From 5ab788d7383289bfc141ab357767bc6c11bbf77f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 30 May 2016 20:57:50 +0200 Subject: rtc: cmos: move mc146818rtc code out of asm-generic/rtc.h Drivers should not really include stuff from asm-generic directly, and the PC-style cmos rtc driver does this in order to reuse the mc146818 implementation of get_rtc_time/set_rtc_time rather than the architecture specific one for the architecture it gets built for. To make it more obvious what is going on, this moves and renames the two functions into include/linux/mc146818rtc.h, which holds the other mc146818 specific code. Ideally it would be in a .c file, but that would require extra infrastructure as the functions are called by multiple drivers with conflicting dependencies. With this change, the asm-generic/rtc.h header also becomes much more generic, so it can be reused more easily across any architecture that still relies on the genrtc driver. The only caller of the internal __get_rtc_time/__set_rtc_time functions is in arch/alpha/kernel/rtc.c, and we just change those over to the new naming. Signed-off-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Signed-off-by: Alexandre Belloni --- include/linux/mc146818rtc.h | 194 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 194 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 433e0c74d643..e9e346b37846 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -14,6 +14,12 @@ #include #include /* get the user-level API */ #include /* register access macros */ +#include +#include + +#ifdef CONFIG_ACPI +#include +#endif #ifdef __KERNEL__ #include /* spinlock_t */ @@ -120,4 +126,192 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ +/* + * Returns true if a clock update is in progress + */ +static inline unsigned char mc146818_is_updating(void) +{ + unsigned char uip; + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); + uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); + spin_unlock_irqrestore(&rtc_lock, flags); + return uip; +} + +static inline unsigned int mc146818_get_time(struct rtc_time *time) +{ + unsigned char ctrl; + unsigned long flags; + unsigned char century = 0; + +#ifdef CONFIG_MACH_DECSTATION + unsigned int real_year; +#endif + + /* + * read RTC once any update in progress is done. The update + * can take just over 2ms. We wait 20ms. There is no need to + * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. + * If you need to know *exactly* when a second has started, enable + * periodic update complete interrupts, (via ioctl) and then + * immediately read /dev/rtc which will block until you get the IRQ. + * Once the read clears, read the RTC time (again via ioctl). Easy. + */ + if (mc146818_is_updating()) + mdelay(20); + + /* + * Only the values that we read from the RTC are set. We leave + * tm_wday, tm_yday and tm_isdst untouched. Even though the + * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated + * by the RTC when initially set to a non-zero value. + */ + spin_lock_irqsave(&rtc_lock, flags); + time->tm_sec = CMOS_READ(RTC_SECONDS); + time->tm_min = CMOS_READ(RTC_MINUTES); + time->tm_hour = CMOS_READ(RTC_HOURS); + time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); + time->tm_mon = CMOS_READ(RTC_MONTH); + time->tm_year = CMOS_READ(RTC_YEAR); +#ifdef CONFIG_MACH_DECSTATION + real_year = CMOS_READ(RTC_DEC_YEAR); +#endif +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) + century = CMOS_READ(acpi_gbl_FADT.century); +#endif + ctrl = CMOS_READ(RTC_CONTROL); + spin_unlock_irqrestore(&rtc_lock, flags); + + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + { + time->tm_sec = bcd2bin(time->tm_sec); + time->tm_min = bcd2bin(time->tm_min); + time->tm_hour = bcd2bin(time->tm_hour); + time->tm_mday = bcd2bin(time->tm_mday); + time->tm_mon = bcd2bin(time->tm_mon); + time->tm_year = bcd2bin(time->tm_year); + century = bcd2bin(century); + } + +#ifdef CONFIG_MACH_DECSTATION + time->tm_year += real_year - 72; +#endif + + if (century) + time->tm_year += (century - 19) * 100; + + /* + * Account for differences between how the RTC uses the values + * and how they are defined in a struct rtc_time; + */ + if (time->tm_year <= 69) + time->tm_year += 100; + + time->tm_mon--; + + return RTC_24H; +} + +/* Set the current date and time in the real time clock. */ +static inline int mc146818_set_time(struct rtc_time *time) +{ + unsigned long flags; + unsigned char mon, day, hrs, min, sec; + unsigned char save_control, save_freq_select; + unsigned int yrs; +#ifdef CONFIG_MACH_DECSTATION + unsigned int real_yrs, leap_yr; +#endif + unsigned char century = 0; + + yrs = time->tm_year; + mon = time->tm_mon + 1; /* tm_mon starts at zero */ + day = time->tm_mday; + hrs = time->tm_hour; + min = time->tm_min; + sec = time->tm_sec; + + if (yrs > 255) /* They are unsigned */ + return -EINVAL; + + spin_lock_irqsave(&rtc_lock, flags); +#ifdef CONFIG_MACH_DECSTATION + real_yrs = yrs; + leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || + !((yrs + 1900) % 400)); + yrs = 72; + + /* + * We want to keep the year set to 73 until March + * for non-leap years, so that Feb, 29th is handled + * correctly. + */ + if (!leap_yr && mon < 3) { + real_yrs--; + yrs = 73; + } +#endif + +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) { + century = (yrs + 1900) / 100; + yrs %= 100; + } +#endif + + /* These limits and adjustments are independent of + * whether the chip is in binary mode or not. + */ + if (yrs > 169) { + spin_unlock_irqrestore(&rtc_lock, flags); + return -EINVAL; + } + + if (yrs >= 100) + yrs -= 100; + + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) + || RTC_ALWAYS_BCD) { + sec = bin2bcd(sec); + min = bin2bcd(min); + hrs = bin2bcd(hrs); + day = bin2bcd(day); + mon = bin2bcd(mon); + yrs = bin2bcd(yrs); + century = bin2bcd(century); + } + + save_control = CMOS_READ(RTC_CONTROL); + CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + +#ifdef CONFIG_MACH_DECSTATION + CMOS_WRITE(real_yrs, RTC_DEC_YEAR); +#endif + CMOS_WRITE(yrs, RTC_YEAR); + CMOS_WRITE(mon, RTC_MONTH); + CMOS_WRITE(day, RTC_DAY_OF_MONTH); + CMOS_WRITE(hrs, RTC_HOURS); + CMOS_WRITE(min, RTC_MINUTES); + CMOS_WRITE(sec, RTC_SECONDS); +#ifdef CONFIG_ACPI + if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && + acpi_gbl_FADT.century) + CMOS_WRITE(century, acpi_gbl_FADT.century); +#endif + + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + + spin_unlock_irqrestore(&rtc_lock, flags); + + return 0; +} + #endif /* _MC146818RTC_H */ -- cgit v1.2.3 From 3a3d1a4e32ab47323d7b8c8b7631a8d36a3098b2 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Wed, 8 Jun 2016 10:21:23 +0100 Subject: pwm: Add PWM capture support Supply a PWM capture callback op in order to pass back information obtained by running analysis on a PWM signal. This would normally (at least during testing) be called from the sysfs routines with a view to printing out PWM capture data which has been encoded into a string. Signed-off-by: Lee Jones [thierry.reding@gmail.com: make capture data unsigned int for symmetry] Signed-off-by: Thierry Reding --- include/linux/pwm.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 17018f3c066e..8402b5dd3e06 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -5,7 +5,9 @@ #include #include +struct pwm_capture; struct seq_file; + struct pwm_chip; /** @@ -153,6 +155,7 @@ static inline void pwm_get_args(const struct pwm_device *pwm, * @free: optional hook for freeing a PWM * @config: configure duty cycles and period length for this PWM * @set_polarity: configure the polarity of this PWM + * @capture: capture and report PWM signal * @enable: enable PWM output toggling * @disable: disable PWM output toggling * @apply: atomically apply a new PWM config. The state argument @@ -172,6 +175,8 @@ struct pwm_ops { int duty_ns, int period_ns); int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, enum pwm_polarity polarity); + int (*capture)(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_capture *result, unsigned long timeout); int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); int (*apply)(struct pwm_chip *chip, struct pwm_device *pwm, @@ -212,6 +217,16 @@ struct pwm_chip { bool can_sleep; }; +/** + * struct pwm_capture - PWM capture data + * @period: period of the PWM signal (in nanoseconds) + * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) + */ +struct pwm_capture { + unsigned int period; + unsigned int duty_cycle; +}; + #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ struct pwm_device *pwm_request(int pwm_id, const char *label); @@ -322,6 +337,8 @@ static inline void pwm_disable(struct pwm_device *pwm) /* PWM provider APIs */ +int pwm_capture(struct pwm_device *pwm, struct pwm_capture *result, + unsigned long timeout); int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); @@ -373,6 +390,13 @@ static inline int pwm_config(struct pwm_device *pwm, int duty_ns, return -EINVAL; } +static inline int pwm_capture(struct pwm_device *pwm, + struct pwm_capture *result, + unsigned long timeout) +{ + return -EINVAL; +} + static inline int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity) { -- cgit v1.2.3 From 89ea94a7b6c40eb423c144aef1caceebaff79c8d Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 17 Jun 2016 15:01:38 +0300 Subject: IB/mlx5: Reset flow support for IB kernel ULPs The driver exposes interfaces that directly relate to HW state. Upon fatal error, consumers of these interfaces (ULPs) that rely on completion of all their posted work-request could hang, thereby introducing dependencies in shutdown order. To prevent this from happening, we manage the relevant resources (CQs, QPs) that are used by the device. Upon a fatal error, we now generate simulated completions for outstanding WQEs that were not completed at the time the HW was reset. It includes invoking the completion event handler for all involved CQs so that the ULPs will poll those CQs. When polled we return simulated CQEs with IB_WC_WR_FLUSH_ERR return code enabling ULPs to clean up their resources and not wait forever for completions upon receiving remove_one. The above change requires an extra check in the data path to make sure that when device is in error state, the simulated CQEs will be returned and no further WQEs will be posted. Signed-off-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/cq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 2be976dd4966..2566f6d6444f 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -58,6 +58,8 @@ struct mlx5_core_cq { void (*comp)(struct mlx5_core_cq *); void *priv; } tasklet_ctx; + int reset_notify_added; + struct list_head reset_notify; }; -- cgit v1.2.3 From e3353c268b06236d6c40fa1714c114f21f44451c Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Fri, 17 Jun 2016 15:33:31 +0300 Subject: IB/mlx5: Fix MODIFY_QP command input structure Make MODIFY_QP command input structure compliant to specification Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/qp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 266320feb160..acb28c989dee 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -555,9 +555,9 @@ struct mlx5_destroy_qp_mbox_out { struct mlx5_modify_qp_mbox_in { struct mlx5_inbox_hdr hdr; __be32 qpn; - u8 rsvd1[4]; - __be32 optparam; u8 rsvd0[4]; + __be32 optparam; + u8 rsvd1[4]; struct mlx5_qp_context ctx; u8 rsvd2[16]; }; -- cgit v1.2.3 From af1ba291c5e498973cc325c501dd8da80b234571 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Fri, 17 Jun 2016 15:33:32 +0300 Subject: {net, IB}/mlx5: Refactor internal SRQ API Currently, the SRQ API uses the obsolete mlx5_*_srq_mbox_{in,out} structs which limit the ability to pass the SRQ attributes between net and IB parts of the driver. This patch changes the SRQ API so as to use auto-generated structs and provides a better way to pass attributes which will be in use by coming features. Signed-off-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 6 +++--- include/linux/mlx5/srq.h | 25 +++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80776d0c52dc..ba933335772c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -46,6 +46,7 @@ #include #include +#include enum { MLX5_RQ_BITMASK_VSD = 1 << 1, @@ -772,11 +773,10 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_create_srq_mbox_in *in, int inlen, - int is_xrc); + struct mlx5_srq_attr *in); int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq); int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, - struct mlx5_query_srq_mbox_out *out); + struct mlx5_srq_attr *out); int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, u16 lwm, int is_srq); void mlx5_init_mkey_table(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index f43ed054a3e0..33c97dc900f8 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -35,6 +35,31 @@ #include +enum { + MLX5_SRQ_FLAG_ERR = (1 << 0), + MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), +}; + +struct mlx5_srq_attr { + u32 type; + u32 flags; + u32 log_size; + u32 wqe_shift; + u32 log_page_size; + u32 wqe_cnt; + u32 srqn; + u32 xrcd; + u32 page_offset; + u32 cqn; + u32 pd; + u32 lwm; + u32 user_index; + u64 db_record; + u64 *pas; +}; + +struct mlx5_core_dev; + void mlx5_init_srq_table(struct mlx5_core_dev *dev); void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev); -- cgit v1.2.3 From d6faca40f40b62aca8ea8c29289c7bf7456172bb Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 1 Jun 2016 16:46:23 +0200 Subject: rtc: move mc146818 helper functions out-of-line The mc146818_get_time/mc146818_set_time functions are rather large inline functions in a global header file and are used in several drivers and in x86 specific code. Here we move them into a separate .c file that is compiled whenever any of the users require it. This also lets us remove the linux/acpi.h header inclusion from mc146818rtc.h, which in turn avoids some warnings about duplicate definition of the TRUE/FALSE macros. Signed-off-by: Arnd Bergmann Signed-off-by: Alexandre Belloni --- include/linux/mc146818rtc.h | 193 +------------------------------------------- 1 file changed, 2 insertions(+), 191 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index e9e346b37846..a585b4b5fa0e 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -17,10 +17,6 @@ #include #include -#ifdef CONFIG_ACPI -#include -#endif - #ifdef __KERNEL__ #include /* spinlock_t */ extern spinlock_t rtc_lock; /* serialize CMOS RAM access */ @@ -126,192 +122,7 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ -/* - * Returns true if a clock update is in progress - */ -static inline unsigned char mc146818_is_updating(void) -{ - unsigned char uip; - unsigned long flags; - - spin_lock_irqsave(&rtc_lock, flags); - uip = (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP); - spin_unlock_irqrestore(&rtc_lock, flags); - return uip; -} - -static inline unsigned int mc146818_get_time(struct rtc_time *time) -{ - unsigned char ctrl; - unsigned long flags; - unsigned char century = 0; - -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_year; -#endif - - /* - * read RTC once any update in progress is done. The update - * can take just over 2ms. We wait 20ms. There is no need to - * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. - * If you need to know *exactly* when a second has started, enable - * periodic update complete interrupts, (via ioctl) and then - * immediately read /dev/rtc which will block until you get the IRQ. - * Once the read clears, read the RTC time (again via ioctl). Easy. - */ - if (mc146818_is_updating()) - mdelay(20); - - /* - * Only the values that we read from the RTC are set. We leave - * tm_wday, tm_yday and tm_isdst untouched. Even though the - * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated - * by the RTC when initially set to a non-zero value. - */ - spin_lock_irqsave(&rtc_lock, flags); - time->tm_sec = CMOS_READ(RTC_SECONDS); - time->tm_min = CMOS_READ(RTC_MINUTES); - time->tm_hour = CMOS_READ(RTC_HOURS); - time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); - time->tm_mon = CMOS_READ(RTC_MONTH); - time->tm_year = CMOS_READ(RTC_YEAR); -#ifdef CONFIG_MACH_DECSTATION - real_year = CMOS_READ(RTC_DEC_YEAR); -#endif -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - century = CMOS_READ(acpi_gbl_FADT.century); -#endif - ctrl = CMOS_READ(RTC_CONTROL); - spin_unlock_irqrestore(&rtc_lock, flags); - - if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - time->tm_sec = bcd2bin(time->tm_sec); - time->tm_min = bcd2bin(time->tm_min); - time->tm_hour = bcd2bin(time->tm_hour); - time->tm_mday = bcd2bin(time->tm_mday); - time->tm_mon = bcd2bin(time->tm_mon); - time->tm_year = bcd2bin(time->tm_year); - century = bcd2bin(century); - } - -#ifdef CONFIG_MACH_DECSTATION - time->tm_year += real_year - 72; -#endif - - if (century) - time->tm_year += (century - 19) * 100; - - /* - * Account for differences between how the RTC uses the values - * and how they are defined in a struct rtc_time; - */ - if (time->tm_year <= 69) - time->tm_year += 100; - - time->tm_mon--; - - return RTC_24H; -} - -/* Set the current date and time in the real time clock. */ -static inline int mc146818_set_time(struct rtc_time *time) -{ - unsigned long flags; - unsigned char mon, day, hrs, min, sec; - unsigned char save_control, save_freq_select; - unsigned int yrs; -#ifdef CONFIG_MACH_DECSTATION - unsigned int real_yrs, leap_yr; -#endif - unsigned char century = 0; - - yrs = time->tm_year; - mon = time->tm_mon + 1; /* tm_mon starts at zero */ - day = time->tm_mday; - hrs = time->tm_hour; - min = time->tm_min; - sec = time->tm_sec; - - if (yrs > 255) /* They are unsigned */ - return -EINVAL; - - spin_lock_irqsave(&rtc_lock, flags); -#ifdef CONFIG_MACH_DECSTATION - real_yrs = yrs; - leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || - !((yrs + 1900) % 400)); - yrs = 72; - - /* - * We want to keep the year set to 73 until March - * for non-leap years, so that Feb, 29th is handled - * correctly. - */ - if (!leap_yr && mon < 3) { - real_yrs--; - yrs = 73; - } -#endif - -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) { - century = (yrs + 1900) / 100; - yrs %= 100; - } -#endif - - /* These limits and adjustments are independent of - * whether the chip is in binary mode or not. - */ - if (yrs > 169) { - spin_unlock_irqrestore(&rtc_lock, flags); - return -EINVAL; - } - - if (yrs >= 100) - yrs -= 100; - - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) - || RTC_ALWAYS_BCD) { - sec = bin2bcd(sec); - min = bin2bcd(min); - hrs = bin2bcd(hrs); - day = bin2bcd(day); - mon = bin2bcd(mon); - yrs = bin2bcd(yrs); - century = bin2bcd(century); - } - - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - -#ifdef CONFIG_MACH_DECSTATION - CMOS_WRITE(real_yrs, RTC_DEC_YEAR); -#endif - CMOS_WRITE(yrs, RTC_YEAR); - CMOS_WRITE(mon, RTC_MONTH); - CMOS_WRITE(day, RTC_DAY_OF_MONTH); - CMOS_WRITE(hrs, RTC_HOURS); - CMOS_WRITE(min, RTC_MINUTES); - CMOS_WRITE(sec, RTC_SECONDS); -#ifdef CONFIG_ACPI - if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && - acpi_gbl_FADT.century) - CMOS_WRITE(century, acpi_gbl_FADT.century); -#endif - - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - spin_unlock_irqrestore(&rtc_lock, flags); - - return 0; -} +unsigned int mc146818_get_time(struct rtc_time *time); +int mc146818_set_time(struct rtc_time *time); #endif /* _MC146818RTC_H */ -- cgit v1.2.3 From d68fa32dccc136bb4e092d53606bb6f5515fa972 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 23:20:37 +0200 Subject: rtc: ds17287: remove unused header ds17287rtc.h is unused since 15beb694c661 ("mips: ip32: add platform data hooks to use DS1685 driver"), remove it. Signed-off-by: Alexandre Belloni --- include/linux/ds17287rtc.h | 66 ---------------------------------------------- 1 file changed, 66 deletions(-) delete mode 100644 include/linux/ds17287rtc.h (limited to 'include/linux') diff --git a/include/linux/ds17287rtc.h b/include/linux/ds17287rtc.h deleted file mode 100644 index d85d3f497b96..000000000000 --- a/include/linux/ds17287rtc.h +++ /dev/null @@ -1,66 +0,0 @@ -/* - * ds17287rtc.h - register definitions for the ds1728[57] RTC / CMOS RAM - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * (C) 2003 Guido Guenther - */ -#ifndef __LINUX_DS17287RTC_H -#define __LINUX_DS17287RTC_H - -#include /* get the user-level API */ -#include - -/* Register A */ -#define DS_REGA_DV2 0x40 /* countdown chain */ -#define DS_REGA_DV1 0x20 /* oscillator enable */ -#define DS_REGA_DV0 0x10 /* bank select */ - -/* bank 1 registers */ -#define DS_B1_MODEL 0x40 /* model number byte */ -#define DS_B1_SN1 0x41 /* serial number byte 1 */ -#define DS_B1_SN2 0x42 /* serial number byte 2 */ -#define DS_B1_SN3 0x43 /* serial number byte 3 */ -#define DS_B1_SN4 0x44 /* serial number byte 4 */ -#define DS_B1_SN5 0x45 /* serial number byte 5 */ -#define DS_B1_SN6 0x46 /* serial number byte 6 */ -#define DS_B1_CRC 0x47 /* CRC byte */ -#define DS_B1_CENTURY 0x48 /* Century byte */ -#define DS_B1_DALARM 0x49 /* date alarm */ -#define DS_B1_XCTRL4A 0x4a /* extendec control register 4a */ -#define DS_B1_XCTRL4B 0x4b /* extendec control register 4b */ -#define DS_B1_RTCADDR2 0x4e /* rtc address 2 */ -#define DS_B1_RTCADDR3 0x4f /* rtc address 3 */ -#define DS_B1_RAMLSB 0x50 /* extended ram LSB */ -#define DS_B1_RAMMSB 0x51 /* extended ram MSB */ -#define DS_B1_RAMDPORT 0x53 /* extended ram data port */ - -/* register details */ -/* extended control register 4a */ -#define DS_XCTRL4A_VRT2 0x80 /* valid ram and time */ -#define DS_XCTRL4A_INCR 0x40 /* increment progress status */ -#define DS_XCTRL4A_BME 0x20 /* burst mode enable */ -#define DS_XCTRL4A_PAB 0x08 /* power active bar ctrl */ -#define DS_XCTRL4A_RF 0x04 /* ram clear flag */ -#define DS_XCTRL4A_WF 0x02 /* wake up alarm flag */ -#define DS_XCTRL4A_KF 0x01 /* kickstart flag */ - -/* interrupt causes */ -#define DS_XCTRL4A_IFS (DS_XCTRL4A_RF|DS_XCTRL4A_WF|DS_XCTRL4A_KF) - -/* extended control register 4b */ -#define DS_XCTRL4B_ABE 0x80 /* auxiliary battery enable */ -#define DS_XCTRL4B_E32K 0x40 /* enable 32.768 kHz Output */ -#define DS_XCTRL4B_CS 0x20 /* crystal select */ -#define DS_XCTRL4B_RCE 0x10 /* ram clear enable */ -#define DS_XCTRL4B_PRS 0x08 /* PAB resec select */ -#define DS_XCTRL4B_RIE 0x04 /* ram clear interrupt enable */ -#define DS_XCTRL4B_WFE 0x02 /* wake up alarm interrupt enable */ -#define DS_XCTRL4B_KFE 0x01 /* kickstart interrupt enable */ - -/* interrupt enable bits */ -#define DS_XCTRL4B_IFES (DS_XCTRL4B_RIE|DS_XCTRL4B_WFE|DS_XCTRL4B_KFE) - -#endif /* __LINUX_DS17287RTC_H */ -- cgit v1.2.3 From 10c2a2e71301deb4d7760c140606bc61841aacd3 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 23:38:44 +0200 Subject: rtc: ds2404: move rtc-ds2404.h to platform_data rtc-ds2404.h belongs to include/linux/platform_data/ Signed-off-by: Alexandre Belloni --- include/linux/platform_data/rtc-ds2404.h | 20 ++++++++++++++++++++ include/linux/rtc-ds2404.h | 20 -------------------- 2 files changed, 20 insertions(+), 20 deletions(-) create mode 100644 include/linux/platform_data/rtc-ds2404.h delete mode 100644 include/linux/rtc-ds2404.h (limited to 'include/linux') diff --git a/include/linux/platform_data/rtc-ds2404.h b/include/linux/platform_data/rtc-ds2404.h new file mode 100644 index 000000000000..22c53825528f --- /dev/null +++ b/include/linux/platform_data/rtc-ds2404.h @@ -0,0 +1,20 @@ +/* + * ds2404.h - platform data structure for the DS2404 RTC. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2012 Sven Schnelle + */ + +#ifndef __LINUX_DS2404_H +#define __LINUX_DS2404_H + +struct ds2404_platform_data { + + unsigned int gpio_rst; + unsigned int gpio_clk; + unsigned int gpio_dq; +}; +#endif diff --git a/include/linux/rtc-ds2404.h b/include/linux/rtc-ds2404.h deleted file mode 100644 index 22c53825528f..000000000000 --- a/include/linux/rtc-ds2404.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * ds2404.h - platform data structure for the DS2404 RTC. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2012 Sven Schnelle - */ - -#ifndef __LINUX_DS2404_H -#define __LINUX_DS2404_H - -struct ds2404_platform_data { - - unsigned int gpio_rst; - unsigned int gpio_clk; - unsigned int gpio_dq; -}; -#endif -- cgit v1.2.3 From 803bb30145df3132f9c8c8704d11a9e6732340c7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Sun, 26 Jun 2016 22:57:52 +0200 Subject: rtc: m48t86: move m48t86.h to platform_data m48t86.h belongs to include/linux/platform_data/ Acked-by: Jason Cooper Acked-by: H Hartley Sweeten Acked-by: Alexander Clouter Signed-off-by: Alexandre Belloni --- include/linux/m48t86.h | 16 ---------------- include/linux/platform_data/rtc-m48t86.h | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 16 deletions(-) delete mode 100644 include/linux/m48t86.h create mode 100644 include/linux/platform_data/rtc-m48t86.h (limited to 'include/linux') diff --git a/include/linux/m48t86.h b/include/linux/m48t86.h deleted file mode 100644 index 915d6b4f0f89..000000000000 --- a/include/linux/m48t86.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * ST M48T86 / Dallas DS12887 RTC driver - * Copyright (c) 2006 Tower Technologies - * - * Author: Alessandro Zummo - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. -*/ - -struct m48t86_ops -{ - void (*writebyte)(unsigned char value, unsigned long addr); - unsigned char (*readbyte)(unsigned long addr); -}; diff --git a/include/linux/platform_data/rtc-m48t86.h b/include/linux/platform_data/rtc-m48t86.h new file mode 100644 index 000000000000..915d6b4f0f89 --- /dev/null +++ b/include/linux/platform_data/rtc-m48t86.h @@ -0,0 +1,16 @@ +/* + * ST M48T86 / Dallas DS12887 RTC driver + * Copyright (c) 2006 Tower Technologies + * + * Author: Alessandro Zummo + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. +*/ + +struct m48t86_ops +{ + void (*writebyte)(unsigned char value, unsigned long addr); + unsigned char (*readbyte)(unsigned long addr); +}; -- cgit v1.2.3 From d4a5f6d71e8bd32f268e738ed39b31a15334cdf7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 27 Jun 2016 00:03:00 +0200 Subject: rtc: ds1286: move header to linux/rtc Move ds1286.h to rtc specific folder. Signed-off-by: Alexandre Belloni --- include/linux/ds1286.h | 52 ---------------------------------------------- include/linux/rtc/ds1286.h | 52 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+), 52 deletions(-) delete mode 100644 include/linux/ds1286.h create mode 100644 include/linux/rtc/ds1286.h (limited to 'include/linux') diff --git a/include/linux/ds1286.h b/include/linux/ds1286.h deleted file mode 100644 index 45ea0aa0aeb9..000000000000 --- a/include/linux/ds1286.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * Copyright (C) 1998, 1999, 2003 Ralf Baechle - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ -#ifndef __LINUX_DS1286_H -#define __LINUX_DS1286_H - -/********************************************************************** - * register summary - **********************************************************************/ -#define RTC_HUNDREDTH_SECOND 0 -#define RTC_SECONDS 1 -#define RTC_MINUTES 2 -#define RTC_MINUTES_ALARM 3 -#define RTC_HOURS 4 -#define RTC_HOURS_ALARM 5 -#define RTC_DAY 6 -#define RTC_DAY_ALARM 7 -#define RTC_DATE 8 -#define RTC_MONTH 9 -#define RTC_YEAR 10 -#define RTC_CMD 11 -#define RTC_WHSEC 12 -#define RTC_WSEC 13 -#define RTC_UNUSED 14 - -/* RTC_*_alarm is always true if 2 MSBs are set */ -# define RTC_ALARM_DONT_CARE 0xC0 - - -/* - * Bits in the month register - */ -#define RTC_EOSC 0x80 -#define RTC_ESQW 0x40 - -/* - * Bits in the Command register - */ -#define RTC_TDF 0x01 -#define RTC_WAF 0x02 -#define RTC_TDM 0x04 -#define RTC_WAM 0x08 -#define RTC_PU_LVL 0x10 -#define RTC_IBH_LO 0x20 -#define RTC_IPSW 0x40 -#define RTC_TE 0x80 - -#endif /* __LINUX_DS1286_H */ diff --git a/include/linux/rtc/ds1286.h b/include/linux/rtc/ds1286.h new file mode 100644 index 000000000000..45ea0aa0aeb9 --- /dev/null +++ b/include/linux/rtc/ds1286.h @@ -0,0 +1,52 @@ +/* + * Copyright (C) 1998, 1999, 2003 Ralf Baechle + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ +#ifndef __LINUX_DS1286_H +#define __LINUX_DS1286_H + +/********************************************************************** + * register summary + **********************************************************************/ +#define RTC_HUNDREDTH_SECOND 0 +#define RTC_SECONDS 1 +#define RTC_MINUTES 2 +#define RTC_MINUTES_ALARM 3 +#define RTC_HOURS 4 +#define RTC_HOURS_ALARM 5 +#define RTC_DAY 6 +#define RTC_DAY_ALARM 7 +#define RTC_DATE 8 +#define RTC_MONTH 9 +#define RTC_YEAR 10 +#define RTC_CMD 11 +#define RTC_WHSEC 12 +#define RTC_WSEC 13 +#define RTC_UNUSED 14 + +/* RTC_*_alarm is always true if 2 MSBs are set */ +# define RTC_ALARM_DONT_CARE 0xC0 + + +/* + * Bits in the month register + */ +#define RTC_EOSC 0x80 +#define RTC_ESQW 0x40 + +/* + * Bits in the Command register + */ +#define RTC_TDF 0x01 +#define RTC_WAF 0x02 +#define RTC_TDM 0x04 +#define RTC_WAM 0x08 +#define RTC_PU_LVL 0x10 +#define RTC_IBH_LO 0x20 +#define RTC_IPSW 0x40 +#define RTC_TE 0x80 + +#endif /* __LINUX_DS1286_H */ -- cgit v1.2.3 From a6a0dbbcfa469cf3e5c4d9522106c0b7b9e9e373 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 14 Jun 2016 11:13:09 +0200 Subject: pwm: Add a helper to prepare a new PWM state The pwm_init_state() helper prepares a new state object containing the current PWM state except for the polarity and period fields which are set to the reference values (those in struct pwm_args). This is particularly useful for PWM users who want to apply a new duty- cycle expressed relatively to the reference period without changing the enable state. Signed-off-by: Boris Brezillon Tested-by: Heiko Stuebner Signed-off-by: Thierry Reding --- include/linux/pwm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 17018f3c066e..a100f6e80738 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -147,6 +147,39 @@ static inline void pwm_get_args(const struct pwm_device *pwm, *args = pwm->args; } +/** + * pwm_init_state() - prepare a new state to be applied with pwm_apply_state() + * @pwm: PWM device + * @state: state to fill with the prepared PWM state + * + * This functions prepares a state that can later be tweaked and applied + * to the PWM device with pwm_apply_state(). This is a convenient function + * that first retrieves the current PWM state and the replaces the period + * and polarity fields with the reference values defined in pwm->args. + * Once the function returns, you can adjust the ->enabled and ->duty_cycle + * fields according to your needs before calling pwm_apply_state(). + * + * ->duty_cycle is initially set to zero to avoid cases where the current + * ->duty_cycle value exceed the pwm_args->period one, which would trigger + * an error if the user calls pwm_apply_state() without adjusting ->duty_cycle + * first. + */ +static inline void pwm_init_state(const struct pwm_device *pwm, + struct pwm_state *state) +{ + struct pwm_args args; + + /* First get the current state. */ + pwm_get_state(pwm, state); + + /* Then fill it with the reference config */ + pwm_get_args(pwm, &args); + + state->period = args.period; + state->polarity = args.polarity; + state->duty_cycle = 0; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM -- cgit v1.2.3 From f6f3bddf7b2b994a927808fcc5a3d07069c35956 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 14 Jun 2016 11:13:10 +0200 Subject: pwm: Add relative duty cycle manipulation helpers The PWM framework expects PWM users to configure the duty cycle in nano- seconds, but many users want to express the duty cycle relatively to the period value (i.e. duty_cycle = 33% of the period). Add the pwm_{get,set}_relative_duty_cycle() helpers to ease this kind of conversion. Signed-off-by: Boris Brezillon Tested-by: Heiko Stuebner Signed-off-by: Thierry Reding --- include/linux/pwm.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index a100f6e80738..fd1092729ed6 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -180,6 +180,61 @@ static inline void pwm_init_state(const struct pwm_device *pwm, state->duty_cycle = 0; } +/** + * pwm_get_relative_duty_cycle() - Get a relative duty cycle value + * @state: PWM state to extract the duty cycle from + * @scale: target scale of the relative duty cycle + * + * This functions converts the absolute duty cycle stored in @state (expressed + * in nanosecond) into a value relative to the period. + * + * For example if you want to get the duty_cycle expressed in percent, call: + * + * pwm_get_state(pwm, &state); + * duty = pwm_get_relative_duty_cycle(&state, 100); + */ +static inline unsigned int +pwm_get_relative_duty_cycle(const struct pwm_state *state, unsigned int scale) +{ + if (!state->period) + return 0; + + return DIV_ROUND_CLOSEST_ULL((u64)state->duty_cycle * scale, + state->period); +} + +/** + * pwm_set_relative_duty_cycle() - Set a relative duty cycle value + * @state: PWM state to fill + * @duty_cycle: relative duty cycle value + * @scale: scale in which @duty_cycle is expressed + * + * This functions converts a relative into an absolute duty cycle (expressed + * in nanoseconds), and puts the result in state->duty_cycle. + * + * For example if you want to configure a 50% duty cycle, call: + * + * pwm_init_state(pwm, &state); + * pwm_set_relative_duty_cycle(&state, 50, 100); + * pwm_apply_state(pwm, &state); + * + * This functions returns -EINVAL if @duty_cycle and/or @scale are + * inconsistent (@scale == 0 or @duty_cycle > @scale). + */ +static inline int +pwm_set_relative_duty_cycle(struct pwm_state *state, unsigned int duty_cycle, + unsigned int scale) +{ + if (!scale || duty_cycle > scale) + return -EINVAL; + + state->duty_cycle = DIV_ROUND_CLOSEST_ULL((u64)duty_cycle * + state->period, + scale); + + return 0; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM -- cgit v1.2.3 From 2b77487f2e8ff7e6496a7f5a08839de9bbb39ab3 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 10 Jun 2016 15:49:53 +0200 Subject: pwm: Remove gratuitous blank line Commit 5ec803edcb70 ("pwm: Add core infrastructure to allow atomic updates") introduced this double blank line by mistake. Signed-off-by: Thierry Reding --- include/linux/pwm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index fd1092729ed6..83d8bcb7e1de 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -408,7 +408,6 @@ static inline void pwm_disable(struct pwm_device *pwm) pwm_apply_state(pwm, &state); } - /* PWM provider APIs */ int pwm_set_chip_data(struct pwm_device *pwm, void *data); void *pwm_get_chip_data(struct pwm_device *pwm); -- cgit v1.2.3 From cd9b518b98d3e989f523e63b2ffda78467a3679e Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 27 Jun 2016 00:03:03 +0200 Subject: rtc: v3020: move rtc-v3020.h to platform_data rtc-v3020.h belongs to include/linux/platform_data/ Acked-by: Robert Jarzmik Signed-off-by: Alexandre Belloni --- include/linux/platform_data/rtc-v3020.h | 41 +++++++++++++++++++++++++++++++++ include/linux/rtc-v3020.h | 41 --------------------------------- 2 files changed, 41 insertions(+), 41 deletions(-) create mode 100644 include/linux/platform_data/rtc-v3020.h delete mode 100644 include/linux/rtc-v3020.h (limited to 'include/linux') diff --git a/include/linux/platform_data/rtc-v3020.h b/include/linux/platform_data/rtc-v3020.h new file mode 100644 index 000000000000..e55d82cebf80 --- /dev/null +++ b/include/linux/platform_data/rtc-v3020.h @@ -0,0 +1,41 @@ +/* + * v3020.h - Registers definition and platform data structure for the v3020 RTC. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 2006, 8D Technologies inc. + */ +#ifndef __LINUX_V3020_H +#define __LINUX_V3020_H + +/* The v3020 has only one data pin but which one + * is used depends on the board. */ +struct v3020_platform_data { + int leftshift; /* (1<<(leftshift)) & readl() */ + + unsigned int use_gpio:1; + unsigned int gpio_cs; + unsigned int gpio_wr; + unsigned int gpio_rd; + unsigned int gpio_io; +}; + +#define V3020_STATUS_0 0x00 +#define V3020_STATUS_1 0x01 +#define V3020_SECONDS 0x02 +#define V3020_MINUTES 0x03 +#define V3020_HOURS 0x04 +#define V3020_MONTH_DAY 0x05 +#define V3020_MONTH 0x06 +#define V3020_YEAR 0x07 +#define V3020_WEEK_DAY 0x08 +#define V3020_WEEK 0x09 + +#define V3020_IS_COMMAND(val) ((val)>=0x0E) + +#define V3020_CMD_RAM2CLOCK 0x0E +#define V3020_CMD_CLOCK2RAM 0x0F + +#endif /* __LINUX_V3020_H */ diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h deleted file mode 100644 index e55d82cebf80..000000000000 --- a/include/linux/rtc-v3020.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * v3020.h - Registers definition and platform data structure for the v3020 RTC. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2006, 8D Technologies inc. - */ -#ifndef __LINUX_V3020_H -#define __LINUX_V3020_H - -/* The v3020 has only one data pin but which one - * is used depends on the board. */ -struct v3020_platform_data { - int leftshift; /* (1<<(leftshift)) & readl() */ - - unsigned int use_gpio:1; - unsigned int gpio_cs; - unsigned int gpio_wr; - unsigned int gpio_rd; - unsigned int gpio_io; -}; - -#define V3020_STATUS_0 0x00 -#define V3020_STATUS_1 0x01 -#define V3020_SECONDS 0x02 -#define V3020_MINUTES 0x03 -#define V3020_HOURS 0x04 -#define V3020_MONTH_DAY 0x05 -#define V3020_MONTH 0x06 -#define V3020_YEAR 0x07 -#define V3020_WEEK_DAY 0x08 -#define V3020_WEEK 0x09 - -#define V3020_IS_COMMAND(val) ((val)>=0x0E) - -#define V3020_CMD_RAM2CLOCK 0x0E -#define V3020_CMD_CLOCK2RAM 0x0F - -#endif /* __LINUX_V3020_H */ -- cgit v1.2.3 From d8d29138b17c9965484427b34cf8046601aef8c4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 2 Jun 2016 16:31:03 +1000 Subject: sunrpc: remove 'inuse' flag from struct cache_detail. This field is not currently in use. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ed03c9f7f908..62a60eeacb0a 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -78,8 +78,6 @@ struct cache_detail { struct hlist_head * hash_table; rwlock_t hash_lock; - atomic_t inuse; /* active user-space update or lookup */ - char *name; void (*cache_put)(struct kref *); -- cgit v1.2.3 From 1adf0c5a4451a100cd9253c1d6e3ca77f4a5a98b Mon Sep 17 00:00:00 2001 From: Andrew Elble Date: Wed, 15 Jun 2016 12:52:07 -0400 Subject: nfs/nfsd: Move useful bitfield ops to a commonly accessible place So these may be used in nfsd as well Signed-off-by: Andrew Elble Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 11 +++++++++++ include/linux/nfs_xdr.h | 11 ----------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index bfed6b367350..c6564ada9beb 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -643,4 +643,15 @@ enum pnfs_update_layout_reason { PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, }; +#define NFS4_OP_MAP_NUM_LONGS \ + DIV_ROUND_UP(LAST_NFS4_OP, 8 * sizeof(unsigned long)) +#define NFS4_OP_MAP_NUM_WORDS \ + (NFS4_OP_MAP_NUM_LONGS * sizeof(unsigned long) / sizeof(u32)) +struct nfs4_op_map { + union { + unsigned long longs[NFS4_OP_MAP_NUM_LONGS]; + u32 words[NFS4_OP_MAP_NUM_WORDS]; + } u; +}; + #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c304a11b5b1a..e66abc2d1f88 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1185,17 +1185,6 @@ struct pnfs_ds_commit_info { struct pnfs_commit_bucket *buckets; }; -#define NFS4_OP_MAP_NUM_LONGS \ - DIV_ROUND_UP(LAST_NFS4_OP, 8 * sizeof(unsigned long)) -#define NFS4_OP_MAP_NUM_WORDS \ - (NFS4_OP_MAP_NUM_LONGS * sizeof(unsigned long) / sizeof(u32)) -struct nfs4_op_map { - union { - unsigned long longs[NFS4_OP_MAP_NUM_LONGS]; - u32 words[NFS4_OP_MAP_NUM_WORDS]; - } u; -}; - struct nfs41_state_protection { u32 how; struct nfs4_op_map enforce; -- cgit v1.2.3 From ff3ac5c3dc2323ba54c3d9ef30ef4942a71b251d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:50 -0400 Subject: SUNRPC: Add a server side per-connection limit Allow the user to limit the number of requests serviced through a single connection, to help prevent faster clients from starving slower clients. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + include/linux/sunrpc/svc_xprt.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 7ca44fb5b675..7321ae933867 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -268,6 +268,7 @@ struct svc_rqst { * cache pages */ #define RQ_VICTIM (5) /* about to be shut down */ #define RQ_BUSY (6) /* request is busy */ +#define RQ_DATA (7) /* request has data */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 79ba50856707..ad899ffed3be 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -69,6 +69,7 @@ struct svc_xprt { struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ + atomic_t xpt_nr_rqsts; /* Number of requests */ struct mutex xpt_mutex; /* to serialize sending data */ spinlock_t xpt_lock; /* protects sk_deferred * and xpt_auth_cache */ -- cgit v1.2.3 From f4a4906e563522aa2eab61cf080460d13b85725c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:52 -0400 Subject: SUNRPC: Remove unused callback xpo_adjust_wspace() Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ad899ffed3be..ab02a457da1f 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -25,7 +25,6 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); int (*xpo_secure_port)(struct svc_rqst *); - void (*xpo_adjust_wspace)(struct svc_xprt *); }; struct svc_xprt_class { -- cgit v1.2.3 From 4f3ccd76572a83278166c12f3e351e74cc03578c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 16:06:15 -0400 Subject: qstr: constify dentry_init_security Signed-off-by: Al Viro --- include/linux/lsm_hooks.h | 2 +- include/linux/security.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 7ae397669d8b..101bf19c0f41 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1356,7 +1356,7 @@ union security_list_options { struct super_block *newsb); int (*sb_parse_opts_str)(char *options, struct security_mnt_opts *opts); int (*dentry_init_security)(struct dentry *dentry, int mode, - struct qstr *name, void **ctx, + const struct qstr *name, void **ctx, u32 *ctxlen); diff --git a/include/linux/security.h b/include/linux/security.h index 14df373ff2ca..7831cd57bcf7 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -240,7 +240,7 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb); int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_dentry_init_security(struct dentry *dentry, int mode, - struct qstr *name, void **ctx, + const struct qstr *name, void **ctx, u32 *ctxlen); int security_inode_alloc(struct inode *inode); @@ -591,7 +591,7 @@ static inline void security_inode_free(struct inode *inode) static inline int security_dentry_init_security(struct dentry *dentry, int mode, - struct qstr *name, + const struct qstr *name, void **ctx, u32 *ctxlen) { -- cgit v1.2.3 From beffb8feb6e26851165ee927e0eb963d6db334b0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 16:34:42 -0400 Subject: qstr: constify instances in nfs Signed-off-by: Al Viro --- include/linux/nfs_xdr.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c304a11b5b1a..890b4aba2711 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1543,7 +1543,7 @@ struct nfs_rpc_ops { struct nfs_fattr *, struct nfs4_label *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct qstr *, + int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); @@ -1551,18 +1551,18 @@ struct nfs_rpc_ops { unsigned int); int (*create) (struct inode *, struct dentry *, struct iattr *, int); - int (*remove) (struct inode *, struct qstr *); + int (*remove) (struct inode *, const struct qstr *); void (*unlink_setup) (struct rpc_message *, struct inode *dir); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); void (*rename_setup) (struct rpc_message *msg, struct inode *dir); void (*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *); int (*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir); - int (*link) (struct inode *, struct inode *, struct qstr *); + int (*link) (struct inode *, struct inode *, const struct qstr *); int (*symlink) (struct inode *, struct dentry *, struct page *, unsigned int, struct iattr *); int (*mkdir) (struct inode *, struct dentry *, struct iattr *); - int (*rmdir) (struct inode *, struct qstr *); + int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, u64, struct page **, unsigned int, int); int (*mknod) (struct inode *, struct dentry *, struct iattr *, -- cgit v1.2.3 From 9aba36dea59264d11cd36219937296b4903c89b6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 20 Jul 2016 22:28:45 -0400 Subject: qstr constify instances in fs/dcache.c Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f53fa055021a..f912a1e5c7cb 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -264,7 +264,7 @@ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); -extern void dentry_update_name_case(struct dentry *, struct qstr *); +extern void dentry_update_name_case(struct dentry *, const struct qstr *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); -- cgit v1.2.3 From 0455e72c9ae9b7e9589f2cc5ba5bc7804be83342 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:38 +0000 Subject: KVM: Add devid in kvm_kernel_irq_routing_entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enhance kvm_kernel_irq_routing_entry to transport the device id field, devid. A new flags field makes possible to indicate the devid is valid. Those additions are used for ARM GICv3 ITS MSI injection. The original struct msi_msg msi field is replaced by a new custom structure that embeds the new fields. Signed-off-by: Eric Auger Suggested-by: Radim Krčmář Acked-by: Radim Krčmář Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 614a98137c5f..a15828fe845c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -317,7 +317,13 @@ struct kvm_kernel_irq_routing_entry { unsigned irqchip; unsigned pin; } irqchip; - struct msi_msg msi; + struct { + u32 address_lo; + u32 address_hi; + u32 data; + u32 flags; + u32 devid; + } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; }; -- cgit v1.2.3 From d9565a7399d665fa7313122504778cb3d5ef3e19 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:40 +0000 Subject: KVM: Move kvm_setup_default/empty_irq_routing declaration in arch specific header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kvm_setup_default_irq_routing and kvm_setup_empty_irq_routing are not used by generic code. So let's move the declarations in x86 irq.h header instead of kvm_host.h. Signed-off-by: Eric Auger Suggested-by: Andre Przywara Acked-by: Radim Krčmář Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a15828fe845c..a7eb5c48251e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1052,8 +1052,6 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #define KVM_MAX_IRQ_ROUTES 1024 #endif -int kvm_setup_default_irq_routing(struct kvm *kvm); -int kvm_setup_empty_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, -- cgit v1.2.3 From 995a0ee9809b6948bb7bfea77f129fe1d5157cc1 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Fri, 22 Jul 2016 16:20:42 +0000 Subject: KVM: arm/arm64: Enable MSI routing Up to now, only irqchip routing entries could be set. This patch adds the capability to insert MSI routing entries. For ARM64, let's also increase KVM_MAX_IRQ_ROUTES to 4096: this include SPI irqchip routes plus MSI routes. In the future this might be extended. Signed-off-by: Eric Auger Reviewed-by: Andre Przywara Signed-off-by: Marc Zyngier --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a7eb5c48251e..a318c3b21608 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1048,6 +1048,8 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #ifdef CONFIG_S390 #define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that... +#elif defined(CONFIG_ARM64) +#define KVM_MAX_IRQ_ROUTES 4096 #else #define KVM_MAX_IRQ_ROUTES 1024 #endif -- cgit v1.2.3 From 7e7ec6a934349ef6983f06f7ac0da09cc8a42983 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Sun, 24 Jul 2016 11:30:18 -0400 Subject: elf_fdpic_transfer_args_to_stack(): make it generic This copying of arguments and environment is common to both NOMMU binary formats we support. Let's make the elf_fdpic version available to the flat format as well. While at it, improve the code a bit not to copy below the actual data area. Signed-off-by: Nicolas Pitre Reviewed-by: Greg Ungerer Signed-off-by: Greg Ungerer --- include/linux/binfmts.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 314b3caa701c..1303b570b18c 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -113,6 +113,8 @@ extern int suid_dumpable; extern int setup_arg_pages(struct linux_binprm * bprm, unsigned long stack_top, int executable_stack); +extern int transfer_args_to_stack(struct linux_binprm *bprm, + unsigned long *sp_location); extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); -- cgit v1.2.3 From 9798ac6d32c1a32d6d92d853ff507d2d39c4300c Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Fri, 15 Jul 2016 16:28:41 -0700 Subject: mfd: cros_ec: Add cros_ec_cmd_xfer_status() helper So that callers of cros_ec_cmd_xfer() don't have to repeat boilerplate code when checking for errors from the EC side. Signed-off-by: Tomeu Vizoso Reviewed-by: Benson Leung Signed-off-by: Brian Norris Acked-by: Lee Jones Tested-by: Enric Balletbo i Serra Signed-off-by: Thierry Reding --- include/linux/mfd/cros_ec.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 64184d27e3cd..d641a18abacb 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -225,6 +225,21 @@ int cros_ec_check_result(struct cros_ec_device *ec_dev, int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); +/** + * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC + * + * This function is identical to cros_ec_cmd_xfer, except it returns success + * status only if both the command was transmitted successfully and the EC + * replied with success status. It's not necessary to check msg->result when + * using this function. + * + * @ec_dev: EC device + * @msg: Message to write + * @return: Num. of bytes transferred on success, <0 on failure + */ +int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, + struct cros_ec_command *msg); + /** * cros_ec_remove - Remove a ChromeOS EC * -- cgit v1.2.3 From 2b66bd692c40034d42d905f37f7f20c3540f185e Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 15 Jul 2016 16:28:42 -0700 Subject: mfd: cros_ec: Add EC_PWM function definitions The EC_CMD_PWM_{GET,SET}_DUTY commands allow us to control a PWM that is attached to the EC, rather than the main host SoC. The API provides functionality-based (e.g., keyboard light, backlight) or index-based addressing of the PWM(s). Duty cycles are represented by a 16-bit value, where 0 maps to 0% duty cycle and U16_MAX maps to 100%. The period cannot be controlled. This command set is more generic than, e.g., EC_CMD_PWM_{GET,SET}_KEYBOARD_BACKLIGHT and could possibly used to replace it on future products. Let's update the command header to include the definitions. Signed-off-by: Brian Norris Acked-by: Lee Jones Signed-off-by: Thierry Reding --- include/linux/mfd/cros_ec_commands.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 13b630c10d4c..7e7a8d4b4551 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -949,6 +949,37 @@ struct ec_params_pwm_set_fan_duty { uint32_t percent; } __packed; +#define EC_CMD_PWM_SET_DUTY 0x25 +/* 16 bit duty cycle, 0xffff = 100% */ +#define EC_PWM_MAX_DUTY 0xffff + +enum ec_pwm_type { + /* All types, indexed by board-specific enum pwm_channel */ + EC_PWM_TYPE_GENERIC = 0, + /* Keyboard backlight */ + EC_PWM_TYPE_KB_LIGHT, + /* Display backlight */ + EC_PWM_TYPE_DISPLAY_LIGHT, + EC_PWM_TYPE_COUNT, +}; + +struct ec_params_pwm_set_duty { + uint16_t duty; /* Duty cycle, EC_PWM_MAX_DUTY = 100% */ + uint8_t pwm_type; /* ec_pwm_type */ + uint8_t index; /* Type-specific index, or 0 if unique */ +} __packed; + +#define EC_CMD_PWM_GET_DUTY 0x26 + +struct ec_params_pwm_get_duty { + uint8_t pwm_type; /* ec_pwm_type */ + uint8_t index; /* Type-specific index, or 0 if unique */ +} __packed; + +struct ec_response_pwm_get_duty { + uint16_t duty; /* Duty cycle, EC_PWM_MAX_DUTY = 100% */ +} __packed; + /*****************************************************************************/ /* * Lightbar commands. This looks worse than it is. Since we only use one HOST -- cgit v1.2.3 From 7c15d9bb8231f998ae7dc0b72415f5215459f7fb Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 19 Jul 2016 15:00:04 -0700 Subject: mm: Add is_migrate_cma_page Code such as hardened user copy[1] needs a way to tell if a page is CMA or not. Add is_migrate_cma_page in a similar way to is_migrate_isolate_page. [1]http://article.gmane.org/gmane.linux.kernel.mm/155238 Signed-off-by: Laura Abbott Signed-off-by: Kees Cook --- include/linux/mmzone.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 02069c23486d..c8478b29f070 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -68,8 +68,10 @@ extern char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false +# define is_migrate_cma_page(_page) false #endif #define for_each_migratetype_order(order, type) \ -- cgit v1.2.3 From 0f60a8efe4005ab5e65ce000724b04d4ca04a199 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 12 Jul 2016 16:19:48 -0700 Subject: mm: Implement stack frame object validation This creates per-architecture function arch_within_stack_frames() that should validate if a given object is contained by a kernel stack frame. Initial implementation is on x86. This is based on code from PaX. Signed-off-by: Kees Cook --- include/linux/thread_info.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index b4c2a485b28a..3d5c80b4391d 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -146,6 +146,15 @@ static inline bool test_and_clear_restore_sigmask(void) #error "no set_restore_sigmask() provided and default one won't work" #endif +#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From f5509cc18daa7f82bcc553be70df2117c8eedc16 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 7 Jun 2016 11:05:33 -0700 Subject: mm: Hardened usercopy This is the start of porting PAX_USERCOPY into the mainline kernel. This is the first set of features, controlled by CONFIG_HARDENED_USERCOPY. The work is based on code by PaX Team and Brad Spengler, and an earlier port from Casey Schaufler. Additional non-slab page tests are from Rik van Riel. This patch contains the logic for validating several conditions when performing copy_to_user() and copy_from_user() on the kernel object being copied to/from: - address range doesn't wrap around - address range isn't NULL or zero-allocated (with a non-zero copy size) - if on the slab allocator: - object size must be less than or equal to copy size (when check is implemented in the allocator, which appear in subsequent patches) - otherwise, object must not span page allocations (excepting Reserved and CMA ranges) - if on the stack - object must not extend before/after the current process stack - object must be contained by a valid stack frame (when there is arch/build support for identifying stack frames) - object must not overlap with kernel text Signed-off-by: Kees Cook Tested-by: Valdis Kletnieks Tested-by: Michael Ellerman --- include/linux/slab.h | 12 ++++++++++++ include/linux/thread_info.h | 15 +++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index aeb3e6d00a66..96a16a3fb7cb 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -155,6 +155,18 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page); +#else +static inline const char *__check_heap_object(const void *ptr, + unsigned long n, + struct page *page) +{ + return NULL; +} +#endif + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 3d5c80b4391d..f24b99eac969 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -155,6 +155,21 @@ static inline int arch_within_stack_frames(const void * const stack, } #endif +#ifdef CONFIG_HARDENED_USERCOPY +extern void __check_object_size(const void *ptr, unsigned long n, + bool to_user); + +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ + __check_object_size(ptr, n, to_user); +} +#else +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ } +#endif /* CONFIG_HARDENED_USERCOPY */ + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ -- cgit v1.2.3 From bf262dcec6383188a3324192c4a7e405b3b1ad23 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Tue, 12 Apr 2016 05:02:09 +0930 Subject: module: fix noreturn attribute for __module_put_and_exit() __module_put_and_exit() is makred noreturn in module.h declaration, but is lacking the attribute in the definition, which makes some tools (such as sparse) unhappy. Amend the definition with the attribute as well (and reformat the declaration so that it uses more common format). Signed-off-by: Jiri Kosina Signed-off-by: Rusty Russell --- include/linux/module.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 3daf2b3a09d2..f777164c238b 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -575,8 +575,8 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); -extern void __module_put_and_exit(struct module *mod, long code) - __attribute__((noreturn)); +extern void __noreturn __module_put_and_exit(struct module *mod, + long code); #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD -- cgit v1.2.3 From 4097461897df91041382ff6fcd2bfa7ee6b2448c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 25 Jul 2016 11:36:54 -0700 Subject: Input: i8042 - break load dependency between atkbd/psmouse and i8042 As explained in 1407814240-4275-1-git-send-email-decui@microsoft.com we have a hard load dependency between i8042 and atkbd which prevents keyboard from working on Gen2 Hyper-V VMs. > hyperv_keyboard invokes serio_interrupt(), which needs a valid serio > driver like atkbd.c. atkbd.c depends on libps2.c because it invokes > ps2_command(). libps2.c depends on i8042.c because it invokes > i8042_check_port_owner(). As a result, hyperv_keyboard actually > depends on i8042.c. > > For a Generation 2 Hyper-V VM (meaning no i8042 device emulated), if a > Linux VM (like Arch Linux) happens to configure CONFIG_SERIO_I8042=m > rather than =y, atkbd.ko can't load because i8042.ko can't load(due to > no i8042 device emulated) and finally hyperv_keyboard can't work and > the user can't input: https://bugs.archlinux.org/task/39820 > (Ubuntu/RHEL/SUSE aren't affected since they use CONFIG_SERIO_I8042=y) To break the dependency we move away from using i8042_check_port_owner() and instead allow serio port owner specify a mutex that clients should use to serialize PS/2 command stream. Reported-by: Mark Laws Tested-by: Mark Laws Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- include/linux/i8042.h | 6 ------ include/linux/serio.h | 24 +++++++++++++++++++----- 2 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i8042.h b/include/linux/i8042.h index 0f9bafa17a02..d98780ca9604 100644 --- a/include/linux/i8042.h +++ b/include/linux/i8042.h @@ -62,7 +62,6 @@ struct serio; void i8042_lock_chip(void); void i8042_unlock_chip(void); int i8042_command(unsigned char *param, int command); -bool i8042_check_port_owner(const struct serio *); int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)); int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str, @@ -83,11 +82,6 @@ static inline int i8042_command(unsigned char *param, int command) return -ENODEV; } -static inline bool i8042_check_port_owner(const struct serio *serio) -{ - return false; -} - static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str, struct serio *serio)) { diff --git a/include/linux/serio.h b/include/linux/serio.h index df4ab5de1586..c733cff44e18 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -31,7 +31,8 @@ struct serio { struct serio_device_id id; - spinlock_t lock; /* protects critical sections from port's interrupt handler */ + /* Protects critical sections from port's interrupt handler */ + spinlock_t lock; int (*write)(struct serio *, unsigned char); int (*open)(struct serio *); @@ -40,16 +41,29 @@ struct serio { void (*stop)(struct serio *); struct serio *parent; - struct list_head child_node; /* Entry in parent->children list */ + /* Entry in parent->children list */ + struct list_head child_node; struct list_head children; - unsigned int depth; /* level of nesting in serio hierarchy */ + /* Level of nesting in serio hierarchy */ + unsigned int depth; - struct serio_driver *drv; /* accessed from interrupt, must be protected by serio->lock and serio->sem */ - struct mutex drv_mutex; /* protects serio->drv so attributes can pin driver */ + /* + * serio->drv is accessed from interrupt handlers; when modifying + * caller should acquire serio->drv_mutex and serio->lock. + */ + struct serio_driver *drv; + /* Protects serio->drv so attributes can pin current driver */ + struct mutex drv_mutex; struct device dev; struct list_head node; + + /* + * For use by PS/2 layer when several ports share hardware and + * may get indigestion when exposed to concurrent access (i8042). + */ + struct mutex *ps2_cmd_mutex; }; #define to_serio_port(d) container_of(d, struct serio, dev) -- cgit v1.2.3 From 6fa67e707559303e086303aeecc9e8b91ef497d5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 31 Jul 2016 16:37:25 -0400 Subject: get rid of 'parent' argument of ->d_compare() Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 98044a8d1487..107d9abe7166 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -130,7 +130,7 @@ struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); - int (*d_compare)(const struct dentry *, const struct dentry *, + int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); -- cgit v1.2.3 From 1a937693993ff10d7e80cca6ddd55f3000aa6376 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 18 Apr 2016 12:58:14 +0300 Subject: virtio: new feature to detect IOMMU device quirk The interaction between virtio and IOMMUs is messy. On most systems with virtio, physical addresses match bus addresses, and it doesn't particularly matter which one we use to program the device. On some systems, including Xen and any system with a physical device that speaks virtio behind a physical IOMMU, we must program the IOMMU for virtio DMA to work at all. On other systems, including SPARC and PPC64, virtio-pci devices are enumerated as though they are behind an IOMMU, but the virtio host ignores the IOMMU, so we must either pretend that the IOMMU isn't there or somehow map everything as the identity. Add a feature bit to detect that quirk: VIRTIO_F_IOMMU_PLATFORM. Any device with this feature bit set to 0 needs a quirk and has to be passed physical addresses (as opposed to bus addresses) even though the device is behind an IOMMU. Note: it has to be a per-device quirk because for example, there could be a mix of passed-through and virtual virtio devices. As another example, some devices could be implemented by an out of process hypervisor backend (in case of qemu vhost, or vhost-user) and so support for an IOMMU needs to be coded up separately. It would be cleanest to handle this in IOMMU core code, but that needs per-device DMA ops. While we are waiting for that to be implemented, use a work-around in virtio core. Note: a "noiommu" feature is a quirk - add a wrapper to make that clear. Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 6e6cb0c9d7cb..26c155bb639b 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -149,6 +149,19 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev, return __virtio_test_bit(vdev, fbit); } +/** + * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * @vdev: the device + */ +static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +{ + /* + * Note the reverse polarity of the quirk feature (compared to most + * other features), this is for compatibility with legacy systems. + */ + return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + static inline struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *c, const char *n) -- cgit v1.2.3 From 06a8fc78367d070720af960dcecec917d3ae5f3b Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 28 Jul 2016 15:36:32 +0100 Subject: VSOCK: Introduce virtio_vsock_common.ko This module contains the common code and header files for the following virtio_transporto and vhost_vsock kernel modules. Signed-off-by: Asias He Signed-off-by: Claudio Imbrenda Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_vsock.h | 154 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 154 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..9638bfeb0d1f --- /dev/null +++ b/include/linux/virtio_vsock.h @@ -0,0 +1,154 @@ +#ifndef _LINUX_VIRTIO_VSOCK_H +#define _LINUX_VIRTIO_VSOCK_H + +#include +#include +#include +#include + +#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 +#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) +#define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL +#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) + +enum { + VSOCK_VQ_RX = 0, /* for host to guest data */ + VSOCK_VQ_TX = 1, /* for guest to host data */ + VSOCK_VQ_EVENT = 2, + VSOCK_VQ_MAX = 3, +}; + +/* Per-socket state (accessed via vsk->trans) */ +struct virtio_vsock_sock { + struct vsock_sock *vsk; + + /* Protected by lock_sock(sk_vsock(trans->vsk)) */ + u32 buf_size; + u32 buf_size_min; + u32 buf_size_max; + + spinlock_t tx_lock; + spinlock_t rx_lock; + + /* Protected by tx_lock */ + u32 tx_cnt; + u32 buf_alloc; + u32 peer_fwd_cnt; + u32 peer_buf_alloc; + + /* Protected by rx_lock */ + u32 fwd_cnt; + u32 rx_bytes; + struct list_head rx_queue; +}; + +struct virtio_vsock_pkt { + struct virtio_vsock_hdr hdr; + struct work_struct work; + struct list_head list; + void *buf; + u32 len; + u32 off; + bool reply; +}; + +struct virtio_vsock_pkt_info { + u32 remote_cid, remote_port; + struct msghdr *msg; + u32 pkt_len; + u16 type; + u16 op; + u32 flags; + bool reply; +}; + +struct virtio_transport { + /* This must be the first field */ + struct vsock_transport transport; + + /* Takes ownership of the packet */ + int (*send_pkt)(struct virtio_vsock_pkt *pkt); +}; + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, + int type); +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk); +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now); +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_available_now); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); +bool virtio_transport_stream_is_active(struct vsock_sock *vsk); +bool virtio_transport_stream_allow(u32 cid, u32 port); +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr); +bool virtio_transport_dgram_allow(u32 cid, u32 port); + +int virtio_transport_connect(struct vsock_sock *vsk); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode); + +void virtio_transport_release(struct vsock_sock *vsk); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t len); + +void virtio_transport_destruct(struct vsock_sock *vsk); + +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); + +#endif /* _LINUX_VIRTIO_VSOCK_H */ -- cgit v1.2.3 From 3e5a4c94a4f88b545d64bbfc7647b06b92c66e98 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 3 Aug 2016 13:44:27 +0200 Subject: vfs: remove file_needs_remove_privs() This function is now unused. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dd288148a6b1..3888341913ef 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2726,10 +2726,6 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); extern int dentry_needs_remove_privs(struct dentry *dentry); -static inline int file_needs_remove_privs(struct file *file) -{ - return dentry_needs_remove_privs(file->f_path.dentry); -} extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) -- cgit v1.2.3 From f0fce87c36aec5c4a895c78b76396f5727047b93 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 3 Aug 2016 13:44:27 +0200 Subject: vfs: make dentry_needs_remove_privs() internal Only used by the vfs. Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3888341913ef..448641bcafc5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2725,7 +2725,6 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); -extern int dentry_needs_remove_privs(struct dentry *dentry); extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) -- cgit v1.2.3 From 0ef7653797addea8ba1bf97f8208a54a62498d94 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 27 Jul 2016 12:06:34 +0930 Subject: exceptions: fork exception table content from module.h into extable.h For historical reasons (i.e. pre-git) the exception table stuff was buried in the middle of the module.h file. I noticed this while doing an audit for needless includes of module.h and found core kernel files (both arch specific and arch independent) were just including module.h for this. The converse is also true, in that conventional drivers, be they for filesystems or actual hardware peripherals or similar, do not normally care about the exception tables. Here we fork the exception table content out of module.h into a new file called extable.h -- and temporarily include it into the module.h itself. Then we will work our way across the arch independent and arch specific files needing just exception table content, and move them off module.h and onto extable.h Once that is done, we can remove the extable.h from module.h and in doing it like this, we avoid introducing build failures into the git history. The gain here is that module.h gets a bit smaller, across all modular drivers that we build for allmodconfig. Also the core files that only need exception table stuff don't have an include of module.h that brings in lots of extra stuff and just looks generally out of place. Cc: Andrew Morton Cc: Linus Torvalds Signed-off-by: Paul Gortmaker Signed-off-by: Rusty Russell --- include/linux/extable.h | 30 ++++++++++++++++++++++++++++++ include/linux/module.h | 27 ++------------------------- 2 files changed, 32 insertions(+), 25 deletions(-) create mode 100644 include/linux/extable.h (limited to 'include/linux') diff --git a/include/linux/extable.h b/include/linux/extable.h new file mode 100644 index 000000000000..2c71dccd1bc3 --- /dev/null +++ b/include/linux/extable.h @@ -0,0 +1,30 @@ +#ifndef _LINUX_EXTABLE_H +#define _LINUX_EXTABLE_H + +struct module; +struct exception_table_entry; + +const struct exception_table_entry * +search_extable(const struct exception_table_entry *first, + const struct exception_table_entry *last, + unsigned long value); +void sort_extable(struct exception_table_entry *start, + struct exception_table_entry *finish); +void sort_main_extable(void); +void trim_init_extable(struct module *m); + +/* Given an address, look for it in the exception tables */ +const struct exception_table_entry *search_exception_tables(unsigned long add); + +#ifdef CONFIG_MODULES +/* For extable.c to search modules' exception tables. */ +const struct exception_table_entry *search_module_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_module_extables(unsigned long addr) +{ + return NULL; +} +#endif /*CONFIG_MODULES*/ + +#endif /* _LINUX_EXTABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index f777164c238b..f95ed243a4de 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -18,6 +18,7 @@ #include #include #include +#include /* only as arch move module.h -> extable.h */ #include #include @@ -37,6 +38,7 @@ struct modversion_info { }; struct module; +struct exception_table_entry; struct module_kobject { struct kobject kobj; @@ -155,18 +157,6 @@ extern void cleanup_module(void); #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ -/* Archs provide a method of finding the correct exception table. */ -struct exception_table_entry; - -const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, - unsigned long value); -void sort_extable(struct exception_table_entry *start, - struct exception_table_entry *finish); -void sort_main_extable(void); -void trim_init_extable(struct module *m); - /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) @@ -268,9 +258,6 @@ extern const typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -/* Given an address, look for it in the exception tables */ -const struct exception_table_entry *search_exception_tables(unsigned long add); - struct notifier_block; #ifdef CONFIG_MODULES @@ -630,9 +617,6 @@ const char *module_address_lookup(unsigned long addr, int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); -/* For extable.c to search modules' exception tables. */ -const struct exception_table_entry *search_module_extables(unsigned long addr); - int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); @@ -657,13 +641,6 @@ static inline bool is_livepatch_module(struct module *mod) #else /* !CONFIG_MODULES... */ -/* Given an address, look for it in the exception tables. */ -static inline const struct exception_table_entry * -search_module_extables(unsigned long addr) -{ - return NULL; -} - static inline struct module *__module_address(unsigned long addr) { return NULL; -- cgit v1.2.3 From 444d13ff10fb13bc3e64859c3cf9ce43dcfeb075 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Wed, 27 Jul 2016 12:06:21 +0930 Subject: modules: add ro_after_init support Add ro_after_init support for modules by adding a new page-aligned section in the module layout (after rodata) for ro_after_init data and enabling RO protection for that section after module init runs. Signed-off-by: Jessica Yu Acked-by: Kees Cook Signed-off-by: Rusty Russell --- include/linux/module.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index f95ed243a4de..0c3207d26ac0 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -298,6 +298,8 @@ struct module_layout { unsigned int text_size; /* Size of RO section of the module (text+rodata) */ unsigned int ro_size; + /* Size of RO after init section */ + unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -765,12 +767,12 @@ extern int module_sysfs_initialized; #ifdef CONFIG_DEBUG_SET_MODULE_RONX extern void set_all_modules_text_rw(void); extern void set_all_modules_text_ro(void); -extern void module_enable_ro(const struct module *mod); +extern void module_enable_ro(const struct module *mod, bool after_init); extern void module_disable_ro(const struct module *mod); #else static inline void set_all_modules_text_rw(void) { } static inline void set_all_modules_text_ro(void) { } -static inline void module_enable_ro(const struct module *mod) { } +static inline void module_enable_ro(const struct module *mod, bool after_init) { } static inline void module_disable_ro(const struct module *mod) { } #endif -- cgit v1.2.3 From 49aadcf1b6f4240751921dad52e86c760d70a5f1 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 27 Jul 2016 23:11:47 -0400 Subject: extable.h: add stddef.h so "NULL" definition is not implicit While not an issue now, eventually we will have independent users of the extable.h file and we will stop sourcing it via module.h header. In testing that pending work, with very sparse builds, characteristic of an "allnoconfig" on various architectures, we can sometimes hit an instance where the very basic standard definitions aren't present, resulting in: include/linux/extable.h:26:9: error: 'NULL' undeclared (first use in this function) To be clear, this isn't a regression, since currently extable.h is only used by module.h -- however, we will need this addition present before we start migrating exception table users off module.h and onto extable.h during the next release cycle. Cc: Rusty Russell Signed-off-by: Paul Gortmaker Signed-off-by: Rusty Russell --- include/linux/extable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/extable.h b/include/linux/extable.h index 2c71dccd1bc3..7effea4b257d 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -1,6 +1,8 @@ #ifndef _LINUX_EXTABLE_H #define _LINUX_EXTABLE_H +#include /* for NULL */ + struct module; struct exception_table_entry; -- cgit v1.2.3 From c7c122ed67e47a7d8033ae21f0cb22a21686194a Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:56 +0300 Subject: net/mlx4: Add diagnostic counters capability bit Add a bit that indicates if the firmware supports per port diagnostic counters. Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 80dec87a94f8..680d110aff05 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -220,6 +220,7 @@ enum { MLX4_DEV_CAP_FLAG2_LB_SRC_CHK = 1ULL << 32, MLX4_DEV_CAP_FLAG2_ROCE_V1_V2 = 1ULL << 33, MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER = 1ULL << 34, + MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, }; enum { -- cgit v1.2.3 From bfaf31687c2628ebb95c58a472d46db3f94c554f Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:57 +0300 Subject: net/mlx4: Query performance and diagnostics counters Add a function to query diagnostics counters from the firmware. Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 680d110aff05..abcce821ac00 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1381,6 +1381,9 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); +int mlx4_query_diag_counters(struct mlx4_dev *dev, u8 op_modifier, + const u32 offset[], u32 value[], + size_t array_len, u8 port); u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port); bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector); struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port); -- cgit v1.2.3 From 3f85f2aaabf785e53bbcd242cb92aeda28990ef5 Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Tue, 19 Jul 2016 20:54:58 +0300 Subject: IB/mlx4: Add diagnostic hardware counters Expose IB diagnostic hardware counters. The counters count IB events and are applicable for IB and RoCE. The counters can be divided into two groups, per device and per port. Device counters are always exposed. Port counters are exposed only if the firmware supports per port counters. rq_num_dup and sq_num_to are only exposed if we have firmware support for them, if we do, we expose them per device and per port. rq_num_udsdprd and num_cqovf are device only counters. rq - denotes responder. sq - denotes requester. |-----------------------|---------------------------------------| | Name | Description | |-----------------------|---------------------------------------| |rq_num_lle | Number of local length errors | |-----------------------|---------------------------------------| |sq_num_lle | number of local length errors | |-----------------------|---------------------------------------| |rq_num_lqpoe | Number of local QP operation errors | |-----------------------|---------------------------------------| |sq_num_lqpoe | Number of local QP operation errors | |-----------------------|---------------------------------------| |rq_num_lpe | Number of local protection errors | |-----------------------|---------------------------------------| |sq_num_lpe | Number of local protection errors | |-----------------------|---------------------------------------| |rq_num_wrfe | Number of CQEs with error | |-----------------------|---------------------------------------| |sq_num_wrfe | Number of CQEs with error | |-----------------------|---------------------------------------| |sq_num_mwbe | Number of Memory Window bind errors | |-----------------------|---------------------------------------| |sq_num_bre | Number of bad response errors | |-----------------------|---------------------------------------| |sq_num_rire | Number of Remote Invalid request | | | errors | |-----------------------|---------------------------------------| |rq_num_rire | Number of Remote Invalid request | | | errors | |-----------------------|---------------------------------------| |sq_num_rae | Number of remote access errors | |-----------------------|---------------------------------------| |rq_num_rae | Number of remote access errors | |-----------------------|---------------------------------------| |sq_num_roe | Number of remote operation errors | |-----------------------|---------------------------------------| |sq_num_tree | Number of transport retries exceeded | | | errors | |-----------------------|---------------------------------------| |sq_num_rree | Number of RNR NAK retries exceeded | | | errors | |-----------------------|---------------------------------------| |rq_num_rnr | Number of RNR NAKs sent | |-----------------------|---------------------------------------| |sq_num_rnr | Number of RNR NAKs received | |-----------------------|---------------------------------------| |rq_num_oos | Number of Out of Sequence requests | | | received | |-----------------------|---------------------------------------| |sq_num_oos | Number of Out of Sequence NAKs | | | received | |-----------------------|---------------------------------------| |rq_num_udsdprd | Number of UD packets silently | | | discarded on the Receive Queue due to | | | lack of receive descriptor | |-----------------------|---------------------------------------| |rq_num_dup | Number of duplicate requests received | |-----------------------|---------------------------------------| |sq_num_to | Number of time out received | |-----------------------|---------------------------------------| |num_cqovf | Number of CQ overflows | |-----------------------|---------------------------------------| Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index abcce821ac00..d73d8e4d3e09 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1341,6 +1341,9 @@ enum { VXLAN_STEER_BY_INNER_VLAN = 1 << 4, }; +enum { + MLX4_OP_MOD_QUERY_TRANSPORT_CI_ERRORS = 0x2, +}; int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode); -- cgit v1.2.3 From 97f2645f358b411ba2afb22e5966753f0ad92916 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 3 Aug 2016 13:45:50 -0700 Subject: tree-wide: replace config_enabled() with IS_ENABLED() The use of config_enabled() against config options is ambiguous. In practical terms, config_enabled() is equivalent to IS_BUILTIN(), but the author might have used it for the meaning of IS_ENABLED(). Using IS_ENABLED(), IS_BUILTIN(), IS_MODULE() etc. makes the intention clearer. This commit replaces config_enabled() with IS_ENABLED() where possible. This commit is only touching bool config options. I noticed two cases where config_enabled() is used against a tristate option: - config_enabled(CONFIG_HWMON) [ drivers/net/wireless/ath/ath10k/thermal.c ] - config_enabled(CONFIG_BACKLIGHT_CLASS_DEVICE) [ drivers/gpu/drm/gma500/opregion.c ] I did not touch them because they should be converted to IS_BUILTIN() in order to keep the logic, but I was not sure it was the authors' intention. Link: http://lkml.kernel.org/r/1465215656-20569-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Kees Cook Cc: Stas Sergeev Cc: Matt Redfearn Cc: Joshua Kinard Cc: Jiri Slaby Cc: Bjorn Helgaas Cc: Borislav Petkov Cc: Markos Chandras Cc: "Dmitry V. Levin" Cc: yu-cheng yu Cc: James Hogan Cc: Brian Gerst Cc: Johannes Berg Cc: Peter Zijlstra Cc: Al Viro Cc: Will Drewry Cc: Nikolay Martynov Cc: Huacai Chen Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: Daniel Borkmann Cc: Leonid Yegoshin Cc: Rafal Milecki Cc: James Cowgill Cc: Greg Kroah-Hartman Cc: Ralf Baechle Cc: Alex Smith Cc: Adam Buchbinder Cc: Qais Yousef Cc: Jiang Liu Cc: Mikko Rapeli Cc: Paul Gortmaker Cc: Denys Vlasenko Cc: Brian Norris Cc: Hidehiro Kawai Cc: "Luis R. Rodriguez" Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Dave Hansen Cc: "Kirill A. Shutemov" Cc: Roland McGrath Cc: Paul Burton Cc: Kalle Valo Cc: Viresh Kumar Cc: Tony Wu Cc: Huaitong Han Cc: Sumit Semwal Cc: Alexei Starovoitov Cc: Juergen Gross Cc: Jason Cooper Cc: "David S. Miller" Cc: Oleg Nesterov Cc: Andrea Gelmini Cc: David Woodhouse Cc: Marc Zyngier Cc: Rabin Vincent Cc: "Maciej W. Rozycki" Cc: David Daney Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fence.h | 2 +- include/linux/ww_mutex.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index 523ea3fbbddd..8cc719a63728 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -358,7 +358,7 @@ u64 fence_context_alloc(unsigned num); #define FENCE_TRACE(f, fmt, args...) \ do { \ struct fence *__ff = (f); \ - if (config_enabled(CONFIG_FENCE_TRACE)) \ + if (IS_ENABLED(CONFIG_FENCE_TRACE)) \ pr_info("f %llu#%u: " fmt, \ __ff->context, __ff->seqno, ##args); \ } while (0) diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 760399a470bd..2bb5deb0012e 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -173,14 +173,14 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) mutex_release(&ctx->dep_map, 0, _THIS_IP_); DEBUG_LOCKS_WARN_ON(ctx->acquired); - if (!config_enabled(CONFIG_PROVE_LOCKING)) + if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) /* * lockdep will normally handle this, * but fail without anyway */ ctx->done_acquire = 1; - if (!config_enabled(CONFIG_DEBUG_LOCK_ALLOC)) + if (!IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC)) /* ensure ww_acquire_fini will still fail if called twice */ ctx->acquired = ~0U; #endif -- cgit v1.2.3 From 4b9d314ce9168b37a2824e6d7820aa6e66f52642 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 3 Aug 2016 13:45:54 -0700 Subject: include/linux/bitmap.h: cleanup Remove two unneeded `else's. Cc: David Hildenbrand Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 27bfc0b631a9..598bc999f4c2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -266,13 +266,12 @@ static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) - return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); + return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); #ifdef CONFIG_S390 - else if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) return !memcmp(src1, src2, nbits / 8); #endif - else - return __bitmap_equal(src1, src2, nbits); + return __bitmap_equal(src1, src2, nbits); } static inline int bitmap_intersects(const unsigned long *src1, -- cgit v1.2.3 From 00085f1efa387a8ce100e3734920f7639c80caa3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 3 Aug 2016 13:46:00 -0700 Subject: dma-mapping: use unsigned long for dma_attrs The dma-mapping core and the implementations do not change the DMA attributes passed by pointer. Thus the pointer can point to const data. However the attributes do not have to be a bitfield. Instead unsigned long will do fine: 1. This is just simpler. Both in terms of reading the code and setting attributes. Instead of initializing local attributes on the stack and passing pointer to it to dma_set_attr(), just set the bits. 2. It brings safeness and checking for const correctness because the attributes are passed by value. Semantic patches for this change (at least most of them): virtual patch virtual context @r@ identifier f, attrs; @@ f(..., - struct dma_attrs *attrs + unsigned long attrs , ...) { ... } @@ identifier r.f; @@ f(..., - NULL + 0 ) and // Options: --all-includes virtual patch virtual context @r@ identifier f, attrs; type t; @@ t f(..., struct dma_attrs *attrs); @@ identifier r.f; @@ f(..., - NULL + 0 ) Link: http://lkml.kernel.org/r/1468399300-5399-2-git-send-email-k.kozlowski@samsung.com Signed-off-by: Krzysztof Kozlowski Acked-by: Vineet Gupta Acked-by: Robin Murphy Acked-by: Hans-Christian Noren Egtvedt Acked-by: Mark Salter [c6x] Acked-by: Jesper Nilsson [cris] Acked-by: Daniel Vetter [drm] Reviewed-by: Bart Van Assche Acked-by: Joerg Roedel [iommu] Acked-by: Fabien Dessenne [bdisp] Reviewed-by: Marek Szyprowski [vb2-core] Acked-by: David Vrabel [xen] Acked-by: Konrad Rzeszutek Wilk [xen swiotlb] Acked-by: Joerg Roedel [iommu] Acked-by: Richard Kuo [hexagon] Acked-by: Geert Uytterhoeven [m68k] Acked-by: Gerald Schaefer [s390] Acked-by: Bjorn Andersson Acked-by: Hans-Christian Noren Egtvedt [avr32] Acked-by: Vineet Gupta [arc] Acked-by: Robin Murphy [arm64 and dma-iommu] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dma-attrs.h | 71 ------------------------ include/linux/dma-iommu.h | 6 +-- include/linux/dma-mapping.h | 128 +++++++++++++++++++++++++++++--------------- include/linux/swiotlb.h | 10 ++-- 4 files changed, 92 insertions(+), 123 deletions(-) delete mode 100644 include/linux/dma-attrs.h (limited to 'include/linux') diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h deleted file mode 100644 index 5246239a4953..000000000000 --- a/include/linux/dma-attrs.h +++ /dev/null @@ -1,71 +0,0 @@ -#ifndef _DMA_ATTR_H -#define _DMA_ATTR_H - -#include -#include -#include - -/** - * an enum dma_attr represents an attribute associated with a DMA - * mapping. The semantics of each attribute should be defined in - * Documentation/DMA-attributes.txt. - */ -enum dma_attr { - DMA_ATTR_WRITE_BARRIER, - DMA_ATTR_WEAK_ORDERING, - DMA_ATTR_WRITE_COMBINE, - DMA_ATTR_NON_CONSISTENT, - DMA_ATTR_NO_KERNEL_MAPPING, - DMA_ATTR_SKIP_CPU_SYNC, - DMA_ATTR_FORCE_CONTIGUOUS, - DMA_ATTR_ALLOC_SINGLE_PAGES, - DMA_ATTR_MAX, -}; - -#define __DMA_ATTRS_LONGS BITS_TO_LONGS(DMA_ATTR_MAX) - -/** - * struct dma_attrs - an opaque container for DMA attributes - * @flags - bitmask representing a collection of enum dma_attr - */ -struct dma_attrs { - unsigned long flags[__DMA_ATTRS_LONGS]; -}; - -#define DEFINE_DMA_ATTRS(x) \ - struct dma_attrs x = { \ - .flags = { [0 ... __DMA_ATTRS_LONGS-1] = 0 }, \ - } - -static inline void init_dma_attrs(struct dma_attrs *attrs) -{ - bitmap_zero(attrs->flags, __DMA_ATTRS_LONGS); -} - -/** - * dma_set_attr - set a specific attribute - * @attr: attribute to set - * @attrs: struct dma_attrs (may be NULL) - */ -static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs) -{ - if (attrs == NULL) - return; - BUG_ON(attr >= DMA_ATTR_MAX); - __set_bit(attr, attrs->flags); -} - -/** - * dma_get_attr - check for a specific attribute - * @attr: attribute to set - * @attrs: struct dma_attrs (may be NULL) - */ -static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs) -{ - if (attrs == NULL) - return 0; - BUG_ON(attr >= DMA_ATTR_MAX); - return test_bit(attr, attrs->flags); -} - -#endif /* _DMA_ATTR_H */ diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h index 8443bbb5c071..81c5c8d167ad 100644 --- a/include/linux/dma-iommu.h +++ b/include/linux/dma-iommu.h @@ -39,7 +39,7 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent); * the arch code to take care of attributes and cache maintenance */ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, - struct dma_attrs *attrs, int prot, dma_addr_t *handle, + unsigned long attrs, int prot, dma_addr_t *handle, void (*flush_page)(struct device *, const void *, phys_addr_t)); void iommu_dma_free(struct device *dev, struct page **pages, size_t size, dma_addr_t *handle); @@ -56,9 +56,9 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, * directly as DMA mapping callbacks for simplicity */ void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, unsigned long attrs); void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, unsigned long attrs); int iommu_dma_supported(struct device *dev, u64 mask); int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr); diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 71c1b215ef66..66533e18276c 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -5,13 +5,58 @@ #include #include #include -#include #include #include #include #include #include +/** + * List of possible attributes associated with a DMA mapping. The semantics + * of each attribute should be defined in Documentation/DMA-attributes.txt. + * + * DMA_ATTR_WRITE_BARRIER: DMA to a memory region with this attribute + * forces all pending DMA writes to complete. + */ +#define DMA_ATTR_WRITE_BARRIER (1UL << 0) +/* + * DMA_ATTR_WEAK_ORDERING: Specifies that reads and writes to the mapping + * may be weakly ordered, that is that reads and writes may pass each other. + */ +#define DMA_ATTR_WEAK_ORDERING (1UL << 1) +/* + * DMA_ATTR_WRITE_COMBINE: Specifies that writes to the mapping may be + * buffered to improve performance. + */ +#define DMA_ATTR_WRITE_COMBINE (1UL << 2) +/* + * DMA_ATTR_NON_CONSISTENT: Lets the platform to choose to return either + * consistent or non-consistent memory as it sees fit. + */ +#define DMA_ATTR_NON_CONSISTENT (1UL << 3) +/* + * DMA_ATTR_NO_KERNEL_MAPPING: Lets the platform to avoid creating a kernel + * virtual mapping for the allocated buffer. + */ +#define DMA_ATTR_NO_KERNEL_MAPPING (1UL << 4) +/* + * DMA_ATTR_SKIP_CPU_SYNC: Allows platform code to skip synchronization of + * the CPU cache for the given buffer assuming that it has been already + * transferred to 'device' domain. + */ +#define DMA_ATTR_SKIP_CPU_SYNC (1UL << 5) +/* + * DMA_ATTR_FORCE_CONTIGUOUS: Forces contiguous allocation of the buffer + * in physical memory. + */ +#define DMA_ATTR_FORCE_CONTIGUOUS (1UL << 6) +/* + * DMA_ATTR_ALLOC_SINGLE_PAGES: This is a hint to the DMA-mapping subsystem + * that it's probably not worth the time to try to allocate memory to in a way + * that gives better TLB efficiency. + */ +#define DMA_ATTR_ALLOC_SINGLE_PAGES (1UL << 7) + /* * A dma_addr_t can hold any valid DMA or bus address for the platform. * It can be given to a device to use as a DMA source or target. A CPU cannot @@ -21,34 +66,35 @@ struct dma_map_ops { void* (*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs); + unsigned long attrs); void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, - struct dma_attrs *attrs); + unsigned long attrs); int (*mmap)(struct device *, struct vm_area_struct *, - void *, dma_addr_t, size_t, struct dma_attrs *attrs); + void *, dma_addr_t, size_t, + unsigned long attrs); int (*get_sgtable)(struct device *dev, struct sg_table *sgt, void *, - dma_addr_t, size_t, struct dma_attrs *attrs); + dma_addr_t, size_t, unsigned long attrs); dma_addr_t (*map_page)(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*unmap_page)(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); /* * map_sg returns 0 on error and a value > 0 on success. * It should never return a value < 0. */ int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir); @@ -123,7 +169,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); dma_addr_t addr; @@ -142,7 +188,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr, static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -158,7 +204,7 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr, */ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); int i, ents; @@ -176,7 +222,7 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -195,7 +241,7 @@ static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, kmemcheck_mark_initialized(page_address(page) + offset, size); BUG_ON(!valid_dma_direction(dir)); - addr = ops->map_page(dev, page, offset, size, dir, NULL); + addr = ops->map_page(dev, page, offset, size, dir, 0); debug_dma_map_page(dev, page, offset, size, dir, addr, false); return addr; @@ -208,7 +254,7 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, BUG_ON(!valid_dma_direction(dir)); if (ops->unmap_page) - ops->unmap_page(dev, addr, size, dir, NULL); + ops->unmap_page(dev, addr, size, dir, 0); debug_dma_unmap_page(dev, addr, size, dir, false); } @@ -289,10 +335,10 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } -#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL) -#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL) -#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL) -#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL) +#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, 0) +#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0) +#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0) +#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0) extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size); @@ -321,7 +367,7 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags); */ static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); @@ -330,7 +376,7 @@ dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); } -#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL) +#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0) int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, @@ -338,7 +384,8 @@ dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, static inline int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, - dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs) + dma_addr_t dma_addr, size_t size, + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); BUG_ON(!ops); @@ -348,7 +395,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size); } -#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL) +#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0) #ifndef arch_dma_alloc_attrs #define arch_dma_alloc_attrs(dev, flag) (true) @@ -356,7 +403,7 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr, static inline void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); void *cpu_addr; @@ -378,7 +425,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, static inline void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle, - struct dma_attrs *attrs) + unsigned long attrs) { struct dma_map_ops *ops = get_dma_ops(dev); @@ -398,31 +445,27 @@ static inline void dma_free_attrs(struct device *dev, size_t size, static inline void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { - return dma_alloc_attrs(dev, size, dma_handle, flag, NULL); + return dma_alloc_attrs(dev, size, dma_handle, flag, 0); } static inline void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { - return dma_free_attrs(dev, size, cpu_addr, dma_handle, NULL); + return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - DEFINE_DMA_ATTRS(attrs); - - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs); - return dma_alloc_attrs(dev, size, dma_handle, gfp, &attrs); + return dma_alloc_attrs(dev, size, dma_handle, gfp, + DMA_ATTR_NON_CONSISTENT); } static inline void dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { - DEFINE_DMA_ATTRS(attrs); - - dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs); - dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs); + dma_free_attrs(dev, size, cpu_addr, dma_handle, + DMA_ATTR_NON_CONSISTENT); } static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -646,9 +689,8 @@ static inline void dmam_release_declared_memory(struct device *dev) static inline void *dma_alloc_wc(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t gfp) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_alloc_attrs(dev, size, dma_addr, gfp, &attrs); + return dma_alloc_attrs(dev, size, dma_addr, gfp, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_alloc_writecombine #define dma_alloc_writecombine dma_alloc_wc @@ -657,9 +699,8 @@ static inline void *dma_alloc_wc(struct device *dev, size_t size, static inline void dma_free_wc(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_free_attrs(dev, size, cpu_addr, dma_addr, &attrs); + return dma_free_attrs(dev, size, cpu_addr, dma_addr, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_free_writecombine #define dma_free_writecombine dma_free_wc @@ -670,9 +711,8 @@ static inline int dma_mmap_wc(struct device *dev, void *cpu_addr, dma_addr_t dma_addr, size_t size) { - DEFINE_DMA_ATTRS(attrs); - dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs); - return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs); + return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, + DMA_ATTR_WRITE_COMBINE); } #ifndef dma_mmap_writecombine #define dma_mmap_writecombine dma_mmap_wc diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 017fced60242..5f81f8a187f2 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -6,7 +6,6 @@ #include struct device; -struct dma_attrs; struct page; struct scatterlist; @@ -68,10 +67,10 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, extern dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, @@ -83,12 +82,13 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, extern int swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, struct dma_attrs *attrs); + enum dma_data_direction dir, + unsigned long attrs); extern void swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, - struct dma_attrs *attrs); + unsigned long attrs); extern void swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, -- cgit v1.2.3 From 1f69bf9c6137602cd028c96b4f8329121ec89231 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 3 Aug 2016 13:46:36 -0700 Subject: jump_label: remove bug.h, atomic.h dependencies for HAVE_JUMP_LABEL The current jump_label.h includes bug.h for things such as WARN_ON(). This makes the header problematic for inclusion by kernel.h or any headers that kernel.h includes, since bug.h includes kernel.h (circular dependency). The inclusion of atomic.h is similarly problematic. Thus, this should make jump_label.h 'includable' from most places. Link: http://lkml.kernel.org/r/7060ce35ddd0d20b33bf170685e6b0fab816bdf2.1467837322.git.jbaron@akamai.com Signed-off-by: Jason Baron Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Heiko Carstens Cc: Joe Perches Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/jump_label.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 68904469fba1..661af564fae8 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -76,7 +76,6 @@ #include #include -#include extern bool static_key_initialized; @@ -115,20 +114,8 @@ enum jump_label_type { struct module; -#include - #ifdef HAVE_JUMP_LABEL -static inline int static_key_count(struct static_key *key) -{ - /* - * -1 means the first static_key_slow_inc() is in progress. - * static_key_enabled() must return true, so return 1 here. - */ - int n = atomic_read(&key->enabled); - return n >= 0 ? n : 1; -} - #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_MASK 1UL @@ -157,16 +144,29 @@ extern int jump_label_text_reserved(void *start, void *end); extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern void jump_label_apply_nops(struct module *mod); +extern int static_key_count(struct static_key *key); +extern void static_key_enable(struct static_key *key); +extern void static_key_disable(struct static_key *key); +/* + * We should be using ATOMIC_INIT() for initializing .enabled, but + * the inclusion of atomic.h is problematic for inclusion of jump_label.h + * in 'low-level' headers. Thus, we are initializing .enabled with a + * raw value, but have added a BUILD_BUG_ON() to catch any issues in + * jump_label_init() see: kernel/jump_label.c. + */ #define STATIC_KEY_INIT_TRUE \ - { .enabled = ATOMIC_INIT(1), \ + { .enabled = { 1 }, \ .entries = (void *)JUMP_TYPE_TRUE } #define STATIC_KEY_INIT_FALSE \ - { .enabled = ATOMIC_INIT(0), \ + { .enabled = { 0 }, \ .entries = (void *)JUMP_TYPE_FALSE } #else /* !HAVE_JUMP_LABEL */ +#include +#include + static inline int static_key_count(struct static_key *key) { return atomic_read(&key->enabled); @@ -216,14 +216,6 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } -#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } - -#endif /* HAVE_JUMP_LABEL */ - -#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE -#define jump_label_enabled static_key_enabled - static inline void static_key_enable(struct static_key *key) { int count = static_key_count(key); @@ -244,6 +236,14 @@ static inline void static_key_disable(struct static_key *key) static_key_slow_dec(key); } +#define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } +#define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } + +#endif /* HAVE_JUMP_LABEL */ + +#define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE +#define jump_label_enabled static_key_enabled + /* -------------------------------------------------------------------------- */ /* -- cgit v1.2.3 From 9049fc745300c5e2236cbfc69f5e8cadb6f1f57c Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 3 Aug 2016 13:46:39 -0700 Subject: dynamic_debug: add jump label support Although dynamic debug is often only used for debug builds, sometimes its enabled for production builds as well. Minimize its impact by using jump labels. This reduces the text section by 7000+ bytes in the kernel image below. It does increase data, but this should only be referenced when changing the direction of the branches, and hence usually not in cache. text data bss dec hex filename 8194852 4879776 925696 14000324 d5a0c4 vmlinux.pre 8187337 4960224 925696 14073257 d6bda9 vmlinux.post Link: http://lkml.kernel.org/r/d165b465e8c89bc582d973758d40be44c33f018b.1467837322.git.jbaron@akamai.com Signed-off-by: Jason Baron Cc: "David S. Miller" Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Heiko Carstens Cc: Joe Perches Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Paul Mackerras Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dynamic_debug.h | 60 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 54 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4f1bbc68cd1b..546d68057e3b 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,6 +1,10 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +#include +#endif + /* * An instance of this structure is created in a special * ELF section at every dynamic debug callsite. At runtime, @@ -33,6 +37,12 @@ struct _ddebug { #define _DPRINTK_FLAGS_DEFAULT 0 #endif unsigned int flags:8; +#ifdef HAVE_JUMP_LABEL + union { + struct static_key_true dd_key_true; + struct static_key_false dd_key_false; + } key; +#endif } __attribute__((aligned(8))); @@ -60,7 +70,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor, const struct net_device *dev, const char *fmt, ...); -#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ +#define DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, key, init) \ static struct _ddebug __aligned(8) \ __attribute__((section("__verbose"))) name = { \ .modname = KBUILD_MODNAME, \ @@ -68,13 +78,51 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor, .filename = __FILE__, \ .format = (fmt), \ .lineno = __LINE__, \ - .flags = _DPRINTK_FLAGS_DEFAULT, \ + .flags = _DPRINTK_FLAGS_DEFAULT, \ + dd_key_init(key, init) \ } +#ifdef HAVE_JUMP_LABEL + +#define dd_key_init(key, init) key = (init) + +#ifdef DEBUG +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, .key.dd_key_true, \ + (STATIC_KEY_TRUE_INIT)) + +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + static_branch_likely(&descriptor.key.dd_key_true) +#else +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, .key.dd_key_false, \ + (STATIC_KEY_FALSE_INIT)) + +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + static_branch_unlikely(&descriptor.key.dd_key_false) +#endif + +#else + +#define dd_key_init(key, init) + +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + DEFINE_DYNAMIC_DEBUG_METADATA_KEY(name, fmt, 0, 0) + +#ifdef DEBUG +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + likely(descriptor.flags & _DPRINTK_FLAGS_PRINT) +#else +#define DYNAMIC_DEBUG_BRANCH(descriptor) \ + unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) +#endif + +#endif + #define dynamic_pr_debug(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) @@ -82,7 +130,7 @@ do { \ #define dynamic_dev_dbg(dev, fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_dev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) @@ -90,7 +138,7 @@ do { \ #define dynamic_netdev_dbg(dev, fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ __dynamic_netdev_dbg(&descriptor, dev, fmt, \ ##__VA_ARGS__); \ } while (0) @@ -100,7 +148,7 @@ do { \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, \ __builtin_constant_p(prefix_str) ? prefix_str : "hexdump");\ - if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \ + if (DYNAMIC_DEBUG_BRANCH(descriptor)) \ print_hex_dump(KERN_DEBUG, prefix_str, \ prefix_type, rowsize, groupsize, \ buf, len, ascii); \ -- cgit v1.2.3 From 20bd723ec6a3261df5e02250cd3a1fbb09a343f2 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Wed, 27 Jul 2016 07:22:05 +0200 Subject: block: add missing group association in bio-cloning functions When a bio is cloned, the newly created bio must be associated with the same blkcg as the original bio (if BLK_CGROUP is enabled). If this operation is not performed, then the new bio is not associated with any group, and the group of the current task is returned when the group of the bio is requested. Depending on the cloning frequency, this may cause a large percentage of the bios belonging to a given group to be treated as if belonging to other groups (in most cases as if belonging to the root group). The expected group isolation may thereby be broken. This commit adds the missing association in bio-cloning functions. Fixes: da2f0f74cf7d ("Btrfs: add support for blkio controllers") Cc: stable@vger.kernel.org # v4.3+ Signed-off-by: Paolo Valente Reviewed-by: Nikolay Borisov Reviewed-by: Jeff Moyer Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 583c10810e32..e09a8895fc31 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -470,11 +470,14 @@ extern unsigned int bvec_nr_vecs(unsigned short idx); int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM -- cgit v1.2.3 From df08c32ce3be5be138c1dbfcba203314a3a7cd6f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 31 Jul 2016 11:15:13 -0700 Subject: block: fix bdi vs gendisk lifetime mismatch The name for a bdi of a gendisk is derived from the gendisk's devt. However, since the gendisk is destroyed before the bdi it leaves a window where a new gendisk could dynamically reuse the same devt while a bdi with the same name is still live. Arrange for the bdi to hold a reference against its "owner" disk device while it is registered. Otherwise we can hit sysfs duplicate name collisions like the following: WARNING: CPU: 10 PID: 2078 at fs/sysfs/dir.c:31 sysfs_warn_dup+0x64/0x80 sysfs: cannot create duplicate filename '/devices/virtual/bdi/259:1' Hardware name: HP ProLiant DL580 Gen8, BIOS P79 05/06/2015 0000000000000286 0000000002c04ad5 ffff88006f24f970 ffffffff8134caec ffff88006f24f9c0 0000000000000000 ffff88006f24f9b0 ffffffff8108c351 0000001f0000000c ffff88105d236000 ffff88105d1031e0 ffff8800357427f8 Call Trace: [] dump_stack+0x63/0x87 [] __warn+0xd1/0xf0 [] warn_slowpath_fmt+0x5f/0x80 [] sysfs_warn_dup+0x64/0x80 [] sysfs_create_dir_ns+0x7e/0x90 [] kobject_add_internal+0xaa/0x320 [] ? vsnprintf+0x34e/0x4d0 [] kobject_add+0x75/0xd0 [] ? mutex_lock+0x12/0x2f [] device_add+0x125/0x610 [] device_create_groups_vargs+0xd8/0x100 [] device_create_vargs+0x1c/0x20 [] bdi_register+0x8c/0x180 [] bdi_register_dev+0x27/0x30 [] add_disk+0x175/0x4a0 Cc: Reported-by: Yi Zhang Tested-by: Yi Zhang Signed-off-by: Dan Williams Fixed up missing 0 return in bdi_register_owner(). Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + include/linux/backing-dev.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 3f103076d0bf..c357f27d5483 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -163,6 +163,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 491a91717788..43b93a947e61 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -24,6 +24,7 @@ __printf(3, 4) int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...); int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); +int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); int __must_check bdi_setup_and_register(struct backing_dev_info *, char *); -- cgit v1.2.3 From 6d25ec147e3a71858bed5439c92accd7f739a0a3 Mon Sep 17 00:00:00 2001 From: John Pittman Date: Mon, 1 Aug 2016 16:35:53 -0400 Subject: Include: blkdev: Removed duplicate 'struct request;' declaration. In include/linux/blkdev.h duplicate declarations of the request struct exist. Cleaned up by removing the second, unneeded declaration. Signed-off-by: John Pittman Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index adf33079771e..de7935961c27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -47,7 +47,6 @@ struct pr_ops; */ #define BLKCG_MAX_POLS 2 -struct request; typedef void (rq_end_io_fn)(struct request *, int); #define BLK_RL_SYNCFULL (1U << 0) -- cgit v1.2.3 From abf545484d31b68777a85c5c8f5b4bcde08283eb Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Thu, 4 Aug 2016 14:23:34 -0600 Subject: mm/block: convert rw_page users to bio op use The rw_page users were not converted to use bio/req ops. As a result bdev_write_page is not passing down REQ_OP_WRITE and the IOs will be sent down as reads. Signed-off-by: Mike Christie Fixes: 4e1b2d52a80d ("block, fs, drivers: remove REQ_OP compat defs and related code") Modified by me to: 1) Drop op_flags passing into ->rw_page(), as we don't use it. 2) Make op_is_write() and friends safe to use for !CONFIG_BLOCK Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 22 +++++++++++----------- include/linux/blkdev.h | 2 +- include/linux/fs.h | 3 ++- include/linux/pagemap.h | 2 +- 4 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb264924..14b28ff2caf8 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,6 +18,17 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ +}; + +#define REQ_OP_BITS 3 + #ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and @@ -228,17 +239,6 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ -}; - -#define REQ_OP_BITS 3 - typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index de7935961c27..ccd68c0d01de 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1672,7 +1672,7 @@ struct blk_dax_ctl { struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); + int (*rw_page)(struct block_device *, sector_t, struct page *, int op); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, diff --git a/include/linux/fs.h b/include/linux/fs.h index f3f0b4c8e8ac..498255e6914e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2480,12 +2480,13 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK static inline bool op_is_write(unsigned int op) { return op == REQ_OP_READ ? false : true; } +#ifdef CONFIG_BLOCK + /* * return data direction, READ or WRITE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 81363b834900..45786374abbd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -void page_endio(struct page *page, int rw, int err); +void page_endio(struct page *page, int op, int err); /* * Add an arbitrary waiter to a page's wait queue -- cgit v1.2.3 From 3851f1cdb2b8d507b10395fc110d4c37d6121285 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 4 Aug 2016 00:08:45 -0400 Subject: SUNRPC: Limit the reconnect backoff timer to the max RPC message timeout ...and ensure that we propagate it to new transports on the same client. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5e3e1b63dbb3..a16070dd03ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -218,7 +218,8 @@ struct rpc_xprt { struct work_struct task_cleanup; struct timer_list timer; unsigned long last_used, - idle_timeout; + idle_timeout, + max_reconnect_timeout; /* * Send stuff -- cgit v1.2.3 From 8d480326c3d6921ff5f1cc988c993bd572248deb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 5 Aug 2016 19:03:31 -0400 Subject: NFSv4: Cap the transport reconnection timer at 1/2 lease period We don't want to miss a lease period renewal due to the TCP connection failing to reconnect in a timely fashion. To ensure this doesn't happen, cap the reconnection timer so that we retry the connection attempt at least every 1/2 lease period. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b6810c92b8bb..5c02b0691587 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -195,6 +195,8 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); +void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + unsigned long timeo); const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ -- cgit v1.2.3 From c11f0c0b5bb949673e4fc16c742f0316ae4ced20 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2016 08:11:04 -0600 Subject: block/mm: make bdev_ops->rw_page() take a bool for read/write Commit abf545484d31 changed it from an 'rw' flags type to the newer ops based interface, but now we're effectively leaking some bdev internals to the rest of the kernel. Since we only care about whether it's a read or a write at that level, just pass in a bool 'is_write' parameter instead. Then we can also move op_is_write() and friends back under CONFIG_BLOCK protection. Reviewed-by: Mike Christie Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 22 +++++++++++----------- include/linux/blkdev.h | 2 +- include/linux/fs.h | 3 +-- include/linux/pagemap.h | 2 +- 4 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 14b28ff2caf8..f254eb264924 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -18,17 +18,6 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); typedef void (bio_destructor_t) (struct bio *); -enum req_op { - REQ_OP_READ, - REQ_OP_WRITE, - REQ_OP_DISCARD, /* request to discard sectors */ - REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ - REQ_OP_WRITE_SAME, /* write same block many times */ - REQ_OP_FLUSH, /* request for cache flush */ -}; - -#define REQ_OP_BITS 3 - #ifdef CONFIG_BLOCK /* * main unit of I/O for the block layer and lower layers (ie drivers and @@ -239,6 +228,17 @@ enum rq_flag_bits { #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) +enum req_op { + REQ_OP_READ, + REQ_OP_WRITE, + REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ + REQ_OP_WRITE_SAME, /* write same block many times */ + REQ_OP_FLUSH, /* request for cache flush */ +}; + +#define REQ_OP_BITS 3 + typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U #define BLK_QC_T_SHIFT 16 diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ccd68c0d01de..2c210b6a7bcf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1672,7 +1672,7 @@ struct blk_dax_ctl { struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); - int (*rw_page)(struct block_device *, sector_t, struct page *, int op); + int (*rw_page)(struct block_device *, sector_t, struct page *, bool); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *, diff --git a/include/linux/fs.h b/include/linux/fs.h index 33f0e96db06f..3523bf62f328 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2480,13 +2480,12 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); +#ifdef CONFIG_BLOCK static inline bool op_is_write(unsigned int op) { return op == REQ_OP_READ ? false : true; } -#ifdef CONFIG_BLOCK - /* * return data direction, READ or WRITE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 45786374abbd..66a1260b33de 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -510,7 +510,7 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); -void page_endio(struct page *page, int op, int err); +void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue -- cgit v1.2.3 From 1eff9d322a444245c67515edb52bc0eb68374aa8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2016 15:35:16 -0600 Subject: block: rename bio bi_rw to bi_opf Since commit 63a4cc24867d, bio->bi_rw contains flags in the lower portion and the op code in the higher portions. This means that old code that relies on manually setting bi_rw is most likely going to be broken. Instead of letting that brokeness linger, rename the member, to force old and out-of-tree code to break at compile time instead of at runtime. No intended functional changes in this commit. Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- include/linux/blk-cgroup.h | 4 ++-- include/linux/blk_types.h | 15 ++++++++------- 3 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e09a8895fc31..59ffaa68b11b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -95,7 +95,7 @@ static inline bool bio_is_rw(struct bio *bio) static inline bool bio_mergeable(struct bio *bio) { - if (bio->bi_rw & REQ_NOMERGE_FLAGS) + if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; @@ -318,7 +318,7 @@ struct bio_integrity_payload { static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { - if (bio->bi_rw & REQ_INTEGRITY) + if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f77150a4a96a..10648e300c93 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -714,9 +714,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_rw, + blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_rw, 1); + blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1); } rcu_read_unlock(); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb264924..436f43f87da9 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -27,8 +27,9 @@ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; int bi_error; - unsigned int bi_rw; /* bottom bits req flags, - * top bits REQ_OP + unsigned int bi_opf; /* bottom bits req flags, + * top bits REQ_OP. Use + * accessors. */ unsigned short bi_flags; /* status, command, etc */ unsigned short bi_ioprio; @@ -89,13 +90,13 @@ struct bio { }; #define BIO_OP_SHIFT (8 * sizeof(unsigned int) - REQ_OP_BITS) -#define bio_op(bio) ((bio)->bi_rw >> BIO_OP_SHIFT) +#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) #define bio_set_op_attrs(bio, op, op_flags) do { \ WARN_ON(op >= (1 << REQ_OP_BITS)); \ - (bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1); \ - (bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT); \ - (bio)->bi_rw |= op_flags; \ + (bio)->bi_opf &= ((1 << BIO_OP_SHIFT) - 1); \ + (bio)->bi_opf |= ((unsigned int) (op) << BIO_OP_SHIFT); \ + (bio)->bi_opf |= op_flags; \ } while (0) #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) @@ -138,7 +139,7 @@ struct bio { /* * Request flags. For use in the cmd_flags field of struct request, and in - * bi_rw of struct bio. Note that some flags are only valid in either one. + * bi_opf of struct bio. Note that some flags are only valid in either one. */ enum rq_flag_bits { /* common flags */ -- cgit v1.2.3 From 1bd4403d86a1c06cb6cc9ac87664a0c9d3413d51 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 8 Aug 2016 13:02:01 -0700 Subject: unsafe_[get|put]_user: change interface to use a error target label When I initially added the unsafe_[get|put]_user() helpers in commit 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses"), I made the mistake of modeling the interface on our traditional __[get|put]_user() functions, which return zero on success, or -EFAULT on failure. That interface is fairly easy to use, but it's actually fairly nasty for good code generation, since it essentially forces the caller to check the error value for each access. In particular, since the error handling is already internally implemented with an exception handler, and we already use "asm goto" for various other things, we could fairly easily make the error cases just jump directly to an error label instead, and avoid the need for explicit checking after each operation. So switch the interface to pass in an error label, rather than checking the error value in the caller. Best do it now before we start growing more users (the signal handling code in particular would be a good place to use the new interface). So rather than if (unsafe_get_user(x, ptr)) ... handle error .. the interface is now unsafe_get_user(x, ptr, label); where an error during the user mode fetch will now just cause a jump to 'label' in the caller. Right now the actual _implementation_ of this all still ends up being a "if (err) goto label", and does not take advantage of any exception label tricks, but for "unsafe_put_user()" in particular it should be fairly straightforward to convert to using the exception table model. Note that "unsafe_get_user()" is much harder to convert to a clever exception table model, because current versions of gcc do not allow the use of "asm goto" (for the exception) with output values (for the actual value to be fetched). But that is hopefully not a limitation in the long term. [ Also note that it might be a good idea to switch unsafe_get_user() to actually _return_ the value it fetches from user space, but this commit only changes the error handling semantics ] Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 349557825428..f30c187ed785 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -114,8 +114,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin() do { } while (0) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr) __get_user(x, ptr) -#define unsafe_put_user(x, ptr) __put_user(x, ptr) +#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) +#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) #endif #endif /* __LINUX_UACCESS_H__ */ -- cgit v1.2.3 From 59bcb7972fc5d53a621ee6b2c3cf1654cebb3dc5 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Mon, 8 Aug 2016 21:57:42 -0400 Subject: qed: Add dcbx app support for IEEE Selection Field. MFW now supports the Selection field for IEEE mode. Add driver changes to use the newer MFW masks to read/write the port-id value. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b1e3c57c7117..d6c4177df7cb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -70,8 +70,16 @@ struct qed_dbcx_pfc_params { u8 max_tc; }; +enum qed_dcbx_sf_ieee_type { + QED_DCBX_SF_IEEE_ETHTYPE, + QED_DCBX_SF_IEEE_TCP_PORT, + QED_DCBX_SF_IEEE_UDP_PORT, + QED_DCBX_SF_IEEE_TCP_UDP_PORT +}; + struct qed_app_entry { bool ethtype; + enum qed_dcbx_sf_ieee_type sf_ieee; bool enabled; u8 prio; u16 proto_id; -- cgit v1.2.3 From f3b0946d629c8bfbd3e5f038e30cb9c711a35f10 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Jul 2016 17:18:33 +0100 Subject: genirq/msi: Make sure PCI MSIs are activated early Bharat Kumar Gogada reported issues with the generic MSI code, where the end-point ended up with garbage in its MSI configuration (both for the vector and the message). It turns out that the two MSI paths in the kernel are doing slightly different things: generic MSI: disable MSI -> allocate MSI -> enable MSI -> setup EP PCI MSI: disable MSI -> allocate MSI -> setup EP -> enable MSI And it turns out that end-points are allowed to latch the content of the MSI configuration registers as soon as MSIs are enabled. In Bharat's case, the end-point ends up using whatever was there already, which is not what you want. In order to make things converge, we introduce a new MSI domain flag (MSI_FLAG_ACTIVATE_EARLY) that is unconditionally set for PCI/MSI. When set, this flag forces the programming of the end-point as soon as the MSIs are allocated. A consequence of this is that we have an extra activate in irq_startup, but that should be without much consequence. tglx: - Several people reported a VMWare regression with PCI/MSI-X passthrough. It turns out that the patch also cures that issue. - We need to have a look at the MSI disable interrupt path, where we write the msg to all zeros without disabling MSI in the PCI device. Is that correct? Fixes: 52f518a3a7c2 "x86/MSI: Use hierarchical irqdomains to manage MSI interrupts" Reported-and-tested-by: Bharat Kumar Gogada Reported-and-tested-by: Foster Snowhill Reported-by: Matthias Prager Reported-by: Jason Taylor Signed-off-by: Marc Zyngier Acked-by: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1468426713-31431-1-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 4f0bfe5912b2..e8c81fbd5f9c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -270,6 +270,8 @@ enum { MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ MSI_FLAG_PCI_MSIX = (1 << 3), + /* Needs early activate, required for PCI */ + MSI_FLAG_ACTIVATE_EARLY = (1 << 4), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, -- cgit v1.2.3 From a0cba2179ea4c1820fce2ee046b6ed90ecc56196 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 Aug 2016 10:48:18 -0700 Subject: Revert "printk: create pr_ functions" This reverts commit 874f9c7da9a4acbc1b9e12ca722579fb50e4d142. Geert Uytterhoeven reports: "This change seems to have an (unintendent?) side-effect. Before, pr_*() calls without a trailing newline characters would be printed with a newline character appended, both on the console and in the output of the dmesg command. After this commit, no new line character is appended, and the output of the next pr_*() call of the same type may be appended, like in: - Truncating RAM at 0x0000000040000000-0x00000000c0000000 to -0x0000000070000000 - Ignoring RAM at 0x0000000200000000-0x0000000240000000 (!CONFIG_HIGHMEM) + Truncating RAM at 0x0000000040000000-0x00000000c0000000 to -0x0000000070000000Ignoring RAM at 0x0000000200000000-0x0000000240000000 (!CONFIG_HIGHMEM)" Joe Perches says: "No, that is not intentional. The newline handling code inside vprintk_emit is a bit involved and for now I suggest a revert until this has all the same behavior as earlier" Reported-by: Geert Uytterhoeven Requested-by: Joe Perches Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 48 +++++++++++++++--------------------------------- 1 file changed, 15 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 8dc155dab3ed..696a56be7d3e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -266,39 +266,21 @@ extern asmlinkage void dump_stack(void) __cold; * and other debug macros are compiled out unless either DEBUG is defined * or CONFIG_DYNAMIC_DEBUG is set. */ - -#ifdef CONFIG_PRINTK - -asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...); - -#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__) - -#else - -#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) - -#endif - -#define pr_warning pr_warn - +#define pr_emerg(fmt, ...) \ + printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert(fmt, ...) \ + printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit(fmt, ...) \ + printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) \ + printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn pr_warning +#define pr_notice(fmt, ...) \ + printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* * Like KERN_CONT, pr_cont() should only be used when continuing * a line with no newline ('\n') enclosed. Otherwise it defaults -- cgit v1.2.3 From db4a835601b73cf8d6cd8986381d966b8e13d2d9 Mon Sep 17 00:00:00 2001 From: David Carrillo-Cisneros Date: Tue, 2 Aug 2016 00:48:12 -0700 Subject: perf/core: Set cgroup in CPU contexts for new cgroup events There's a perf stat bug easy to observer on a machine with only one cgroup: $ perf stat -e cycles -I 1000 -C 0 -G / # time counts unit events 1.000161699 cycles / 2.000355591 cycles / 3.000565154 cycles / 4.000951350 cycles / We'd expect some output there. The underlying problem is that there is an optimization in perf_cgroup_sched_{in,out}() that skips the switch of cgroup events if the old and new cgroups in a task switch are the same. This optimization interacts with the current code in two ways that cause a CPU context's cgroup (cpuctx->cgrp) to be NULL even if a cgroup event matches the current task. These are: 1. On creation of the first cgroup event in a CPU: In current code, cpuctx->cpu is only set in perf_cgroup_sched_in, but due to the aforesaid optimization, perf_cgroup_sched_in will run until the next cgroup switches in that CPU. This may happen late or never happen, depending on system's number of cgroups, CPU load, etc. 2. On deletion of the last cgroup event in a cpuctx: In list_del_event, cpuctx->cgrp is set NULL. Any new cgroup event will not be sched in because cpuctx->cgrp == NULL until a cgroup switch occurs and perf_cgroup_sched_in is executed (updating cpuctx->cgrp). This patch fixes both problems by setting cpuctx->cgrp in list_add_event, mirroring what list_del_event does when removing a cgroup event from CPU context, as introduced in: commit 68cacd29167b ("perf_events: Fix stale ->cgrp pointer in update_cgrp_time_from_cpuctx()") With this patch, cpuctx->cgrp is always set/clear when installing/removing the first/last cgroup event in/from the CPU context. With cpuctx->cgrp correctly set, event_filter_match works as intended when events are sched in/out. After the fix, the output is as expected: $ perf stat -e cycles -I 1000 -a -G / # time counts unit events 1.004699159 627342882 cycles / 2.007397156 615272690 cycles / 3.010019057 616726074 cycles / Signed-off-by: David Carrillo-Cisneros Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Kan Liang Cc: Linus Torvalds Cc: Paul Turner Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vegard Nossum Cc: Vince Weaver Link: http://lkml.kernel.org/r/1470124092-113192-1-git-send-email-davidcc@google.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8ed4326164cc..2b6b43cc0dd5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,7 +743,9 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; +#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ +#endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; @@ -769,7 +771,9 @@ struct perf_cpu_context { unsigned int hrtimer_active; struct pmu *unique_pmu; +#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { -- cgit v1.2.3 From 1ea049b2de5d803374fdbf43add23c8d1c518e7b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 11 Aug 2016 10:15:56 +0200 Subject: bvec: avoid variable shadowing warning Due to the (indirect) nesting of min(..., min(...)), sparse will show a variable shadowing warning whenever bvec.h is included. Avoid that by assigning the inner min() to a temporary variable first. Signed-off-by: Johannes Berg Signed-off-by: Jens Axboe --- include/linux/bvec.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 701b64a3b7c5..89b65b82d98f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -74,7 +74,8 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, "Attempted to advance past end of bvec iter\n"); while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + unsigned iter_len = bvec_iter_len(bv, *iter); + unsigned len = min(bytes, iter_len); bytes -= len; iter->bi_size -= len; -- cgit v1.2.3 From 023e9fddc3616b005c3753fc1bb6526388cd7a30 Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 9 Aug 2016 19:13:00 +0200 Subject: KVM: PPC: Move xics_debugfs_init out of create MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As we are about to hold the kvm->lock during the create operation on KVM devices, we should move the call to xics_debugfs_init into its own function, since holding a mutex over extended amounts of time might not be a good idea. Introduce an init operation on the kvm_device_ops struct which cannot fail and call this, if configured, after the device has been created. Signed-off-by: Christoffer Dall Reviewed-by: Paolo Bonzini Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01e908ac4a39..d3c9b82812c3 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1115,6 +1115,12 @@ struct kvm_device_ops { const char *name; int (*create)(struct kvm_device *dev, u32 type); + /* + * init is called after create if create is successful and is called + * outside of holding kvm->lock. + */ + void (*init)(struct kvm_device *dev); + /* * Destroy is responsible for freeing dev. * -- cgit v1.2.3 From a28ebea2adc4a2bef5989a5a181ec238f59fbcad Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 9 Aug 2016 19:13:01 +0200 Subject: KVM: Protect device ops->create and list_add with kvm->lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM devices were manipulating list data structures without any form of synchronization, and some implementations of the create operations also suffered from a lack of synchronization. Now when we've split the xics create operation into create and init, we can hold the kvm->lock mutex while calling the create operation and when manipulating the devices list. The error path in the generic code gets slightly ugly because we have to take the mutex again and delete the device from the list, but holding the mutex during anon_inode_getfd or releasing/locking the mutex in the common non-error path seemed wrong. Signed-off-by: Christoffer Dall Reviewed-by: Paolo Bonzini Acked-by: Christian Borntraeger Signed-off-by: Radim Krčmář --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d3c9b82812c3..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,6 +1113,12 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); /* -- cgit v1.2.3 From 952fcfd08c8109951622579d0ae7b9cd6cafd688 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 12 Aug 2016 16:10:33 +0200 Subject: net: remove type_check from dev_get_nest_level() The idea for type_check in dev_get_nest_level() was to count the number of nested devices of the same type (currently, only macvlan or vlan devices). This prevented the false positive lockdep warning on configurations such as: eth0 <--- macvlan0 <--- vlan0 <--- macvlan1 However, this doesn't prevent a warning on a configuration such as: eth0 <--- macvlan0 <--- vlan0 eth1 <--- vlan1 <--- macvlan1 In this case, all the locks end up with a nesting subclass of 1, so lockdep thinks that there is still a deadlock: - in the first case we have (macvlan_netdev_addr_lock_key, 1) and then take (vlan_netdev_xmit_lock_key, 1) - in the second case, we have (vlan_netdev_xmit_lock_key, 1) and then take (macvlan_netdev_addr_lock_key, 1) By removing the linktype check in dev_get_nest_level() and always incrementing the nesting depth, lockdep considers this configuration valid. Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 076df5360ba5..3a788bf0affd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3891,8 +3891,7 @@ void netdev_default_l2upper_neigh_destroy(struct net_device *dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)); +int dev_get_nest_level(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); -- cgit v1.2.3