used by both. Example, adding qdisc: # tc qdisc add dev foo clsact # tc qdisc show dev foo qdisc mq 0: root qdisc pfifo_fast 0: parent :1 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :2 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :3 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc pfifo_fast 0: parent :4 bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1 qdisc clsact ffff: parent ffff:fff1 Adding filters (deleting, etc works analogous by specifying ingress/egress): # tc filter add dev foo ingress bpf da obj bar.o sec ingress # tc filter add dev foo egress bpf da obj bar.o sec egress # tc filter show dev foo ingress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[ingress] direct-action # tc filter show dev foo egress filter protocol all pref 49152 bpf filter protocol all pref 49152 bpf handle 0x1 bar.o:[egress] direct-action A 'tc filter show dev foo' or 'tc filter show dev foo parent ffff:' will show an empty list for clsact. Either using the parent names (ingress/egress) or specifying the full major/minor will then show the related filter lists. Prior work on a mqprio prequeue() facility [1] was done mainly by John Fastabend. [1] http://patchwork.ozlabs.org/patch/512949/ Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +++- include/linux/rtnetlink.h | 5 +++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8d8e5ca951b4..2285596e7045 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1739,7 +1739,9 @@ struct net_device { #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps; #endif - +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto __rcu *egress_cl_list; +#endif #ifdef CONFIG_NET_SWITCHDEV u32 offload_fwd_mark; #endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 4be5048b1fbe..c006cc900c44 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -84,6 +84,11 @@ void net_inc_ingress_queue(void); void net_dec_ingress_queue(void); #endif +#ifdef CONFIG_NET_EGRESS +void net_inc_egress_queue(void); +void net_dec_egress_queue(void); +#endif + extern void rtnetlink_init(void); extern void __rtnl_unlock(void); -- cgit v1.2.3 From f0d22d1874730530a2ac304fd0888cb8a6864527 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:25:57 +0200 Subject: net/mlx5_core: Introduce flow steering autogrouped flow table When user add rule to autogrouped flow table, we search for flow group with the same match criteria, if we don't find such group then we create new flow group with the required match criteria and insert the rule to this group. We divide the flow table into required_groups + 1, in order to reserve a part of the flow table for rules which don't match any existing group. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index bc7ad019afde..06ac6e8fccfa 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -61,6 +61,12 @@ struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); +struct mlx5_flow_table * +mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, + int prio, + int num_flow_table_entries, + int max_num_groups); + struct mlx5_flow_table * mlx5_create_flow_table(struct mlx5_flow_namespace *ns, int prio, -- cgit v1.2.3 From 2cc43b494a6c30ec0e554ea91ce763c97069e8cc Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:25:59 +0200 Subject: net/mlx5_core: Managing root flow table The root Flow Table for each Flow Table Type is defined, by default, as the Flow Table with level 0. In order not to use an empty flow tables and introduce new hops, but still preserve space for flow-tables that have a priority greater(lower number) than the current flow table, we introduce this new set root flow table command. This command tells the HW to start matching packets from the assigned root flow table. This command is used when we create new flow table with level lower than the current lowest flow table or it is the first flow table. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1780a85a8797..323e713c44ba 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -185,6 +185,7 @@ enum { MLX5_CMD_OP_MODIFY_RQT = 0x917, MLX5_CMD_OP_DESTROY_RQT = 0x918, MLX5_CMD_OP_QUERY_RQT = 0x919, + MLX5_CMD_OP_SET_FLOW_TABLE_ROOT = 0x92f, MLX5_CMD_OP_CREATE_FLOW_TABLE = 0x930, MLX5_CMD_OP_DESTROY_FLOW_TABLE = 0x931, MLX5_CMD_OP_QUERY_FLOW_TABLE = 0x932, @@ -258,7 +259,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; u8 reserved_0[0x2]; u8 flow_modify_en[0x1]; - u8 reserved_1[0x1c]; + u8 modify_root[0x1]; + u8 reserved_1[0x1b]; u8 reserved_2[0x2]; u8 log_max_ft_size[0x6]; @@ -6946,4 +6948,31 @@ union mlx5_ifc_uplink_pci_interface_document_bits { u8 reserved_0[0x20060]; }; +struct mlx5_ifc_set_flow_table_root_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_set_flow_table_root_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x40]; + + u8 table_type[0x8]; + u8 reserved_3[0x18]; + + u8 reserved_4[0x8]; + u8 table_id[0x18]; + + u8 reserved_5[0x140]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 34a40e689393a6b13673ab395a9a4d063d249fe9 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:26:00 +0200 Subject: net/mlx5_core: Introduce modify flow table command Introduce the modify flow table command. This command is used when we want to change the next flow table of an existing flow table. The next flow table is defined as the table we search (in order to find a match), if we couldn't find a match in any of the flow table entries in the current flow table. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 56 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 52 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 323e713c44ba..7f166955d4c9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -194,7 +194,8 @@ enum { MLX5_CMD_OP_QUERY_FLOW_GROUP = 0x935, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY = 0x936, MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY = 0x937, - MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY = 0x938 + MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY = 0x938, + MLX5_CMD_OP_MODIFY_FLOW_TABLE = 0x93c }; struct mlx5_ifc_flow_table_fields_supported_bits { @@ -260,7 +261,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_0[0x2]; u8 flow_modify_en[0x1]; u8 modify_root[0x1]; - u8 reserved_1[0x1b]; + u8 identified_miss_table_mode[0x1]; + u8 flow_table_modify[0x1]; + u8 reserved_1[0x19]; u8 reserved_2[0x2]; u8 log_max_ft_size[0x6]; @@ -5669,12 +5672,16 @@ struct mlx5_ifc_create_flow_table_in_bits { u8 reserved_4[0x20]; - u8 reserved_5[0x8]; + u8 reserved_5[0x4]; + u8 table_miss_mode[0x4]; u8 level[0x8]; u8 reserved_6[0x8]; u8 log_size[0x8]; - u8 reserved_7[0x120]; + u8 reserved_7[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_8[0x100]; }; struct mlx5_ifc_create_flow_group_out_bits { @@ -6975,4 +6982,45 @@ struct mlx5_ifc_set_flow_table_root_in_bits { u8 reserved_5[0x140]; }; +enum { + MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID = 0x1, +}; + +struct mlx5_ifc_modify_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_flow_table_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x20]; + + u8 reserved_3[0x10]; + u8 modify_field_select[0x10]; + + u8 table_type[0x8]; + u8 reserved_4[0x18]; + + u8 reserved_5[0x8]; + u8 table_id[0x18]; + + u8 reserved_6[0x4]; + u8 table_miss_mode[0x4]; + u8 reserved_7[0x18]; + + u8 reserved_8[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_9[0x100]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From 4cbdd30ed5c8bc5cf40813b025b4fb57b376a592 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:26:04 +0200 Subject: net/mlx5_core: Enable flow steering support for the IB driver When the driver is loaded, we create flow steering namespace for kernel bypass with nine priorities and another namespace for leftovers(in order to catch packets that weren't matched). Verbs applications will use these priorities. we found nine as a number that balances the requirements from the user and retains performance. The bypass namespace is used by verbs applications that want to bypass the kernel networking stack. The leftovers namespace is used by verbs applications and the sniffer in order to catch packets that weren't handled by any preceding rules. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 2 ++ include/linux/mlx5/fs.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index df2f79ef3cac..7be845e30689 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1258,4 +1258,6 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } +#define MLX5_BY_PASS_NUM_PRIOS 9 + #endif /* MLX5_DEVICE_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 06ac6e8fccfa..a94341271e3f 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -39,7 +39,9 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 enum mlx5_flow_namespace_type { + MLX5_FLOW_NAMESPACE_BYPASS, MLX5_FLOW_NAMESPACE_KERNEL, + MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_FDB, }; -- cgit v1.2.3 From b4d1f032d75b2efb73304e8c12faa7149ad700c7 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:26:05 +0200 Subject: net/mlx5_core: Make ipv4/ipv6 location more clear Change the mlx5 firmware interface header to make it more clear which bytes should be used by IPv4 or IPv6 addresses. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 7f166955d4c9..68d73f82e009 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -298,6 +298,22 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 reserved_1[0x1a]; }; +struct mlx5_ifc_ipv4_layout_bits { + u8 reserved_0[0x60]; + + u8 ipv4[0x20]; +}; + +struct mlx5_ifc_ipv6_layout_bits { + u8 ipv6[16][0x8]; +}; + +union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_layout_bits ipv6_layout; + struct mlx5_ifc_ipv4_layout_bits ipv4_layout; + u8 reserved_0[0x80]; +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -328,9 +344,9 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 udp_sport[0x10]; u8 udp_dport[0x10]; - u8 src_ip[4][0x20]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; - u8 dst_ip[4][0x20]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; }; struct mlx5_ifc_fte_match_set_misc_bits { -- cgit v1.2.3 From 038d2ef87572757861a177b19f9d489def2c48b8 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Mon, 11 Jan 2016 10:26:07 +0200 Subject: IB/mlx5: Add flow steering support Adding flow steering support by creating a flow-table per priority (if rules exist in the priority). mlx5_ib uses autogrouping and thus only creates the required destinations. Also includes adding of these flow steering utilities 1. Parsing verbs flow attributes hardware steering specs. 2. Check if flow is multicast - this is required in order to decide to which flow table will we add the steering rule. 3. Set outer headers in flow match criteria to zeros. Signed-off-by: Maor Gottlieb Signed-off-by: Moni Shoua Signed-off-by: Matan Barak Signed-off-by: David S. Miller --- include/linux/mlx5/fs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a94341271e3f..8230caa3fb6e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -38,6 +38,16 @@ #define MLX5_FS_DEFAULT_FLOW_TAG 0x0 +#define LEFTOVERS_RULE_NUM 2 +static inline void build_leftovers_ft_param(int *priority, + int *n_ent, + int *n_grp) +{ + *priority = 0; /* Priority of leftovers_prio-0 */ + *n_ent = LEFTOVERS_RULE_NUM; + *n_grp = LEFTOVERS_RULE_NUM; +} + enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_BYPASS, MLX5_FLOW_NAMESPACE_KERNEL, -- cgit v1.2.3 From b6a0e72ad3cffabaf30b856deb58fbe64a0f36a8 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Mon, 11 Jan 2016 10:19:10 -0800 Subject: net: Fix typo in netdev_intersect_features Obviously need to 'or in NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM. Fixes: c8cd0989bd151f ("net: Eliminate NETIF_F_GEN_CSUM and NETIF_F_V[46]_CSUM") Reported-by: Jack Morgenstein Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2285596e7045..5ac140dcb789 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3873,9 +3873,9 @@ static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, { if ((f1 ^ f2) & NETIF_F_HW_CSUM) { if (f1 & NETIF_F_HW_CSUM) - f1 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); else - f2 |= (NETIF_F_IP_CSUM|NETIF_F_IP_CSUM); + f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } return f1 & f2; -- cgit v1.2.3